Medical Cost Insurance.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19</td>\n",
       "      <td>female</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "      <td>southwest</td>\n",
       "      <td>16884.92400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>male</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>1725.55230</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>male</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>southeast</td>\n",
       "      <td>4449.46200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>male</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>21984.47061</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>male</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "      <td>northwest</td>\n",
       "      <td>3866.85520</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age     sex     bmi  children smoker     region      charges\n",
       "0   19  female  27.900         0    yes  southwest  16884.92400\n",
       "1   18    male  33.770         1     no  southeast   1725.55230\n",
       "2   28    male  33.000         3     no  southeast   4449.46200\n",
       "3   33    male  22.705         0     no  northwest  21984.47061\n",
       "4   32    male  28.880         0     no  northwest   3866.85520"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv('./insurance.csv')\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1338 entries, 0 to 1337\n",
      "Data columns (total 7 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   age       1338 non-null   int64  \n",
      " 1   sex       1338 non-null   object \n",
      " 2   bmi       1338 non-null   float64\n",
      " 3   children  1338 non-null   int64  \n",
      " 4   smoker    1338 non-null   object \n",
      " 5   region    1338 non-null   object \n",
      " 6   charges   1338 non-null   float64\n",
      "dtypes: float64(2), int64(2), object(3)\n",
      "memory usage: 73.3+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### There are no missing values as such"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "northeast    324\n",
       "northwest    325\n",
       "southwest    325\n",
       "southeast    364\n",
       "Name: region, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['region'].value_counts().sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5     18\n",
       "4     25\n",
       "3    157\n",
       "2    240\n",
       "1    324\n",
       "0    574\n",
       "Name: children, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['children'].value_counts().sort_values()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Converting Categorical Features to Numerical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "clean_data = {'sex': {'male' : 0 , 'female' : 1} ,\n",
    "                 'smoker': {'no': 0 , 'yes' : 1},\n",
    "                   'region' : {'northwest':0, 'northeast':1,'southeast':2,'southwest':3}\n",
    "               }\n",
    "data_copy = data.copy()\n",
    "data_copy.replace(clean_data, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1338.000000</td>\n",
       "      <td>1338.000000</td>\n",
       "      <td>1338.000000</td>\n",
       "      <td>1338.000000</td>\n",
       "      <td>1338.000000</td>\n",
       "      <td>1338.000000</td>\n",
       "      <td>1338.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>39.207025</td>\n",
       "      <td>0.494768</td>\n",
       "      <td>30.663397</td>\n",
       "      <td>1.094918</td>\n",
       "      <td>0.204783</td>\n",
       "      <td>1.514948</td>\n",
       "      <td>13270.422265</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>14.049960</td>\n",
       "      <td>0.500160</td>\n",
       "      <td>6.098187</td>\n",
       "      <td>1.205493</td>\n",
       "      <td>0.403694</td>\n",
       "      <td>1.105572</td>\n",
       "      <td>12110.011237</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>18.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>15.960000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1121.873900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>27.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>26.296250</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>4740.287150</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>39.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>30.400000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>9382.033000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>51.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>34.693750</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>16639.912515</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>64.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>53.130000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>63770.428010</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               age          sex          bmi     children       smoker  \\\n",
       "count  1338.000000  1338.000000  1338.000000  1338.000000  1338.000000   \n",
       "mean     39.207025     0.494768    30.663397     1.094918     0.204783   \n",
       "std      14.049960     0.500160     6.098187     1.205493     0.403694   \n",
       "min      18.000000     0.000000    15.960000     0.000000     0.000000   \n",
       "25%      27.000000     0.000000    26.296250     0.000000     0.000000   \n",
       "50%      39.000000     0.000000    30.400000     1.000000     0.000000   \n",
       "75%      51.000000     1.000000    34.693750     2.000000     0.000000   \n",
       "max      64.000000     1.000000    53.130000     5.000000     1.000000   \n",
       "\n",
       "            region       charges  \n",
       "count  1338.000000   1338.000000  \n",
       "mean      1.514948  13270.422265  \n",
       "std       1.105572  12110.011237  \n",
       "min       0.000000   1121.873900  \n",
       "25%       1.000000   4740.287150  \n",
       "50%       2.000000   9382.033000  \n",
       "75%       2.000000  16639.912515  \n",
       "max       3.000000  63770.428010  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_copy.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "corr = data_copy.corr()\n",
    "fig, ax = plt.subplots(figsize=(10,8))\n",
    "sns.heatmap(corr,cmap='BuPu',annot=True,fmt=\".2f\",ax=ax)\n",
    "plt.title(\"Dependencies of Medical Charges\")\n",
    "plt.savefig('./sampleImages/Cor')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Smoker, BMI and Age are most important factor that determnines - Charges\n",
    "Also we see that Sex, Children and Region do not affect the Charges.\n",
    "We might drop these 3 columns as they have less correlation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "female    662\n",
      "male      676\n",
      "Name: sex, dtype: int64\n",
      "yes     274\n",
      "no     1064\n",
      "Name: smoker, dtype: int64\n",
      "northeast    324\n",
      "northwest    325\n",
      "southwest    325\n",
      "southeast    364\n",
      "Name: region, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(data['sex'].value_counts().sort_values()) \n",
    "print(data['smoker'].value_counts().sort_values())\n",
    "print(data['region'].value_counts().sort_values())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Now we are confirmed that there are no other values in above pre-preocessed column, We can proceed with EDA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAuAAAAImCAYAAAASbz+gAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3de7xtZV0v/s8XUQS2IMjWjYDiSUzRlJKIsgsGKmqK5iU6JWj2Iz2aZpcV1qnIoqO7k5aVnmOpoCdTslQyLfHW7Si67UcomklJuhcsQW57q4lufM4fc2xct3nZe6815lprv9+v13yNOZ8xvvN5xtzfPdZ3jfWMMau1FgAAoB8HTHsAAACwP1GAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAArJiqalV1/2mPA2AtU4ADTFlVfbCqbq6qg6Y9lnGq6uiqem1VXVdVO6vqX6rq16vq0GmPDWC9UIADTFFVHZ/k+5K0JE+c6mDGqKojk3woycFJvru1drckj0py9yTfssJ9HbiS7wewlijAAabrnCQfTnJRknPnr6iqe1TVX1bVjqr6aFX9ZlX9w7z1D6yqy6rqpqr6dFU9fbkOqursqtq2qO1FVXVp9/xxVfXJ7oz2bFX9/JCx/mySnUl+vLV2TZK01j7fWntha+3KedudUVWf6c7q/2FVVdfPt1TV+6vqxqr6YlX9SVXdfd6YrqmqX6yqK5N8uaoOrKpzquo/uphf6bY5o9v+gKo6v6r+rVt/SfdLAsCapgAHmK5zkvxJ93hMVd1r3ro/TPLlJFsyKM7vKNC7KR+XJXlTknsm+dEkr6qqBy/Tx6VJvrWqTpjX9l+72CR5bZKf6s5oPyTJ+4eM9Ywkf9Fa+8aYffqhJN+Z5GFJnp7kMbuHneR/JLl3kgclOS7JBYtifzTJ4zM4q/6AJK9K8mNJjk5yeJJj5m37giRPSvID3XvenMFnBrCmKcABpqSqvjfJfZNc0lr7WJJ/y6AwTlXdKclTkvxaa+0rrbVPJrl4XvgPJbmmtfb61tqu1to/JfnzJE9d3E9r7StJ3pFBcZuuEH9gBoV5knw9yYlVdVhr7ebuvZZzjyTXTbBrL22t3dJa+1ySDyQ5qRvH1a21y1prt7XWbkjy8gyK5/le2Z1V/89uX/6ytfYPrbWvJfnVDKbq7PZTSX65tba9tXZbBsX8U01fAdY6BTjA9Jyb5D2ttS92r9+Ub57l3pzkwCSfn7f9/Of3TfJdVXXL7kcGZ4q3DOnrTekK8AyK/Ld3hXkyKPQfl+Q/qupvq+q7h7zHjRmciR5nbt7zryTZlCRVdc+qenM3zWVHkv+T5KhFsfP38d7zX3fjvXHe+vsmedu8/f9UktuTzP8rAsCaowAHmIKqOjiD6Rk/UFVzVTWX5EVJHlZVD0tyQ5JdSY6dF3bcvOefT/K3rbW7z3tsaq09d0iX70lyVFWdlEEhvnv6SVprH22tnZXBVJa3J7lkyHu8N8mTq2pvf3b8jwzOYD+0tXZYkh/PYFrKfPPPcF+XefvffWb3mLf+80keu+gzuGtrbXYvxwfQCwU4wHQ8KYOztSdmMEXjpAzmRf99knNaa7cn+YskF1TVIVX1wAzmi+/2ziQPqKpnVNWdu8d3VtWDluustbYryVuT/HaSIzOYP56quktV/VhVHd5a+3qSHd24lvPyJIclubiq7tvFH1NVL6+qh06wz3dL8qUkt1TVMUl+Ycz2b03yhKr6nqq6S5Jfz8KC/X8luXDeWDZX1VkTjANgqhTgANNxbpLXt9Y+11qb2/1I8gdJfqybx/z8DC48nEvyxiR/muS2JGmt7Uzy6CRnJ7m22+ZlSUbdS/xNGVxI+WddQb7bM5Jc000LeU4GZ6aXaK3dlOR7MpgzfnlV7UzyviS3Jrl6gn3+9STf0W3/Vxn8gjFUa+2qJD+d5M0ZnA3fmeT6dJ9Bkt/LYB77e7qxfDjJd00wDoCpqtba+K0AmLqqelmSLa21c8duvAFV1aYktyQ5obX22WmPB2BvOQMOsEZ19/l+aA2ckuTZSd427XH1qaqe0E3BOTTJ/0zy8STXTHdUAPtGAQ6wdt0tg2kaX87gwsjfyeB2gvuTszKYYnNtkhOSnN386RZY50xBAQCAHjkDDgAAPVKAAwBAj/a7r+s96qij2vHHHz/tYQAAsMF97GMf+2JrbfPi9v2uAD/++OOzbdu2aQ8DAIANrqr+Y7l2U1AAAKBHCnAAAOiRAhwAAHqkAAcAgB4pwAEAoEcKcAAA6NGqFeBVddeq+khV/XNVXVVVv961H1lVl1XVZ7rlEfNiXlxVV1fVp6vqMfPaH15VH+/WvbKqqms/qKre0rVfXlXHr9b+AADASljNM+C3JfnB1trDkpyU5MyqOjXJ+Une11o7Icn7utepqhOTnJ3kwUnOTPKqqrpT916vTnJekhO6x5ld+7OT3Nxau3+SVyR52SruDwAA7LNVK8DbwJe6l3fuHi3JWUku7tovTvKk7vlZSd7cWruttfbZJFcnOaWqjk5yWGvtQ621luQNi2J2v9dbk5y+++w4AACsRas6B7yq7lRVVyS5PsllrbXLk9yrtXZdknTLe3abH5Pk8/PCt3dtx3TPF7cviGmt7Upya5J7LDOO86pqW1Vtu+GGG1Zq9wAAYI+tagHeWru9tXZSkmMzOJv9kBGbL3fmuo1oHxWzeByvaa2d3Fo7efPmzeOGDQAAq6aXu6C01m5J8sEM5m5/oZtWkm55fbfZ9iTHzQs7Nsm1Xfuxy7QviKmqA5McnuSmVdkJAABYAat5F5TNVXX37vnBSc5I8i9JLk1ybrfZuUne0T2/NMnZ3Z1N7pfBxZYf6aap7KyqU7v53ecsitn9Xk9N8v5unjgAAKxJB67iex+d5OLuTiYHJLmktfbOqvpQkkuq6tlJPpfkaUnSWruqqi5J8skku5I8r7V2e/dez01yUZKDk7y7eyTJa5O8saquzuDM99mruD8AALDPan87YXzyySe3bdu2TXsYAABscFX1sdbayYvbfRMmAAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRoNW9DCAAAG9bMzEzm5uayZcuWbN26deI4BTgAAOyFubm5zM7O7nGcKSgAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9OjAaQ8AAICNZ2ZmJnNzc9myZUu2bt067eGsKQpwAABW3NzcXGZnZ6c9jDXJFBQAAOiRAhwAAHqkAAcAgB4pwAEAoEcKcAAA6JECHAAAeqQABwCAHinAAQCgRwpwAADokW/CBABgzdgfvsJeAQ4AwJqxP3yFvSkoAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD06cNoDAACAaZmZmcnc3Fy2bNmSrVu39tLnqp0Br6rjquoDVfWpqrqqql7YtV9QVbNVdUX3eNy8mBdX1dVV9emqesy89odX1ce7da+squraD6qqt3Ttl1fV8au1PwAAbDxzc3OZnZ3N3Nxcb32u5hSUXUl+rrX2oCSnJnleVZ3YrXtFa+2k7vGuJOnWnZ3kwUnOTPKqqrpTt/2rk5yX5ITucWbX/uwkN7fW7p/kFUletor7AwAA+2zVCvDW2nWttX/qnu9M8qkkx4wIOSvJm1trt7XWPpvk6iSnVNXRSQ5rrX2otdaSvCHJk+bFXNw9f2uS03efHQcAgLWol4swu6kh357k8q7p+VV1ZVW9rqqO6NqOSfL5eWHbu7ZjuueL2xfEtNZ2Jbk1yT1WYRcAAGBFrHoBXlWbkvx5kp9pre3IYDrJtyQ5Kcl1SX5n96bLhLcR7aNiFo/hvKraVlXbbrjhhj3cAwAAWDmrWoBX1Z0zKL7/pLX2F0nSWvtCa+321to3kvxRklO6zbcnOW5e+LFJru3aj12mfUFMVR2Y5PAkNy0eR2vtNa21k1trJ2/evHmldg8AAPbYat4FpZK8NsmnWmsvn9d+9LzNnpzkE93zS5Oc3d3Z5H4ZXGz5kdbadUl2VtWp3Xuek+Qd82LO7Z4/Ncn7u3niAACwJq3mfcAfkeQZST5eVVd0bb+U5Eer6qQMpopck+SnkqS1dlVVXZLkkxncQeV5rbXbu7jnJrkoycFJ3t09kkGB/8aqujqDM99nr+L+AADAPlu1Ary19g9Zfo72u0bEXJjkwmXatyV5yDLtX03ytH0YJgAA9MpX0QMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0aDW/iAdgw5uZmcnc3Fy2bNmSrVu3Tns4G4LPFNjoFOAA+2Bubi6zs7PTHsaG4jOlb37po28KcABgv+aXvo1hPf0ipQAHAGDdW0+/SLkIEwAAeqQABwCAHinAAQCgRwpwAADokQIcAAB6pAAHAIAeKcABAKBHCnAAAOiRL+IBAGBZ6+nbJdcTBTgAAMtaT98uuZ6YggIAAD1yBhwAAMa49oKLl7TdftOOO5bz19/7gnNHvpcz4AAA0CMFOAAA9EgBDgAAPVKAAwBAj1yECQCsKe49zUanAAcA1hT3nmajMwUFAAB6pAAHAIAeKcABAKBHCnAAAOiRAhwAAHqkAAcAgB4pwAEAoEcKcAAA6JECHAAAeqQABwCAHinAAQCgRwpwAADokQIcAAB6dOC0BwAA+5uZmZnMzc1ly5Yt2bp167SHA1Mz+0sfWNK268b/vGO5eP0xv/XIXsa12hTgANCzubm5zM7OTnsYsGK2n3/5krZdX/zqHcv564996Xf1Nq61yhQUAADokQIcAAB6pAAHAIAeKcABAKBHCnAAAOiRAhwAAHqkAAcAgB4pwAEAoEcKcAAA6JFvwgRgw/AV78B6oAAHYMPwFe/AemAKCgAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPTIN2ECAKwTMzMzmZuby5YtW7J169ZpD4e9pAAHAFgn5ubmMjs7O+1hsI9MQQEAgB45Aw4ArDhTJWA4BTgA+z3F4sozVQKGU4ADsN9TLG4MfpFivVCAAwAbgl+kWC9W7SLMqjquqj5QVZ+qqquq6oVd+5FVdVlVfaZbHjEv5sVVdXVVfbqqHjOv/eFV9fFu3Surqrr2g6rqLV375VV1/GrtDwAArITVvAvKriQ/11p7UJJTkzyvqk5Mcn6S97XWTkjyvu51unVnJ3lwkjOTvKqq7tS916uTnJfkhO5xZtf+7CQ3t9bun+QVSV62ivsDAAD7bNUK8Nbada21f+qe70zyqSTHJDkrycXdZhcneVL3/Kwkb26t3dZa+2ySq5OcUlVHJzmstfah1lpL8oZFMbvf661JTt99dhwAYDXNzMzknHPOyczMzLSHwjrTyxzwbmrItye5PMm9WmvXJYMivaru2W12TJIPzwvb3rV9vXu+uH13zOe799pVVbcmuUeSLy7q/7wMzqDnPve5z0rtFgBseC5sHM6cc/bWqn8RT1VtSvLnSX6mtbZj1KbLtLUR7aNiFja09prW2smttZM3b948bsgAQGd3kTk3NzftocCGsapnwKvqzhkU33/SWvuLrvkLVXV0d/b76CTXd+3bkxw3L/zYJNd27ccu0z4/ZntVHZjk8CQ3rcrOAACw7l37q29d8Pr2G790x3Lxunu/5KmrMobVvAtKJXltkk+11l4+b9WlSc7tnp+b5B3z2s/u7mxyvwwutvxIN11lZ1Wd2r3nOYtidr/XU5O8v5snDgAAa9JqngF/RJJnJPl4VV3Rtf1SkpcmuaSqnp3kc0meliSttauq6pIkn8zgDirPa63d3sU9N8lFSQ5O8u7ukQwK/DdW1dUZnPk+exX3BwAA9tmqFeCttX/I8nO0k+T0ITEXJrlwmfZtSR6yTPtX0xXwAACwHqz6RZgAAMA3KcABAKBHCnAAAOhRL1/EAwAbkS+pAfaGAhwA9pJvQgT2hikoAADQI2fAAZiqR7/uogWvb9+xI0kyu2PHknXv+Yln9jMogFXkDDgAAPTIGXAAANaV2f/+V0vadt345TuWi9cf85uP72Vck3IGHAAAeqQABwCAHinAAQCgR+aAAwCQJPn8z398wetdX/zaHcvF6477n9/W27g2GmfAAQCgR86AAwD7jb961dySti/fevsdy8XrH//ftvQyLvYvCnAAgJ7NzMxkbm4uW7ZsydatW6c9HHqmAAcA6Nnc3FxmZ2enPQymxBxwAADokTPgALCOmLoA658CHADWEVMXYO046qBNC5aTUoADAMBe+MVve9RexZkDDgAAPXIGHACYmv990dL7ct+64/Y7lvPX/9Qz3ZObjcEZcAAA6JECHAAAeqQABwCAHpkDDjChMy7+5SVtbceNSZLZHTcuWf/ecy/sZVwArC/OgAMAQI+cAWcs37oGALByFOCM5VvX2Ft+eQOApRTgwKrxyxsALGUOOAAA9MgZcFhnTOuA9eeHLrpsweuv7vhKkuTaHV9Zsu6dz3xUb+MCpkMBDuuMaR0AsL4pwAEAWDM23+XwBcuNSAEOAMCaMfOgH5v2EFadizABAKBHzoADAGxwLuBfWxTgAAAbnAv41xZTUAAAoEfOgAPEn2cB6I8CHCD+PAtAf0xBAQCAHjkDDsCqMK0HYHkKcABWhWk9AMszBQUAAHqkAAcAgB6ZggIxVxUA6I8CHGKuKgDQHwU4AAAr7qiDjliw5JsU4MCaY0oQwPo3860/Me0hrFl7XIBX1RFJjmutXbkK4wEwJQggyb/88vYlbV+/cdcdy8XrH3jhsb2Mi3030V1QquqDVXVYVR2Z5J+TvL6qXr66QwMAgI1n0tsQHt5a25Hkh5O8vrX28CRnrN6wAABgY5q0AD+wqo5O8vQk71zF8QAAwIY26RzwlyT5myT/2Fr7aFX9lySfWb1hAQCsLX/7iusWvP7PW26/Y7l43Q+86OjexsX6M1EB3lr7syR/Nu/1vyd5ymoNCgAANqqJCvCqekCSVye5V2vtIVX10CRPbK395qqODmAPuH0hAOvBpFNQ/ijJLyT530nSWruyqt6URAEOrBluXwj7j7f88ReWtH1px+13LBev/5GfvFcv44JJTHoR5iGttY8satu10oMBAICNbtIz4F+sqm9J0pKkqp6a5LrRIQCwes58/ZuWtH19x84kyeyOnQvW//Wz/mtv4wIYZ9IC/HlJXpPkgVU1m+SzSX581UYFAAAb1KR3Qfn3JGdU1aFJDmit7VzdYQEAK8lFyrB2THoXlJ9d9DpJbk3ysdbaFaswLgBgBU1ykfJPXHzNkrYv7Nh1x3Lx+tede/wdz3/j4oXvfVMXd9OOXUvW/cq5x0w4atiYJp2CcnL3+Mvu9eOTfDTJc6rqz1prfpUGWOOcAQVYGyYtwO+R5Dtaa19Kkqr6tSRvTfL9ST6WxJEcYI1zm0aAtWHSAvw+Sb427/XXk9y3tfafVXXbyg8LAABW31F3vduCZR8mLcDflOTDVfWO7vUTkvxpd1HmJ1dlZMCKMv1gY/DvCLC8zQcdvmA5qV988BNWYzgjjS3Aa3DF5UVJ3pXke5NUkue01rZ1m/zYqo0OWDGmH2wM/h0Bljdz4lOmPYSJjS3AW2utqt7eWnt4BvO9WaecOQMAmL5Jp6B8uKq+s7X20VUdDatqGmfOFP0AAAsdMOF2j0zyoar6t6q6sqo+XlVXjgqoqtdV1fVV9Yl5bRdU1WxVXdE9Hjdv3Yur6uqq+nRVPWZe+8O7/q6uqld2U2JSVQdV1Vu69sur6vg92XH6sbvon5ubm/ZQAADWhEnPgD92L977oiR/kOQNi9pf0Vr7n/MbqurEJGcneXCSeyd5b1U9oLV2e5JXJzkvyYczmId+ZpJ3J3l2kptba/evqrOTvCzJj+zFOAEAoDcTnQFvrf1Ha+0/kvxnkjbvMSrm75LcNOE4zkry5tbaba21zya5OskpVXV0ksNaax9qrbUMivknzYu5uHv+1iSn7z47DuvBzMxMzjnnnMzMzEx7KABAjyb9KvonJvmdDM5OX5/kvkk+lcEZ6z31/Ko6J8m2JD/XWrs5yTEZnOHebXvX9vXu+eL2dMvPJ0lrbVdV3ZrBFwZ9cZnxn5fBWfTc5z732Yshw8pzNwuA/cO231p6rL/tpl13LOevP/mXjlmyLRvPpHPAfyPJqUn+tbV2vySnJ/nHvejv1Um+JclJSa7LoKhPBrc2XKyNaB8Vs7Sxtde01k5urZ28efPmPRsxAMB+6qi7HJl7HbQ5R93lyGkPZUOZdA7411trN1bVAVV1QGvtA1X1sj3trLX2hd3Pq+qPkryze7k9yXHzNj02ybVd+7HLtM+P2V5VByY5PJNPeVkT3CEEAFjLfuH+z532EDakSQvwW6pqU5K/S/InVXV9kl172llVHd1au657+eQku++QcmmSN1XVyzOY5nJCko+01m6vqp1VdWqSy5Ock+T358Wcm+RDSZ6a5P3dPPF1wxQEgP499vVvXdL2tR1fSpLM7vjSkvXvftZTexkXsP+YtAA/K8lXk7wog2++PDzJS0YFVNWfJjktyVFVtT3JryU5rapOymCqyDVJfipJWmtXVdUlGXyt/a4kz+vugJIkz83gjioHZ3D3k3d37a9N8saqujqDM99nT7gvAAAwNRMV4K21L897efHQDRfG/Ogyza8dsf2FSS5cpn1bkocs0/7VJE+bZCwAALBWTHoXlB/O4D7b98zg4sfK4FvqD1vFsQGwPzp008LlfuyJFy2938FXdnw1SXLtjq8uWH/pMx/R27iAfTPpFJStSZ7QWvvUag4GAO50+hnTHgLAqpq0AP+C4ps+uUMMALBRjSzAu6knSbKtqt6S5O1Jbtu9vrX2F6s4NvZj7hADAGxU486AP6FbtiRfSfLoeetaEgU4APuFx73+L5e0fW3H4B4F1+748pL173rWE5ZsD5CMKcBba89Kkqq6OMkLW2u3dK+PyDe/xRIAAJjQpF9F/9DdxXeStNZuTvLtqzMkAADYuCa9CPOAqjqiK7xTVUfuQSwAwMQO3XTUgiVsNJMW0b+T5P9W1VszmPv99CzzpTkAAPvqB8548bSHAKtq0m/CfENVbUvygxl8Cc8Pt9Y+uaojAwCADWjiaSRdwa3oBgA2lMMPOWrBElabedwAwH7tKd9nygv9UoADAGwgn/uZzy5p23XDrjuWi9ff53fv18u4+KZJb0MIAACsAAU4AAD0yBQUAOhZbTp8wRLYvyjAAaBnB51x9rSHAEyRKSgAANAjBTgAAPTIFBTYRzMzM5mbm8uWLVuydevWaQ8HAFjjFOCwj+bm5jI7OzvtYcCq8UsmwMpSgAMwkl8yAVaWOeAAANAjBTgAAPTIFBQAgHXiyIOOWrBkfVKAA2O5CI9xHv36P1rSdvuOHUmS2R07lqx/z7P+v17GBRvNTz9oZtpDYAUowIGxXIQHACvHHHAAAOiRAhwAAHqkAAcAgB6ZAw5r2G+/+pFL2m6+tZJUbr51+5L1v/DcD/Q0MoC1Z9OhmxcsYa1SgAPABvPki65c0valHV9Lkly342tL1r/tmQ/tZVyr7fGPfHGv/d394KMWLGFSCvB95PZsALB/+vFTz5/2EFinFOD7yO3ZAADYEy7CBACAHjkDzhL/sPXMBa+/evPXu+XsknXfO/PXvY0LAGAjUIADK+I5r//BJW3X70iSyvU7ti9Z/7+e9f5+BgYAa4wpKAAA0CMFOAAA9MgUFPZLb3jlwukQO29JksrOW7YvWXfOC0yV2GjOeMPPLGlrO29IkszuvGHB+vee87uj32zTQQuXADCGAhxgH9SjHjTtIQCwzijAAYChDtx0jwVLYN8pwAGAoe71qJ+b9hBgw1GAAwD07IiDNy9Ysn9RgAMA9Ownv31m2kNgihTgAGvYoy767QWvv7Hj5iTJ7I6bl6y77Jm/MC/u95a81zd23NLF3rJg/WXPfOGKjRdYm466yz0WLJkuBTgAwAb38/f72WkPgXl8EQ8AAPTIGXBgqp74xh9c0vaVnUlSuXbn9iXrL32GL0YCYH1zBhwAAHrkDDgAsOLuumnzgiXwTQpwgCmYmZnJ3NxctmzZkq1bt057OLDiHvYot9mDYRTgAFMwNzeX2dnZaQ8DgClQgAPr1ulvfMbChp1fSJLM7pxbsu59z3hjX8MCgJEU4ACwjtSmuy9YAuuPAhwA1pGDzzh32kMA9pHbEAIAQI8U4AAA0CMFOAAA9MgccAA2jNq0Ka1bAqxVCnAANowDT3/stIcAMJYpKAAA0CMFOAAA9MgUFFbMZb/z6CVtX7n59m45u2D9o37uPb2NCwBgLXEGHAAAeqQABwCAHpmCAsB+rzbdrbt94d2mPRRgP6AAhx688g9PW9J2y60HJKnccuv2Jetf8LwP9jEsoHPn058w7SEA+xFTUAAAoEcKcAAA6NGqTUGpqtcl+aEk17fWHtK1HZnkLUmOT3JNkqe31m7u1r04ybOT3J7kBa21v+naH57koiQHJ3lXkhe21lpVHZTkDUkenuTGJD/SWrtmtfYH1puXvOaRC17fdGslqdx06/Yl6371vA/0ODJgGmrTETmgWwLTtZpzwC9K8gcZFMm7nZ/kfa21l1bV+d3rX6yqE5OcneTBSe6d5L1V9YDW2u1JXp3kvCQfzqAAPzPJuzMo1m9urd2/qs5O8rIkP7KK+7NPZn/jZ5a07brphjuW89cf8yu/29u4ANg/HHrGc6c9BKCzalNQWmt/l+SmRc1nJbm4e35xkifNa39za+221tpnk1yd5JSqOjrJYa21D7XWWgbF/JOWea+3Jjm9qmp19gYAlrHpsNTd7p5sOmzaIwHWkb7vgnKv1tp1SWL3ZbUAABa0SURBVNJau66q7tm1H5PBGe7dtndtX++eL27fHfP57r12VdWtSe6R5IurN/z144rfeuyStttu+lq3nF2y/qRfencv4wLYSO5y+g9PewjAOrRWLsJc7sx1G9E+Kmbpm1edV1XbqmrbDTfcsJdDBACAfdd3Af6FblpJuuX1Xfv2JMfN2+7YJNd27ccu074gpqoOTHJ4lk55SZK01l7TWju5tXby5s2bV2hXAABgz/U9BeXSJOcmeWm3fMe89jdV1cszuAjzhCQfaa3dXlU7q+rUJJcnOSfJ7y96rw8leWqS93fzxFlnLn3Fo5a0ffmWb3TL2SXrn/iiy3oZFwDAaljN2xD+aZLTkhxVVduT/FoGhfclVfXsJJ9L8rQkaa1dVVWXJPlkkl1JntfdASVJnptv3obw3d0jSV6b5I1VdXUGZ77P3pfxzszMZG5uLlu2bMnWrVv35a0AAGCoVSvAW2s/OmTV6UO2vzDJhcu0b0vykGXav5qugF8Jc3NzmZ2dHbvddb/5Wwte337TTXcsF687+r//0koNDwCADaLvKSgArGGPev2rlrR9Y8etSZLZHbcuWX/Zs/5bL+MC2EjWyl1QAABgv6AABwCAHpmCAsDq2HTIwiUASRTgAKySO53+yGkPAWBNMgUFAAB65Aw4G4r7uQMAa50CnA1l0vu5M9wv/vHSaQNf3FFJKl/csX3B+pf95Ad6HBkAbAymoAAAQI+cAYc98JrfX3p2+NZbBmeHb71l+4L15/20s8MAwFLOgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAj9wFBWA92XTwwiUA644CHGAdOeCM75z2EADYR6agAABAjxTgAADQI1NQYJ05+JAkad0SAFhvFOCwznzn97dpDwEA2AemoAAAQI+cAQfYX2w6ZOESgKlQgAPsJw4447unPQQAogCHJMmh3YWNhzoxCACsMgU4JHn090x7BGxkZ1z8m0va2o6bkiSzO25asv695/73XsYFwHS4CBMAAHqkAAcAgB6ZggKsmjtvSpLWLQGARAEOrKJjTp/2CABg7VGAM9bdD64krVsCALAvFOCMdc7J0gQAYKW4CBMAAHqkAAcAgB6ZWwCsOdXdPaXcPQWADUgBDqw5Bz96LwM3HbhwuScOvcvCJQCsEgU4sHE8+h57HVqPvt8KDgQAhjMHHAAAeqQABwCAHpmCsg7NzMxkbm4uW7ZsydatW6c9HAAA9oACfB2am5vL7OzstIcBAMBe2C8L8Ote8gdL2m6/6ZY7lovXH/2rz+9lXAAAbHzmgAMAQI8U4AAA0KP9cgoKAHtg0yELlwDsEwX4PjrqrgcvWMKkDjkkSVq3hLXrgNO/b9pDANhQFOD76PyTvn3aQ2Cd+p7v/ca0hwAATIE54AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPfBEPq+rwQxYuAQD2dwpwVtXZp9xp1d77kt87Y0nbl25p3XJ2yfqnv/C9qzaWje6gQ5OkdUtWxKa7LlwCsN9QgANjPeCRbdpD2HDqUSdNewgATIkCfIo23/UuC5YAAGx8CvApmnnY/aY9hDXrsIMXLgEANgoFOGvSk091gx4AYGNS5QAAQI8U4AAA0CMFOAAA9MgccNhP3LW7l/dd3csbAKZKAQ77iYee5l7eALAWmIICAAA9UoADAECPFOAAANAjc8BhHx16SJK0bgkAMJoCHPbRaY9wcSMAMLmpTEGpqmuq6uNVdUVVbevajqyqy6rqM93yiHnbv7iqrq6qT1fVY+a1P7x7n6ur6pVVVdPYHwAAmNQ054A/srV2Umvt5O71+Une11o7Icn7utepqhOTnJ3kwUnOTPKqqrpTF/PqJOclOaF7nNnj+AEAYI+tpYswz0pycff84iRPmtf+5tbaba21zya5OskpVXV0ksNaax9qrbUkb5gXAwAAa9K0CvCW5D1V9bGqOq9ru1dr7bok6Zb37NqPSfL5ebHbu7ZjuueL25eoqvOqaltVbbvhhhtWcDcAAGDPTOsizEe01q6tqnsmuayq/mXEtsvN624j2pc2tvaaJK9JkpNPPtkVcwAATM1UCvDW2rXd8vqqeluSU5J8oaqObq1d100vub7bfHuS4+aFH5vk2q792GXa98pRdz10wRIAAFZD7wV4VR2a5IDW2s7u+aOTvCTJpUnOTfLSbvmOLuTSJG+qqpcnuXcGF1t+pLV2e1XtrKpTk1ye5Jwkv7+34zr/oY/Y29B148iDK0nrlgAATMM0zoDfK8nbujsGHpjkTa21v66qjya5pKqeneRzSZ6WJK21q6rqkiSfTLIryfNaa7d37/XcJBclOTjJu7vHhvLvF/zQkrav3/TVbnntkvX/5YJ3Dn2vn/r2O6/s4AAA2GO9F+CttX9P8rBl2m9McvqQmAuTXLhM+7YkD1npMQIAwGpZS7chBACADU8BDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjw6c9gBgJd3tkIVLAIC1RgHOhvL4765pDwEAYCRTUAAAoEcKcAAA6JECHAAAeqQABwCAHinAAQCgRwpwAADokQIcAAB6pAAHAIAeKcABAKBHCnAAAOiRAhwAAHqkAAcAgB4pwAEAoEcKcAAA6NGB0x4Ae+6og2rBEgCA9UMBvg696NsOmvYQAADYS6agAABAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADAECPFOAAANAjBTgAAPRIAQ4AAD1SgAMAQI8U4AAA0CMFOAAA9EgBDgAAPVKAAwBAj9Z9AV5VZ1bVp6vq6qo6f9rjAQCAUdZ1AV5Vd0ryh0kem+TEJD9aVSdOd1QAADDcui7Ak5yS5OrW2r+31r6W5M1JzprymAAAYKj1XoAfk+Tz815v79oAAGBNqtbatMew16rqaUke01r7ye71M5Kc0lr76UXbnZfkvO7ltyb59JC3PCrJF/diKHsbN40+7ePKx02jT/u48nHT6NM+rnzcNPq0jysfN40+7ePKx02jz7W2j/dtrW1e0tpaW7ePJN+d5G/mvX5xkhfvw/tt6zNuGn3aR/toH9dOn/bRPtrHtdOnfbSPfe7jep+C8tEkJ1TV/arqLknOTnLplMcEAABDHTjtAeyL1tquqnp+kr9Jcqckr2utXTXlYQEAwFDrugBPktbau5K8a4Xe7jU9x02jT/u48nHT6NM+rnzcNPq0jysfN40+7ePKx02jT/u48