{
 "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",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.model_selection import StratifiedShuffleSplit"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Project Goals\n",
    "To create a model that predicts median house values in Californian districts, given a number of features from these districts"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Get the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>median_house_value</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-122.23</td>\n",
       "      <td>37.88</td>\n",
       "      <td>41.0</td>\n",
       "      <td>880.0</td>\n",
       "      <td>129.0</td>\n",
       "      <td>322.0</td>\n",
       "      <td>126.0</td>\n",
       "      <td>8.3252</td>\n",
       "      <td>452600.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-122.22</td>\n",
       "      <td>37.86</td>\n",
       "      <td>21.0</td>\n",
       "      <td>7099.0</td>\n",
       "      <td>1106.0</td>\n",
       "      <td>2401.0</td>\n",
       "      <td>1138.0</td>\n",
       "      <td>8.3014</td>\n",
       "      <td>358500.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-122.24</td>\n",
       "      <td>37.85</td>\n",
       "      <td>52.0</td>\n",
       "      <td>1467.0</td>\n",
       "      <td>190.0</td>\n",
       "      <td>496.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>7.2574</td>\n",
       "      <td>352100.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-122.25</td>\n",
       "      <td>37.85</td>\n",
       "      <td>52.0</td>\n",
       "      <td>1274.0</td>\n",
       "      <td>235.0</td>\n",
       "      <td>558.0</td>\n",
       "      <td>219.0</td>\n",
       "      <td>5.6431</td>\n",
       "      <td>341300.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-122.25</td>\n",
       "      <td>37.85</td>\n",
       "      <td>52.0</td>\n",
       "      <td>1627.0</td>\n",
       "      <td>280.0</td>\n",
       "      <td>565.0</td>\n",
       "      <td>259.0</td>\n",
       "      <td>3.8462</td>\n",
       "      <td>342200.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "0    -122.23     37.88                41.0        880.0           129.0   \n",
       "1    -122.22     37.86                21.0       7099.0          1106.0   \n",
       "2    -122.24     37.85                52.0       1467.0           190.0   \n",
       "3    -122.25     37.85                52.0       1274.0           235.0   \n",
       "4    -122.25     37.85                52.0       1627.0           280.0   \n",
       "\n",
       "   population  households  median_income  median_house_value ocean_proximity  \n",
       "0       322.0       126.0         8.3252            452600.0        NEAR BAY  \n",
       "1      2401.0      1138.0         8.3014            358500.0        NEAR BAY  \n",
       "2       496.0       177.0         7.2574            352100.0        NEAR BAY  \n",
       "3       558.0       219.0         5.6431            341300.0        NEAR BAY  \n",
       "4       565.0       259.0         3.8462            342200.0        NEAR BAY  "
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "file_name = 'data/raw/housing.csv'\n",
    "housing_df = pd.read_csv(file_name)\n",
    "housing_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 20640 entries, 0 to 20639\n",
      "Data columns (total 10 columns):\n",
      "longitude             20640 non-null float64\n",
      "latitude              20640 non-null float64\n",
      "housing_median_age    20640 non-null float64\n",
      "total_rooms           20640 non-null float64\n",
      "total_bedrooms        20433 non-null float64\n",
      "population            20640 non-null float64\n",
      "households            20640 non-null float64\n",
      "median_income         20640 non-null float64\n",
      "median_house_value    20640 non-null float64\n",
      "ocean_proximity       20640 non-null object\n",
      "dtypes: float64(9), object(1)\n",
      "memory usage: 1.6+ MB\n"
     ]
    }
   ],
   "source": [
    "housing_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1H OCEAN     9136\n",
       "INLAND        6551\n",
       "NEAR OCEAN    2658\n",
       "NEAR BAY      2290\n",
       "ISLAND           5\n",
       "Name: ocean_proximity, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df['ocean_proximity'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>median_house_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20433.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "      <td>20640.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>-119.569704</td>\n",
       "      <td>35.631861</td>\n",
       "      <td>28.639486</td>\n",
       "      <td>2635.763081</td>\n",
       "      <td>537.870553</td>\n",
       "      <td>1425.476744</td>\n",
       "      <td>499.539680</td>\n",
       "      <td>3.870671</td>\n",
       "      <td>206855.816909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.003532</td>\n",
       "      <td>2.135952</td>\n",
       "      <td>12.585558</td>\n",
       "      <td>2181.615252</td>\n",
       "      <td>421.385070</td>\n",
       "      <td>1132.462122</td>\n",
       "      <td>382.329753</td>\n",
       "      <td>1.899822</td>\n",
       "      <td>115395.615874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>-124.350000</td>\n",
       "      <td>32.540000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.499900</td>\n",
       "      <td>14999.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>-121.800000</td>\n",
       "      <td>33.930000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>1447.750000</td>\n",
       "      <td>296.000000</td>\n",
       "      <td>787.000000</td>\n",
       "      <td>280.000000</td>\n",
       "      <td>2.563400</td>\n",
       "      <td>119600.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>-118.490000</td>\n",
       "      <td>34.260000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>2127.000000</td>\n",
       "      <td>435.000000</td>\n",
       "      <td>1166.000000</td>\n",
       "      <td>409.000000</td>\n",
       "      <td>3.534800</td>\n",
       "      <td>179700.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>-118.010000</td>\n",
       "      <td>37.710000</td>\n",
       "      <td>37.000000</td>\n",
       "      <td>3148.000000</td>\n",
       "      <td>647.000000</td>\n",
       "      <td>1725.000000</td>\n",
       "      <td>605.000000</td>\n",
       "      <td>4.743250</td>\n",
       "      <td>264725.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>-114.310000</td>\n",
       "      <td>41.950000</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>39320.000000</td>\n",
       "      <td>6445.000000</td>\n",
       "      <td>35682.000000</td>\n",
       "      <td>6082.000000</td>\n",
       "      <td>15.000100</td>\n",
       "      <td>500001.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          longitude      latitude  housing_median_age   total_rooms  \\\n",
       "count  20640.000000  20640.000000        20640.000000  20640.000000   \n",
       "mean    -119.569704     35.631861           28.639486   2635.763081   \n",
       "std        2.003532      2.135952           12.585558   2181.615252   \n",
       "min     -124.350000     32.540000            1.000000      2.000000   \n",
       "25%     -121.800000     33.930000           18.000000   1447.750000   \n",
       "50%     -118.490000     34.260000           29.000000   2127.000000   \n",
       "75%     -118.010000     37.710000           37.000000   3148.000000   \n",
       "max     -114.310000     41.950000           52.000000  39320.000000   \n",
       "\n",
       "       total_bedrooms    population    households  median_income  \\\n",
       "count    20433.000000  20640.000000  20640.000000   20640.000000   \n",
       "mean       537.870553   1425.476744    499.539680       3.870671   \n",
       "std        421.385070   1132.462122    382.329753       1.899822   \n",
       "min          1.000000      3.000000      1.000000       0.499900   \n",
       "25%        296.000000    787.000000    280.000000       2.563400   \n",
       "50%        435.000000   1166.000000    409.000000       3.534800   \n",
       "75%        647.000000   1725.000000    605.000000       4.743250   \n",
       "max       6445.000000  35682.000000   6082.000000      15.000100   \n",
       "\n",
       "       median_house_value  \n",
       "count        20640.000000  \n",
       "mean        206855.816909  \n",
       "std         115395.615874  \n",
       "min          14999.000000  \n",
       "25%         119600.000000  \n",
       "50%         179700.000000  \n",
       "75%         264725.000000  \n",
       "max         500001.000000  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x1080 with 9 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing_df.hist(bins=50, figsize=(20,15));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Split the data\n",
    "Here we create training and test splits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_set, test_set = train_test_split(housing_df, test_size=0.2, random_state=8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>median_house_value</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17875</th>\n",
       "      <td>-121.99</td>\n",
       "      <td>37.40</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1845.0</td>\n",
       "      <td>325.0</td>\n",
       "      <td>1343.0</td>\n",
       "      <td>317.0</td>\n",
       "      <td>5.3912</td>\n",
       "      <td>235300.0</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9360</th>\n",
       "      <td>-122.53</td>\n",
       "      <td>37.95</td>\n",
       "      <td>22.0</td>\n",
       "      <td>7446.0</td>\n",
       "      <td>1979.0</td>\n",
       "      <td>2980.0</td>\n",
       "      <td>1888.0</td>\n",
       "      <td>3.5838</td>\n",
       "      <td>271300.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4338</th>\n",
       "      <td>-118.31</td>\n",
       "      <td>34.08</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1609.0</td>\n",
       "      <td>534.0</td>\n",
       "      <td>1868.0</td>\n",
       "      <td>497.0</td>\n",
       "      <td>2.7038</td>\n",
       "      <td>227100.0</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>986</th>\n",
       "      <td>-121.85</td>\n",
       "      <td>37.72</td>\n",
       "      <td>43.0</td>\n",
       "      <td>228.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>42.0</td>\n",
       "      <td>10.3203</td>\n",
       "      <td>400000.0</td>\n",
       "      <td>INLAND</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8129</th>\n",
       "      <td>-118.17</td>\n",
       "      <td>33.80</td>\n",
       "      <td>26.0</td>\n",
       "      <td>1589.0</td>\n",
       "      <td>380.0</td>\n",
       "      <td>883.0</td>\n",
       "      <td>366.0</td>\n",
       "      <td>3.5313</td>\n",
       "      <td>187500.0</td>\n",
       "      <td>NEAR OCEAN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "17875    -121.99     37.40                35.0       1845.0           325.0   \n",
       "9360     -122.53     37.95                22.0       7446.0          1979.0   \n",
       "4338     -118.31     34.08                26.0       1609.0           534.0   \n",
       "986      -121.85     37.72                43.0        228.0            40.0   \n",
       "8129     -118.17     33.80                26.0       1589.0           380.0   \n",
       "\n",
       "       population  households  median_income  median_house_value  \\\n",
       "17875      1343.0       317.0         5.3912            235300.0   \n",
       "9360       2980.0      1888.0         3.5838            271300.0   \n",
       "4338       1868.0       497.0         2.7038            227100.0   \n",
       "986          83.0        42.0        10.3203            400000.0   \n",
       "8129        883.0       366.0         3.5313            187500.0   \n",
       "\n",
       "      ocean_proximity  \n",
       "17875       <1H OCEAN  \n",
       "9360         NEAR BAY  \n",
       "4338        <1H OCEAN  \n",
       "986            INLAND  \n",
       "8129       NEAR OCEAN  "
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_set.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>median_house_value</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>15722</th>\n",
       "      <td>-122.46</td>\n",
       "      <td>37.78</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1682.0</td>\n",
       "      <td>379.0</td>\n",
       "      <td>837.0</td>\n",
       "      <td>375.0</td>\n",
       "      <td>5.2806</td>\n",
       "      <td>400000.0</td>\n",
       "      <td>NEAR BAY</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19685</th>\n",
       "      <td>-121.61</td>\n",
       "      <td>39.14</td>\n",
       "      <td>44.0</td>\n",
       "      <td>2035.0</td>\n",
       "      <td>476.0</td>\n",
       "      <td>1030.0</td>\n",
       "      <td>453.0</td>\n",
       "      <td>1.4661</td>\n",
       "      <td>65200.0</td>\n",
       "      <td>INLAND</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6989</th>\n",
       "      <td>-118.04</td>\n",
       "      <td>33.97</td>\n",
       "      <td>29.0</td>\n",
       "      <td>2376.0</td>\n",
       "      <td>700.0</td>\n",
       "      <td>1968.0</td>\n",
       "      <td>680.0</td>\n",
       "      <td>2.6082</td>\n",
       "      <td>162500.0</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5804</th>\n",
       "      <td>-118.25</td>\n",
       "      <td>34.15</td>\n",
       "      <td>13.0</td>\n",
       "      <td>1107.0</td>\n",
       "      <td>479.0</td>\n",
       "      <td>616.0</td>\n",
       "      <td>443.0</td>\n",
       "      <td>0.8185</td>\n",
       "      <td>187500.0</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5806</th>\n",
       "      <td>-118.26</td>\n",
       "      <td>34.14</td>\n",
       "      <td>29.0</td>\n",
       "      <td>3431.0</td>\n",
       "      <td>1222.0</td>\n",
       "      <td>4094.0</td>\n",
       "      <td>1205.0</td>\n",
       "      <td>2.2614</td>\n",
       "      <td>248100.0</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "15722    -122.46     37.78                47.0       1682.0           379.0   \n",
       "19685    -121.61     39.14                44.0       2035.0           476.0   \n",
       "6989     -118.04     33.97                29.0       2376.0           700.0   \n",
       "5804     -118.25     34.15                13.0       1107.0           479.0   \n",
       "5806     -118.26     34.14                29.0       3431.0          1222.0   \n",
       "\n",
       "       population  households  median_income  median_house_value  \\\n",
       "15722       837.0       375.0         5.2806            400000.0   \n",
       "19685      1030.0       453.0         1.4661             65200.0   \n",
       "6989       1968.0       680.0         2.6082            162500.0   \n",
       "5804        616.0       443.0         0.8185            187500.0   \n",
       "5806       4094.0      1205.0         2.2614            248100.0   \n",
       "\n",
       "      ocean_proximity  \n",
       "15722        NEAR BAY  \n",
       "19685          INLAND  \n",
       "6989        <1H OCEAN  \n",
       "5804        <1H OCEAN  \n",
       "5806        <1H OCEAN  "
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## reduce the number of categories "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAD6CAYAAACmjCyGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvqOYd8AAAE4JJREFUeJzt3X+MHHd5x/H32WdBgBJ6qc8/oJRUj1OaWlUjmupAtWycVFUCNKeqkG1jiaTuJRBiBYKKSN2W4v4SP0QdR3Fa+9LQokihTptLAkeipGC1UmhU2go1RGnypBGFXOQNGDAkKg729o8dw/q4y86Z9c1dv++XdLLn2e/sPuO7+8z4uzOzQ51OB0lSOVY03YAkaXEZ/JJUGINfkgpj8EtSYZZ08E9PT++enp7e3XQfkvT/yXDTDfTxCyMjI5uBa5tuRJKWmaH5HljSR/ySpMEz+CWpMAa/JBXG4Jekwhj8klQYg1+SCmPwS1JhDH5JKozBL0mFMfglqTBL/ZYNy9bxq+e9Wvq0WrHXD9aR9MI84pekwhj8klQYg1+SCmPwS1JhDH5JKozBL0mFMfglqTAGvyQVpu8FXBFxOXB5T+ks4M3AR4HVwCFgIjOPRMRGYA/dHcqDwM7M7ETEpcA1QAe4MTMPDHIjJEn19T3iz8yPZ+aWzNwCbAX+G7gOmKxqk8CuavgNwLaq3gEuiYi1wHbggupre0SsGfB2SJJqWuhUz1uAaWBDZt4HkJn3A+dExNnAo5k5U43dDYwDFwH7M/NoZj4P3FLVJEkNWOi9ei4HLqM71dPrGLAGOBH6ZOYzEXFWVX+sZ+wMsKnuC7bbbcbHx0+qtVotWq3WghqXJHXVDv6IOB94JDOfi4iVsx5eSXeuf13P+NXA4dl1YH1Vq2V0dJSpqam6wyVJfSxkqmcHcFP19yci4kKAiNgKZGY+CZxbzemfGH8XcC8wERGrImIYuKKqSZIaUOuIPyJeDRzrmb//A2BfROwE2sBVVf1a4LaIWAE8BNxZndVzK/BANWZvZj49sC2QJC3IUKezdO/fPj09fXBkZGTz2NhY060smPfjl9SweUPIC7gkqTAGvyQVxuCXpMIY/JJUGINfkgpj8EtSYQx+SSqMwS9JhTH4JakwBr8kFcbgl6TCGPySVBiDX5IKY/BLUmEMfkkqjMEvSYUx+CWpMAa/JBXG4Jekwhj8klSY4YUMjohtwN10P8R3ElgNHAImMvNIRGwE9tDdoTwI7MzMTkRcClwDdIAbM/PAALdBPZr6kHfwg96l5aL2EX9EvBN4KjOPALuAyczcQncHsKsadgOwrap3gEsiYi2wHbig+toeEWsGtgWSpAWpFfwRsQO4Drg+Il4PbMjM+wAy837gnIg4G3g0M2eq1XYD48BFwP7MPJqZzwO3VDVJUgP6TvVUQb8WOIfu1M4B4OisYceANcCJ0Cczn4mIs6r6Yz1jZ4BNdRtst9uMj4+fVGu1WrRarbpPIUnqUWeO/63AnszsAO2IOAicP2vMSrpz/etOFCJiNXB4dh1YX9VqGR0dZWpqqu5wSVIfdaZ62sBbACLixcAbgEMRcWFV2wpkZj4JnFvN6QPsAO4C7gUmImJVRAwDV1Q1SVID6hzx7wH2R8Rb6e4oPgT8M7AvInbS3TFcVY29FrgtIlYADwF3Vmf13Ao8UI3Zm5lPD3IjJEn1DXU6S/cUvOnp6YMjIyObx8bGmm5lwZo8rbIpns4pLSnzhpAXcElSYQx+SSqMwS9JhTH4JakwBr8kFcbgl6TCGPySVBiDX5IKY/BLUmEMfkkqjMEvSYUx+CWpMAa/JBXG4Jekwhj8klQYg1+SCmPwS1JhDH5JKozBL0mFMfglqTDDdQZFxKeAl1WLNwP3ApPAauAQMJGZRyJiI7CH7g7lQWBnZnYi4lLgGqAD3JiZBwa7GZKkuuoe8X8rM7dUX58EdgGTmbmF7g5gVzXuBmBbVe8Al0TEWmA7cEH1tT0i1gxwGyRJC1A3+Mci4nMR8amI+BlgQ2beB5CZ9wPnRMTZwKOZOVOtsxsYBy4C9mfm0cx8HrilqkmSGlBrqgfYmplfrsJ9H/C/sx4/BqwBToQ+mflMRJxV1R/rGTsDbKrbYLvdZnx8/KRaq9Wi1WrVfQpJUo9awZ+ZX67+fDIivskP5vtPWEl3rn/diUJErAYOz64D66taLaOjo0xNTdUdLknqo+9UT0S8NyLOqf6+GlgLZERcWNW2ApmZTwLnVnP6ADuAu+i+ETwREasiYhi4oqpJkhpQ54j/TuCmiDijGv8+4BFgX0TsBNrAVdXYa4HbImIF8BBwZ3VWz63AA9WYvZn59CA3QpJU31Cn02m6h3lNT08fHBkZ2Tw2NtZ0Kwt2/OqhpltYdCv2Lt2fJalA84aQF3BJUmEMfkkqjMEvSYUx+CWpMAa/JBXG4Jekwhj8klQYg1+SCmPwS1JhDH5JKozBL0mFMfglqTAGvyQVxuCXpMIY/JJUGINfkgpj8EtSYQx+SSqMwS9JhTH4JakwwwsZHBEHgE8C9wOTwGrgEDCRmUciYiOwh+4O5UFgZ2Z2IuJS4BqgA9yYmQcGuA2SpAWofcQfEZuBV1WLu4DJzNxCdwewq6rfAGyr6h3gkohYC2wHLqi+tkfEmoF0L0lasFpH/BGxgm54T1alDZl5H0Bm3h8R74mIs4FHM3OmGrMb+Ajw48D+zDxaPdctwEXAx+u8drvdZnx8/KRaq9Wi1WrVWV2SNEvdqZ4JukH96mr52KzHjwFrgBOhT2Y+ExFnVfXHesbOAJvqNjg6OsrU1FTd4ZKkPvpO9UTEK4DXZeZne8orZw1bSXeuf13PequBw7PrwPqqJklqQJ05/iuB8yLiIPB+4IPAqoi4ECAitgKZmU8C51Zz+gA7gLuAe4GJiFgVEcPAFVVNktSAvlM9mflh4MMAEXE58B3gAWBfROwE2sBV1fBrgduq9wQeAu6szuq5tVoHYG9mPj3QrZAk1TbU6XSa7mFe09PTB0dGRjaPjY013cqCHb96qOkWFt2KvUv3Z0kq0Lwh5AVcklQYg1+SCmPwS1JhDH5JKozBL0mFMfglqTAGvyQVxuCXpMIY/JJUGINfkgpj8EtSYQx+SSqMwS9JhTH4JakwBr8kFcbgl6TCGPySVBiDX5IKY/BLUmEMfkkqzHC/ARHxQWBrtfj7wOeBm4ANwLPAlZn5VES8EtgPvAT4L2BHZh6NiM3AnwAd4I7M3DP4zZAk1fWCR/wR8VLgqczcBFwMvA94F/CFzNxSLf9FNfwG4H1V/QvA1RHxIuCPgTcBm4HzI+K807AdkqSaXvCIPzOfBfZViz8LfIfu0f949fiXIuLFETEMrMrMh6uxfw1MAV8E7snMIwARsQe4BPiPug22223Gx8dPqrVaLVqtVt2nkCT16DvVAxAR7wTeT/cIf1tmHut5+BDwE0D7RCEzj0UEwBpgpmfsDLB2IQ2Ojo4yNTW1kFXUkONXDzXyuiv2dhp5XWm5qvXmbmbeDPw08JvAcET0rjcKfK36E4Cexw8B63rGrq9qkqSG9JvjvywifrlaPA6sBA4Cv109/lrgaGZ+D/heRJxbjb0c+BzdN4J/LSJeVtWvAe4e5AZIkham31TPvcDNEfGndEP/E8DHgZsi4jK6Z/W8oxr7buCvIuIM4HG6Z/V8NyI+AHw6IjrAVGb+22nYDklSTf3e3P068LY5HvqdOcZ+he6ZP7Prn6N79C9JWgK8gEuSCmPwS1JhDH5JKozBL0mFMfglqTAGvyQVxuCXpMIY/JJUGINfkgpj8EtSYQx+SSqMwS9JhTH4JakwBr8kFcbgl6TC1PrM3eWqqc+AlaSlzCN+SSqMwS9JhTH4Jakwteb4I+LPgddX4z8G/CMwCawGDgETmXkkIjYCe+juUB4EdmZmJyIuBa4BOsCNmXlg4FsiSaql7xF/RLwJGM7MLcBW4L3AnwGTVW0S2FUNvwHYVtU7wCURsRbYDlxQfW2PiDWD3QxJUl11pno+A1wPkJlHgW8AZ2fmfVXtfuCciDgbeDQzZ6r1dgPjwEXA/sw8mpnPA7dUNUlSA/pO9WTmceB4RJwJfBi4GXjHrGHHgDXATM96z0TEWVX9sZ6xM8Cmug22223Gx8dPqrVaLVqtVt2nkCT1qDvHvwm4GvjDzHw8It41a8hKunP963rWWQ0cnl0H1le1WkZHR5mamqo7XJLUR505/rXABN25+8er8hMRcWH1+FYgM/NJ4NxqPMAO4C7gXmAiIlZFxDBwRVWTJDWgzhH/LwJjwD9GBHSP1q8C9kXETqBdLQNcC9wWESuAh4A7q7N6bgUeqMbszcynB7gNkqQFGOp0Ok33MK/p6emDIyMjm8fGxk5pfW/ZUIYVe5fuz7DUoHkD0Au4JKkwBr8kFcbgl6TCGPySVBiDX5IKY/BLUmEMfkkqjMEvSYUx+CWpMAa/JBXG4Jekwhj8klQYg1+SCmPwS1JhDH5JKozBL0mFMfglqTAGvyQVxuCXpMIY/JJUmOE6gyJiBfB24KHMfCQizgQmgdXAIWAiM49ExEZgD90dyoPAzszsRMSlwDVAB7gxMw+chm2RJNXQN/gj4gzgDuA54NvAI8AuYDIz74uIX6mW3w3cAGzLzJmI+FPgkoj4F2A7cAHd4L8nIv4pMw+dli1ScY5fPdTYa6/Y22nstaVTVWeq5xhwGfDpntqGzLwPIDPvB86JiLOBRzNzphqzGxgHLgL2Z+bRzHweuKWqSZIa0PeIPzOPAkcjord8bNawY8AaYKZnvWci4qyq/ljP2BlgU90G2+024+PjJ9VarRatVqvuU0iSetSa45/DyjmWDwHrThQiYjVweHYdWF/VahkdHWVqauoU25QkzXaqZ/U8EREXAkTEViAz80ng3IhYW43ZAdwF3AtMRMSqiBgGrqhqkqQG1D2r5w7gp4DvRcQbgD8A9kXETqANXFUNvRa4rToL6CHgzuqsnluBB6oxezPz6UFuhCSpvlrBn5m/MUf5bXOM+0+6Z+/Mrt8O3L7g7iRJA+cFXJJUGINfkgpj8EtSYQx+SSqMwS9JhTH4JakwBr8kFcbgl6TCGPySVBiDX5IKY/BLUmFO9bbMkmju07/85C/9KDzil6TCGPySVBiDX5IKY/BLUmEMfkkqjMEvSYVZlqdz3n777bRarabb6Ov2r/4YrVd9u+k2+rLPwVqMPgdxGump9NnEaaTL5vd9mfQJy/SI//bbl8fH9/7dV1/edAu12Odg2edgLZff9+XSJyziEX9EvBv49Wrx9zPznxbrtSUNRiMXrP3PKzl+9ZAXrQ3QogR/RJwHnA9sBn4MuDsifjUzv7sYry9p+WvqKunaqh3UIJ2und1Qp3P696IR8UHgU5n5r9Xy7wL/mpkHX2i96enprw4PD7/y5S8/+b+kDz/8MBs3buz7up3HX/DpT7svHXkRP/fypb9vs8/Bss/BKrnPoQ1bTnndw4cP33DxxRe/e67HFmuqZw0w07M8A6ytsd4zzz777EufeOKJk/pctWrVs4cPH36079pn/fyCmhy0Fw8dXveNkZGnG22iBvscLPscrKL7PHx4oE93wmIF/yFgHfBUtbwe+EK/lS6++OLzTmdTklSixTqr527gWoCIeBlwMfD5RXptSVKPRZnjB4iI9wDjQAf4o37z+5Kk02PRgl+StDQsywu4JEmnzuCXpMIY/JJUGINfkgpj8EtSYQx+SSrMsrof/3K6w2dE/Dnwerr/xh/LzH9ouKV5RcQB4JOZeUfTvbyQiNgG3J2ZR5ruZS4R8WfAG4CVwM6l9vMZESuAtwMPZeYjEXEmMAmspnt1/cRS+Ledo89XAX8JvBR4jm6fMy/0HIthdp899bXAv2fm+saa62PZHPHPusPnm4FdEfGiZruaW0S8CRjOzC3AVuC9EbEkd7IRsRl4VdN99BMR7wSeWgrBNJeI+DngzOp7fhHwe812dLKIOAO4h+5V8+dW5V3AZNXzZLXcqHn6/AjdHekb6fb4gYba+755+jzh/cBXF72pBVg2wU/3qt/dmdmpfvk/TfeIein6DHA9QGYeBb7RbDtzq45YttP9pV+yImIHcB1wfUQs1e/514CfrI6iN7D0vufHgMvo/t6csCEz7wPIzPuBc5pobJa5+nx7Zn6x+vvXge8telc/bK4+iYjzga8A7SaaqmtJHoXO41Tv8LnoMvM4cLwKgQ8DN2fmUvhhnW0C+Djw6ob7mFcV9GvphtJq4EBEXJSZzzXb2Q/5FnAm8FngJ4APNdvOyaoDkKMR0Vs+NmvY7OVFN1efVY2I+CXgfcCVzXT3A3P1GRFDwA7gd4A3NtRaLcvpiP/EHT5PWF/VlqSI2ER3XvKjmfnpfuMXW0S8AnhdZn626V76eCuwv/qfXhs4CLy22ZbmdB3d7/XrgNcAb4iI1zTaUX8r+ywvGRHxR8CbgN/KzNNzr+If3WXA35/YUS1lyyn4l80dPqs3dyaAbZn5eNP9zONK4LyIOEh3TvKDETF7rnIpaANvAYiIF9N98/SJRjua20v5we/TEPCSBnup64mIuBAgIrYC2XA/c6re3/lSZn5gqYZqRKwC3gG8p/qden1E/G2zXc1vWd2kbbnc4TMi3gx8jB9MTR3KzEsbbOkFRcTlwHeW4lk9EfESYD/wk3SD9UOZeU+zXf2wiPhx4K+BEeBFwCcy86ZmuzpZRNwB/BTdOfLP032jdB/dKbQ2cFVmfrO5Drvm6PPVwChwvBryN5l5a0Ptfd/sPjPzup7HPpWZb26suT6WVfBLkn50y2mqR5I0AAa/JBXG4Jekwhj8klQYg1+SCmPwS1JhDH5JKsz/AWwHoio+0VJIAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing_df[\"median_income\"].hist();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create income category\n",
    "# Divide by 1.5 to limit the number of income categories\n",
    "housing_df[\"income_cat\"] = np.ceil(housing_df[\"median_income\"] / 1.5)\n",
    "# Label those above 5 as 5\n",
    "housing_df[\"income_cat\"].where(housing_df[\"income_cat\"] < 5, 5.0, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot histogram for new category \n",
    "housing_df[\"income_cat\"].hist();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.0    7236\n",
       "2.0    6581\n",
       "4.0    3639\n",
       "5.0    2362\n",
       "1.0     822\n",
       "Name: income_cat, dtype: int64"
      ]
     },
     "execution_count": 175,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df[\"income_cat\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From the above histogram we see the data is not evenly split. We stratify in order to properly represent population with splits. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stratify data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Size of training set: \t 16512\n",
      "Size of test set: \t 4128\n"
     ]
    }
   ],
   "source": [
    "# split data again but this time with strata\n",
    "split = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=42)\n",
    "for train_index, test_index in split.split(housing_df, housing_df[\"income_cat\"]):\n",
    "    print('Size of training set: \\t {}'.format(len(train_index)))\n",
    "    print('Size of test set: \\t {}'.format(len(test_index)))\n",
    "    strat_train_set = housing_df.loc[train_index]\n",
    "    strat_test_set = housing_df.loc[test_index]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4128, 11)"
      ]
     },
     "execution_count": 188,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strat_test_set.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 11)"
      ]
     },
     "execution_count": 189,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strat_train_set.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 190,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.0    0.350533\n",
       "2.0    0.318798\n",
       "4.0    0.176357\n",
       "5.0    0.114583\n",
       "1.0    0.039729\n",
       "Name: income_cat, dtype: float64"
      ]
     },
     "execution_count": 190,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# strata ratios \n",
    "strat_test_set[\"income_cat\"].value_counts() / len(strat_test_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.0    0.350581\n",
       "2.0    0.318847\n",
       "4.0    0.176308\n",
       "5.0    0.114438\n",
       "1.0    0.039826\n",
       "Name: income_cat, dtype: float64"
      ]
     },
     "execution_count": 191,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# compared to original population \n",
    "housing_df[\"income_cat\"].value_counts() / len(housing_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 192,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now we can drop the income cat column \n",
    "for df in [strat_train_set, strat_test_set]:\n",
    "    df.drop(\"income_cat\", axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 10)"
      ]
     },
     "execution_count": 193,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strat_train_set.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4128, 10)"
      ]
     },
     "execution_count": 194,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strat_test_set.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save strata to pickles "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the strata sets\n",
    "strat_train_set.to_pickle('data/interim/'+'strat_train_set'+'.pkl')\n",
    "strat_test_set.to_pickle('data/interim/'+'strat_test_set'+'.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 196,
   "metadata": {},
   "outputs": [],
   "source": [
    "# read pickles to dataframes\n",
    "strat_train_set = pd.read_pickle('data/interim/'+'strat_train_set'+'.pkl')\n",
    "strat_test_set = pd.read_pickle('data/interim/'+'strat_test_set'+'.pkl')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Explore data (gain insights)\n",
    "So far we have a general understanding of the data. Let's go a little deeper. First we'll make a copy of the data so we don't alter the training set. Note: we are not working with the full data set from here on. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 199,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing_df = strat_train_set.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 200,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 10)"
      ]
     },