nHT6HNd7OO6vggTAADWm/U+BxwAANaXvb3ic70/krwuyfVJPjGv7aQkH05yRZJtGdzScJK4hyX5UJKPJ/nLJIctE3dckg8k+VSSq5K8sGs/MsllST7TLY+YMO5p3etvJDl5yD4Oi/3tJP+S5Mokb0ty9wnjfqOLuSLJe5Lce5K4eet/PklLctSE/V2QZLbr74okj5t0H7t1P53BLSevSrJ1wj7fMq+/a5JcMWHcyNwZETdJ7tw1yUeS/HMX++sT5s6wuJG5MyJuXN4MixuZN6NiJ8idYX2OzJ1R/Y3Jm2H9jcubYXGTHHOGxY7NnW67OyX5/5O8c5K8GRE39pgzJG5k3oyIG5s3w2LH5c2IPkfmzaj+RuXNiP5G5s2Y2LG5MyRu0ry5ptvminR3eJgkd4bETfLzarm4sbkzJG6i3FkudpLcGdLn2NwZ1t+43BnS30S5MyR2kuPOcnGT/Ly6e5K3dv9un8rgbnWT5M1ycZPkzXJxkx5zloud5OfVkrhJjzkL3mfcBhv1keT7k3xHFhbS70ny2O7545J8cMK4jyb5ge75TyT5jWXijk7yHd3zuyX51yQnJtma5Pyu/fwkL5sw7kEZ3NP8gyMSc1jso5Mc2LW/bA/6PGzeNi9I8r8mieteH5fBxbL/sTgxR/R3QZKfH/PvOCz2kUnem+Sgbt09Jx3rvG1+J8mvTtjfyNwZETdJ7lSSTd3zOye5PMmpE+TOsLiRuTMiblzeDIsbmTejYifInWF9jsydEXHj8mboOMfkzbD+JjnmDIsdmzvdup9N8qZ8swAbmTcj4sYec4bEjcybEXFj82ZY7Li8GdHnyLwZETcyb0aNc1TejOlzbO4MiZs0b65Z/LlNkjtD4ib5ebVc3NjcGRI3Ue4sFztJ7gzpc2zuDIkbmzvDxjlJ7gzpc5LjznJxk/y8ujjJT3bP75JBsTpJ3iwXN0neLBc36TFnudhJfl4tiZskbxY/9tspKK21v0ty0+LmJId1zw9Pcu2Ecd+a5O+655clecoycde11v6pe74zg9+ajklyVgb/mOmWT5okrrX2qdbasC8UGhf7ntbarm6zDyc5dsK4HfM2OzSDz2uSfUySVySZWRwzQdxII2Kfm+SlrbXbunXX70mfVVVJnp7kTyeMG5k7I+ImyZ3WWvtS9/LO3aNlfO4sGzcud0bEjcubYXEj82bMPiajc2dU3FAj4sblzcj+RuTNsLhJjjnDYsfmTlUdm+TxSf54XvPIvBkWN8kxZ0jcyLwZETc2b4bFdobmzZi4kYbEjcybcf0Ny5sxsWNzZ0jc2LwZYWzuLGeS3BkSNzZ3hsRNlDsjjMydFTY2d0YZlztDjM2dIUbmTlUdlsFJytcmSWvta621WzImb4bFjcubEXGTHHOGxY7MnRH7mOxp3rQxFfpGfiQ5PgvPZD8oyecy+Hr72Qy+vWiSuP+b5Kzu+c8m2TlBv5/L4D/ALYvW3TxJ3Ly2D2bE2ahRsV37Xyb58UnjklzYfT6fSLJ5wn18YpLf69qvyejf5OfHXdBtf2UGU3+W/VP5kNgrkvx6BmcL/zbJd+7h5/r9GXNj/UX9TZQ7y8RNlDsZ/Bn5iiRfSvfb/CS5s1zcJLkzKm5U3gyLmyRvhuzj2NwZEjc2d4bEjc2bMZ/p0LwZ0t+kx5zlYsfmTgZ/Jn14ktPyzTOgk+TNkrgJ82Zo3Ji8WTZuwrxZbh8nyZvl4ibJm+XiJsmbUZ/pyOPNkD7H5s6QuEmPOZ9N8k9JPpbkvD3InSVxE+bO0LgxubNs3IS5s9w+TpI7y8VNkjvLxU2SO6M+03G5s1yfk+TOcnEjcyeDqS0fSXJRBtOe/jiDInZk3gyLG5c34+LG5M3Q2FG5M2IfJ65z7nivcRts5EeWFtKvTPKU7vnTk7x3wrgHZvAnnY8l+bUkN47oc1O33Q93rycqwBfHjUvMCWN/OYP5UbUncd26F2fRPN3l4pIcksGB5fBxibnMZ3OvDAqPA7r/EK/bg8/1E92/ZyU5JYODyZL9HPHZvDrJz+1Bf5PmzuK4iXOn2/7uGcwlf8ikubM4bg9zZ7m4kXkzLG5c3iwT+9BJc2eZz2ZPcmd+3ER5M+KzGZk3y/Q3Ud4MiR2ZO0l+KMmruuenZcICfFjcuLyZIG7ZvBkXNypvlovNBMecEZ/NyLwZETcybyb4bIbmzYg+R+bOiLiJjjnp5r4muWcG1x98/7jcGRY3LncmiBt6zBkVNyp3Ruzj2GPOkLixx5whcWOPOWM+m3E/q5brc+xxZ0jcuGPOyUl2Jfmu7vXvZTCnetwxZ9m4cXkzQdyovBkZOyx3hsT99iR5s2QM4zbYyI8sLaRv3f0P1f1n2DFJ3KJ1D0jykSHr7pzB/KCfndf26SRHd8+PTvLpSeLGJea42CTnZnAxxSF7Ejdv/X2X+wwWxyX5tgwuWr2me+zK4DfvLXvY36jPfLnP9a+TnDbv9b9l6W+ywz6bA5N8Icmxe9Df2NyZYB+H5s6i7X4tgws9xubOcnGT5s5ycePyZlR/o/JmSOyvTJI7E/Q5NHeW+UzH5s2Iz2Zk3gzpb6JjzgT7uCR3kvyPJNu7z24uyVeS/J9xeTMsblzejIoblTfj+huVN0Ni/3xc3kzY55K8GfGZjsybMZ/NuOPNsD5H5s6E+zjpMeeC7N0x54Ls3THnjrhRuTOuv1G5MyR2b445y/W5JHdGfKZ7esyZ/9lMfMxZ1OceHXeG7ONyx5wtSa6Z9/r7kvzVuLwZFjcub0bFjcubcX0Oy50hce/b07xpTQG+4D9JBvNyT+uen57kYxPG3bNbHpDkDUl+YpmY6tb97qL2387CixMW33Vh2bhxiTmmzzOTfHLYf/IRcSfMe/7TSd66J2Pttrkmy19It1x/R897/qIkb96DsT4nyUu65w/I4M9JNclYu8/nb/fwsxmZOyPiJsmdzfnmRR4HJ/n7DM5ujcudZePG5c6I/sblzbC4kXkzyVhH5M6wPkfmzoi4cXkzdJxj8mZYf2OPOSNix+bOvPc4LQvvSjI0b4bFjcubEf2NzJsRcWPzZtxYh+XNiD7HHnOGxI3Mm1HjHJU3Y/qc6OfVMnGTHHMOTXK3ec//bzfOccecZePG5c6I/sYdc4bFTXLMGTnWYbkzos9xx5xhceOOOUPHOS53RvQ57ufVsLhJcufvk3xr9/yCLmfGHnOWixuXNyP6m+iYMyR2ktwZOtZhebNs/5P8p9+IjwwuWLguydczOEvw7CTfm8GfVv45gz8nPHzCuBdmcFeLf03y0iz/547vzWBi/u7b21yRwdXH98jgt6fPdMsjJ4x7ctf/bRn8Bvw3e9Dn1Rn8J9/dtvhuJsPi/jyDP5ddmcG8qmMmiRuXmCP6e2MGtzu6MsmlmXeAmyD2LhmcJfpEBvPYfnDSsWYwt+s5Q/JmWH8jc2dE3CS589AM5ppd2e3Pr3bt43JnWNzI3BkRNy5vhsWNzJtRsRPkzrA+R+bOiLhxeTN0nGPyZlh/kxxzhsWOzZ1573FavlmAjcybEXFjjzlD4kbmzYi4sXkzLHZc3ozoc+wxZ0jcyLwZNc5ReTOmz7G5MyRukmPOf+ned/etL395wmPOsLhxx5xhceOOOcPiJjnmLBs7wTFnWJ/jjjnD4sYdc4aOc1zujOhz3M+rYXGT5M5JGdza8Mokb09yxLi8GRE3SZ2zXNxEx5whsZPkzpK4PTnm7H74JkwAAOjRfnsbQgAAmAYFOAAA9EgBDgAAPVKAAwBAjxTgAADQIwU4AAD0SAEOAAA9UoADkKp6e1V9rKquqqrzurZnV9W/VtUHq+qPquoPuvbNVfXnVfXR7vGI6Y4eYH3xRTwApKqObK3dVFUHJ/loksck+cck35FkZ5L3J/nn1trzq+pNSV7VWvuHqrpPBt9Q96CpDR5gnTlw2gMAYE14QVU9uXt+XJJnJPnb1tpNSVJVf5bkAd36M5KcWFW7Yw+rqru11nb2OWCA9UoBDrCfq6rTMiiqv7u19pWq+mCSTycZdlb7gG7b/+xnhAAbizngABye5Oau+H5gklOTHJLkB6rqiKo6MMlT5m3/niTP3/2iqk7qdbQA65wCHIC/TnJgVV2Z5DeSfDjJbJLfSnJ5kvcm+WSSW7vtX5Dk5Kq6sqo+meQ5/Q8ZYP1yESYAy6qqTa21L3VnwN+W5HWttbdNe1wA650z4AAMc0FVXZHkE0k+m+TtUx4PwIbgDDgAAPTIGXAAAOiRAhwAAHqkAAcAgB4pwAEAoEcKcAAA6JECHAAAevT/AAu9vTjbjB+zAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 864x648 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12,9))\n",
    "plt.title('Age vs Charge')\n",
    "sns.barplot(x='age',y='charges',data=data_copy,palette='husl')\n",
    "plt.savefig('./sampleImages/AgevsCharges')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2e69a038b38>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,7))\n",
    "plt.title('Region vs Charge')\n",
    "sns.barplot(x='region',y='charges',data=data_copy,palette='Set3')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'BMI VS Charge')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAckAAAFNCAYAAABrHpS/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdd5yU1b348c/3mbqzvVMWpYMgoIgC9oZIscWeGDW2JBpjkpuem5uYX4zem9zkJiYaa6ImlmhUrNgLKohgAwHpZWnb6+zszszz/f1xZstsY4FdFvC8X6+VnbPPc54zC+53T/seUVUsy7Isy+rI6e8GWJZlWdb+ygZJy7Isy+qCDZKWZVmW1QUbJC3LsiyrCzZIWpZlWVYXbJC0LMuyrC7YIGlZ1i6JiIrIyP5uh2XtazZIWlYvEpGNItIgInUiUikiz4vIkDZf/3si4Jzd7r7/S5RfmXh9pYi808UzVonIVZ2U3yQiSxKfjxeRlxNtqBKRpSIyu5t2DxSR+0Rku4jUJp5xs4ik7uG3wrIOCjZIWlbvO0tV04CBwE7g9nZfXw1c0fxCRLzAhcC6Htb/AHB5J+VfTXwN4FngFaAQKAC+DdR0VpmI5AALgRRguqqmAzOALGBED9vUI4n3alkHDBskLauPqGoEeAIY1+5LzwLHiUh24vWZwKfAjh5W/RBwvIgc2lwgIocBE4FHRCQPGAbco6pNiY93VbXTninwPaAWuExVNybavkVVb1LVT9tcd7qIrEn0Tv8iIpJ49ggReV1EykWkTET+KSJZbdq2UUR+JCKfAvUi4hWRy0VkU+KenyeuOT1xvSMiPxaRdYmv/ysRyC1rn7NB0rL6iIiEgIuBRe2+FAGeAS5JvL4ceLCn9apqMfAGpufY7HLgBVUtA8qBtcA/RORcESncRZWnA0+qqruL6+YCRwOTgIuAmYlyAW4FBgGHAUOAX7a791JgDqZ3Ohq4A/gKpredCQxuc+23gXOBkxJ1VgJ/2UXbLKtP2CBpWb3vaRGpwgxvzgB+28k1DwKXi0gmJhg8vZvPeIBEkBQRBxNwHgBQk5D5FGAj8L/AdhF5W0RGdVFXLrC9B8+8TVWrVHUzJkgfkXjeWlV9RVUbVbUU+H3iPbX1p0TvtAG4AHhWVd9R1Sbgv4C2SaS/DvxMVYtVtRETcC+wQ7VWf7BB0rJ637mqmgUEgG8Bb4nIgLYXJIY+84H/BJ5LBI/d8SQwUESmAScDIeD5NvUXq+q3VHUEcChQT9e91XJMj25X2g4Hh4E0ABEpEJFHRWSriNQA/wDy2t27pc3ng9q+VtVwog3NDgWeSiw4qgJWAnHM/Kpl7VM2SFpWH1HVuKo+ifkBf3wnl/wD+A92Y6i1Td1hzHzn5Zge5aOJXlln127BDFce3kV1rwLnJXqke+JWTE9woqpmAJdhhmCTmtHm8+1AUfMLEUnB9GabbQFmqWpWm4+gqm7dw/ZZ1h6zQdKy+ogY5wDZmN5Qe3/CDMe+vYePeAAz53k+rataEZHsxPaNkYlFMHnAVXScG232eyADeKB5MZCIDBaR34vIxB60Ix2oA6pEZDDwg11c/wRwlogcKyJ+4GaSg+pfgVvatCU/8X20rH3OBknL6n3PikgdZk7yFuAKVf2s/UWqWqGqr+meH+r6NlANbFXVD9qUNwFDMT3EGmA50Ahc2VklqloBHAtEgfdFpBZ4LVH32h6042ZgcuL65zFDwV1KfC9uBB7F9CprgZJEGwH+iFnY9HKiLYuAqT1oh2X1OrGHLluW1Z9EJA2oAkap6ob+bo9ltWV7kpZl7XMicpaIhBIZfX4HLMOsxrWs/YoNkpZl9YdzgG2Jj1HAJXsx7GxZfcYOt1qWZVlWF2xP0rIsy7K6YIOkZVmWZXXhC5fmKS8vT4cOHdrfzbAsy7L2I0uXLi1T1fz25V+4IDl06FCWLFnS382wLMuy9iMisqmzcjvcalmWZVldsEHSsizLsrpgg6RlWZZldeELNydpWZZl9Vw0GqW4uJhIJNLfTekVwWCQoqIifD5fj663QdKyLMvqUnFxMenp6QwdOhSR9iegHVhUlfLycoqLixk2bFiP7rHDrZZlWVaXIpEIubm5B3yABBARcnNzd6tXbIOkZVmW1a2DIUA22933YodbLcuyDlLxulq0vh5tCOOkpePk5h1UAW9fsEHSsizrIOTW1lD/8EPU3PUXcF2c/AIK7nsI7yGH9nfTDih2uNWyLOsg5NbUUHPn7eC65nVpCVX/cwtuTU0/t2z31NfXM2fOHCZNmsThhx/OY489xtKlSznppJM46qijmDlzJtu3b6e6upoxY8bw+eefA3DppZdyzz337PXzbU/SsizrIBQvLelQFl23Fm1q7IfW7Ln58+czaNAgnn/+eQCqq6uZNWsW8+bNIz8/n8cee4yf/exn3H///fz5z3/myiuv5KabbqKyspJrr712r59vg6RlWdZByDuoCAkG0TYrOYOnnIakpfdjq3bfhAkT+P73v8+PfvQj5s6dS3Z2NsuXL2fGjBkAxONxBg4cCMCMGTN4/PHHueGGG/jkk0965fk2SFpWL9OGenT7eti5BYaOQ7ILkGCov5tlfcE4WVnk3fMAVb/6ObGtW0mZOYuMq7+BEwz2d9N2y+jRo1m6dCkvvPACP/nJT5gxYwbjx49n4cKFHa51XZeVK1eSkpJCRUUFRUVFe/18GyQtqxdpJIz77jOwda0pWL0UJp8G445BPPZ/N2vfEb+fwIRJ5N31N4i7SGoqTujA+2Vt27Zt5OTkcNlll5GWlsbdd99NaWkpCxcuZPr06USjUVavXs348eP5wx/+wGGHHcZvfvMbrrrqKhYuXNjjzDpdsf/XWlZvijW1BsgEXfYOMnIipKT1U6OsLzJPTm5/N2GvLFu2jB/84Ac4joPP5+POO+/E6/Xy7W9/m+rqamKxGN/5znfw+Xzce++9LF68mPT0dE488UR+/etfc/PNN+/V822QtCzLsvZbM2fOZObMmR3K33777Q5lK1eubPn897//fa88324Bsaze5PXD4FFJRTLxePAfWPNAlmUZtidpWb1IgiGc485Ct2+AnZth2Dgkq8DOR1rWAcr+n2tZvUxSUpHhh8Pww/u7KZZl7SU73GpZlmVZXbBB0rIsy7K60KdBUkSyROQJEVklIitFZLqI5IjIKyKyJvFndpvrfyIia0XkcxGZ2ab8KBFZlvjanySRxl5EAiLyWKL8fREZ2pfvx7Isy/pi6eue5B+B+ao6FpgErAR+DLymqqOA1xKvEZFxwCXAeOBM4A4R8STquRO4DhiV+DgzUX41UKmqI4E/AP/dx+/Hsg5oGo+h9dW4az/B3bYBbajv7yZZ1i7Nnz+fMWPGMHLkSG677bZ9+uw+C5IikgGcCNwHoKpNqloFnAM8kLjsAeDcxOfnAI+qaqOqbgDWAseIyEAgQ1UXqqoCD7a7p7muJ4DTxB6WZlldq6nAfeoO9N1n0Ff+gfv6ozZQWvu1eDzODTfcwIsvvsiKFSt45JFHWLFixT57fl+ubh0OlAJ/E5FJwFLgJqBQVbcDqOp2ESlIXD8YWNTm/uJEWTTxefvy5nu2JOqKiUg1kAuU9ck7sqwDmDZFcJe+BvFYa2HZNqirhJTU/muYdVBx1y9DP3wD6qshNROZfArO8Al7XN/ixYsZOXIkw4cPB+CSSy5h3rx5jBs3rrea3K2+HG71ApOBO1X1SKCexNBqFzrrAWo35d3dk1yxyHUiskRElpSWlnbfass6WLkuNEU6FGtjxzLL2hPu+mXoe8+bAAlQX42+9zzu+mV7XOfWrVsZMmRIy+uioiK2bt26t03tsb4MksVAsaq+n3j9BCZo7kwMoZL4s6TN9UPa3F8EbEuUF3VSnnSPiHiBTKCifUNU9W5VnaKqU/Lz83vhrVnWgUeCIWTc1ORCfxDJKeyfBlkHHf3wDYhHkwvjUVO+p3Vqh34P+3JWrc+CpKruALaIyJhE0WnACuAZ4IpE2RXAvMTnzwCXJFasDsMs0FmcGJqtFZFpifnGy9vd01zXBcDr2tl31LIsAGTgMOTUi2HQcGTkJJy510Kw/4Za3aZG4rU1/fZ8q5c19yB7Wt4DRUVFbNmypeV1cXExgwYN2uP6dldfZ9y5EfiniPiB9cDXMIH5XyJyNbAZuBBAVT8TkX9hAmkMuEFV44l6vgn8HUgBXkx8gFkU9JCIrMX0IC/p4/djWQc0CaQgQ0ajhYeA40G8e3eM0N6I7dxB7f13E9u4gdA5XyJ47Al4srL6rT1WL0jN7DwgpmbucZVHH300a9asYcOGDQwePJhHH32Uhx9+eC8auXv6NEiq6sfAlE6+dFoX198C3NJJ+RKgQ44vVY2QCLKWZfWc9HPC9XhZGaVXXEp8x3YAGt9fSOb3f0zaJZchXpst80Alk08xc5Jth1w9PmTyKXtcp9fr5c9//jMzZ84kHo9z1VVXMX78+F5obQ+fv8+eZFmWlRAv3dkSIJvVPfpPQmfOxZOX10+tsvaWM3wCLvTq6laA2bNnM3v27N5p5G6yQdKyrH1OUkIdypyMTPDYTJkHOmf4BNjLoLg/sf8iLcva55ysLIInntxa4PGQ9R8/wpOd029tsqzO2J6kZVn7nCcrm+xf3kJs4wZimzcROHoqTo4NkNb+xwZJy7L6hScnF09OLoHJna3ts6z9gx1utSzLsqwu2CBpWZZlWV2wQdKyLMvar1111VUUFBRw+OEdtsv3ORskLcuyrP3alVdeyfz58/vl2TZIWpZlWb2m/oVn2T7rVIqPPIzts06l/oVn97rOE088kZx+Wv1sV7dalmVZvaL+hWep+tXP0Yg5fi2+fRtVv/o5AKmzz+rPpu0x25O0LKtT8fJyYsVbiO3cgVtf19/NsQ4ANbf/oSVANtNIhJrb/9BPLdp7tidpWVYHsZ07KLv+WmLr1oDXS8Z115N2yVdM6jjL6kL7fLy7Kj8Q2J6kZVlJ3IYGau683QRIgFiMmjv+RLyysn8bZu33PAMG7lb5gcAGScuykmhDmOhnyzqUxzZt6IfWWAeSjBu/iwSTj2GTYJCMG7+7V/VeeumlTJ8+nc8//5yioiLuu+++vapvd9jhVsuykjjpGQROPIXomtVtCh18o8b0X6OsA0Lz4pya2/9AfMd2PAMGknHjd/d60c4jjzzSG83bIzZIWpaVRHw+0r9yOfHt22h46QWc3Fyy//NmnEw7H2ntWurssw7YlaydsUHSsqwOPDm5ZP/0F2R974eA4GRnIx5PfzfLsvY5GyQty+qUk5YGaWn93QzL6ld24Y5lWZbVLVXt7yb0mt19LzZIWpZlWV0KBoOUl5cfFIFSVSkvLyfYbgVud+xwq2UdYLShDmJR8HjBH0S8vv5uknUQKyoqori4mNLS0v5uSq8IBoMUFRX1+HobJC3rAKJ1VbivPgLVZeD1IVNnwSFjEX+gv5tmHaR8Ph/Dhg3r72b0GzvcalkHCG2K4C5+yQRIgFgUfe9ZiEa6v9GyrD1mg6RlHShiUSjbllymCmGbfNyy+ooNkpZ1oPAFkIHthr0cD6Rm9E97LOsLwAZJyzpAiM+PHHUaNAfKlDTk1IvB3/OVer1NVVHX7bfnW1Zfswt3LOsAIqF0nJPOh3gUcCAYQpx9/7uuui6Ea9FVH0BTBMYdA6lZiM+/z9tiWX3JBknLOsBIIAVI6d9GNNThPnMXRBsB0LUf48y9FnIK+7ddltXL7HCrZVm7TbeubQmQpkDR5e+h8Vj/Ncqy+oANkpZl7T6nk2TnNgG6dRDq0yApIhtFZJmIfCwiSxJlOSLyioisSfyZ3eb6n4jIWhH5XERmtik/KlHPWhH5k4hIojwgIo8lyt8XkaF9+X4syzJk0HBIaZP83PEghx+HeOwMjnVw2Rc9yVNU9QhVnZJ4/WPgNVUdBbyWeI2IjAMuAcYDZwJ3iEjzr6Z3AtcBoxIfZybKrwYqVXUk8Afgv/fB+7EsKyUNZ+41yNRZyJGn4Jx3PaTZ8yatg09/DLeeAzyQ+PwB4Nw25Y+qaqOqbgDWAseIyEAgQ1UXqsmw+2C7e5rregI4rbmXaVlW3xERs9J27BSciccjaVmIx4tGm9BwLVq50/wZi/Z3Uy1rr/T12IgCL4uIAnep6t1AoapuB1DV7SJSkLh2MLCozb3FibJo4vP25c33bEnUFRORaiAXKOuj92NZVhc0FkOL16DvPA2uCx4vzulfRguG9Ms2FcvqDX39L/c4VZ0MzAJuEJETu7m2sx6gdlPe3T3JFYtcJyJLRGTJwZLJ3rL2O00NJpdsc3KBeAz3naehMdy/7WpHmyJouM72cq0e6dOepKpuS/xZIiJPAccAO0VkYKIXORAoSVxeDAxpc3sRsC1RXtRJedt7ikXEC2QCFZ20427gboApU6Yc+IeiWdb+KB4z+WXbqq8x+WUBt6EBt6aGeGkJnsJCiMdpePVlJOAn5eTTcHLz+rTH6cZjSH0t7gcvQWUJMmQUTDwBabsAqQ2NNpkFSXbV7hdan/2LFJFUEUlv/hw4A1gOPANckbjsCmBe4vNngEsSK1aHYRboLE4MzdaKyLTEfOPl7e5prusC4HU9GE4GtawDgFtXR6xkJ/GSnbjhMHh9kJGTfFHhoeDxotEojYsXsmPO6ZR942u4O7az80tzqf7drVTdcjM7LzoXt6x3R3m0oR6trTRzo/XVSGUJ7ssPQfEaqK9GVy1Bl7yCtt3vSaKnuWMj7oKn0MXz0boqm3rvC6wvh1sLgXdE5BNgMfC8qs4HbgNmiMgaYEbiNar6GfAvYAUwH7hBVeOJur4J3ItZzLMOeDFRfh+QKyJrge+RWClrWVbfildWUPW/t7Fj1qlsn3M6Nff8FTcaxzn9yya3rC8Ah4zBOeFcJJCCW1VJ5S9+CrEoKSeeQv1zz6Dh+pb63MoKwq+9skdtUdc1ga1NINOGOtzXHsF98s9QVYo7/0HT062vTr5340qIJvd+tXQb7ksPwZbV6OoPcZ+9ByL1WF9MfTbcqqrrgUmdlJcDp3Vxzy3ALZ2ULwEO76Q8Aly41421rIOQG4lAUyOSnkFvL/qOLHyX8FNPmBfxOHV/u5vgcccTOPKoRG7ZmDkUOpF8XeMublWVud7ng2hThzo1svvnYmqkHl23DN26FhlwKIyaDIEUdNUSKN9ukr+7cairAscBkZbhXwDSspJWNmhTBP3sveSHNEXQ0mLk0MN2u33Wgc8uObOsg4yqEtu2larf3EzZd79F+PlniDcHqN6oPxol8vabHcoj775N7cMPUv/8c7iRppYACSDBAP6JR5jrFrxFaM7Z4PW2+XoKoTNn7147miLo4pfQJa/A9g3oR2/ivjMPbWxAm8/ddOOQSHCgmz9HJhzXWoHjwTl2bvKcpDimF9xeP560YvUvmx7Dsg4ybnkZJZddhFtRDkDT0g/I+snPSb3gkl5ZhCI+H8GTT8VJS0NSU4m88TqxzRvxjzmMmjv/TGzTBhpef5Wcm2/Bk5sHgCcrm5zf/h9Vv7uNpg+X0LhiOYWPPkXtww8ifj/pl12JJy9/9xoSa0I3rkgu27YOUGToOHTbOohF0UgYCg9Bl7+HTDoJZ9aVpqebmQf+5ETx4vPjHHky7ta15hqArHwkK7lt2lAP6oI/BfHaH6MHM/u3a1n9wA2HcWtr0fo6nPQMnOzsDj9s4xXlxMvLEUdwsnPw5OT2qO5YcXFLgGxW99jDpJw+syVo7Q11XULHTieY7kK0kfQ5s2jaXoLWh4lt2gBA4ztvoTVVaMCLpGUB4C0cQM4vfo1GGpBgCk5aGtk//QXAHgYaAY8PYm2Gbh0HUYUho2H8NPTzpejHb+GcciFaVw015RBMNWdxtjvWSxvqzOpcXwD50g2wZY25Ln9wS29TY01Qth33/fkQqUdGHgHjpyHB0B603zoQ2CBpWfuYGw4Tnv88Vb+5GWIxJD2D/HsewD+2dc4rXlZG2TevIrpmNQC+wyeS98c78eTuOlA6aeYHupOVRfCU0xGPQ6y0NGl4sz2NRaGxwSxsCaWbHpK/k2FHgEg97vP3mXMkATatJHDyRZT88CftKo3jLnga55SLWoKIk5YGaa3Dm3vVC/MHkSNPRj94ubW+w48zQc7nhyNORsZPN18IpOBk5QMjO61KaytxX3kYaivMXOq02cjwCR3Px4w04L78D9OLBHT5uxAMwWHH2IQJBykbJC1rH9GGekChqYmaO26HmBnO09oaKv/rx+T99W94cswWivBLL7QESIDo8k+JLHyX1Lln7/I5Tm4u6dffRNqM06F4JaDIuKlIamrn7VKF0mLcVx8xc3iATJ0FIyZ2eoiy7tjUGiCby9Z8SGjG6cRGjsQ7fCQSCkLVTijZ0ppcoJeJ12faOHAYWrIFyRsEqZktbRavz2xL2QVtbMBd9IIJkGCGaN99BhkwFNr3Nsu3tQTIlrKNnyEjJppgaR107K8+ltXHNB5DS4tx5z+A+/j/oR++Sv6ddyHpGS3XRNevbwlQ6rpEP1/ZoZ7o2s979DxPdg4Zl1wM7z4B6z+B9Z+iL9wH4ZrOb4jU4777TMvzAdM7SwRCjcfR+hrcVR/gblrVaeARf4DUL12Mk19A5O03cCsqIXsADBhqVpX2EQmkINkFOGOOQnIH7tmwZzxmVsK2pdrptg9Jz+lYlpnXbS/dOrDZv1nL6muNiSG65mw0Wz7HcTxkXPcNYtu2oXV1aDyOBM0KSnEcUs+7kPAzTyVVE5o1t8eP1PXLWheeALiu2RZx9Bkdt4Oomsw4bbnx1qDZUIs7766WuT/nzCvQjByoSfS8PF5kwglU/s+tNLz4HABNn3xE9POVZP3nL/f/+TqvHwYMg01tFgF5vC1HgWlTI4iYHmooHRl1BLrmY3NdaiZyxMmIt2OP262rQxvC4PXiye4YXK0Dgw2SltXXmheEtLVjI2lzvoq77B3wB3HGT4fU1rk674gRZP/6f6i9907weMj45rfxDi6ixzobZvT6O98v6fWZhS5bWod3ycgBr89s1P9sUdLiGPfdZ3BOuxSt3AGRMFI0Grcx2hIgm0XefpP4jh0Qi+MdNJj9lfgDOMecgdvUANs3QGomzvHnoB4v7Nxs/o48PpwjToL0HOSo05GJJ5i/00BKp2nt4mWlVP3uNiJvv4l32DByfvkbvMNH9FqKO1Xt8d5XdV3ipSWE5z2JW1dH6gUX4SkYgBO021p6wgZJy+prwdSOm9izC9Bta2HjZwC4m1bgnP11CKWjrovj8xA69RRSTjwRjblm9etuJASQYYejy98zi3HALGYZM7nza/1BnGlz0GCq2TaRMwDnmJlIShrqxjtu/K+tRIvX4Iyf1loWLkGCwaSEAJISQiMRqn7zK3Ju/S1Om+HlfUFjUWhOORcIdbuwRkLprUkQRCCYipRvx53/QMs1bvFqnHOvR9KzIZDSZV1ufR1Vv7uNhvnPAxD9bDml11xO4RPP4snfzW0u7euuqSG6YR31T/8b3+gxhGbMwpPX/Yplt6yUkovPbUnmUPfwQxT+6ymc4Z0vYrKS2SBpWX3NH0CmnokufsksYgll4Bx1Gu5b/269prEBLdkCg0ei2zegi14wvbRh43CmdDJEuiuhdJyzr0M3rwZ1kUPGtgwfdkZCaXDMGUhTUyJTjlnZKo7HbKVY/2lrkPf6OmSfkfR0Mm74DtX/e1tLWfo13yD84nM0rViOG2nESd+9t7A3NBJGP1uIrvrA/IIwZQYUjUxKcNCetAl86sbRlYuTL3BddOOK5IQEnT073EDkrTeSb62uwq2r2asgqa5L5L0FVPz4P1rK6v/9OPl3/a3bVc+Rdxe0ZjsCiEWp/du9ZP38Vzj+jsPEVjIbJC2rj4kvAMMnIkNGmxWtXh/uivdNqrS2vD6TAu2Nf7UU6frlkJYNk04wAaunzxSBUAYydkrP7/H6zfxce2lZOGddiy5faALk+OkdAq6TkkLqOV8iOP1YIu8vwjd6DE2ffET4qSdImT0XJ7Tv5iVVFS1ebXrSYFarLngKOecbu5E5Rzr/paKbXzRaeD14hw8n+tny1jKPBye1B/d2w62spObuO5LKYmtXEy8v7X5rUGe/YNmz6XvMBknL2gfE50/aTuCMmIi7cnHr4pj0bCR3IFq6tcO9rgqUlqL19TgZGThZHRMP9CXx+SG7EI49C4Qug7WTkQEBP/5IhMpf/JTYurUEph9H1nd/iNPF9pM+EWtCN6zoUKzbN3bInNMVcRw47Gh07Set52GmZyODR+zyXk92Djm//A2l11yOW10FHg9ZP/wZkrZ3QRLBpM3r2NhubwsedwJOdjZuZaUp8PpI/9q1thfZQ/JFO1lqypQpumTJkv5uhvUFp7EYROrQTavM/NegYWYOsLoM9+k7W68bcSSR4iqqfnsrxONIRib59z6If/SYXm2P29CARhpw0jP2OgBrPI5bWWGGloNBPBmZvdTKHj7fddFP3kY/XZBU7sy6EikY0sVdndSjCg11aGmxWcGbO7DLsyc73BuP41aU49bWIqmpOGnpe/2LgqrS8PqrVPzHjS1lvrHjyLvjnm6zMZmFO6WEn5+HW1ND2vkX4hQU4gTswp22RGSpqnYYerFB0rL2I9rYgK78wPyAVxc9+cvsOP+clsQDAL7DxpP3l3taEg/srdj2bVTf8Sdia9eQMnMWoTlnI46DxOph0yoYPHLP9yB2Q1VN70YET3Z279bdUGeSI1TsAEBGTEKmnL7/b0fZBbeulljxFsLPPYNv1CiCx5/UK6kG92fqumbParTRTAf4A2YKo5d1FSTtcKtl7UckkALjpyKjjgA3TqysMilAAsQ2rEva+N8TGgmb5ACxJgimmYU6mPR3pVd/lfg2M8wbXfkZ7s6dOPkFpEw9BinbhqxcDIcdA0ee3Gs/nNyaGiKLF1F7718Rr5eMG7+L//AJSfN25odj2GS48Xh3K8BJShrOjC+blbmOY7a/dLMi9UDhpKXjHzsO/9hx/d2Ufaem3JwH2hg2+1WnzIBRR/RJoOyMzbhjWb3IDYeJlZQQLy0x5znuAfEFkNQMJD0bJy0Np10vK3jiyUiw6x/42tSIhmvRRMYYjYRx338R96m/4D57D+7z94D0DGkAACAASURBVJpk34BbW90SIJuFX3wW37DhlN54PYyaaupYtaR1O0UviK5fS8X3v0101Qqaln9K2TeuIr5zR+t7iMegZAvu8/fiPvFH3NceaWlzT8QrKnDDEUjLQlIzD4oA+UWkkTDue8+2zgurmqPRmnrv3+Ku2CBpWb0kXllJzR1/ZMec09hx1kzqHrivx+c4qioarsX9fCnuivfR+mo0HsfJziH/ngfwHT4BSQmRMnM2WT/8WUsS8w71hGtx33sG98k/4776CFpZYnLGtj1SKlyLfvIWGot2Gmyd3Dzc2hrcinI03pyntPemZTQWo/6Jx9oVKuGXXmx93diA+9ojEK41r8u24b73LNq877MLbm0tDQveouz6ayj75tU0vP4Kbm0X6fg6tCtqfrko22a+/734S4G1h9w4VCefaINqh9zBfckOt1pWL2n88APq/mE2n2s0Ss2dtxM4eiqeya3THBqLES8tof7Jx9FolLQLLsZTUAixRtxn72nJF6ofvYlz9teR9Cx8I0eTd/vd5sSQlJSuA2RTxBzhtHmVKSjfjvvSQzizrkC9PpNqLRFktLociUWRUCqpF15C/eOPmnu8XjKv/za1D/0dvF4kkNgvOfKIzreH7AmPB+/QYR2KvYcObX0RbeyYpahkS3KqvU7Etm+j/Mavt7yu+I9vU/DQY/gnTOr2PlU1369X/tmSUECmzoLOTgKx9h2fHykaZdIsNvMHu03m0NtskLSsXqDxOA2vvdyhvGHBmwTaBMl4WSk7LzgLrTfBsO6Rhxj47MtIxZbkhNqxJnTl+zBlBuI4PVvYEotB8ZrkMjcGjgfn1IvN/Jw/gLvkVXNqRSAFTzBExg3fIfWiLxPbuAHPgIHUP/4ITcs+IeuHP0UaqpGTzkcGHNrtRvzdISKknnM+9U//m3jxFgB8Y8YSnDq99SJfwAT1tkExbxDsIq1b+Pl5Hcrqnnyc7MMndp+QIVKP+8681uepootfMntbbZDsN+ILwJTTzSK2LashIxfnuLP26YkrNkhaVi8Qj4fgtGNpeCE5f2lgyjFJr8Pzn28JkAA0NhJ+63VSDxvasdJ4tGNZdxyBrPyWFZ0Acuxc3MUvQ3EiL2swFWfmV822k0TQ8GRl4cnKwjdsGG5lJelXXEXmDTchaelIKLTLbD9ufT1ufR3a2IgTCuHk5O7yHk9+PgV/f4TY9q2Ix4tnwIDkbQz+IHLS+eg788zQWkYuzrFnIYHufzj6hnXcx+gbMXLXGYtUOyZ3cOO77LlafU9S0mD6HLNgx3GQ4D7cc4udk7SsXhM8/mSCp800LxyH0HkX4B93ePJFnfywjhcXI0PHJSclF0EOm7pbB/lKMBXnuLNbh6JCmUggtTVAAkTq0eXvoZ20Q7w+PPkF+EaMwlM4ACc1tdvgoqrEKyuof/oJdsw+nZ1nnUHJVy8mXlzco/Z68vIITJiEf9z4Dvv81HWJVtQTnzADPfZ8YoWH07RlKxrvflVv8IST8LXZQ+odOozQmT04PaU5yXtbaVk9Oo/S6nviCyCh9H0eIMHuk7SsXhWvrkIbGkDE9KraJfWO7dxhhltrzYIUCQZN4uuBgyBcg65YZOYex08zKzN384e0unGINEA0Av4gumMT+vaTyRcVDMGZPhfJ2rv9dVpXRbykxOzjbPNzJHD8ieTe+rtuE5prPGY26q/+yGzvGDkJUtJafimIl5aw49xZSb1uT0EhBQ8/gSev+6w58Ypy4iU7wVU8hYU93keo4Tr0w9fQresgpxBn2myTzNz6QrD7JC1rH/BkZkFmVstrjYTNafbb1sOQMXgy8yh8/BnCzz6NNjWRet75ePILzRFK6dlw9ExAdytPa1vieCCUBiQW9xQUoY4naV+lHDIWd9MqnPRpiKfrHwEaj+PWVCM+H05aeksGmuYhSK2rJl5VmXy6CRBdvQqNNEJ3Cc3ra3Cfuau1rhWLzCkoqSawalNT8rA0EC/Z2Wa1bdc8ObndZqDpioTSYOosJNpoAnc/bxvRaJNZvOQPdPv3ZPUt+523rD6i0Ub0k7chHkNGHoFWl4HXhyczg4xrv9npPe2HVzXa2HpUlT+42z1LAqk4Z1yGu/Q1aAwjwyeag4PLtnab8zNeVUXDKy9S/8S/8BQUkPndH+DNy8Fd8krruZOFh+I/9iwIBqHNntDgcSd2m6dUXdecsNE83+d4TM852oTWVZmN/ykpeA8dRmzThpb7/EdMRgJ9u4imfY7d/qL1NehHb6Dl25GiUTBuGpKy74caLRskLavvRBvRmgpkxATc+X83KyYBmXSi+aHn7z5jiEbC6IevmyTbHg8y4XgYM3mXi1faEq8XzcwzGXxE0OK1sOZDOP2raHkZIEhmBk6btmg8TsMrL1J1y83mbXy+Ere2jrxf/AyK1yDjpiGHjAYEDVdT8MA/qfjB94htLSbl1Blk3nATTsouemFtep9y7FzYsQl3XiJnbcEQnJMvIO8vd1P5q5/T9NkyAlOOIeunv8CTdfAPf2pDPe6rD0NVqXldVQr11TBtzi7/zVi9zwZJy+orCs7oybiLX0oKCvrpAmTUkbCrIFm8Bl3zkXkRc9GP3kAGDoX83Vv+LsEQFI1CK3aaw5gnnET1n/5A+JmnkECAjOu/Teisc1sSkbvV1dT/+/GkOjy5uWjZVmTabJMm7OV/miHcQw/Dd+TJ5P3v7yEjBycl1ZwG0l17HAfGTTXvLSUN8flx137cekHJFnTNx3gOP5ac3/0RGpuQYBAnfR8eSNmfYk0tAbKZblyBTDljl/9mrN5nV7daVl/xBSAt08zjtaXaZe5VjTahkXrcaKPZF9b+69s2dHLXrklKGs7gEcghY2h48w3CTz4OsRhaX0/1b28lvn1b67V+P57CwqT7m1Z+hhwy1pxU8tmi1vZvWolu34AzdCTewoG7DJAtUjNwzv0mMuE4tH1GFTAHUMdjeDIy8eTnf3ECJIDj6TgUnpJmjsqy9jkbJC2rj4g/gIbSkWHtklFn5nWavUbrq9FFL+C+9A/TcxjYmpVGDzkMPeEi4hmDiJeVorEY2tREvLSEyIdLiG3ZjFuz69ym2tBA5M3XO5Q3LnoPd9UStGwb4vOQ+Z0fIG2OdvKNHAWBENpmD2ZLndvWI7s407A98XhNbtoxRyFFIzt+/ZCx5nDqxkbipSXEtmw273sXW0D6WrymmljJTuKlpWh0N/ex9pQ/gBxxYutrEWT6HNiNYXar99jhVsvqAxqPm4UydVUw+TRIzUS3rEFyByBHntJhEYY21JkhzJpEr+q955C516BDxqA4NEUCVH75YjQSwcnOJu/O+xGvj5LLLkATi2bSrv46GVdc3W1vTgIB/FOOIbLgzaRy/9gxZv9kfTVy3Nl4Dh3HgKdfJLp2DU5OLp6CAiQYhIHD0I/fSq5z0AiTHWdPhTKQ6XPQD1+HaBMyejJyyBi0qYnGDxZR8aPvmQOnCwrIv+M+E7D7QbyslIpf/JTGdxfgZGWR9Z83Ezz2BJxQ7wYv8QVgzBRk6Di0ptIcFB1I2a09s1bvsfskLasPaPl23PkPmCX8Hi8yfS4y4FCzQrWT1ZNaU4H71F+SCwMhnLOuJV5Xz85zZqOR1uTe3uEjyLjxu1R891ut14sw4MXX8Q4Y2G3b4hXlVPzshzQufBc8HtIuuoT02TPhw5fMBamZOHOu6vSAYY2E0VUfoMveBXWRoeOQY2bu9SZvN1xv5uIAxMFJzzR7Jc+ZhYZbt4J4R44m/+6/7dEWj71qXyRC9e//h/p/Pdxa6DgMeP5VvAMH7dO2WH2j3/ZJiogHWAJsVdW5IpIDPAYMBTYCF6lqZeLanwBXA3Hg26r6UqL8KODvQArwAnCTqqqIBIAHgaOAcuBiVd3Y1+/JsrqjkXrcRS+0JuiOx9B3nkbOv7HrZNker8nG0/aXVq/PnIXY2JQUIAFi69d1XOmpita3m//EHORMrAlcF3x+PDm55Nz6O5P0AGDzZ/DxK21ucCEeN/d5fNBQa1bYBlKQoeNg3DSc0ZNNW33+vc7pGq+qpPb+e6j75wMQjxM49nhyfv3faENDUoAEiK1dDf0w5Kr1dTS+vzC50HWJbdpog+RBbl/0328CVrZ5/WPgNVUdBbyWeI2IjAMuAcYDZwJ3JAIswJ3AdcCoxMeZifKrgUpVHQn8Afjvvn0rltUDrgt11SbAZeW3ziU1NXV9j89vtng0a56HCqYioRBOuywzgSlTcdtttndy83DaJDKARM9vyau4T/zJHJ/1ysNouBZPVjbegYPwZGUgZZtNm5sfPW4a+ukC3PdfhNoK3KfvQD9dgH7wMu5z9yZOD0k3Z152ESA1EjYZbCLhXX67Yls2U/fg/S3Br/G9d6h/5ikkPQMnOyfpWv8Rk/tlH6OEQvgnHdGh3DvkkH3eFmvf6tMgKSJFwBzg3jbF5wAPJD5/ADi3TfmjqtqoqhuAtcAxIjIQyFDVhWrGhh9sd09zXU8Ap8kuMxlbVh/zB2HSyehxF9LoKSQ+9iSYey14HNwNn6FVpS3nImpTBI01If4gMm4qzrnXI6ddgvOlG5GCIYiIOVPyr/fjGzMWRAgcM42Mm76HpKeTdtnX8BQNIXjCyRT87Z847Ychq8vQttsrKnbgrvwAdePEq6oIv/QS7tjjYeJJyIiJyMkXgteLrvkICaaiy95JCqA01KE7NiY9Qhsb0JItuAufx924Eq0px339MdzH/4D7+mNobWW3366mTz/uWLZkMfh85N15b8uxWv5JR5Jz6+/wZGV1uL63aSyKNtSZD1WclBAZ3/oOvkQuXgkGyfrZLzv8UrLbz2moR0s2425dZ86y/IJNfx0I+nq49f+AH5KcoKpQVbcDqOp2ESlIlA8GFrW5rjhRFk183r68+Z4tibpiIlIN5AJlvfw+LKvHxOsjFnYpvexLEIuRMmsOWZddjLvEzPkpIEechBaNRj98zSQHOOIkSM1EMlOQzORAJx4PvpGjyP2/O4hvLaZp5Qoqvn8TbnUVobO/RP7df8dJT+80V6qWbetQRsV2tCFMw+svU/Wr/wLHITB1Otk//yWy+DmoTvzvI4K6naSBU7fNpy66+XP0vWfNLQMOxX3j8dZ9fqXFuK8/hnPGV7vMGNP+pBSA4Emn4oRCeMaOI/++hyDugt+3T5IJaKQeXfae2ccZSEGmngmFh+AtKCTvz3ehkQji9Zqe7q6SJnT3nOakAYkVwxoI4cy9xmwbsvYbfdaTFJG5QImqLu3pLZ2UaTfl3d3Tvi3XicgSEVlSWlrayS2W1XviFRVU/fevzfmOQPrFl8Kyt5Ou0U8XILEm2LYe3bA86cDlLolQes3lVP/vbcR37kAjEer//Rji9XWdTDx/iPkzlIGMm4ocfhwUjUWjccJP/dt8zXVpXPgusfVrk46G0s2fm7nHtoMzgZSkrSk0htFPF7Q2MZTeYSM8VaWtOVojYbS0GHf5QrR8O9oYxjNwEJk/+InZcuL1Ejr3fFJOP6NlNacnNw9PQcG+CZCui25YbhLNRxuhrgp9/TFIDBt7cnLxDhqMp6BwrwIkgJZtTTrWjMYw+tlCk/zd2m/0ZU/yOOBsEZkNBIEMEfkHsFNEBiZ6kQOBksT1xcCQNvcXAdsS5UWdlLe9p1hEvEAmUNG+Iap6N3A3mNWtvfT+LCuJxhInW9RWEq9o/WcowaA5E7Gt9j20WBO6czMyvN3RWm1IMIXgiacQefuNlrLQ3HOQbrYgqD8IJ12IkxIyq1JjUZzBI9CAD0/REFj2Scu1NX+7n7xf3Yy+8ZgJavXVKOCc/XV01QcQCCGjJ5uN7V2JNkEwNTngB1PB8ZhctsvfQz8zC2AUkMmn4hx2DKkXXELojNmgauZgu8n92qeiEXRjYglFVj5aOAxxY2j5jt4/EaS+pkOR1lcjrgt7lt/e6gN9FiRV9SfATwBE5GTg+6p6mYj8FrgCuC3xZ/NR4s8AD4vI74FBmAU6i1U1LiK1IjINeB+4HLi9zT1XAAuBC4DX1Q7qW/2lrhL32XuQQ8eTetY51N5/DwCR9xcRGjIatnzeem3+YLS23e9zwe57Jk7AS/b3vkd48mQaP/yQ4LRppBw7HfF2PQ3vpGWAI7jz/tqSJcctXoNz5hXk/Oy/KN25g6YPzZYoJzUVDWWa0zgawyYYBlLMvr2ps5LOltSGerOoB0EmnoAufw/yi3B3bsaZPgf3nadNwPT5cU4635wk31CHrng/qX366QJkxEScUDrkd38E1j7h9SM5hbjZg4m5Aer++TCSlkrGdYch0Sji673zJaVoJPqBk7xoauzRXa+AtvpFfyQTuA34l4hcDWwGLgRQ1c9E5F/ACiAG3KCqzWu9v0nrFpAXEx8A9wEPichaTA/ykn31JiyrLY1FcT952wSiTctJO/NsnMxMGl55mWhxMc55N6GZOeiOTUh+ETJ+Ou5LD7VWkF2IZBd2/QAww7dvP0aoaCShMWdDbQW89RhccBMai5reapM5R5JACPF4EK8Pt3hNhzR4+vkSSMsm/09/oXH1Gpz0DDxpIZh/H25To1ltO/LI1swvsSgqgnh9Zi7ttUegfLup69QvEy2aTPi5Z/CPPYyUEUfinHu92Xbi9bdshFc0aT4TSBre7dH3OdoEsUbA6ZNTMcTjhQknEF/2CWXXX91SHnnjdQrnvYi3cEDvPSyYhjP7atwPX4doI3L4sUhu93tcrX1vnwRJVX0TeDPxeTlwWhfX3QLc0kn5EqDDOJSqRkgEWeuLQSP1Jq/nzs0mdVlW3m6ditF3DdPWH/iuC4vmESoaScqtt+HkFAAujDwSZ8zRaCAIjhdn5lfRnZtMQMsp7HTzfhKPBwIpsHVNa1l6NioOFK9FFzxlgqHPj3P6l9H8ItP76+z74w+a/Y8lWwhOnmIy/rz4d2hqNF+PNqEr34fxU6GqFHf5e2a7x8QTcJsaWgIkRWNoePc9qm4z/9uG50H9c/PIu/2ujhv+vX4oGgXFre2X4RM6TdHX6bc4Uo9++Aa6YTmEMnCOnQu5A1uODzP7QaNmDtXnNz3gPaDiUPvow8llkQYi7y0g7bze+3EjXi/kDsA56UsmMcP+8O/Y6sDmObIOGNrYgLtoPvrG4+iK93HnP4Cu+djMBe5OPW48aXl/bxCfH6ftPkdVKC3Gk5uPk5qGpGbgZOYiaZk4voDp5aVm4AyfYBKP7ypAAgRDOCdfaAIlQEoazknnIyj67rzW3mK0CXfB0y3zgjJomDnQuZk/iIyYhG5a1aYnpx0TsWfmIXXVJnhuWY2u+xT32btxfEGzBxTQwuHUPvj3pNuiny3Hrek43yaBFJzjzkKOPgOKRiHTZiNTTu/R8U8ai6GfLTIrTmPRxEkk/4DmrTSJBA7uE3/E/fftZnVq4673aHbK4+l0a4eT2TcLh8QftAFyP2Zzt1oHjmgTbFqRVKSfLjAHCXt7ttBDG8PoumVm8YjHixx5CgwesddZYwDIzMM561p0xWJICSFjjzaLVnZDvLKC+NatxIq34J90BE52Dk7QtE0cD5o32MwZxmMmG04wZM4abM7uk5aFTDjObCNx46iqOQFk1pVoSTGEa5C8QbhLXzUJCwYNN/f5AsjISeiq1pSNMmIC7uqlMOBQCNeZvLKxqOn9FgyBHZsATV792szfee9Qgqkw9mhzVJjXR4+3NUcj6ObPk8vcOFpTDqF0E/A3rmgtX/aOSZxesPvBx/EHyLj66zS8Mh9NJGzwDh1GoJNkAtbBzwZJ6wDSSa9PtfPyrmoo3Yp+8HLr67efRM6+zgw/7iXxByBnABw7B5CkhNQai5n9daFQl4mq41WVVN76KyIvzzcFXi/59zxA4MijWp/h8UAo+dgo9fogLQtcF+fE83A/eBkt3WqOozrhS2jeIHPEVcEhSH01+vkHSHYhctTpuLUVOKF0xOuHiSdCSjq6aSWSMwBGTMIJ15qDmjOyEV/A9FADKTjT5+J+8DLSUEXGN75F5c9/bBrj85F/13143AbcD142v4DkDDRnWja/B8cBZzcXp3h8kFXQmgC+ua7UTJP2b+u6Drfojk1IwZAO5T163MBBDHjqBSKLF+Gkp+M/fCKe3Lw9qss6sNkE59YBQxvD5od0mx+IMulEZMKxiGfXqw41HkPfmYduTO6NyhEn4Uw6sYu79l68rIy6xx+m6ZOPSTl1BikzZuJpl24NILp5IzvPPjOpzDfucPL+cnen1zdTVaitREu2oOuXwfY2Z076/CaLTygdrdiJ+9ojyOCRpke4ZTWkZ+HMuKxlEYy6LjQ1mMC7YzP62iOtdQ0ajow6EskdRLy23hyEnJqCNsaIbdlEeP4LhObMxVu9xWwZSZBxU2HSiUgsBuGaxMKi3R9i1Loq3PkPmp6zCDLheFO3P4iu/hBd9ELS9c6sryEFRV3UZlnJ+i3BuWX1FgmEcI47B926xgz1DR2H5A3uUYAEzGG2uQNbh+Wa5exiVeleiFdUUP6d62la/ilgzm2Mrl9H5k3fw0lJDhIa7jiH5lZVogjxslLcmhqzhzCUmnQcloigqZlIoaALn0+uINpkPpqFa828HqA5A2HCSUQ3bEDS0nEyMvFkZaEIRBrQpa8m17VtPTJlBjsu/wrxDesIHHcCOf/vNjw5ufjHT8A/fgIarsF94unk97XqA5yxx+A+f2/LHKKMngxHnpLUw9wVScvCmX2VWd3q8SUnVz90LOzcjG78DMRBDp8OGV3/YmFZPWWDpHVAkZRUZOQR6IhJPZ/Par5XBEZMRNcvh8qdpnDQcCSv73ob2hBuCZDN6p/8FxnXfB3aBUlPXj6egkLiJTtbytIuvwrqatl51WW4pSUgQtrXriX9iqvxZLamL4tXlJsMPrkDobRNFkePtzUheEqaGbKsKjFzmYcdT8n138At2WnS582cTdYPfgwr3sWZeLzZbtFOvKwMd/tWABrfXUDkzddJ/VKbFZ/a8p82ZWr2XTa2nmSiqz9Exk0z7dgNEkoDOs4/SzAVps1Cjjotsbo1YPcbWr3CBknrgLSneewlJQ1nxlfMfkIRs9JzN39Q7xaPp8MRWE5q54uMPHn55D/8BLX330N0xTJCZ51HysmnUvmrn5sACaBK3f13k3beBZAIkvGKcqp//z9EV35G/h9vh6XzobbSBIrjzmmZb5WUVJwzvoLu3Iz6gsQr6sj5r/+HBINE162l+ne3Eb/0y3hzB6KbVyGjjkQ/frO1gRk5xGtqWg55BmhcspjQ2eeZ7QxgencjJiUlVZeRR5htO+1ouNasum1ehRroer62J8Qf7JW5Zctqa7eDpIhkA0NU9dNdXmxZ+yFJSYU+2IjeGSc1ldSLLqX+sdZ9d5nf+yFOu5MstDEM9bU4FcVkXXM16gsiqem4FRVE13dclBLbvg0nOwsQ6p+dR9q55+K59lrU8cCRM3EyM4mXl+NkFeI07yNUNcHajaMSoOLH1xHfanqdwVNOI/uXvya2tRjv2OHoqiXI2CnI9DnoltVIRg6MOorKy7+S1I6UM2a1BEi3rhbcODJ+euvq16KRyIChLUO8Lbw+JCMHXfcp+onJaysTT4BDxyKBvcuJalm9qUdBUkTeBM5OXP8xUCoib6nq9/qwbZZ1wHPSM8j4xo2E5p5LdOUKAlOOxsnPb9kADyaLjH6+FP3oTfMakKNnwOijkIx0Uk6fSd3f7mmtNBDASU+n5i9/JPWrV5J6ysmw9EVYVWFO7hg1hXhsKOr48bTd7xeuxX32bnTwaGoXPNkSIAEib7xG6lnn4Rs3Dl31HjJiIvrOPMgfjBQcAk0RNK6kXngJNXf/BaIx0r56Jf4jjgTAra8nvq0YZ9NH6LZ15r7MfBOU/QFk9JFmFeq6T82q2+lzTG7YxOkhALrwOSQrzwRYy9pP9LQnmamqNSJyDfA3Vf2FiNiepGX1gCc7GycrC/9hY3Gra9HaWuKRCJKZieMPQLQR/WRB0j360ZvI0PE4oXTSv3olGq4n/OLzeAcOJONb36H23rtoeO1lUmbOxqnaADWJPLCqyOoP8IydDOnJC1d07cdmXjAQIrZhfYd2xqsqCGRmoJU74ZDRyPHnous/haaI2XuZlkXqxV8mNGsOgFnsk9jD6dbVIj4vbEv0eku3mm0om1YiA4eaZAkTj0fGTjELa4Ih3EUvdmiDrlu2x9s2LKsv9HQCwJs4seMi4Lk+bI9lHXQ0EkbXLye+dQtl11/DjtmnseO82UTefB03XG/ymbbLrUos2jKP6cnJJfO7P6DwsSdJvfjL1Pz1zzS8ZvZ6uiU7Oh5NBWh9Tes8YbNGM5colTtIOWNm8tcch+DUY80K0rOuhUEjkdwB5lgsx8F9+0moKcfx+80Co7z8lgAJoE1NdL5ftbVMPF4kJa11DjivkzylnZVZVj/qaZD8FfASsE5VPxCR4cCaXdxjHcQ0FjUnqYdrO10F2R/i1f+fvfMOk6o6//jn3Dt9Znul946ggGDDBvaGDcUSTdRYEmM0GjXll2oSEzUxPZaoGE3sBbvYUURBpCm9w7K9TS/3/f1xZmd32AUWYWHV+3mefXbnzD33npndnfeet3zfBhJrVhF+43WSW7doA7QbSDKBhJqwKtYhTXVaC3QPkWQcWTwHqa2k4U93kVih2zBJMEjdrTcizUFwOKHX4OyJ/UZkaZoaHi/K4aTxzttJLFuaGY8u+KT9XGWgCtp31FDDxoMyYNs6vAeMIPfq72KWluEYPJTif9yPUViIMgxtyEwT67X/IAveQFYsgJqtWG8/qbt/dIDh9ZFYuxbK+2dfc9Rh4Ow4mUb1GgIlbTKLS3qheg/p8Fgbm/1Fp9ytIvIE8ESbx2uBs7tqUTbdG4lFtGbqonfBSmqJsQOP7tos0V1gBZtpfuA+gg/epwcMg6K7/4Hn8MmdypgUEW0IXv8PWJaOC449EkZO2jPJungMWbkAOfA44osXZT+XSpGs2oYpFuYhpyAVa5Ca+ntXAAAAIABJREFUClROPmrwWJQ7+7oqN4+8H9xCwy9/mhlz9OuLMfxgJBZC1i0Dbw7qsFM7FjX352jZvCXvQ/UGAudfgO/Mc1GAEfCBpJBkUu9AU8n2Wq4N1e13vGmMoiKcww/AioZQpQNQoVpU/1Go4p7td7Qtr8frxzh2emuvTZdHl3LY2HQjOpu4MxT4B1AmIqOVUmOA00Xk1126OpvuSXN9VqG5rFgAxb1g0JgvXJqxp1ihEMGH7m8zYNHwm19Q+vDjmMWdkBOLhrDmvpDV208Wv6dvAPbESCqld4TBetwHjSMyu1USD4cTs7CQ8Kxn8R1/PIZhosr6oMr7d2jkDLcb74kn4z3qaJIVFRi5uRg5OeDLQU06CTVuCoilVXNiYcRyZxl45XBBQSkcdhoogUQSUywtDF65QZeMTDxBF+abjvbNk/OKtSBDhy9T4ejVC6u5CSkqRXm9GO5dC5crj3+39W1tbPYlnU3cuRe4CfgXgIgsVko9CthG8muIVLRP+pBNK1D9R2rX4f4gHs+qRQRI1dbQaV1XoX2n+Lbtr74obh9qwlRYMJu8624Alxv3qFEYhYWYpeWwZTk5F1yE9epDSHO9vqzHj3Ha5eDLzTqVxCKo+m3IigU4cwtR/fuRrKqmeeaDuMdNwHPAKKxXZ0I0pHfCY46AkYe0K6lQDgdiWUjdJli3FCo36CcSMeT951Hl/cCXg3HsdKy3ntA7ykA+xtHn7LKHo5GTu9PnbWy+bHTWSPpE5KPtdgl7+Olh82VFlfZtZ3pUeX+9+9hPKJ8Px4CBWVmbvtPPRPk6uUtxulADRiGr27hEA/mtajVfdF2GAX2HoYp7IkDBddfqAv14JSq3D5ZvGMFnn8Yz/mhU7QbU6k+0kVu9WBu5NCKCbF6lyzLQNl3WL4PhRxF84F4chQVYkc1ZOz9ZPAc1+MDW1lptiUchFtGdQbZDGmsxAvlIUU+MUy/XLtaWnaWNzdeMzibu1CilBpG+LVdKnQNUdNmqbLo3ecWoYQe3tkjqNRjVf9R+c7UCmEXFFP/z3/jPno5z5Ghyv/N98q65DsPXuTipcrpQ46boQvjcIug3AuOEizvX5zGNpFIkqyoJv/4K0Q/fJ7FuDdGFC7CaQ6j8EpTpRF57WBfZ121DPngBaiuIvPwilTPOJRExWhNfYmHtNm0hGkaWfZh9wVATygSjsAizV692HTKA9nHFFhxOSCY6FABXebpZsjIMlC8HFcjXyTz78fdrY7O/6Oyt/3eAe4DhSqktwDrgoi5blU23Rnl8MO5o1AGHaZekw7lfk3ZacJSVk3fTj5BIGCMnd4cJIztCef06AWnUIWA6O9UMuC2prVuonHEWEtSGyTlsOHnX/5DaH1xL0d1/Q1Wuy4p5AqjKNXiOPIr40sU0/uXPFP/qF6jKDVrKbfl8GDhav7dKdezKNh1IIkF03jxck8fBmjbKNi0ttDp6rQ4n9OgPBSXazVu5Ue+mDz4BXF2jeJMKNqMczqzSERub7k5ns1vXAlOVUn7AEJHmrl2WTXenu+pkGh4P7MGHsHI4Ot3AuS2pYDNN9/4jYyABEiuWk6quwmpsILVlE45AB+5Kj59Ura6mskJBrUZz3IVatQaQz+bB2Mkojw9j/BQdc0zHXqWkF8maOqS5ifBzTxM4dzqmaSAbPgN/nla12Vk7Kn8emE6Mw07TRtgwwO3f7ZuLXWE1NRFb/CnBRx7CKCwk98rv4ujZa69fx8amK+hsdusN2z0GaAQWiMinHU6ysfmakGpsJLH8M6y69u5Oq6EBwx/Aqq5C5Q9ESnq3dunw+JE+owi/dBsAgfMuwLBiWO+/BqFGjBMvwXr3GdTwg8EXgMJyjGnXIJtXQU4BRkE5yRUr8J1yOs7RYzAKilH9B6LGTgbD2GU5hVJKa9h2sY5tbNFCaq+9MvM4+vablD/zEmZp17Uos7HZW3T2Vm5C+qtFaPEU4GPgKqXUEyLy+65Y3FeZVGMDWIKRn2/HeroBEo9qlRtFuhtFx6UOHWFVV9H4xz+Qc8m3iM55NzOuPF7cBx5E88z7cfTti/XuM3p3589FEnFUoIDgSy/gHjMW7/En4B46EJk7S+8UnS6dWevP1Ts8dNwUZ6FuNJzGM/5g3AeOQ5lt1uvoPi2irOZmgv95MGtMQiFiCz/Bd8JJ+2dRNja7QWeNZBEwTkSCAEqpnwFPAkcCCwDbSHYSKxImsfxzGu++E4nFyPnWt/FMOgQjN2/Xk226BImEsOa9DBuX64L2iSdA76GdjknGliwisfwzUpXbKLjt94SfexojJ5ecK64muuAjSv95H3z2HsTCWHOexTjzuxg+7dINnH0evpNOQ9VuQt59OnNONWYysv4zjEkn7TLem2UguxsOE6OgoN3w9l1QbGy6K501kn2BttpjCaCfiESUUrG9v6yvLqmqKqovuziTwFF303UU3zcTz4SJ+3llX0/ESiHLP4YNWi6OWAR571nUmd+BThpJ1wFjAGj80x04Rx+Ad/LROEeMxMzPwX/EIfDB8xlVGXXQ0VnnVQ4HZm4u4h6IOuMqpG4bqrAcEQs18ICdxxS/BBheH7lXXUv0nbeRiO4b6Rw2AudgW37O5stBZ43ko8CHSqnn0o9PA/6bTuT5rEtW9hUl8ubr7TIcQ4//F9eYsbojhM2+JR5DtqxuNyx123QPxZ0gsQjEIph+L3nX30TTP/5CYukSzIIifMcfB68/hDrsNNSJl+jzFfUAbyCrTVYLyu0FtxeVrzVXv0oOeEev3pQ/+xKxBR9jFBTiHDoMs6gTKkg2Nt2AXRpJpQNmDwIvAUeg/3+vEpH56UMu3MFUmw5w9O7bfqxvP9R+LMT/WuN0oUr7ILXZZb8qv3Sn0yQRQ1YtRBa8AYBv0EF4n34B4jGo24Ka97zWgP3wZdSZ12AMGtNlL6G7o5xOzLJyfCeftr+XYmOz2+zyk1lERCn1rIiMR8cfbfYA97jxOIePJLFcb8DN8h4Eps/o3nGlrzDKdMDow3Xvw5otYJha2HxXGZ/xGLLwrdbHaxaitq7COPQUrCXvtI6X9t6vSkT7klRjI1ZNNfFlS3CNPgCzuBQj15aps/ly09n/3g+VUgeLyMddupqvAWZRMcV/v5dURQUSj+Ho0xezuH1bI5t9h/IFMKacl85uNcDlRjl34fq2Uu3c5kRDWgTc44NoWJdsHHpqO+3UryJWJEL42ado/GNrDl/eD3+E/6zptniAzZeazhrJY4ArlVIbgBDa5Soi8vX1Ie0BZmERZmHR/l6GTRt2u0WTwwX5pdBQ1TrWdzi4vRinfVsbUNOxS0HwrwrS3ETj3+/OGmv6y5/wHXfiHok72NjsbzprJO2CJhubNiivH2PqDGThW0jNVijrh/QYSuSDD3CPm4CZ9/Uq6dHtubIT3SUaydaftbH5EtIpgXMR2SAiG4AI6QYEdLoHkY3NVxPlz4UDjiTm6U3Tm/OoPP9c6q7/DrEP39/fS9vnKK8X9+GTs8Y8Rx2D8nz1Xc02X206K0t3OnAn0BOoAvoBnwOjum5pNl8HxEpBKpkVAxQRHd9LJnTSi8vTYdlEl60pEgIrqRsMe/w7VUSKLVxI3S03ZY0F//sw7kmHYX6NCubNvHwKf/lbgo8/SuyjeXgOOQz/Oed/7XbUNl89Outu/RVwCDBbRA5SSh0DzNjZBKWUB3gXcKev86SI/EwpVQg8BvQH1gPTRaQ+PedW4DIgBXxPRF5Nj49Hl6F40aUo16Wzbt3ATGA8UAucJyLrO/mabPYzEm5Gln+M1FWiBo1B9Rig1WWa67FefwSCDTqud+gp0He4lmXr6jU11mC9+bhuOxXIxzjmXCS/VPeF7ICOlGOMgiKU8+uR0doWs6iY3CuuQS64BOVvL5QuqRTEwrq5tdevb366oUi+jU1bOttPMiEitYChlDJE5C3gwF3MiQHHisjY9LEnKqUOAW4B3hCRIcAb6ccopUYC56N3pycCf1dKtdRF/AP4NjAk/XVievwyoF5EBgN/BG7v5Oux2c9IJIj16sPIkvdhy2rk3aeRVZ8i0TDW3Be1gQRIJZH3Z2UUa7p2TSGst55o7csYbMB64386U3UHr8H0u3CNPSgzprw+8q69HsO/+51EvgoohwMjL6/jDh8NVVjP/B3rpX9jPfUXfYO0D36vNjZ7QmdvdxuUUgH0zvARpVQVkNzZBBERoKVvkDP9JcAZwNHp8YeAt4Gb0+P/E5EYsE4ptRqYqJRaD+SKyFwApdRMYBrwcnrOz9PnehL4q1JKpa9t052JRdo1CZblH6EGjIL6yuxjxdI7EP+e19xZsSjS1ITEYiiPF6OoqNWdaqWgsSZ7QrhZC43v4DWoBa9S+KNbSdbWY9XW4jpgDEbxzoUIvo5INIz1wQuQbFW3lE/fQQ0a2y1brtnYtNDZneQZ6KSd64FXgDVoabqdopQylVKfouOYr4vIPKBMRCoA0t9bPlF6AZvaTN+cHuuV/nn78aw5IpJEt++yayu+DHTUZcPhQgwDyvtvN+6ETpZopOrqiC3+lMhbs0lWVSLJROY5KxIh+t47bDv9RLadehxVF08nuWF9mzUZkLOdFJ3HD6aJJJNIIpH9nMMJsTDqw+dwbl2EW2pQi99AmZ39t9o1IkKqvo5UQ8NeO+d+wbKguT57TAQStvSzTfems9mtIRFJiUhSRB4SkT+n3a+7mpcSkQOB3uhd4eidHN5RdoTsZHxnc7JPrNS3lVLzlVLzq6urd7Vsm32BywN9hmYNqYOPQ3kDGBNPgJ4D9WAgH2PqBeD2YoWCpBrqd1hWkKqro/aH36f6G+dTe/13qTzjJJIbN2ael+Ym6n50U0ZoO1Wxlfr/u5VUffrD2+PHOO4CCKTjjN4AauoFpOobabjzd9T/+mckVq/CSs/H6UYNTkcdQo3QUIUx8YS9VhuZamok8vor1Fx1GbXXXU1swcdY4Y5dv90epwvVb3j2mMdv7yJtuj2dzW49Cx3vK0UbphYxgU75v0SkQSn1NjqWWKmU6iEiFUqpHuhdJugdYp8203oDW9PjvTsYbztns1LKAeQBdR1c/x7gHoAJEybYrthugPL4MA47FamvhoYqVM9B2igpBb4cjCPP0m5OpRCnh9SmTTT+6Q5S1ZX4zz4P77HHtcseTW7ZRHz+R5nHEgnT+Je7yP/JL3EUFWkDE49nzYkv/wyFIA3VyKpPIZCLceIl6UUapJqaqTzn9IxhDb/wHGWPPYsxeIhW0hk/BTX8YKS5DlXcs9M73s6QWLGcuh9en3lcfcUllD3zEka//nvtGvsK5XTBuGPBdCKbVkBuEcYhJ+3V98vGpivobEzy98BpIvJ5Z0+slCpBJ/w0KKW8wFS0oX0euAT4Xfp7S2eR54FHlVJ3oUtNhgAfiUhKKdWcTvqZB3wD+EubOZcAc4FzgDfteOSXB+Xxo3r4oUf/9s+1kXKzqquouvAcJBQCoGHZUkDwTzsnK+vUqm93f4RVU4NVWQFFRRh+P45BgzFLSkmsWY1VXYV/2tmoeBDrlYcyc+SzjzBO/ibKGyDy7DMZAwlAKkXzww9Q8JNfoJxOnY3r8aGKyvf8DWm77nic0BP/3W7QIvLmazi/+e29eq29gcQimZuaHZXNKG8AJkxFjTlCZy3vZ7k+KxpFmpv02vwBDN+Xuy2ZTdfQWSNZuTsGMk0P4KF0hqoBPC4iLyil5gKPK6UuAzYC5wKIyDKl1OPo1ltJ4Dsikkqf62paS0BeTn8B3A88nE7yqUNnx9p8xYivXJExkC2EnngM7zFTMQtaY4iu0WPxnnwq8U8Xktq6BQDfyacRfuN1HP0HgmlScOvPiH78IYGLLkGCITyHTML66OWscxNsQOqrUN4AytNew1V5vdoYdCHKNHH0G9Bu3NGnX5ded3dJNTVhKAtr3kuwZQ3kFGAccQZS1KPDzjbK4dSx3P1MqrGB0JOP0Xzfv5BkgsC5M8i54mrMDhpE23y92amRTLtZAeYrpR4DnkWXdgAgIk93OFE/txg4qIPxWmDKDubcBtzWwfh8oF08U0SipI2szVcXs7B9X0eztDSrblIiIVRzFflnngCXX0Z8wyZSVdUot455SSpJ84P3EZz5QGZO3vdvAqdbJ5DsAO/kY2gqLsGq0bFs5fWRc9GlHZc47EWUaRI493zCLzxHqkJHF5wjRuE+aHyXXrczSCQEYiEpIb74E1zxKm0gIVPjapz5HfDl7N+F7oTkunU0/eWPmcfBR2fiOvAgfMfbCpw22ezqP70lg1WAMHB8m+cE2KGRtLHZW5jlPXAfPpnY++8BoHx+8m76Eam6WqJz5+AePx4WvgmbV2bmuMZNIbRmLeFH/0PJfQ8h4TDBR2Zmnbfpnr/jO+U0jAOPwnplfesT/jxUgU66NoqLKfvv00TeewsJR/BOPX6fNQw2S8soffhxkps3odwuzLLyfSKML9FwG9epD5XORJZkEuoqsD58GcJNMPAA3MPHIq9v1xwomdC1pd3YSEbff7fdWOSN1/EeMxXl3P87XZvuw06NpIh8E0Ap9RBa5aYh/bgALVNn8zVBRDIycTtSn+kqzIJCCn99O6mKClI11ThHjiL69ps0/PpnAJQ/MwvVxkACsGwugbMvwX/mOZhFxSS3VUAqlXWIxNNOkcIyjNO/jaz4BAL5qIGjdfwMUEphlpQQOGt6h2tL1ddh1ddhhcM4ynvs9bZnZnExZvG+McoAEmrCeudJqN6iY4uHnw7l/bSbNBbGevVhXU8K8PlH0HMQFJbBtg2tJ1EKunl7MPe4CTRvPzbxENtA2rSjsz6jMS0GEkBE6pVS7VypNl9NJBpCNixHNq1ElfeHQWP2egsoKxZDmeYO3ZhmQWEm/piqrqLxrt93eFzrCVMojwejxdh5vXgmH0X0vdaGyL7TpqF8Pq0bW1CGOqS9q02SCa32IwIOZ1aySaqujrqf3kIsvSsxS8somfk/HOU9dvl6JZmAUBOy+lOd1dt/JMqXQ6qmmtgnC7CCzXgOn4xZVLTPdGslHsX66BVtIAGiIeStx1FnfxccTqShutVAtsz5/CPUuKnIO0/qMhjTod9H1y76ce5nnMNH4D9rOqFnnwTLwnP0FLzHdBgFsvma01kjaSilCtporBbuxlybLzESjyHz30DWLNKPt6xGtq3DmHwmVjBEctMmUODo3aedG1KiYf2h6nTvUHfVam4msX4twYcfxCgqJucb38QsLUOZHYgNtJzXspBwayJPYtVKnCV9UNWtWhRq9GFZNXhmXj4Fv/gN4ZdfJDZvLp6jjsF77NSdysdJPIqsXYIseFMrxfQZqpsop28QkuvWZAwkQKqqkuYH7iXvBzdj7MpINNZivXhfJh4qyz7EOPlSqq/8Fsk1q/Rr8Pooe/xZHH367vxce4tkAio3Zo9ZKYiEwJeLCuS1L0J2uogtXoo5+DDMslKMQC54/ftUkP6LYBYUknf9TeRceQ2IoLw+W4zdpkM6a+juBD5QSj2JjkVOp4MEG5uvIMk4snZx9tjWdViNTVRf/g2SG7WbzdF/ACX3zcQsLtHF/o01WoO1sQbVZ6iuJ/S2N0iJVSuo/tZFmcfhF5+n/KlZmCU7lnZTHi/uI44kNkcbqPrf/prS+2eiBjZC9WYYMBpV0rNddqVZWERgxkX4zzoH5fHutLsHAJEgMu+V1sebViKFC2DM4SjDJLl5U7spyfXrkFhspzspScSxFr2TnTAUbkIq1lPwo59QfZmu05RImKZ/30P+rf+H4ep6cXccTijpBZtXt44ZRmsto8ePGjER+Txdi+rLwRg/BZelIJFA5eaiuvkOsi1GTg5GTveNm9p0DzplJEVkplJqPnAsWkjgLBH5rEtXZtN9MJ1Zmpv0GkT41ZcyBhK0cYi89QaBc8+HaAjr1ZlanxWQNYu1QTjk5KwdpRUM0nz/v7IuJU2NxBZ+gu/4E9kRZl4ehb/4Dc3/eYjYvLm4J0xE5RZgFA9Bho7bacxUGQbK27l6OKnZ2n5s6xrUiAng9uE+eBI4HJBs1Xb1TTsbM2dXGhvScUZtKomZl4PZpy+pTXpHJ81N7VycXYVyeTAmnYQVegzqq7QH4PDTMjtysYDhkzBGTtK7TrcXPH5MpTLtzSQYSbcYa034sbH5MtNpl2naKNqG8euGy4M68Chk/uuZITVwNMm5T7Y7NLlhnf4hHs0YyBZk00o4YDKpeAqVmwuxKBgmRkH7bE3l23XSh1lUTO7V1yLf+CbK78dwufUONpVElBOlFFawGYnHMXJ30JViF6iiHu3ci6pHf102AhgFhZTcN5PGO2/HamoiMOMiPIcesevzOt0YYydjbVndaiy9AZ1Ru24Fjh49M0YycMllGPuwcbEK5GMcdxGkEtrYub0o00GychtNf7ub+LKleCYfRc7F38Rs6xloqtUdU5rrtbzfUWcjJb136ja3sfkyYMcVbXaKcjhh8FhUj/5IxXpUaW/IKcJ/9nRCT/4v61jfGemyWqdbZzi23S3lFhL9YA4qr5DkmtVE3ngN59Dh5F5zLfGVn5NcuQIAR9/+uEZ0rpe3Mk2U26ndoskYsnKh3v0NG4+VdNB41+9JVmzFP+0sfKecsfuF4t4AavwU5NN3dElEjwGo4QdndkiG14v7wHEU/eWfkEph5Bd03ijklWCcchmyaiG4vKi+Q7HmvoRx2Gk4hgzFyM0lcMllOAcOykyxImGsxkaSG9bj6N0HlZeHGdj77sLtk7JStbXUXHNFJlYaXLOKVOU2Cn78c4xAQLcYe/eZVgHzaAjrrccxzriqW5eB2Nh0BvV1U3GbMGGCzJ8/f38v40uPFQwSW7SQ5n/+FQyD3Kuv1W2i/AGseBRWLkQ+eUMbSpcHJp5K6M23serqCP734cx5HH37UfyvB4i89QZmYSHuCZM6VfIgIlC9Gev1R1GHnYIs+xBqK/Rzk8+j8pILkebWJP/c627Ef/a5mLm7l5whiTgk0tmtZlqGbi8h0TCybT2yYTnUbEEddDSq9xAEA6xU1g5Skkmi779L7Q3XZkpZ8m/5Cb4zzsbwdu1OM7l5E9tOPS570DTp8erbOgYdbsZ64k/t5hlnfgeV214IwsamO6KUWiAiE7Yft3eSNl8IIxDAe/hkXKNGAyojNi6JBIkVK0gsXoln8nkYAR+p2noa/vAHAjMupu4nN2edJ7lxAxKPk3PBxXp+LKJLTkwnKhZBGqtROYXa7de29i4awnrvWUjGUf48JG0g8QZIbt2aZSABws8/jaN3bxy9+uAcMrTT9XDK6YIdZObuKcrjgz5DUGXp7FW3T8dM08+3dDtRhoHVUE/9L/8vq9az4Y9/wHPscV1uJHE628VejaI2bnLDhKIemZsUQMcru3mGq41NZ7CNpM0eYeZrF6akUiCC1VBPzVXfymit5t38Y6JvzCY2fx6+06ZhFhSSTItKt6BcLq3m0lCNteB1yC1G9RyA9c5TIKL7pY07FoZP0DWNoHd2wXTpbtss1US8XXcQ0DWMyY0bqf/prZTPenWn2bOdRUS0q3fD55BK6obRnsBuxeGU6QRvtjERy4JIM7L8Yx27HTERsQSrbrvudLFYluHqKoxADrlXXUvTX9MyboZBwU9+gZGuW1UeH8aRZ2G99Tg0VIMvF+Pos8FtC4bbfPmxjaTNbmGFQkg0ipGTkzFuqapKgo8+jBUJE5h+QZYYefDB+ym8426a/nY34WeeIvfa71N38w26CS/gP3s6yufXO8OXH9BuxhGTsOa9nBXTlIVvowYekEmawTChrC9UbkSqNqMGjELWLdM7SyuK5/gTib6myzeU10fOZVfS8OufI9EIyU2bsoykFgyI6bxtt7fzWZnhZqxZ97Rm8S56V8fhAu2N9G4RDWE9f49OgAJk9aeoky7XYgjvvp05zDl0GMrT9f0YDb+fwPQZeI8/geSGDTgHD8HIy8u6GVC5hRjHXwxWElRLduvOlZlE0obfEpTXg9EF8VUbmz3FNpI2nSa5dQuNd99BYtVKvFOOJzDjIiSZpHL6GUgwCID/jLOzXHOpym00P3g/Bb+6XdcQJGKUP/U8sSWLcQ4eitmjF2ZeHtbqRbrUIadQG5lIMPviYmWVQiiPTwsafPgSsmQO6ohpGEPHIXWVGD0HUnDzT0ldcTXJdWsxy3rQfO/fSW5cj2viITj6tXbSkGgYWfqB3rU5XKjxU6DfcFQnmgHL+s+ys3iTCV1DOH7qHkn3yda1GQOpBwRWfkTB//2Kpnv/SWzuHJyjx5B33Q/2iZYrgJGbi5Gbi7Nv/x0eszsqTFY8RmLpEup+9iNSW7fgOWYqBbf8ZK/L+tnY7Cm2kbTpFKmaGqovuzjTkaJ57T+wGhvwHn9ixkAChF98jvybf0LDHb+FWAyzvAd537sBs6AAWfwesmQOmA48uUWwqhpjwAV6Yn4JMnk6VsIiuXEzjj7DYOPy1gXkl7SLcSl/LsbkaWlNWRPl9mnZPMAELenm81N98XkYRUWUPfcyqaoqQs89jWfSoRg9e2HUbkaWzU2/yCTywSzdPHkXRjJZWQnhEO3kCFJJJBHbs16JHbWYsixUfgF519+EXHE1yufF8H15GxZLQyPVV30r0wQ7OvtVmvLyyLvx1q6PsdrY7Ab7Vqna5kuLFQpmDGQL4Refx8zPzl4MPfYoOJ2Uz3qN8pffpPThxzByc5FEPCNtRyoJ9ZXQUKUlzwArZVD705+Qqqig5tqrsXqMgEEHaeM44ADUsTOwghGS2ypI1bU2V1YuD8qXg9pB/MssKqD0oUco/us9BB/9DzVXXELTn++i6sJziTz/DFY42G6ObF270/ciVVtDzXVXQ0m/bMNtGKgBo5HZ/0VCrXHXlgSczqLK+mWXThgmaswRKIcDw+PBLC7+UhtIgGRlRcZAthB97x0k1P73sa+QVIpUdRXxFctJbt2C1dS439Zi032wd5I2nUJ5PO1qH83SMlQggFFSilU/55yYAAAgAElEQVRdlTnOPW4CZn4ByQ3rabj7DlLNTeRddyOOQ6ZBYzVq6wqoWAfKAJcHCTaiUjEKf/Froh/ORZqbqLr0InynnI77wAMxfD2R+R9T97MfI02NOEeOpuiPf8VRVr7TNUsyCUvnohxOrNxe7eo6m/71d7yPP9X+tRbtXKBcEgmSyz+j4c4/kP+Dm1BbVoBYGCMnIks/gJotyLIPsYZMIL5sKZFXX8I9YSKeyUd1yj2qfAFdQ7lpJcQiqAGjYS8Lyu9vzOKSdn9PzmEjUO79J2uX3LyJ6ktnYNXres/AN75FzuVX7nbZkM1XC7tO0qZTWM1NNN1/D8EH79MDDicl//o3rnETsGpqiLzzBlYwiO/4kzCLS0jV17Ht9BMgFqPwjj+TWLqY0HNPoQI55F97HU6/wug3BLaubaMFmos65jy2nX9upskxSlH2zEtUnnO6dqum8RwzlcJf/XanyR4SDmK98iAMGE0q0JOqc0/PPsDhoPzF2agFL2U6X6jBY1Hjp+60HjJVU03VxeeRqtiKysnBe9SxqPwCcqadjno/bXQPPIbg3E91HWka9xFHUfjr2zvMvu1q9G5Wuo1UnNXcTHjWszTc9XtIJjB79qLkngdx9O6zn9bTRO3NNxD7YE7WePms1/adwLzNfsWuk7TZI4ycXHK+eQX+aWeT2roFx6DBGHn5rf0Wzzk/6/j4J/MhFsN98CRSlRU0txjX+npqb76RsmdeRAVysVoMZBpZ/Qn5N/+Iuh/eACJ4jpmCBJuzDCRA/NMFWM3N4HLtuOOGwwF5RbBiPsbk83AfdkTWh6DvlNNRwTrUuCkoX47OmHW6dhlPNAqLKPrD3dRceyVWfR3ROe9Q9Ps7Uatbb76kuC/Bh76XNS825x3dvWQfGkmxLAg3I5/P00lGIydBoGC/C5EbOTn4zjgLz9Tjdba0z79P+2Zuj8TiWVrELaSqq20j+TXHNpI2ncbMy8PMy8PRrz9WbQ2xBR+j3G6cAwa2a5NllJQB4Bp7INE572WfSIToB3PwTzlGPw7kYxx6CsSjiAiekT0oe/lNnaziNHVXDYczy1C6xhxI+KVZKJcb3+lndtjmSLk8GAefgPXKQ7BtNQU//SXhF54jvngR7iOOxHfU0bDgFaRmC+LyYJxxVacSbpRh4Bw+grInnkOiUe0itGKwdbHulDFsAuJ0g9km5G8YuCcdBns5KUUsS2fCOlwd69NGQ7pMpaWcZM1ijFMug+Kee3UdXwTD78fwdw83ssrNwXvciQQfuLd1zOvD0Wf/7Gxtug+2kbTZbVJVlVRd2OoSdQwYSMm9M7N2As6BA3EdNJ7Utm04BwwgNjfbjWWWlCGW0iLnR5yRaasFgC8HxymXQSyiP+D7jqLoN7+j/rZfYTU24Bw1mpzLrqT2hmuxaqpxHzQOM29Mx4vNKcA49QqIR8DlwT/jInzTziY2/yPqb78N/+nTcI4Zglr8NlK1CdV/ZKfeA+VwZJUriAicoFWDcHkwUilyr7iaxj/+AbO0jMLb7yK2aCFNf7oD/+ln4hgydI9jXRIJIasWIptXokr6wKhDUb7sdmRSsS67nASwlszBOGLaDnt8fh0xXG5yLr4UEnHCL72Ao2cv8n/8c4z83dT7tfnKYRtJm91CLIvgY4+2xgyB5Lq1ROfNxX/KaZkxs7CIojv/TLJiK2ZePtF5c0mu0X0KvVOOBytF41/vJv/6G5Cqja0GErR7cOVCxO3RDXE3LMXVayilMx/BCkVIrFxB3a03ZtYQmfMurtEdG0mlFPgC+gugppqqGWdn5kbfeoPCX/0Gd1k/cHxxo6GUgjZdMZTpwDftbFwHjAWHg4bf/JLEct1EJ/zc0+T/7Nf4Tz/zC3fJ0M2wX0fWLtGPq7cgVRsxppyP8rTZnXUgDadMZ7ZKkQ2g/2Zzr72BnEsvB9Ox+4L4Nl9JbCP5FUFikVZ3pNPVqWL4L0QqRWpbRbthq76u3ZhZWJTJ5iz+x/1aicfpRCIRmh+4j8hLs8i74Yeo7XY6ADTXo3L6t7aq2rISJUni1Skafv+brEPdB47DamokVV9Hcv06nEOG6Xipx6N7HFZuBK8flV9CYvOmLAMP0Py/R3H9+jcYX9AFKdGwjvfFI+DPz6jNmHn5mOMmkFi7JmMgM9e87594Jx/9xeNwyTiybmn2WM3WdrFbVdoH8edBKF3OYJiosZN1dxebdhhuN7htQQObVmwj+RVAoiGsea/A+s9AKdSwCTD2yL3asaIF5XQSOP9CIi/NAsAoKqbot7fj7N9PG6PcQlSbHZUVCesEG8ui8U9/IPru2xi5eeR+5zqcw4aD4dC1hYvfyyoHUMMngMePmA5dVwnQUI33+AuJzHlXJ+Aohe+Ms3AMGUrwycdo+vNd6cmKwjvuxnPwwcisf2UMhxT1wHXYtHavyfD6iS35DLO2AdeIkRj+QLtjdoREw8iC2cjqdA2o24tx0qWQ18b4daC+o0yT9koEu4nLC7Fwm5Ma+qvtdbwBjJO/hWxZrctJ+o/I2vHa2NjsHLsE5CuAtepT5INZWWPq+IswegzY69eSaAirsZHE6tU0P3Af+bf8CLV8DqqlA4QvB+Pkb6H8uVixKNF33yY2by6YphYayCxQUf78qyivD7FSKEnB5x9ANIQaexQUliGxCIYIsnE5ON2ovsPAG8BqbEQiYVAGhs+HRCNUnDw1axdlFBZRev+/Ue8+nv2+HHcRtbf/gdg7b+oBh4OiP/2Nxj/dSXLNKsoefw7nkKGdfz8aqrGe+2f2YO8hGIedmrlZSNXVUXvDd4h/ujBzSOHv7sR7/ElfWL5OUilkw2fIe8+2vrYxk1GjD20Vge9GSCIOpmOP5PpsbLoSuwTkS4hEQnp35dmx6LakUrB1Tfsntm2AvWwkJRrGmvM8bFmNs6gHBddfi+GQ1jZVoEW/t25AckuQcBgjLx/X+IkE//2v7U4mxFcsJ/i//xCf/xHuQw6n4Oe3odwOkpXVhB66A2fPnniOPBIVbsYYMzZjdMz8/KwyimRzUzs3o9VQr4W2tycRpfAXvyG+eCGJtWtxHzSOyJuztcC5CMFnn6Tgph91/j3pQLGHYANEw5kdm1lYSNGdfyX64Qckln+G76RTcfTps0cGQ5km9B6KOvM7SM0WVEEZ+ALdzkBKNIxUrEPWLtEiDcPGZ3kabGy6O7aR7IZIIg61FVgfvQrxCGrYwTDkwA7dp8o0kT5Dtau17XjPgXt/YdEQbNHJN9RW6LhnWb+sQ2TwOKILFtFwx+8gmcQoLKL4ngdxjh5DYtXKrGPNsjLM8h44+vYj9uH7hB57FNeBB1F73dWZYxxPPUnxnXcgi96Dg49DdaRr6vXiHDaCxIrPM2PeY48DtvOSON2okt4Yvhy8Rx4DphPD4yIw5SgCU45CnF7ia9fv1lui8ouR7cpTVN9hSF0lqqC104hZVKQTm9okN+0pyuUGl7vbNjaWVBJZMR/59B39ePMqZOMKjOMu3C0xdBub/YltJLsj0TDWaw9nYnTyyRtalmzQGJ1FuR2q50AYcpCOixkGatSh2TGxNBIJpbtrCHhzdv+DKhFr/bnXYNTgA7WRWPROazyx51Aavjct0xzYqqul8Y7fkn/LT0muXkV8ySJwu7XoecBD/klHIhecR3z9JlLBMM33Z+84kxvWkaqpRyXjqB2EBiSRoODXvyP46MMkli3BPWEi3qknEFu0GM+kU2DjZyivX7tx29xoeMaO1jWUaZ1V5c/Dd+IlnXorJBJEarYihoFx4iVYH78GoSZU/5Gokt5YiQSp5ibMnNxOvrlfQWKRVjWlFuor9d+RbSRtviTYRrIbIpUbspJYAGTNIh2T6yBrVXn8MOE41IFH6QGXG7VdOYNEgliz/wt12/RAXjHGCRfvnuvLn6+L5YeOA38usmA29BmGMfUCrEXv6g4Y8WTGQLYQX7qYVFUlOd++BueAgaAE1VAB6XihAlwjDiXVpx+RF57r8NJqyEEdZmSmamupueYKMBQFP/kl8SHDSKz4nOqrL4NYDP/0GeR973qUx4NyuHRMtaFG1w421WYMJAChRl1SMfAA7brckYs7EsR69eFM2YpVWI5x5FlI3TbYvJrUus9IWgHYVo956OGdf3+/AC2xPgmHscIhQGHk5HSPThpK6f6fbduJQYeJTDY23RX7r7Ub0pH7TOWVdNhCKfO8y627Yfhy2hlIQGc3thhIgMYa3aR4d/D6MU65DNVrEDL3RQg2IJ/Pw1rwBmriCRhTZ2AUFqFysvVUPYcfiWPAIFyjD0Atno3pNGD+a9nrX70AZ58+BC78Rta4o29/HP0HovJL6QiJRUmuWUVy1UokFiX46EzCzz0NsZjOfj3pVIxArjaQsTDWvFeRV2dCQ3W2gWwh0owsehdCTVifvIlUbtIlHm2vWVuRXddZX4m15D3EV4BVPpTIygpqbvw+oeeeRhIJugKJhrHWLsF67xmsbZupv/3XbDvpWCpPP57gIw+RamzokuvuFm6f7s/Zln4joAtFDCQSQqo2YW1aiYSbd7sDi43N9tg7ye5IbiH0Hd7aT9Gfhzrg8A7jcZ2mobrDMRHp0IXbEUopCORhbV+fV7cNWTwHNXkaRoGLknseov5nt5JYtxbPUceQf9OtmMUlWnC8rXFpiwipykrEsij979OEnnsKx8BB+Kae0GFpQ2ZNTicqJwdpbqbhtl9QeNsfiH38IVZjA/5pZ2OWt6l9TMRhyyrtku41CBIx3Wy59QWi+o3EeucpVJ+hyMpPkCXvow46BkZN0kX40LozcntRBx+PCuSDYZBqDlL9natIVVUC4BwxUuvH7mUkmUCWfYgsfR96DCDy9ltEZuksV0mlaPrrn/Accjhm3r4XUs8iEoRIEOP4i3V5UHFPVFE5yu1DRLBqa4gvWQxOB67ho/ZYu1UiIay3HsuI1YvTjXHq5fr/ycbmC9JlRlIp1QeYCZQDFnCPiNytlCoEHgP6A+uB6SJSn55zK3AZkAK+JyKvpsfHAw8CXuAl4DoREaWUO32N8UAtcJ6IrO+q17SvUB6/1jIdP0UnhHj9e5wRqAYegCz7MHtsyIFZBlISCayGelL19Rh5eRiBnI61NQvbt6hSRT10obph4BoxkuJ/PgBWCuXxYgTSa3e7UUPHIXUV0GtwaxIQoEYeglnWA2/vvhj+AK4RI0nV1tA88wFi8+fhnngoORd+I0sjVkQwfB56PP08VmMjzU8+TvXV36L0vodxDhuepWaTqq/Dqq1BRk7BKC4kFQ2h3DmoY2cgy+cBYIw+DAk16gQlj08bVUCWzEENHgs+bSRVeX/E4cI48kysJe8j27Qwtiosp/iv/6Byxrk4Bw7Cf8oZnb4B2