     "execution_count": 200,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 201,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing_df.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", alpha=0.1);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Looks like California!**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 202,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmcAAAG2CAYAAAA6OCEGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvqOYd8AAAIABJREFUeJzs3Xl8VPW9+P/XObPPZJnsJGQDTgg7yK4oiBFUsJW2aLGbtXW5rVVre+ut1/bX3237/d5re3t722urV9u6tFasijsuuCAqIMoOAvGwhISE7JNkksls53z/+AQhISQzZEgCfJ6PRx4wZ858zmcmk8w7n/fn8/4opmkiSZIkSZIkDQ/qUHdAkiRJkiRJOk4GZ5IkSZIkScOIDM4kSZIkSZKGERmcSZIkSZIkDSMyOJMkSZIkSRpGZHAmSZIkSZI0jFiHugOSJEmSJEmnomnay0BS180HgNeAPwFZQC1ws67rrZqmTQJ+jxh4Wg/cq+u6qWnal4HvASbwP7quP61pmgL8O3AhEAHu0HV9t6Zpqb21PVjP9Rg5ciZJkiRJ0nDWouv6pV1fTwE/B/6k6/qliEDq513n/Q74WtdxE7hG07QRwLeBsq6vb2ualgMsA0xd1xcAXwP+u6uNU7U9qJRzoQjt6tWr/xtgyZIl3x/qvkiSJEnSuabrc3ZaApvcFutntqZp+4HDQDvwQ+C3uq4vOeH+1cBtwD/run5b17Es4NfAu4Bf1/Wnu45fC3iAhV3n13cd/0PX+X/s2faJtwfLuZLWnJaenr4AuHOoOyJJkiRJg0QZxGtNUwxjgTUcjvuBzX4/Pr//s9tZOTm0d3TkArEOqFym63qFpmmjgIeAzh73R4EcoPrYAV3X6zVNy+g6Xn7CudXAJUD6scDshOMjutrq2fagO1eCM0mSJEmSzqBofT2db70V9+NsiAlcn90uKyM9J6cm1sfrul7R9e9BTdN8HJ9/dowFMT8s99iBrpGzpp7HgbyuY02apmXqut7Q47ill7YHnQzOJEmSJEnql8PrJW/+/AG30+j1Euv4m6ZpPwRe0nW9vCvgGgFs0zTtcl3X39Q07TJA7wrcJmiaNkLX9aPA7cALwAbgUU3TXkDMQ7sRMQetFTFy95OuOWilXW3s79n2gJ/waZDBmSRJkiRJ/Qr5fFStWzfgdixlZSg5ObGe/hzwB03TXIiY5W7gE+AhTdPuBeqAW7vOvRN4QtM0FfgQeK5rteYjwJtd5/xR1/UaTdNWAXM0TXsHkbo8lmL96SnaHlQyOJMkSZIkKSaDnePTdf0AcFUvd13Xy7k7ESsyex5fCazsccxEBHo9z/X11vZgk8GZJEmSJEn9cni9ZCcgrVnn9RJKQH/OZTI4kyRJkuISjUbZvHkzjY2NnAvlmIYrRVHIyMhgxowZWCxDMi+9m5DPR3UC0ppGWRnEntY8L8ngTJIkSYqLrutYLBYWL148LIKGc1U0GmXr1q3ouk5paelQdweFxKQ1za4v6dRkcCZJkiTFpbKykosuukgGZmeYxWJh/PjxbNy4cVgEZ3avl9wEpDVrvF6CCejPuUwGZ5IkSVJcQqEQTqdzqLtxXnC5XASDwyOUCfl8HE1AWjMk05r9ksGZJEmSFDdVlVszD4bh9DorJGZDbgWZ1uyPDM4kSZIkSepXotKaR7zek/ZfkrqTwZkkSZI0aEwjCg0HMet1CAfA5kLJ0iBzFIoq57ANZ2Gfj7oEpDXDMq3ZryEPzjRNexp4CtgIPIjYLb4DuFnX9eq+HitJkiSdHUzTxDy8Gfa+BZ0tYLWDagMjjKm/B64UzNIy1KKZQ93VXi1evJg33nhjqLsx5GT4PDiGNDjTNG0BkN9189fAvbqub9c0bQ7wM4Zo2wRJkiQpscw9a2Df25A6AsVTfPL9oQ7Y8jRGexPqhMWD30GpX3avl5wEpDWDXi+BBPTnXDZkwVnX3lffBv7UdegGXdePFQ1uBCJD0jGpV36/gWGYpKTIv5skSYqPUfGxCMwyik6ZulTsbsyMYtj3FoYnA7VoxuB2coDq6+u57777+M///E8A7rzzTn73u98Nca8SK+zz0SDTmoNiKEfObgYeBQoBjgVmmqbNRux3dUs8jdXV1bFs2bJux1asWMGKFSsS0ddu2tvB6YTzpcTPJ58EefLJNgwDrrnGw+zZrqHukiRJZwnTiMK+t8SIWT9zyhTVgpmaC/vexCyYdlbNQQsGgzQ2Nn52+1wLzCBxRWiVBLRxrhuS4EzTNC8wQ9f1/9U07ZsnHP//Ed+3r5wwihaT7Oxsnn/++UR28ySGAc88A9u3Q3Y23HgjpKSc0UsOC++8EyA11YLdDm++2SGDM0mSYtdwEAKtKBlFMZ2u2N2YbfXicdlazJepqqri9ttvJycnh7q6OnJzc7nvvvvYsGED999/P4qiMGPGDO69915UVeXSSy9l+vTpVFRUkJyczH333UdOTk63uWU//elPWbp0KXPnzv3sOrW1tfz4xz/G7/dTWFjIpk2beO+99/jtb3/Ltm3beOSRR7jxxhs/a6e2tpZ77rkHn8+Hx+PhF7/4BcXFxdx9991EIhFqamoIhUI8+OCDZGVlxffaDjKb10tWAtKafq+XcAL6cy4bqpGzW4ALNE1bC4wAopqm5QC7dV1/eoj61K+aGti2DYqK4PBh2LEDLr64/8dFo7CvGhQFSvMg0WVrOjtNTBNcrjPz98jIkRY2bgyiKCbjx9tjekxdnUFtbZS0NJX8/Pj/1iov70DXO0lJsTBjRhIu19nzF7QkSceZ9TpYbfE9yGrDbNiPEkdwBlBRUcGDDz5ITk4ODz30EL/5zW9Yv349//jHP0hNTeVnP/sZq1atYvny5dTU1HDLLbcwbtw4XnnlFX71q1/xm9/8pt9r/Md//AcrVqzgiiuuYO/evbz88ssA3HXXXTQ1NXHjjTd2O/++++7juuuu48orr2Tr1q3ce++9PPHEEwCMGzeO//qv/+L+++/nlVde4Zvf/GZcz3ewRXw+mhKQ1ozItGa/hiQ403X9V8CvALpGzvzACiBb07Tbuk57TNf1R4aifwDBEJRXiv+XFoLdBm43dIZg8y5oaYH2GMf23t4Fa3aI/189A+ZPSFw/N22K8tJLhmj7apU5cxIfxCxZkkR2tpVIxGTmzP6rgpeXh3n8cVHFJhqFZcsczJkTW1AHsHWrn5UrG/B4VDo7DbZv7+Dmm3Ow24dPMUZJkmIUDohVmfFQbRCKf8p4aWkpOV0f+ldccQW/+MUvmDRpEqmpqZ8dW7NmDcuXLycnJ4dx48YBYiXmH//4x5PaMwzjpGN79+7l17/+NSCCq+zs7D77tHfvXn71q18BcMEFF9DQ0PDZfTNnipWpxcXF7N+/P96nOyTkn8mDY8hLaei6/mjXf58Zyn6cKBKBx1aDfgQUE0oK4caloNdARzLUNkFaDryzB2wpcFk/K7+rGiHNA1EDjjT2fW48OjpMXnwxSm6uGDF78cUokyeruN2JHUGz2xUuuij2VOYbb4TxehVSUlRCIZPVq0PMmmVDVWPr11tvtTBihA2PR/waOHQoyOHDQTRNplMl6axjc4ERZxLLCIM9/p/3ffv2UVdXR3Z2Nm+//TYFBQVs3LiRtrY2kpOTefvtt5k4cSIg5imXl5czduxY1q5d+1mg5nA4qKurIy0tjR07dvC5z32u2zVKS0t56623uOKKKygvL6eurg4ARVEwzZPr3o8bN461a9dy+eWXs2vXrm6pS0U5u2Zf2bxe0hOQ1mz2eolr3tJ5aMiDs+GooQXWb4OGo+J2fSNM1+D/PgzV9eBKhsI8KMiBNz+GSaMhO/3U7V02GR5/F1QFLhnAqFlLS5RXXmmntdVg8WIPI0Yc//Ypivjq5XfDoDOM4504vd89ZrdfWrE8L9M0OXgwSCBgUFBgJyVFvrUlaThQsjRRxywekTBK5pi4rzVy5Eh+8pOf0NjYSE5ODvfddx+bNm36LF04depUvvjFLwKQmZnJAw88QFVVFW63m/vuuw+AW2+9lRtuuIHs7GySkpJOusaPf/xj7r77bh5++GGKioo+GznLyMigrq7uszlnx9xzzz3867/+Kw8++CAej4df/vKXcT+v4SLi89Ei05qDQn6C9SLQAZ8egNwMERRs22Xy7bdM9vhAtUBykoLfr5CVKlYvHK7tOzgryoJ7xe+DAc03e+45PwcOhElKUnn88VZ+9KM0rrrKwquvRgG46ioLHk9i/hJraYMmH+RkgrvrD1i/36Cz08TrVbFaT32dRYvs/O1vQZqboxgGXH21I+ZRM4D581NZtaqBpCQrgYBBTo6NwkJHn4957bVm1q1rRVEUPB6VW28dQWZmnKmUs9S77wb44IMgl13mZO5cuRm1NMxkjhIFZkMdKHZ3v6eboQ5wpYjHxXupzEweeuihbsfKysooKys76Vy3281vf/vbk45fffXVXH311ScdP7ZIYMSIETz++OMn3e90Olm9evVJ52dlZfHwww+fdP6xVOexa54N5GrNwSODs17YLDAxD2oDYoVm5U6T1loIFYlNX4NtJm3lMHOiQnqqmI/Wn0QsAmhoiJKWZsHtVvD5IgQCJvPmWZg6VTSelJSYt/zRenjoKQiFIC0VFs2O8uhjnezd08m4UpWiIpUbbkjC6+39x3T8eBu33aZSV2fg9aoUF8f34zx7djJJSSrl5Z0kJ1uYOzcZh+PUL2BHR5T332+jsNCBxaJQVRVk82Y/V1yRFtd1z0aRiMnrr3eSmamyenVABmfSsKOoFszSMtjyNGZGcZ/lMUwjCi01MP26s6qMxvnC6vXiTUBas87rTUBvzm0yOOtFThZcUAoVVVBdbeKvBUtYRPtGSKTZDBvs2AVXLIQxIwenX2Vlbp55xg/AlCl20tNPPyg7fDhKeXmU5GSFCy6wYrcfb2NXuZh3V5gHW7ZG+NuDAQ7uD6BaFOobVDweg1deCfDVr5485H9MXp6FvLzT/+U6YYKHCRM8MZ3bM6VrmudPDTqrVWHaNBtbt4a48EIZmEnDk1o0E6O9Cfa9hZma2+sImhnqEIFZadlpFaDNz8/nkUdiX0Mmt2KKX9Tnoy0Bac2oTGv2SwZnvbDZ4MbrYZ8OGz+EF1eaWJ0KoVaIugEFUrwQCcGKMvAM0jz1Cy5wUlhoIxg0GTHCEleq8ET790f585+D2GxidGzPnijf+Mbx1GNWulit2tAM+3YFaGkBu10sDDhUYbD/gBVdjzJ3LoyJf1pIwrlcFhYt8vL6682oqkJqqoWZM5OHuluD5tprPVx9tRu3W65mlYYvdcJiDE+6CNDa6kV5ja69NYmERSpz+nVn3c4A55vz5O/eISeDs1NwOmHqJBiRpXD/76CmxsTRpBCMQvoIuKgYLp8GpcWD26+MjIH/aGzYECE5GTIyxIf5p58aNDSYZGeL4GxyKXwxBIeqoHaciRFQ2b5NIRIFi2Kwb2+E8eOdPPYY3HUXpPWRPTRNk23bIlRWGkyaZGX06DPzo71gQSpjx7oIBAxGjLDhdg/fXyGhkIGuB2loiJCVZWXMGMeAyoQoipLwFbqSdCaoRTMxCy6AhoOi/lm4E+wuMfk/c5RMZQ5zVq+XlASkNa0yrdkvGZz1IycHfv97ld/93qSlxSQlCWbPVtE0hauuGurenR6HA8JdK9uPray0nvBOUFWYM1V8ZTrtREKdtEfs1FQGSXEbFBc7mTvXRU0N+P19B2c7d0ZZuTJMUhJ8+GGU2293MmLEmRnhyc2NvZbaUGloiPCXvzTg80WxWhUiEZOMDAs33phJerr8cZTOHoZhoJ7GZFpFtUC2FneB2fNVb7XWhkrU58Mv05qDQn4axGDhpQozpit0dkJGxtDNZ2ppMVFVSE4e2CjJggU2ysujHD5sEI3C/PnWz+av9XTppQ5e+9jCyLDJ2JkuRuRYcPst1NTAqFGQm9v3taqrDVwuyMlRqagwaGoyGTFiQN0/a5mmydNPNxMOmxQXH199WlsbZtUqHzfdlDmEvZOk2KWmpnLgwAFGjx59WgGaFBvDMDhw4MBnRXSHmlytOXhkcBajlJSh3Udzy5Yozz4bRVUVvvENlZKS0/8Ryc5WueMO12eBU0HBqX+5hsIKjiQbSxeJ25W18K3rwW4Rf/hY+3kHTZpkZf36CIcPG6SkKOTnn7+/yOvrI1RVhSgq6l4WJDvbysGDQZqaInL0TDorTJ8+nS1btlBeXj7UXTnnpaamMn369KHuBgAWr5ekBKQ1LTKt2S/5SXAGGAbs2QNNTWJ0KT9/4G1u3GiQlqYQDMKWLSYlJQNrLzlZobS0/wDP6YDiXNhfJWq8ZadBQV7/Qdkx+fkqd9zhpLHRZORINWHlPs5G4bDZa1FeRVFQFAiFhkEFYUmKgcvlYt68eUPdDWmQRX0+AjKtOShkcHYGvPEGvP22mNtlGHDzzVBcPLA2J01SefVVA0UxKS0dvNEnRYGvLoHNn0DUFCVGYg3MjsnMVMk8RzN2pmny+uu1fPBBI9OmeVm2LA+LpfcANCtLlCwJBo1uddsCAQOnUyUzU/44SpI0fMm05uCRnwYJZpqwfr0YMbNYoLYWtm0beHB2ySUqo0YpWCwKeXkDe2uHQrB1OzQ3w+hRMLafUTiXEy4eHqPqw05TU4h16xrJz3fy8cfNzJqVRmFh71XQ7XaVK69M5dlnm8nIsJKcbKG1NUpzc5Qvfzmtz10XJEmShpoMzgaPDM4STFEgNRXa2sDrhUBA3B54uwoFBQN/SxsGrHwa9uwV5ULWroPlX4SZZ1Hw1dIS5pVXarjkkkwKCvrfDuZMcruteDwWqqoC2GwqSUl9/0jNnu0hNdXC2rVtHD0aJi/Pxhe/6KWkRBaQlSRpeFO9XlwJmHOmyjln/ZLB2RmwYgX89a9w+DCUlMCFFw51j46rr4d95TCqGD7ZFWLPngg11VYe+ZMt7qK2fj9s3gzBIEybBl37/55x9fVBNm/2UVDgHvLgzOWycPPNxRw40E5BgZv09P7LeZSWOiktlcGYJElnF9PnI5SAOWemnHPWLxmcnQEjR8KPfiSCFpeLXieBD7WODpN9+yIkJytUHg5TV2dlxIjYOxoMwp//DHX1YLXAhg1w223g9ZqUl4dQVYWxY22YpkJ7EFx2sCXo3aZpSdx991gyM/veDH2wZGc7yc4emmCro8PAalW6bb8lSZJ0ppxiSq2UYDI4O0MsFnAP7aBOr7KyYOIE2LoNoobCkWqTmTMUUlLi+4mrqRGjcEWF4nZFhUiVPv1sgL37oowrCTJ9ros6q4fWDrBb4dpLYHxhYp5HTo4ceXrrLT/vvNOB3a7w9a+nMmrU8C/CK0nS2Uv1erHLtOagkMHZADU1mdjtp7f5+FBQVbjuSzBhnMJllzqxWgxmzYx/+x+7Xcxfi0ZFIBqNiiK5H22GlBQbBvDEWrj8cijMhkBQ3P7BFyD9/Nn2sl+trWK3hoyM+B7X0hLl7bc7yM+34vcbvPhiG3feGWcjkiRJcTBbfEQ/SEBa89IyyJZpzb7I4GwAtmyJ8OyzEex2+Kd/spOTc3YUWLVaYdpUmDb19Nfe5OXB/Pnw3nuAAuPGw6ULFJ5ZBQcrInQEQzg9STQehXYX5I8ETKhvOR6ctbebrF8fweczmTBBZeLE8+vtuGsXrFwpgtyFC2HRotgfa7EoqKqojRYMmqSmyj0JJUk6sxQFLAn4mBuOU32Gm/Pr0zDB9u0zcDrFxPiaGrPX+Y2mafLRRz6am0NcfHEGHs/JL3lzs4nDwVm3efWVV8LMmWLULCtLjMo9+AcnO3cGOdro4c777Gz7EGwumDUdRo8Hd9c0sXDY5NFHQ1RXm3g88PHHBitWwAUXDO1bsr3dYN26IIYBl1ziICXlzAXcb70F6eliXuK778KCBWJEMhZJSSrLl6fwyit+UlMtLFsmhyMlSTqzlFQv1osHntZUUmVasz8yOBuAefOsHDoUorBQYcyY3j/EKysDrFp1FNM0iUZhyZLuEdzatRHWrIngcMC3vmVP+PZGx657pmpoZWbCxkPw93WQnQSfm6Qya5aLe/4P+A+DoYJ1BGz4CJaWQX5XMdq6OpPqapOiIvF87XaTTZsMLrjgjHQzZi+8EGD37giqCjU1UW66KemMXSsnB3bsEAFZWlr8xX2nTnUydaqceydJ0iBp8WGuH3hak0vKIEumNfsig7MBKCxUueeevj8c3W4LDodCZ6eJ12s76f7334+Qm6vQ0GCyc2c0ocFZXZ3BX/8aprnZZO5cC0uXWlESPJ58oBGe3wU5ybCvHsI74JuzobFJbP3ksEOyE5Ky4JKJx4ezbTZRsNcwTFRVIRg0yc4e+pHD2lqDjAxR7Leuzjij1/r858V+rZ2dIkUs94+WJGlYU8Qc40S0I/VNBmdnWGamg+99bxR+f5TiYtdJ90+caGHTpiiKAqNHJ/bTefXqCB0dJvn5Ch98EGXiRAujRiX2p6K1E1QFPHawqlDTKo7f8BXYvguamw06AmFG2sFptQHiOWZlKVx4oYX166OoqonTCYsWDf3b8corHaxcGcAwTL70pZO/X4nkdsOSJWf0EpIkSQmjpHhRL0pAWjNFpjX7M/SfhueBrCwHWVm93/f5z1uZMsWCywV5eYkNzsJhsNmUz0arjDMwEFToBZcNDjVB1IDFpeL4vBnw+/sM/vnuVuqORqjdA/96j4X770/F41FRFIWrr7YyebKFzk6T3FyV1NSh/3Nq/Hg799xjwzTB5Rr6/kiSJA0brT7YmIC05oVlkCnTmn2RwdkQs1gUxow5M0HAlVdaeeyxEIcPw6RJFoqLE3+ddA98d55IbyY7oLRrl4APPgiyalU7yVaDjNHibVZXF2XTpiALF4oRKUVRzkifBsrpHH59kiRJGnIKx5IfA29H6pMMzgaorhUqG8W8qpIRw2uJcEGByo9+5Phsf8/TmW9mmtDeAUmeU5+T4RFf3Y5liNppEydaOHBAHCspUWlrM+PugyRJkjQMpHjhwoGnNUmWac3+yOBsAKqb4cG3IRKFqAmXT4RFk+JvJxw22bMnQiRiMmGCLaEjNw6HgmMAuxyteQ/e/gCWL4WZU2J/3Lhxdr7yFXj0UT+XXCL+1KqpMRg7dnDfcs0+WPkC1NTB3Olw5cLETLxvbjawWiE5Wc7ilyTpPNHmg00JSGvOLoN0mdbsiwzOBmBbhfigL04X863W7YOyCf1/+Hd2Gqxe3cbBgyEmT3bS0GBl+/ZI16KACDfd5Ip7E/IzpbUNQmHxb7zGj7ezfLmHtWs7URS47joP48YN7hZDL62B2gbIzYZ3N8CoQhhfMrA2Dx2K8qc/iW2Tvvc9N+npMkCTJOk8IX/dDQoZnA2A2yECF4BACNy22EZl3nnHz0cfdTBihJU1a9poanIxe7YdRVE4fNjA7zfj3uvyTPnc5WLELD/39B4/a5aDWbOGboNyXwukJInl36oKgUDsj62uDrF6dSspKSpLl6bi8Yg15E1NUQIBk3AYWltN0tPPUOclSZKGkxQvzElAWtMj05r9kcFZnCIRaGiAiAn6XqjUod0PGWnwtXmxtVFbG8HrteByqbjdKoYBhw8bKApkZKh4PMMjMANwOKC4YKh7cfouvQgeWQmf6mLbEcvnYn/s3/7WRCQCBw5E8XhUli4Vv1AmT7ZxzTXgdPJZEV1JkqRzXpsPNicgrTmjDNJkWrMvMjiLQ2cn/OUvcOQI7D4AIyeA1wmRRvjB9ZAUY1msmTNdPPGEj9bWKBaLwne/6+HQIVHJf84cGxaLQns7HKmBkbng6WMyvtS3KROgKBMirTAiG55fBeNLY9smKRIxsdlULBaFSOT4cZtNYf78wU3PSpIkDQtyG99BIYOzOOg6VFbCqFHw0SfwwUeQPU6sZnz6PfhGWWzVkydNcvGd71hobIwycqSN7GwrY8Ycvz8SgYcfh9o6yMmG229JUFXm85QCFOWLIPfIEfH6xhKcfeUr6bzwQgtjxthZuHBw9648tnOCJEnSsJHihVkJSGu6ZFqzPzI4i4PdLgq5RiIiWKqsgOYQXHQhlFdBdRMUnKLYbE+FhXYKC3u/LxSC+gbISBf/hkJic+xjqqpM3nknyvLllnO6UKphmLz6qp89e4JcdVUSEyee3j6SS66CJ/4OPh+UXS4q88eiuNjBnXdmn9Y1B2LVqjq2bGllxYocJk2SG5pLkjRMtPlgRwLSmlPKwCvTmn2RE2bioGmwYAFUVMCGTdBUC9Xb4Y1XYd1hqG6FRt/x8w0Dyith/5H4ruN2wzVLRDB4zdLugRmIwNBuT3xNtU8PwuYdIn07HNTWRnj/fTGD//nn/X2eGw6b7NtnUFFx8jYIJSXw43+BH/8YFl56JnqaOIZhsm1bG+GwwZ49HUPdHUmSpOOOFaEd6Ne5O6aQMHLkLA6qKvZCPFRpEOgECyoRoOkAHNgC/+mGsW5YcjHMmwab9sJz74nHfn0xTBoV+7VmzxBfvcnNVfjylxP7rfv0IPzpSTCBGZPhy3FMnD9TUlMtpKaqNDZGmTKl91Ez0zTZtSvEQw8ZtLYqZGerLF9uYc6c7nlg5+kNug06VVVYsSKHTz5p59JL04a6O5IkSccleWFGAtKadpnW7I8MzuK0cWOQV17uxOy0EY04wGMBLzQehQMVEDZh714o/TdobhMBXdSAlvbYr1FdDU8+KUawvvAFmDDhzD2fY/ztYjeA1BSob0xMm1VV4rWYPRtSUuJ/vNutctttaTQ2RsnPt/V6zpo1nfz85wHKy62kpsK4cTY++kg5KTg7m0yYkMSECUlD3Q1JkqTu/D7YnYC05sQySJVpzb7ItGYcAgGTV17p5KK5KoW5JqQakGVApgjA9m6F+hZIssFLr8HFk2HqGJgzHqbHUfj0+echGBQT2J96SmxgHg/DgE1b4OXXoCHGQGu8JuqZeVNg2RXxXW/XQfifVfDMu9AZOn782edg1fOwfkN87Z0oOdlCcbEdq7X3cfAnnwxRWalitSo0NyscPhzF40nsFlENDbBlKzQ1JbRZSZKks4tMaw4aOXIWo0jExDBMTFPU/po922D/ZgUMoBmYAvhgbD6MShejUMluWHFZ/NcyTTHipqri//HaWw7PvAAuB+z9FH6N2zkGAAAgAElEQVT4vf7npzmdcN1ppDJ9flj5NqQlw+ZySHHD4lnivtmzIByC8ePibzdWVpsFwwiTlRWlsQnGj7cyY0bvT/ZABaz7EHKyoGxebCs2QyF4+BFoaYH0dPjhnXLlrCRJ56kkL0xPQFrTKtOa/ZHBWQx27w7w1FMtNDdbeegvLkIBG6gK5CmQq0IBmBlgUaDKD5OL4eo4R59OtGwZPPGEWF147bVgjfO7FOia0J+SAm1d6coTgzNfK7y+DuoaYeJYWDD79AOOUBgMEzxOaO0QOyUcc+Fc8ZUIpyot8f07XWzbatDUbDB+nIWLLrJQUnLyC9baBo8+A24n7N0vXtNFl/R/3WgUOjogOQna28VtGZxJknRe8vtgXwLSmqVlkCLTmn2RwVkM3n23HV+Llfvvd4PVBjZFzJxvUyAZbMlgC8CsC2DmNLhsCmTHWFKjNyNHwt13i9Tm43+F1a/CTd+GjIyTz21rA78fck/YXmnSeNh/EKpqYMUXum8p1doGP/glNLfCtPHwxjoRvJVdJIKQPXtEIDd+/MmrRHuT5YV5k2D9bkhPhotPY+P3voTDJs8+G2XnTpNRoxS+8hULbvfxIG3iRAuvvZbM7t0GaWkmJSWWXjeO7wiIwCotVZRCaWyO7fouF3zly7BtO8yaGdtomyRJ0jnpWFozEe1IfZLBWQxKSpz8f/8WAidQoIIbOGJCCAjBtEJoj8DofGj2i0G1RPD7Yf8BMefs6NGTg7NgEP7wgEi5ff2rxxcOOBxw3Rd6b/OVtbDvIGSmw4594HDBY8/D3Gnwlz+LxQgA+flw880nByOGAW++CYcOwZVXQmEhLJ0LZdPBbu0eCL67TgR7iy6nW5HdeOzZY7J1q8Ho0QoHDhh8+KHCwoXdh64yMhTmz+97OCs7EyaXiufscsDFs2Lvw/hxZzY1K0mSdFZI8sK0BKQ1VZnW7I8Mzvrh94Mv4MHhDEOyAvlABzBOhT0qHjeMHwl762HfUUi2gRnqr9XYZGTA8i9BayuMHXvy/YYh5kRFIsc3YO+Pooj0nL9dBF42J6SlwSd7RQA4qqvcR0WFuN2zUG5lJbzzDiQlwXPPwZ13iuNOO3z4MaxZa9JYHyGomLz3gZXMTIWtnyj87+9O7zWIREwUBRRFwWKh2zZK8VBVMafu8kvA7RJfkiRJUhz8PtATkNbUyiBZpjX7IoOzPuzaDf/4B2zZBcnJVmx2g7Biih20XQrkQMkMsCtwwxwIG2LO1aaDMLUoMX2YeYpaZyBSbt+5VYycjR4dW3tj8sHjgvpmMTpdmAdfvxbyc0V6MxIR/5pm72nN5GSxeKCtTRR3PaaiEv7+rMG7azrQD4SJ2EySXTYU00VlipUdOuRnQ3qcJTUmTFAZPdpE328QDCl4M09/TF1VxYihJEmSdBoUErO3pkxr9ksGZ3147jkxelWiKdQ3ePjc2DBr2xTaFRVHB4yeDpNLINUjRqRcNvB3grOPV9Uw4A0dPqqG0WnwxQnicacrK0t8xWPBTMjNEasXr74cyromxl95JaxZIwKzpUt7bzc9Hb77XVFW4lhA2N4BjzwNL74RoeITAzMcAhuE1SgRFMJuD//zskJ2CiyZLeaoxcrpVLjpJgt//YeFXftg1asKI3Mhb0R8z1mSJEkaoCQvTElAWhOZ1uyPDM760hXdF42EbR6VnAwH39bgqfVihCkrB/7rO7D5MKzdIwbU7DYom3jqJg80w9pDUJAKu+ogNxkui3HUKxFKRkFqMtQ1QFYGTD2hwO38+TBnjgg0+5r43jMg3LAVduui6OxnpT9cFgxVwe+L0haB9mSIWuCZD2DaGDF6FytVVXB7QLWcHX9wHaqHl7fChRrMGMTvrSRJ0hnV7oODCUhrjioDj0xr9kUGZ3340hdg5T/EKr+vXweuDHjmLVBaTCJ+6HTD7r0Kk0ZBsgpeL4xMh9Q+NtYOd239aLOATYVgHHOoDhwIY7MpFBTE9m2LRkVdthMLuHpT4fZvQX0TZKRBkqf7YxyO2PtzzMEqg5feCxPJAbCCTwUMMFUibgeBVoUX3oWsVMjyQFNHfMEZwNIyMVqWmdZ91Mzvh6eegaO1sORKuGBq/P1PtA91+LRGpLhPNzjrwGADAWbgxJuQPIIkSVICyF9Hg0IGZ30YPx5mLoYNe8BZJFZH+o6aVOwxwQ4tR+Hffg2zLlRQVZgxEUbMgfc/gbQUmFBycvHXMWlQmgl6E6S7YG5BbH05eDDMQw+1YbUq3HlnCllZff+EtLebPPRQhM5OuPlmMTH/GLcbivoIIOP159c6CfpD0GQBqxPGpoNqgB/osNCighqCulqwFkPPeNTfAb428ZqdKmhzu2FeLyssN24SK1pzsuG5F2B86dDvo3nJOOgMw6wBjJq1Y7KNEGOwy+BMkqThweOFSQlIa0ZlWrM/MjjrwTDgYFVXSQgrbCiHJDc8+z6U5sHWDYAdMCCowAcbwJUFC+fApp2wpxw6gyLtee0SsSXSiexWuGEa+EPgtoE1xs9du13BZlOwWnsvStvaGuXw4TBZWRZycmw0NZlUVBioKtTVmd2Cs57Pd+06aGqGxWW974EZNcWeoc5e5uJXNcHBYFfdt7AC6Qq4FfBbIA1ogKhuMuIChfYOSHaC94TgqaIGHn1ZvF52G9z4OcjPEf2qqoVwBEZmg/MUI3p2uzi3s1O8LmoiavAMUF4a3NDj95dhxNe3LCzcgRfbWZHIlSTpvNDhg8oEpDULysAt05p9kcFZD6+9B+s2i7lNEyeIvSJ37oeWDnBbxfZELU1gpABBsComtY2wfpvC1LHQGRBz1OoaoeLIycEZiA/plDhHd0aOtHLnnSlYreD1do/oOjoMHnywEZ8visWicOut6ezeDU1NYbxelcLCU684OFwJr78pnq/LCUuv6n7/oSA80QAdBkx1wxfT4cRtLnc3QKTEiRqxYuxFRKzGCQ0EAR/4w6A6wBWE1BNGx154F9wOSM2AplZ4+X24eRk89Qbs1EXNuPQUuOkLYq5cT3NmiZ0Uauvg8suGX5HYhkZ4+Q349KBIyS5dDGNjrPkmAzNJkoYVuVpz0MjgrIft+0TJh3AU6o5C6Uj4aA+MyRPzhwILFSJvQHVAzOdSLQaRdpOROVa+s0Lh2VfhUNfI25Q+Cpd2dp66XMWpZGb2/lNRVxehtdXA41E5ciTEoUNh1q9XmDPHQlWVSVOTSVJS722mpoDHDYEAjOixAtIwRWDmUiHDClvaYawTpp0wT+1QJ1g8CrZkG8HxBuwC2gAHUAd0ArkGEVNFiSg4wuK1dXSNIgWCokYagMMmbu+vgp2fQnGeSAtX1cH722BpL9stORzw+atPPu73i7mCqamnfj3j9dHH8N57sGABzJje//mRCDy2Ejo6oSBP1JZ7/Cm4/SaRhpUkSTqruL0wIQFpzbBXZFukU5LBWQ9TxsL7W0TgtPhimD4RaurFSsyaJrhmGdyyzOSG28K0qwoOh8nRIwpLL4ySnWHlW9dCZQ2kJImq9L3Ztw/+/ndxjRUrjlf2P13Z2VZcLoXVq1sxTZO77rIyb57Cu+9GyM9Xyc4+dT4tLQ2+/z2xdVPP4CxsihGzDKsYwbIq4De6n6OokNMEzQcAUwGHCe1AjQGtUYhGUSsMVNVGxkQ7qckKDa0wsmu3gwXT4bm1It0bjsC1l4u0sKoen6/ndkCLP/bXY98++NsTIpW45CqYNy/2x/blpZfA4xH/xhKcVVVDkw+KuuYVpiSL7bN27RXBWUeHyaFDop/5+eD1yj8nJUkaxjp8UJ2AtGZeGbhkWrMvMjjr4ar5UDpKBAej8kWAcOvV8HE5JLngoonQ2QFuI4QSUgm1qwSDBuU7HdgMMaqiFfd9jbffFhX2FQXeemvgwZnbrXL77ZkUFFhJSlLRNDslJQoXXWTD7QaLpe8P/ZSU3ueaOVSY7oZN7WI7UasiRs5OlBGAZh3y8uForUIooohowzSBKCgmRruCvyrCiHyVsaNs3Vazzp0MmV6obYLcDLEFVlML2GzQ4BPz0Jrbeh81O5V33xUblXs8om5booKzmTNhw0aYd1Fs5ysKnw3fNzYYtLdDe4dCY4PCww8bfPyxQUaG0nWuyaJFKpdeKgLpHTuguRnmzj29FbSSJEkJJ9Oag0YGZz2oKmg9qvvnZcLnTxgFc9pVioqibNliwWIxsKrw0UcqVVVi0/Jx/ezDWFgoAghFgQtj/KDvqbPT5JNPwmialZQUlZQUC9/4RvfNN5OTT+8noK4VOkKQnwbXpIPmhDZDBGbZPaavOYJQkCJqpl2QA68fhZBFxGdYLWI4TFEwwyauSJRrZthI6pHK1QrE1zHpqXDTMnjzQzGKdtksUew3Vvn5sH+/mIs2Rjutl6BXn/8cLF4U+2rQ/DzIzoA3Xo+w/t0okShkZSvUHrZQVQk2m0pSEpSWihToa6+Z5OebJCcrPPmk2FPVak1ccClJkjQgbi+MT0BaM+jtPjdZOokMzk7T177mIRAI4XYbuFxOTFPF4eh9BKqnxYtFCtE0YUovCwZiUV4e5g9/8LNihZtFi04dLfh8YWprg5SUeFBj2JF9VxU8uUlMBxibA9+4EKZ6Tn3+mHyxmrKxCTqC4HSLOWrNBhAFIia4QIlGafZZeeBvkHErjOunzER+Dnzz8/12t1eLFkF6BoSCMKOP7a/iYZomPl+UaBTsdktMr6XFAt/4MvzXvxt0dooVt74G2LDewOk0yMxUOXJEpbRUwWpVcLpMnnrWYNk1FlJTxRZZPTe7lyRJGjIdPjiUgLRmdhk4ZVqzLzI4O03XXGOjutpKezukpSksWQLZ2eKrPzbbwIMGTbNyww1uJk3qe3niiy8e5aOPfPzwh2MoLu6/uNmmQ2JFapobPq0DXwDS+wjOxhfDj2+A59+FneUw+hLoaFbZYTWoOBTBNAxwqqhuC5GISbIHtu/tPzgbCJsN5s5JXHuGYfL8861s3hwATEaNsvPVr6bhcvVfGyPJIxZdOB0iWKupiWKaFmw2qKoyyciIAlYMA7bvU+gIQFsIViyDwpFiuyxJkqRhQaY1B40Mzk5TRgb84AcKzc3i/2eq8GlDg0kgYFJQ0D0QcLtV5s/v/6Jz56aRmmolJye2iUtF6bDvqNgjNNUFSTE8bOZ4mKrB7x8XKyvJgINHrCQFFAL2IElGJ2GLg2QLRDtNRuacXT+ZO3YE+PDDdkaNsqOqCgcPhli71s9VV/U/TGqzwc03W3jggQjBoEF2NsybZ7Bli0J6uoGiGEQiVoIhsaXWrOlinl1jM0ybPAhPTpIkKVYuL5QmIK3ZIdOa/ZHB2QC43eIrFp2dYmJ3zx0D+hIKmTzwQIRAwOS222yMHBl/UDN2bBJjx56ijkYvFpRCkhNaAzC9SKyi7I9pwspVoO+BjTsgZEDhaFGPrbXOTqdPwWKq5KRbaK9XSEvg7gSJ8v4m+PsqyM2Em74KubnieDQKn+hRrDb1s1RmWpqFI0fCMbd9220WFixQ+fTTKO+/H0LToLEFPj0MDZ0qrW9ANAhpKSYWm4rNBhNLz8SzlCRJGoCAD44kIK2ZXgaO+NOamqY9DTwFrAH+BGQBtcDNuq63apo2Cfg9oALrgXt1XTc1Tfsy8D3EjJ3/0XX9aU3TFODfgQsRG9fcoev6bk3TUntre2BPOH4yOOuHacKnn4p/x46NL7gCseXTk0+KNvLy4Otfj21eGog0WFaWGJ3z9JFaPJFhmLz//mEmT84mLS3ODSwRc/jnxJly7OyEveVwwSSIGPDBZhiVJ77sNiuHqyw4wlBYpHCoGrbvgYnj4+7aGVNbBz+9D6wq7NoHzfVw063w0X6obYV9+6zs322Sk2PidCg0N0fJz3fQ3GySltb/G0JVYcoUhcmTLVitVt5cG6UuoGJzmTS2WQnWw4zxUFKictu3FDzuU3+/OzsN6uoieL0WUlLktk6SJA2iIUxrapq2AMjvuvlz4E+6rr+uadqirtvfB34HfE3X9WpN0/4PcI2maRuBbwNliODsJU3T1gEXAaau6ws0TcsFHgcW9dH2oJLBWT/27oVHHhHf0W/eABMnxvf4HTtEG6NHQ2WlKGK6dKm4Lxo12bcv1BX42bHZur9jLRaFW26xYBjdNy/vi6KA02nBYhm8fYwcDrEZeUUlmAaMyIG2TjhUCxkeGJWvUHMI3tkJhxugYQRMr4dxWYPWxT7V1kIobGJ3g8ehEAnDH9+Cdgvo5XDFNCctDW70gx2kuBUyMuxs3WqjvDzIHXc4Yq5PpigKn/+8DcNmIepSGFOs8M4HCqEoFBRBmhey+3hN2tujPPRQA42NUaxWuOmmTPLzh9mWCJIknbtcXshKQFrT7xULxmKkaZqKCLD+1HWoRNf11wF0XV+jadpdmqaNAvbqul7ddc5/A79GbCT4sK7roa62/gxcBSwE/rmrjRpN08o1TSvure0BPdfTJIOzfkQiolL+sf+fSigEGzeKSvtz5x6vTB+NHt9TUVW7t/HSS342bAiiKCZTpzq4/vqTh9RUVYlrT0ZFUZg9O7//ExNIVeGG62HzdmhugT++AAcrxZSCSWPgrm/DwWr4tyehNEvMZXtDHz7BWXoa5HpMGtpM5s5SOeyO0upRaWxRyRoFNpvCN1aksmBcEqYJjY3w8MNhwmERYMfzZ6CiKIzVLGzcIUbHpk4SKVWPE67tZ3Xq/v1B6uoijBrloLY2zMaN7SxfLoMzSZIGSacPauNPa67cXMvKLXWf3b76KzfjTPbmxtHEzcCjQGHX7Z6hXRTIAY4FZui6Xq9pWkbX8fITzq0GLgHSdV2v73F8xCnaHnQyOOvHxIlw/QqR1pw06dTnrVkjRsVsNtB1uO02cXzKFNi8WYyaJSfDxRcff8zOnSEKC61YrbBrVwjDME9ZomH3boPaWli4UEGJN7c6CJKSoGQM/M+j0B4EpwuKiuCSmSavvBTmz4+bfPSJBQsqRkRldAksegjGD4P0Zn4+fPdmhdffUKjLC9EyO4zZaueqUXasFviX2cfOFOP5Xi/cequCwwEZGfGPUI7X4MLp8PEOkbr+9U9g9tT+H+d2q5im2Eu1o8MgLU2mNSVJGmSnkZRZMSuHFbOOzzHbmOyhyZZeE8tjNU3zAjN0Xf9fTdO+2XW45y8/C2J+WO4Jj8sCmnoeB/K6jjVpmpap63pDj+O9tT3oZHDWD1WNrezF0aNiK6SkJJEmM02RYnS74dvfhtffgOYmEaQdq101YYKdTZs6URSFiRPtfdbO2r7dRNfh4ouVYbe59zHvbhAjQDNLYVeFqH3WWhXmvl8EqKzsRLzdHLgy3PjrVR54EH7/u6HutXDZZQoXXww7UXjONAkdMvEGYGkxVPggEO4+0udNU9myCxpbYXI/RYd7UlVYthiumC+2Bev5/YxE4MAB8X7KOuGaY8Y4WLIkhc2bO5g928PFF8e+0EOSJGnAXF7ISUBas9UrpuDH5hbgAk3T1nJ8ZKta07TLdV1/U9O0ywBd1/WDmqZN0DRthK7rR4HbgReADcCjmqa9gJihdCMiRdqKmEv2E03TcoDSrjb292x74E84fjI4S5CFC+Hxx6G1FZYs6b5wYN062LBejLisXCnSWSUlcM01SZSU2DEMEaj1ZflylVBIFDId7iYWQI5H7C/68XsRjlQf2xhTAToI+q0EPU527YH7/xeuvhKKi/pqcXDY7TADOyWmlaSxCsdi5ce2QUOge3D2xPNQUyfS1v/0NSgu6L3NvrhOUQll7VoxEuvxwF13iRFXECnR+fOTmT8/Of6LSZIkDVSnDxoTsFrTUwbW2FZr6rr+K+BXAF0jZ37gTeAhTdPuBeqAW7tOvxN4omuO2ofAc12rNR/pegzAH7vmmK0C5mia9g4i4Ds26f+np2h7UMngLEFGj4Z/+Rcx6pHc47PzwAFRnDYpCfzt8Mo6GFUNcyYqTJkSW/0xu334jpgdc+lFsL8CKqvFRulLl8GRTxVRiBYr4o8WBSNi0BGMoo1VaO9Q+d9H4V9/KPbDHA5SlO7j9tdOFKtQT9TeAW6X2Mg8GOq9nWgU3lgntrK6YoHYiikW7e3iMaGQ2MJJkiRp2Bi8tWYn0XX90RNuXtfL/TsRqzJ7Hl8JrOxxzATu7uVcX29tDzYZnCWQ6xSVK0rHwWuvig9dvRYa7NAShd374QdfFdXjzwW5OfD9m6GhCdJSRWX8m25y8Je/2GhoiGAYJopFIaegk5G5Ecr3GbSEk6mqtWB7GG5ZAfkxTBF94QMoLYBxhf2fmwhu28nHvrIM1qyD4lzwnOL7V1MHb30g/j9xbOyja4sWidR3drbcIUCSpGHE6YURCUhr+uJKa56XZHA2QJUt4LJCZh91yBbMF9v4VFVDsxNMFbLS4EgddHSeO8EZiOeZdMJrMWaMysqVXn76Ux8tLSZH66Oku334fWEOV7vRGxSuWpSE22Xh5bXwT9f3f41UD7iH+DUryAMtD159FXZvgeuvh8k9KvpnZ8D0SWIUbEQcK1Pd7u4LRyRJkoaFoA8qEpDWdJaBRe6t2ZchDc76q/Y7lH2LxfYaWLkL7CrcPvfUAZqqwqxZcOhNaAvC7gNwuBauLQPveTB9aOFCJ6+9ls3zz7ezcmWAHTvaAJXiIiuVzSb6vg6cThced2xvx0un9X9OW5vJunUGCxaoJCWdmXl6e/aISfudnaLIcM/gzG4XI2ySJEnnBLm35qAZsuzxKar9XooI0n4+VP2Khz8EkSgEo9ARw9ygnTpMHwdfWijSYdctIq4aZmezpCSVoiI7ra0WwEooZMHfBC6bQUW1lRdfCtNSbSZsjlUgAAcPisApVq2t0NIS+/nTZojN3tsDMHNm/H2UJEk666gJ+JL6NSQjZ7FU+x2KfsVr1kgxxT3JBoXe/s+fUgIffSL+aLho6vkTmB2TkWFn7NgkJk608frrAWqqFYqKICUpgtNh0NLooK5OYeTIgV8rO1vhO9+xcPQo+P1iMUZf/H74/e9FCvL7349ti63GEKj5MGUuFA7S/DdJkqQh4/RCRgLmnDV64RQLqSRhqNKasVT7jUtdXR3LlnXPIa1YsYIVK1acTv9iYrfCxXGUgFi2AMYXi/+XDoPSEYNp2y54e51Cs99CoFXF77djs5kEAgpJSVE8XjtZWSppaYm75rPPwtatIjD77nfps21FEaspT9zRoT9TS8RenGkOsWvAsfp1kiRJ56SgDyoTMOfMUgaKnHPWl0EPzuKo9huX7Oxsnn/++YF274yyWmHimKHuxcA0N0fR9TA2m8K4cTaczv4jmZqj8I8XIBKK8MFHHbQ3t2NXTMaMcTBqlJUf/MBFUpKVggIxGT4RTBO2bxcjWocPQ01N38GZxwN33CH+H2sf9pdD0yH4oBI2bYBbboS8eDYkSYCmJoPXXgsTCsHixTby8s6z4VhJkgaX3JhkUAzFyFlM1X6HoF9SPxoaojz4YBuBgEE0CoWFVm66KbnfwriBTjCiJtu2BvC3maiqhXZ/J7W1Fu64w8OcOb3UquhDKASfVoj/lxSdXGEfxEjYJZeILbWysmJLO8YTGBoGvPkOFOSDzQq1dbBhE3zpGnF/JALlB0Qh3vy82NuN19/+FqSpycRuh0ceifKjH7nOikLFkiSdhRxeyE5AWrNOpjX7M+jBWZzVfqVh5OOPg4RCJkVFIpg6dCjCoUMRxo7tO7gqzIfMdJPKahXMCFYiqE6FzEy4+urYKusapihsaxjwxMuw76AIwEqK4IZlYo9KgEAIqpsg1wtXXgkXXSTqz9nii/+IRKCuAbwpvQdtiiLajIRFcBaOdC+J8sFH8NIacDngrlvE5uqJZhgm9fUmeXkKqgqHD5t0dvYerEqSJA1YyAfVCUhrGmWI/cilUxnSUhr9Vfs9l0QNsY/i2ezYfqEnHInpcc3N0NqsMmZkFKM9SEuzgStZ4Wc/S8HrPfWLYpqwqRnerBcrY2emwWwn6IdhdFdB1/2V0NQCWemiqO9Nv4Sj9TAyC/79NigcAbUNMKow9gr9pglPPg97PhUjX9/9JqT0KHmiKGKU7MlnxG1vCsyb272NGF8eKith9WoIBsVo3wUXxPY4VVWYP9/K22+Lao7TpllO2p1CkiQpoRLxOWb0f8r5ThahHQRvVsLbVTAtC5aPgT72Nz9JZ+fxyebOU+zF2N5usHt3mORklXHjrCjKmUlrzZzp4OOPg1RUiGr/+flWior6fwvV1kEoCFddmczIkTby8wy+daOdkSNPPZxlmvD3g/B/P4a6/RBuBkcELiyBwk6xDRYKWC3gdoKvFX70n3CwAjLToLoe/v0BKMoWteSmjIfrvxDb8+zsFIFZUT5UVEJN7cnBGcCEcfDPt4u+ZGaA44SRs3mzIADkZfU9atbaCn/5C4BBMBjlscctHG1SiQBzpolCtn25/HIb48ZZiEahoEA9Y997SZIk/h977x0eV33n+7++55zpVb1akmXLVS7Yxg1jwNQECAlgOgskpG0Km73J3r2b3+7mJtnd3ORms3t3k/3dZMmSACGQhBBCr8Z09y43Wb2NyvQ+55z7x1fEBctykYUTzut55rEszYzOnJmR3vqU99sxQQkB/UHInvnd/CljibOzTMGAV3ug1gvbBuGyWigeQ2QdSyIBP/4JjIQhGIDPfPr4Fg8PPpiivV3HNE1uusnF4sVnxz6/rEzlC1/wc+BAXi43zLXjcJxYDJgm7N4Fb70hg7vnznNx7bVyI7JQeH81a3AYHnsangvDBjtE34H8IBijUR+/Owj1JbA6Cc0NcNs14HHDg0/C29ukSBsYNHG4BF4dZtTK2KRde2VlynESp8bplGJuRwuUFEPNCYb8AwF5OZaWAXi1H3wRmNkAziN0qK7DwAj090DLbhgc1OnujpPLmUQTgp6Un9mzFQ52wFc+efzv29cPL78Gc2cLzptvTehaWFhMArkI9E1AWzNvtTXHwxJnZxlNgecQ6m4AACAASURBVPklsG0I6v3gP4V5oI4OGBqGhnpoa5emqgsWHH0dXTfp7tapr1cYGDDo6zu79eLiYpVly05eDPT0wLZtcPVHoLtH2lq8vh56e2HGDLjrLinUcjmTN97I8fDvoM+usLtSI/6OoBADIwfEkKsjikkHglcE/OU9MHMqDIXh6/8KkUFk/9iEbMqgQ6iMRKC9S1bBTnYWSwi46WNw6YWyrXkygu5Y7JpsYzu095th/+YVWL8Bdr0NcxrgzXdMdJfG7BqTwWGdXF4nl1dOeLzPvQSH2qBlL8ydZc2ZWVhYTBJ/5OM5fyxY4mwSWDsdLpsCAbsUaydLUZEUCn198t/jWUGoqmDNGgcvv5zF5RIsXmwnHpf2EY2NY4exTxaGIY89GJQD9NEotLaByw07dx128P/GN3Ls2WOQMhUONkK2T0cf1NBVIAWohryzOJCDHo/K1x8W/Mdn4ZGnoauXUfGGnPVKCTIa3HI9FHtlJQyk2PW4xz8vigJlx2kp6jrE4/LxnIhZlXDfJeB1gMMG8YxcavA7YccBqCyGzTlQNPAUCw5FNNp68zTWG3z2bnC4oXnGCe6/CfYfhNkzT33ZwcLCwuK0cAShegLamr1BOIX0lg8jljibBBQBJSfZyjyS6mq45y44cBCmNY5tB7FmjZMlS2SL0eEQ3H8/7Nolw7NvuOHMjv1Mqa2FhQul55imwaWXw7e+J+fQLlklNyF/+EOTt94yKS9XiEUV8i5BdtBE0UwwBGgmJEcrgm5gxIAh2NGi8c3/gpY2wI6cYSggS1VZUEvggsUQGE0H+O2zsHGbFGefvh3KS0/98RxohTffgbtvP7whOhaVo+3Oln54ZKsUZ9fPg0uWwCsb4cJLYPE0+NS9Kht36Dh1wZzZHhYv1hhvdGzFMlgwT7ZgrTEzCwuLSSEXgYEJaGvmrLbmeFji7Bwjk5WdOc9oZWf6dHkZD7//cEmuqEi2ucar7pyIRx/dha6b3HbbvPGvfAQjIyatrSZ1dYKKCmnxsHYtXH455PLw4wfB6QanB2bNlpWzjg45S+d0QsAwKPYqpITOUFaDfsBuyramAjgEzABqpU1O0AelfnCVQToFf6i510DtddCiw3Lk99m0HepqoLsP9h44PXE2vVFW1MYTZkfydgd47GBT4Y02+PJqWDkfHPbDaQTnNduRCvPkmSjDXgsLC4uTQjAxbU3rD8pxscTZOcTeNnjkedk6u/pCWDH/9O7nuutg9eozixNSVQUhTm1+zTBM7r/fYHgYvF6Tr35VwekUf2jJdvVI8fmRy6U4mj06K1VWJqip0ejsLBCLCYIJnYpmjahNoI1AISPAC+SB2SZ4AIdCJgDtaWmlsXwO9NRCNAGGD0qr4OaLYEMclgfk96mtgo5u+XPheEP+hmGijLNKq2mnfl6nl8K+kKxwXTSaEOE6xUpqJmPyne8UME3467/WcLmsn24WFhaTjH2CtjW7g3Kd3WJMLHF2DvHsm+B3SzPTZ96ApXNPrULzHqoKpadRFTqSG2+cc8q3MU1IpWQUUjZrUigc/fWKMphSLefDKspg7gxZObrzTnj0UQ2HQ9DQYLDoCsHzOQ27Hd4RkGgDfUCA14QawNTwpgVT/LAnAtO8sHohbOuAg0Ngmw5+DQoqlI8WoxQF7r4JWjsg4IMpx4Sr792r89BDedasUVmzZmKHuC5shGo/6CY0nebz0t5u8txz8hzfdJPJ3LmWOLOwsJhkchEIWW3NycASZ+cQRQE41AXpLPg9Jx/Afa6gqoK771bYtMlg7lwFr/doAWG3w6duh4FBadrqHZ0Fq6yE++4DGdom1WjxMCgmpJIQKxJE4yp9GRPTB/4+8GuCRbMh1wMLgIAH5tZCzzDUalCxCGa54ZojqlwuFzTPOv6xh0ImsZhJV9dJOseeAkLA9LIzu4/GRsFtt0lx1tRkCTMLC4sPAMHEZGtaP8LGxRJn5xCfuBiefxuyebhi+R/noHd9vaC+fux3r812clmTC0tg72boiEIoB81VMLxHEBaQrINESm6knpeEhAbJjGwH/+2tsOZ82aJUVXkCY1noT4FLk35zxzuvK1aolJcLamrOTUVstwvuvsfGUFguFlhYWFhMOrYJytZMB+XylsWYWOLsHCLgg5uu+KCP4uywfwCeWAeb34TsAFx9Fdxz54kjlbo7YVkxZHNQHIQbvgHr34VdIWgdgEV+6EvAnR+FbM7EbYdiv8H3vpdn3z4dr1dh9VV2dvpUCsi24qoauLJO5ma6XdLcF8BmE8yapdLTC8++BDObYEHziR/Tli0GL7xgctFFghUrzq6oC0fhRw9DKg0VpfC5Wy1vMwsLi0kmH4Ehy4R2MrDEmcVpk8udnEBoHYR/egI2vmTScwjKXIL+B2DxebBo4di3u2ARPPWqbO9+9GIoCsJ1V8KlSfi/j0FfL0ybAppu8MtHCmzdqrNpU4KBgSS6boDNzg/vd1Ha5KN5jZ3ZC2BdFna/BNEhWVlf+7GjRdgvH4d4Arbvhvoph8Xb8Vi3TgaNv/SSyYoVJ3nSjsAwYMNOSGdgxcKjg9OPpTckhVl9DXT0yiWIyjNslVpYWFicElZbc9KwxNkkYZrwy054fRAuKINb6mC064ZhQioPTm1sk9pcHrYfhGgSppTDzDE8zyYDXYdf/Qp27JCJBWvXnng+7kAIunYa9L5tkslBr9vEcCqkUieuNq1YBDOmygWH4BGxVU4HfPF2iMahOABPPGHQ0aGzYUOe/n4BmKA5weZCNwUDe+PoahG6qVAUgkQEzpsh7TWefP6wODNNKORgZATKy8Fug0gEDh2C4mJoaDj6+C6+WPDiiyarV5/eT5qWVvj1C9IHL5uDqy4c+7o1FdKfraNHirLiE4hGCwsLi7OCLQilE9DWjAfl9r3FmFjibBKIJODn2+Df9oGSh61lsLxEbhmGM/DQbhhISh+sm2fBrGOsGgoF+PlzcLAHnHa5MHD1Crmh+EEwMCBNZevr5b+rV0PVCfInq/yQjJroBqAZkAW7x2D2zLHFmWHILMySI1IRTBN+9VvYtgOuuQpWLpefnz5d0NnJ6Hboe+94MXoxQSjEh/N0dTgoqQT36KteN2TE0nts2QKhXtCzcPuNcjbt//5ECjTThE/dA01Nh6+/aJHCokUnfdreh6KMHqEpA9xPRNAPX7pTRlVVlVstTQsLiw+AQgRGJqCtWbDamuNxbk4//wlhGHD/8/Bvv4fWZ2H/q7Dp9/DzjbA1Do+2QDgNdX4Z7/SLPRDNHn0fbX3Q2isrZt19sGkb/M3/gd+/DG1dk/+Y/KOblh0d8t/jhbEfybwa+It7FYIlYCso+FW45+6x/cKyWfjxj+Hb34ZXXz38+UwGtu4Avw/e3STtOtrb8zQ2Cu65R2XJEoHdbgImFGKQDUM2DqaO3W6gFOC/fwLmz4KOLjjUDnW1EBqU1cA3N8OONkgXZDszHIZYDKY2yHzNjs4JOX1/YFYj3HEt3HglrF4y/vV9Xpg65cTtTwsLC4uzijoBF4txsSpnZ5mCLluR4WEwDbC7Rythr0CqFuIxOG9U3LhtMJyW1bTAEb+A87qs8BzshJ17Yc8mSKbg3jfhppvhM7fBvDEsIsY9voKsEJ2Kn5rXC5/7nAw1r62VvmYnQlHg5osEH9ugsmcPeL0qM06QG9nfL4VfTQ2sXw+XXCI/73LBJRfClu2waoXBF78YZc+eAqWlgu99L0BlpZOVKwXf/naYXM4EPQ+oKG4PtXUqy+bAcD/ceRPs3AMPPgZ790nRdcEF0DUM8+bLymQ4DrWVUFkhv64qMPMEx3w6CAELTvN5s7CwsJh0bEEonoC2ZjgoI14sxsQSZ2cZuw1uWg1PbYVwBFBAzYFmky2tSjcMpaHMDZmCzOwOHFMZqSkFuwZv9cG2EORKADsMHYDt22Dz/NMXZy+8MCp6Ljm125WUnLpTvssFixePf73yctkm7e2FC4+Zw7riUpkr+Y1/yPHUMzlcTtjfCl/7mwzf/Y6PNWs0tm8P8swzUXI5wOagboaTm6+1U1EOr24wKfIY2FQFmyaorYbOHujtlzNd1Q2yGhlLyNbhp++F7m4ZhXU8Y9+9++T1Gqee2rmYSF5dL5cFrrrs9EyLLSwsLE6KQgTCVltzMrDE2STQ3ADP/K3BJ/4xy4GQDVupxrIlUJyBe+bAg7ugKyYrKWtnQtEx0T4BL1y2El5oAz0JxAEnUAmxJHjGiAJ6dQts2Q8rm2HFGLYQ559/YjuLycI0TcSoAZnLBZ//PCSTEDjO4Ptrb8FIWBCNFOjPqIDC0y8UGErqfOfvVP75n8txODTe2ZBHKS2mea6L4iJZwQuPGPzbv6f55B12aqvsdPbAkgWwbCkc6JBCrSgAjVPk93I6j59taphwoAt+8iA4VPjr/zZ+e/dM6E9C1jSJ5MFtF+wchN2dMNUPu9fJCuiKpVBcNO5dWVhYWJw+1h+Ak8I58Gv5w0Gi+F3+6but7OjxEA+vosxexs5Enm57js8ucZLLqbg02do8Hg4nXLQQbCPw1htg5KGoAWZNg9VL4aVOaI3CsgpoLoXX9sM3fiNDxrd1wZwGKfKOpWyS7RgiEZN33y1gGHD++SqlpQqdnTo//3kOvx/uvtuJ3y+w2d4f3J7LwRtvwaYt4PEKDFMANrA70U2Vru4CD/9a5QfftvHDH5axYaPBuy0KybzA4ZCWFV6vYNEKlVmzVC6+WM6xvRcgft89MBKR25D9KXjkLemNdlEjzD1i4SGtw8OdcCAKLTNgBRMfQt7aCS++JS02sgH47haTV9MmWa2ALWdg2+1g5QxBuASuugbqvJYws7CwOMvYglA0AW3NoSBkx7/ahxlLnE0CObJsYzdRxYWoGCSr72frUICIP856LcEh4WSt68Ql3mK3rNZcezX4A9AVhul++OLH4Yl++NleMAS80AlVbtjVA2igFqAjBwOp44uzM6GlRc6dLV4sg83HI5Mx+clPcsTjJkLA1q06X/qSg3feKWCaJj09cOiQzsKFx39ZvrsRnnsBEkmIxAUet0JW10BRQTcZCQkO7s0RCtl46qksbW0mU+oVaqc6OdgpB+nvXaswZ7qLTA6e3AA9QzB/KlwwW25EBv0QisN/bQCvQ9qd/NcmWLkAGophvgfWD0JbCqYFINUML0bBexDW1oHXBgHtzNMdXngTugdg8FXwLISNgxAzwfCCHjAopEx27BeYU2DGcmgIjn+fFhYWFmdEIQJRq605GVjibBJIA1E8eIij2Q1KquwsKMrS7U1SJRwMkEXHRD2BM9/UMrh6Pjy/G+Ysgsu9cONiiCiwazsEnZDMQSgM77SCXYWmGTDfDlkHFCbY9K+3Fx58UIqQvXvhi18c/zahkEk0alJXJ5eEOzsN+voMmptVduzQ8fuhtvbE9hoFXVapbr1JY/4MF9/5bo5Y1gaagt+jU+xT+O6PcnShkk8aTHfBHR+DTQcgbxyOjnp6I2xuhVI/PLVRtobVUiig0x+FEV1Q45R2HDuGYWsH5IagEbA7waFBJAcHE9KaY2sE3gjD7CDM8cFN1cf3rDMM2NgK/VFY3gQVY/iVLVsAh14GxwwoVWCeA3wIhjYrKKqDXEGh2A5N/sPCLKfLSp/LeldbWFicDSwT2knD+jE+CbjQcLGQNMMUUJnvmMpUh5MnUAmRZxmBEwqz91jVBHNq4MUO8Dhk2++dNih3ycsrByCoQtIDh4bACIK7DHwKVPuOf5+GcXoB67ou/bnsdsifpJnge0HomYyJosjv7fMJfEGVv/orFbsdnM73n4dUCh57DPbvh1RULi+sXC440O+lfmmBzECehiqTXNZkwWKNZ940uOpGG31RKJkteGIjbGqVXmIbD8GXroLOISmMXA5IOODlkMkB2wCHbMP0dHno66qmPqbRZIPNqiCXBAomG7wGzqhJlVthiaYQK0CVEzqyUO+GKU7YEYMFfph7nBm03d3w+EZw2aGlB756zfE9zhbNgYomeCUBKwxoHxDMy0G+WeP328HpAc0Oq2bCYAZeHoEHtkDXu9Boh+/fCzNO4D1nYWFhccqoQQhMQFuzzyr1j4clziYBOyofpZH9lOBFYyZBVBTuoJo8Bq5T+FNk0yBsHZEtziIH+ByyIoQObfsgPQIVtbCkBpZXwJJqWFojK2vH8sLb8NpmWDwHPnHJqbXipkyB66+Hri5pQ3EyFBcL1q7V+N3vCug6XHedhmlX+IfHIKAIYt1yk/XKS2HVqsO3e+opaG2VDv1VVdL4tmkOtHQpVJXAznZBb8iktFShJ2RimhDwCYRTkM7DoRA0lEk7jK4hiKRgbh28vB28TkjlwFueIOoaon3QzfCgFxFM0B0PsDclyFUCCcBjgE1giAIRRaclrzHLqVJkg5ECNAflOVQE5MYIJ09mpRgu8UIoJo1wxzKgrbHBnaPt4q9dBem8SYQsotZGKi7F7C7goU2wuwCdT0A+AYMJ+HoOfvWtk3teLCwsLE4KPQLxCWhr6lZbczwscTZJBHGwlPKjPqch0I4jzAoF2Z70ucF3jIeYxyZ/oQsBHjvM9MLz7fByK/R2geEwGN5v4i0zuHaGxrK64yuuTBbWbYLaCti0Gy5efOqRQOefLy+nwoIFGvPny8cshCCcAArw1lbY9roc2v/lw/A3/wNuvlm2MA8ehIrR97HDIR97PAJ2u2DRCo2OPkFo0CAfh+71JrOXqDz7mmAwBBcvgvppUqCNRGAwDP/yawh4oKkSgl6Y1wCZSp39UYVYq4/soIuimgQ5X4H8u3YoAcKAw4S8oIBCVJhUYuCzqVxZDiVRaI1DsROCNpg2xoLA/DrY0wPdw3DdEnCMsQByLC477LO3c4gBmhY6KY82Ue/2cN9Og0FziIjpQ4RdlPvBDxiJU3teLCwsLMbFamtOGpY4O8fI5eGnT0LXANg0uPsaaKg+/PXlldIHTQFmFcsqzeJKeGgn6HYDIwlKENLuFM5aBTh+P9NhBz0Kjz4Pc5vB65qUhwfwB8uMoSGTjRt1gjEItStEwgKXR5BNwTPPQCIBn/mM3CgNheS/hiFbqjVVcFs1/PARFV+lwv6wSShqQlrn4IMG5DK4PFDohDVX2nDVqKQSsHQalAakOD3UA7VlMGUJFDQ3jTkXZWlBSjMZ6QxSWqRhZgWEgCLkdkDIQCk30Eyd7pCdDcDePmh2Q07AyhlwcRX4xnhnuR3wyYtP/ZxlydPGAMV4Sdh0duUjbO72kLe38Ofiv+gNzGLvJZ+k700Fpx0+e8PpPTcWFhYWY6IGwTcBbU3VamuOhyXOzjHae6GzHxqqYDgK67ccLc7yOoSjsLMftjjhggZZ0BnYCkYUMMEYBo8vx1M7bPxmL6yZBxfPPfr7hMMgEjC9HrZtgkd/B7ffcPT8mWFA7zCUBaSYO1O6B+Ghl6GyCC6fb3L/T2R70+GEZMhAEwrOnKC4WFbkOjpMHn9c56KLFB5/XKGrSwqz5cth2jRZQesLw+ZWgYEpxVNGgawOOZN0Flq2w0BPlhu/4OSS+YcfnNsJDZXQGYJ12+Gjy+x83FNNq0fHiGlkHRplqkK0EuIbTJhmQgBEjYnbZWAMa7jSKrPK4O1BUBKgmKA0jC3MzgQNFRd2IiR5qqWSXV0lZJzgNANkAyqVhSR3fFLgv0HO0ZUWT/wxWFhYfMjRI5C02pqTgSXOzjGcDjlon85CIg2BIwpfhgEPb4XWISj1QCQNu/uhTAUjDbxnlZGD+CC0RV00OOAHvwJ3AZYuOOL7OCGdgyefBaHDDx+CGY2wdJEclhJCsGk/PLoOFs+A29ac+WN7twUyOdjbBYUhHcOAmhqBrkNtiaDCbzB/vmDKFIHHA2+/neXgQYOhIcGXv+yivRO8HphSe3g+7rUDYBimjFYwgIwhc7Iw5KnIGSSTGtvW55k51XFUYHgvcLAEsvvg0vMgVnAwfyqsngo7EoAGfzYffrrKoD0h26YZhyA16ETkBEEDRF5ukCp22ZJ1H7Nc0TUMj70NZX64abkMrj8dVBRWMYd99BPz+eh2aOTdUEU1O7TPUK9V8NMBwV/VQKkVim5hYXE2EExMIrfV1hwXS5ydY9RVwjUXwlvbYW4jXLb08Nc6I1KYNYxWRbwOaZmxbwD5hnGPrkDmBY7eIBessvHb18CRgydekIHfTgckcvDAHnjZBlEFlCzs2waf/5qOo2Awcxp865sqboeCXQPfcVqenZ2weTMsWSKXA44lHIZ162DZMqgerfzNb5TB4lUlYIzIJACQkUNer7xNebmJx/PeO1fg9YLHI2hph8dfgpIgfG4tuF3Q1gOJPGAHCqPnwNDlTISuSKfegkHeUOhqU9i4BS5YfvgYe4FeFXwC9ofhN/3gs0G/Li03DqTg6XZICIPK6XF0u07UECT2+ajLO6hwQVcUrqoEIw4lPjiv8ujzsG6PXDjY0wNtgzC75uRfC8fixYlBJa66ODV6Cn+Pn681Knxi6jQ298HWELitDU0LC4uzhRoEr9XWnAwscXYOcsECeTmWWOb9G5VeBxR5YfFK2JoAM6PgH4aldQpLm2B2Mfz+RZjVeLg12ZeAX2yFvX7Qm0DZBjbN5FCLge6E1mFB6X8Y/O9/VPj67XJO6lgeeQTicblF+dWvvv/rBw/Ck0+CzXZYnDXVwv93u9ya3LxZ8OtfGwSDsko3dapBf79CoSDIZGBoCJYutXPddQaNjQq/fF4Ky8EROdTvz8MDT0KgGIYSyL/EDKRAswNmAbIFQJBL6hSX2RgaglhMLhU4HNAMVJmQL8jjBNkZzRvQkYfkEPRGIePNYXfmMRUVhzBRpiRI73aQTECFDz42E2a45MfBY4RsU6W0zPA4oGwMO5NToR6Njzsd1DU4mFkN1UHI5qVXWyoHb9ngyjGiuiwsLCzOCCMC6QloaxpWW3M8LHH2R0SZV7Y8DVMuAgAMJ2FmGfia4JrkaOZjD1xaBdPKwVkLi2ZL8fGesGsIQPsB0IOAD4wicBZBok1gBASGYrKuU/DtX0CtxyTRl6bIp3PZZS4qKuRLZupUWTlraDj+sc6bB/fdB42NR3/eNvqKO+88hdZWkx07DBRFVs7+/u+hvV0wMgJLl0IgYPDmmwbxOFxyvsqjz0NTHdSUQ0ef3Fr9xHx4cEiQSZlSoAUUCBXkZgUGmCpCVYkaKuV5ePklSEYNaisN5i5SiBcUSoNQ44ZrqqElBldWG2wUcX4bFuSFg7QnS1gR6CbYswLVYeAImJSogkYHPN4BX18AehbaR2BK5eEA8uVNMK1Cblt6x8hAPRXK0fgz/LzSCc+NwLXzoMQDU4qhfRhqrQgnCwuLs8lEtDUtxsUSZ39E+G1Q6ZRZmZVBKBgydPuqWbA5Ba/npQC7cTF84oglAvsxM0g2FTwdwLvIfLMC+A1wTQPdBgGvIGsT7N0PP95egLDOysocg4MF/uIv5G//G2+ENWugeIzBc6cTFi4c+7FomuCWWzTWrDFJpUwqKwWKApWVJjYblJWZfP/7OoGA4IkndO67T+Gv7jlcNiwJyuWFaRVw7UJYv1UhXQB3rY2EliFxUAehoNkKNC93opYoDPSZVJWb9HQaFDKw84COb6Hg/AWCf18Hn70QlpUZPE0vupmmtF4wUlGghyCmKhDIpIVC3MGw22BbTEFPCmJ5+M7rYO6AQ4dgZgN89y/APzoDWDbBgeiRNLyw18RQTSraFa6eB59ckiY3NIKr5gz6phYWFhYnQgmCawLamorV1hwPS5z9kVDQ4afPQ++gHEKvqoB59dBcCX4nfNQH0z1yLr5p1BvtYAcc6IA506D+mN/ZX/gYfOt+Kcac5RDNCdJJjfpGk7IKQTYv0wdG5imoLbBxi8HgsMrMmQU+8hGNcBgefAj8frjjdtkmPB3Ky2VEEsDDD+vs2CE/f+GFUmjmRwXnsSkGQR988jp49k3p0fatz0O8ADsOKWzd5ifZn6WjS2fZ+RpfuNvO9//F4LnXBTt65cJDMmOSEXDrKigtgp4wvNsOTXPStJChARd6wSTqzmLkQTENMHSc+Tw1RjetNJIxfGSAai/4EvB6Lzh1adExGDksziYavxN8TSm2KylmlJcACurrz+Ha8hZ86i8Ju6voC4NLM6kpA7tmTd9aWFhMAGYEshPQ1jSttuZ4WOLsj4RkBgbC0FgN/SNQbYeVDYe/rgiY5ZMGtq+8DVtbYPdBmFoLb2+H/3b30Zufn70BplZBZzf85tewo1P6dGWjgo9/AoQG//w0pIXASNmIdasc6hCsf1vnm39rcOXldrp7QBuQHmTHWwo4FUzTpKVFtkmTSRmofuedKlu3msyerYyKuKNpqIbPr5Ufv7wLnt8B2TTs6BKsmeekogEWzoGHXjbZ0i9ommVSaoOL18BwWNBiqiiqIJeX4m/Y0HndTLMPjS0FCGdMBjNBVGeBVI8fIgoOZxwR0HHZDPymXCBo9gA2CFZDUQyuvQDqK+VmatcQlAek6e1EoSrw+bkO+k2FJjGqWmfNB83GhrCTr/8kxqYtTjJRqJmb5udfcbKy4TTVs4WFhcWRTIQJrcW4WOLsAyQSg54BKApA9RHhAbECPNQPCR3uqIRqh9yYnFYl58lUFZobjn+fm3bDK+/ISKD97XL70zClzcOR4szlhOtG7TFGeqClFVw2qAhCogCqIce3EjsgvFP9Q5hmIQf/8L8UbrnJZOECgc8nI5XOFCEEy5bBW2+BECYXXaQwc6bCzJnvv+6BAwaPPGKyZo1g1SopTnZ3Q1UQPBWQyUjvtBXzIJKBTE7w0TWwZQ/cu1awZJ7gt2/Bi+tha6sUtPX1Bl0rE3TpJoowCOlZBn2CbNSFGs8jYgKblieVcbEjPZ9ih0LeK8iG4J1uWd0zq+CfPgfTR1u9D7wArf3yubvvWhmuPlGUoFEijnj71k/jpVgNa/9nnojugRSAScc+B1/6VYb1X3Hgsd7tFhYWZ4ISBKfV1pwMmBykCQAAIABJREFUrB/XHxDDEfiPRyCVBUy4/RqY2yS/diAF7aOeWW9H4YZyWdm54zLoGZJu/qVjRC0NR6TwqiiR0Uz9w3DjFVBROvax/O1/h5lN8NCzUNEIr3eBnoeaoE46bZC2CTJ/MLhRyBdMfv97gy9/+fT+hHp7C2zaBRctlfYe73H11Qrz50vxeaBb8LPfwMpF0DT16Nu3t0N/P7S0mH/I4GyqhHUtUmBWVcBnr5JbrM+8A7kCFPsFU6cK6mph/S7YegjmVcIDmyFpGHTGCqwY0FE8BsN5BwNKgYwi0EMqeVVD5KTIzSQ8+O0K1ZqKSMDBEVgcgGQenAX46XpYMx1WTofOQSj3ywzNeHpixdmRhNva8FRW88lvm0TCbvmXbQ6wC4y4YCBi41d9cPcZVjctLCw+5JgRyFltzcnAEmcfEAc7pNFsQ7WsoL29/bA4q3JIYZY3YfoR1gw2Tbran4iFs2DjTugegPPmwOdulsPzJ0JRQHdD/XRI6pDKQHkQVlWnEd15Zi3zsVUT9LZJY9dgUKGo6PRWdhJJ+P2rUOSHXz8HzTMOz5MpiqC+HnbshWfXyazPh56Ar31Gms++xwUXCIqKYOpUwfAItHfBikYo8sBIAhY2SGEGcNECGIrJdIKLF8MrWbi/FQJlsOd1CPt18OYpaHm27k7hrkiSyDvQAfWgwDmQJTnkIau6IKegBWFGUOGGBvjdFmhPQ7sJ88sgHYNN7WBkIZOHjy+Hl7bBhbNlRfJsoOdytL7wApmmNfSPTIWogDJkatcAmJrG5SvttKXPzve3sLD4cGFa25qTgiXOPiB8HtlOy2QhloCZjbIyEzekw/tf1klxVnKSwdjvUVMB990JQ2FZLTvZofRoQvqgXbcCBmOwdTv0R93cfofBtZdrPPeSxubtBjt3mnzkUoWPXSco6HL+ze8G/0nMVOUKss1YWgSDwzCt/v2D/iDPiSLkOYon5TLEkbjdgiVL5Azav/wYXtwGxRXwj38urSuOxOOCP7tCfvxAN+yIw4ATup3Q2wh5zUApKBTyDqJpB8knnSiYOKpiJNu96CioaROnP0POdOLWVGlpokufW78C+aiM3wzFYFoQ7Jr0HFs0TV7OJqrdzsK77uI/X3fi8ENeGHIDVwPNCQuvUylvhGVWF8HCwuJMUYJgt9qak4Elzj4gZjXCFatg825oboKly+BHYegvyCflZj/MPs02WFFAXt6jOwuPDcH+OCzywF014DhGFN3xUegbAmHAq2/AtBoAhV2tCiuXws03wM03KBgGPN0irSPaW2WVz++CT10FU8oZE92A/3wdukZg9ky4vv7oObsjmT8LWg5CWxdctRqCY1hRJBKQ02E4CyUavLEbbr0YIkSwYcNteohlZavTpsCuOOzPg+qESAIo0/EEk2S77Yhag1yRG6M3T1EgQnHlIFpIYBgKVOkYbo2RQ1XU+RTKA7DNzECtzqKCg3e32LArUOyBKj/UlcBlc49/zGcDzenEZYfKYgg5FVIqeFT41MchmYW1QVhUNnnHY2Fh8aeJaUYw9TNva5pWW3NcLHH2AaEocOlyeQH4RQSGClBng7QBj8bga3bwnGEJOVKA+wdhVwi6+uANQ/qc3XOED9owCQa9MYq8Hgb3BVDVwyaqqipbke+xrQte3As1PugcAFuVFGdbD55YnKVz0B2WrceOEWi4YOzrOh1w1w1jf314BHp64fHfys3OBdOgvBYWNsIgIbayBdW0MbhvJTt7XPgccO8iCOVh1wgoBkQLYJgFNJuJUqejl2kYugrV4CBNoDiKfVEOp5LHV5Yg3lfLvGCQ5UEPB1xJZpZl0R3Q6YkxPRXk+ho3sSzMr4YLm2DrIDgSML8Y/KM+c/mCrB7uD0F/HFZMhaB7/OdwPHQTZs+ASxbC7kMQsEN5kXyORoDpvsOmxRYWFhanjQBjIrY1rZ9H42KJs3OE3gIUj77oXYoUanHjzMVZXx5yJjhNCA9KcbApBndXyQ3DMEnWsRuBQMdgTsUsbFqQ0LB8/+h5k/AQpFKQyAgeeBo2hkE0QW8Shg9BKAhXLDnxcXid8NF5sKUTrp53+o9n03Z45BnoGJRLAVcshEoNvnybnMnrR8fEJJk32DFgUh+Anji80gm7whAbkPFMelon3wV6uQM9qGEmFISqgypojLUxv2sbw74iwrUllNihrrGFwbzK5kwJXTYFVdXRqyKUGAn0Uo1nttSzq7OEwAGF+LMCj1cwJQh1U+C8KijKw3Ob4d390BWDIhesaIJf/Bk4TrF1fSz9WXgrA5+9Hp5+W0ZFlTshHIO1qyF4lvzWLCwsPmSIIEKbgLamsNqa42GJs3OEJju8m4YpNogaUqAFJ2Dw0i7kLNuiSnCYUpDF0/DNbTA3CPPrk5gKlOAlSop8MMKnbwmyfoOMijq0y+CJx2H3bggXVNoPymH6bSFomA7T3FBQofgE26DvsapJXk5ELAuaAu7jCJZkBr75exgW4K6A7gT8LgQ3r5axmgDlVLCYJeSwscV0M5SSt3vkFdhpgt5vUjRtkJKGKPoMQai9kgKgenUUWwFFMagZ6MG+N8/8+p20T2kErYpEVieT00maCTBdtGZiBBwJvIqdoYSL/b0m8WyS3iEf5EFLQlcGNmZg64j0gqsxoSsCeRXiMdjZDd1RmHYS5+5E1Djh7lr4z5flpm40C1MrYe0q6BuEVFoGxVtYWFicCaYZQTestuZkYImzc4QrvZAHdmWgRIUbA6AqMUbYh51ivIw9WZ7MweYuGbo9r+rocPSpDmh2w84UVFTASBJEGMoC8O6QQTSYpaMohp0kNdhZjJ/qCrjlWnn7R5IQjZi8+pZC5RQo1aC5CormQWsYqnzQHQPnGVZ/hsLw7l54th/qyuEryyGnmDyczeFE8DFs3PFTwTMtYA7L21SVw9XXQNQBv9oFty8ARSiUUsZQHgI2+OU7sO9lKXhpAoc3g68uSnrIgTDBm4szcqgMfRh0t4JSliI5206qYGfEX0y/WopQbThcOeIpP33ZAIVCBkXLEM55qPJkifY6yWdsuAIJ4mEpzgpxucggNBhwwFAG6lzgMCCvQMYOFR6onqBop6ANfE6ZdJArgEuD/3wcekNQVgxfuAXsZ/gcWVhYfMgRAuN4W1yncT8WJ8YSZ+cITgVu9MvLe3TxHHlGMDHQ+AROju/2+sQu2NkvK12fssGMI4a/FQG3lMBiD0SMDCmPzrNxO0kzShc6AZLMppoRkqRR8XH02uVH15qcd77C5/+HoH8PLJgJzVNhybwUf/9IhH5h4+ZVRdQHj/9SMgzY3CLfi4tmHX87c3AYPvfX0BeGZBNcslReP2SYtOoGioB3tps8129iRu3yTkzo64ent8Jdl8GeAdgdy9BgdtG5ayd/d+Aq9nW56dwAsYOAGxgyMGtNzMUm2UEnesGGoSuQUyBqQjHoaRu77POIJoIoBZ24FqCiPkRYKaE7D6Yti27oaCKPnvWSTin4hIFqCPS8gNjoA7QDmlywsGlgA/b1ga8ctDhMr4THPiUD0SeKm5fCa/vAbYeF1bB+HdRVyVnDWEJuyQLs7IInN8PKJrhkEhcXLCws/tgJoCgT0NZkDKNOiz9gibNzGJ00Ck4KJDHQx7xeMicD0NN5ub14LKqAWleaVraScaeoqc3THirDXZGg2DdCNDeXYb2SAxjklTT32O34heAVIuzQUpQ22Lj6yhK2bxesPB9WLYO482XmVwuKilMsnd6I4PhDZ63d8NiLcn4t6IXpde+/zsZtUmjV1ULPQZgyHf71B+BwC1avtdEdSPM9exZVcaKrGmimnEo1YNde6DwfsrYMDwyGmO7YzbrNVRyMZfCO7GdZbQ/retaQz9ghbpDL24lsLEIvsVFIqOSyDpn63ijAIfCVRsnanOwzZlPkClPiGSSVdZFS3bhtccIpF0bBxlC4lETKT9RQqCmNMaN5iJ0bKqUaMxXsbtAd0OCXWadDPuhIQbkXKIHvfwyqik7vdTEWQTdcd97h/686D97cBkvmSs+493h7v/TYe3WPJc4sLCxOHpMoBd6cgPu5CDjBBpmFJc7OZSq5ijCb8NOMi+oxr3f9PHhxP5R6YNYYlgkZsuQpkBD9zK8qcF0V/E7PsyeTY1ssyyFRTKktTd6h4zNz3Om0s50UVdjo0/Lcem+Br3K4zBMmwkeuBIMUeWJjHpvfc9gZ3zeGF1pNhWy5dfXIAPX+g1AahPiAIPCiSvTWHGZKw9QEGALhMjCTAlQw3Qq741BVrINusi85kzc6pqD1xrjxsl/S0VlNWWA2vfur5PCdIojtKYZqIV/9PgOiilx5NEzsthyFjA2bLY9hM0ARpHUXNnsBVS2g50HVdAYi1diUHEWeCJG8k9LZMeaWxohG0wzvK8ah2yjocMt88Ah4pk9GYlW4YXY5LDsmiD6Xh71tMnZr1tTjVxhPlatXw0dWvf++Lm2GZ7fD0sYz/x4WFhYfIoTAmIjVb6utOS6WODuHcVJBFVePe71SD9x63omvU0yABUynjX4qkWrJkVXYlamhPVvMSNpFGBcRB5jFOW53CqbhoJUMQTSK0diV1/mf8RxtZo41tuV81vsaNgVeSfTxUuYN8ql5fNzp5+pSgTYqCCpK4C/vkB+PZYi7oBn+6W9g515Ytgjeeg0GBiCdNVGcJgowu86gb34GdURHH9TIZwS4BWpzgZBikktp3OX18cwbZfTtchJwpAkNFhOKlBETbggYoOUhq0GFFGmYyDakAeQFBEzyBQ2fM0att5tkxkPesGN3ZkGAWy3g8aRB6GipLKm0lzl+SCccRMwsJV4TgY6jNE0gZCPogy3tkIjK9uUV9dJS5NPnSxF2JL95EbbtlYd05crDFitnyvFE3rQK+OIVE3P/FhYWHx4EATRWTcj9WJwYS5x9SFAQTKUaL7M4xJt00IeqCvKppSQTfky7iSkU4maOd6JJHvTvoUFxchlTmUEZWUPw1/E020QSUzX5WaEYM3kDl2gbeTjrpVhNEnWF+EnSiXvIweVHVKxPJqVg+pI0tXNVWrvsOJsho+l0B7PYLtGZrmu4qg7SqIF5noHRo5IddjIUKee8ui1c5H+HMkeGpf5Z/Ovm6zBUJ+FuPz954E6UoJ1smQIXK2CqkEDGG+UNSAvQhfQZaTOg3MA3FGPKzHbKPCMkojPRnF5UbZgUUO41KXPFCaW8eKsH8cZ1Kk0fzXU5Wl0CxZNnXpFCetjGvDKIpWTrsMoOqxulEW7XCDiP867b3wF11TKg/mDX+8VZ7zC0h6A8ANPHLqJaWFhYnDUMouR4ewLuZxXyB7HFWFji7EPClj54+RDEh+fin74dwxcmENRBeIibLkRKR3SbFAxBoUrnqWqd2xWdHJupJM1+UyEsElRrScJmBXF89Ob7OZTVKNJCVKhh7IVaup06G6Mml5cfLlvroz4X6hituv1EeC4dYv3rRdhDRRwMaXRlYFqJyoUuk1YzwlzbOziKSjjQ1kDCruKak2KmtoePaE/Tm65B1X1E1B2smZWi1fNxsi+68E3PE8560Oe6pNnbAWCpgIwJrlFR1mdCCggJbBsyTLmonYrqGO5FJRjlBVyqTqNwM5Us71LAqWqssNvRyRMOxJmGrND7cbMCD44RBz/Y7WB/ENpHIBKFlIDuEtm6dduh3Pf+c7DqPHhlg/z4suMIsx89C5iQ1+GWC+G8sxwLdTx6QzAUgWm14JkA81wLC4s/NgQ6ExGuabU1x8MSZx8CemLw7+/AQAK2davURS4kZmp4S9Moc/0EVZPcgI5p5tFtCtG+IC1zy/k3JcH1og+b2Eun6cXBUrK6hlcZYZa+l3vVl4moKfY4Z7I7X49b7aIoMwXnEfMEkQz8eKf8+DPzIHicSKowWTo6nQwMqWQGIZqRL8xduzR2NOvUNvYzUnASKwRRqnWMuAJ2aFDaSOY8FJwaJTaTuBakbs4hasq66dg1lYRwUwg5oExAmQplKoqWQ/Hl0O0Kpg5s1yClQqzA3Cv2UNkYp3RgBn9um8FvCBEnRg2DzMTFMAYhBijDThY7K3JBBvMKAS8swk0ldh55HlxtsAHwV8LsMqgvhjl1EE/BhdOliW55EVx70eFzcOlymDtdtjtLj1kU6BwETKgrg5E47O4cW5zlddgzDNVeKDsDAaXr8Nom6OmH1UvAZoMfPSo/X1UGX7x1YubiLCws/ngwAXMCxJl55ofyJ48lzv7EiWfhp5tg5wC0jUAiDfHOGhRbDkP3o5TaUYp1ciaoBQXTboJdZ7injJFMGT9QSql1dKG6DbzONqrNDMNGNTdpXdTaTDZoXsJ6EboKrQUvizIGVxzhLTiQgsG0/DsplIY9YXipG2YF4fpp0nC2mWKeTsaxpZ3k7RlyOYWATSUZ0SClMDvj5l/j00mabhS1gN2ZI+9UcJopvLYY8byf+qBAU0y0aWmMqIqoMlAVE9GRxwyZ0KJBv8B4TsW8UZXRC2kBdcCQAEXQOzyb6q6FNEx3UU4eBRtpIkzBgx0byzHZXEjTnYoQaJ3Lr9b78Dvh1jVQOWqua7NBsQEXqPDpj8uNTZ8LHloPIwno7IaRbvC64aqV8vrvUTmGGW1ZAAqGFGbhJKycM/bzvWcY/v+tMKcUvrT49F83uw7Ac+tlrunPfgdXXyx92xqqobNPhtNbxrYWFh8uFALYWTEh92NxYixx9idO6xB0h2C6R+YuFgAtayPvUSCbpcm/l0BwmNhcN31tNSQzXkyfSSrjRbUbRDqL6CvU4ahL4auNcZf5M74u3mCG6zPsLewibhaTwoNDZNFNG2srPDQf4dXWGIBL66Q4q3TDz/bJf7cMwcIymBEEDzauLy/mXTNCljRer5NIXKPCqfF3jU6+sr2RdoeHQGAE1Q52TwFdF3SYU1lq38Q0RxKPolBBjHW2OhJTPWjVBqk3HGgz8xgpA31AhUEFmjTMblBtGVx1WQpFdjJVTmyDUFvqpilo45JmeI0kJk7KidCKnzI0UglBpBOMpMqB7T52dILLAeorchNz1lS4+mqoqYGSEmhskOegc1AKs4YyaAvB9ZfBYBz+9xNw2QI4f8aJn8NpVXDb/2PvvePsqu877/ept9fpRRqN5qiMehcgigwGDAZswBiw17g7bomd4jh5ZZuT3SdPnnV2Y2+y3rgldhw/9jo2GAOmGYxASAL1MpJGR9L0Prf30/aPM1gCqyKBDDrv1+u+Zubc8/ve351758znfuu1sH8Arq6HKxee/tzWMCyuhxUXWKVumCCI4Fchk3dFWWuDK8w2rPSEmYfH5YhNjjLbLoKdK4C6C9/QWwhN0+YBy4GfAoKu6/aZzvfE2duc/X2w8wAUqm7XiLQD9VHIOzWiwVE66nopECIRrKIsr3AsO5/ydBCrqGBMijgZATsEZr+PatLPrvgKuuRH0cXnWaF+mpx5DMeUGDfiXOUXqQ+8yHYrRNRaSIccxCfBu+aA41SpGc+zrn6Y4ZKGLFxBRJGoUKOPcYyWDM3Lp9m3bRFmVQAf3Lgxz5QQ4+BEgLSvnsKAH3+wQiBexRezWNZygHTgHVzDQVqEKm3OtRyqrcLMO1iajDAlIR2tUOkXoTJTndkOGDbtNwwRbC2jxAympuop+eoQV01SWmCSbo2j49CJnyKzmKKfguVnax/IgTLJwkLq2mFyEkZG4OmXoJaDdUvglo2QjYPsd5sCCwI0x2FWHfRNwqJZ0NUKf/QVKFTgoU3wyFfcLv5nYlmnezsbDUH4/AV4zH7zePOhbxgGx+DeW6Au7oYyPY+Zh8fliwPYXljzvNE07cPAA7jN3QaAe4E/PtMaT5y9zdEaLGY1WhwZU2hWBZZF4NM3wDZhC+XkLhpDo5QlPzpd9FpXI0WqOENhnKqIYwvYVQnHcbCjIopUI+LkaO0bJ1I4Rrmrkc9ETQYkCdEXRBUmGDQa+FYhTEkcYbVVx1eqzxKwprBjJSTfBBtbY6QqB1HlMvWhjWziAHnKDAnT2Iss2plk8kgQNQ8v7BUYSBcpF1op1sLYIT+BfIWqUiRaNtGcW/nkoiQKAioStgPrKhZPDhVQ40XsLhF7UkVRRGqOCCEgAP7WEmGtgC2KVA2VUKTErPUp5q2W6Qj5OUyeKCGGqCEwmygwVcxSc2Qa08tQSq0ofjdx/+Bh2LYbyrZbZfngPuiddIsgEgGYXQfjWSgYMFQEMwv6Zhgag2oeJiTYr7tTEc6VI0fANKG7+41614CqwvtufvUxUfSEmYfH5YxIFD8X3udH5BxK+N9efAa4Gnhe1/WXNE3727Mt8MTZ25g0ZYbmH+eW2QYfNuL4RmPMTfqpq89js52csZ8D5fkU5SCzhQGSlRQjRhuS7CDFKiSlNDVBJp2qp2HWGKvU7SypHqRlZBRbFnD07xBc9VG6hBwZZKCBh6sJsopI0MnyvDnNT/M93CmBf+RJmHMvYVUhpASAneRYT54ySSL826RAT9Hh0N5WypsjiCELZwH0HLHw2yZCREYsgWXJZI/Vk6hJjO6DYLfrnTJt+EEfHJ6W8JWi5EYDWJaFPU/APKa4VdthIOmgLqwhqjaGoVAzVeSgxfwV4wjBJkK4DcjeSZgBKhjAVazmSFpiZy+oJ3niRQHiCZjMwdaDcOVKkGfmfjoOPDkFh/rhpech6UDRhqkStNW7xQFSFeIRGBsAzkOcPf44VCpvrDjz8PDweC02ecq8fBHsrAXOEi54e6Hg6i1H0zQBOOvgPk+cvY3pYRIbm1n+AAf9B1gULJA1KkxbTdRLzTjydtp8o/QxG59QIyCVkKoW2BBXMyhOlarfR7w+TYs1ThOTmKoKqoqvWmEg3MgP9VUI8iALWo+CCsOSSM5sIms4jKRb+cPiR/h//NOsK7XxlxOP0dTSToEGItSjzrz9RgsWO7NhpkcjVLaEwA92VUI47GB0A45DrKGKmkwhCQ4RU2Ht1nqWdoq/aTQ9UILDeVgYgQN1AqgKk9slsgMOqRYBc6EDVwgQdDAlhWIljO0IyPUGiUSOakCmxY7jkxwWESWMSQody4ZhW6QudOps/d4RaNPg2gVQF4JUCq5ZCY4KT+Zg/0EYzMNkBSIKhBJQGQfVgoABHQ5oHef3uj7wgDuz1MPDw+PNxIGL0krjcgtrAv8APAe0Aj8Dvnm2BZ44exsTRKGKRZ4yNStH18AW1MoYY4kOaFiLLPlpVydwbIc+u4O8HMEfqJA341ATyBYTlCtBfGKVsXwLA7k5xBpKDK1cRFspz38Y+gq95QQVaxZyfg3vn/dLIv5jNBglBtItqKUqSyL7WBvZhq+lytfM5bzPPsBWaQ6rxBu4BoEWY5KvD0EpOI/S4TCOLYLi9iBzMiJODQxboCNpcmWXj7k+B/w17lxi0RE8cZHwSzOdcwSIqtDaJrAhKbH/oEPPGIw1CJi2gGWKlKoRjLopWpoGUfwO7TGBzlo3C5V6HpB8CAj0MUHJstmbEXk5V+GmAMxKwmgWWk4qNDo+Drk87NgPc1ogFnOHjit++KcXQK+A0wDyFEylYf1C2P0ENPpBLMD9d8KambGkxTL88HFI5+D+m2FW86lf15hX6OTh4XEJEIkSYP1FsHN5NUrUdf27mqY9DywD9uq6fuRsazxx9jZmMY1UMUlRYm2ljFoZphpsZH7WoDdmMu7TkJwaDZSYlEyuc15kqtzC/pYy46kWHEMiEsijOFXypRiGIaNYJl3h/Wy1b2EP7ZiCQ0LNEg3kOJZNsr7xECYwnUvgyDJm0c+WwrVE/TkWNPawu9KCVKuhCJs5HE7xBw++i52H5iCsMzArMkhAFRBxHb+KgFMQiAVF7ICFHDDxI9Iall71+a01AHe2w5ZpuK0V9vRBLQNXLxNYvwa+PwjVElgiZGyRkcG5VCcShBcVmCqHOBbyYQkizhwBQYA2kqjFFqyCTRdNPDcNf7QOHtoJxybcUKplu3POG0Og+mCHDp2d8PVnYOUsuCIGex0Iq27VY3MEVMEVeRELcpLbXsSyQJahdwD0Ibf1xrPb4YHbTjy/TN6tDPWd1Rnu4eHh8cZgk6fIzotgZxWQOOt5bxc0Tbt25ttJoEXTtBZd1zedaY0nzt7GqEhcwSwADEnFYDdSxY9syyzlKvZkGkk7aRwBFsaPIaoFrGQf1/n6+Xb1KnpTi7BKIWq1JLH6FIVokJfFpfjNWZjyPBpbBilOR0n40oiqwUSlhXJ1HzGrQi4fJ2vFaQuOEPfnSFXq6JlYzBXy91kx8Axt1SB/m7iRnkNtmHkFdogIbTa0WDAuQVmENiAj4GuDtpCPm+UQ9VgsIojvFK71tXXubfNR+Oetbk+3jn1w6/vhxrnQX4GoCKkKHE0J1IaTDDwdgbkWqikSCClMNEJzCBRk1kmd7M3DENARhGQQPn6Nm+A/mYeeATgWhYao2/xVESGZgPYE7BmCL9wEo2nYcggiBbiqE4rTcNs18PCTsGYZVC3IFyERcxvT+hQ3hy3eAA9tgXmtrl79l1+6w+A//z5QvL9aDw+PS4BXrfm6uX/mqwisBbLAO860wLvMXyYo/k6U2V/AKPbydMzHpJjiYGotC+O9TBpZgsZKSr5hJAyuDWwn2NTHV/MfZ7rQSDw+TXhBlhG1hV5nPi+X4a7ATnz+KFakhOLUkEQLSbCRHIWEkoUa1CwfWSlJyYwgqiYoDoF0larqo1q22XNkMWZhphlsVcbJ2oTqC1S7FMxOGUwF/JCsh/VBuF0OIp5l7MdoHn5yEMISmDEYyEBfxu3SX6jCYMGdlBArwoEdYJkKTlXBVECPwMP74e5VsLUEBQeuboE6yWYsXOZFQeAqAjTFBLYfgZ06RKJweBTWzoaru6Egwa83wzWL4JGnwTcM9QOwbjE0JCCdB0GFu26FAzqsWACxmXFOEwVINsPgIHxnqyvswmG4cwXYNcgW3Eawnjjz8PC4FEhECbH2Iti5vMq+dV3/zCvfa5qmAI+cbY13mb+cCM1V4G4dAAAgAElEQVSlEmohxx6wyzT5BfpSa2j2wXsUh3GO0sfLqKLNmpjN11Z8mZ85N1J0wmyzr0S2LeJCmmmhnsPVGGt9I+yLxEhlGojZORaoR1jimwYxSCJSYGykjYP5xbREhzH8ItNCksnoXJYUD2DOLjNVaMOqSFAE4iA4EJaL+CoKVkYkG03iE21uROLTDSAKZxZmAIUaBIOwegH0DMLy9XD7QnihD1JPgd+AVgmSs+CADYIPnAJgQa0CvzoA23zQ3gx+ATIWdEct+uQKMrAAH/VITGTdOZkUwMrC2nlwxzvgX34KnTLs3ApKBFYvdltlPPUiXLnUDatuWObeyhUI+N0QqW3DTzfDwDQ82wfZEpRMSE3D3iH4/+6Gupgb2vTw8PC4FFjkybPnIthZDsQvfENvTZK4hQFnxBNnlxkRAqxnHhWxxuzWIBkDkgqoooCFSoU4eZIkhRGa5RgRq4iJD8sWsRwRSbSRHIuCGGeeepAOJYgV2E2dPU2bkqJZjJKs3YRUnE3EgYmSwvHiXJgGX7DC12d9jKeWZHh36BCzijF4SYYJIASOIJKaSKIoBtWCgujYLLZFPrtOQD6NLrNtKJXdQdyCAPVh6JdhMALzl8HvrYY5cSj2QjEObU3w7H7Yn4JAvYkpGFRqEqgSzX6JqSgcHIa5ESgZEA1AT0GiMyRRJ0jEZlz6G5fAH/8djI/D8i7YuhPmtoH4SmHCjN9+chqmRt22Gzv3wLuugyuXuHs9uWdYzYQVc2EkBwZuiFR2XFsxPyyf98a9Jzw8PDzOhUsV1tQ07SvA9TM//ntgC24F5Dzcj/ef0nV9WNO0NuBbQBA4DPy+rus1TdOuA/7LzEP/m67rX5+x+0Xgrlfs6rq+SdM09VS2X+dTfWX/B2ceWwBKM3s5I544uwyZ/crYDBGaZzwx06Q5iE6YBFNspJlJfGxioTjJDjvETc7jVMUwslDDL5VZN6ajTQVQZl1HqmUuY4wSQaaGj+emGsjlw/hMBacsQUFEscuoLVWGco3YsyxGaotQu3wkFwqM10TIAEEHw1YxgiqyAldGBTbOElne8Or9WxZsOgh7j8JTT0ImC6u74W/+GI5WoKUeFgiQc9xk/b1DMFSAiSxIEkQiNtn2Al3v6GX6cIipXzdROhrlQKxKXvZRDMD/3OO2vmjpgNmLRdYJcTIm7A7Dmih0NsGSJtgwDyJBGJuEkXG4/UZIyVApw3ganjwAkfDMHE3JrdiUpFc/n2298MhOt8DgqsVwpObaIwd1Ebjvejw8PDwuORIRwqy5CHbOvbJJ07QQMKzr+jWapkWAHwFPA9t1Xf+kpmmLgf8BvB/4GvCnuq7v1zTtk8BnNU37BvBXwLuBPPB9TdNWzphfC1wHRICHNU27GfjsaWy/bnRdP++ulJ448wDAwATAh0qZADWuYS7vZaHwJCL7aefXGAgErRJlIUCmJc6xgI/6lx7FWHwfTpePquAQqjXx7ICE5AiUKzWcSQUsG0PyYexSsHMi8YUpKkqQcNDiXXekyTTUs/0g5PMCqiIRr4erO6ApBnfPA5/sCrJcDhIJePko/Hw3bDkCB49AdxKe3wmbdsDs5a6XyhChUYKf7YD9Q+6A9XIEwg0OmbUmrfER9J5WUk824Bgi1IOTU+g/AL5rQQhAvARjaSiNwN4ARCT4t0nX1soIxNvhiYMQCkCDAfe0wzN9MCZDR6t7e8EBOwVBP2RyEJ1pjD2egeEUBFR4eLv7XAURegfhXcvd3Di/As0xuP4MszdfGRHl4eHh8UZjUSDHgYtgZzGc4/BzXdeLnOgL1g0UcL1o7525/4CmaX5N02RA0XV9/8y53wUeAvYAv9B1PQegadrXgffgerH+Ttd1B8hpmvYocOXpbOu6bp7r85sRhGd0EOq6/tkz3e+Js8scG4sh+ilSJIyfNFn8+GijGYkAddTT7ojETAPZyDDmb6IkBqk6PoSkw8BCm8md+zja/05u03roS6UIWiHaJR/6hIToGNhlxa1RQaByJEh+IEJwdpmMbdDvy/JnN9SRuELgmQHYnYaBCsxvhru6YMFME+mf/wK2bYcP3gtTNeiV4Diu4BougpOFdBZuDMEH22CiCu0i/GAfdDa4AiYRhqoKtTikCVE4EMHJiSfUTTPQbqNMi1j1UAjArBL4DGif8TBaDhwqQrgKowHo6IBsEewYOBHYeQTmJF2BCHD1Inj8JTg86FZ7fuAO6BuDf/8dqBjQ0IjrkRt1hVZQhs+tguZlULOgMw7R0+SZjU3Ad38M9Un4yD3uyCUPDw+PNwo3rHn+nwZ/+SOdx3909Dc/33VbK0G/1XI+NjRN+wzwZ8CfAv9O13XrpLvHgXrcJBkAdF23NE0DaAJGTjp3BPdqz+mOn8b22Hls90fnce4p8cTZZc4wgxxmH1XyBAizgRsIEkBGxsaizCgdBYW8bWDJEiUphGQZhI0iVb+KFbCoW3wQ32MB6n5+mLTWxVylhtDVyAtqhGrhlZAlMA1Wo0TqaCOVXBFBgLQgUWx1uLlLYE0THBiCZw9DcRJ2qhAQYXbcrVK0bbAdWDEHJraB2giRTvAfh/nzoJhzddbyqPvcxnPASZ4lAfCbkKyJ9BcbsBXzxJ0WrmM7BHaDjayIhHNwZQisNihYEBIhZ0GjCofG3Xy0eQvd5QMZODzpijLxpGtX0A+rl8J9i2Fhi9vP7D/9bzh63J3ncbwPxHZ3GL0iuTlnuQq846SBBCNTMDYNc1vdcU/WzGXj+CCkspArQCoDzY1vyFvEw8PDAwCZCFFWnfe6e+9bxb33nfj5yFaFQkocPR8buq5/Q9O0bwI/BWRN00Rd11+ZldIITM18BUDTtFeS48aB1SeZap05BtACDJ90fPsra09h+3z2+tz5nH8qPHF2mWNSo8AkNfIUmSTFAFEWAyAgIiEhV0uUCSJOWxBzkCoOqlmi2uijJPjRlW7WTR9ga90yEv4GClIDidGDNCcWcbysYlmSm92OAI021UKQYHMRNVyhlAnxuaNFsrMtmsdC/MnfKRwpgFUGuwRiFWQLFs53+OS9VY4uyrFNrrJotUx8IMLCBj+LVkocKBk8FqgQqIq8Vw0SEEQawrCgGQ6Ouv3DKgbcuUrgrx6UqAoC9Ktg4za9rcf9zOSDxiab+XGReQr8YSccrsDTGZBkWBiEDTHYmoHKSU5u04aWGVFoWK7QeuV7UYC5zaAoboVmuQi5NIz0uqHM21ZCLAGGCYIC33gBUlVY2gQ+Cb7xczg0ARXbnd9ZLLtC8wYNVi6GhjpoPPV0KQ8PD4+LhkmBDAcvgp1uIHpO52qa9kGgX9f1F3Cv2BLwa+BjwLc1TVsI1HRdNzVNMzVNW6Treg/wEeBZ3OKBr2ia9r91XS8Anwe+PmP+i8CHNE0LA7cC//N0ti/k+Wqa1o8rBEdwReCwruudZ1pzScTZKSovdgD/hPsvsgJ8XNf1kdMs97iItNHBQVQc/NTRQIn8b+4rsgWFA4wGBon2TFL2KQTkMrYoosgWkVyOEaGJ2Zv6aR06SqGtlayY4MVQA9NFkeEGBacGEjWEnIO8qIawxMYYD2AZMmZOpjalUHIsPvuoTA0be54Nu3EdyFmwBZEaFvt2mXxJqmA958eJRwi3mkSjZUaKRbZMh0l3ZAktq/H3DvRVI/y5vw5RhPvXuQ1hs2XorIc/+xWkjzswLLgFzc244iwAjDgInQZaqMzacIJpA74/4FZtisB9c2Bp0g1tzm+BfWPQn3Zd/QsbYHWb69V65CAEZv6yyibc1g2hmZCj3wcdLSAVISC4jruAAvNbHXZOOTzbA74I7HxK5IZ22NTn9jtz0iCq0PMrWLrI9cK9fAzuWAMb3mID0HM5+MUv3ZYn777ZC8d6eLxVcBCwkc5+4jnYOQ8eB76hadp/ZaYnN/DPwD/MCLci8OmZc78I/KOmaQHgCG61ZlXTtP8EPKppmgM8pOv6DgBN03ZqmvYc7mX8P+u6XtE07e9PY/tCeA74b7qu79M0bQluaPaMvOni7DSVF48B/0fX9Z9omnYl8IfAl97svV2OqPi4mls5xDYERGazAACbCuNsppcEAXk3Qb+DE7bRxnWwREy/iB23WVrbQ3FJiEpPjFUHHuPB2Z+jRJ4hZy5GyodPKTH/hh5C4SIDA3MxgyLpaT+qUyHsFMnrCWTLRm4v4eR81BoceLeD8wMByirUWbDCwalKVPQAQlJCKFlk+nzkgyoRXwVbqqEg05VwKGGzVyhhkURCQJFhzZwTz/f5Xe5gdyqCW9Cs4sZLDzpgCzh+ga3Hg4yW3AKA4wKsT7o9z/ZkYF4c/ikDwyY0zIMPChCSoD0GkggbOqEtBntnHPZddbB3HJ59BuqCcEc3fPROkAX41XPw7o2waD38yy6HJ/Y7lIuQLwsQtHm44FCOCTgVERw3ry1vw2QK/t0iyJWgd/StJ8527IZ9PWBb0L0AFp6h4MHDw+N3B5kwMVZcsJ0pJKrneK6u69OculryE6c4dxDXA/ba48/ietFee/x/4FZjnnyseirbF8hcXdf3zdjfr2la19kWvOni7DSVF6PAMk3TfgEs5tVJeh5vMFHqWTvzfhZmPtEIqFSJ4zCEz8rjVFUamaB1dBI7aYPiUM2qTE1EkEMmk5+OcOCHV3Bw0E+PfwHkZGi1SCxOE43micaz1KwhMk4S/6oCtf1BipkwidA0U1P1KIEqtaAPpa5KuD1H9K9zVJ71MTbZAUHRbf4VFnEkEAwQFAfbFKm2gpATcYoyx9I16usNFgsWkmOB8Ntv7/qQzVhKdIVZGciaMFmDoJvqyssShQmb+R+QMfwShRq8MA0rwrAkDkeqMGBApwrHa+4Ugg7/qx9jTtK92TZ882U3j6wpDNkKfHs7/MFV8OkPuDeAzXuhNO7ezJIAPpDiBtUAOFUJIjMuNgPsKkyXoFyCYhW00wxH/11mVpsb4vWFoL7uUu/Gw8PjXDEpkKb3ItiZj5vke9mQ1zTtPcAvcCtFS2dbcMlyzl5TebED+O/ALcAs3H4k58XExATvfe97X3Xsvvvu47777jvNCo+TEV7jZna9aHczyDMU5WNEnRHCUyXsgIDtQFXyk60ksPwq/uN5tPpj/MPaP+TX/+taiMgwGxgXmc7XkYwniDenCc/OERMyYEBDfhhjU5hKVGb8rlYGU134KjXMjIqZlDHaFOK3p8ltSVAaiSEEbbcuuSzghAUEycHxOwhliJbStLaNELAN3mcM84CpAxIE7wTfolc9rz+9VeCB/26BI7mO7LEq2AY4M1WbFROiMmM/K3LnH0c5nIexEozXYHMK9pegFoG05S4PnaEfY6YCQ1m3oAHcas3+NAxmIDHTgPb4CPziBXBKAk4WVzDKIDebmGERsShh48CoACEQLLB16OkErRPeseRivPpvLloXfOkP3OKIYPBS78bDw+NcuURhzbcDHwO+itt8di/w4bMtuGTi7DWVF78HbJjp8BuZOXbT+dhrbGzkoYceegN2evniJ0aruZDh2ssUn64gzLWwowJ2xcE3bRAnR1VRUOJl7L4a89I9PJa73Z3KUQOwMUUf5k6ZufN1JuU6EsODxH54hOtTe8gmmnjsjjuR4w5lXwjGbbJCAjlqEPQXSQhpsmunqe3xgyEitVgIhRq2qmALIuQgXMmxpHMf1ZKf+eURGpum2aQ0sqpWZXbxX0H6HMgnJmVc0Szh31Ci8nAAcjbUim4js2oMzKgr2tI2+47brN8Md1wLWxRoDkBAgoEitKtQH4TrQ9A1ky9l43CcKgkkkiiAWwjgOG6F6SsVnDZu+PMVCmUQRfAJAhFVoGK7hQFmv0pgThUnoOBMiFSLYOegJQONDtx7DayYD33jsHj2W2/eZvTccoE9PDx+h5AJkWDZBdtJI7j/Ii4fVgAfOqkC9KxcipyzU1VeVOE3MyEkOI/2wR5vGNtHdnLAOYQvGKP2wTvJ6s8hD/cQGHUQVppQVyI/KVA1HWo7fHT5dLfNvS1BAcS4zcLGHr4w7+usmXyJluEBtvxMpHFPnmBjgkqwDp9cJVZJ0RwZJhDLkzAj+H15orUcasihJTJKaKFJOluHWQJlvoGcrOGzBSafSSCOO9AmUK4FCWBRNgWSgsB2n48my4evshXCd/3mOdkRgaX+IC+vNOApB3wqOEkwVSjYcNSAUQft5joKWfj1NrDmQdnvjliKqRCx4UOvGQs3QJUfM0kzKh+jCYB4AFa1wvYRiPmgaLgTC+YmT6zraIZYCDJ5SAgQaYJ0GZINCp9ZpfD9J2EsCMW5QA3a6uC+q6CzCyZz8OAWaIi5xz08PDzeSAyKTHHsItiZC4QvfENvHW4D/kbTtCeA753UKPe0XIrP26eqvHgJ+BdN04SZY39xCfblcRKZ48fpfe4x0u0qoXiFrq5Gmtb9NSNf/Qvax3dCTSLTYTPS51A7DqnBANF6nY6WHfT3rYf5Dmq4ysdb/4kVDbsI+iuoUYFFa00KUxJtWzII2WFa1w5TDIcRZ9Ww69ppNXvJhpoQylWq0/CJwLfwH5jFo/Ovwz+riZZYPQVLpd8Q2Le6RP55P5Yt0dI8Ttqu4/FDS6hTTK7oOIwlhME60TewbML/Pwh3rpXJDMgc6aqA6oOBOIyY7kDLkIKySiK+wI/WDpkabB6HXQaoItSL8PnXFEDbDiQEmQ78zEGhTAEJGRU/71kEzRHonwllXjPHrc58hWgIPnEHbD4Arc3w7AvQ4YP/+GFYrsF4LzzhuDlsExlYHodpH3x7F8yNw6dugbYkHh4eHm8CAs5FmK3JZRbW1HX9c5qmScDNwFc1TWvQdX31mdZcioKA01VebHyTt+JxBmr5PM3Hyjh1UZxagM7GW9n37R/QlmmiaPuw9vqoHKwwfdTCrIiEohbZI4f5yLxP81z8frZMfoLm68dpnTuEmLQYUNoYaG7Bl0nTGdWRKyaJgUnm7TjMoNZBWg4Qy41RmZK4fu83KA7kUbf2sXjRKM3LVhPKd/BS4xiNy5axsL6Jdsmms8Okv9liVqaD68zneWpyNaFQkelKkMxkC8FkP/hOFMVUbDBsN0TZUg+ZTpXJHRUwFJinuln+94gYMbcT4SoVHAPCBjSFIFWGiQIcHgWfCckk/DQDWQs0n8wdiQjD0lZ2kQGgg8W0SfPYMAc2nOb3PJqC7/3arbysGVCW3X0emYZHJbjzVuiahO0Tbs+37voTYdGjaRhsPL04y1dhyxCsa4O4/9TneHh4eJwrCiGSLL1gO3kcjIuwn7cKM6Ol3o3bey0JfP9sa95imSoebxbJBQto715O4sgo2nvuoDQwilkuMy7PZn6iifEGg/Auk0TNZloSGU2liWJy9dAU3ZFeNnY/wrcmv8W2Y+vwRcvUDIlUJkGvej25RRJ/fuxrRPqKLHnsAP5FZfLtJbIruphonM90MElHZByxOsbxHodcag9zrUdJTF7PeG4/0TvbaZNF7idEu6yiBIr0j1XZYxk0GSIjpsh8uwhY4L8CB4eyJXC0CKIEmyeg2uiwqCSyqytILmS73fU6cD/QVaEQdviJItA1AeX50BW06Ju26ZsU+NvtErYg0LkCNi4BMwu/yMCu+CC3zinQFkxiY9HHfmI0ECZ+yt9xzXCFmQDMmelrHVVhKue24kg0QliGj2gwzwePVVwv3WQaokFXcB2agivaT/0ajhbgyWPQGrn04qxsQd6ExtOMovLw8Pjdp0aRSfovgp0OIHThG3rrsBd4AreX2p5zWeCJM49TIvt8LLr//t/8HG5upjw1hb+5itxikXr2WXYYIEfHKL1kUJyCagDUoEjTkjj7k3FS32zj+w0fwvgbmUpaYtvANVQDAbK+KPtu2ch/0z/PVKSewkiQii1gGCIBo0DLxBDZcZWVbRK+bhV5wKJwfAfxhndhHRwickecfbZFH7BUsFgmhelofB/XlbbzYirMfH8/19YNQ+SjjEkFfpbZw0/GGjmSawM7wJxYmoDPYF57gK3phNuoTJXcEU4G7l9F3mHM75DoNknOMXmoaGCVFSzVwYzLZDI+ju2EUtGNjB7dATtjKlvqOvjQ1XtZ0mGiEMSggoPzW9WwAMfGIVeGOQ0njjU3urf+SbjDBwtn0jLqZ6oad+gwkoKgD7q7YOkZRjbNS8KXroSG13ENLJVs+vpMZFmgq0tGkl5/GMKw4C/3ufUXH+6EdYnXbcrDw+OSImB7Yc3Xw7JTTRnQNO2buq5/6lQLPHHmcU4ooRDae99Lja0cI0rwSpOGiRQdyx16hoEo1AyRbDJAoDVE5dZuos+nye1Mcmi4m3w+hBFSCfsKDE20syOwnl8qt/OO0NPo13ZwtHMJdUOjLH78WWoFg+Z2kVnqHIY6G5m4wWRVqI+CuomtjbdTMitEBZG0YLHXhk2OzCflZta33s7QWIErWg1CCZUMP+Hn+RTfG7uJfMUhIQ2gF+ZhKxZLxT56qy00zrUZztdjlyV32KXEzEgnByPkcEgVUB0HcJAsB9OxmJ5WsUZtkEU2HQW5CcxeaNQUsj6RzUfiNLceRpKnQTA4wIMESDKX614l0tIFOJ3mkSWYPjGsga4EtERg+xF3e1Nld5/r2k7/mgmC21/tfCkUbP7xH/NMT1s4DixZonL//SFE8fVdUHsm4LkBt1vJjY2AJ848PN6SKASp58L795QxuaB5SG8xzjD+6bS/TE+ceZwXDvUcox+hoY35V49SPKJSaQpQWNVKWo3gL1cYuXsNk82NLP3ubtr+6yQ7BlbiBATKcoixTCvlWhgEh0fW3c3x2+dihFQks0b30Ze5a3onx7o0Ni+7DmfXr5AbZfZ3biBQraM/MItA/QH8+w9iHFU5tvEe1GQTI45JxBS4uRhk72iEuggsbNuE4Rxma/4KalSwSz58lg0jAlkzTrh7BDPrZ04ixrDmgI5bIyziqh/VgRGovShQa1GR4gLOLgnbVAHJHYUrAgEwpx1Y6DCxqxEn5CAuq7LLrCdvzKJDLSHIeSxq2JhInKgGiIfd4tZTYVqQPElYKRJ8fCW0BOBXh2BxC9y78oRHDWD/Ifj5ExAMwL13uAUGr4dDh2pMT1vMmaPgOA49PTXGxvy0tr6+y0XSD2tkcGTY+AbOAK0ZUKq61a/CZffB3MPjjadGiQmGLoKddsBrcngmPHHmcV7kKZMijBFpwVm0hvBUlqEWhTRhxJJJ8/Iw+1o6SCXaKJphVv/JoyzJ7eDftn2Q3qFuDMkHKsh6BfnqCoVAhISYQVDhV9qdNHUa5DoizJEHcVbJ1EkFGhsLbBfWUmelqeBjnbKVfD7KtrFlTEWitEp+tlHl3no/f/JOkcYIgIiETBEfqlBBlE1y2ThWTUKs2lRlH/5gEUmP0Rx3mNKq1IZkqIqoio1kCZSHBPA78KyIs0rAqXNAFxEKNpJaw2zwgx+wBFeoWQJlM0Jvdg3jTwnkUhLlOQn+36sDBKQgR1MKEdX1gAF0Nbm5Y5kixE8KPebKEFBhwWu8YkEF3rfUvdk2jI9DRQK/H0ol+PHDUJ+Echl+8gh84XUOIBFm+rO9guNcmNiZlYD/cr0bOfYrZz//9TCZge/8EvJFWNIJ798I0oX3yvTw8HgVXljzzcITZx7njI3FcQ7gJ0BONNgfWc7ixCGqH5tPbVJACklMLXJIxevIkmB+sZcdTSuIxbO8t+7H1A5LHOmdR2FfAnGdSUaL0o5IthZHlg0CSplH1tzK8sxeTFkGycGRBMJOiYxko0g1JDtLda5CmzjM3cGf8J1SA0ZEw0CkhEPHTOWi46whyCjNYYFd6VZyNYV8PoaUtKgPjaNYUN21lDWKSv1uh6Oag9FoUToEdywU+EHaHe1Jv+B60XwCzpACBQGhaMIxAYKGq5hkB1RovB3WdeTZfdDHsC0gEMLsU+ltmE1TC3x7p3v6n1/tdu3YvtsNS24bcnPMJNEdnB7wwQMbwX+Gbn9PPw3PPAPt7fDZz7qFArbtNqO1VKieYXDd2cRWd7dKS0uNvj4Dx4GVK1Wami5M6URfU5CQdxwkIHiRXFwvH4JyFWY3wb7jcM0yaG84+zoPD49zRyFII4vOfuJZGMLAwjn7iW9/TnsB9MSZxzmTJ0UFG4cQRRFqjsqhBRrR4RrHV6+gEpU5ovipESJiZ7gr/RCKT0IxBQREnmlPcahOQVpUxd9eJU+M0XIzc/x9CBYUhRBaUy/FZpkBdT5WTUB2LCbkJuaZRygoQVSnhiEr7GtYTMQoclvlQZ4Kf4HZgo/ISf/oBcGPX7iHm4N5dtXnqQoihmwQlMrMn1Wg+Nw6/KMJOlod5giwcVKgWoPH8jZH4wKtjRZFRSRXEKEe7L0SZATIgl1VsGUHggLEgAAohgMjFj3+OOmsRKIiECjIpMZFnmiC338AYn5oCLohytEx17sV8MNffBF29sLotJvkP6/FFWapAvx4G6SLcNtKWDbrxGsxPu5+nZwE04RwCG66Dp7a5OarfeDOU7+GB47Ag0/BZ+6HutPkfgWDIp/6VJiBAQtFgY4O+XXnm72WKhbfreV5NGUQHAnwpW4/awMXfhmKhqBSg2zRncYQ9KpCPTwuOjVKjDF6Eey0AIEL39BbDE3T2nRdHz7p0F+d7tzXdVXUNE08nzEEHm8PLAwsTAaZTc05ioSJUa9SrA/js0sIAwK+ahF/bIwN8mZ8YQvTV0feVgnkanxKfpaeum6yiShOFCrVCHppAelAHTgwN3qIoFhEkRwSTJNSkkTNAkuqB2g1hnhZXA0CBKplKlaAoF0hqJRQBLjWlkm+9CxMj8Gqa6HZVTI3yWG2+G12txfwSVVUJOpqnZRbwog7LCYmHGIxgWIRJiYdGjtEerY7mF0Cc2bZ6HMMyvtUnJGZggEZN4TpE9zPPLIDEQfDEklHJIovQmCFTa3fxjctoQiQGnYrJr+8wRUOogBNDa6YSsQgFICXn4GJSXjXmhMes8f3wVgWkiH4yUugNZ4QHcjqAAYAACAASURBVLfdBs3NoGmgzpx/3ZWwdrkbzvOdRpyEg9DaePZxT36/yPz5FyN88Wp+aA/yI3uMoX9toTIBxdUKD90joVygB219NxQrMDgJt10BSW88lIfHG8DFma15uYU1NU1bC/wjENY07X5gia7r39N1/bHTrTkvcaZpWhfwLaBd07Q7gdm6rv/yQjbt8dYhQAQRkbxZwSdYyIKBjYhCjbmDR4g8PEzcybKk9TgkwTGhqI0z4G8jPJnjphd+xfrWF/mr9R/gEfFd2JJMVQwwVa5HUQ0EW2BI6SQuZAiZeUSrwtrJrcTMIjVT4RrxRfqis+m351BvpnFEid7IBm4QwtxzeD9seRLCURg6Bh/9MigqEhafjxzl+dIUOwoLsM1m4sjctApaNYnNmy2O99nE6wRqosJkwSYccKhuEfjAhxx+MNvmpR7cFhuOA6bgFg6EABz8TpHahB8nbmEERKzFkutN6wRxGsLH4agN3/shvO89EJrJLZNluOX6E7/bjRthehrCJ1dXOm41pyi4359MIgE33vjqY6YFwxnXMzen6dSvYX0C7nu3WzRwKbCwCTkVLFNGdiwc59ShDduBZ6ZgZwbmBOGOZvCf4X+CIsPNa9+gTXt4eACgEqSJhRdsZ5QqFS4r/85XgVuBB4F9wN8B3zvTgvP1nH0D+H3g28AA8L8AT5xdJgSI0OLMp83YzqDsJyJZiDgo1IiMT6G2GXQHhsi/UKTvmEC6qY7AUpH4BpvSiEh2X57EMZ0PDe9i3ydWMlhrQfBXqJkqMSVLwp9GcCyyRLBEmVAtz2bxWrpTPcyzj5I8btOc7uWFd89iqGEFoujnbmklV0kJfLWK6zIKx2BqzE3eUiDHIXLiNtaEwywNDlBn30tCiiALQFjkHe8U6XsYBrKw5wDceJ1AQrAYK8Dyosw1SxXed9REn7ThsAiiDVHR/cupmFTMAELIQY1XMIdkrKCfoiohNQkIC6AqwF2tcPAw7NgN155mVMCqlb997KalMFVww5p3rjl7qO7Hz8P+mf6Qt6yBaxe/+v6DOvzw5+6g9Q/fDXNnn+874ML5gDCbgiyQfGAKc7iRL3TLp/SaHSrAUxPQ5oddWYgrcNMZerp5eHi88VQpMUrfRbDTiFtNddkQ0HV9TNM0R9f12swopzNyvuIsquv6gZkHyM+MJPC4jJgrrEI0HmGTNMiEHULCxAacmEzkmRSB2UUGni9gXNmG1Raj3JPFvqodea6PybEk/RMLeGlvB7fd8yxbg/MZoANZNWgOjCCKDgYqCJBFxW+VqUkKff65zN8GDblGnPIYt/zCj/V7NxAS56EKMXdji9fCwBGYHIHr7gC/6xoyyCGiohDDFEeJiBVkIr95Pi/sgmIZOttg1w7oOSjQNUsmJEBFhaAK7/fL/GvRpj9kQ6EGsuLmm1kCQsBGStlIZQup5lAa9UFRxOoXSc6G8DoYPQjNYTcv7FRUKrD3gJvEv3ihOxYKoD4Cf3DTq88tFNxiANuGd74TojPhu3IVegbcSQNTWXhmN1zd7QqxV9i2G0JBV7e+tPvSiLOgIPNFpZN0k4PczKvyBE+maLoeQ78EYQlStTd5ox4eHqfAq9Z8nWzTNO3vgaimaV8Cdp1twfmKq6Mzhn2apt0DF2GOg8dbCgmZrtAf0WJ8jcPVYXoKGSoBATVmEA+WkQ4W8EUcItMF8i11mIJEoOhQbZB58c83kNseZku+G/lph7aNw8RDOYrhAI7kFhgEhMpvHivvD1OfncSfL/B8LEZDOkNCDaNORPGVFiBETogsgmG4+7cbLcfopsBRyowRphMfrx5EKUluCM1xoHuJO2A8GoQDs+DLAxByoDsOsxeITI5DyVTBsaEKKBJKtkK8cRp8EtPjDRAV3PtqNqWlIrfVQToDt10HK5b99u/TNOGf/xX6B91qzU2b4XOfhPipJz7xxBOwY4cruioV+MAH3OM+BVrrYEsPHB6E9jg8tAnuvO5EZeasVtjRA6YIV19xHi/6G0DiLAUG88Kut2yg7Iq0K73h7h4elxyVAM0suGA7Y5SpXl5hzS/gztV0gCngb8+24HzF2aeALwMjuJ1tP3me6z3eDkhx/OLvMXvXPbQO6jj5LCkngqyGeOnhGg1NEBrM0FQ0YXkz4WKWbQuuZKiulUJHhIFqB2P7mlB7bVoahlkW3okqGWSEKLYAChYCDpYkEaiU8ZfLWP4q/ekDDF97G3N2ge80uUqvRSVBB/diUUEmjPCaT33XroL+URgYg7VL4J53wvPH4MGXoTIFogr+IixcBY1HBXpKIseRqEy5is6xBcwphZyYwMpIbpJYHJiCuuMQTcKSq2HD2ld7sV5hahoGh6Gzw/25b8C9rTiNOKvV3Hw1SXp1uwxRhA9fD7t6YMMC6GyEHYfg+tUQj8AeHX7dAyMm5IHnRmBlGeyZ6cPx37EE+rgCn++E8ar7ffIMbUU8PDzeHKqUGb4ITWhN6oDLqqTa0XX9u5qmCcBS3MzlypkWnJc403W9CPzH178/j7cLotBMun81UakPYiKCWaN5/Xp8v1RIb+plThzWtBYQGeJXG7oYFFsJldKkChHEVJmGWaMEjlUZF9oZO9rK7O7jBIUyRcLUZt6WIQoU1QCKL0q73sOOoo+mcJaptTU2hOxzLsQWURE59X/3WAQ+dy8YJqgzDVL/erPblkGOglWFrVnIORBYZ3P1FTWaXlCY6JMZOOpQGPCTmvDDXE5ca1QgCoUyNDvw0bWuVwxcT9n+/TAyAp2dEE+4TWNLpf/L3nuH2XWV9/6ftfc+vcyZ3pt0VEa9WrIl9yJjg7GxHVwwEAMxAYckkEuSm3tz80vCA1ySPCSBQCChGv8AY+PeZMtNlmRZVi+WdDS9lzNzetvl/rFGSJY10oxG2JK1P89znlPmrHXW2TPnzLvfd73frxSTtUx5PRHr1snnm6bs2DwevweWzYQj3XCwQwZxRzs/n9oMZUVQWQE9R2AoCtv2w4aN8ue3XAPLT9ij9n7j02CGvXHCxuYcwi5rniGPhMPhTyGlM+YhD8A1pxpwyq++cDh8gHf2iQnkvyATKSiQjkQi0zfasjkvqbzsq+x9wENOP8zMq5bib7ifmdc/QIfxGHu3vIxBgbA3SyaVJhHXMEcUUgkHoUSMsUApXitO8VA/imFSGegnXl+MS+RxkKOAk9LBYbTBAu3BWvZcsxB1ZYZUXRGrCocoUh5hGfe8ww7pTDjcC+VBaaV0lBEB6hB4opDvg2wRFFTw5qFjWEUzFIQTKpoF+pAgqwG9puzSDCI7O1XIHIKfjkFTCJY1wLe/DZs2QTwuuzKzBZjbIiuyW7dBdRXcchPMDk+83pISuPfeiX++fK4MxAwTmmugvR/mNspmgmwewuUQjcEty+HAHplVUxR4ffu5F5zZ2NicWzjxUMHsac8zSIo8xllY0XlDPTJ2WhWJRFaHw+G3TjfglMFZJBJpOf5+OBz+LvAk8BxwHXDjma/V5nwnUFPD6r/4GpZloYx75dRddRUj+/YRjcbZ9Pbb7NsXI9u7h8A31pJxBWjoP8hh/0q0vigVDz9BvVrg0o+0UjtmEDHnM1heiceZwlAEah8cqFhIR1UjIWMMKqEnWcvgQDnZsq00Og5SIc783MAw4PE34KLZcOlxgcmH58LbUci0g74dhBsGHeDrVlhZr6D7IZiWHYXhRtiXAiulQMyEKOASeBVB7LDFQdXir44I4lFBrBXyqoVumPhd4NEE+j7BF74omDcfBnohk5re76StD9YsklmykRhsOyiDs5oq+OHjMoN3/y1w1ULIRuE36+Weu/owfPsFaCqGrg4YisFli+DqZeeWT2W0AL8agOECXBqCK04ipDuagK5BaYEVrju31m9jcz6TJ0M3/WdhpiKYoJrxAeVNYAvwuXA4fDEweroBUy0aLIpEIl8cv/1sOBz+mymOt/mAIRTlHQnqkpYWZt95J/0HDyI8XhTVTe6VAZo/91903HAZ7tIiVonniW/pxVNsMq/sIL5Xu6mu0ChPDRDV6+kvq6RPqSZSO5OEz08m58WTy4HTxBEqkHYEOdRfxevlP+Sjnn9BOYkoYpoUBjoBiiZcu6rCfde/2ybpqyuhLwvrXZAchFonCBNUXeA8AAczUuKiLghWGuINMFQA/YiCpYMeg5xhYAwZZAKCtlZB3lKxvMh6pGqRyAsyOYuC2+LBgyrDKVDzsKcbli2DpSdpHpgMJQHYlYZivyyrlgahfQB2HIGbL4eRBHSPfy2MZUG4YDANHd1wbQX8x3poKYY5VfDCW9BcBTNrT/2a7yW/HYKhPJQ44NkRaHJD03h927IsnuyCv/sxxIag2Q1fuElwy2XvnCORhld2S0/TZTNhXtN7/jZsbM5LLATWWShJCsQFVdiMRCJ/fPR2OBz2AHedbsxUgzMjHA4vi0Qi28Ph8Ao4K8Vnmw8YtZdeStONNxLt7katrSXg0nD19OD+3sMUeWDJKg+7iqrwMIoWz2N2FwhszeFytZK6soKQM0a8NMhy8SZaweBh7TZGtSLZOqkINL9Ot7+ZztbdbHT+F2tnfPYdAVqeHNt4HQOD5VxC8BQBmv8kG9f8GvzgCkiugcK9EHTBnt3wLz+CPa9BoBbSDphdBC+2QmJMZtfctZDvAWcMMt0WmIKgS5BKmlgBFeaYEBjfJTBqorcqjOYsNr1