S0SMWR5OtYXKCL64vPtDonNn4dr9AF7/9qdROIxrI9egY0rELcXCspg/VLUcRcBaWnDGWdj1dUCYPbuQ+mDj2ZJ/e32NRtrMgYS0O/Tonfg0FNt8QSbL0xX7iSTwA9E5BOlVA6wQCn1OnAp8IaI/E4pdQtwC3CzUmokcD4wCugJzFZKDRWRFPAP4NvAh2gjeSLwMtqg1ovIYKXU+cDtwHld+Jr2Gcrjy0oy6QwigtVQr5vzbp8wEshHHXsesvBtLfU2djLkZt+5J1auoPrbl2hlHNMk/5af4jvldAxf9jpUUbnOqN2UzlYtKEP6jCS1cQOx+fNwDh2Oo0/fdh94ynTCqEORjcsxxhyB9BmiP9T6j0IV98zK3k01NFD34x8S+/ADvbalS0isXE7hbX9oFTNvqsV67T8QbkYZJnlnnkreVd8Fry/bQNbVUnvjdcQ/mY/Zpy+l/7wPQVF5wbkYufn4Tz0VDBPPcAOzrlIb8uotYKV0TK2kd9ZOVhwu3e+xerMutWmhbhtmvJHyF2ajXC7Mol33jvzCOFz6BipUj2f8BKLvvJX1tOugduVe+5ZkHKo26Z9jEdi2Xv8cCSLeAKEn/pcxkACpzZuIvvs2/rPO/eLXjHTQQDvcjEolO5Tns7HpDF1mJEWkAqhI/9yslPoc6AWcARydPuwh4G3g5vT4/0QkBqxTSq0GJiql1gO5IjIXQCk1E5iGNpJnAD9Pn+tJ4K9KKSVfN4UEINXYSHTOOwQfnYmRm0/edTdglpRhFBailEK5PNqFWNxLT/D4snY5qdpa6v7vVm0gAVIpGm6/Dc+RR7c3kh4/xmGn6Z2WpBCnh+i771B38w2ZY3xnnkv+9TdibCfirTw+GHwgJGKooh7IoLEow2iXJCPRSMZAthCb8y4SjUBeno7JffgylPZF/IWoaDPyyRsYp1+JcmcnN8UXfapbdwFFv7wNVn9MrCqGVVWFVVVF45+0Uk9i/Xryr78RgvXIG4+iho3XakCVG5GaLVDcS2fJJuMgFjR14Dqu24Y5clLXFs27vKjxU5D3n4eKtXiOOAfPwoVE35oNDieBiy/FOaA/EmyEcBP487RreF8aCocLSvvAxhWtY4aha0cti1S6SXdbUjUdhAR2QdtwgSrt074cZ/jBnersYmOzI/ZJTFIp1R84CJgHlKUNKCJSoZRqycjohd4ptrA5PZZI/7z9eMucTelzJZVSjUARsIPA11eX+PyPqP/xDzOPqxZ8ROkDj5DcvAnXiJEol06W2GHZh1gkN6zPHksmkHCI8Ksv4RgwELO0PNMwuO1O16qpoeHO32VNDT/zBLlXXtPOSAJ6Z5FMaF3Vdcv0rmPEJJS/dferTBPl8Wqj2DLm87caHysFQycRnPU80bmP4Bo9mpwLLtLn2o7EOi22oHJyMXweqAwisfYJHRKJEHrxBYjH8Z1yOSrcgPXqzNZSnLK+GEefA4aJ1FeiyvtDOIQaNFpnmFash7K+Xa4qo0wT+g5DFV2JbFmD8vko+OnPkRtvBsPQ7u1ta7E+eCE9wUAdOx16DtpnijfK5caYeCJWqAlqK8DlQR1+mv7ucBCYcZFOsGrB4cB30qmdPr/EIjr5bNVCpKAUNWA0eHRimfXJmxANo0ZM1L8jG5s9oMuNpFIqADwFfF9EmnYSo+noCdnJ+M7mbL+Gb6PdtfTt230bqFqRCCQSGLm7V1tnBZsJPvHf7MF4nNjCBUTenE3R7XdhlnScHdqC8njwHH0M0dmtWadGSSmpiorMDtF//kXkXfO9DtYnSHMHyjPJZLshCTZgvfWEzrT1+FATT4SNK7Be+jfGqZdnYq8qJ5fc711PYxsx87zrfgDxIFZFCJVTSOPMmYSfeRKAxOfLiC9bRvHdf6dlTyrxGKSS+E45jaa//xnE0jcL1ZvxHDEd9Y+/tu6cDQP/GWdR//Mfk9pWgXPoEJy1K7JLcSo3apdebhEEGxG3D4p7YL39FCTjqP6jdHnMPkC5PNrgFJTqLM5Z96DSWbjq5G9qLd8WxEI+eAF12hW7rdsqyQRWfQNWKIjy+TBy81BWEqlYq70BfYaCJ9BhNxPlz8WYOkP/HRiGznZNH+fo05eSBx6h6d5/oFwucq++FqOT8UgRQbasQd57pnVs1acYx1+Eyi/BOGIaSArl3vvaxTZfP7rUSCqlnGgD+YiItNw2ViqleqR3kT2AFr/LZqBth9PewNb0eO8OxtvO2ayUcgB5QLt2FCJyD3APaO3WvfHa9iaSSpHaspnGf/4Vq7qKwIyLcY0/uMNGwh3icGKWlYNSeA47AvfESSS3bMYs70GqchuphoZdGkkjkEPBLT+lweki+v57OAcPIe97N9B45+2ZY0KPPULOpZe1M5IqkIN/+vkEH/q3fuzzE7j4m+B2Z7nDJBbRu5uWUpRoGHn/eYzjL0LWL4PmBsTjh3AzbPgc36ET8TzzIomVK3EOHYqqWQ+zH0EAKemN/8QTM0YSIPHZUiQe12n/zXVY82dDqBFj0Fh6vPImqaoqxOGGgjJU3SbKHn8WKxgkuWEDZmkZ4VnPZjqcSGNDO6k7AFJJnWXcf6QuE/noVT1uOnRXjqJyGDEJSSaRpkZwODD3sCdhqqaGVH0thseLysnN7OYBxEohSz/QMngtWFarKHwLkaB2EXcCSSa0TJ9pkti0mepvXog0N4HLRc+XX8d663+Z8hlZoF3c5HT8GrPadrXB8AdwHzSewt//EaWMdgliEgkhtVugvlobYl+uVhgC/XezeLtG3g3VEAmBN9B6nI3NXqArs1sVcD/wuYjc1eap54FLgN+lvz/XZvxRpdRd6MSdIcBHIpJSSjUrpQ5Bu2u/Afxlu3PNBc4B3vwyxiOtuloqLzgbCerdWOzjeRTecbcuf+gEhsdD7revwX/qaZhGHFW9HgZNQI0aR5PX12ljaxaXUPDTXyChMGKlqP3e1VlSb75TzwDLIlmxFeXxYBYUZq6fc+kVOPoNIP7pJ+RcejmhJx+j/tab8J58Kt5jpurefKkkVG/OvmgqLT6glC6XiASxZt2b6W5heAN4T71cxx83tYlvVW/GHDwBo7CoNQHE4UQ5nRANYb3474xCkMx/HTXuWILPvkb0nTcpufdBYp8tpfHG6VhNTXhPOJnAeRcQer7V/ReePRv3FZcgc19ovaY/T38B+HKQirVaVLz3EN0my+HE2rgCgk00/0fXa5olpeT/6P9wDBqi2zDtJsltFVR/80JSFfq+0HviKeTf/OPMe49lIeHmrDkSbob8UmhoE/frORDMXcckJRJCFr+LbFgOuYWYIw7DNXwEsY/n4Ro+EmvDClTb+tJkQhvpiSd8oRIlM5DTbkyiYaz3noGKdfrxJ2+ijj0Peg9pjaN3VBJk98i06QK6cid5OHAxsEQp9Wl67Edo4/i4UuoyYCNwLoCILFNKPQ58hs6M/U46sxXgalpLQF5Of4E2wg+nk3zq0NmxXzriS5dkDGQLwUdm4j74kE4bOKOsDKNqdesdduVGpGoDJX/5G6qDD6IdnsfnB58fKxrFPf7gjJEMXHQpZu8+VJ5zOhIO4Rw1mqK7/oajrAwAs6AA/5nn4DniSGquuJTkBv0BF5s/j9S2beRc/m39IVraR7vB8oqQukrYuhZME4p7asOz7rPs9k+RoFayiTS3X6vTgfL5IG0kc6+8RtdMNla3Sug53aieg5BIEM+kiURemoXV0ED9j29uvcRLs3D06kXgkm/hPfxIzJISxBIoLUH5AsjKhai8ItTwgyGdBKIcTqTHAFizGOulf2euZRx3AdGVy2m+5+8ApCq3UfXNC+kx6zUoLev07wHAisVovvefGQMJEHnlRXIuujRjJJXDiTHiYKwNrTczsuhdjCkzsBbMhpotqPIBqHHH7DKBRZIJZNE7yIoF6YsFoaGa/BtupHLGudpVvf0OFbLlCvcGsUjGQGbWtuANVHEvLWfn8aEOOhp5q02Hl6IesINdq43NntCV2a1z2HHHvCkdDYrIbcBtHYzPB0Z3MB4lbWS/zBj57Yu+jYJClLPzvx6ViGGt/CR7sLkOw+vRhmR31+TxkHPFVRhl5UTfmo3vjDOpmj4tE6NLLFtK4913UPCTX2SyX5VSSDiUMZAthJ74L4Hp52MUl2Acdhry+UdIxXpUWV/UhKlIPIJxzPkoj26btT3SVIcaMSkrBoXbiyrtRcm/HiD++Wc4Bw3GLCrC8PqQmE8HpnsOQgaMo3nWcyinC9/Jp+M98WQSK5a3u0Zs7gcU/O5O6m65gcTSJTiHDqPwd3di9huIKukNkWas+bNRHi+MOgx8OSjDxFo8p/UkiRjWR6+Bv892J48RX7UC7+4aycYGEmtXtxtPblyfXQNZUIaaMkOLCzhcGOOO0epIh52mXcZOF6ozKjfxGNLG2Oq1R1CmQnm8xBYthLKfwcqPsxKk1KhD90zoYnuk/d+Adn3rvz2lFJT3Q512BbJ2KRSUonoOtEXTbboEW3GnG+Do1x/XAWO1+DegPF7yvvt9vavbHVweXQifdfIvnvZvFhSSc9El+KedRWLldkksQHzRQiQcgjZGuKN4kJGbB0qlW209m6ktlNr/Z++8o6Sqsu//ue9Vzp0bmpxzBkUEQQUUQTCHQUfHPGNOo2NOo445jGlUVMxZxIARlaASlSA5xw5V3dVdud67vz9ud3UX3SCofEd/03stFqtevfyq37nnnn323gaFrRBuv8r+ZC607wmLv6p/CbfqjNa6CzIRQ4w4Frl6EcLtV32eLi8Wtw9LSavsAzrc0LEvsrgLOyefjIzHAah55UUKnnoOM5ItMwdg69OP6PT3SC1dAqie0fKLzqdwyktgpmDhp1C2RdVD1y9Dm3CuqoHtinAFlo5DGi22FLfY7X2ug1FeTvInVVe19epD5IP3cY4YSXLRgvqVdB1b/4FZ2wmbA9GqE7KgRKkGNdT33Zf6nKap2uIuMnzC40MKsHXtDhY72tHnqinWVBLRayh4f2NFG7tLCfQ3UGcSPYdmsnioJS7lFiOaELbYGxjhKmQkgkwm0TyeLJGKZjSjIZqD5O8Aem4eeQ8+Rmr9OsyKMuz9BqLl7uOLx+FGDBmL/PyVTDAT7XupfrVfAaHr6P4AsnUb9RJtoIVpH3wAYhfChXC7cY47mtiHtSowQuC/6hpIRyGl1zffW6yIkSciw5XI5d/BtnVKRuyovyAmXaCWaQLRsR/mtCdVJlFQgmjbAzr03mPWIBwuxJAxVD/8YCZAAshIhNjXM7EfNBzvuRdQ/ex/IJ3G2rMXntPPZOex2S0IxtYtyHic0J234R4/HtuAHoiFnyh3i7KtCLdXvbgbCHiLNt3QCoqyaqWuScej5e2ZuWmUl1F6xqkYW1QDvpaTS/4jT2CUl+H9y7lEp7+HFgjgv+ofaLshAv3afkDhcKENPQrzo+czU6ii7wjwBdR0sW5RtWWAA45QohS/ZQZZdx5Oj5KyW70IGdyh3GYKS3YrOL+vMEJBqh64h+g0NTNhad+Bgqee+1lyWzP+N9EcJH8n0PPyfpVCixBC1fuO+Rty5yaEPx+8OU16UP4SaD4/uf96kMrbbsSsqsRxyKEELr8SYawZbIQAACAASURBVCSRNUk1pWd3ITQdz6mTcY0eS3rTRmz9BqAFfDB7Ggw7WgValw858EiqX3+T1E/LcY46FOfQSfDd+5jzP0Mbfoyahk2nkN9+WM8yLduqgpMnAG277fl+WO1NEjmE3Y6tew+s7dvjnngspFIYkQgIgRYIYETrs0MtJwd0ncTcWSTmziJwzXU46+T0rFbM5fPQDjkec/FMqKpAtO6M6H8IwuGh6LV3McpL0TxehM/3szqq8VlfZwIkgBkKEv34A4xgEKHr+K/4OyCwdu2+fx0+fPloky5Q9Ui7U7WZ2BywS+fIbxWwdgfh8kDvYQjTRPzG+rfpLZszARIgvX4d1c8/i+/iy9Fs+098vRl/TDQHyT84ZCKqevZKNyMKW4EngNap729+HM3lwnnIKOx9pyFNE93twpw7HblNNerTqgvaQeMxq8OUTT4RvbAIvbCI8BOPYuvTl5xzTkduXoXofgCmK5fyKy8nvUbJ2iW+/5b0aWfgPaA3BLepNovaaUKzKVLIHogiRiiETMTRnE58Z5+NY8hgql9+icTc2QiPR7mC2GzISAjzs+eg/6GYoSQ1r79C7p33UnHJBZiVlQivl9w77yU25+vMvmveeB3HDdciaipVf2JoB+Z3HyG6DFBTxokoWGwITUMvKEAv2HsdUqOisf6FWVmJ5nQRees1ou+/S+79j6L/TA+tNAxFfIrVKLEHq2OfWiKEroPLq/79lyE0bb/YaqXXNq7zplb8BPE4NAfJZuyC5iD5B4GZTDbqu5PplHKqWKh0OyW102M9h+4dUWMfIazWzJSUufYHqAuQAFtWIXdswDTUC9ko3Zlxw0itXwsOD3LhDMTgMeDKyQTIOkTefgPPhKPQcgrqGaRWG1qvgzA3N1jXakO0aN/k+RllpVRcfSn+cy9AiAhsWIrV5iD38ktIlZ6GpWUJYtOPyBw/cot6UUopqHnxORLzvkPLyaHwxTeQqSTC6SI+5xuq7rg1s3/N64HcIrT2J4DTizb6VMz5nyknkZYdEX2HZ9cDAbM6jEyonsNM20YTcI0dR/jxR7N6Mz2nTCa5ehUuJJ5jjsfStt1ut88gtFN5XdbWdMXgMdC5n8qsmwGAfeBgNcvQoMbuPHIcwvPrTASa8f8nmoPkHwBGKEjNKy/W991dewOWTl3UVOcPDZqqNV1NtXYd9Is8+4xgBekN6zGCFdh690PPzVV9h02hobB3HUo3Y+k+FOF0IWP15A/niFGIqlKQUjlmdGvVaFPN51d11Ta7SKcFCtHGnYm5dC7C7kT0Htakq70ZjxF+4lGEzY5ul7Ck1gIrEYM572E/6i+Yn7+miE2d+mHaPIp67fKpFhQg8twzRJ57BjSNorc/IPbxh/UHsFjwX3gpYv1iTNNEG3EMwu1HO2h8LYPUrtpCpFS1Ok3DKN1J8JbrSXw3F2uXbuTedhd6i2IluK3rtRJt6v5q+QUUvvwm4ccfgWQC7zkXYGnXHlvP3jDpuD0+tzrIWARz9vtZzFM5/1NE2+5KqL0ZAGi5eeQ99BiV99yJWVWF+/iTcB425v9Msq8Zfyw0B8nfOWQ6TeTdt7L77v4ymeJpn6B7nPV9ay07IjsOIj53DtrsWdj7D9wnxp4RrKDi8gtJLl6kSDUeD4XPvoi1Q8emN2jfC9b8kLVItOsOThcFT79A6NbrSW/ZjHP0EfjOPAt++EJ5YnYfgpkycE06lui7tc37QuC/7CqMcA1aThrRIBkTNuXCoQ2fpAb+iShy8VdI00R0HahaMXQLMhIhsXA+rnHjEeWbGt/H0i3QujOsXoxMJ9Hyi2HIEUgJnj/9mcT332ZISXpJK4TdTu5d95FavZL0+rU4Bg2Gzcth03LE8GMyhBVhtYPVjkynSW/bRs3rLyETCbyTzyB0y/Vqvyg1oLLz/0LhE08iZr2p7vGB45QGq9WO5nBg69KV3DvuBlPW24vtEyRU7yI4JWXTykH/w9DcbhwHH0Jhz95qQOP1ou0iit+MZtShOUj+zmGGq4h9ND17YSJBas1K9EFDoG0PKNuM2ao3paeemGFzWtp3oODpF/Y6UKY3byK1dg05t92FpWWJ8pYMV2FGI022oohAAfQfpVoBhED0PhgCBQirFVvPXuQ//qzyk3S5ETYrHHqCyrZ0C7oT/BddgeuI8aR+Woatb39iM7+g5urLKJr2cWObL1TTPDVVmO89kcmU5Ip5aBPPVwQltwf7ICXHR/eDGm/vzQG3D/JaIqSJOeM56H4gWvsOGD8speCp54nN/Bw9Lw/bgEFgtaLn5qH1G4Ct0If8/kNIxpVodssOjfZvlJex84QJGS1Y12FjMgEy8yzLSpEpQ2Ww6RRy9jRE8cWZLE+m00rtKJ1CJhL7TuTSrYjWXZXEXx2cnn1rA/mdwUwkkOEqZDyOcDpV/3ATOrH7CqFpzW0fzdgrNAfJ3zmE3Y7epq3qU2wAvbAYdB3twCMwy7YRfvSxrHaH9Pp1JH9ajvPgEXt1HDMUIve2u6l5TZFcACxt25P/1JRGQVLGajA/exWRV4x2yLEgNGSgMEtQWt+lhUUaaeX6IQRYHSAE1S9MQdZUE376iUxwSa9ejbVNuybPUa5bku3yYaSRP82DwaOVNN95fyV4y/XIll0Q5ZszfXaibQ9kKon85h3EqBMwVy9WNl8/fo3p9GPr3Zeqh+5FOF2kNm1Eb9UGa+cutfffAa27IYraqYFDIgkVQYQzhp5bH8Rin86oF0sH0jt3YGnfgfT6dZllwuHInr6WUikJuX3IZJLED4sI/v1yzGAFlg4dyX/ocSyt916QX9jsMGSM0pHduhr8BWhDx/1hlWjMRILEvG8J/v1yZCSCVlhIwWPPYO3U+b99as34H0JzkPydQ3N7CFxyJaULF9T33U2YiBYPITdEVb0pp7iRrB2ArGks5bY72Pr0Jf7tnEyABEhvXE/kjVfxnX9hFg1f7twMoR3I0A7kGqU4KHodhOw/qsm6joxFMOe8D1tWg6aradeuA7F26kzNC8/Wr2ixYOvbT2mPCq2R52WT2pwNlun5BeTedjcynUI77BRIJ1TGVr4to8Eqf5qHKG5bbyMT3Ioo6UnObXdBOo3QdTR/IGMtBiAsFsy4JPrpJ1Te809IJLB07Ez+v5+qFwnYpU2h5uUXyLnhVsov/ZsiXNls5Nx4K2xaWr+SpquaKEpdp+LSv9YPFtatJXjd1eQ99Hh9b2IDGFVVyJowZmUlemGx8g3VdeWicsARiNQo0C1/aC9FGa4iePXlSrACMEtLqbjmCgqempI1QPlF+06nIBlXAxWLrZEHaTOaUYfmIPkHgF7SisLX3sHctgXhdCAiQcTiz5GmgShuh+4J4DnjbOKz60k8wutVLL69hOYPYJY3bkNIrV6p2J4Ng0CkqtF6sjqEMM1GlH1pmsi1P6gACWAaSlu0dRe8fz6L1NrVJGZ/g/B4KHr1bcSW5ZgrFyhSy+AxUNQ6w8wUHXohl8yubwGxWJWpbsNA2UDiz9y+HvnJi9knandmtZCIFu2x7gVr1KyupvKOmzOMyPTa1VTdfzc5N92O5vbgOmw01U8+illZWfv9GvSWJRS/9T5mJILmciEcduTc99UOnR7EsKOVShJgRqNZmSigFJia0Eo1qqqofvoJaqZOUdfg9VH4/MtYO3RSn622X0Tc+m/AjEZVy47P32gaVcZimQBZh/SaVUoQ/1dAJmLItT8iF32p6rVtuqIdeFSzrF0zmkRzkPwvQqbTmJUhEJrKBHbjYiA0Dd3jQmyYB+HyLNUbWVOF8ASwdutBwZSXqJ76HFpuHr4zz0bbh9G20HUcB4+g6oF/ZVHjXROOQXNmCxKI1l2QCz7LWk/rNrjppu90ErmLWDWALNuC3m0wuf+8R9WbbHZE+QbkD7V9ifGIUg86/pLaQCFU28XE85BrfwTTRHTqC87d9/OJQCEyt7jemstiRes5FHPmG+pz226IFm336v4Y27c1luVbugQZi4Hbg5ZfQNHr7xH9+ENkIo5rwiSEyw3JBJrPl8l85Mjjaq+nNlOuHVRoLhfC48maEbD17dcoQwWQ1eFMgKz7XHnnbeTe+7Ai/MRrlIuH1YYo6aQC8u/MIUNKqezhHn2Q9OaNuI6aiOvI8VlZs3C50HJyMUP1ZCRb/4GZAYBMxKCyHLlllRpM5Zfs1porC7Ea5Lx631Q2rUTml0DPA/e7SEIz/nhoDpL/JRiVIaLvvUPNyy8g3G78V/xdydG5d/NHbrEh8lsiG9ofCYHwqsxJ93rR+w/E2q2HqlX+gqZomUyQe8e/CD/zJDIaxX3sCej5+cha82QZjSCcLnB50Y48UznAp1OqLSN3N+LdFpty4di2LmuxKFS1Nt0fAD/IRBxz3dLsdQaPhh0bMJd/B7oFbcBhkFeM1mf4Xl2PcLrRDj9V3bNYBFHUBqlb0I48U0nvW6x7bcxrKWmlAlYDI2nH0GEId61JtKahFxbhPf1MQIkDVN5xM7EvP8PSui25t/4Ta5duuz2eFsgh/6HHqfj75ZjlZVg6dSH39n816UVpBCvAbsc58jD0/HwS879XhKV0CqLhehk/QLq8aEedDa7fVw+gWVFO6Z9PwawVUahathQZjeD981mZuq2Wk0v+408TvOYK0hvWY+vbn5wbbyM+ZxaOoQchtvyEXPiF2uFSFOP6gCN+3u1kV7s2QG5dq9jStuYg2YxsiD+g/eKvwqBBg+T8+fP/z44nTRNZU4NwOrNIG9EZHxL8++X1KwpB0Xsf7Za0AiCjNcpnb8cG5YIx9ChEy467FQ4w43HMcBgZj6G5XGiBnD1KfMXmzMKoqFCBOpEg9uVnyFSSnBtuJfLOW8RnfYV94CA8p5yGnpevRvJSItGUrNtu/BJlPIL57cew6SdVJ+s7AtG5f9bLTBpp5MIvlGYrQKAQMfBQCJWC1aaa/7etRZt0AcL36+pRvwRmLEZiwfeEbr4es6Icx8EjyLnpdvT8xqo6ZjRK5V23ZUmfCZeb4vc+3qMKjzQMzFAQmUopwlZt9mlUlGNWhhAOpwrKpoFRVkr0kxkYG9fjGHUYemGRyjwXfIbcxQ1GDJuA1qnfXl2nTKUwq8MIhzPj7rI/kFy2lNI/HQ+ahn3AIITPT3rrFgr+/VSje2pUlCNTKdIb1lMzdQrx2d9Q+OKr6D/MyCZyAdrxFyPce7aXk8GdmO8/lbVM9DsE0fvg5l7J/2EIIRZIKQfturw5k9yPMEIhYp9+TOyTj7H26In3tDPQCwoxIxGi77+bvbKUxOfM3mOQFC4P2sjjVDYjBNhdu6XDm/E48W9mErrhGmQ8jpabR/6TU7DVsjZ3RbqsDN3vVzU9TcMIh4l9+jF59z9CzUtTqX7mCQCSixaQXLyI3HsfQugW0qU7MINBoh++j96yJZ6Jx6HvYgklHG60g46CwaPVeTdoos+so1uQPYYi/S2Uu4TPh7DYMLetU3ZNHftAux7ITSsRvQ7CjMfVcjOlstRAATh8xObOwdanL3pu/i/sNVQwQkFSq1aSWrUCx7AR6AWFOIYeTNGrb6upXodDCSA0ARmpIf7NzOxl0QhGRfkeg6TQ9UYBIr1zB8EbrsHYugVj6xZ8V16Dd+IkpBHDM24syWU/Ebz5OgL/uAlbvwFN90Sm9q5P0ggGqXntJeJffIqlc1f8F12GpUXL+u8rKzMiEcLl+lk92j1BKywg57Z/Yh80BLatQyQi0KoLwt5YvEJzOZFbtmI1Kgicfw7pE05EOBwgzcY73psxv9uH6D9KTe2bBpR0RHQZ2Bwgm9EkmjPJ/QQzHif8+MPUPF/P3rR06kLBU1PQfH6q/v0QNVP+k7VN/n+exzH4gN/k+OnSneyYMAYS9SQVa5eu5D/xbCNmYLqslMS876i6507MUBD7oAMIXH8z6VAIa0kJO44YlVUHBSj+6AvM6jDpjRsJXnVJZrle3ILCF19vMsPaE4zKSqLvv0v1lP8gnE6Knn8J+dEz6iVWC3HgkeAvQLoCxL74BEfndoj5H9fvpGVHEkkXweuuIfeeh3AeenjWIEJKiUwnkckksroGNB3N50VzZE/PGZWVhG67kfjn9XWr3Hsfwnno6L16kRpVlQSvuJjE/O/rF2oaxR9+3sgyS5qm0loVGmY0hozFEXYbwufHrKlG00Du2IRMG0ibC82qw8IZEK1Wz6R9b9LOIiIfTMd/yZVoMok5/T/19VOLDW3S+T+bXZmxKJX3/Yvom69mlumtWlP43Cvo+fkYwSChW28gPvNzAByHjSXnupuyWn1kOqkCssW6R1lEGatBLp2LLN2EKGyDaNMV88vXIRlHG3s65JdknptZHUYu/gLWLanfQZ9DkAXtEJuXwaoGf8utOqENm7hXov4ylVQELmnWslv/uCzgZvw22F0m2Tx02k+QNdVE3nwta1l6zSpkJIKwWPCeehqWBlmj45BDsXb87fq/ZCyWFSABUmtWNwp2ACQShG68NkOQSMz/jvCT/8baujVCtzQ2bbZYQdNIrVtL5LWXsr4ydmxXx9lHpJb9SNV9d2EGK9C8PsyNK7MCJIDcsBzhzSH20QdYAjmIld9l72TbWmw9e4IQVN3zT8xQqH7beETp3H71Nqz5AVlTRdmZp1D1wL0YwSAyGUdGq9W/SE1WgASoeuCeLALJnqD7AwSuvxmtbqBgseC/4ho0TzbJSMajyOXfYs6YqqbRqyoI/fNm4rO+JvLOG1BdiZzxPHw3HbHgIzSHFalZSRX1Rh50PLLLYFi/BFuHdvgnjkWzKj9IbcI5iI59EN0GoR19HjiyM2oZiyDDQWR1JbLWO1JGIsSmv5e1nrFlc4ZdGp87KxMgAeKfzyD+7Wyin80gvX0bZk0YY8sGEgvnUz11CslVKzDD4Ub3RsajmF+9jVz+LZRvU9e/bC6i10EgJeYPXyOrK+s3SMazAyQgNRsVf7+SVMqO7D8a0b4XstcItCHjMgFSxqPqGivLkE34fgqrDeHyKm/S5gDZjD2gebp1f0EINJ9f2TA1RG1NUC8opGDKi6rWZLMhvL4mSRq/FJrb3YgZaD9gaKb/TxqGateQkvTOHVmEFIDkwvlK2WfTRgpfeI3yC8/F2LYVAN/Z5yFcLrWvpjKrfVREkek0kQ+mZT6bVZVKKWYXCLcfKTWiMz7Ef+75ShBgV9S2oagXtMqmZCqBXPglcvUitc7WNWjF7fCdewGhm65HzwngPngwLPwMbA7kkEmNzzEabcRuzTpsTQ0ylVQ9lpqGpU07il59GzMSUVOzXm+WKIORTCDW/IBcUBt4qsqhbAs5V15NauMmNF2gez0w6gT1st+6luT6zVRccXFmuj1w9bU42/eBVBJp92Cu/gGt20BEThEMHa+IXbu25MRqML94Dcq3qQUlndCGHQ1CoBcWkt7UQJNXiIxaT2LeLgMS1G/ErKkheN3VFL05jfDTTxObrp5j+OEHyLn5DlzjJ2bXwY0U7NxF93fzKkTPoeppmSbJNauxD8hBxmtbQOwuZO8R4AooA2yrndSKZZRf/FesPXph69GD9IaNBG64GavXr/pyv3kH6ljVgQK00ZOV/VYzmrGPaM4k9xO0QA7+q67NanZ3H3tiFntVz8vH2rEzltZt0QM5mIkERrACMxFvapf7dvycXPKfeFYpxwiB/cBh5Nx8B1isJFf+ROj2mwg//igyElZTgLu8TK29+2BUVlLz0vNUXHERBc++SM6td1L4+nu4T5mM7vVh69Ebz+Q/Z21radN293qvu4EEbN17ZT4b27dhhKNQ1KA9w+5C9D0EbFas3boT+fgjZLve2TsKFGLsLAXDwH38iYi6zC2VVC0RnQYg+41Gdh0ClaXYe/fBPmgIybVrkcm0CoKJGCIVwdqla9auPX86Ha2JGpxMpUitW0Pw2ispv/BcIu+9lbG90vMLsLZthx7wI6KVmItmYm5Zg1kZJL18ieofbYhUEpGKobdogY0azPefwvzoOUXE6XIAodtuqh/MSEnlg/chW3XHTEvKb7iR8PufYtSoQZnQ9UYB0jQMjNIdyFY9oLjWSWXrGmT5VrTcPALX35LVcuL581lobjdmTQ2OJpSbHMNGkFqxHBIJZCyWCZB1qHroPtXi1BBCg12Nmq32+n7Qtr1JzJ+v6r5WG+lQCDn8JKqmvkLZhRcQfv4FsDpxjh2nbtnypUTefJ3UmpVotUxjWbG1PkACVJYh1yxWU9sNn108irl5Neac6Zgbf0LGG2eczWhGcya5nyB0HccBQyl672OSC+dj7dQFvVWr3ZI9jIpyqqc8TeL7udgGDsZ31nn7XNfb9fi2rt3If3KKyq5sNnSfn8SihZT95U8qIGganokToDpEzk23U3nX7chYFGuXrvjO+xtVD96H44ChxO+/m+SPi3EffUzWMfT8fITWg8KX3yI24wP0lq1wjjoMze3C3LoWgjsRrTsjrU5kNIqwWhC6qDWFzgNvLsLhwgxWYOvdB2uv3qSWqqm16jffIPfGWxDJGDIVR/gLwOlGEwLfGWdTdsFZpEeOxNL3MERwM+QUQYvO1Dx4P4Frb8Q55gg0R52KikAOnUT4+Skk5n2PrWdv/BddAgjsBx2M3qIltOiAzGuJ2LEWXD5y7vgX0Q/eJ71uLa4jx2MfelCTjihmKEjpn07MEFoqly1F3HgLzrFHItw+xdpdtxT5fYPaaauuiOKuyrOxsix7h3YXFk0g19UGUJsDWdgepCT39ruJfjSd6Hu1wvCJBNJiI3j9taTXrsE1ZiwiUom58Uelo9uiPTK4A3ZsRLTtjlEdpeKqy0Bo+M46B1v3oYif5kL5NkTrLth696V4+mekVq/A0qoNWm4emtdLesd2ZCyG98xzqHn1JdAEnlNPx9K2LekNtcEo3bjBX8Zi6v+6+p+uK/3efofUZ9CA6D8SmYwjjvwLqa3bcB0xHmGxIOMRrG3bEfngfczKKmzdexKfMxujtJScm+/ArAyRmP89vnPOx3PcCYi62nKotPG5BHcgpEldXiBTSeSSWfVs6tWLoFNfGDymkd3ZL0UdW9kMhxEuN5rH86vIZM3476A5SO5HaG4PwmbDMvYIZE0lwqIhU4lG3n5GVRXBG64hMWcWgGJVrlxB3n2PNClJti9oSNIxaqoJ/+cxFSCFIP/+h1WmMOddrH2PIP/xp8FiwdiymYrLL8LWszdGuXqJ1/3fEMJiyZgr27p1B2pH53Peh1oPSLnwczhwPNUffop33Fjkd+/Xto0AbbujDT2K1PJlhG6/icAV16C3aAFCwwiWY1aUIbYuR+SVQE5hpiFeLyyi4KnnMGtqwO2Gdt1rg7CDwDU3oPl8WVmUmUwTuuduErWKRMl0GqO8grJzz4CkmrK1tGtP4LqbSa3YhLa1ktCdt+IcdTiW9u2Jz/kG+wEHZl27NAyIVpNYvCDLFgwg8u472Ht2Q3TsAckEcvHM7Bu3ZSVal8HgGgRlW+sVgFp3Jb19B1Z37XS1piMPPJrKhx4i/tWXCKcL3znn4/vrxYQfexhLpy6k16whuXgR9kFDcB98IHz1WobgKXOL0fqOwFz+LXL5t4g+I7F27ETs0xkE/3E1hc++gO7yIdp2U4dzOtGcTizFxdnna5qEbr4O97EnkPfAIwDEPv8MIxwm98570Vu0RAvkYOvbn+QPizKbuU86FWG3I7/7WDX8+/PRho5X7T+tuiBDOxG5RUihK1GAhZ9jQSJaHY4M7sCc+wFUh3C17YrnrrswVyxCnn8e0c8/R8bj5N11H0IDuXI+8pMXkE432pCx0K4H1HqsZn6rHftmnFsASCWQK7IJfHLtj4h+IzMqSL8W6c0bKfvLaUpOUtPw/e0S3Ceeiu797xtaN2Pv0Rwk9yOkYSC3r0fOfCMTGMSwCdCuZ1YLhIzHMgGyDsmF85G/wbRrQwghMtmQY9hwLF4rcsV8RI8D0VIRKp97hvhM1Zyt5eTgPe0Myi++AKxWnCMP27uDpBKZAJnBstl4jj8RVn2HOHiiYloKDbMyiBEKYWnbFqQkeO0VGTNcx6jDsZ00Abatw2zRheRnn5Letg3n6LHohcXoefloObkkFy2g/G/ngMVC3j0PYCspQpaugxbtlT+l1QbJRCZAAjjHHknN1OcyARJQPpo7thN55001La1pxD75KPO974KLsq8pVo35yVT0NgMb3QKtoBDsLlJr16I57QizCRk1TcMwNfTDJkMsjPDlgAS9qgp8tdlGq65EP/gw80xkNELVQ/dR8OyLuCYeg++cC6i4WvXauo85BtYuyj5GcIeaPrXa1FTumgV4jj2O2KczAIh8+gn+M04Dtx8jXEV6w3qi06dh7d4D54iRGZcM4faQ+68H0f0B0ps2EJ35OY6DD0HPy6fq7jtI/bQMraCQgv88T+zzT0j+uBjnyFHYhwxBGAnM7aqNh9LNmDOeRzv6PExTkNiwncT0T/CfdCLyy3pWrTANzE9fqh88rFms/nasNpj9Fu7h45BOJ8LjRa6Yp5xoABJRzE9fQjvmQhh1ospWjRQMGoN0+DHKy1RGtx/6P2WsBmI1KGUoD2YyReUdt2T0ljFNwo8+iGvcBNgPQdIoLye1bg3oOtZ27ZsdTn5DNAfJ/YlEDDlnehbhQ373MaJlR8UQrYXQtEaSZMLh/E0sgRpCc3vwXXAR8dnf4Bw5ErF9NbJiO6LbYPSOvcm55jrMiy7DrK5Gzy8g/NLz2Pr0w/+3i9Hy9/KPrin2bCqJsNvQ+g5X9R+hIbsMJXTnnaRWrMB+4EHk//spyi8+H7O0FOFy4z/3fMT6ecjB46i47jpSy5UaT/jxR8h/4lkcBwzFDFYQvP7vKqu4536s4Y3IVTMBkEKgjTkNw+FDmia+K67B2roNwmrFjEWJrK4N5LqOa/xEnCMPRS9qgW3IUNLbtqLn5KLnF+AYe6RSGXLUZxcyEUOuXwY1legeF/YhB2ZssYTHg/+8C0ht30nFBWfjOXUy3uEDGxXBnwAAIABJREFUs1sV2vTADNdQ+udTIJlELyxCy8kj/85/Ir55A/odghg8BjOeID7/zUa3M71lM75Lr0aUbcRz0smEbr5BiaWnm7j3pkTJC9U+mwaya7au3RAFrVWP7scfEbrpH5nvor37knv/w+g5uciqSqqffZLUsqVYe/Qi9/a70O064Xfexj5gIP5LLldTq2Yad5di3AedhVbUSnl4mkm0Q0/G/GSqYqrGoxCPErzuHyTmzsI5dhyyoS+pxaqCYyqbmS23rEY74AjkT9/DmgVorTpCMq6eQ9aKElmxDdG2O6KgBJkySP60nNDtl2CU7sR11NH4L7wUzetFdB+MXFZvZyY69vlFmrcyVoM5Y2rGdYbcYuSQCaTWr9tlRYkZDEKD3tPfAkZZKaWnn6ykEwFLm3YUTHmxOVD+RmgOkvsTsrYHriHSqUatDcIfIHDVP7JeUv7LrkI04au4J5iJODIcrvfey81rRN6wtG1P8TsfKKZqdCtUbFej8RXzFCP3sMnoxV3R3G4CF16GGYmoKcPKSkyvN0vH1agoJ7VqJWYshr13H7S8fDVVlVMEoZ31t6F9H8zyIGxfqpYfOJHySy7E2LEdgPhMNX1W8OQUjGAFtvYdwEwi/KNIVVRmAqTamaTq4fuwPvofME2M7dtwjp+IvX9/5AdPZ61nzvuEhL0lRqgSzeEgdOsNyEQc7/kX4j39LyTmzCL3jn+RWrOK0G03IZxOfGefj63fAPLuewi9oJD0pk2kt26GaATTZkXz+NTzqx3kiMWfknPZxRjR8zHD1Vi7dkd4PIgd2/Ff+XcSixeRwoOl3+FoldsgvwRZ0pXqO27OZLJG6U6M0p0k167HVtBKCSYECtB6D8c2cIgywm4Aa5dulJ17BjmXXIa9dy+K35mOUVWF8LRHzmogUuHPRzrc9QGn0wAi7yhyjbVbDxzDRyI0jXRZKeEn/511jOSSH5BVVRimpPzSv5JetxZQRJmKyy4i/8GHcR50MNGPplNx6d8QXh+By6/GVpyDHsjD/HCKsjIDKGqLNvQozK/eUjMFuoXEXDVzYoarkFYHGXqbkVYi9LvCn4eMhjPPVlitqh8zpxBZvjVrVeGt1UF2ejCqtquZhlrCU/TtN9Dz8vGdcwGi1zBFYNq8Cko6IApb/6J6pFy3tD5AAgR3INIxnKMOI/JGgwzZ5UYvLNzn/f8cIu+9kwmQAOlNG4jN/ALPcSf+5sf6X0RzkNyfsFiguJ2SkatDbnFWFgmg2Ww4DxuNfeBgUmtWYenQCS0npwHx5OdhxmLEZ39N6PprlAxdYSEFTzybcYbIHMvpRGvdFkvrtshQGeb29eolarWhHXYKsiqI3LQMs203cOdQfv6Z6gVptRK48lqcRx0NsShmPEHFRedmiBtaIEDh1NcRXh/a6FORqxYhg9sR7XohLS7kti2ZtgOJngmQdUh8Oxvd70XXksjvpitVnp4HIZtSi0km1QDE6aLwlTexFBRAuomp6VQCW59upLftoPyCszKLw/fdTcHU1yl84z2SS5dQ/fSTme9Ct1xP0VvT0XNzCd50Xb11mNVK4dPPYencHYFUOrqeANRUIr7/AIsngDZmMumyCkTVDqzV67EW2nFffjnpUDWpUAi9pDfhxx/FddQE1VKy6zNMpTA7DCG5bAm2kp5opsR78qmkli0h8e0csNvxnfc30DWM1StJLl2KyM1HVofQW7chuXEdttGTYd2Pyoi6dVew2KDPcEynH61FO3wXdSVw1dVKyNvpQUbCUFXR9G8qXI3ucGQCZB3SG9eD3UFy+exMEJDxOMFrr6TFx59jLvkq271k50boNVT5WnboixGut3BLfP8tXHEVeHOgOqQywdItityz+Cu1kt2J1u8QzLkfAiD6HFxvo9Z3uBLQr1G9laJzP2WuXfcTWLu6UXtT7IvP8Jw8GT0vD9GqE7TK/hvZF0jTzBoQ1kFU7sR3/oXIVIrYZzOwtGpDzk23of2GbV51x09va6xFW9eu1Yxfj+YguR8h7C604ZNUj96ODVBQgjZodJNOBcLpRNdAHzhAUeRt+9bgLKvDBK+7OiMgYJaWErz+GvL//RR6Tm6T25hSRx4wEWJhtKJWmEtnwaYVan+rFkL3A3EcOJSadWshlaLq3w/hGDac0G034jz08HpmI2CGw0Q/m4GWl4dj2CGYzgLi65YTf/529JYl+C+7ChKlsH6ZYrk6HFkm0Y5DR0O4AvlV/fSiuX09ltFnoLdqjbFlc2a55/QzEG4XIhmHNXOR3+9AG3s60u3PsvESHfsijJiynKqDrqPl5CJD5Vj69MtqkK9DfPbXOEYdnuWtSSpF5YP3k3vnvSpjNoLq2YZ2qunkNt2pfvNN3IP6KkWcuueycxPawSdQ/eI0vGedS/zzTzA2b8R/1XUZazPNH8A2YBDWXn3YOWmcmhYVgtz7HsHWroScG24BqQZCsZmfIwDnuAkIn4+yU48HIOf2uzEryrDqcYTQkOXbFXPTakeMnkxq2TIcJQJt7QLkmh+QFosiqVhsiM0r8Z1zAaFbrkfzB3AcejiWNm0xw5XoRUVohYWYpbWMUYsVx6GHgRAY27fjv/o6MAyiH08ntWwpZjiMtuvsCbUaxgcdQ/SD6WiFFdiHDccsL0cvaUXwzjvIu/1OBClAIAL5SuO3Qx/McAjN48Pcuh4KShCDxiAKWmZIXMLtRxt3pprK1S3qehtkopaS1o3Oxdq1GzQhf/dLIDQNOvdXzjQARW3QBhyKTMbRSOG/4ir8F14Kmt7YiDyVUrM+bvcvlsQTmobntDNwT5ikLMR0nZqXp+I66uhfe2nNqEVzkNzPEC6vciZIJ2vluhqLgEvThLKtmF+8qhrkLVbEqBOhqO1e1yXNaLSxws6qFXv03hMeD4lFC6h64F8UPPIYojZAZrB6Aa4jj6LmZeXJ6Bo9lvDzz6jjVdarotj6DSD3hpsR0aBy67DplN9wDemVtftbvBA9Lw/fuReozGXTMnJuuI3gTf9QLiJuN4FLL0OunJt9fCONCO+k4LGniE6fRmrTJtzHnYi1RaEid3w/A9F1EMKfC1Iqx4+V85BVFYg2XcHmRP44C1tXxd70TD4D55gjkJEIllYlyE0rsXbqTGrNanL+/g8srUpAgtR0dK+bwmdfoOrpJ0nMUcHSrKpUDe5VlaQ2bUfP8SO8xYDA3FmK89DDYdUu12AaULEVY+sWVbezWEitWomlVWsKXngVY9sW7L17QXArREMUPP4U5VdcioxE0AMBKh/5N/EvPwNdx33cibiOPAq9sICcyy7DDFeTHHsksRkfkVqzCs/RE+HbdzA7D4biLpiBdmg5AWR1NWZ5GXLLqnpBhVQSOe8Tdc/Kt2EfMoGCqa9hLchV7SemCa1ag9ulntV1V2Nt247c2+5Aqy5Fmga2Xr2pnvocwmrFe+a5JBfMU0Gq60BVi8/8QByYSdhxwjj1nFq1pviVN2Dn5tr6YTekxUZ46ssgwT3pOPSWJZiRGDuOmQimiWPoMLT8AlIrp5L/8OPoDaTnhNPTpPgEgJabi+es85QEpGmit2qN/6xzEGWbkY6uexT8r4OM1SBrW3VEoEAdryECBYgRxyJXzkcbeDjmZy+reimoqeZDjmvkVWmUl1H94vOkli3BOXosztFH7HYwu8dzS6cwt2+j4vKLVMB1OMm7/2G0XRnKvwDSNCBag1w5H0wD0XWQ0r3dtc/1/3P8b13tfwk/a4Ibj2J+/Xa9gkw6hfz6bcTR56leur2A5nYr4+Sq+uBlH3JgRmGnDjIZr9WsBGGx4jjoYGy9+6DZLUihNS0aXXcMf4DUmtUkf1iM76+XwNNPIKw2cm++FTH3HTWaB8yVuRQ8/BjG1s0YwSDVL75A/KuZeE47E63bYDSXF7uwUDx9BrIyiHDY0SyqhtRI00bTEYs+xj20H+LU05ArvoVlq5C9h6ENPAxz9jRkTRXygKOJfvwewm7F3qMnuicXZr4KRhpLj2H4r7keTJOyM05VAcBiIe/eh3CfejruiccgFn8K62crlZqeQyFWgb56NrmXXELI6SLx/be4TziJxKKFOIcfQnrLZuJzvkHzeAk//ggYBt4zz8YzqGuj+4bDjVlZqUyVdR1rt+4Iux1b775IvwP52dTMqpaWHSl8diqprdtILPlBBUgAw8AMV2H1O5DTnlAvLYuVwJl/Vln89Gl4J5+O7DuKmk9nUvPcXwFlyFzwzAvImhrk1rWNTk2WbYFAPmLJl9gOOU7pvtaJpK/7Ee2os4l99D559z6ErUtn5MdTkHYn6ZaS4LVXZvYT/HExhVNfQyOtPCyHH4NctUBJv/UZQeWjj6gA6Q9Q+NhTyPmfwKaV6hxWfA+9R2CUlRL7cDo1L0+l6O3pKoDV1m3j39ROvdpsGRFzMx7HDFYQ/24OlhYlWDt3Rc/LQ6ZTmd+i5nLhnXw6nvETkMkEQqYRS79ARqogvwQjGlfP3GJBOJ2YFRXE58zC0qYN1i7d0Bw2VV+tnaGQ3hy0I87IUu8RdqdqOylui5z/aebYgJpqrq6ABkHSCFZQ/rdzSa38CVBqRulNG/FdeGkjHeGfgxkKEbzu6sysjIzHCF5/DUWvvwuuX2kiHavBfO+JjNOKXDEfbeL54Nv3YP5HRnOQ/D1AGrX08QZIxBoRfPYELSeH/MefIXjdVaTXr8M+5EBybro9S7xAxqPKjqoum2jZETF8ErrHDbFqxFF/Qe7YqHobTRPR+2DSZeUIfwDN4cBxyKHYBx9A/OsvqXn5BfIffYrUyp8QO9bUvxg0He3AcZjrFqGvX4bu8pJ37TVEFy9B2GzIj97OBELh9qN17g+FXal+9118xx6L3Lyqfl95LRC+XOg8EFp1Rn78PMRq61ktO2DW6X/2O5zQ7bdmCYq7jjsB3+HDEKvmIbauwDliFDuPHV/Pvk2nCd12kxKc37mqvq4kJSydgxgzWY2kF84g78abkTVhcPuofvNNhMuN8+ARGKXdKD39pMw+a956A8/xrysiiJGGDn2Qhe2Qmg1L+w4Ih5PA1dfhPHwsut+vMpQFu0z3bluL1v0g0hs2kFyyOOurwEWXIL96rf53kU7BkpmK5KVbMCNRzKSOe/wxmKVlRD98P2PI7Dv3ArClYOsayClUmVfZVuWxuWaxIvlsWJbtIiIl5orvEW4P1VOeJvfMk9XvsnVXItOydV6RkthXX+DpUYKUSWjVGZFXgpSS+PJl2Pr1xzV+IprXhx4IYNYGyAxWzcdzzLHEPpwO6RSRN17Bd96F2PoNILm43vrLffxJiNqGfLMyROjO20jUOq7Y+g0g/5HHYc0i5LK5iuDTfQha9yGYX79STw4C8OdjlAcJXn81qWVLcY4dh/uEkyk/78zM7It98AHk3HgzosEUPtUh5MafEN0HZ52+EAI0HTPShF5tpDrr2DIazQTIOkTefA3vGWfDPgZJmUplaRQDmMGKpmv5+wi5flm2FZlpKHbx4DH/U44pzUHy9wDNogg9wR31y/z5jeW79gBhsWLr0ZOCp1+oVdixo/uz1X1kqLQ+QAJUlSOi1Zifvqio+YDoOhAx6iQ1rYLE4dhGy3feQ+p21ZcWiZD3wL+pfv5poh++j++iy2HFnPrzaN8TuXUN1HkaViXg++l4JinCidllQP13kSrkT99h6l6qH74fPTcX1+jTMbeuA6sDU2pUv/wKltZtcdhciLoA6XAh89ogXXnQrj84XCQWzMu61ui0d/GdeipsXwvdDsz4ajaEWVGOcNghmE0iApBVFfWKOLEa5GcvgsuL78Q/g82KyMvHCAWzWl5kuIqKW28h/+57kIkkVU8+RuyTG9CLW5Jzyx1Yi4uwWFKwfjGyXU+kzQEeP1RnC6fLZJzEt7NwDD+E+BefAuA+8RQ0px1z19aIwraYoUpSq1dQdf+/1PlYreTefT9GKEhi7mzSWzajF7cArwetdSd1bTWVyi7K5VX13ESsXs+1IXQrtl59MHbsQEpTveyTMTU1vQssLVqoe7V9HYa0U3rysegFhfgvvpzEgvmErr8GgJZfzmq0LaaRmcaztGuP3rY9msdD3n0PE3n7TZI/LMR52BgcIw9DppOkN+0k8f23+M48G/3qf1B61mlK2SdcgfyxvidWLpsLha2hc3+lqlO3vPswgldfSqq2FcjWtz/hh+7LKk8k5n2HWR1Br+0zzSDSQIC9AYTdieg6CLlzU4P7Z0EU7lIXtVgy/cCZbX0+yA7jewVhd9SKStT3Jlu7dkPsxtt1H/fexCKRJbX5v4DmIPk7gHC60UadgDlrGpRuVgSfYUc3rn3sBfbYG1W6Oeuj6NQPc9GXmQAJIFcuQOs+BLllNeZ8NdUnATF4DHQZgObz4Rx1GLYBAxG6Bc3jwew5FDO/HSRjCK8n6yUFgGkiyzarEXjXQSprmfcJ+HKRvUdRee+9AMQ//wxjyxZin3+CjEYxdqpBg2vcBJyDBkDrLmpk2+VAgrfeTOLb2WCz4Tvvb/gvv5qq++6uvzaHE5w+jG4jiLz6Kp5Jx2Lt3CXzUgQl+J7asAFrXitERXagFLlFyOqQakeoy9yi1cgfv4aSTogW7dBz8xCBAK6x43AfNR6A5IYNSKFRPfV5om+/ASj3F5GMI2e/k5FMM3/8BjHqJJKetliHD0IsmAHRMAQKMErLSXw3F89pZ+CadBzR6e/hOe54ZDgIvjwIN2CjtumFljSoeuSB+oCdSlF11+0Err2BxNzZOA89HM3pROga5rwvoFS9xOWP3yBGT0a0bI/w5iBdXvXs6mY1LDa0zv2wezZjbX8OWssS5JqFsGUNriNPJPL+tAyL0tq5C/Z+feGbN5BtekFKaeEa27YSvO5qCqa8RPT99yCdwigtRStqmy103qk/0VnKTFmTSTSXAxkJo+Xk4v3LOare5nIhTZPknG8ov+Svmet1jj2SgieeUaWGLbtkqACbVqjfLyB3bITcFuAOZP0WNIcDM1LTaFOZTmf1loL6u9kdRMsOcPBElXE5XGgDD1es3gbQXG7cx51EpIEtWeDKa9F+gbqWnpdH/kOPEbrpHyR+XIy93wBybr6jkR3eL4Fo3xO5ZFb9zI7Fiug+JEOa+l/BfguSQohngfFAqZSyV+2yXOA1oB2wAThRShmq/e5a4CzAAC6WUs6oXT4QeA5wAh8Cl0gppRDCDrwADAQqgJOklBv21/Xsdzi9MHAsMpFA2OzwM/5/vwSipGO2RJrLA+sb2z/JSBi5ckH2skVfItr1yLSv1BnuGuVlVE/5D5Fp76Dn5SvSgD+/kSapcHmR29YjN61EO/o8xElXIKMRKi65MMM+TSxegO+8v1I95T9ZI3rvueej+QPIQCHktaT6gw9VgARIJgk/8gAFz7+SVZP1X3iJ6lFc9ROeY45Hc9rJu/teqh57lOTSJdgGDMRz8mQqrrmC/H/dh96+N2xcpoTUBxyK3LAc7C60oeMwl9WTcWRNJaI6hCzdjOg3kuK3psHaH2GJstZy9hyqbKfqaomAll+A5rBma4pKiVw2ByMkCD94L3n33Ico34QMlBC8SNUTg9deScEzLxC47AqEriFXLUIbNgFz0UyV9RW1BqcHQWNbNKOsFC0nF/dJp+I7+WSE04EwUsjSTVnryQWfIXNPVYxrpwdt/NnILashnUQUtkUi0WQKraYUaRaiTTgXc/l3aKEtFD73EumtWwGJ7nYgFn8GnQeSKguheWV9xmEYpNeuQW/RAmPzJtKhEI4RxyI3rVADtzbdwF+At20PmDsNqsqRgLTale2XNwdRawxgVpRTed/dWRl8bMZHyiC6qAgiTbzSWrRH6FYYMgZqqql+8QVsBNBblmSCfOzrL3FPOp6q++sHWnpRMZaWJWiFJ2D+8BUg0AYemtVisiuE3QkdeiNKOqp6ehN9l5rPpyTqJh1HctUK7AMHq3aUXygeYilpRe59D6v6rd2Ovht96H2G04N29HnIdUvAMBCd+qj31P8Y9ufE8nPAEbssuwb4XErZGfi89jNCiB7AyUDP2m0eE0LU/WIeB84FOtf+q9vnWUBIStkJeACo/3X/wWBUh0mtWsnOP53AjvFj2HnKcSSXL1P6oL8lvDmIwaMViUjTQeiIdt2z19EtCF+e6llriHSqkVWUmUoReedNal56AVldTXrDesrOPxvRd2RWkBfdBiODO+sJAGt+QJZtUeSVAfUep0LX0XJzKZjyMvYhB6oa0zMvYvE4Md97ArlkFubOLSTmfc+uSG9YR/6Tz+K/7CoKX3kbM5Ek9I8rqXnuGUpPOQ7hsCPmTcd//AQKHn0c94mnELz+75ilO6l58w1k58GIo85FHnQMMq8E0a4n2hF/xlz6LWyrV04Rrbsid25U3pamgUhE4Ke56v6kU/DD1wgzndWfKnS96fqyYSCsVlKrVmKUBaFtL4K335p5cec/+Ch65SbktCcwpz0FFiuyqhzRqhPaiGMQ7XuBpogglnbts3ZtHzoMvbAA36ghSo+3qhqzunG9rOFzFUIgXF60LgMQnQdgLp2F/OBZ1b6kaWimgTl3umJqR8Mw82WsbVpjplLIlIHZdTjV3/5I1eOPYVZXKwPmWlhat8GsqMBxyCg0h5Oqx/+thNv7jVRC47PeRlSXZzflpxLIJbORDXoupWk08qm0du6CRIBuhZxidV/q0KYbhrRT9egDGBVBpNONY9gIIp98RM71t2Syt8TCBTgOGUne/Y/iOHgEnsl/puCFV9HzCxDFbdFGngADjyC5rYzEwoUY5WXszrBeCIFwuPcoTKDn5GDr1RvPsSdgbduukdfovkL3B9ALCvcYIKWRVn6p4SAyWtPIFWVXCE1DuH1ovYeh9RuB8AR+cxWwPwLE7h70b7JzIdoB0xtkkiuBkVLK7UKIFsBMKWXX2iwSKeWdtevNAG5GZZtfSim71S4/pXb78+rWkVLOFUJYgB1AgfyZCxo0aJCcP3/+nlb5P4NZVUn827loAT+hW27IagDWCgspevmtX+UE0hRkOq2mT6SJ3LoG4Qkgt6xGbvwJXD7EoNFIU8Cyr6EhG7JNV8TAMaQ2/D/2zjs+qirv/+9zp7dMeoFQQ+9dkN67ir2vvaLr2nVd+1rWddfeOyiCKKIuigLSld4hQOgkpGcyk+kz9/z+OMkkIdHH3XX32d+zfF4vXsCdO3dm7tw733O+51MOEy3Yj2XAIITZTMXttzR2xAFSn3keY04WhmQ3mtOJPJKP3LYywZwVA8bVEnQiiDEXIPQ4MhZVLGCHMifXvV6k1NFsNpUNWF6k2lbuDPy7j+F949VGr5nxzmyqnngE59nno0fCeJ/7M8Jqw3n5FdgmTFY/QjVVsH8DovQo5HZC5vUHixXdHyC45FuCK5aR+sDDGA6uQ+s/Bll4EJHdBn37KggFEJ36ItJbKiu/7LbgdCO3LFeaUpMF0bYrWBxIuxPdkkrZ9Vehl5WCEOR8tRjWLlDFpQ79J1Hx7HNEtmwi7dnnMIeKkHn90aMSaTJjMkaRaxrHT2kTL0ffshzhTlXt8kANvq8WYxs+Ct/brxPJ34VlwCCSbrgFzWpCLy9HGi2UXXExGa+8juHADwnhPYA4bQqhw8UYMrIwts9rZKgva6pV9mRVCThT0EbWzv4k6nrxVUJWW+Kt+xLdm09w5XJMbdvhOP8iqh68n/CGH1XSzBXX4JhxDmgGIls343nyUWRNDVpqGpmz5iCWvA+ZrZTp+eaTiEytOqMNPwthMiPjccIbfiT84w/43lPuSuaevXH/7i48Tz9OdG8+5tOGkP74EyptRgoCS5ZQ/fxfkAE/WnoGWR9/hiE9g3hlBRg0NE2owZvRjDRb0SxWlQFqNjdKfYlXlFN+07UJwo2WnkHm7E+amsH/Qsh4HL2ykujhg2hutypw/4MERA+F0D1VRPN3q5SW9AwMyU3j25p/vRiy+DByxadqfdXqQBt3EbpmBU0kOkP/zRBCbJJSDjh5+797TTJLSnkCoLZQ1nk0tQR+bLDf8dpt0dp/n7y97jnHao8VE0JUA2lAg6GoghDiOtRslNatW/9qH+afgZSS4OqVVP3+bjLemtXEIUMvLUU2MOD+n6CHQ0ifIrZoySkJ/Vfc40H6a5ChEJo7GUN6Ohidium6f6uKEMrrhRgwXhlEe6qoeu0N0h/7o8rgKz6MyGmPaN8TzwvP1dtsCUHGh59gap/XpEhqLidlN12PDAbJ/nQh4sC2emlJcoYqNBuXIPqNgYItqghJiUxKQ5twCTjcCJcLEfIjw8HadRANWVOFSM7E2WUQkf37CS1firDZcV1zA+Etm4gV7Ce04UdMbdsriccLr6Alp+J74xWCy5ZgyM4h5Q+PYMxpj2YyoplA//4jjFOuxj5sKI7x49CcDuQBIB5H7v4RWXIE0aG3yjysKgWbA1lehDyyB63/WMhqDeVFaIOnqPNVVYJIy8ZgMZD5yqvIaBxhsyIrCjFMvAx972YI+pBZ7Qmt20hkyya01DRM7drBqg2I8kIMOe0Rw85ErvuakyFLjiCGTIWSo8iqErSc9jimTqds5vU4z5iBffJUokcOIywWTkwag3XEaCz9ByIDfiof/gPpf3keUXIAQjWIdj0I7dhD5R+UHaLz8itJuv7mRC6jcLrV9xGLITUNajzIKlX0tdMmIY/sRlaWEC8rpubTuVj69CN2/CixE0WkPv0sejgMwSCRgr0YrGbkicNY8tqQ+ugTVN5/D3plBdGDhzC7UlRc14DxSIOxkVuP1n2wGjxRy2Z96nGSb7uT5AceIbh4Ee7f3kHFHbcm1q8j636g/PbbSH3iKSofuL9RKoleXkb0wH4M6RnK+aa8EH3JHCWJMpoQo85DZrdtlPlah/C2LY0YqXp5GTUfvY/71jt+kdbyZMSLCim99PzE8oBl6AjlifszhTK6e6dKrql1EHKcdxFJM29rQtBrFuEgckUDmVnIj77qc6JpnfG9/x4pDz6GoVXu6uYOAAAgAElEQVTr/7r1xl+C/xQeb3PfjPyZ7T/3nKYbpXxDSjlASjkgI+PXnZn9o9CrPfjnKJF+vLwUY5vG7TJDi5ZqbfIXIO6pwvfOmxSfOYmSc6fj/2wecW818apKPH/6I8VTx1FyzjRKr7iIWO2PiR6NQbueita9fwty5WfIzd+D1YltyOnIeBzRaxjayHPB5iBeVtrIhxIpqXr0QZJuvAVDy9zEZvvZ5xE7fhzprYZohFhpGdrkK5QryvgrkAOmEq8JINv3QmS2qp1h1n5t3gr0TcsIrliK7903iVdUqCSV/VvRv52FXPsV+tfvQTxMyoOPkv3NcrI+/RJhMRP8VuU1hn/8AduYcdjGT0av8eOf+6F6LBYjfvwY5TOvh/TWyOMH1A+kOw1hMmJw29HsVnCnoo08u55ZXHFCRT2tXoiMBFXb2F+N1m8M+povERYb2unT0L+fp2aUhQVqtO6tRBzehrbxC8TKuYj9G4kePIDnk78RdbQkHpaEt23DecnlZL79HuxuQHaKBJEGIyK9GSPs1Gyl0ctug2jdFVlyBO3gRjJfek0RZcpLcUw/AzQN69DhuK69ATR1q8QOH6L4ovPwfLmUcMyFb+nKRIEEqPlolvLqbQBhdSCcbkQkhP7N+3B8Pxzbh750jhpc9RqOuXd/kq66Tq21XX0d5vZt0QwSQ7ACo9uJffBgRDQE5UcR677ArFeR8sCDgNL3irbdQeroO1ajTbwc0bYbtMhDm3CZkqsk3oxAs1gIb9mErXNrUq65FGGzJgpk4vTt2AYmK6IZW0dhqd0WDqCv+Kze1zYWRa5a0NRruRYNvVET2woLVWfmJyDDQdXePEnepQcCVL/8fCNNc3jNSmLHm9rLJV6rsoKqJx5tZLHn/2QOshmyUbOIxZqYxlNdjiEjk/DG9ZTdcFV9YskpNMK/eyZZIoTIadBurWMyHAca8qRzgaLa7bnNbG/4nOO17VY30JSF8h8KYTSh1Y4afe++RcqDj1L1+EPEDh3E2Lotac++gHayjZWUqlVqNCoiQi0imzfhqzWoloDniUcx9xuoyA5ST1jAxY8fw/fOmyTdcTfBRV+huZyY+4xFnNifIKzgqcSWIpFrv4AepyNSc5DrvkYOu4C0p57B2KYtkb35eN98nXjhcYTNRsbbs5Qdmd0OJhORPbtI/dNflRg7MxNhcxAPhKl89C7CG9dj6tAR11XXYg02kwRfVQJOG9b+/SESQOg2pd9LnAQduXkZYvgMtCQn+L3Y87Kw3X83elyj7Le34Js3B/cttxHN30PoRyVP0dIzsE+cjDCbiZcUY/RWgDtNsYgdbhXfVQerQ81oTpLliLy+ULAZrfvpKuuwxoO+/luVYXjSD6HcuwkxZKrSWtrdyNyuVN5xG7GDBwh++zVZX3xD8jmTET0Gqyi1Bv6fosfp6u+WHZQv6YlDta+viBPCbE2sd0mLHY7vQxQfxtGprSI8CUGsqBDzwNPQKyow9+ytrOWqqrCePhzhTMLUrQeeJx9tfO7j8Sbrzg0/T6PHpEQe3YfoMxK8Hky5OZhaZqJZBBQdQN/wbeJ6FP3GQsCLaNdDGVYczcc84gJMXbthbNMO4XIgOvdXexvNiKFnIHS9ySDRkJqG+3d3q8HM9m8RsSgMbdk4QcdiIeX+P2BwWEl76hlCP6zB86cn0T0eTJ06Y2zVRu2n641b3/Cz2mTbyDFU//WZRkXKceElP+mvLAM+9DVfQtEBSEpDG34WpGQhDAZkJNJ80S05AT17NXs8dB29vJkw6QbWjj8Lo0lpYxtepxktEwzfeFGh8hP+50mx/+fw7y6SXwC/AZ6q/Xthg+0fCSH+ArRAEXTWSynjQgifEGIwsA64HHjxpGP9AJwLLPuf1iP/k6A5nbh/ewfhDT8S3bsHz9OP477jHkztOyAsVgxpja9WGQogj+YjD+5AJGdAz2FqtqPHkXoMkeRWszcg+Z77MRjiiH0/kHzGOOR1N1B+1x3ECvYRLdgHXi+BxYuIbN6Iuf9A7KNHE/cW4eoZhZXzEsxBuWwuYsKl0KYbxiQnWrQY1m/FmtkKyyuvE1q3HuFwKLp5do56TrAGa5YLWXIUEfchvSY8r72EZdBgnJf8hqSbbiVWsB/N5UY6UtVnaGiGnd4Kc9f+aJEA0mBG+qppglAA4lFkURFytbqEBGDIaU/Wx5+gh6IIdzJSSkwdO2Hq3IXkW25FHN0FegzRqiWy1QXESkowRiWarifE0Xo4jAh60dd9gzZgvJKBRCNIVzqhPXuxtu8MZks9sSkcaL6wmC2AQJw2Be/sD/Df+4hy3AE1yEHC0V2Ijr0QQ6Ygiw6B34PI64UeE0TW/4ilezdE226qECGUhdtJYnORko3M6w2F+xEpWcjczvgXLsT70nOY+/SFEaMJLl5E+ouvIyxWAt+oBBi9vIzk+x6k8q7bEseyjpuIZvsJMXsDOZLo0BvRvqfKTfR48L2nNLOGzCyS73sQg+d4Y/H89pUqLuv7uervo/loVgvpL72pHHJ0XRXHXyBQN/fsDfEIcp8dYtWIw9tV+/aB+5ABP+l/fQGTXo3+2UsAWHLak/Xxp4R37MDSb0D9fWUwNNUmu1J/UpuspaWT8d4cvC88iwwGcV15LebOXZvdV0ZC6Ou+VgUSVIfk29loZ90Idhea262YrQ1awVgsmLt2I15RQWTHNqIF+7CNHqe8c50uhMuF/cyzqXn/ncRTDNk5aEm/MCnIakcbfzH6ygWKeZ6Ri+w6jOpaJrWwWuFX0Vb+38O/UgIyBxgFpAshjgMPoYrjPCHE1cBR4DwAKeUuIcQ8YDcQA26WUtYN6W6kXgLyde0fgLeBWUKIAtQM8sJ/1Wf5V8HYpi3ZC78hvG0LhoxMjG3aNqtvkvEYct8m5Jbl6v8lR5HHC9CGnYH+3UdYWnUi8613Kb36N5g7d8PaozOs/KS+L318H2mPPEbJJRdgnzIN4XRh6tSFyOaNRDZtILJpA5YBp8GIQU3yIPX8jWj9RqN/95Gy5jJZkK16IP1+TB06Ir0+ZJpZreEFapDr638c5JE9kNcHYTTgffkF3LffTdnVlyVYj7YzZpB8402wZgEEfNC6C6LLQDi+F33nGmjfB5nZXvnfBuqTI8jrpXxZa89HAicOYug3CoPTSayyHENOC5KuuwnNaUesnJsoxvJoPgw9h8q7f4cMBcl49yO0pCRVWKvKkeu+BE8Z8eQcZFouseIyjM4szO07IG0WhB6pT60IB9VxM3KhrLZdJjRE39HEq6qRZivWfgOpea/+x80983fEfTWILiMhqsP6ReBMQljtxEMxym66nnjhceX48vs/oFWVqY5AWg7SW4lw1spvKioov/UG3Hfdg3HkQCJ7dqEZSzG2aYtwOonm5+P+3d14X3kBvbqaqodnJta+A18sIO35V0h98TWCn3+GZchQbGPHN3JoagjRvicyfwOiUz8wmtCXzYOWHanZdZSaDz9Q10pVFWXXXUH23PlwdE/94CEWBU2rXw+zuxDuNITFqpiWu9ep7d1O+1lvUBmPIfQIetEBRP+xyJWfQeF+zLmdyJo7H6mZMBBGLlnZ6JoQrTpiGzex0XqbsNZpkxcqGUpaCzXbayZ8AFR6jqVHT9L+/AJSj2P4uTSPWLQRIxpQrc5ISH12IbAO6E/y3ffh//wztJRU3DffAvEYlffdkcgm9b70HGnPvaIYwRYrriuuQUtOJbh4Eca8Drhv/u0vJvYJTYOULNXCljq610v5zTeo4ACjkeQHHvnJ7/6/Hf+yIimlvOgnHmo24l5K+Ufgj81s3wj0aGZ7iNoi+/8rhMmEISsb+4TJP79jONREt4i/OpEWwZE9aELDdcHFGFq2RBzZ0XjfgBdhkLjvuBvbmAloVitJV11LeO1qYkcPA2Du1x+cTRluwuZQP3Z13pV9x1H18quEV9cmWKSkkjl7nlovspnrR891OLQD+7ipGLJbUP3cM41kAcEvFuC+7iYMU6+CeJy4PwDeStjyvdrheD4yvS0MnIY4sl2xMrPbo3XoDZpQrcyTEY+jr52PbDeIynvvIvWZ59C8JY1kBAAU5mMdORr/xx9S/dwzmHv3xTZ6nPL29JRBXl+Cew5R/dzM2hMhSHnsKbSMTPSyEmwjzlZrjzUe9G2r0EbMQC8+hvRVIVp1hKpSNJOVwJqVRHftJOOdWcRPFGFsl0f8xAnKLj0fpMQ6Zhwpd90DS2cj03IIrV9HvFAV2/CGdRSfexbu2+/G3qM9etFRSG2JLC1FuJMIb9sMFiuazUHJWVMSjkKW04eRcv9DVN5/F/7PPiHtxdeRAX8TcpjvrddJfuBhUp54RrE5f4K0ISMhYuUV0G8KxhS38ncFpDuT4LJ3Gu8ciRA9chSzPak+kaVFe2TFCWXMYDKjTb4SYXcifVXoX7xeP3jZv+XnvUEDPuUlGo9Bl4Fok69Q5zslUzGzrXb0bauaPE0WH1HF/aTiK5zJaKPPq72PNEQD0/Sfwi+auWkGlala1mCNUdNU1mrdf5OTsWVbsd57F8QjiEPr0XuNTxTIOlQ//2fMPXtjSEvDkJKK67IrcJx1NsJiVcsbvwAyWIM8uhcqTqiWfXIGWmoGGa+9TdzjQUtyo7lcf1c0338T/lOIO6fwcxCi+SBao6l+5nfiEM5LL8c2amyzLSNDajqOCy5NUPwNmVlkvDubrM+/JnvRUpyX/AaR1Urd3HWw2hF5vSHoVze43UXcF0wUSAC9qpLqV1/Ev/Az9KpmloQNBmQsroT+ZWVNHtb9NeiBMOX33EW8qAiqGjjf+L2IozuQCCKGVOJt+kP7nmCxItGUEXlDpGarNZeqUgwpKcQLj1P9pz+ih5thCRvNKpUDiBceR7Pb8Tz+EFit4EpB5nSg+pUX6/eXkupnn0JoGobUdCqffAqGnQPjfwODJlP+8IOU3f8A/g07kLpEHtiKKNxLrOg4gUVfUnbFxXj+9ASlV16M5nQkZlmhZUvQfX60yVcqz9uak9ZpYzGiBfuRaa2pevkNis+YRPGZkwh8uRBT566kPfEnqp/7cyPLvfDa1Yrh7EoisPAzwls3N8oxNHXuStoLr+G++340uwNisZ9lNepeD8JoQoajKhqsDpFAE8IZgKFla8jtBOktlHdq7xHIgzvQxl6IdKUhnGrGIvdvadxq1+Poezag1zRPRpF7N9cX1PwN6N99CJEwIjVbdTgCPkRWU/a6aNu12dlpvLIS3eevJfn8soLzSyCsdrSh0+vDCQxGxOnTFUO6DjYXWt/RCG8xwluKdvq0ZhN7ZDhMQz6iMBoxpKT+HQXSj75sLvLHRcj9W9C/eR95JB+MRgwZmZg7dsKYlfWLj/ffiFO2dP8fQNgcaIMmon87u76F1bqLouM3kFagxxA2F6LfWPTF79fvm5oNrhS0kxJBDGnpTWzstPEXK/9Lvw/hdKOv/0a1iAZPRu5eT6y4MZMQVJExtcsjtGYNtjbdlXNNHToOwL/wc2Q8jm3aGdS882b9a2VkYkhLJ7Ivn6QrryXw9VckzWicgyeO7UHLzUNm5hBYMJ/YiSLc19+Idmw7ol03xIiz4dheSEpDtGiPvuJTcLjRktwIq5XI9m2InPZwaFv9zMZkgdwuBJc9Aqgsy/CmDUT27QVhRBsylZg/nEigqIPu8SA0De+s93DfejvBFSvwPPEIjquuJ+X+BwEJsTiRTevBkI45rx/8sLv2yTp6Rbka8Jy09hb3elV0ly6wj52A95UX6mfcQuC69DfUzP6A8AbVlpTBAJ7HHyJj9jyie3ar454MIcieOx89FEZLz0IG/GS8M5vQ+h+wDhlG5X13qpml0Yj7d3fjOGMGmkv9qEspkQG/aofqOtGCA1TcfisIyJr1UWK9URzZhfvGm4js3JbIm3SccwGRLRuJ7NmFtf9AjM4WmCwOtNHnq/W4hsW4ubaqhMiu7VgGDWlauE8WsjuTIT0HWVOtCuyXbyL6jkL0HYXc+UNtvFN/9f03/B4DASK7dlD95yfRq6txnH8xjrPP/fkW6t+LpDS0adckou8wWxENwtaF0QgpmWhDzwAkwmRB08ox5nUgdqAgsZ/riqvR/hkNYyTUxJNXbl+luh3/gO3lfyNOFcn/X5DWAu3smciSY4ikFKRmQC6ujViyORGDJqh2nB5H69QL7awb1YjRlYLIat0kzw6UoJlwEGJhlWBvtiay+WTpceKVFcgOgxEmEzISwjDyHCzeGrBYEEIkmHW28ZMIrfye8OaNGP/8V4wDJiNCPkRuB+LVPmQshm3seEydumBwJxP4+m8Y27bHfctv0dLSMXqrKb3kfGQwgG3ESExtusGR2uLSIg+ZkkPphNGJoh/+cQ1Z8xcigz6QZug4GHxliG/eV1Zyw6YhjUayFiwisOw79EgUeo9H1FQgNIFo3ZnqN15DcyVhv+Q32CdNIbh6Jc6LLgdAP7IHrXVPTF27E91TX/CtI8egZecgzCZ8s9/FdflV2CZMwj5sON5XXwIhcJwxg+CqlQS//QZDTgvSXngN/9yP6n1Gx08ivLm+dS6S3Bhbtcb3ySdEtm0m+e77yJw9D99bryNDIZwXXwZCEN7c2ADDmNcRGQoSLSzENmU60X31nqXClYQxOxO+ex/RZyyh/Hyqn30aY6vWpD72BHq1B+vwkfgXzIdIhOo/P6n8XV0u4lWVBJctIbTsO8y9+yqyyPx5pD74MKbOXdQP9qBJyE1LIFiDKDtI1gdz0X0+hNVCcMm3eP70JIb0dMzduimjCCnVdXlS0RMdeqv1yDpvUJMFmZ1HzQvPYe7ZG3FS1JPo2Fd5okbDatA3ZBr62q8gvaUafMRURqbo0Btt1Dlgd4PT3ag4gep+lN9wVWLm5n3hWQzp6dinn/Wr6QSFUNFv/A+hHqJBhJ4hLZ2M19/F//lnRPfuxnHmOZh79vqHdJj1L9Dsm/vHj/dfiH+p485/Iv43HHf0YBDp9yPsNtXe+ich43HlGBKNIgwaCEnoxx/xffAewmTCfdMtmPoNwOD46ZGilBLKixIBsRhNiBFnI1q0RxiMxIpPUH7dlYk1S8f5F5F0xZUIm13JMLwe9Gic6P4CtOwcyq++LFHETJ06k/7q20ibHVlZSez4EYhFiezcif2sc9AslkZrKoGl31J5x62AYtm5b7kN24iRtZFIAu/sD6h5+43Ee9fcyWTMnkflPbcT3b0TYbXhvvMebMOHo8VC6DvXog2aiEjJRC89Ts0XX+J9+QVMXbtjGTAQ29gJxI4fUy1EqWPpNwDfR7MILpiPlppK8p33YNQC0KIT3vfeI7J9K5b+A7BPnkbgm0XYJk4hvHoFWk4LrH36UnLxufUzP5OJjLc+oHzmdUifj+T7/oAhNRX/l19gHTwE27iJBFYsI/DZfAwtWuC+9XYCS5fge+FZnJf+BmO7PGpmvYt17AQcZ51DbO8utOQUwjt34X3uGYTdQeof/4Re4yN2/BiWPn0RLjeRndsIfLUQQ3YL3Ndeh3ZwA3jK0HtPpORiFdbsvupKyP9BkaByOxO3Z1J67VUQi6rA5Q4dqX7+Wfwff5g4146LL8V9+eXIDYsVK7JlHlq/MYkUC1l8GJypiPQc4iVFlP/2FmQ0SsZLryL2/QglRyEtR7Uf3emJIiRDQfQTB9BcqSrnUtMgJ4+Ke+/GMnQ4rsuvamKBJvU4BP3KSzSzFXLzMig9pkzzIyHkocamFmLQRLSug5pc+/6Fn1H10P2NtlkGnkbaX15Ec/1Ctui/EDIeR8ZjaL9QJ/2zxwr5FcmqwfqoGHoGon3P/6q4q1+C/xTHnf/zkLpeL0i22NErK/C++iKhdT9g7tUH92/vwJj1y62spJTo5eVEjxxCczgwZLcgduwIlXfdRrykGOvosTgvvJSqB+tv+vJbbyRr/pcY8jo0f0xdh6BPBT3XjeJjUeSqzxFn3YhuMON767VEgQTwz5tD0jXXIvdvgj3KO1Wz2rGOvghdM2ObMp3gksUYc1uRfP/DCLsDzWQAmwGt5ijEY1imT0akpiiPzXBApVqYzIrZm9cR+/gJ6MEg3vffIbRxI6Z27amZ+yEZ736If+5HCS2c/bwL8b7+SsLpR4aCeP74CNYFf0NfNVe1t2rXcIXdiTE7B+FKIl5agm3sBMpvuBqkTvLvH8aQkUlo9Urso8chqz0EFsyn/NabyF74NVhtmHv2xNylC9F9eym/8RpkKIh90hRqPvkY65DTiR853IiMRDRK8NuvsQ4ZRvDbr4mXl2HrnIv5ojOgpgrNJHBMmIBttErmkKEwvleeB03DNmFyIhTa4E7CEPOhBY9DuAjTmOEYkt3ISAT/wk8JLV8GgA9w33UfeixO2tN/RdhtCF+50nkmZxDetBEMBpKuvR7WzK/XARZsRutyGrbxEwku+w5DVjbS58Nfm1xSB+fU6cjl81THAZSRAAKRnqOs/dLbEFq3FuuIDAzZLUl/5S3iJ44jdq+C8lqiUHkh+tKPlaFEbYtPVhTB6i/QAbKVdlFak9GSU3CcMaNZj1ChGVQHJR5D0wzIMnV8eXw/2unTlJ62btBvNCFaNxOAjWKVN9mW1/EnJRAy6FfLGprhV127/CkIg+FX80hVLN7zkUUHFHGnXQ9ISj1VIP8OnCqSvyJkOIg8tk+5yACi13Aix0rxfzoPgODxY8QOHST95TcxpP68T2Md4sUnlH1V7bpTxgcfUz7z+oQm0pCegX/hpye9EUlwyTeY8mY2fY+RMLLooHJtqTkpFy8ahngMGYkR3Zvf+LG6FuueBubioQBy23IMQ6fjvvUOnBddBkiE0UisuAhTWgr6395JrJvK4sOIKVeBELWkixCYLJimXE3G00/BkR2gGXHNeAs9BuU3X4f0+/EvXIBt0lQC8+cCYBs5mqrf393kM8dOFGHK7YDWZxRY7ejBAPHyKsz9BpD2zF/R/X605BSMrdvgOOscQqtXEly8SD3fYCD1qb8QO3SQyNbNRHZsw9qnF6bWrSm76Tq05GRSn3wac/ceaDYb2fM+JbxvP9H8xuG5oFxdZDQCRiP2CRNhw5f1bieRYchv3kebcBnC6QCjhrlnb6IF+9ErKlSBzG2FbfBAJXGo+3jfz8U2+Ur0iMTzRGMTAN+7b5E5ay7i0GY4tBNpdSD6jgJPGaZUs8qSrKlqIpQXxYewjxuHfdqZhDesx9KvP5rNjt5gLVbYLPUFMnENBZHp7Ql8/jnE4tjGTkCYzErfazViaN8Wfee3jU9KjScR6Bz31yB1A3rvSWhOJ+LgJigsQKTmkPzIH3+yAyJ1Xc0it61EWmyQmatmqv5qlS4z7mJkwTYwmRHdhyDNdnXfGAyJ9Uap6xhbtsQ6ehyh2qQWQ4uWuK68psnMTeo6eEqVtrC6HDJy0UacrdbqIxFkjQ9ht6P9nUHJvwQyFlHny2z72YImw0G1nxDKP9hkbrKPsDkUqzXvJ4wKTuFncapI/pqormhkSC3Xfolp8BkYWuYmaP3RPbuQ4V/mkqFHIvjefbMxMSMSTRRIUFo5U9umDENj27zmDxqsQa6YD4MnN9b2gUruEBrICNZxExIRVoDSUEWbed++SkWQ8JVjSrETD0Qpv/M2bMNH4Ro/tJ5YVAu5Zz30Ho425gLkwR2Knu+vQq6pLwgU7kcbfYkKNQZkwE/SdTdhGzYcLTkVQ0YGlgEDiR1tkEeoaRhbtUGk9la6SiByoECJ3d96lchWJdzWMjJJ/8uLSCnxPP14/fPjcbyvvYTrsiuIbN2MMScHueITjK264L5pJtahwzEmOZGHtqGHQwinG2vnDpg7dlYpKLXfiUhyY5s0lejbb5A562OExYzs0A9xogBsSegxEJOvhpBPmYcbjKQ/9ijVsz9CS0sDsxlL/4GI0kNNz/XRfMjq1GSzDIfVd1MXKlzjQa5eiDbpNxg8HuwzzkVk5DQ9njsNQ3ZrPE89TmTrZuznXkjSb2/H8+iDiV2E1aFaoXUsas0A3YZTetE5CVs13ztvkjX/C7TcVmBzKKKIw11PlAJFljIY0UMhQiu+p+rB+xSr1mYn/aXXMNicaOktEr6xzaLWpBtA7l6HNnwG+o+LoKpEZZXm9YQhUxCaEd1fQ/CLBdTMfg/N4cR9+92YunZDSB2WzyH5ykuRN9yoPI3TMzBkZDZ9vZBf6YNDtYzjsuPKaanveHyz3ye0eiXmnr1IuuEWFdP1K0H6q5FbVigf4DZdoVNf9T2cvF/Qj772CzheoGa5vYZDl/4Iyymm6q+JU0XyV4Q8sL3JNlF+FHPvPgRri6Sw2n75QnwkQuz4sZM2ykY2XKFVy0m67kaCSxYnioape08sAwY2/x7rfmR2/qC0fZu/V+G3aTmIoWcqe7Qda7CPGIZeWoJ/oRI7J99+J8KZhDSaEjMCANGmi9Jw7lyLBDRXKhnPPkfl448ixw1vyhuwOWDbKvSj+Yi+oxG5ndD3b228TzyGLCrA0qsP4S2bsE87k+CKZTj690APBglv2oDrqmuJnThB+Ic1aMnJJN99v2o1Gk1IfzWEAhhSkokXFSYKJIBeVor/66+wT5za5NzoniqE04Xj7HPRRFTNoA5sxXHG9VBeiCz3KqeZ4wVKexoLgz2FrI/mE1r1PcRiWEeMAm8pKTPGg0mn6kXFVHX/9g6E3YHniUdIvulGxI8LE68rS47gvvZaQrvySf/rywQWL0KaHc2fO+KYe/ZuNIBxXnI5orxxTiRSImuqEZktsQ0dQfTAQYzteyEO1l6jNid0OY3yyy5RSSVAYP7HOOd+TuZH8wivX4e5e0/Vtu4/AQ5sQWa0Q7hTCW3a1Mh3VIaC1MyZhfuOe5WlX3Im2pCpimkcDSsJxJBpaiLr9+J59A8JezcZDFD54P1kvPYOIqMx0zpeWYFeXa00uG63krXkdlR5lzUe9LVfInoORWTkKuKZ1Y5WO+uKbNyA57H6Yl927W/IXvgNmlGHgA+x5Ts1Q46dhz4AACAASURBVNMMyhhi/KW157cBYtH6AglqtpaTh/et1/F/rHyXYwX7iO7aQdorb6moN1fSP0W0kcEa9MWzEo5OsrIYQjXQbwzCWD9LlLWeyxyvZcLqceTW5Yq1eqpI/qo4VSR/TaQ1M1pPzSZeS49HCNz3/B7xC8kBmtOJ89wLCa9dndjm+2gWac++SOW9t6NXVWHIzsGQlU36G+8RLy1RnrCpqT8pehYpmUp1VeNBX/EpoutpiIETkBYbIuBF/34eSImo/AzXkF7qB9hoQliMSKNFRTWt+xpqqhHtuiPyeqN/9Vb9C/gqoaoIYbMhbckqm9Jba5yclAad+qu1EYcbuXMtYvo1iGOWJs70wuHC3G8A7jvvRTicGLOykTYromAz1v4DEEYjKbfcBHfeVSt9sSGMQpm1b1RtNNEiD72qKTEtfuwohoyMRqG7AI6zz8PcrRvmFAtie62hgZRKemAyIZLTVOuttk0tC7ahjT6fmu9W4Dj7HNiyBFbOUbOupFT05FxC3y0GILJjO+nPv4oht5VK4WgIKdH3bye8fhPx4mJcl1+JoV1b9MK9ylwBIDkTkd4SsWExqU/+meDSb4ns3I515GhMXbpByT7lVtN/rPKhFRpYbOj+EKW/uRCkJPnOe7GOvBDNakGYLehGSyN9JYDurcbSs6dKUqnV5+pmM7o1Fb2qktixUkxdu2ObNJXgN3+r/wixmDpXkSCRHdvRqyqxTrgcGQ6hB4IEFi/BkJmtEklO8huNFx4nXjtAMdSu+cUryimfeX2CXWzu3Ze0v76E1qYLlBUiD25XM9WgHyw2FXaMIqoQDmHu3JG0Pz2rBmveaojHCa1djWPyxPprTdfVH6sDNANxTxUyHEEYNOWrbDSp4huLQE47tL6jkN4qXNMn4Zg4kfK770AvKyW6by96eRlVjz2IbdQ4HOee/z/GXv0kouEmWa6yYBuix1D1XuoQiypf35MgywqVbvQUfjWcKpK/IkSrTsj9Lep1Sekt0dp0IfXxp4kdO4qxZa5yt/g7nC0s/QeS8thT1Mx+H82lUhYM7fLImrcQGYkiHHaIhKl6+AEiu3eCHsc6fBTJt9+FIaOZFlBSGiKvl5r1+r3IA9sR7XoosmLhwXriQzwGB7YgIn7EaVPQHLXCaLsTbeyF6sfFbFUMw5PcbEQ0iOZOpvLhP5D5xjvImipVeF0pyM3LkKXHERm5aGPOB38NdOqHPLynft0uKRWtbRecF3Wg8oG7Ca9ZhblXH5Lv/QPSno3m8yGMoKVnq/U/BDIcRpis6JuWKl2o2QoVJ7AOOkN5pdpsmDp0Il5SjP2scwiuWkHq03/Bv2A+sYMHsE+eim3MWMTBLcj8BuznNl2RlSeUhCYcarKOK3euxdy5ExQWoPUdjezQFwTEAzHK76z3RdWSUzDkZOG+4WaEHoMuA5AVJ9T6dTgIZivRHduJbNtCrGAfGe/MRht/iYrnqmWE6qsWgMVOvLQYy9ARWMdPRiCJlZZgaNsLrUs/9LV/U7MPUC4zud0Sek/Pk4+BpmEeMIi0++5D2K1kvvU+JRedC7qOsXVbTO3aNyGnSI8Hz5+fJLJ9K+aefUi6cSauK64htOJ7ZDAAJhPOiy9X5t2+AMJgoPL396r34HLhvvV3OKdOA7MFGdebDE4spw0hsn0rxpz61JPgd980kt9Etm0htHYNjmlnwKAJiH6j1QMN9Icy4ENfPj+xhGDOakPGCy9TesWlABhbt1HXRW5HlWYCiuAzeArxqioq77tTRZelZ5D62FOYe/dFjDwbuX4xWp+Rah09GlE+wanZpD/zF3VsowkZChHdtZPorp3EThSSfOd9/5hAvzntqNWpBj0NYTQjWuYlOkN1EBm5nMKvi1NF8leEsDnQxlwIkSAganWHDox2F8bsxrPMRixYq+Mn9Vma24192plYh41Q7Zw6f8XaGzDu9xNc9CXhH9cknhP8+isck6c0WySF1Q4DJyD6jFJEDpMFYXMoAoCrGTG1zUXN3DnYJ03B4E5S79nqUIQCoxE69G5M5gFkdh66/0vct92pSCRmCzIeQ1/+CdQxEo/sRvqr0UacjQwH0M64LiEFEK5U5MEd6JZUwmtWoWVk4r7jHspvvjbh6mObMo2k62eiFxYT+nEttlFj0QMhxMiLiOzcQfxEGbZhU8FfSfaCrxAyDqVHERkt0A0WAocPodf4cd/8W0XKOLgFFr+rzAnSW6rA6fQWCHc6+vL5iEmX06zoTAhMHTshdUlg1Rr0ag+20WPxfz2P+DHVArUMPp3UBx5AeMug4gT6nvXq3Ldojzb6fGWm3q4bzsuuxG8yY2yfV6sR1NEP74bCAlVIbQ7kwKkE580hun075n79sQ0fBbpOcO0abG0zGhl2y32b0dp0w5CZRby01ilH11WmaFIKcu1CDO17kvLkM0i/H+vQ4coNqAHiFeVU3HUb0XylWw3/sBpPZTnJDzyC+457iO7Lx3HmOWh1nsNCw5DswtS9J9HdO8l4+XUMJXth2WxV7HsOI/2Vt/A8/hCR/N1YBp6G68prqfnoA+zTzlLvW0oie3Y3OdXRvXtg2hkqAcXceKAZ9/ng4PbGa+wlR9Cy8zD16Imw2jB16oyw1Lrh+L3KoSethWJH/+kJIluUflWv9hBc9T2W7t0gNRs55Srk+sX13rMAlcVo7STG1m2wTZxCcOl3iYcCX36O+6ZbE/fo3wWjGdF1UP09JQRi8GQ4aeAiNE3de+VFcGSPKva9R4Ljf1/C8n8Np4rkrwxhczRd2zgJCRbs9lXqJugzClrmJeKPmiAaRnPYm31cLyslvG1rk+3h7dsw9RuEZrU2WSMRFlsTmzthsUF2G2QdmafWhk5mdyS25EdE+XH0JUsVEcdgVBZjWW3AmYKYcCly6wpAQJ+xyBo/9snKr1UvK0bkr0XrMzJB2U+gvFBJQTZ8q274Wpsy6VH2ddrpMzC2bov9rLOpmfVeI9u74KKvcEyfgfftN0i67kYqfnczGe9+SMVvb0wI66tfeoGsTz7HoAeRy+ercw+I1l0wpKao1woHEWs+SzA/9e/nQW5HxOnTkYUHkfkbkJ0HES0sxpCRAe50VVTrzlvP4egGM7GDezH37oNmNiIDAVwXXULoh9XE9uaTfNvtsP5rxKCJ6Lt+qP/8RQeRma3gtOkEV62EeAzXTTMxtW4H8Ri6P6B++Dr0RpYXI9NaUfXQ7wmvU8cIb1xH7NABTD16Yx8zBvbUt+UTqC7HOm4C/o+U8YSWnEzS9TerghXyI/duwtRmAJ45HxL425ekPfVsouUJICORRIGsQ3RvPsJmI15WivT7CefvwpadQ/TQAQxpaYiQh7SnnlGqCe8JKKpdN5MSsX0VYkQ2yfc/SLy4mMj2rXjfep2U+x9MhAfLaBT7tDMJLPys0evaJzddRwbV6o2XlWGsqWzato/6SXvmBYTVkmiBCqtDDUzTcpChAHpFKZHNG9QTNI2Ml1/HGKtGX/S2ipAbNFEtpZyswzQZSXv1bSKbNuB5qp4Epl7nHxPsC4sNeg1XxgneSiW1MduaHUQLqwNtyDQYOEF9nye5+pzCr4NTYpn/DXjKFAvWVwXeSkX1r117ipeV4f/8U3wfvk+sqBC9rAh9xafoKxcgy08gG5BmAEIb1mEbO77JS1iHjaL8uiuI7MtHDwabPN4chCMJbcwFMPla4j0nEGs/hFhZBa6LLoYdy+uZqiYLcV8N0X35RPbmI20pqnU69ExqPl9AyXlnUnX/XZScOYnw5s3EWvZCasYmo3/MVvXDmdVGZSZWnFCC9cR5OoGpW3dso8Y2Q2CCeEkxemkxscMHMbRsifTXYJ8+A+uoMWodMRZFej3IDd81fuLRfOxjxhI9cghhtzfNECwsQEQjkNaSiCGd6k//hufZPxH3B9DGX4IYPAW6D0FMupJYRBLdvQNiEbRjO+G7DxCr58GeNWS+/T7pr7+DIcUNVnuiDdoQsuQoGDSsjjBWewij0wqawPvGq5yYMoaiEUOoeutdRIfeENcTBbIOwaXfYenZC90fRKY2bbWJzFxcl19J5gdzSH/5NTI//AS9qhLPk48j2/eB1p2JezyqEJrNCCGRvioVFhyPgcGAltK4w6AlJyMsVnxvvooeCmLt05/iiSMpmTGV4KqVhItr8H04C81iRMtprdrGuR3rP3PxYfwLPkX3ebFNnkbqo08mOi0yWANH92BMSybloccwtMzF2LoNyQ89jiG7cQi17vMS3r6VqkceIPjNl+jt+qpBTMP32rY7xpycn14j1HWoLsXUvScA1qEjMGhh2L9Rzd69FcilcxC5HepboZoB2nZDtO5EvKwMvdpD+itv4jj3AhCC5N8/1OSc/T0QVjsiJROtTReVddqMrKP+/cfVH6k3WfY4hV8Hp2aS/2ZIKZEFTWd+8tBOpNlJ6aXnJZLWvS8+R+YHH6JVFkMogF50AO2smxqlJFi69yReWYHzimsU485kIum6m4l7qki+4x7Ca1dT8/472CdNwdy3fyN/ShkJIQN+pK8CzeYAZwq6P0DZjdcSO6DWbIx5HUh/6Q1o2QGt60CQIK0OvK+/hn+OYvgZWrQk872PkFLie/v1Rp+r+tmnSHnsKTyffEzyxechV3+u1j2FQAwYj3/VWkydOmLKcsOhXY2eK7LVLDK0aQO20WOJ5u/G2LYdwmojevQwpo6diFdUYGjRktSHn6BmzmzlGTr4dJznXUT57TPBZGyayA4QDuCaOhVMZvT2vVSrrg6tOqGHI3g/mUvSRZdg6tINYTajmUzIYACZ0RrdmYn/47mYunTD3KkTwmKGlXPrBxJH9kB2O0yZqard7K1EpLdoMtMhLZfAd99iGzoCze1CC9WAyYB18GCcM2aAriNjMeSuHyClpSKTNGQX22zIaBQRjRDHirFDPzi0Xc0q+o9DSolmsxKXOuhQ/dyfCS79jrRn/orWoi0UHcDSpgU5Xy9VOY0r5iFrPKoNP+xMNIuDlIcep+Ke2yEcBrOZlEeeRDidZH+9DKSk5LwzIBbD3G8AMhTCv2A+aY88Ais/QQ/WgNmKdvp0dClV6zg5m+DSZ6iZ9S5ZCxZhSE5WhJtYDH3xB1DjQQDW1l2wvP4OkV27CCz7DtuwkY2/wk0bqbjtpsT/A199QcYb7yDWfKra9j2H/XSiSB0MRkSwmpTf3UF58Qmsp52GKDvSeB8pkeUnEOMuQR7YhtZtkOoEbf4eU1Y7wp4qyq66lLSXXsd1/Uw0h+NXMwP4OchgDfqSOYkWu+jYV7Fg/w2GB/9NOFUk/80QQiDTcqBgW+MHUrMJ79yeKJCgqPW+jz7EPW4wHNiqbtYD25VQvBbG3FZEDxYgTCbSX3sH4XQSryxHP1FM9ax3iWxSbaTg4kW4bpipRNMWK/GqSiIb1xP4ZhGmTp2wT5yIiEQIrvohUSABYgcKCH6/FMeY4ehLPlZMP4uNpHNmEN2zi8jWLcSLCqmZNwfHWec0Sm4H0L1eNKud6M4dxE1XIUZdjGYUSF3DO+fDRBZh9t++RWvfs9ZaTCA69YVoCFOyA9/rX5J0/c3kfLUYWV2GiEcRrTvhX7aM9BdeBaOJ8t/NJFagUtYjWzbhuPAS3DN/BxJEp77K8LoOyZkQrEHfuwm6DEbrPhjd7lI6xPRW6Jntqbr3LlL/+BTR/N1EDh3CNf0M9O/nKlbwwOlUPvgAyfc+gPfVF6neuwfLoMG4b5qJWPdFffp7yWH0tn0RhQegS39kZTGizyjkzjVq1N+qM3FbKtV/vhnvy8+TNWc+YvmHiGFnYY5XIlcsV9dMajba4CnEC3biuuIqfG/VD0RcV1+PDIcQua2Q5eWQNwTRbRBCxtG3rlTm70LDOGAS3tUriR07hm3yVCzZbuS3s+qvy1HnInf9WE9MioaRKz9Dm3Illm5dyf70C3RvNZo7Gc1uV+xPILxjO9Knsj6tQ4cTWPQlSdffANuWKflEyw5qcFB0AK37EHR3BpGCg8RLS0i6YSZaWprS+235HpGW3ZgYdTQfoRmIbNuDrPaogUgt4lVVeN96tdG1Fi8qJHroMFrHYWgOJ1qLlmjNpec0gLBY0fqNQd/yPemPPoxIy4FDW1XGZMP9ktPU+mVSCvqid8DvVQ8UbMExfjqh1avwPv8X0l99uwlhR0YjEPCpa9vhRuR2UB7J/wSkHlfrlg3XoPdvQXTs02T98hT+OZwqkv8LEG26Ivdvrb/A01siWuQR3/JVk31lKKTaO3Woi9+phZaUhG3iFPTKCohFCSxbCiE/tglTmvhT1sx6F+e5FyCFhv/zT/E+/ywAwaXfEvx+GalP/4VogwJZh9jhg3AoVRVIUG2obctIuvZ6ym++oXafQwirFVOPnkR31udZ2sZNJLxxHa6rr6Pi5uuIFR4nY9Y8yi47v1E0UNk1V5L18Xy07oMhGkEWFiDXfIFo2VGFzrqcsOlrlfUIyJ2rcIy/DM8bb+CYOj1RIOsQ+PxTsj79CiqPqxQIVwryyF5EcjqibTcl5UjOIJq/B5PLBG16EC6rIbx6C4EvHkIGA+jlZRhbt8GQmY2+b7PSkLbqRODbxSRddyOVv79bhdYCwcVfo9fUkHLVpYg9a1UrOac9oXU/Ys8wIXI7IrLbIHUdLa+XWker8qCXlpL2zHNUPfEo4e3bsE+6AgJe9Iaa28pi5NE9aFE/jqEDsQ0bTmTPbiwDBiOcLiW5yV+N1qo7/gWf4Jg6Hfnd+/XtN6nDzpUkXXEVwTWrsQ4bgb5jeaNVM2GyqMzHhojHQAjk9hWIwgIMtaYCskV75IgZCIsdY3Y2wmZX58vnxZCaqoT5R9apdeuKYuSJQ4jULEUMa9sDc06U7L8tQXM60RxO9MIC1WZ3Nw0cJx5DS08n5aLLEqQ1GQ4o2U8zekQtKQlDTks0m7WJD6uUEr2iPGEwb+nbDy09Qy0zDJyQ+Lz0Go5+4lBCiiHyeoNDJXFIT1l9gaw7d0d24Jg+Hd/Hc5qElgNQVYr+zXsJ5rhMSkObdPk/VyhjUUXaOQmysuQUw/VXxqki+S+G7vUSLy8jsn0rpm49MGRlYXAnq0iqUKB2wd2GsDmwDh+JcDiQ/loBs6ap9cD9tcxVV0qzfpQi7EcsfR8cblxnXoC+aYmytTp5P5Op9j1VUzPrvUaPRfN3o3uqsI0cg3/enEaPOc48G3loPbLbUJWsUFOJOLS9UcyW45zzETY7ac++iO+dN4nu2oFlwCCsw0ZQfttNpD/3ar1DTjTSJDtPhgLIaAzhcBE/tg3CEYQ9CZHZGkffTsrwoOF6ZTSM3LsBzWJWjjC1htt10NzJxI4fw2gIoS+dgzZjJvh94KtSYu14DLoPw//+h7gvmIEsLyW4ciXBRQ0GKkKj9MZryHzjPThUO6CJRTEkJaEluRMFsg7htavhvj+g5bZThKCUTCwxI3iPI1wp6MvnI7uPRGomKm69oYH5Qw9Sn3gG6fOoVufJdoGArCpFpLVAC1ahteiAccxoJdz/sj60mOP7sQ89U8Vcnbw+FaxB91bjefxhRJKbrPdmKYJWbStaVhZDVmu1NlwHkwVMVtUihfoCUHRQtXwtStqS8fYHVD3yB4LLl5H2x2eInSjC0mcU8uhe5L7N6vjFh5ElRxFDphLem4+ld996dx1vFZQXKb2uydKoPS56DMXR35nQ/Uq/F33V5xCLkHTdjZTffH3iezd26IQxt1WT+Lc66GVllFx8Dnp5LTEsI5OsDz/BkJmV0FnWQZt8hbJNNBhV67nu8eZY6EIg4zrOiy9DS24cayXDQfStyxtdm3grkFVlf1eRlMEapQmtjd3CYlOD7ZO0kiK77S8+5in8Mpwqkv9C6OEwgW++auS1mXTjLTgvu1KlgZxkNWVISydr3kJ8s99D+nw4L78SQ1YWItWlbKdSs5rcWFLXiZeVQq0eUBZsUW3D5Gys48YTWlJPWnHffo8KP66uRjSn1RSC8LYtSpf54QcgJUnX34yhRUukbTievz5LZNdOLAMG/b/2zjs8rurow+/c7atdrXpxkzvuDVcwHYzpLdRgaugEhxpqChB6MSGUmN4cPiABTO+mY2Nj49673KRV1/a95/vjrFaSJRmbQGTBfZ/Hj6Wr3buz5+7eOWfOzG8IXPp7klu24OjTF98Z52CGQgQnX4z/okvJvHSy3uusr6fyjluxFRYhfh+2wiKSW7eQWLsG18gxRGfPTL+0/7yLEKeLyOzZ1D33FEYgS4fjohXw/cdIp54t9/NiYWyFRUS/nYn32BMIvfpK+n1kXnwZ9dNfJXDGJGTUoZi1FRgl/THnfw6FJajO/Qh/MwdHly6Iy03oyy9x9u2XdpL23n0xw2ECZ59PdN5c3F1767KQLWtx73syyWrdMoxo4w3dVtwJEjHMj/QkQ9nsOCacDiUlmK8/CoFc4mVlxGbNbCapF1+0kMT6dbjHjkbN/VCLdX/3cfNLU9JfJ78smqmzgTMyMUYejCru0VjzB8imZZidByJZBVBbgXTrB7lFKITofB3iVzXV1L3yMv6xA2GNXvWr8lKtkvP5a9p5ZgQw9jlWj/l2+6DY7Om6PXE4cA4YRN4jT+gEEo8Xe/cSRCnUwi+RkgGojcu1Iw9uBgwqrvw99l69yZ/6NLbcPF3v963C/O5jjENO01GWRAIZto+eUFVsBCkmGU/A7Pf1hAmwZxVR+MJLhGZ8gr1bCe5xe7fpIAHq33wt7SChUX0p88xzWzy2oWWcGY+hqqpQkTLE48EI5KP82Y0F/yLQZyR2XxnOAYNbrG5VPNYyMQyaj+cPoOprMN95ulHmr1s/jHGH689ETVBPRBwuZNSEH8yst9h1LCf5E5OsqkSFUvWPhkF1KqTZQM3jj+I97jetFhqL3Y69cxeyrrxWh+UamiQH2s6US6xbQ/CqK0isWom9R09yb70DyS1GFn9F1nm/I37oYcRLN+M95FCSZduIzp2Do2cvsm74M8FLzk+fx73fAcRXLKd26sM49xylm9B2LcE5YJB2wvE4zoGDiXz1BeH338GsrCD7trvJnfIwlbffTPSLz7Tzz/AhdZXw4fNIZh4555+tlWBys8i9ewrlf7iE6vvvIvfeB4mvO5L4ooV4Dz8Se+8+RBd8T/D3F6Rtinz+KYUvv4qtUw8wbC0l8XoPx5lbT9kF55B9zfV4D5pAYvMmnIOHEnrzNS2enV+kpQBVkmRdiGSgO7EF3xN68m96rC+/Qneor6sl4+jjiK9fh6NXHzwHHkzFDX8kMPlKyi88h+K33kP1HwMr5yHLZ2IbejBZ19xA1W1/hWQScbvJ/svfkKWN9aokE5jfvIOx73E6QaTvntgdfkKbWobJkmXbkHULwWZHmUlk/DGoOR/pVVXfPZFAHmrRNzqBByBUQ3LuDGToQZidBiJuF2xaiZgJQh98QOakM8GMY65aAJvWQNe+eA86hNC775Dcshlbrz4weG/EEC0wUdgVc8m3yPhUT0WlqHnxX5jBcjIP3RcWfN447iMOaJGp3CDYr0xTF7gbNm27L4Ax8QzML9/UYuE1OlSZWLWS5JYt2ql5fBgTJmHO+RBz1vvI4PEoZwbm91+kZfSUCLL/iagmUyVZNRfZuJTMs85HvJkkqyqJr1pJsiKIo6QHRk52s5KIZDDYYtzN1o5Fo5gVQcKffowRyMJeUEjFTdeiYjHyHnsGx8SzUOuXQn21FuZwuPH06NfiPABKGdBzuBZib8DrB9/OZb+qZAK14IvmOrjrl8LAsUhBVxh+ADJoL33c5bW6e/wMWE7yJyRZEaTihmuIfq1vlAXTXkFtX34Rj7e+b9EEsdt3qsoqGQwS/MOlJNbpkEtizWrKr7mC/HvuhllvIt9Mx5ldgPOIY3XGamrfzigooODZlyh4+XXC776NvXsPHH37Ef74A7A7iM35FhUJk3vXFLZNOonk+nUggm/S2WRePJmaB+8j+u1MiEaJzp9HbPa3ZF51He6x4xDAjCZg4D7Ikq+QRZ+h9hiD6fSRqAiS/8w0SJqIy4WtRy8yjj0BMQzMujrqXnim2ftTkTBit5OsrqX+jdfxHX2iLvqPx3QPwYwcbI4MCp54jsTmTdi6dMWMRCiffCHusXsTuHQy4vaAYaAwiH43h8isb8g8/Sw8BxyCGa6n9v9eJLZ4Ebm33wMblpBx5NHUPPYosQXf4xo1GlAYgQCx5ctwDhyN9B+FWVVN7dRHdFbv8y+hEgm9D2czUMkqJLhFh4ALuuoVlM2uRQMWf4OhFBnHn0js+7mNqjMiePfbDxZ+jHHAicTWbcTIL8B+2Nl6HMo2oKqDqA1N9l0DeaguQ9h26m90/ajNRmDylXgOOgRja1jfXD/7D1SlJBE3rULtMYqcW+4gvnol4ffeoW7LJp1shUJV1SJZxRAOgSeDmiceo+6ZJwGwd+6EZ/xvMFQMyesMnoy26/HiUZ2J/fmrjddxzSKMfY4huWI+kc8/a3KBtcMThxOKSpD9TyS+bBm1995P1uVXNurMph6rZn+gQ7Jb1urVbF7n1KRJSFZVUnX37YTf0g0GxJtBwXP/h6NJuzjfb07WGeANoX6bjYzjT2z5vdqwnq2nnZBWKrL37EX2n2+l/IKzqbhqMvmPPY2tX2PbwR19V21+P/EtLmTcccjWleBwo4r7sNPVd8kEqkldbno4aiq0k4xHdY6AzQ4SsZJ2fgYsJ/kTEvnq87SD1L9/geegCYQ/eDd9zDVmHGIzUMEt4PHpllU/EhWPpR1kA8nSjeDKgL4jIRpCuvQmPPPrZokt5rZt1L/yIhmnTSK+dDHhGR+RWLMa36SzyH/8GYysbMyaaqof+bt2kABKUffsk+Q/8y9wODCys0mUbsQxcBB5U5/GyMyk4oariS/SBdeeiYcTOON0ZMtKoltqqLzwqPTrZ5x4Kr4zz0Ft20J05te4Bg1GMgMtQmXidoPTQXLTZpxDhxOZ9z2uEaOJL1+GLQbJtfNxpGqivAAAIABJREFUDehHZOVyah96AKOoE75jjyfnlrtwdOuKhCqgtgwVj6LWL8UdCOA640yqptyPa+RInENHkHHiKWQoQMDoNQhbMIijTx/qpj1P7p336SbKU59A5n+M+s8nKBHoNRznkMFU/vlGEmtW4T3meMrPP4vE1i1kHH8S/jPORoXqCX3wHvZOnXFH4jBvBlRuxRh3JE6ni4KHH0KZNqqffIKMww7H8HkxDj6V8Ny51P/rX2RechkVD/+d5NatZBx3Ap7RI3XiS0oHV5UMpvKuOxoFFpJJqqfcg+egQ0gsXgz7jG90kA3UlJNYs4rgpY2r9dDrr5Jz1/2UnXWa7pDy90cwssxmesHV991DzWP/JHfKw7h7tx3O1B+uJGppcwUmQjWoZJKEZFL14A0AuMbtjaOkm04+MQzw+FHROBU3XqsnD5P/0PLckRDiz8HsNxrpOoDIrJmIz4+jrBwVi6cdJOjOMVV3307uXfen9zNtRUUUTHuFmqmPIAL+8y7Gtl1vVzNUT/XDf087SIDE6lWYwXLs3Up05neylfDpDjAKi0isXEFsYx3iiuEu8WBk7WQdpcOlV6tbmpSliCCFJVqG771nG/V9S/pjjD2s1Y4hFj8ey0n+hDTtNgFQ+/TjFDw9DUe/AUS++hzX8D3xHXMsfPw8ZiQEXj/GYWcjvsCPej2x27EVdyK5uTF8ZxQUoJRB1b+m4+i7B75B+5Dc1FKJJbFxAyJ6n0rV6hBY3TNPEn7nLbKu/xO2Tl2IpbIAm5IsK8PIySX7T7cQ37ABl99P3fNP61KURY2KJOF33ybjiCOxdx9C9bnnNDuHc9BgDJIou+Ds2pmqe27De+Sx+C+ZTPiTD9MdTuy9+6ISJnUvvtA40bDbyb37AZKlG7H36AnVOgM1cOUfCc/4GLO2BlfXrhgZHszFXyAFXXTYEnTni8JeZJx0Mol167Dl5FA77Vn8x58Aa+dgbtuAhOvxjR+NvbCI4LVXkjvlYRxupev4QK9+Vn6Ha6/jMXLz8E06i22/PQkSccTtJuO4E4ivXEFw8kXpiIG9d1/ypvwDw+vC/OattDSfuL3kXH2V7sSyroJk5wFU3XEbeY8/S2TGR8TXrSW5cYPOXHZ4MEYejFleqlcObh/x1SubXxzTJLltG/4zTtctura7dqqgBzV/365sYttWEqUbsXXpSnLjBiquv5r8Rx4n/59PpBLOvqd22vMkVq/ClpOLGYnsWHvYsIHR8rYidgdGfhEZxxyPvVcffEcdhfn+81oQHyCnCOOgU3DuOYrwplKSZeXYM3MaHQBAyQBimzYj/s6E//NvHL36gIKKG/9Izi136rHu1h3HoCEky7aRLC/Te4INpnm8OPfoT84td+hJkaeVVVfSRNXXtThshkKIy4Vz+J6wo+L+VrBlBrCNGImjX3+wOxq3UXYCEYEufWHEQahls8HlwRg1AeVyw/efNR+fdUug/+gWuQ7/S1RCd89RNRVIRmYz8fmOiuUkf0I8hx5OfaoxMKBv9mKgknHc+x2I94D9YMa0xo38UK2Wpht96I+SkzJycsm990HKL7sQs1w7r5zb7qHq9luIzp5J5LNPiHzzJTk330HNPx9uNgP2nXwaRoaPnL/dSfDqP0A0ini8ZF3/J6KLFuJyOPGdNonaZ55Mt1IStxtn/wHkP/YM9a//G+9hR1F93504+vRttXQktmIFjr79Metq08dco8bgGT0C9ekrSDSMON1kXXIx1Y8/hXPwUPIff47Y/HkYmZk4Bw9GRaKEP3gXW3En3HuNx6ytpeapx8i9ewqSjKC2bMFe1JeKf9yPc+gIHMP3JHj15eTdeReq71jMUD0y9lhk2deofuMI3nQT8cXamdf8/T7yn3oevBnEom6kaCj2wnxk3oe4xx9B4Zix2MJB2LIOY+wRqPLSdENtasr1zXjz5vQ+qWfCYSS3bqH2qcebhdQTK5cTX70aZ9fCtIMEdNPqxTOR0YeSLN1I5e23UvDk8yS2bMbIDJB39wOI1wMblqDenooq7okx8Uzd59Dmwr3P/oTffiN9OvH7sRUVIx8+jRo1AboPgLVNJOWyCtIZzk0RhyNd35pYsxqlFLLyO4z1S3FnBHDffQ/RpSuQ2q2Qm01svZ5gGDm5iGGQrAjqbQWHA8OfiTHiAMx3n2nM6MzKRzncGFlO3TLM50ct+LLRQYIuc9myjqwrrkmPRd6UB5HSpVC1TWdyFvci/tlnVP31xvTTPBMm4p14BMltW8l76gVUfT2JDetxjxoNHq8ukdn+e7MDTVXD78d/znnNlI2MQJbWffX5ybntbmzbZbDuLIb3xzkvcXth4BjdOFlES1/GIpiV21o8VlWXIYXdftTr/CRUbNHZ42ZSS0AOGa/VqdqS3OwAWE7yJ8TRdw8CV11L7WOPgqQyNjMyqH3kHzj69sM7sFeLTDdVXa7T9X+EkxTDwNF3Dwpf/I9uvGuzUXXvnc2yRuOLFyE+H4UvvUb1A/dhVlXiP/d87F27IE4nrtHjKH7zQ1QsplcfyST2rl0xbOAK2PHu8zjRxUupffZpAr+/gqoH7yOxbCnZN91MYuMGVCSCWV2DZ8JhJEpLMbxeYosXQSKOZ6/xUFeuM09ffhGAzPMv0Ko7Dd3uYxFk3kf4TzlVa4HW1FD/6it4JhyKK8eF6crGd9a5uEeNJfTuW9gKi/CfdS4qVItRXw75nWH5N+T86a9EPvsUQQhcfS31b0ynZuojWtC7U2fyH/4nidLStIMEvedZ88Q/cfTZg9pHHtTXsE9fcu+8C5s/E/Ozf6f3g9SKucjeR+syia3rsfUaQPZ1NzXbc3aNHAUOZ+v9BJWJqqlqsX+l6qsR00T8AbL/fCtV995F5BPd6gu7nfyHpuIoKoTRE1Ez38F8fRXGUeehVi0gMPlKnRwUCpF51u/SBf6qsESvKoYdhPQahtpWCvldUKbgv+BiorNnpSdM9u49MDIzSW7RNZLOQUOQcG2jwHZ9DVRsxXPEOZjT/4kUdcFw2qj40/VkXXcj4nQTvOxCLT7udBL4/RVkHHkkxjEXYq5eiFI2lCeL8tNOxjVmHJ79D8I5bDjSyj4b1eXYeg4i974HUZEoYrchow5BzKTuOFMRpObB+5s9Jfz+u/hOPwszGCT04XvpkGu110v+48/q/f1Mv17R7ERSi4pHcfTtR/6Tz1P3wrMYefn4zzgb3G5y7/9HM8Wq/yVi2KDp1ozDhfQc0koJSMsG7P8rVLheN6Vuco9T87/Q3WgsJ/nrQJlJPfsv36Rnd/4cPatLYQtk4Tv5t3gnaiFmI5BFsqoSW+cuxNesgpxinTqvGlcZ0n0QZjyJzdXwGiZmeTmhj95HxaJ4Dz0cW15emytNsdux5eUDumNDYtnS9N/s3XuQ/dfbicz4iGRZGYErrkHcbqQ+iGxehcrwIYaB2JV21hmdUN4MKFuDmvNhOlznGrQ39hv/SnjGRwTOOAtx2DHrQ9i7dCHvnvsxN63BKOqCZ7/9MEvXgMdPYsNGpGYzLP+WzNNOxdGjJ5FPPsLeqTMsrm3+JsJ12AryqXvtdRIbN5B17U04unVGvfkYxv6n4ho6gvJLzks/PPT2GxS+8BLEapCcYtTaJdg8TjyFLoySLiSqaql59KH045ObSql96SVcQ4e2GD+zsrKZU4uvWE5s6XI8Y8c0EzIHUEtm6YShXkOJLllK+WUXE7j0D2RedgXukSOxORRE68n9221UP/E49S9O05+LomJd2J4Z0OHIJjcR6T4QtegrTG8hkhFodJAAiQRVD9xH7tV/0IX0ucUQ3KxbbBXtQXDyxfhO+S2ObiUEr5qMWRHEyMsn7/4HsRcX6gJ/JVDQndAnHxN69WX8v7uQwpdeI/TG6xgFhXj2O4DKm28CwDFoMDm33QVLPqcZiZjOrnRnaK3dWW+QfdXVhL/+ivjC+dpBAp59D8CxRz+S1bVIrB4Ke1L3ysvUPfmYvm7TXyXjhJOIL1+Gq/9oXUfZbyxkpfYF/QGS1dUtHJGKxzGD5Vqer0kvSnu3EjIvmYyRGcCWX4BtziwQwV7SnZxb7iD0/rskN5WSccyxOPoN3GF5COibvJr9AaxdjL24B9nXXQ++rF1qbfe/Qodhe8PwA1BLv9UyhKMOad8SEKWaZ+E2sAvlLrsjlpPcFeqqdIPheEw7kPwuGAec1MxRisORdloAtrx8cm69k/KLfkfts0/jP/VkZPksLSRQMpBYRR3xea/iO+FkxOnELC9j68nHYlbqOqzaRx+i8JXp2DvvWEVDKYWRnUPg8qsJXn4JANk33UzFdVemsyhrn3qMvIceI7ZoAd7RwzHCdbBhOWreDH0OwDj6AszvP21+8sVfYzvwdDL22wuZ9w7EY9hyizH2PR5zzkfYBo7V3TIScWwDxqA2LMPVt7/uqJFMIMtm4ujXH9eeo8DjbdFJg8wcxOuj7l/PaSEFm42cq67WpRAqQd1L05qZYwbLic2bgzNailrwpe5vGaqBzasxv3iNZE7LdPzoV5/jn3QW4vOl9zwBMo4/ifqXm58/WVWZGo2WSGFXEpU1lF90CgDVD9xL0X+mw8IZqTpAUPM/I3D6bzF8OmHEe8TRBK+ajGf/A/GfciZq7id6Bd17KCTjsGwOxp6HkWwoHWr6XqsqweFCrV2EFPfQqjhZBVTedCOJpYux5eYSvOZyvW8JmOVlBP94JflTpiBfv6ZXrtmFeEaOo+b+u3AOGETtk1Mxq6ow531H6K3p+E8/k6w/3oCIiREO6uSk7XFnIGMmomoqtOxecCP2omKdLYoONXv2P5DgFZei6uqwFXci774HyJhwaNpJohQoRWzed7hGjICDTqf6vnsIv/+OfomDJ+CfdDZ07YYt1XpLJeJEv59L8PJL8Z1+Jr5Tf0vtE1MxAllk33onlTf/SSel2R34zz2fzIt+j3PwUILXXqmT2IDw+++QfbPe925rNakScdSCL1CrU2pRpStRm9dgnHApsPs5SUiFYQeN01J0CLi9bbbc+5/gcCI9BqUFJABd7tKBV5FgOcmdRsVjmHNnNO8pV7ZRZxvuYPYmIjh696Jw2ou6RiwjgAzdH0QR27iV8ssuQLwZeA+ZiC0vn9BHH6QdJIAKh6ib9pxeBbYimqwiIZ0Sv2EFdOmNe/RoCl99m9j8uSSrKps1tyWRoO7F5/EecRSJihpcnUUX1zclFm3ZTcA0MXw+zI9fSK+CJKcItfAbjEF7Yb7/XHq2aK5bgnHIb1GrFyI9BqLWLYFB+1B1sVaYse/Rj/z7psB3H2hZvpwiGDmReOmmtNKQ//gTUFt0bR/JROtdEBwOCCehvhq1bQOEUqvT4GbsIybqv8cbZ7DuffZFvE4Knv0XNU88hhksx3fSqdi7daeyacKV3aHDxLEoZOU3U/mRAWMwN6wgumhV+piRmQnRMNJU0k0p1ILP8Z9+BrE1a6m87S+4R48h48STob4K6TMCInWo9cvSCjdSV46ty8DmvR+BjGOOQ8o3IBkBHaIeMh4zrojN0iF1w5PRrEAe9MoZafLVrtyKEa+j8KXXMAKZYBhEPvsk/eeK664i+9Y78Y4fh1q2GmPIPpjBzVpxBpA9RqLKS5H8LlpQO/Uexe3GPW5v6lavwnfyaZRfeoFuwgwkN2+i4ua/kPvAQxT9+zVACH/2GYkN63HtNR5xuIguWJh2kACRD9/HPXosyWAQ74EH689TZRUVV12Gqq3BXlCAe8ggHN26YSYVdS9Oa8zaTsSp/edD5D89DbO2Nu0gG6h99mnc4/fT8oaxqC6dcLp1baFN13Q2K7EBva9WW4l4W/ZoVNGwvhckYuD06LKYdnBQYth0QtpugDicMHx/HRpftxSy8rTc38+USKTCdfp7b7PrCcLP9DqWk9xZzGSjcHUTVLjuB2saJRFDPvs/bKlQW4OKidH/AL031ORmrmItO1aYkUhzWasmj1VzP2mcua2eD72GYCvoijvPSbQm0uI5xOM4+/Un9NabuIYOa7lHumUt0n0AqmlHjk69tM1NH+tw6eL+zWtahFPUirlQWAKde2F06o2JgXu/A4jOmY1r2AiStSFsY47CDJaRWLeW6ksvIuuq68id8hC1zzyJkZ2NmvUGxv4noEL1ZF5wMZGvPk8nl9i6dsPRozt8nuoBGKlHBRsyfAXDbpD3wENU3Xk7iS2b8E44TK9Q3n4Kw7CRdcT+YHdh9BpIct0Kcu+ZQu205zG8XjLPuwBWf4dZvU07+zWLddF4176obesRpwfnoCGNb9bu0KvB7UnEiS1djK24EzmXT4ZgKTaXA3PWF8jAsbqJb1PyS6h64F7yn3qBmscfJbFmNd5DJ+IZMRTmz9BNn8N1qHiSyNdf4xoxkujsWZihOmydOjebDNl79NRqQE2QaB32ngMw33oS/2mnE37vnbRDs3XqjGv4CMyPX0JGT0Q5XRiHnw21VeB0oeqrIRrRq1i7U68YuvXD4XTj6NWbRGmp7g4Tbr4Sji9dDHXVyBcvg2EjY/wRRCvrsXcrASA665sWwxZbshjHHkp3NnE4ULEoZpWW6bNlZ8HcD3BlZKJ6j6Lu+adbPD9Ztg1bYSvNxl1OPXlZsxj1zdt6y8PpxpgwCXKLwOaA7IIWkoBtOUg1/wvU4pT9Xr9OqGqtafmvDHFnwND9kAFjtIDGz7SKVKFanRzWoHxU2A1jv980i+r9VFhOcicRlwfpN0r3/2vA7tg5MWGnu6W0V35XYkv0Xo7vt2cgKTFm76GHU/voQ403HLtdhwlbSwZJRLWEVxPU6gUYfYajvn4L574nY+TkpkNxiOCfdCZSuhT3AQfoVPai7rBlbePzq8sxBo/XxerbNiBF3XVWnalQdmda5FyVrtTyaduLYoM+b0FX1KKvUcvmgM2O/+ST8J9zvq6Ji8VQiTgVt/41XTZS99I0si8+j5xLzkNsIF376hKBLn2w9R9H4StvEH73TWyFRbiGDUPmva9fy7BpybqFX+m3OHQfWLsAe1UpeX+7RRdcuz3I2vmo1MqIFbq0RZlRDH8OrkH9cd59vxYwX/BpOq1erVoAxd1hXR3mt+8jXfoiRSXYyrYRuOpaah5+UI+tNwDeTB3yTSH9RuGwu5FQEPVtqnxl4BioLgPTRIbvj1o6W99Ihu1H/cxZOPsPRDIDZF1xDSpcj9iAaAQ5/GzM8k3w6SvQuQ+Gx0PmZVdQddffSG7ZTN69DxC87moSa9dg79WH3L/dji3DjdnkMycl/VArvoNIHcaaORRO+z8iX3+FBLJxDd+TxNZNOHoNQRwOzDcfRymltVuTWvzCOOwsfV1L+iF9hmM6PdjcOrU/55bbMevrU5KHjU7GOWJkY62mmUTNfBv3cZfo0gDAc9Ah1L/cXCfYNXI0RnZ2OgtXXK50mVNoxgwCE/eBZd+CLxv3mLHUrW5c1WMY2Et6oOIxnIOGEFs4P/25D1x2pS4LevvtxpyAWATzy9cxJpyuGxiPmoBZsVXvqzU0Q2+tfCESanSQAKFazNkfYOx9DOJ0tXz8rwyx28H+861ulWnq+0ptY8SNretR5RuRri21rf9bLCe5C0hxD9j3eL1R7vZijDhw50IJTjfGgSdrXcxwHeR1QkYcRHzqVHLu/TuuPUdhpGb+trw8Cl+ZTt20ZzEjUfyTzsSWakjbulG0tX0GCz+l4IlnqH9zOsmKCnzHHodRtwUSUexFnRGvH2Pf41BLZ+sVZHFPpLi7LlAeMBbZ+xjdANYwUMkExsGnaSWV+mpweVBeP+LxoRbPbJyBO5zIgHEopwsxTVRxD6TvCCS/GHE16Xgfj5E35WHCn3xEbPFCMo4+DqNTL9S2T1BfzEQOPEmXDmxcgWxchr33MHxnnaudYnU5ZiBfy+8N2QfldGMc/FttU2UZavZ7+r0VFUN2LmKzYxqt9PezOyCnEMnK17VcHjdK7YVau0QfK+6BuXgm0q0vRr9RKLGjVAKxmXj3Go3nkLd0bWKwDOehZ6CWzkLV1yDdB+jrPG8GjDtSv1Z2gV55Dx6P+uoNpMcgjNETUb5MlDhxj/Fg5OVj8+uSBZXhA5QOpwGG0wUnXAbRMC7sJMvLCUy+CkePHrDgU/JuvUV/FsO1yPIvUd79oKAbROq1zFs8RlobZssaZNt6PPmdkZ5dkJxc7J06oyKhlHqLQ0+GGoTGxQCXF+XyICMORERoOpqGPxMcdvL+/jDBG/5IcuMGnEOGkXP9jcjcJivmZKJZKN/Rrz/+Cy5JKfsoMk46DXunzti792w8d04uef+YSvCaywm9NR3fiSdhG7Y/smEZvtMmkSgrJ/LxBxi5eWTf8GcS69ZQff/dZP/lb7pWcvNmPAcfgi2/EKKRlmpX1eWNx3xZGIefo997g7B5K05PtZacUh1MRRQsJ/mzY5q6G8v2VJXDz+AkRbUSxutIiMhE4AHABjyulLpjR48fOXKkmj179n/1mioa1k1dHTv/hVCmqZN1VFJ/AV1eLeLcSt0agEom9b5PayvIhsfEY6jvP9V9AFPIHiMhKw81M7V6sdnhoFOgbJOegUdCGEf+DskuaGJbUicj2R1IQ2mG3dEiVKKU0p0IlKlXQG4vqjqoyxvKSiER044lHMIo6gZmAhJJxLXjkItSKr2fo+JRvdcjoJxeiIZADASahVJUPKZn+021OSsrQZmITRCHs5makQrVYE5/TJ8PwOHCOOp8cLmbvU8zEdcC2qsW6P1UM4n0H40M2z99w1TJBCDN9ohVqFaLkrs8qE1rdG1fz8HQa4jeq/H6kYyAbvNUV6PDw3mdweZExeJIZiA9UdoVVDKBmvdpeiUNgBgYR5yLKi/Vn6G8TpgzXsE4dBLmW082joE7A+PQSeDLSo+jSiRQy+doEfWG0w0cBwPH6cbcO8CMhnVoNJnQY7X0a2ja8svjwzjqvGYi/WYkovfqzSTicCDeDAxPy9VbsiIIiSQ47BiBrJQzt6GicVQkDCIY2TmoWEyLASiQQKBZ4b4K1WK+8Zjuc9lAtz0w9j56l8KCqr4G8z//aJ6lPGQfZMh4xGatO/4XmKUrUR82j0IYx16EBH5AEWoHiMgcpdTIFsc7spMUERuwHDgE2Ah8C5yqlFrc1nN+Cie5O6EiId3mqHQldOqlm8Yqhdq0Gqq26mwzl1eLIkfDOnTq8e/Q+e7S60fDqJXfa8FnEb0CG7bfbieNpR18nU7OME3dcszjazXbUUVCUFuJ2rwaKSyBQN4PdntXiQSUl2J+OV2vtLv0xdjzQFR1BZLf6b9usrvD1w7X65KdNQvBm6m7QWxcidqwVK/8inugSleh/DkY/izUxhXaeRZ3R3l8GNtdKxUNQ30Naus6JL8z+LJ/VLd7VV+D+c3burVWTiHG3kfrsWynDExlmlATxPzqDagsg869MUZPQLwtBQd2eJ5EQhfNf/M2hGqQnoO0k9zNPvO/ZFQ0jFq/VDdTtzuQEQch+Z3/q3D3L9VJjgP+opQ6NPX7dQBKqdvbes4vzUnuDqhEAmKpFajDuUsr7F8SSim9SlGA/edLWmj1tePR9P6jcriQhlBpQ4g7FtGrc5sDSSQAEwz7z76HpmIRnXBlyG7jRFQkpFeBrURLduk8DVEVp/tHKWZZ/Hco09QRBeEn+Wy15SQ7emygM9C08+1GYEw72fKrRW/U79ps/JeIiLRbOr44XDrRhtTO4/Y37dRKsNW//Zx2Od2wa1KnPzs/ZlXc6nms3o3tihjG/0Q8oaM3H2stbtNiaSwi54vIbBGZXVbWyoavhYWFhYVFK3R0J7kR6Nrk9y5Ai462SqmpSqmRSqmR+fn52//ZwsLCwsKiVTq6k/wW6CMiPUTECZwCTP+B51hYWFhYWOwUHXpPUimVEJFLgffQJSBPKqUW/cDTLCwsLCwsdooO7SQBlFJvA2+3tx0WFhYWFr88Onq41cLCwsLC4mfDcpIWFhYWFhZtYDlJCwsLCwuLNujQijs/BhEpA9b9wMPygPIfeMzuSke2HSz725uObH9Hth0s+9ubEqVUixrBX52T3BlEZHZr8kQdgY5sO1j2tzcd2f6ObDtY9u+uWOFWCwsLCwuLNrCcpIWFhYWFRRtYTrJ1pra3Af8FHdl2sOxvbzqy/R3ZdrDs3y2x9iQtLCwsLCzawFpJWlhYWFhYtMGv2kmKyJMisk1EFjY59hcRKRWReal/h7enjTtCRLqKyCciskREFonI5NTxHBH5QERWpP7Pbm9bW2MH9u/210BE3CIyS0S+T9n+19TxjjL2bdm/2499U0TEJiJzReTN1O8dYvyhVds7zNiLyFoRWZCyc3bqWIcZ+13hVx1uFZF9gTrgWaXUoNSxvwB1Sql72tO2nUFEioFipdR3IuIH5gDHAmcBFUqpO0TkWiBbKfXHdjS1VXZg/0ns5tdARATIUErViYgD+AKYDBxPxxj7tuyfyG4+9k0RkSuAkUCmUupIEbmLDjD+0Krtf6GDjL2IrAVGKqXKmxzrMGO/K/yqV5JKqc+Aiva248eilNqslPou9XMtsAToDBwDPJN62DNox7PbsQP7d3uUpi71qyP1T9Fxxr4t+zsMItIFOAJ4vMnhDjH+bdje0ekQY7+r/Kqd5A64VETmp8KxHSJkICLdgeHATKBQKbUZtCMCCtrPsp1jO/uhA1yDVLhsHrAN+EAp1aHGvg37oQOMfYopwDWA2eRYRxn/1myHjjP2CnhfROaIyPmpYx1l7HcJy0m25BGgFzAM2Azc277m/DAi4gP+DfxBKVXT3vbsKq3Y3yGugVIqqZQaBnQBRovIoPa2aVdow/4OMfYiciSwTSk1p71t2VV2YHuHGPsUeyulRgCHAZektq5+kVhOcjuUUltTNw8TeAwY3d427YjUftK/gReUUv9JHd6a2u9r2Pfb1l72/RCt2d/RroFSqgqYgd7P6zBj30BT+zvQ2O8NHJ3aG3sROFBEnqdjjH+rtnegsUcptSn1/zbgVbStHWH/jwIOAAACc0lEQVTsdxnLSW5Hw0VOcRywsK3Htjep5IsngCVKqfua/Gk6cGbq5zOB1//Xtu0MbdnfEa6BiOSLSFbqZw9wMLCUjjP2rdrfEcYeQCl1nVKqi1KqO3AK8LFS6nQ6wPi3ZXtHGXsRyUgl2iEiGcAEtK27/dj/GOztbUB7IiL/AvYH8kRkI/BnYH8RGYaOua8FLmg3A3+YvYFJwILU3hLA9cAdwEsici6wHjixnez7Idqy/9QOcA2KgWdExIaebL6klHpTRL6mY4x9W/Y/1wHGfkd0lM9+a9zVQca+EHhVz3GxA9OUUu+KyLd03LFvk191CYiFhYWFhcWOsMKtFhYWFhYWbWA5SQsLCwsLizawnKSFhYWFhUUbWE7SwsLCwsKiDSwnaWFhYWFh0QaWk7Sw+IUiIt2lSYebXXxuJxF55ae2ycKio/GrrpO0sLBonZSiym/a2w4Li/bGWklaWPyysYvIMynR7FdExJvqBXibiHwtIrNFZISIvCciq0TkQvjvVqEWFr8kLCdpYfHLZg9gqlJqCFADXJw6vkEpNQ74HHgavWocC9zcHkZaWOyuWOFWC4tfNhuUUl+mfn4euCz18/TU/wsAX6qfZ62IRBo0XS0sLKyVpIXFL53tdScbfo+m/jeb/NzwuzV5trBIYTlJC4tfNt1EZFzq51OBL9rTGAuLjoblJC0sftksAc4UkflADrqxr4WFxU5idQGxsLCwsLBoA2slaWFhYWFh0QaWk7SwsLCwsGgDy0laWFhYWFi0geUkLSwsLCws2sBykhYWFhYWFm1gOUkLCwsLC4s2sJykhYWFhYVFG1hO0sLCwsLCog3+HwIm5wtWJQtJAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 504x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(7,5))\n",
    "sns.scatterplot(x='bmi',y='charges',hue='sex',data=data_copy,palette='Reds')\n",
    "plt.title('BMI VS Charge')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2e69a19b2e8>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnEAAAG5CAYAAADh3mJ8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3df7BdZX3v8fcHEgUrID+CQA4KCloBBSRQvO2gLWoiWqGKbei1QEGjDrZ6q6VSO1PpNb2FXuUOWrkXCgK2BhCrMFyhWKzl2iIxtGASKCUKlvyC8FOk8iPhe//Y69hNODk5QHb2eU7er5k9e+3vWs+zn3WYyXx4nrX2SlUhSZKktmw17AFIkiTp2TPESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdpSkpyYpLvDHscz0eSbyd537DHIWlyMsRJ2qyS/FKSf0rycJIHkvxjkkOHPa5hSPKCJJ9KckeSR5PcleSCJHsNe2ySJj9DnKTNJsn2wFXA54CdgJnA6cDjwxzXeJJMG2D3lwPvBH4T2AE4ELgJOHJTf1GSrTd1n5KGyxAnaXN6FUBVLaiqdVX106q6tqq+Dz9bAv3HJGcleSjJD5P8l65+d5J7k5ww2lmSHZJcnGRNkh8l+aMkY/67luTPk3yna7NDkvOTrEqyIsmnR0POemN4APjUev3skeSnSXbqqx2c5L4k05Psk+QfupnG+5JcuoHxvBl4C3B0VX2vqtZW1cNV9RdVdX7foS/vxvNIkmuT7NLXx1eSrO6+6/ok+/ftuzDJOUm+keRR4JeTvD7Jv3R9fSXJpUk+3dfmHUlu7v72/5TkdRv/TyppWAxxkjanfwPWJbkoyduS7DjGMb8AfB/YGfgycAlwKLAP8F7g80le3B37OXozWK8A3ggcD/x2f2dJtkpyHvA64K1V9TBwEbC26/Ng4K1A/7VnvwD8ENgVmN/fX1WtBG4A3t1X/k3g8qp6EvjvwLXAjsBIN8axvBlYWFV3b2B/f9+/3Y3lBcDH+/ZdDezb7ftn4K/HaDsf2A5YCHwNuJDeLOgC4NdGD0zyeuAC4AP0/vb/B7gyyQs3Mj5JQ2KIk7TZVNWPgV8CCjgPWJPkyiQv7Tvszqr6YlWtAy4F9gT+pKoer6prgSeAfbqZs98ATquqR6rqLuAzwG/19TWdXljZCfjVqvqP7rveBny0qh6tqnuBs4C5fe1WVtXnutmxn45xKl8GjgNIkq7tl7t9TwIvB/aoqseqakM3V+wMrNrInwzgi1X1b904LgMOGt1RVRd05/44vRnDA5Ps0Nf2iqr6x6p6qms3DTi7qp6sqr+hF+xGvR/4P1V1YzdLehG9Ze7DJzBGSUNgiJO0WVXVbVV1YlWNAAcAewD/q++Qe/q2f9q1Wb/2YmAXejNTP+rb9yN619mN2gc4Gji9qp7oai+nF+5WdcuGD9Gbddq1r93GZscuB96QZA/gCHqh9P91+04FAixMsjTJSRvo435g9418D8Dqvu3/oHfuJNk6yZ8l+UGSHwN3dcfs0nd8/3nsAayoqtrA/pcDHxv9m3R/lz27dpImIUOcpKGpqn+lt7x3wHNofh//Oes16mXAir7Pt9Fbirw6yau72t30Zph2qaqXdK/tq2r/vnb9QWescT9Eb8n01+ktWS4YDUdVtbqq3l9Ve9BbmvxCkn3G6ObvgMOSjEzwfNf3m/QC6pvpLSnv1dWzgfNYBczsZg5H7dm3fTcwv+9v8pKqelFVLXiO45M0YIY4SZtNkp9P8rHR4JJkT3rLkt99tn11y62XAfOTbJfk5cDvAX+13nELgD8E/i7JK6tqFb0A9pkk23fXzL0yyRuf5RC+TO8avHfzn0upJHlPXzB7kF6QWjfG+P8O+CbwtSSHJJnWnccHx5m967cdvTB6P/Ai4E83cvwN3Tg+3H3X0cBhffvPAz6Y5BfS83NJ3p5kuwmMRdIQGOIkbU6P0Ltp4MbujsnvAkuAjz3H/n4HeJTeTQjfoRemLlj/oO76rj8BvpXeb7AdT28p9lZ6QetyJra02e9KejcV3FNVt/TVD6V3fj/pjvlIVd25gT6OBb5B79q/h+n9LWbRm6XbmIvpLR+v6M5j3CDcLSe/CzgZeIjeTSJX0f28S1Utondd3Ofp/U2WASdOYByShiRPvzxCkrSlSHIj8L+r6ovDHoukZ8+ZOEnaQiR5Y5LduuXUE+j97Mo1wx6XpOdmkL9ELkmaXF5N7zrCFwM/AI7trhGU1CCXUyVJkhrkcqokSVKDtrjl1F122aX22muvYQ9DkiRpo2666ab7qmrGWPu2uBC31157sWjRomEPQ5IkaaOS/GhD+1xOlSRJapAhTpIkqUGGOEmSpAZtcdfESZKkLcuTTz7J8uXLeeyxx4Y9lA3aZpttGBkZYfr06RNuY4iTJElT2vLly9luu+3Ya6+9SDLs4TxDVXH//fezfPly9t577wm3czlVkiRNaY899hg777zzpAxwAEnYeeedn/VMoSFOkiRNeZM1wI16LuMzxEmSJDXIECdJktSggYW4JNskWZjkliRLk5ze1T+VZEWSm7vXUX1tTkuyLMntSWb31Q9Jsrjbd3a6OcckL0xyaVe/MclegzofSZKkyWSQM3GPA79SVQcCBwFzkhze7Turqg7qXt8ASLIfMBfYH5gDfCHJ1t3x5wDzgH2715yufjLwYFXtA5wFnDHA85EkSVuIRx99lLe//e0ceOCBHHDAAVx66aXcdNNNvPGNb+SQQw5h9uzZrFq1iocffphXv/rV3H777QAcd9xxnHfeeZtljAMLcdXzk+7j9O5V4zQ5Grikqh6vqjuBZcBhSXYHtq+qG6qqgIuBY/raXNRtXw4cmcl+5aIkSZr0rrnmGvbYYw9uueUWlixZwpw5c/id3/kdLr/8cm666SZOOukkPvnJT7LDDjvw+c9/nhNPPJFLLrmEBx98kPe///2bZYwD/Z24bibtJmAf4C+q6sYkbwM+nOR4YBHwsap6EJgJfLev+fKu9mS3vX6d7v1ugKpam+RhYGfgvvXGMY/eTB4ve9nLNuk5SpKkqee1r30tH//4x/mDP/gD3vGOd7DjjjuyZMkS3vKWtwCwbt06dt99dwDe8pa38JWvfIVTTjmFW265ZbONcaA3NlTVuqo6CBihN6t2AL2l0VfSW2JdBXymO3ysGbQapz5em/XHcW5VzaqqWTNmzHiWZyFJkrY0r3rVq7jpppt47Wtfy2mnncZXv/pV9t9/f26++WZuvvlmFi9ezLXXXgvAU089xW233ca2227LAw88sNnGuFnuTq2qh4BvA3Oq6p4u3D0FnAcc1h22HNizr9kIsLKrj4xRf1qbJNOAHYDN99eTJElT0sqVK3nRi17Ee9/7Xj7+8Y9z4403smbNGm644Qag9yivpUuXAnDWWWfxmte8hgULFnDSSSfx5JNPbpYxDmw5NckM4MmqeijJtsCbgTOS7F5Vq7rDfg1Y0m1fCXw5yWeBPejdwLCwqtYleaS7KeJG4Hjgc31tTgBuAI4FvtVdNydJatSpp57K6tWr2W233TjzzDOHPRxtoRYvXszv//7vs9VWWzF9+nTOOeccpk2bxu/+7u/y8MMPs3btWj760Y8yffp0/vIv/5KFCxey3XbbccQRR/DpT3+a008/feBjHOQ1cbsDF3XXxW0FXFZVVyX5UpKD6C173gV8AKCqlia5DLgVWAucUlXrur4+BFwIbAtc3b0Azge+lGQZvRm4uQM8H0nSZrB69WpWrFgx7GFoCzd79mxmz579jPr111//jNptt932s+3PfvazAx1Xv4GFuKr6PnDwGPXfGqfNfGD+GPVFwAFj1B8D3vP8RipJktQen9ggSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1KCBPnZLkiRpsrnqX+7cpP294+C9N3rMNddcw0c+8hHWrVvH+973Pj7xiU887+91Jk6SJGmA1q1bxymnnMLVV1/NrbfeyoIFC7j11lufd7+GOEmSpAFauHAh++yzD694xSt4wQtewNy5c7niiiued7+GOEmSpAFasWIFe+75n4+HHxkZ2SRPJTHESZIkDdBYj3VP8rz7NcRJkiQN0MjICHfffffPPi9fvpw99tjjefdriJMkSRqgQw89lDvuuIM777yTJ554gksuuYR3vvOdz7tff2JEkiRtUSbykyCb0rRp0/j85z/P7NmzWbduHSeddBL777//8+93E4xNkiRJ4zjqqKM46qijNmmfLqdKkiQ1yJk4SWrQpv7F+cnk0cfX/ux9qp7n5l7O09TkTJwkSVKDnImTJEmbxKmnnsrq1avZbbfdOPPMM4c9nCnPECdJkjaJ1atXb5InEWhiXE6VJElqkDNxkiRpi/K2+V/fpP1d/cljNnrMSSedxFVXXcWuu+7KkiVLNsn3OhMnSZI0YCeeeCLXXHPNJu3TECdJkjRgRxxxBDvttNMm7dMQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXInxiRJElblIn8JMimdtxxx/Htb3+b++67j5GREU4//XROPvnk59WnIU6SJGnAFixYsMn7dDlVkiSpQYY4SZKkBhniJEnSlFdVwx7CuJ7L+AxxkiRpSttmm224//77J22Qqyruv/9+ttlmm2fVzhsbJEnSlDYyMsLy5ctZs2bNsIeyQdtssw0jIyPPqo0hTpIkTWnTp09n7733HvYwNjlDnCRpUtl+p52f9i5pbIY4SdKk8u55vzfsIUhN8MYGSZKkBhniJEmSGmSIkyRJapDXxEmStJm9bf7Xhz2EgXjigUcBWPHAo1P2HK/+5DHDHsLPOBMnSZLUIEOcJElSgwxxkiRJDRpYiEuyTZKFSW5JsjTJ6V19pyTfTHJH975jX5vTkixLcnuS2X31Q5Is7vadnSRd/YVJLu3qNybZa1DnI0mSNJkMcibuceBXqupA4CBgTpLDgU8A11XVvsB13WeS7AfMBfYH5gBfSLJ119c5wDxg3+41p6ufDDxYVfsAZwFnDPB8JEmSJo2Bhbjq+Un3cXr3KuBo4KKufhEwepvH0cAlVfV4Vd0JLAMOS7I7sH1V3VBVBVy8XpvRvi4HjhydpZMkSZrKBnpNXJKtk9wM3At8s6puBF5aVasAuvddu8NnAnf3NV/e1WZ22+vXn9amqtYCDwPPeNheknlJFiVZtGbNmk11epIkSUMz0BBXVeuq6iBghN6s2gHjHD7WDFqNUx+vzfrjOLeqZlXVrBkzZmxs2JIkSZPeZrk7taoeAr5N71q2e7olUrr3e7vDlgN79jUbAVZ29ZEx6k9rk2QasAPwwEBOQpIkaRIZ5N2pM5K8pNveFngz8K/AlcAJ3WEnAFd021cCc7s7TvemdwPDwm7J9ZEkh3fXux2/XpvRvo4FvtVdNydJkjSlDfKxW7sDF3V3mG4FXFZVVyW5AbgsycnAvwPvAaiqpUkuA24F1gKnVNW6rq8PARcC2wJXdy+A84EvJVlGbwZu7gDPR5IkadIYWIirqu8DB49Rvx84cgNt5gPzx6gvAp5xPV1VPUYXAiVJkrYkPrFBkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBg3zsliRJ2oJkm+2o7l2DZ4iTJEmbxPSDjxn2ELYoLqdKkiQ1yBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdJktQgQ5wkSVKDDHGSJEkNMsRJkiQ1yBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdJktQgQ5wkSVKDDHGSJEkNMsRJkiQ1yBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0aWIhLsmeSv09yW5KlST7S1T+VZEWSm7vXUX1tTkuyLMntSWb31Q9Jsrjbd3aSdPUXJrm0q9+YZK9BnY8kSdJkMsiZuLXAx6rqNcDhwClJ9uv2nVVVB3WvbwB0++YC+wNzgC8k2bo7/hxgHrBv95rT1U8GHqyqfYCzgDMGeD6SJEmTxsBCXFWtqqp/7rYfAW4DZo7T5Gjgkqp6vKruBJYBhyXZHdi+qm6oqgIuBo7pa3NRt305cOToLJ0kSdJUtlmuieuWOQ8GbuxKH07y/SQXJNmxq80E7u5rtryrzey2168/rU1VrQUeBnYe4/vnJVmUZNGaNWs2yTlJkiQN08BDXJIXA18FPlpVP6a3NPpK4CBgFfCZ0UPHaF7j1Mdr8/RC1blVNauqZs2YMeNZnoEkSdLkM9AQl2Q6vQD311X1NwBVdU9Vrauqp4DzgMO6w5cDe/Y1HwFWdvWRMepPa5NkGrAD8MBgzkaSJGnyGOTdqQHOB26rqs/21XfvO+zXgCXd9pXA3O6O073p3cCwsKpWAY8kObzr83jgir42J3TbxwLf6q6bkyRJmtKmDbDvXwR+C1ic5Oau9ofAcUkOorfseRfwAYCqWprkMuBWene2nlJV67p2HwIuBLYFru5e0AuJX0qyjN4M3NwBno8kSdKkMbAQV1XfYexr1r4xTpv5wPwx6ouAA8aoPwa853kMU5IkqUk+sUGSJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGjSwEJdkzyR/n+S2JEuTfKSr75Tkm0nu6N537GtzWpJlSW5PMruvfkiSxd2+s5Okq78wyaVd/cYkew3qfCRJkiaTQc7ErQU+VlWvAQ4HTkmyH/AJ4Lqq2he4rvtMt28usD8wB/hCkq27vs4B5gH7dq85Xf1k4MGq2gc4CzhjgOcjSZI0aQwsxFXVqqr65277EeA2YCZwNHBRd9hFwDHd9tHAJVX1eFXdCSwDDkuyO7B9Vd1QVQVcvF6b0b4uB44cnaWTJEmayjbLNXHdMufBwI3AS6tqFfSCHrBrd9hM4O6+Zsu72sxue/3609pU1VrgYWDnMb5/XpJFSRatWbNm05yUJEnSEA08xCV5MfBV4KNV9ePxDh2jVuPUx2vz9ELVuVU1q6pmzZgxY2NDliRJmvSedYhLsmOS103w2On0AtxfV9XfdOV7uiVSuvd7u/pyYM++5iPAyq4+Mkb9aW2STAN2AB54tuckSZLUmgmFuCTfTrJ9kp2AW4AvJvnsRtoEOB+4rar6j70SOKHbPgG4oq8+t7vjdG96NzAs7JZcH0lyeNfn8eu1Ge3rWOBb3XVzkiRJU9q0CR63Q1X9OMn7gC9W1R8n+f5G2vwi8FvA4iQ3d7U/BP4MuCzJycC/A+8BqKqlSS4DbqV3Z+spVbWua/ch4EJgW+Dq7gW9kPilJMvozcDNneD5SJIkNW2iIW5at/T568AnJ9Kgqr7D2NesARy5gTbzgflj1BcBB4xRf4wuBEqSJG1JJnpN3J8Afwv8oKq+l+QVwB2DG5YkSZLGM6GZuKr6CvCVvs8/BN49qEFJkiRpfBO9seFVSa5LsqT7/LokfzTYoUmSJGlDJrqceh5wGvAkQFV9H28ikCRJGpqJhrgXVdXC9WprN/VgJEmSNDETDXH3JXkl3dMQkhwLrBrYqCRJkjSuif7EyCnAucDPJ1kB3Am8d2CjkiRJ0rgmenfqD4E3J/k5YKuqemSww5IkSdJ4JhTikvzeep8BHgZuqqqbx2wkSZKkgZnoNXGzgA8CM7vXPOBNwHlJTh3M0CRJkrQhE70mbmfg9VX1E4AkfwxcDhwB3AScOZjhSZIkaSwTnYl7GfBE3+cngZdX1U+Bxzf5qCRJkjSuic7EfRn4bpIrus+/CizobnS4dSAjkyRJ0gZtNMSldxfDhcA3gF8CAnywqhZ1h/zXgY1OkiRJY9poiKuqSvL1qjqE3vVvkiRJGrKJXhP33SSHDnQkkiRJmrCJXhP3y8AHkvwIeJTekmpV1esGNjJJkiRt0ERD3NsGOgpJkiQ9KxN97NaPAJLsCmwz0BFJkiRpoyZ0TVySdya5g96D7/8BuAu4eoDjkiRJ0jgmemPDfwcOB/6tqvYGjgT+cWCjkiRJ0rgmGuKerKr7ga2SbFVVfw8cNMBxSZIkaRwTvbHhoSQvBq4H/jrJvcDawQ1LkiRJ45noTNzRwE+B/wZcA/yA3qO3JEmSNAQTvTv10b6PFw1oLJIkSZqgid6d+q4kdyR5OMmPkzyS5MeDHpwkSZLGNtFr4s4EfrWqbhvkYCRJkjQxE70m7h4DnCRJ0uQx7kxcknd1m4uSXAp8HXh8dH9V/c0AxyZJkqQN2Nhy6ugdqAX8B/DWvn0FGOIkSZKGYNwQV1W/DZDkIuAjVfVQ93lH4DODH54kSZLGMtFr4l43GuAAqupB4ODBDEmSJEkbM9EQt1U3+wZAkp2Y+J2tkiRJ2sQmGsQ+A/xTksvpXQv368D8gY1KkiRJ45roExsuTrII+BUgwLuq6taBjkySJEkbNOEl0S60GdwkSZImgYleEydJkqRJxBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0aWIhLckGSe5Ms6at9KsmKJDd3r6P69p2WZFmS25PM7qsfkmRxt+/sJOnqL0xyaVe/MclegzoXSZKkyWaQM3EXAnPGqJ9VVQd1r28AJNkPmAvs37X5QpKtu+PPAeYB+3av0T5PBh6sqn2As4AzBnUikiRJk83AQlxVXQ88MMHDjwYuqarHq+pOYBlwWJLdge2r6oaqKuBi4Ji+Nhd125cDR47O0kmSJE11w7gm7sNJvt8tt+7Y1WYCd/cds7yrzey2168/rU1VrQUeBnYe6wuTzEuyKMmiNWvWbLozkSRJGpLNHeLOAV4JHASsAj7T1ceaQatx6uO1eWax6tyqmlVVs2bMmPHsRixJkjQJbdYQV1X3VNW6qnoKOA84rNu1HNiz79ARYGVXHxmj/rQ2SaYBOzDx5VtJkqSmbdYQ113jNurXgNE7V68E5nZ3nO5N7waGhVW1CngkyeHd9W7HA1f0tTmh2z4W+FZ33ZwkSdKUN21QHSdZALwJ2CXJcuCPgTclOYjesuddwAcAqmppksuAW4G1wClVta7r6kP07nTdFri6ewGcD3wpyTJ6M3BzB3UukiRJk83AQlxVHTdG+fxxjp8PzB+jvgg4YIz6Y8B7ns8YJUmSWuUTGyRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQQMLcUkuSHJvkiV9tZ2SfDPJHd37jn37TkuyLMntSWb31Q9Jsrjbd3aSdPUXJrm0q9+YZK9BnYskSdJkM8iZuAuBOevVPgFcV1X7Atd1n0myHzAX2L9r84UkW3dtzgHmAft2r9E+TwYerKp9gLOAMwZ2JpIkSZPMwEJcVV0PPLBe+Wjgom77IuCYvvolVfV4Vd0JLAMOS7I7sH1V3VBVBVy8XpvRvi4HjhydpZMkSZrqNvc1cS+tqlUA3fuuXX0mcHffccu72sxue/3609pU1VrgYWDnsb40ybwki5IsWrNmzSY6FUmSpOGZLDc2jDWDVuPUx2vzzGLVuVU1q6pmzZgx4zkOUZIkafLY3CHunm6JlO793q6+HNiz77gRYGVXHxmj/rQ2SaYBO/DM5VtJkqQpaXOHuCuBE7rtE4Ar+upzuztO96Z3A8PCbsn1kSSHd9e7Hb9em9G+jgW+1V03J0mSNOVNG1THSRYAbwJ2SbIc+GPgz4DLkpwM/DvwHoCqWprkMuBWYC1wSlWt67r6EL07XbcFru5eAOcDX0qyjN4M3NxBnYskSdJkM7AQV1XHbWDXkRs4fj4wf4z6IuCAMeqP0YVASZKkLc3AQpykyevUU09l9erV7Lbbbpx55pnDHo4k6TkwxElboNWrV7NixYphD0OS9DxMlp8YkSRJ0rNgiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIa5N2p0jjeNv/rwx7CQDzxwKMArHjg0Sl7jld/8phhD0GSBsoQp+fM3xqTJGl4DHF6zvytMUmShsdr4iRJkhpkiJMkSWqQIU6SJKlBXhMnbYGyzXZU9y5JapMhbsCu+pc7hz2EgXn08bU/e5/K5zkVTT/Yn9+QpNa5nCpJktQgQ5wkSVKDDHGSJEkNMsRJkiQ1yBAnSZLUIO9O1XO2/U47P+1dkiRtPoY4PWfvnvd7wx6CJElbLJdTJUmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaZIiTJElqkCFOkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkSZIaNJQQl+SuJIuT3JxkUVfbKck3k9zRve/Yd/xpSZYluT3J7L76IV0/y5KcnSTDOB9JkqTNbZgzcb9cVQdV1azu8yeA66pqX+C67jNJ9gPmAje0wYQAAAYgSURBVPsDc4AvJNm6a3MOMA/Yt3vN2YzjlyRJGprJtJx6NHBRt30RcExf/ZKqeryq7gSWAYcl2R3YvqpuqKoCLu5rI0mSNKUNK8QVcG2Sm5LM62ovrapVAN37rl19JnB3X9vlXW1mt71+/RmSzEuyKMmiNWvWbMLTkCRJGo5pQ/reX6yqlUl2Bb6Z5F/HOXas69xqnPozi1XnAucCzJo1a8xjJEmSWjKUmbiqWtm93wt8DTgMuKdbIqV7v7c7fDmwZ1/zEWBlVx8Zoy5JkjTlbfYQl+Tnkmw3ug28FVgCXAmc0B12AnBFt30lMDfJC5PsTe8GhoXdkusjSQ7v7ko9vq+NJEnSlDaM5dSXAl/rfg1kGvDlqromyfeAy5KcDPw78B6Aqlqa5DLgVmAtcEpVrev6+hBwIbAtcHX3kiRJmvI2e4irqh8CB45Rvx84cgNt5gPzx6gvAg7Y1GOUJEma7CbTT4xIkiRpggxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdJktQgQ5wkSVKDDHGSJEkNMsRJkiQ1yBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdJktQgQ5wkSVKDDHGSJEkNMsRJkiQ1yBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdJktQgQ5wkSVKDDHGSJEkNMsRJkiQ1yBAnSZLUIEOcJElSgwxxkiRJDTLESZIkNcgQJ0mS1CBDnCRJUoMMcZIkSQ0yxEmSJDXIECdJktSg5kNckjlJbk+yLMknhj0eSZKkzaHpEJdka+AvgLcB+wHHJdlvuKOSJEkavKZDHHAYsKyqflhVTwCXAEcPeUySJEkDN23YA3ieZgJ3931eDvzC+gclmQfM6z7+JMntm2Fsmhp2Ae4b9iD07OWPhj0CaVz+29KoIfzb8vIN7Wg9xGWMWj2jUHUucO7gh6OpJsmiqpo17HFImlr8t0WbQuvLqcuBPfs+jwArhzQWSZKkzab1EPc9YN8keyd5ATAXuHLIY5IkSRq4ppdTq2ptkg8DfwtsDVxQVUuHPCxNLS7DSxoE/23R85aqZ1xCJkmSpEmu9eVUSZKkLZIhTpIkqUGGOGkMPs5N0iAkuSDJvUmWDHssap8hTlqPj3OTNEAXAnOGPQhNDYY46Zl8nJukgaiq64EHhj0OTQ2GOOmZxnqc28whjUWSpDEZ4qRnmtDj3CRJGiZDnPRMPs5NkjTpGeKkZ/JxbpKkSc8QJ62nqtYCo49zuw24zMe5SdoUkiwAbgBenWR5kpOHPSa1y8duSZIkNciZOEmSpAYZ4iRJkhpkiJMkSWqQIU6SJKlBhjhJkqQGGeIkaRNK8qYkVw17HJKmPkOcJE0SSaYNewyS2mGIk7RFS/JzSf5vkluSLEnyG0nuSvKnSW5IsijJ65P8bZIfJPlg1y5J/rxrszjJb4zR96FJ/iXJK5IckuQfktzU9bV7d8y3u+/6B+Ajm/n0JTXM/+uTtKWbA6ysqrcDJNkBOAO4u6rekOQs4ELgF4FtgKXA/wbeBRwEHAjsAnwvyfWjnSb5L8DngKOBVcBfAUdX1Zou8M0HTuoOf0lVvXHQJyppajHESdrSLQb+Z5IzgKuq6v8lgf98Xu5i4MVV9QjwSJLHkrwE+CVgQVWtA+7pZtIOBX4MvAY4F3hrVa1McgBwAPDNru+t6QW7UZcO/CwlTTmGOElbtKr6tySHAEcB/yPJtd2ux7v3p/q2Rz9PAzJOt6vozdodDKzsjl1aVW/YwPGPPsfhS9qCeU2cpC1akj2A/6iqvwL+J/D6CTa9HviNJFsnmQEcASzs9j0EvB340yRvAm4HZiR5Q/ed05PsvwlPQ9IWyJk4SVu61wJ/nuQp4EngQ8DlE2j3NeANwC1AAadW1eokPw9QVfck+VXganrXvh0LnN1dczcN+F/0rq+TpOckVTXsMUiSJOlZcjlVkiSpQYY4SZKkBhniJEmSGmSIkyRJapAhTpIkqUGGOEmSpAYZ4iRJkhr0/wFwngJb/VsMzQAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,7))\n",
    "plt.title('Smoker vs Charge')\n",
    "sns.barplot(x='smoker',y='charges',data=data_copy,palette='Blues',hue='sex')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x2e69a291a20>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAnEAAAG5CAYAAADh3mJ8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3de7SddX3n8fdHolwLcgkXE2poRS1Q20qK2Dpd7dCRaJUwVtpQLWlLG2XhtFPtUGidsbdMlV5s6RRmoShBLZBSK6lTtAy2Oq1cPHgptyJRFAIJRECIikjwO3/sX+rm5CQ5weyzz+/4fq111nn273mevX8PrJX1Xs/l7FQVkiRJ6svTxj0BSZIk7TwjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEnSCCX5nSTvHfc8JM09RpykWSfJS5J8PMnDSR5M8i9Jfnjc89qWJD+XZCLJV5KsT3JVkpeMe16S5jYjTtKskmRf4IPAXwAHAAuA3wUeG+e8tiXJG4E/A/4ncAjw3cD5wNIRfNa8Xf2ekvplxEmabZ4LUFWXVtUTVfVoVf1DVf3rlg2S/FKS25I8lOTDSZ7dxn8zyXVbYifJGUluSbLH5A9p+79i6PW8JF9K8sIkeyR5b5IHknw5ySeSHDLFe+wH/B5wZlW9v6q+WlWPV9XfVdV/G9r0GUkuSbKpzWfx0HucneRzbd2tSf7z0LpfaGch357kQeB3khyY5O+SPNLm9QdJ/nlon+cnubqdwbw9yc8MrXt5+4xNSe5J8hs7+z9H0uxhxEmabT4LPJFkVZKXJdl/eGWSk4HfAl4FzAf+H3BpW/1HwDeANyc5ksHZsddW1den+JxLgVOHXp8IfKmqPgksB/YDDgcOBF4PPDrFe7wY2AP42x0c00nAZcAzgTXA/xpa9zngP7TP+13gvUkOG1r/IuDzwMHASuAvga8Ch7Z5Lt+yYZK9gauBv2rbnwqcn+TotslFwOuq6ruAY4CP7GDekmYxI07SrFJVjwAvAQp4B7AxyZqhM2GvA/6wqm6rqs0MQu0Hkzy7qr4JnAb8KoNYOreqPrWNj/or4KQke7XXP9fGAB5nEG/PaWcDb2zzmuxABuG3eQeH9c9V9fdV9QTwHuAHho73r6vq3qr6ZlVdDtwBHDe0771V9RftM74B/DTwlqr6WlXdCqwa2vYVwBeq6t1VtbkF6d8Arx46rqOS7FtVD7X1kjplxEmadVqg/UJVLWRwxuhZDO47A3g28OftMueXgQeBMLh3jqr6AvCPwCIGZ6229RlrgduAV7aQO4lvRdx7gA8DlyW5N8m5SZ4+xds8ABw0jXvVNgwtfw3YY+iS72lJPj10PMcABw1tf/fQ8nxg3qSx4eVnAy/a8l7t/V7D4KwdDALw5cAXk3w0yYt3MG9Js5gRJ2lWq6p/Ay5mEDcwiJbXVdUzh372rKqPw+C+LwaXOa9hcHl1e7ZcUl0K3NrCjnZf2+9W1VHAjzA4w3XaFPtfC3wdOPmpHFu7l+8dwBuAA6vqmcDNDKJ0ixpa3ghsBhYOjR0+tHw38NFJ/232qaoz2nF9oqqWMrjU+gFg9VOZt6TZwYiTNKu0G/PflGRhe304g9C6rm3yv4FzttznlWS/JKe05YMY3Pf1ywzuFXtli7ptuQx4KXAG3zoLR5KfSPL9SXYDHmFwGfKJyTtX1cPA/wD+MsnJSfZK8vR2L9+50zjcvRlE2sb2ub/It2J1K+1y7PsZPOCwV5Ln8+S4/CDw3CQ/3+bx9CQ/nOT7kjwjyWuS7FdVj7fj2uqYJPXDiJM022xicDP/9Um+yiDebgbeBFBVfwu8jcGlzkfaupe1fS8Ermz3nz0AnA68M8mBU31QVa1ncDbtR4DLh1YdClzBIHRuAz4KTPkHe6vqT4E3Am9mEGN3Mziz9oEdHWi7p+1P2hzuA74f+Jcd7PYGBg9BbGBw2fdS2p9fqapNDKJ0GXBv2+ZtwO5t358HvtD+u70eeO2O5ihp9kpV7XgrSdKslORtwKFVtXyHG0uaUzwTJ0kdaZebX5CB4xicbdzRnziRNAf5178lqS/fxeAS6rOA+xlcjr1yrDOSNBZeTpUkSeqQl1MlSZI69B13OfWggw6qRYsWjXsakiRJO3TjjTd+qarmT7XuOy7iFi1axMTExLinIUmStENJvritdV5OlSRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6NG/cE5Bmq7POOosNGzZw6KGHcu655457OpIkPYkRJ23Dhg0buOeee8Y9DUmSpuTlVEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOjSyiEvyriT3J7l5inW/kaSSHDQ0dk6StUluT3Li0PixSW5q685Lkja+e5LL2/j1SRaN6lgkSZJmm1GeibsYWDJ5MMnhwH8C7hoaOwpYBhzd9jk/yW5t9QXACuDI9rPlPU8HHqqq5wBvB942kqOQJEmahUYWcVX1MeDBKVa9HTgLqKGxpcBlVfVYVd0JrAWOS3IYsG9VXVtVBVwCnDy0z6q2fAVwwpazdJIkSXPdjN4Tl+Qk4J6q+sykVQuAu4der2tjC9ry5PEn7VNVm4GHgQO38bkrkkwkmdi4ceO3fRySJEnjNm+mPijJXsBvAy+davUUY7Wd8e3ts/Vg1YXAhQCLFy+ecptRmVh83Ex+nHahx/bZG3Z7Go/ddbf/Hzu0eOKGcU9BkkZqJs/EfS9wBPCZJF8AFgKfTHIogzNshw9tuxC4t40vnGKc4X2SzAP2Y+rLt5IkSXPOjEVcVd1UVQdX1aKqWsQgwl5YVRuANcCy9sTpEQweYLihqtYDm5Ic3+53Ow24sr3lGmB5W3418JF235wkSdKcN8o/MXIpcC3wvCTrkpy+rW2r6hZgNXAr8CHgzKp6oq0+A3gng4cdPgdc1cYvAg5MshZ4I3D2SA5EkiRpFhrZPXFVdeoO1i+a9HolsHKK7SaAY6YY/zpwyrc3S0mSpD75jQ2SJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDo3sj/1KkqStnXXWWWzYsIFDDz2Uc889d9zTUceMOEmSZtCGDRu45557xj0NzQFeTpUkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkN/YIG3D/t/85pN+S5I0mxhx0jb88tceHfcUJEnaJi+nSpIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjrkH/uVpA4t+e+Xj3sKeooef+ArANzzwFf8/9ihD/3+z457Cv/OM3GSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOjSyiEvyriT3J7l5aOyPkvxbkn9N8rdJnjm07pwka5PcnuTEofFjk9zU1p2XJG189ySXt/Hrkywa1bFIkiTNNqM8E3cxsGTS2NXAMVX1AuCzwDkASY4ClgFHt33OT7Jb2+cCYAVwZPvZ8p6nAw9V1XOAtwNvG9mRSJIkzTIji7iq+hjw4KSxf6iqze3ldcDCtrwUuKyqHquqO4G1wHFJDgP2raprq6qAS4CTh/ZZ1ZavAE7YcpZOkiRprhvnPXG/BFzVlhcAdw+tW9fGFrTlyeNP2qeF4cPAgVN9UJIVSSaSTGzcuHGXHYAkSdK4jCXikvw2sBl435ahKTar7Yxvb5+tB6surKrFVbV4/vz5OztdSZKkWWfGIy7JcuAVwGvaJVIYnGE7fGizhcC9bXzhFONP2ifJPGA/Jl2+lSRJmqtmNOKSLAF+Ezipqr42tGoNsKw9cXoEgwcYbqiq9cCmJMe3+91OA64c2md5W3418JGhKJQkSZrT5o3qjZNcCvw4cFCSdcBbGDyNujtwdXsG4bqqen1V3ZJkNXArg8usZ1bVE+2tzmDwpOueDO6h23If3UXAe5KsZXAGbtmojkWSJGm2GVnEVdWpUwxftJ3tVwIrpxifAI6ZYvzrwCnfzhwlSZJ65Tc2SJIkdWhkZ+IkSdLWsvs+gz+/sPs+456KOmfESZI0g+Yd/VPjnoLmCC+nSpIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDI4u4JO9Kcn+Sm4fGDkhydZI72u/9h9adk2RtktuTnDg0fmySm9q685Kkje+e5PI2fn2SRaM6FkmSpNlmlGfiLgaWTBo7G7imqo4ErmmvSXIUsAw4uu1zfpLd2j4XACuAI9vPlvc8HXioqp4DvB1428iORJIkaZYZWcRV1ceABycNLwVWteVVwMlD45dV1WNVdSewFjguyWHAvlV1bVUVcMmkfba81xXACVvO0kmSJM11M31P3CFVtR6g/T64jS8A7h7abl0bW9CWJ48/aZ+q2gw8DBw41YcmWZFkIsnExo0bd9GhSJIkjc9sebBhqjNotZ3x7e2z9WDVhVW1uKoWz58//ylOUZIkafaY6Yi7r10ipf2+v42vAw4f2m4hcG8bXzjF+JP2STIP2I+tL99KkiTNSTMdcWuA5W15OXDl0Piy9sTpEQweYLihXXLdlOT4dr/baZP22fJerwY+0u6bkyRJmvPmjeqNk1wK/DhwUJJ1wFuAtwKrk5wO3AWcAlBVtyRZDdwKbAbOrKon2ludweBJ1z2Bq9oPwEXAe5KsZXAGbtmojkWSJGm2GVnEVdWp21h1wja2XwmsnGJ8AjhmivGv0yJQkiTpO81sebBBkiRJO8GIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUod2OuKS7J/kBaOYjCRJkqZnWhGX5J+S7JvkAOAzwLuT/OlopyZJkqRtme6ZuP2q6hHgVcC7q+pY4CdHNy1JkiRtz3Qjbl6Sw4CfAT44wvlIkiRpGqYbcb8HfBj4XFV9Isn3AHeMblqSJEnannnT2aiq/hr466HXnwd+elSTkiRJ0vZN98GG5ya5JsnN7fULkrx5tFOTJEnStkz3cuo7gHOAxwGq6l+BZaOalCRJkrZvuhG3V1XdMGls866ejCRJkqZnuhH3pSTfCxRAklcD60c2K0mSJG3XtB5sAM4ELgSen+Qe4E7gtSOblSRJkrZrWmfiqurzVfWTwHzg+VX1kqr6wlP90CS/nuSWJDcnuTTJHkkOSHJ1kjva7/2Htj8nydoktyc5cWj82CQ3tXXnJclTnZMkSVJPpnUmLskbJ70GeBi4sao+vTMfmGQB8KvAUVX1aJLVDB6SOAq4pqremuRs4GzgN5Mc1dYfDTwL+L9JnltVTwAXACuA64C/B5YAV+3MfCRJkno03XviFgOvBxa0nxXAjwPvSHLWU/jcecCeSeYBewH3AkuBVW39KuDktrwUuKyqHquqO4G1wHHtGyT2raprq6qAS4b2kSRJmtOmG3EHAi+sqjdV1ZsYRN184MeAX9iZD6yqe4A/Bu5i8HDEw1X1D8AhVbW+bbMeOLjtsgC4e+gt1vGtmFw3xfhWkqxIMpFkYuPGjTszXUmSpFlpuhH33cA3hl4/Djy7qh4FHtuZD2z3ui0FjmBweXTvJNt7SGKq+9xqO+NbD1ZdWFWLq2rx/Pnzd2a6kiRJs9J0n079K+C6JFe2168ELk2yN3DrTn7mTwJ3VtVGgCTvB34EuC/JYVW1vl0qvb9tvw44fGj/hQwuv65ry5PHJUmS5rwdnolrT3xeDPwK8GUGDzS8vqp+r6q+WlWv2cnPvAs4Psle7b1PAG4D1gDL2zbLgS3BuAZYlmT3JEcARwI3tEuum5Ic397ntKF9JEmS5rQdnomrqkrygao6Frjx2/3Aqro+yRXAJxl868OnGPwNun2A1UlOZxB6p7Ttb2lPsN7atj+zPZkKcAaDwNyTwVOpPpkqSZK+I0z3cup1SX64qj6xKz60qt4CvGXS8GMMzspNtf1KYOUU4xPAMbtiTpIkST2ZbsT9BPC6JF8EvsrgoYKqqheMbGaSJEnapulG3MtGOgtJkiTtlGlFXFV9ESDJwcAeI52RJEmSdmhafycuyUlJ7mDwxfcfBb6ADxFIkiSNzXT/2O/vA8cDn62qIxg8gPAvI5uVJEmStmu6Efd4VT0APC3J06rqH4EfHOG8JEmStB3TfbDhy0n2AT4GvC/J/Qz+ZpskSZLGYLpn4pYCjwK/DnwI+ByDr96SJEnSGEz36dSvDr1cNaK5SJIkaZqm+3Tqq5LckeThJI8k2ZTkkVFPTpIkSVOb7j1x5wKvrKrbRjkZSZIkTc9074m7z4CTJEmaPbZ7Ji7Jq9riRJLLgQ8w+KJ6AKrq/SOcmyRJkrZhR5dTtzyBWsDXgJcOrSvAiJMkSRqD7UZcVf0iQJJVwK9V1Zfb6/2BPxn99CRJkjSV6d4T94ItAQdQVQ8BPzSaKUmSJGlHphtxT2tn3wBIcgDTf7JVkiRJu9h0Q+xPgI8nuYLBvXA/A6wc2awkSZK0XdP9xoZLkkwA/xEI8KqqunWkM5MkSdI2TfuSaIs2w02SJGkWmO49cZIkSZpFjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0aS8QleWaSK5L8W5Lbkrw4yQFJrk5yR/u9/9D25yRZm+T2JCcOjR+b5Ka27rwkGcfxSJIkzbRxnYn7c+BDVfV84AeA24CzgWuq6kjgmvaaJEcBy4CjgSXA+Ul2a+9zAbACOLL9LJnJg5AkSRqXGY+4JPsCPwZcBFBV36iqLwNLgVVts1XAyW15KXBZVT1WVXcCa4HjkhwG7FtV11ZVAZcM7SNJkjSnjeNM3PcAG4F3J/lUkncm2Rs4pKrWA7TfB7ftFwB3D+2/ro0taMuTx7eSZEWSiSQTGzdu3LVHI0mSNAbjiLh5wAuBC6rqh4Cv0i6dbsNU97nVdsa3Hqy6sKoWV9Xi+fPn7+x8JUmSZp1xRNw6YF1VXd9eX8Eg6u5rl0hpv+8f2v7wof0XAve28YVTjEuSJM15Mx5xVbUBuDvJ89rQCcCtwBpgeRtbDlzZltcAy5LsnuQIBg8w3NAuuW5Kcnx7KvW0oX0kSZLmtHlj+tz/ArwvyTOAzwO/yCAoVyc5HbgLOAWgqm5JsppB6G0GzqyqJ9r7nAFcDOwJXNV+JEmS5ryxRFxVfRpYPMWqE7ax/Upg5RTjE8Axu3Z2kiRJs5/f2CBJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6tDYIi7Jbkk+leSD7fUBSa5Ockf7vf/QtuckWZvk9iQnDo0fm+Smtu68JBnHsUiSJM20cZ6J+zXgtqHXZwPXVNWRwDXtNUmOApYBRwNLgPOT7Nb2uQBYARzZfpbMzNQlSZLGaywRl2Qh8FPAO4eGlwKr2vIq4OSh8cuq6rGquhNYCxyX5DBg36q6tqoKuGRoH0mSpDltXGfi/gw4C/jm0NghVbUeoP0+uI0vAO4e2m5dG1vQliePbyXJiiQTSSY2bty4a45AkiRpjGY84pK8Ari/qm6c7i5TjNV2xrcerLqwqhZX1eL58+dP82MlSZJmr3lj+MwfBU5K8nJgD2DfJO8F7ktyWFWtb5dK72/brwMOH9p/IXBvG184xbgkSdKcN+Nn4qrqnKpaWFWLGDyw8JGqei2wBljeNlsOXNmW1wDLkuye5AgGDzDc0C65bkpyfHsq9bShfSRJkua0cZyJ25a3AquTnA7cBZwCUFW3JFkN3ApsBs6sqifaPmcAFwN7Ale1H0mSpDlvrBFXVf8E/FNbfgA4YRvbrQRWTjE+ARwzuhlKkiTNTn5jgyRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUoRmPuCSHJ/nHJLcluSXJr7XxA5JcneSO9nv/oX3OSbI2ye1JThwaPzbJTW3deUky08cjSZI0DuM4E7cZeFNVfR9wPHBmkqOAs4FrqupI4Jr2mrZuGXA0sAQ4P8lu7b0uAFYAR7afJTN5IJIkSeMy4xFXVeur6pNteRNwG7AAWAqsaputAk5uy0uBy6rqsaq6E1gLHJfkMGDfqrq2qgq4ZGgfSZKkOW2s98QlWQT8EHA9cEhVrYdB6AEHt80WAHcP7baujS1oy5PHp/qcFUkmkkxs3LhxVx6CJEnSWIwt4pLsA/wN8F+r6pHtbTrFWG1nfOvBqguranFVLZ4/f/7OT1aSJGmWGUvEJXk6g4B7X1W9vw3f1y6R0n7f38bXAYcP7b4QuLeNL5xiXJIkac4bx9OpAS4CbquqPx1atQZY3paXA1cOjS9LsnuSIxg8wHBDu+S6Kcnx7T1PG9pHkiRpTps3hs/8UeDngZuSfLqN/RbwVmB1ktOBu4BTAKrqliSrgVsZPNl6ZlU90fY7A7gY2BO4qv1IkiTNeTMecVX1z0x9PxvACdvYZyWwcorxCeCYXTc7SZKkPviNDZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOmTESZIkdciIkyRJ6pARJ0mS1CEjTpIkqUNGnCRJUoeMOEmSpA4ZcZIkSR0y4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSJEkdMuIkSZI6ZMRJkiR1yIiTJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDnUfcUmWJLk9ydokZ497PpIkSTOh64hLshvwl8DLgKOAU5McNd5ZSZIkjV7XEQccB6ytqs9X1TeAy4ClY56TJEnSyM0b9wS+TQuAu4derwNeNHmjJCuAFe3lV5LcPgNz09xwEPClcU9CT0Ey7hlI2+O/LZ3KHyyb6Y989rZW9B5xU/0rXVsNVF0IXDj66WiuSTJRVYvHPQ9Jc4v/tmhX6P1y6jrg8KHXC4F7xzQXSZKkGdN7xH0CODLJEUmeASwD1ox5TpIkSSPX9eXUqtqc5A3Ah4HdgHdV1S1jnpbmFi/DSxoF/23Rty1VW91CJkmSpFmu98upkiRJ35GMOEmSpA4ZcdIU/Do3SaOQ5F1J7k9y87jnov4ZcdIkfp2bpBG6GFgy7klobjDipK35dW6SRqKqPgY8OO55aG4w4qStTfV1bgvGNBdJkqZkxElbm9bXuUmSNE5GnLQ1v85NkjTrGXHS1vw6N0nSrGfESZNU1WZgy9e53Qas9uvcJO0KSS4FrgWel2RdktPHPSf1y6/dkiRJ6pBn4iRJkjpkxEmSJHXIiJMkSeqQESdJktQhI06SJKlDRpwkSVKHjDhJkqQOGXGSNA1J9k7yf5J8JsnNSX42ybFJPprkxiQfTnJYkv2S3J7keW2/S5P8yrjnL2numTfuCUhSJ5YA91bVTwEk2Q+4ClhaVRuT/Cywsqp+KckbgIuT/Dmwf1W9Y3zTljRX+Y0NkjQNSZ7L4KvYVgMfBB4CPg58vm2yG7C+ql7atr8Q+GngB6pq3czPWNJc55k4SZqGqvpskmOBlwN/CFwN3FJVL568bZKnAd8HPAocABhxknY574mTpGlI8izga1X1XuCPgRcB85O8uK1/epKj2+a/DtwGnAq8K8nTxzFnSXObZ+IkaXq+H/ijJN8EHgfOADYD57X74+YBf5bkceCXgeOqalOSjwFvBt4ypnlLmqO8J06SJKlDXk6VJEnqkBEnSZLUISNOkiSpQ0acJElSh4w4SZKkDhlxkiRJHTLiJEmSOvT/AWlq25D6KrAAAAABSURBVJI2OY+AAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,7))\n",
    "plt.title('Sex vs Charges')\n",
    "sns.barplot(x='sex',y='charges',data=data_copy,palette='Set1')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Plotting Skew and Kurtosis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Printing Skewness and Kurtosis for all columns\n",
      "\n",
      "age : Skewness 0.056 and  Kurtosis -1.245\n",
      "sex : Skewness 0.021 and  Kurtosis -2.003\n",
      "bmi : Skewness 0.284 and  Kurtosis -0.051\n",
      "children : Skewness 0.938 and  Kurtosis 0.202\n",
      "smoker : Skewness 1.465 and  Kurtosis 0.146\n",
      "region : Skewness -0.038 and  Kurtosis -1.329\n",
      "charges : Skewness 1.516 and  Kurtosis 1.606\n"
     ]
    }
   ],
   "source": [
    "print('Printing Skewness and Kurtosis for all columns')\n",
    "print()\n",
    "for col in list(data_copy.columns):\n",
    "    print('{0} : Skewness {1:.3f} and  Kurtosis {2:.3f}'.format(col,data_copy[col].skew(),data_copy[col].kurt()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Count')"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,7))\n",
    "sns.distplot(data_copy['age'])\n",
    "plt.title('Plot for Age')\n",
    "plt.xlabel('Age')\n",
    "plt.ylabel('Count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Count')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,7))\n",
    "sns.distplot(data_copy['bmi'])\n",
    "plt.title('Plot for BMI')\n",
    "plt.xlabel('BMI')\n",
    "plt.ylabel('Count')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Count')"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,7))\n",
    "sns.distplot(data_copy['charges'])\n",
    "plt.title('Plot for charges')\n",
    "plt.xlabel('charges')\n",
    "plt.ylabel('Count')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### There might be few outliers in Charges but then we cannot say that the value is an outlier as there might be cases in which Charge for medical was very les actually!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Prepating data - We can scale BMI and Charges Column before proceeding with Prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1.438764</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.453320</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0.298584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-1.509965</td>\n",
       "      <td>0</td>\n",
       "      <td>0.509621</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>-0.953689</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.797954</td>\n",
       "      <td>0</td>\n",
       "      <td>0.383307</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>-0.728675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.441948</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.305531</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.719843</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.513149</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.292556</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.776802</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        age  sex       bmi  children  smoker  region   charges\n",
       "0 -1.438764    1 -0.453320         0       1       3  0.298584\n",
       "1 -1.509965    0  0.509621         1       0       2 -0.953689\n",
       "2 -0.797954    0  0.383307         3       0       2 -0.728675\n",
       "3 -0.441948    0 -1.305531         0       0       0  0.719843\n",
       "4 -0.513149    0 -0.292556         0       0       0 -0.776802"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "data_pre = data_copy.copy()\n",
    "\n",
    "tempBmi = data_pre.bmi\n",
    "tempBmi = tempBmi.values.reshape(-1,1)\n",
    "data_pre['bmi'] = StandardScaler().fit_transform(tempBmi)\n",
    "\n",
    "tempAge = data_pre.age\n",
    "tempAge = tempAge.values.reshape(-1,1)\n",
    "data_pre['age'] = StandardScaler().fit_transform(tempAge)\n",
    "\n",
    "tempCharges = data_pre.charges\n",
    "tempCharges = tempCharges.values.reshape(-1,1)\n",
    "data_pre['charges'] = StandardScaler().fit_transform(tempCharges)\n",
    "\n",
    "data_pre.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Size of X_train :  (1070, 6)\n",
      "Size of y_train :  (1070, 1)\n",
      "Size of X_test :  (268, 6)\n",
      "Size of Y_test :  (268, 1)\n"
     ]
    }
   ],
   "source": [
    "X = data_pre.drop('charges',axis=1).values\n",
    "y = data_pre['charges'].values.reshape(-1,1)\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2, random_state=42)\n",
    "\n",
    "print('Size of X_train : ', X_train.shape)\n",
    "print('Size of y_train : ', y_train.shape)\n",
    "print('Size of X_test : ', X_test.shape)\n",
    "print('Size of Y_test : ', y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.svm import SVR\n",
    "import xgboost as xgb\n",
    "\n",
    "from sklearn.metrics import r2_score, mean_squared_error, accuracy_score, confusion_matrix\n",
    "from sklearn.model_selection import cross_val_score, RandomizedSearchCV, GridSearchCV"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Linear Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wall time: 32 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "linear_reg = LinearRegression()\n",
    "linear_reg.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CV Linear Regression : 0.745\n",
      "R2_score (train) : 0.741\n",
      "R2_score (test) : 0.783\n",
      "RMSE : 0.480\n"
     ]
    }
   ],
   "source": [
    "cv_linear_reg = cross_val_score(estimator = linear_reg, X = X, y = y, cv = 10)\n",
    "\n",
    "y_pred_linear_reg_train = linear_reg.predict(X_train)\n",
    "r2_score_linear_reg_train = r2_score(y_train, y_pred_linear_reg_train)\n",
    "\n",
    "y_pred_linear_reg_test = linear_reg.predict(X_test)\n",
    "r2_score_linear_reg_test = r2_score(y_test, y_pred_linear_reg_test)\n",
    "\n",
    "rmse_linear = (np.sqrt(mean_squared_error(y_test, y_pred_linear_reg_test)))\n",
    "\n",
    "print('CV Linear Regression : {0:.3f}'.format(cv_linear_reg.mean()))\n",
    "print('R2_score (train) : {0:.3f}'.format(r2_score_linear_reg_train))\n",
    "print('R2_score (test) : {0:.3f}'.format(r2_score_linear_reg_test))\n",
    "print('RMSE : {0:.3f}'.format(rmse_linear))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Support Vector Machine (Regression)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_c = data_copy.drop('charges',axis=1).values\n",
    "y_c = data_copy['charges'].values.reshape(-1,1)\n",
    "\n",
    "X_train_c, X_test_c, y_train_c, y_test_c = train_test_split(X_c,y_c,test_size=0.2, random_state=42)\n",
    "\n",
    "X_train_scaled = StandardScaler().fit_transform(X_train_c)\n",
    "y_train_scaled = StandardScaler().fit_transform(y_train_c)\n",
    "X_test_scaled = StandardScaler().fit_transform(X_test_c)\n",
    "y_test_scaled = StandardScaler().fit_transform(y_test_c)\n",
    "\n",
    "svr = SVR()\n",
    "#svr.fit(X_train_scaled, y_train_scaled.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 10 folds for each of 60 candidates, totalling 600 fits\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n",
      "[Parallel(n_jobs=-1)]: Done   9 tasks      | elapsed:    7.2s\n",
      "[Parallel(n_jobs=-1)]: Done  82 tasks      | elapsed:    9.0s\n",
      "[Parallel(n_jobs=-1)]: Done 205 tasks      | elapsed:   11.7s\n",
      "[Parallel(n_jobs=-1)]: Done 376 tasks      | elapsed:   15.6s\n",
      "[Parallel(n_jobs=-1)]: Done 600 out of 600 | elapsed:   40.6s finished\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=10, error_score='raise-deprecating',\n",
       "             estimator=SVR(C=1.0, cache_size=200, coef0=0.0, degree=3,\n",
       "                           epsilon=0.1, gamma='auto_deprecated', kernel='rbf',\n",
       "                           max_iter=-1, shrinking=True, tol=0.001,\n",
       "                           verbose=False),\n",
       "             iid='warn', n_jobs=-1,\n",
       "             param_grid={'C': [0.001, 0.01, 0.1, 1, 10, 100],\n",
       "                         'gamma': [0.001, 0.01, 0.1, 1, 'scale'],\n",
       "                         'kernel': ['rbf', 'sigmoid'], 'tol': [0.0001]},\n",
       "             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n",
       "             scoring=None, verbose=4)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parameters =  { 'kernel' : ['rbf', 'sigmoid'],\n",
    "                 'gamma' : [0.001, 0.01, 0.1, 1, 'scale'],\n",
    "                 'tol' : [0.0001],\n",
    "                 'C': [0.001, 0.01, 0.1, 1, 10, 100] }\n",
    "svr_grid = GridSearchCV(estimator=svr, param_grid=parameters, cv=10, verbose=4, n_jobs=-1)\n",
    "svr_grid.fit(X_train_scaled, y_train_scaled.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVR(C=10, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma=0.1,\n",
      "    kernel='rbf', max_iter=-1, shrinking=True, tol=0.0001, verbose=False)\n",
      "0.8311303137187737\n"
     ]
    }
   ],
   "source": [
    "svr = SVR(C=10, gamma=0.1, tol=0.0001)\n",
    "svr.fit(X_train_scaled, y_train_scaled.ravel())\n",
    "print(svr_grid.best_estimator_)\n",
    "print(svr_grid.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CV : 0.831\n",
      "R2_score (train) : 0.857\n",
      "R2 score (test) : 0.871\n",
      "RMSE : 0.359\n"
     ]
    }
   ],
   "source": [
    "cv_svr = svr_grid.best_score_\n",
    "\n",
    "y_pred_svr_train = svr.predict(X_train_scaled)\n",
    "r2_score_svr_train = r2_score(y_train_scaled, y_pred_svr_train)\n",
    "\n",
    "y_pred_svr_test = svr.predict(X_test_scaled)\n",
    "r2_score_svr_test = r2_score(y_test_scaled, y_pred_svr_test)\n",
    "\n",
    "rmse_svr = (np.sqrt(mean_squared_error(y_test_scaled, y_pred_svr_test)))\n",
    "\n",
    "print('CV : {0:.3f}'.format(cv_svr.mean()))\n",
    "print('R2_score (train) : {0:.3f}'.format(r2_score_svr_train))\n",
    "print('R2 score (test) : {0:.3f}'.format(r2_score_svr_test))\n",
    "print('RMSE : {0:.3f}'.format(rmse_svr))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Ridge Regressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import PolynomialFeatures, StandardScaler\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.linear_model import Ridge\n",
    "\n",
    "steps = [ ('scalar', StandardScaler()),\n",
    "        ('poly', PolynomialFeatures(degree=2)),\n",
    "        ('model', Ridge())]\n",
    "\n",
    "ridge_pipe = Pipeline(steps)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\sahil\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\ridge.py:147: LinAlgWarning: Ill-conditioned matrix (rcond=2.25803e-19): result may not be accurate.\n",
      "  overwrite_a=True).T\n",
      "C:\\Users\\sahil\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\ridge.py:147: LinAlgWarning: Ill-conditioned matrix (rcond=2.14414e-19): result may not be accurate.\n",
      "  overwrite_a=True).T\n"
     ]
    }
   ],
   "source": [
    "parameters = { 'model__alpha': [1e-15, 1e-10, 1e-8, 1e-3, 1e-2,1,2,5,10,20,25,35, 43,55,100], 'model__random_state' : [42]}\n",
    "reg_ridge = GridSearchCV(ridge_pipe, parameters, cv=10)\n",
    "reg_ridge = reg_ridge.fit(X_train, y_train.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(Pipeline(memory=None,\n",
       "          steps=[('scalar',\n",
       "                  StandardScaler(copy=True, with_mean=True, with_std=True)),\n",
       "                 ('poly',\n",
       "                  PolynomialFeatures(degree=2, include_bias=True,\n",
       "                                     interaction_only=False, order='C')),\n",
       "                 ('model',\n",
       "                  Ridge(alpha=20, copy_X=True, fit_intercept=True, max_iter=None,\n",
       "                        normalize=False, random_state=42, solver='auto',\n",
       "                        tol=0.001))],\n",
       "          verbose=False),\n",
       " 0.8259990140429396)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reg_ridge.best_estimator_, reg_ridge.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CV : 0.826\n",
      "R2 score (train) : 0.741\n",
      "R2 score (test) : 0.784\n",
      "RMSE : 0.465\n"
     ]
    }
   ],
   "source": [
    "ridge = Ridge(alpha=20, random_state=42)\n",
    "ridge.fit(X_train_scaled, y_train_scaled.ravel())\n",
    "cv_ridge = reg_ridge.best_score_\n",
    "\n",
    "y_pred_ridge_train = ridge.predict(X_train_scaled)\n",
    "r2_score_ridge_train = r2_score(y_train_scaled, y_pred_ridge_train)\n",
    "\n",
    "y_pred_ridge_test = ridge.predict(X_test_scaled)\n",
    "r2_score_ridge_test = r2_score(y_test_scaled, y_pred_ridge_test)\n",
    "\n",
    "rmse_ridge = (np.sqrt(mean_squared_error(y_test_scaled, y_pred_linear_reg_test)))\n",
    "print('CV : {0:.3f}'.format(cv_ridge.mean()))\n",
    "print('R2 score (train) : {0:.3f}'.format(r2_score_ridge_train))\n",
    "print('R2 score (test) : {0:.3f}'.format(r2_score_ridge_test))\n",
    "print('RMSE : {0:.3f}'.format(rmse_ridge))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## RandomForest Regressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wall time: 9min 47s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "reg_rf = RandomForestRegressor()\n",
    "parameters = { 'n_estimators':[600,1000,1200],\n",
    "             'max_features': [\"auto\"],\n",
    "             'max_depth':[40,50,60],\n",
    "             'min_samples_split': [5,7,9],\n",
    "             'min_samples_leaf': [7,10,12],\n",
    "             'criterion': ['mse']}\n",
    "\n",
    "reg_rf_gscv = GridSearchCV(estimator=reg_rf, param_grid=parameters, cv=10, n_jobs=-1)\n",
    "reg_rf_gscv = reg_rf_gscv.fit(X_train_scaled, y_train_scaled.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(0.8483687880955955,\n",
       " RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=50,\n",
       "                       max_features='auto', max_leaf_nodes=None,\n",
       "                       min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                       min_samples_leaf=12, min_samples_split=7,\n",
       "                       min_weight_fraction_leaf=0.0, n_estimators=1200,\n",
       "                       n_jobs=None, oob_score=False, random_state=None,\n",
       "                       verbose=0, warm_start=False))"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reg_rf_gscv.best_score_, reg_rf_gscv.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=50,\n",
       "                      max_features='auto', max_leaf_nodes=None,\n",
       "                      min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                      min_samples_leaf=12, min_samples_split=7,\n",
       "                      min_weight_fraction_leaf=0.0, n_estimators=1200,\n",
       "                      n_jobs=None, oob_score=False, random_state=None,\n",
       "                      verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_reg = RandomForestRegressor(max_depth=50, min_samples_leaf=12, min_samples_split=7,\n",
    "                       n_estimators=1200)\n",
    "rf_reg.fit(X_train_scaled, y_train_scaled.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CV : 0.848\n",
      "R2 score (train) : 0.884\n",
      "R2 score (test) : 0.879\n",
      "RMSE : 0.348\n"
     ]
    }
   ],
   "source": [
    "cv_rf = reg_rf_gscv.best_score_\n",
    "\n",
    "y_pred_rf_train = rf_reg.predict(X_train_scaled)\n",
    "r2_score_rf_train = r2_score(y_train, y_pred_rf_train)\n",
    "\n",
    "y_pred_rf_test = rf_reg.predict(X_test_scaled)\n",
    "r2_score_rf_test = r2_score(y_test_scaled, y_pred_rf_test)\n",
    "\n",
    "rmse_rf = np.sqrt(mean_squared_error(y_test_scaled, y_pred_rf_test))\n",
    "\n",
    "print('CV : {0:.3f}'.format(cv_rf.mean()))\n",
    "print('R2 score (train) : {0:.3f}'.format(r2_score_rf_train))\n",
    "print('R2 score (test) : {0:.3f}'.format(r2_score_rf_test))\n",
    "print('RMSE : {0:.3f}'.format(rmse_rf))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "models = [('Linear Regression', rmse_linear, r2_score_linear_reg_train, r2_score_linear_reg_test, cv_linear_reg.mean()),\n",
    "          ('Ridge Regression', rmse_ridge, r2_score_ridge_train, r2_score_ridge_test, cv_ridge.mean()),\n",
    "          ('Support Vector Regression', rmse_svr, r2_score_svr_train, r2_score_svr_test, cv_svr.mean()),\n",
    "          ('Random Forest Regression', rmse_rf, r2_score_rf_train, r2_score_rf_test, cv_rf.mean())   \n",
    "         ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>Model</th>\n",
       "      <th>RMSE</th>\n",
       "      <th>R2_Score(training)</th>\n",
       "      <th>R2_Score(test)</th>\n",
       "      <th>Cross-Validation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Linear Regression</td>\n",
       "      <td>0.479808</td>\n",
       "      <td>0.741410</td>\n",
       "      <td>0.782694</td>\n",
       "      <td>0.744528</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Ridge Regression</td>\n",
       "      <td>0.465206</td>\n",
       "      <td>0.741150</td>\n",
       "      <td>0.783800</td>\n",
       "      <td>0.825999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Support Vector Regression</td>\n",
       "      <td>0.358771</td>\n",
       "      <td>0.857234</td>\n",
       "      <td>0.871283</td>\n",
       "      <td>0.831130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Random Forest Regression</td>\n",
       "      <td>0.347522</td>\n",
       "      <td>0.884422</td>\n",
       "      <td>0.879228</td>\n",
       "      <td>0.848369</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       Model      RMSE  R2_Score(training)  R2_Score(test)  \\\n",
       "0          Linear Regression  0.479808            0.741410        0.782694   \n",
       "1           Ridge Regression  0.465206            0.741150        0.783800   \n",
       "2  Support Vector Regression  0.358771            0.857234        0.871283   \n",
       "3   Random Forest Regression  0.347522            0.884422        0.879228   \n",
       "\n",
       "   Cross-Validation  \n",
       "0          0.744528  \n",
       "1          0.825999  \n",
       "2          0.831130  \n",
       "3          0.848369  "
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict = pd.DataFrame(data = models, columns=['Model', 'RMSE', 'R2_Score(training)', 'R2_Score(test)', 'Cross-Validation'])\n",
    "predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(12,7))\n",
    "predict.sort_values(by=['Cross-Validation'], ascending=False, inplace=True)\n",
    "\n",
    "sns.barplot(x='Cross-Validation', y='Model',data = predict, palette='Reds')\n",
    "plt.xlabel('Cross Validation Score')\n",
    "plt.ylabel('Model')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training Data without Scaling for RandomClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>bmi</th>\n",
       "      <th>children</th>\n",
       "      <th>smoker</th>\n",
       "      <th>region</th>\n",
       "      <th>charges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>19</td>\n",
       "      <td>1</td>\n",
       "      <td>27.900</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>16884.92400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>33.770</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1725.55230</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>0</td>\n",
       "      <td>33.000</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>4449.46200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33</td>\n",
       "      <td>0</td>\n",
       "      <td>22.705</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>21984.47061</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>28.880</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3866.85520</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex     bmi  children  smoker  region      charges\n",
       "0   19    1  27.900         0       1       3  16884.92400\n",
       "1   18    0  33.770         1       0       2   1725.55230\n",
       "2   28    0  33.000         3       0       2   4449.46200\n",
       "3   33    0  22.705         0       0       0  21984.47061\n",
       "4   32    0  28.880         0       0       0   3866.85520"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_copy.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Size of X_train_ :  (1070, 6)\n",
      "Size of y_train_ :  (1070, 1)\n",
      "Size of X_test_ :  (268, 6)\n",
      "Size of Y_test_ :  (268, 1)\n"
     ]
    }
   ],
   "source": [
    "X_ = data_copy.drop('charges',axis=1).values\n",
    "y_ = data_copy['charges'].values.reshape(-1,1)\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_train_, X_test_, y_train_, y_test_ = train_test_split(X_,y_,test_size=0.2, random_state=42)\n",
    "\n",
    "print('Size of X_train_ : ', X_train_.shape)\n",
    "print('Size of y_train_ : ', y_train_.shape)\n",
    "print('Size of X_test_ : ', X_test_.shape)\n",
    "print('Size of Y_test_ : ', y_test_.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=50,\n",
       "                      max_features='auto', max_leaf_nodes=None,\n",
       "                      min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                      min_samples_leaf=12, min_samples_split=7,\n",
       "                      min_weight_fraction_leaf=0.0, n_estimators=1200,\n",
       "                      n_jobs=None, oob_score=False, random_state=None,\n",
       "                      verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_reg = RandomForestRegressor(max_depth=50, min_samples_leaf=12, min_samples_split=7,\n",
    "                       n_estimators=1200)\n",
    "rf_reg.fit(X_train_, y_train_.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R2 score (train) : 0.885\n",
      "R2 score (test) : 0.878\n"
     ]
    }
   ],
   "source": [
    "y_pred_rf_train_ = rf_reg.predict(X_train_)\n",
    "r2_score_rf_train_ = r2_score(y_train_, y_pred_rf_train_)\n",
    "\n",
    "y_pred_rf_test_ = rf_reg.predict(X_test_)\n",
    "r2_score_rf_test_ = r2_score(y_test_, y_pred_rf_test_)\n",
    "\n",
    "print('R2 score (train) : {0:.3f}'.format(r2_score_rf_train_))\n",
    "print('R2 score (test) : {0:.3f}'.format(r2_score_rf_test_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "Pkl_Filename = \"rf_tuned.pkl\"  \n",
    "\n",
    "with open(Pkl_Filename, 'wb') as file:  \n",
    "    pickle.dump(rf_reg, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the Model back from file\n",
    "with open(Pkl_Filename, 'rb') as file:  \n",
    "    rf_tuned_loaded = pickle.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=50,\n",
       "                      max_features='auto', max_leaf_nodes=None,\n",
       "                      min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                      min_samples_leaf=12, min_samples_split=7,\n",
       "                      min_weight_fraction_leaf=0.0, n_estimators=1200,\n",
       "                      n_jobs=None, oob_score=False, random_state=None,\n",
       "                      verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf_tuned_loaded"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred=rf_tuned_loaded.predict(np.array([20,1,28,0,1,3]).reshape(1,6))[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "18999.110\n"
     ]
    }
   ],
   "source": [
    "print('{0:.3f}'.format(pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.11 64-bit (microsoft store)",
   "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": "3.10.11"
  },
  "vscode": {
   "interpreter": {
    "hash": "a948cc73775d2840a24a4d541dc2edebbd76a6732a9fe754de12225d66d842c9"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}