sAAoUCw554fP/AD/4B1g8F/pHYOdhmFUHM+tO/h56++GZDRDww1WXQjQBBzthwQy4cim0DciOR4cmDdZHkzJruK8NlrTA4T3yOcYe6MyDpUKFJaVEns/A2iwsPEckicZ0CGjgVOR7yhzX8LUpB/+wEY7EQCuH3YPw42fgupXShQGkUO9P18NAFHxu2NsGn7leHl8bG5tT48JNGdM3rR0mcUGVNcPh8CdP8vDPTjVmqsHZHwM/CIfD5cAgdremzQSs+PznEZpGrKODsVCI/k3PMntBhkIO2g9n8H4iQPxgjrA/R90ikxIPRPsU9FgOpdognDhCnaOLrOkmFI/zb8H7GSpUItIGqkdHcxjsrlpJyYYHaJlxEeUcU3EVKGhoWFiokzh/6OyE2lqZSfvdHAICTsApJSu+8SC8eAjMDJRH4G+/DB3DUKFBLgCxNOhZGUA1VMGerCA+YGGNmrJDdAFQaskmahMpuRG2YJcFKQElFuQtjDrBdpfgn38CX7zD4hdP6+g6FJWq/OUnFUKBd6//wd9CLg9HOqRX5x0naKM1VUJFSGbQAG6+WL7X5hrYdkQ2GBgWbNkv3ai0BGR0CMwClw8OJ0y+rCrUTW9731nhymL4zaAsa1Y6ZObsKLtyYGVAK8g4Phkc99o87k8gnoL+KDSMC9rmdTjUbQdnNjaTIUeWToanPY+KHzHN/cLnGdXj1wqwevz67AVnkUjkAHDpGS3N5oLC4fWy+ktfIj0ygpHPM7B3Jwe/eTe1VaN0tys4DvUwOncWJYZOrq3Atu0GOQty/UcY+/My6it1LE3Biit0OBvQ0iYKBpm4h6GaChxWD/2FaiLhZXTrj1Gqzf9dR6YDBytZi4mJ6zQq1KmU1A770IegboJ/0Bt2wvYeqKiQ/o3pDMypk3uaCkthMA6DCami8bUvQk87PDNTpadb0N0JGU2wvVqQH1YAAywBcSAkwAC8FjgtSAvoAT0seG4rvPFyjrbOHC6RpWW+g/tvCxEKvDvY1HWZFVNVmRE7EY8L7rtB+k763FIPDeCu66BoK+x8ERL9MiB1aTA2AqYbSuphX3+BbG2KTtzUnQOK3ssCUOOEpAF1rndaOlWqMHs5dB2E6Bi4cnDPDfL9H8XrlvZWqax8PJ2D0okTqzY2NsdhITDOQsFMufDKmt88entcTuPF042ZqrfmjznB5S8SiZyid8zmQsdVmifHZmqqIdDwCLv/4wHE2GvoERPvWC9jl3jxO7NkUhmKZwkG/Q6SL4/w9meXoaV1anK9RPyzyPa7KZhONI+FwCRjunEUDA4zjx6zjTkM4uVYdOWY5GZTnw/uvhu83omfM5yCkBeiIzB4QMprPPwU3HkbvLELZlRBRQCKgtBYBQ5LtjXPa1FoagJvUKrcv/6WIDOgyB34LiBtyiyaQ8hPlWVBHsiBaZm0txVQLbAUGGjNMNjrpabChThhh/udt8Cjz0J5KVw5gT2U2wmzTtg75nWDtwiWzoTuXlkiTBXAYUI6AWtiMIrCpeWCBadzSj8OXZcyHr8vqiaQR5qfhT1B0P4QRD98shKumvfO57idcNdV8MuXpZPCslmwYvrNZzY2FwQu3FQzgXHvFIgSo4B+FlZ0fhAOh483n2uC09eGp/oV+v3xawW4BDiJI6CNjcQgSoqfcfTPzDPnMFd9+5uM7O+n49WX8Wz4F1of7KKmXiWfM0mPagyHgmRUP9FMJYcyM1hRshOzV+W29Y/iSOn0Vlbxws2XYwYUUv0emms7SalekmQ5RXx1Sk4VmAEsaJaaZAe3QT4Omgu+/2MZFN26DrbthdpKWHepDEoa6uHT98AbWyFYBFdeBten4d/CgvSoyv59FvGcRc8TGXTLAXEBPgGqBao8WpU+MLQ8ejqPMHV0TeXr/zdHOGzyp/e7qaw8dvbaWAd/+tnJv99sHnqj8vbhQZhVDR9dBa/vgt4UoEJVALxZqDdVPuspIjUEr+6TGbpViyYWrd22E377FCxfAh97D3u5O4fh5y8KTAsWBS3+dJ1Am8C9blYd/M875f4z1wXVMGZjMz1yZOk4faPhaXHiQZly+HFe86vjbkeB+083YKplzTeOu7s5HA6/PJXxNh98LCwMcqg4MenFooBGFQA63YyIfnbMb6Rv/t003H0tRd/8C176xhOoClhHBP6SHK5iA/WfNuHChf4xk6vffIk2bzMjpSVUGQPc+vIT7LsxTFljH0vT29CSyzGKXOhkUHG9ywVgusysglUL4YXnwBWD0mIYi0LvEFx/BVy0+N1jZs+SF5ANmq1HwJuGhAIfuUIwvFnQO1/lyY4U4IUBBbygOgXXNsAtlytU3efm//yfHJmMiuJ2M5bTeGWLQTSV5zv/131G2anRJPzoRXltAR1jMtNlZqClAVYUgTMIC6vBUYClzeAA/uNXx97LroPwxTulT+eJ7HtbJgB37oZbbnjvZCyGEzIh2VgGXSOCTB4C400A+TyksxDwHdtXqKrv3GNoY2Nzes5WWfNsdHyeT0QikSunOmaqZc0/OO5uMxeY/4LNqTEp0MUrJOjBSyk1zARMrHEPtQQqv8GFSQ63qbBej2J84WZmDA8w8MOtMKqT3RTFbQgql1SSyzlQHk5R0RxkJFCKcFqYCiwc3Im/rRd6R2jevgN1qc6WxV4Slo/6/lHKM0uYv+Q6hNd/6gVPgngGvv8KjOSgcTkcTENsFGa0wNqVk5vj0CBsbYcFFTBblzIct18BLxRcDA7AoUNZcnmVhlInn/pjlfmz4JqLwevxcd11Xp54Ose/fKdARakgrgn6hyz6h6Cu+nSv/G6eeBNSOWgYT6q3dsCubqirlObpZSb84A6oOC4ztvEtGcA11Mj7Hb3QPQBzmt89/7orwemExfPfW32xmZVQ5oeuEVjeDP7x7XEdPfDzR2W2sKIUPnWLdIWwsbGZOi7cVHIGXzwnMMYoOoWzsKLzg3A4PBP4IVAJ9AH3RSKRI6caM9Vz7+NFaUeBm6c43uYDTJJe4nThp4oUAySZgY9V5NkGQIQ1pHHhMjvZlguQVSEdqKTx/7uZq0udRH6zDZc/Q2b/KOqhBCAIuRVmjvUQmjNCrCyE7lApjQ0RPWTgHhlETeTI9g/gtDZiFlezXlvCwUM+vt77M2Z/9DPgmN75w6EBGMtAuBIaboRXG2FNNXzyevD7JjdHXgcxLv3g0mT2aeVKWDRXcMM6N0NDbmaFoXcMXn4TNu+EngH43O3gcglWrnDhD5oMDxo4nQoNM5wIIJGQTgNTCYJ6olBy/LqzUO+Ei+sBC1JjUHJCRszrkSVAkGs3zYnLgVWVcOfHJreWVFraSJUVT/5YTkSRF750vQw8i7zymFgW/OJx2cFaUSqP6fMb4fYPTe+1bGwuVLJkaaNj2vN4cKKdRJ/yA8z3gb+ORCJvhMPh5cB/AOtONWCqwdkDx0d74XA4DAxMeZk2H0gEKgKZQQMTFQ0P63BxCQAZLNLsYMwskFVHGPFWIhjhoNNJ4Y9voGlmORV6J4FIhMN78+RaLcqzWcgJKjoSBOv9UO5kQHXj+uZOcl6L4dlu6l0JgpEITbRRvrwXbVGSwv5t8HoOltwKoYYzfk+aIv/JA2gOmNUAd1wDxVMwCm8ug5AH2oZl6W1pPQTdIDyyA/Qov/0u1FfJfV0dvTA4AoMpaG03yKdy9PSYXHqtj7VLVf77v6R8xsIFcNutk9+AX1kEfaNQPt6h6PSAIwaVbhgZg8bKd8+1IAw7GqF13O945UJomObJ82gMvv//y85XtwvuuwPKSqY3p0OD0HFr13UZAJaOm8gHfLKL08bG5kwRWLa35pkQPLotLBKJvBUOh0+bv5/UV3o4HL4ZWcL8+3A4/L/HH1aA/4VUcLKxwU8NZSxkjFaKmUsRMwBQCJA2oUlkWC9UVCsLxHCbcaKaj5jupnXExFFdyUHPLG6sSXF1fQcjWh2jO7M4YjF8HoHDHyKWq4JN/VTMmYuS6KK+NcFwcw0Ov9wNMfPNIyQbPKSDaYh1wtbvw+J7oLLl1IufgJZqaCqDjhHI5KG5WGqBbd0DvYOwYj74QvC9DTIrtWo23LVCBnVHCbjhtpXwZjc0BOCi+pNnuxprINIpJR7cLtjaCpsOwm9+kKLniIkrZ9C9P0Wkyo3fL5sGduyERQth3rx3z3c8iQRs2gLNfugfg/ZB+fjMZrhyHhxqh7wFa1tkZux4bTCnEz59C/QPQzYHR/rg1Z3QWA9vdsK6ebBtGOr8MOckdkon42AbJFPQWAtdfbD3EFyxenJjJ4vDAQtmw+6DEPTDWBzWLj+7r2FjcyHhxkUFNdOeJ87IBVXWBEbG46jHkbaXpxWLm2zmrBKoArwcK21agG3fZPM7BApVrKCKFe94fGsaHk9AQHWzvHgG+3gDA50SbZDZDDOUL2egUMFsK4Jq5DlcPIeGgQJNmVJqmuNk0rPQUxouMiiZeVQ21lK85mpykUdg7xZywolTyYIqyDsc5PIOTM8YI44ApVoIDj0N5XPeGXFYpqw1ngaXAz6zRgZnP14PPb3wj78ENQlBH7y+G145BK17oJCBx0sg/mW4/7jSWbIAD7ZDSodOC1ZOcNJ423Xw0lZIpuGyFfDQFqgphlzcQjjBygmGhkyyWSnbIYQslRYm8R23/kVprq6o8LnPQsqU4xvLpUvCD5+E1j54ZpvsXl3VIjOGR4NIVZUdqT95Cg51yQCuoQ8SDmiPwyMRaAzCVycZ/AR9slSaSMkM4ETdn9Pl1nVQWQaDwzBrLSyzzd1tbM4YKWRkNwScAZ8BvgX8PbCLSQj4Tyo4i0Qi/wlS5ywSiXROZ4U2Fx6vpqFUgwFdcE2uimvYx7OODCZHSAkPYd8RNtesxj2SYXX2DUKZGEpJlITw4DHLCWVU9HQMw/JQdfGNDD+8hcLYKEpwFcKxnYCZYMxXSgENt5ajz1/J29kWlLRGWaCaP4lvRdWz4BzfTJV6FHJvge9OcJ0m5YQsl1UEAAsqQ7D9EFRqslz2/A5oPQSJDFgeSEXhe//17uAsY0CparHjkMXTvXD5akEo9M4vKL8PPnKl9Ih8+eU4B7YWGFZ8zLnEwxsv5lGKVZZeKrjsMtiwQQZOJaUwEoXXNsLSJXIPGshy3jMbZHZq3RVQXCzPprweKAtB8wlJ9YFRqCqRhuev74fnd4FuwsVz4drFxzobB6JQHpIBlWZAzaXwZB6umwULptB/0RKGG6+A/UfgQ5fDormTHzsVnE646uLfz9w2NhcaWXIM0jXteYIoOC6gAC0SifQBn5jKmMmWNf85Eol8BfjPcDh8ogjtDVN5QZsLj/kuGaC5BdQ4FCqMMi6x1vOiFURY8kysyd9GtKqI4VQRiiuLy6sxFCjQGvSx/FA/wXQlg7PLOFD0NKOfmEnTS0nmWrUU3fEJirb+lFxPN/3BMp654jp2Fy2iPDRMhT7ESwkHFf1u7oq9DeXL5ILyu6RjuX5wUsEZQNALNyyHLQfhnqth336IdMlAxwBMTQYCWR2i8XeOrfTAqmKTf/q1idYKL7ih9YDgS19SUNV3f0F1duZ5/vkYcyud7Gkb5eLVpTSFfMyos0jnVHDC/V+AwSH43n/CI09YjI3m8boMvvJnGjfeqPHqGwrb90i5i188Al++D5qbZMYtcJLdDh9dAw+/Cjkd2odhdo1MNL68RzYxXDluxP7hNfDrF+W+tLUr4Oc5yFnQVA4zp9B7IQRcdpG82NjYnB9YcJYyZxcW4XD4VmSl8Xc2K5FI5JT/fCZb1vzW+PXnz2xpNhcy1/thkRt8CoRUsNQ7caTfpljpZ1Arw5cbJHk4yIDLS//Sciq1AeZxEJ8Zp8rZz65lpdRZvZh56FKLOVAX4OE/XMKVh4b58FsqlWuvJ9X1KkmC7KlfSAsHqXN0M+CrYHVwIwdoJDnwBv6jwZnvbii8De4J5PQnYM08eQG4egmMxODfHoaRNGzZBLkoYMF1tx8bk83Cth15vvmVFG+95UMIiyMVCitXwooVMHMm1NSArls8+aROa6vJ3LmyNdLtEpS7dZrLDYaHXFSUQ3cfFHQ55rWNsHWnRUckxuhIAUyde++FG25wcvMfhNBUFadTlj0VBZoaJ35vC2fA/CZ46HW5p8w5bntXWQR72o8FZ/NnwN/Uy3KqpsHdWRgyoMUWc7Wx+cDjwUUZFad/4mlIMYhB/iys6Lzh74DrI5FIz2QHTLas2T9+86JIJPLQ0cfHdc+m31dr84FGCKg9zuNWKEXEEn9LFz+npngH2YxAbcrjKHFg+0FbtwAAIABJREFUoCEs6KGSYs3NLA6jiiC6sEg7RnhR/xT79bmYBSeXDG1mvzvDQKAUZ8UM6MhRNjZCXXEPUaOEfq0KZ65AbUkXo4nV/K7q5gzLyxTJ6zCagmIfODWoKIEbVstsE07oHIOLFsJ/f+nYmMeeg2/9q04k4sLjtTB0GBw02bJF5ZlnZND0R38EqZTJ5s0GlZWCTZsUli3zs3t3ioULPay70k0iB4fbZUfjxcugKwUPbIEDQwVyDrcUKBuJk8uZPPGEitdrsObacvqHBdW18PCLcMli8HilNEjWJb1Bax2gWHIdiiL1wXLHuarkCsc6O393+I77XS54/+02T8voqPwbDIXe75XY2JzfZMjTy6Tjiwkpxpqkwd4Hhr7xy6SZbFnz60AIuDkcDh9VulWQJui/nsoL2tgAFLlK6N3xRUZW/ALTdYSCW8XCQsdBSngpIoafBDmcBEmSNj18O/9ntOrNOCyd/nQ5T3nWEEr8moLPR3koSDyq0O+spNQ3wqBSDnlw63lwQ19ZKS56qEAaTFpYU7LeTWbhhxtgJAGlAfjcVTKQuWSh9NMcicvSZ9MJEhOhIotC3kJVBU7NwjQskkmFkhJoahL09MChQzBjhlxLPG7h8cDNNxdz++3HtCU+dauUnfC4IaHDv+6CnU7I+xSI5SAmdeEAdN1kx44c93w6x/5+N+ufg9EEqEFYuAp6PTBqQEm1tGiqfBsWF8On74DGRvj1LhjLQsAhA7brlsJYGoYSUui1eJqaZO8lm7bAU88AAm65CVYsm/ocugkHhmB2qSzx2thcqJy9sqYx/cWcw4TD4e/xzuqtA9gWDoe3Ih2ViUQiXzjVHJP9qvk1EATmc8wjygL+cSoLtrE5SkMImlwans5SuufsR1VUTBQEkCTACFmKiaLlC5SKMQbNcjr1RnxWklQsSLbNT8Qxl1/O+jhX515g5liBjTespcvRhJUTzHEcwmMaKB4LpyOM5TI5wFtYpMmygwIxvDRSyWWonD790zoIQ3G5t6p9CNoGYeG4fFptubycjOsuF0TvL/CNr+t0dXkxDEFZmUVLi2B0VJY9KypgxgyFj39co7vbYuVKFYfjWOBYKMjMz/F2SQJwey0Up8AwLNl9qipgSDeG0VFY/3KeQ6NudAtMJ/SmYWQI3JVg5CF6GPIpWZ7c0w+JTUAtBOaCLwPX18q9Zzrwry9AwQBNhc+uhbppapK9V7ywAaqrwDDgxZfOLDgbTMFjB+GuhTBjklIhNjYfRDy4CI/b8U2HDP2Y5M7Cis5ZfjndCSZb1twxfvOy6b6gjQ3IjMwnlsEDb12P66BJYe5mwqNHiLuCmDmFAV8FdWYPi8xuUEHoFkUixmChglzWhcuRo9w3SE+0lg2zrqQ/dDHVwQSLC20MJkMcMhbjSUG4OE2DMocdfQ6SIsMb+a0EzWIurXGBs4MhNlHFVaddb9AjpSWG4lJItmiSLutCwO23FVFWmuT557MoioNbb3Vjmio7d8rA6NAhyGR0HA6TRYsUqquPnZnu2Q+/eQwQ8PFbYN4cKHLCDQ6dt7oLRL0a0SI3pByQzx49uqRSCi+8YKE1m1hOAc4CpqoxJICoieGwEKbAXaSQsxRGHFCeg0AOal2wqgGW1YBXg8d2yPfRUAqDcdjSCredJ8FZTTW0d8jf2bw5ZzhHAL64EkLnQQnXxub3SYY8XVOrzp2UMgofaO/HSCTyymSeFw6Hn4hEIh852c+m6q35NuBEpuUUIBeJRM5M3dPmgqfEC/ev0egcu4mh4Q/hbP8evrZf0NpYSteKRazIHgSXB6eSxSWSzC0cJqoXExdBFAxySReWZVFWNITpzRKzVMpdfi5y1LHNSJANlHFAiXM420Mh18wes4ohfQ6FpIvaoWH+cXGUOc7J7Z9oKoe718LBXphTAw1lk3+fmia49toA11577LFsFjZulOKw69cXeO01HeEsUF1j8b//0s3ll7swTXj4cWm0blnw8GMw76tQKFi8+liej7QILqoz2NYBu7cHsfoFmYQOqLS0uHE4FAxHBs/F+ykNjeG1Aux5ewGGU0BUxfIKMgFAgbxL8EJS0JSAPgXco7AtBldVgM8F2YJcQyYv758vfPw2eH2zPBlYMw1JjWLP2VuTjc35iixrTl8C40Lr1jwFE/4nmeoOivXA08BzwHWALaNhMy0UBZpKoAkHVN1PcvEaTM8WGkQMU6/Cny1gaj6EpfCx1k42OS5hrL8En5mkNDRMScswgUCSlOnBi0mOHB0YqEqArIBgspi3sxateh0ZXx5DqAS9cXIF2Fw4QqVz5qTXuqBeXs4Gw8MQi0F9Pbz5ZoGBUY2icoXDPQbf+m6OpUs1AgHZbZnLy8DINR4U5XKQz4PPJ5jhg+ZKi9kulXC4lKefNnA6Tfn8GRoDq/pxlEUZTgTwzElSpIwRPVIGXSqMAGNAwIRFCrrLojWnkK2DuQYs9cLz/fCJepg9CocHYGYFXD775O+pUJACukWBd+r9vp8EAnD9de/3KmxsPhh4cTH7LBif5+jDJHv6J37wmTBOnWpwtiQSifzJ+O1nw+Gw7RBgc/YQCj7vEkJkGOJZFM9KVDQscwiHNpsZznXMGdWIORMUXBYxv4+isiFSpofUaACFNFmHQSIexeUJ0EiOxdFHEMY8ImIuutuBgwKqaWAYCkOigjHG0Mmg8d6mRvz+8UxUZvyzKQSKqaMXMuzdafD1r+usXOnijo95+e1TsnXh9o/KjJthQn29Qne3SUmJYMc+gTvgpKxGozmsM3eWRSwjeLwAY9vAtVggGg00ly49mroEvA30j58BuwR4LfALzLiJVqMQyUNNCg6PwKMGfGUVOJWJg67RGPzoN/K6qRbuuflYMGljY/PBIE2eNvpP/8TTUEl+Ejt9L2ymGpyZ4XB4WSQS2R4Oh1fAWXFAtbH5HQKVCtYSYi4DyqPkfQUE9RTzUSoWVhF6No3W14+7OUHD3B6cOZkl0gp5oqM+FCuAI1rBgWg5yegY5bPn0lDupNnoY7eoRtctjLxKS2g/86xWGrMJCq5BNHEKEbDfA6EQ3HEHPPywoLzcyew5eYaiebKxAh7N5KGH8mzalONrX1P4yhdl4NjWCd/8HuQLgrkzXMwL5dm5zyKha8SHVP72HwWlRSqtbSYFj0U/gmiiirKSPvwNcXRFIZtS4JkCxFXIabLNxwG0A80WKIKhFARV2DIEeQXeHoBHDsgN8ROxbY9sGG2ogSOd8jJv1ntwIG1sbN4zZFlTPSvz2ACncICfanB2H/DDcDhcBgwBn53OqmxsJsJJGTXcRYExNIJ0pv081QOvHHCR8Acpy2VxGHliXSE8RSmyuoe331xIvCdIuTdNKOQgFjJ4bXcLX1y6jQ81p/i+x8cOo5uGkt20qG1cTZwifRgnm8D9+wvOCjoMj0tt+I47XVywQBqWW5ZGJGLx9W9mePUVg9GohdMJO3YY/OhHKdaulcHZY+vB55FekfuPCD5/t4vGWfC334DtmwwyORMNQV5XcFeAOSwoJDS2f2clrsdzGJfqFLYPQlceTAfgAcUHIU1qa+RU8BrwIZXegwbpoTwVxYJguZMNYwp/ME92a54MtwuSGYgl5Rev8wITMbKxuRDw4mTOWejWLNCNZZc1ASaU0zhlcBYOh5/h3UFucvwC8M/Y+85sfk+oeFHxsjcOP+6x2JHRGVDB1JzEk34KWReqw6CAm0SqiESmiLzloafPTSZvELAaKKkN8u2RufztxaV8W3HTh5vR3HOE9N04lBB+ZRmqFT3tWgZGwO2U+6mmQjYP/70eeqNS9PUz10L1cZ2OR8uEc+Y4uHSNi+efzeBygccjyOVMenrMY8dDkVVJAMZNyRVg++Y8sREdNJXePqhqNKg1nIxVCEY7QS8oZHd5YccQEAWKkC4iOUhZMOZCWQNm0g17TcSGAsMvxRgeMohkLd4qd9B0TYhfzVP5UAuUnCTwSmShvR92HoTr18LMBhiLwStvQDwB82fD0gXHjNRtbGzOP9IU6GVg2vPUUHiPN5K8v4TD4T8HvgwcFaS0IpHIvOOUMN7F6TJntl2TzftKwYRHB+CQadDj0SmrV+k94mY4W8rBjXOoXNiPnlSJjQVx5LIYSQ3ddBBtF/QKk7qKIrIZiydGcywsdVODhxrlBixrCGF6wMqAc8kp1zAyBv/6IIQC8D8+NbUAo20AekagqQL6R+GNg3DzBF2D69a5+e53VVpbdbJZcDoFV1xxLNV28zr42W+gqxcuWQ71NfDWDiikTRwaOJwGFiaFjIKKxfVrBI+0W/R2Hl2whjzXyoMaBVFAOEMolQW02R5y/RaMKSQfS8KoKdNkBcgNFejenuaZ1gCborDQhGX1sHKWPBa9Q7BxJ1y7Vr5KVz+0dsEjT0vjda8H9h6UjQ0XL5/8sbOxsTm3sMuaZ8yngJmRSGTSnlWnDM4ikYhtzWTzvmCSwWCAzpybWKGKQ3kD01DwNlnUugU9fQ66Dsxg1Cqjam43Y5FShBD4m2PE20KYhsboCMRT4FYE0RTkSi08CHDMQyifA6MVRDVoC065Fq8bGqqhonjqmR+PU278T2UhnYfgKdT16+o0/v3fS/jOd5IkEiYLFjj5+Md9DA9DWZkMxv7yC7JM6nHD2Bhs2QgChXxWxTR1ykrBLRR81YKVYaj/KPx7DwwNGeTiDsALFMAsoPg0UFRUYUBegC7ANKQdgG6CpYGhABaOlE6tB17dCUY5tPVAwAs+U2fXfoPRIYXGag0hBEJAew+MxaFRGjLgdsGmt44FZ6Yp9cdKis8dW6VcTh7T4mK7LGtjczK8OGk5C96aOjkgM/0FnT90Inf3np3gzMbm/cBglFb+ie1mhKjqpy+/jqHhK0i5vZB3UOS38M630McsPKE0hayDQtyFYsoSoLs0Q3osQD4rxuezcAqB8/i9l2pYXiaBxw2fv+3M3ktTJXzkIth6CFbPgTWnUQVcs8bF/PkOUikLy1L4yU8E6TR85CNw8cVStFYb/9Ru2wYODe79tMavH8qRSSk0NcA996j84b0ClxNe0QTt18Phwwpbd6rEByuBPFhgCgdqkYowTXK/VsEyEIW0PKs1TDBygAK6QDNg4zMG+/bCoFdQ6VXo2pxm20tR0ukCzoCL/p4gcxf7qauE6jIZlB5F14+tG6T22BNPyaDzy196589+30Tj8KsN0rj+mhWwer7Um/vBD6SzQnk5fPaz4DuPbKpsbN4L0hToZHja8zRQYJI63h8U6oBD4XB4DzJxaEUikVNuCbODM5tzjo7YL3km28pIqB7D0qA+xrVVT+I0DPbn57FnYCkuwOUx0MwCmmaieEzMAiiOYylzpxsCfpPhNFzicfJGh2A4BbPKYE7Ze6fFdUmLvEyWUEghFIJ9+yCZhKIi2L9fBmfHY40blrfMVfjzP3UzMmLxV38FRUUKhiGzU5ddCpUVglhC5ds/8bDhCQeDg1lABYcTI2NiZBVIG4AODn28f+joURSAwnCXyfC/J0BAwi0YavSyq28Eo1BAUQVaOsO+gxqf+bSXq1cqaCo018ORDnA4wNDhk8cFuKY5XiIxec95chMMRKE0CI+/DjNqoKddas81N0NbG7S2wsJTdKfa2FyIWIB1Vrw1LzhumeoAOzizObfQC+z+7x8ydt0KKs1+Xslfw4ijiIzTz4zRVi5ybsS00gzEl+FpHCHR7cdVO0r53D6ibeWgCwqjDhTVpLZRJ23ARSUqh9928kYa3Bps6oSLG+Cj897vNwvxeAFdtygudiBOqJk2N0NTMwwNwRVXvHvsihWwYwd0dYFlCe6+W1BUBC+9BBs2yGzULbfAokXSW3LOZoXuiAPNpRFNWBgOC59PMJYCNahgpB1YAx4wg4AB6hia5kBXNUAF0w2KgHSWxOEsYOLxChSHk3zASY/h5NldBtetEjgcgk/dJveapdLQ3AB1x2lXrr1EWiuVlU4+azacgXgOGoKgTeP/QyorS9VOh7yfL0ixWsuCkRH5WDB45vPb2HxQ8eFkHhMYCU8BizTStfeCYcrxqB2c2ZxTmGNDxJ4ZosF1kHzeguVp3DPdmBkNn8gwJ3mYYREkO1zLxct2YObSDO4pZ6Q2BCUWsb3FNPgLLJ9RRkulE6MgWF0t2NwLjeN7m0wLtnbD2iYofR9z65s2jfLUU4NYFqxYEeTmm6tQlGMBmtcLn79v4vHFxXD//TA4KIOL0lKZ9XnuOWhokKXEX/9a3g6FYOUcg93bTfIFhUZF5fCIid+rkHFY5MW4I5vmlfYDKGCF0J05MFX5PaopYADCJa+tUjLptNxYNwhKXLBtQ54H/Tqf/KSbeEKwYxeMjAIm1FYd27OnqjBrclVlAAZS8B+7IG/ARVVwyzQ01K6/CH72HMRSsCQMNWWgVMDtt8Phw9DSAo3vreydjc15QYoCbYxMe55mClxguwZ+CzQBe4GFQCuw4lQD7ODM5tzCG8Q3Av4H3qR7/gwWd/yWl/7iC9QUBlhmbifvd7BqYBsL93dy06otuP1R2mO1jB0I8rz3ExRfu5OyoIv8WB2eoYu560rY1gdt/XC4Q5ayFtQDFiRz719wlkrpPP30EDU1LlRV8OabcZYvD9HYOHGDeaFgMTRk4HQKyspkx5TXC01Nx56TTMrA5/i9ackk7Npl8LV/0OnvVxDCYPkqi9ZBjcoyyPstSnwWe3ea4FHBVMASYI5HUl4h7zuBIR2EBpYha8hGAPJp0AVW3qRjs8HhFgfxuMXPHxIkUxAMwJPrZZasZQLrp9MxnIGcDhVeiIyd2RxHaa6Br94FmRwUB44FjMuXy4uNjc3Jkd2adlnzDOgAPhyJRPrC4XA18N3TDbCDM5tzCsXrZ/at9zL4879n1p4DNNW1csOudt6sXU3a7aYqM8C8A7tILWmheH8bmZCPuS3DWLFRGjIPs6PsWjweaKwqcMVFUFBMtu3OsXfQwewilY5BQUaH5iqo9L9/79M0wbIsFEWgKLLD0TQn/spKJk1++tMkfX0Gpmlx5ZVurr323ZFlba3sNOzrk6XM4mK5wf23j1qYppSzSKcE7W0WFT6oL4ciQzBsqpTUQdREBl9JwC1A94AqKA9rDLWb45vELIQmsAzGN6EIhHCBaTI4qNDfD6oqGB6BxnEvUrcLBoaOBWepLBzuhxL/5EzkZ4YgXAw9Cbj1DAO84/G45MXGxmby+HCwYGKv7kkjiAOF6S/o/KEqEon0ARwXoJ0SOzizOedoue9PMLc+gzW8gzJfhrLeCLNS7eg+L66sIFFRQUeZgncA9GINrZDA6yunPBBg6YyPkGCUIspRgaeJsieh4qnQ6Um7CaoOuqPw19eBU4XBqAwcTiVxcSIWFvsYZZAMCymh/AzkFAMBjUsvLeHVV6MIAXPn+qmvn9ht7vXXs/T3GzQ0aBiGxUsv5ViwwEl19Ts/wiUlcN99sHWrDNKOdniWlCiMjJjk8hZeH5iGxp0fg+oaKCqBVw8Ibr9C4dEnTN7YK8CU+9As4UAoCrW1KTRFoW9Yh5yKZShgmQg1jWJoKIqJgYWq5slm/Xg8cp9Zexf4fTIobKw7ts6fbYSOISms+8fXQF3pqY+XW4PP2hv0bWzeV1LoRDi9aPfpCKPzPp4bvx90h8PhPwMeA24G+k43wA7ObM45HGVlzP2XBxn+6TfIdT1FolvD6dBxCB/u8MV0+BpxRg+TqVmGN9qKWwQo9q6EubcDATwck/EfJE9zpYd83KKyOos/6mDVDHDp8JXvyM3qpUG4aD58ZM3kNqf3kWEzA3jQ6CPNnYRRJrZIm5Drry9n8eIAum5RU+NGVSeeY2zMxOORP1dVgaIcZ5p+AlVVcNNNx+4/8QS8+IJJRZncb7Z0hYLXrVBTCVdcarJ5S5beNoVETGPZco3huEV70sJMgYaguixDsi2KZjmom+lluC1NLq8QKjG5/Q/yPPiTLLmcG0WxaGx00t1t8sgjWe78mIeXNlq89HIer0tHwQk4ME3oG4W6EugagdGUDM4sy3YQsLE5l7HLmmfMvcBfA/8O7EaK0p4SOzizOSdxzwzj+rvvsvmXqwns30F5f47Zt3wMZqymxBGjNf4QuXgHnlEPM1kLVZdD+bvbL9cSIrF0lKzpprSviPmzLNYthS9+S9A/Ai4XoMCWvVBdCqtPrUcLHHOqtTiFa+0kqa6eOFt2PAsXOtmxI4+qQjZrEQgIqqomVuq2LOgdln6XDz2us+m1OIqw0ITKQLePK6+QchEvvJCntFSnXFUY7de55Q43+ZjGAScMDUK+oLNyboxYLEd3DHxVCW6+xqQtFmLewhA3rVVYMDvNA7+wSCUF1dUqc+cXWP8WLLnM5IVn4/zwZyamCT//WYInHy9mwQIXNy2HJ7bDnBoIV8JzrbCxC4rdcNd8qLrATqungmVZ4zIqdiRr897ix8EiSk7/xNOgMsoU9FjPeyKRSBL4m6mMsYMzm3OWZ5UYQ3dcj3t4NVd5m3D65X/sckpwBT9Nzh/HV1uKRxRPOMccvMxwuhEXCw7qBr/Vs3wtBXtLVBapDixTMDAKs2thx6HJBWdVeFhLFQNkWEDJGWXNpsq8eU7uvtvHW2/l8fkEV13lwes9+RlsWx88ulGarSsCdg3DsMdFg9ckOVigkLcIhUDXLTo7LYaH3ZgmeDwFzLRJIAA3flgwmIGOTqhWFBbMC7BpU0xKcoT9/I9bfLS1KfzmQRjNeMiWGPQpWToGY7wWc+Aqd5B73ODJ11RMjwPNIRjMqDzwiyTf+LqLFTNgxQy53kgUNrRDUxGMZuGht+FPTtnHdOEyNpblxz/eSTqd51OfWkJdna35YfPekUTnINPsyAHmoDNFm+LzknA4/GAkErkrHA4f4J3ikVYkEjmlmJMdnNmcs5SgMagUqKiownnCDoUgFVL/YBI4UEhYFg/rBUqFwK+BNUena7uKb0QlXAvRBHSNwSvbYfkcuU9qIgSCFoppYeKg8PfBwoUuFi585y724Tj8drM0Vm8og+Uz4FcvSR/Qxkr5nBuuEvygDdoyKjVFcO1NsGEv1JUIVq2yeO01KdQb6XHx5GaorDAoCav4ZkNVg4qZd5NPZli0KEAo5CAaVXl0fZJfveFl505It6UgqEO9BrM8OIQT2jPs2prDKHNS6NExLQtLVVEc7y5oZHVQhdx/FnTJAM3m5LS2jtLfn8DjcbBtW68dnNm8p1iIs+SteWFkfSORyF3j11OQIZfYwZnNOcs6ilmOn5Kz8GeatixMwC0Ebg/MrQOr22RuiUquAP+9DUQLPL4JPvwafO1eKQFxLpMvwE9ehGweKoLQOSTV71fOhqLjgkunW2XRIg+DIzrVlU4efF4lmpBa3+E6Jz1jKYb6fZBWMCzoTZqkhM6dazXmLVOIpoLcu9jL669n2L07j7/K5GtPKAwegZIrhii6Wmd4aymFSA4SCoXFYAadtA1rlDgVdA+YhkVRSKV21rHmia4EdCSh1CklTTpiUoPuw1PQP7vQqK8PEgy6yOUM5s+fvhiojc1U8KOxmOmb4ToYOgurOXcJh8OfPN1zIpHIz071czs4szln0RBUcXYcqEuEoEIIuk0DDcGCJsHigkrH2/DEXgtjiUFdEWTR2NQNW3fDNWvOyktPmyPt8OZOGSxetvpYVm8kAWOpY1IUXicMjILzhE/13gNQXqGgG0427bTIYP3O/3zna3HQspDzA6asg+qC2ECe1naLkrCDOZUK9fVOYrE0JSUam9oNBg/48YbTOKImTi1HwzUdHOmcBSNx2J7E6E2TVtzkHSV43RrLl2lcc7lCPCXPmLuT8P19Mr9vWnDPHBAm+JxQbyeDJqS83Mdf/MUlGIaF1+t4v5djc4GRRGc/sWnPMw+dD/jH/ESpjIuBUmADcAUwCNjBmY2NQwg+6XTxhq6TxWKJU6N2iQJLYMcDOrs8BiOKIJDSUAzI5t7vFUu6e+FHvwSfFzIZ6OyGP7pHemq6HGCZ0qNcVSA9vmbthKpDMAD9A9A3ADndAg9gIiOjQgKECpoJ+rj4rMNEcUF7u8l1Bty6VM4zb56Lh36TZN8ehxSozQq0YIFkR5CSyhHQVUgact7+DAYmhstJzuvhjS06dbVObrpWztWTktcNARmoDWbg8trf//H8IOBy2V/bNu8Pdrfm5IhEIt88/n44HN4AXBWJRArhcNgBPHe6OexPuc35QfIgZNohuBRck9trdiJ+Ibja8e5swz2LNbY9Z2G6FdwJmGnAkinvEPj90N0nY52y8Qapzh5IZ2T2rCQAly6Al3ZbaKognoSmSnCfkGxctghaO8DUoX0MSIMyLvJvmQHIDUghMXeR1LLwWlSVpFnR7GC408XAIGx9HfbscZMSUPAY4BJker24i/0IxaLn5VrIWvJbdziHvOGEAig5g3wO3A644XK5ptrx7F9nQmbOGs/xErKNjY0say6laNrzOOk/C6s5rwhGIpGjqrs6nL42bAdnNuc+uQHo+ZnM8MR3wIyvgpj+2dtRrl0o+KHi5Lk3wV8Mt10mPz1/+D9heAD+YB3c+bHJG3SfTUpC/4+9846Poz7z/3vK9qZd9S5b494rNgbbQEjikGAOAjGBQAi5g3CXXC9Jfskvd6/c7y5czd3lAoEkRxJCuxBCDx0biG0w7n0tWb1L23d2d8rvj5HBNrZlWZILzPv1GuQdzXznOys0+uzzPN/PA4XhSF46AwEfeIbdN7JZg20v5Nj4oobsgM/fJJMsdRNPCYSOWj/hclnO/IEAHOoQOHzYxNSANISLApQWafT2pYml+xFkqGgsYeEcB/PneYln4J13rQbr9Q0Crzd7cFVp0JPBLLgYfDts/Sx0AYp16C1AIgtIgAGGhJExyGVMXni0h92fLWLhQjc1frhzllVzVus/sThrT8AbrTC7zNpsbGzOLSl0dpIc8zhz0MdB4l1QPKMoyuPAU8BngOdHOsEWZzbnP0bByt9JPjA40QEEAAAgAElEQVRy1r/HUZwBrJhlbQAFDVbdCq0HwemB7+yDoBfWfnpcL3laTJkMn74C3ngbQn649iqrdybAf/xHjieeKFBVJZDLwQP35bn5y9CS94Dw/qIAzYCsCjnd5G9uUnn5ZejoczGr3uTmz4sEgxEKhQgOB0SKDe79lUhBF0nnRVwOq/+kKFqbZhpENydgRxwcfnBgNUQ3PDizEk6jCLFCwCfIGIaTnm4VK49aoLlJ4uabB9i1qxJRFKkNQO0pImaP7IZkDnb1wjcuBbvEysbm3GKnNc+MaDT6fxVFuRKYB9wTjUZfGOkcW5zZnP94aqD8asgchPClVk5uAuhOwuuHoW0QmmJQXWVFy/p6YdPWiRdnnf3Q1AkLpkB/n0lONaioELh0mcily4491jBMXn1Vo7wc8nkdt1vEMCT2bVO5/Q9dvLhVpKUbcgZsaocZFbDIm+Lgzgy1pfDlm300NnrIZqG+XsLrFcgXYE8TfOla2NdsidSlcyDggQ2b4PFNIDtMtPY84IOCDJoJZg4EAaffy7zVToqqyihPSGw/lKNvII9RkAAB0xRpb88yMGBQWjryA77SD30Zq9m5c+yr921sbMZIAJmF41DK7/loSg9teHtNURRPNBrNnurgj+Q7ZHMBEl5ubafAHBjAjA0hNExCkEb317w3Bfe8M+y3BVAPrS1QlLJqteaehRq0/30NdjXB3d/L8eJvsoiCzppPivzjP/ixakjfR9PA5dI4cKCAKBoYhkBtrRuXC8pDJn98nSX2+pJQ3ASXTYNtz2hEIhK6bvLSSzleeklEEKC8XOCOO9zsbxX4r0fgkvkm110Gbjc4HAIDcdDLYGUV5AsCmx400dABEesRYvVd8vskSitgfiXULRDZuMeBLDnJa7qlckWTvKHz7bsz3P2dIIETeMlpmkk6DcEgXD9TYHkNlPqs4JyNjc25JYnONtJjHmc++jgYclw4KIrydWA2MAtYD3wVuO1U59iPPJsPBWYyiXbfD9B/eh/Gay+P+vx3u6yWR+V+KPHDH3wGwjOgvAj+7Da49uqRxxgrF82AIofJi0+mKORMcqrISy+p/OxnH3RldToFLr1URNcNQELToLZWIxwWiUQs0VVdCvMnw9c/Bstq4corvaiqiWFAPu+gulqgoUGkt9egvd2grgKWzTR4/uEhlizp5uKL+9i4MUc8bTlslBVDTYXIxZ/0Yj06BDBVQCTgd7L2Y1CUUHnh+SzPvpxhyXKBuZe7EMtF8JtQJSAo5Ty7QeRHDxts3gp3/xD+9T7YfwjyeZP77tP53vcKPPOMjkOCSWHwn8RNJZWBDe9CS+cE/lBsbGzew0prCmPePmppTWBtNBq9CchGo9F3gSkjnWBHzmw+HBQKmDlrlaCZHH3BakE/NjpTUwo3fBK+sdLyDxsNhmHVZ42Wi2ZBX5vJDyUNU5IQZMs4t79fP+Hxt9ziY+vWHE1NGl6vSUWFk3XrfGRzAgXN6hJwNI2NLr75zRIEAe67L0dvr0EwCKYp4PMJhIMwcCjGE49nyOUAdNasGeDgoQq8LpG9rdbDec1nfMyvTrN9u05Xlwtdl5k2TSKbVWlrS+P2uGnvUKklxx23O/lWQab7kAMKJuruQVq1LN/YHWfdl4pZONeNrsPPfgWf+xS0tZnU1Ahs3Ghy1VUmwik6ob+wEX63Hbxu+Mbt4BofSzwbG5uTEEBiMWNvfOsdhy4DFxiioigRwFQUxQkjvwG2OLP5UCBEIkjrvgA9XYgLl4z6/Fll8GYrZAvgkq2VglOLRy/MXnsLXt4ARSH4wmehrGR058+YJqBMdXDoQA5MKAoJXHWV64THlpXJ/PjHJezcmcftFpkyRUaWRf79QUhm4WvroPi43IEsW2Lnhhuc/PrXeYaGTK691kFlpaUmd+7Mk88LWDLMJBaDluYsV1/i4+8fsbzVvn6jjLq6hCefjLN+fYLqahlZlvF6daZN05EcsHW7RvP+fja9HKKntRpSBqR7QUsBJvmUwM/+W0X4/XKWLfcxMCSgA5MmCTQ3G6xaJZ1SmIG1UEGSIBy0fN5sbGwmliQGWzhlqdRpsQjjLDe/O+f8HbABKAVeAL470gnnRJwpivK3wOXDL/9PNBp9fXi/G1gHPBCNRj+CkU+bsSBNmw7Tpp/RuZMj8Pk58NQBGMjA7FK4epRD9fbDC69BTRUMxeGpF+D2z49ujMZJAv/9X0Xc+6M0albn1pvdrFnjPuGx+bxBX1+BxkaZSMT6VdZ1K4KUK7y/qvNERCIit9/+wXHXrHHx6KMZCgUBEJGkPD6fSCQEU2tA0+Gh9RDwOvGGJObOdVNe7iCR0GlqyhAMQnW1SFdbH0qjk8oyJ+QE0POQU7E+MAqAAZrOq68m6Um5aKhxUBIRuP12CVW1FiiMxOrFMK3BEmnnwubExuajhomAPi6rNUfXW1NRlH/ActmXgX8FXgbuxxI7PcDvR6PRhKIos4H/wKq7eAv4ZjQaNRVF+RzwR1ifOv8zGo0+piiKABwZVwO+Fo1GdyuKEjrR2GO85c3AvUAA6yE4C3jmVCec9Ueaoig+oCMajV6qKEoAeBh4fdg199vAD21hZnMumFtpbaZV3z5qdB0QrJSmJFm9L8+E5UtFli89tSvr228n+da32mluzlNZ6eY736li9eoAkgR3ftbqGuA+ccDtlNxwQ4i9ewv813+l0XWTL33JydSpbkQR/nQtPLEJmrqgLwFar4RbM3nrrTTt7QU8HoG1a310dqoEgxILF/pxOEzcaZWsLIIpAjpHonLgYDAuMBgXqJ8EtVUAAl7v6c1VEKDKbi951lFVncHBPOXlLiQ7ZPmRIoDIUk7zF/QU+Ech8BRFuQqQo9Ho6uGU4KvAFcD90Wj0t8MWFX8H/AnwfeDmaDTaqSjK3wNrFUXZCNw+fI4JPKUoynrgYsCMRqOrFEWpxGqndGSsE409Fp4e3lpO94SzLs6i0Wga+NHwyxlASlEUEXgQaAQmK4ryZ9Fo1C7ztTknnIkwA6gog+WLYNO7ljD69MfGd15HGBwscO+9vezfX8Dvl2htVfnbv+1hxQofDoeIw2HZj50JDofId79bxne/a1l0OI/ysAj5oCJosDUKLqfIRQtc/MPfdNHVVcDlErnyyiDt7RKf+1wFlZUeduyI4/NpTKnMEG2qJqN7gBRHekd5Ax6mTJZYcYnEvDMLeNqcZXTd4P77m+joyLBwYZjrr68711OyOYskMdjMBxcojZalGERO//DnGG53FI1G84qiDAGTotHokX0vKoryp4qiTAL2HaUd/h34JyAM3BeNRvMAiqL8GFgDXAb8xfAYXYqiHFAUpQGYcvzYY71fQI1Go383mhPOWTJAUZSvAH8D/BXw51ipzGcURVmMFZb87GjG6+3t5Zprrjlm37p161i3bt04zdjmw0YfOj1oTMKBbxxC9YIAn/k4XH4JOB1wgk5R40ImY5DNGoiigNstkc8bZLMmiYRJcfH4Xcd5nLlYPK6z5cU+1EGRNdcEqS+GcFgiHHagaQZFRTLd3QW+//0hIhERw/CxfLkLkHjuuRz7DopoWghJKlBb52TmLC//fLcbUxKYZPfVvCDI5Qy6urL4fDLNzZlzPR2bs8yZpjXbHn6C9od/897raZ9eC27P8c3BT0g0GjUAYzjdeDfwQ+DO4w7TgXKg86jz+hRFKR7ef+CoYzuBS4FINBrtO25/xfBYx489Vp5SFOVVYO9R87vrVCecM3EWjUZ/qCjKj4BfYfWd+qfh/e8M156NirKyMp544onxnqbNh5QMBj8nQRqDSTi4eRyMFY/gG3vU/5SUlTmYMsXN9u05BgdzyLLI0qUhfL4zDPmdJr29BeIxnYhDx0jkKJnmo7hYprVVw+EQUFVobS2wYIGH+noHHR0CPp+bcNiJLA9QUWqA5GUo5qSkVOJf7/YyRZnQKduMM16vzHXX1bBjR5zVq+2eWh81gohchGfU51207kZYd+N7r0Mbt+MYjHed7vmKolwK3AV8OxqNHlQU5Q+PO0TCqg+rPOqcUmDw+P1A1fC+QUVRSqLRaP9x+4+v1h2PpaW3YEXxzt+0pqIoNwEt0Wj0Daz8hgTkFEVZEI1GtyqKYsfJbSYcDchj4kYgc45cd0xMorSSI890JiGf5q+j0ynyV39VRWWlh82bcyiKm5tuCuF2T2z9T329k0WLPAwN6SxZ4qOkROY736ngj/6oh/37c7S0xKmudpFOG6iqgaqahEIiiYRAdbVEPK5RXKyi5XQuucjNFOXYJfmJBHg8ExdxtBkfFi6MsHDhKJJSNh8a4hj8zsyNeZzlGJzuQnZFUSqA38eqJTsSxTqkKMrHotHoS4qiXA5Eo9Fos6IoMxVFqYhGo91YRq+/AX4H/I+iKL/Bqjm7DasGLYFVS/Z/FEUpB6YNj/GBscd8w9AKPHRU8/MROReRs+eBHw4X60nAz4FXgP8eLvbLYb2pNjYTRhCR6/DTTIEFjDpQOy5kUNlLEwYGZUQo4/Rzkl6vxB13lHDHHRM4wWFM02Tz5gQHDmRpbPTw2c+GEUUBwzB56SWTXbtyDA6qyDIkEnmKiqCqSmb1ah8LF3rYvFlD1wN0den09WkUFYksXhHi/90LVWVw/ScgHoMf/ABmzICbb574e7KxsTkDTAHTGIcPgeaoovyLgWXAy4qigBXdugP4kaIo3wR6h18D/DHw4HAd+ybg18OrNX8KvDR8zH8P15g9Dlw0nG7Ueb/o/1snGXss1AH7FUXZd2RHNBr91KlOOBcLAgaAG07wrSvP9lxsPtpMwckUzp1zqQc3DVSjkqPoDNKqqgp79sC8eae2zRgrO3akePzxfiIRmV270jidAosXB+nsNHnnnQLxeG44aiegaTo9PXm+9rUIkiTwq19lGRjQEASZK6+MUCiYfPJTMq9slykvhoMt8Ma7sGi6FTULnHqRqo2NzTkkiMAyzmAZ+AnGOV2i0eiRlY7H8wEdEY1Gd2Ktyjx+/8NYzhBH7zOxat6PPzZ2orHHyKg7M9vuQDY25wgRgblMPePzTdOy7zAnOCvb2ZnD57MK//N5k87OPGB1QggGJUxTIJsFwxAwDAft7QIbNxaoqBB59dUssZiGYcCf/VmQefPcJDMCL28DWbJsR3QdSkrg61//oMhUVXj8SejuhavXgNI4sfdqY2NzcuKYvGmcoUfQUVyCyUfJBScajZ52rdkRbJMaG5szIKvBuwOwsR/6T7Gy3DAgq06MgPJ4YMmSiTdgnTbNh6rqtLaqZDI606dbBcHFxZDNmni9QQoFD7peiiCU4HIF+f73c+zdm2fXLpWODh1B0Pn1r2M0N6uURuATl0D3AFSXwSWLrOucKPq3Yzds32UJuEcen9j7tLGxGQFTwNDFMW+jTGt+JLEjZzY2o0TV4f5D0JmxGoI7RfiDKVB53CKmWNzqGdnbD431cONacLs/ONZzfbA7BSEJ1lZA3egXQ00okyd7uPPOatrbc1RVOWlosCb48st5wmGTurog8biIYeQwDIHOTh/BoMFvX8vTeKmTKifUlAkkkwabNmWZMcPDqiWw6jS6bHk9lsCNx6Gy4tTHHu6ALbugOAwrFry/sKAw/EF/rAsNju+Zapomzc0aiYRBWZlEVZX9OLX5cBNE4GJx7KUgo0lrflSxnyY2NqMkmoTOLEwKgIFBZ9ZgQ6/EDfXHPnBe3wT9g1BXDQeaYdseWLbw2LGe7IFtCah2Q1qHH7fBHzdA5Dxr4l1X56au7n1lqWkmW7Zo1NZKDA3lME0HkuQATHRd5/BhE58mI1Y70LwmDYU85hmED2dOh3WfhcFBWLLw5Mf1DsCPf2X1/kxlIZ2Bq1bD3ig88rTlQXfTWlAaRj0FTBOefx3e3ALhkDVORSn89rdZXntNRZKsY264wcf8+WOvx7GxOV+JmyZvFLQxj7PKNLGNWE6Nnda0sRklhml1h4yRZDdNHBbb2Gk2keJYU8583ko5aoDqgNRxpRq6CTuSVqTMIUKRAzQT2sduwH1W0HXr/sJhDTDQNAFNEzEMg1w+T0hxggkDSZPeXivCdOmlvlFdQxRh0Xy48nIoGm7ibhiw9yCk0laLrOd/B/f9GvqGoKwYyovhUJt17NOvQDBgReCef/3M7vNQiyW0q8shl4fHnoWhIZ0NG1Tq62Xq6x1UVMg8+WT2jASojc0Fg53WPGvYkTMbm1EyyQ9uR45304N4RQ/oMkpJB+8QYxULEYZD9kuXwANdcEAFZzmobujrhU+EIeKwPhm5RMgb4B6utzJMK006keTz0DosXurrzizdJ8sCc+ZI7N2rcdFFTnbsiANuLNmaxe9zU9GqcsstHvQWFZ/hYuFCLw0NYw8JtnfBvQ/CVZeD6YTXtoBLhj3N4HVbtWufvMQ6tjQC0RZL0NVMO7Prqbn3+6X6vZBMW6lSQQBBEDAM63vxuEmhAM7zLOppYzNehASBFeNQ5Bo60x55HyFscWZjM0oCDrh+SopH+xO4dB9KOE6lX2KIBHkKuHCim/C9AY39jTpG2sBj5GjqdeN1uWlR4c4qKJLhM+XwSCfIAhRMULzQOIEdBnI5+OnPoLXdel1fC1/4vIkgmHg8o1OFn/yki64ug0OHBGRZQNezALjcEqKkYw5pzHXA7GvGr/sCQFU5fPF6aKiBp9+0en4Wh2DeTEtEJdLw2jtWZK+hFHraYPI0+NTlZ3a9yXVQXgItHVb68pqPQyQigiDz0KMasbTI7mYZveDgnoc0/uH/yPzBl4QP1Bfa2FzoxEyTDXljzONcbpqUj8N8PszY4szG5hT0o5HBoBwZ11FVAGVOmQVVQ0TQERDIU0BCxDH8K/VSpsCzZIi7TGbU7sBjqOgxB29vWUBVqIiXRPhsDcwPWlG0tiz4ZZjht1KcE8X+A9DSCpMarNfvvquyc9sgoZDJvHkerrsujCSN/KlW1022bMmRzRaQ5QKhkEBJiRNdFxmICYDBjv0ysfj434Msw/xZ1r+Xz4WN/2Py6nMGSRUapwpcslTEMOHen4JXh/pqaC6AfIZOil4P3PF5K2Ln80JlGaiqgC74CZdmWf+OA7KAAJlcgT//uk5Od/EXfyRgBwhsPlSYAqYxDqaKdlpzRGxxZmNzEraR4SWSCEAYic8RxjfcZi1CkAYqOUwnIiICsJAZiMMC7plCnmxKJiAOEJDTDGVDOMUCwaoW4vuKuL8f1t4MDtmqOTvZCs2YCgeGrH9Pi0BojPXmhQIIw+LPMEz27h5iyWKJ2lqRLVsyzJjhYc6ckZeLfvvbSX784xyCAC6XgdNpkEqB7LASm4GgiNMp4fZO7CMm7DXxJHWmVwu8sl1g4wYgb3LxxQK5JDi8UFcHra0Qi0H5GX5cd7uOXUyg6yDJIj0xHxTyw9W7AhgyWiHPY792snaNwFS7d6jNhw3dFlZnA1uc2dgch45GK3t4nShhgniYTicQJcc8rJyjgMAcFGooI4+GHw9+vKjkOEwHKUeCULiIfEzHNA1EDByOAk6c+CPQ1AuHumF6zcnn0ZqAn+wCzbAawjmb4ctzoHoMLvpKI/h9VlpT00wE0aC6WkYUrdRkJqOPOEY0qnH//Xl0XcLhEMhmBUIhHZdLxzBM1IJMoMjDxRe7USZPbAFdfz9IgkB7iwCGJQ737zcpKhIoqYDeNmhuhtJSCIfH77o+H6y6BH75KFidX0RLlZoAJroBHV3Y4gwrymoY4HDYf9QvdIoEgZWusf9OF9kh5RGxxZmNzXG0sINOopgkSNJMlt3oXIrI9GOOExCIEHrvdY48G9lOBpXFgo+DoTwHkkF6c6UUGQkKqQjewclkdKveLDNC/+Bnm8EjQ3i4dqk/C88fhtvnnPm9hUJw55dh+04QBJGZU7zs3p1GkgQ8HpEpU0YulDp0yEBDQCyRcGg68T4Rv9/J/PkC113nJVgkUxR20lAnUBQacbgxEQpBOm2SyUBdGPZ2C5QFYP8hWLIUbrwaivxWz87xLtS/8nJYdw3843+KmDkDTBGEPN5KAa9XYJotzOjqMnngAYNMBq69VmD+fNsg4EImZsD6zMjHjcQVBnbN2QjY4szG5ihMTPpoRUUnTJY+PBTI4mMPJVQBJ6/Wb6eHNFnChJjuglXZbhrLmnm9bwrR7HTkpA8pK+E0oMGpUxrR4RS9PTtTUHmU80TIBe2psd9jJAKXrbL+ra8oYt8+N5mMQWOji0hk5EfCpEkiZpWTZIlMskeDXIr29kGefNpJLCbxz//sZNq0s/PJuLxc4NprRb79bRMfJitmQkESKY7AXZ+DmhGMa8fKV/8QfrPdycF3cxRyGnK9g8olLr79OYGqyom99oXAhg0GhYLVnuupp0zmzz/XM7IZEyZgjMPvtu04MyK2OLOxOQoBARkXMTooxk8RJlkMygkSp5tKTv7XvotevFj1Wi5JZbZvG88OrSLtcWKmDBJ5g/USzElkufKiXbSEe8lRTyNzEE5gOTg1DE1xqBgWaH0ZmBEZ3/uVJIFZs06/JUF/v8ljj5ksnCLzRo+APqSjF4YwDZ18PsWzz3nw+WV++aCVKj2ebNaynTg6iqVhIo/CMTyTsRYFHBnjsstE/vEfTZ5+2rL48Hrh9tuh7DiXS9M0OXBAJ5k0mDHDgc839j8ylZVw418IDPa4kUzI+2FeLVw5d8xDfygoLhZIpUxU1ar9s7mwKZJg5Th0MCkahzUFH3ZscWZjcxyTWUCUA2RJISJSSjkOnEic2hBMQiKH5TRrkiSLg14xTKoriENTKS1JkkyFiEk5wuVuAoTppIkiSoejcseyZpJVc9aSsF5H3HBl/bjf7qh4+22dfB5u+JiDmbtyPNMOh5EwBWtxgGlKbHnHIJ02CQQEegcsx35k+PmDBhs2aKh5gytX6nz5yzKbSwboJscSwiymaMTr/24jPPOsVaB/2xehutrav2KFwIwZlnArLrb6jh7Ptm0aDz+sIopQU6Nx110ehHGofbllATywB/I6lLng6iljHvJDw6pVAh6P9XNZutSuM7rQiemwfhyi91fodlpzJGxxZmNzHGEquIiPs4etePAiY9VhVfH+R/88GVL04sBDYPgxU0slW9mDGxfgwSVqmHlQQvuoDHVhCCLoEG8vZ1tXKUurU0iCjMqJiziKPfAnC6E1adWa1wVBPsclO7oO2nD3llBIxOsVcLnKyKpJTFNGlly4gwJ7hgTeecFy13+lG/at18ntzYOaBXTe3uzmew9l8V4jMe0SF4NLYswpCh5jV3I8pgnPPW/12BwcsoTaZ697//uRiLWdjLY2HZ8PyspE2toskekah25LdUH4y8WQzFupZ6cdFXgPWRa4+GJblH1oMIGx25zZac3TwBZnNjYnoIEZ+Ciij25kZKqox4e1TFIjxwFeIsMQeTLk9DqezFQiEWKFp5IhuRsnTiLOKpaE3yXngMFcxPK8Sps0Vh1Cz4nkyGJgEOTkisIhQePIAaUJ5dAh+N//hZZOiEkSnc0a0Q6D2hKJpUtF/H6BfftCFHQDR61M4fNuvrRBwGgFpwrtRpJAZR+57UHIa0CB/IAKgwJZwcnWTg/7X/HysS/ARTNPPg9BgNoaaGq2RGLFKOvJFi50sHWrRmurwfLlDlyu8RMNbtnabGw+zBRJsHJ0HdhOOo7NqbEfJzY2J6GUSkr5YFW3SoIcSdL00WcmeSrv5Q1tBoKZ41UNvhsop4whyLRzm6ePn6fmkRFymKqIX4JqV5DKom5cQohJ5mwyuQh5AUrOw57Zqgq/+AXITmjqAz0rsPpjMu19JmuuhEWzJJ5/Ps/Lr+gc9DsZmirTOFNm/zboLkBshwEdHkSqwJOzPMH0YbsOU4DtGtkBB2q9m2teh//4G5NrrxKQTvLw/vyNsHWbZWUxb5R1XTU1En/+515U1aqFsrGxGR0xDdYnxj7OFZqd1hwJW5zZ2IwSFwFAJEWCvWY57UIJ1Z4oyZyXmBbm8cI2/j65mwoziOELcE1gF5vj1Wg+EY+hUeUJcUXJLGYZc3moDfYlLZ2yshg+OcGrC0eLqlrGtd4AiBKIMoiCQHm1QFGJ1Yx83ToPK9fCD5ogOmQ1b493QKIZ6AQ0AQMnBHUY0uC91OWwQOowMHMCQxXwyBMmtdUCyxadeD4+H1yy4szvx+8X8fvP7NzeXo3nn08gywJr1gQIh+3Hp81HkJGtEG3GAfvpYmMzShy4mcEa8jjIE8OLyoDuImmEKOhOdqvVPOfewhfzZXTtbmKbHMTQuqkuKTA9PIAj6KREmsqBBOxOwmQf6Cas74cFRVB+HvVkDAZh0iTYvx+0DGiAKljp1rqjPvomNEtqzYvAa02gJsHIYe30CNbXQUD2gpbHEmjD5q0IoBoIWZ28KtDde356Yf3yl0MkkzqaBtmswe23F5/rKdnYnFWKJFg5BhPso8exOTW2OLOxOQO8FDGd1bwtrscn6chCL9m8F7djEEyT35pL+ITwNE/456JVykhugWgB+rMmNya7EFyH0MxF7xlISMP6pTAexbbjSGenRmlpAVUVWbbcgVgkIjlh0TQoPaoWrtRpFexHPDDPDfEyiLWBLpngFixhlnRYtm6ayXDPA6y7FkGVEFIGLa0GRQE4Hx9NqZRBMChRKJgkk+fZD8rG5iwQ02D9OPTLtdOaI3P+PQFtbC4QHDiZg0xUKNCiiYTFBF6ypA0vquHlaU8puUoXbYHJuKUcslvnsL8RI3aAvyRD2BcHh8nOtIzH9DLVL1JxHkXNDh/WuO++NA6H1YInHs/xla/4CYc/GNkqdsHyYtjQDwXA6wC3F9IDgqXDUoBXsurNRDcYBlbUzAGmBrqKkTMJuuAH/6kyuS5AXd359Xj6vd8L8uijcSQJbrppHHtB2dhcSNifS84K59fTz8bmAsJPkAVcTCc9PFXwY5o6EQYwdLhU3km/5CHpDSNIIi7yyBikBR/tgTKaKCYlb2HxZJn2lJsSMci1ganI4oyCHUYAACAASURBVPmT0nvttRyBgEAkYs2ptVVjx448q1adWEF+qgIavPCmA959HUo9kHYJVs62ACCA5AK3w8qPGjroBkjgcibJJQy2b5E46BP5yl0F/unuEDNnusjo8HYcdiTBLcHyEMzyW6s3zyazZnn41rfcCIJl3mtj81GjSIKVwXEYp3fsY3zYscWZjc0YKKKEz0nFxHwpfprJopkuPu3s4k/T+/hvjxeOqq0wh//rEAzatEHqTIOIXEV1WGSATtKU4TmFrcZoMQxIp60i+jPRfJpmHnOeKApWwOskiALMDkGVBFsqwKVCd6uAqg8LGQcgGOASrMkZJgjgcmQxdQ1Mk2QKslmR/Qd0fvazBH/9zWJ+OSTSkbNSp0MF+HknXFkMHys59l4NE+QJrmWRZVuUjSexmGXVMnv2+HjO2UwsMQ3WD419HDutOTK2OLOxGSOyIPCHjgBfca9HLLxp7XR5mavGaPUlyJle8oKLPA5kXWdybgC3kEHW8yBXgGcZoiBgjGO+QNfhwQdh715obIRbbwXHqRscfIBly5z84hcZ0mmdzZvTtLYW2LkzwMCAxGc+4zjpH9OWfquX4ox6CHrgxbcgFQRzCBAFRB0M0QAyuF0Q8KdIJAwwdESHG1E0SSfzvP22zjtdBh2CSMMRx38JAjK8NgQXFUHvEDy6BaJdUOyE2TVW66TKs5B1VEmikqboFC29bE7NW2/B44/Dn/yJJdBsznNsE9qzhi3ObGzGA6PXEmZiHWCCs43Lxasp7biHVkx2uGew1zeHar2TBr0fpyfDYTlAea4NQ6tEdpThYCcJWnFzGU7G1oiwrw/27bNWWjY1QVfX6Hsbzp7t5MYbTb72tV42blLBdBCNSrzxRoZczs9NN504TCWL1lvg88CVK6G6AjZshOZ9oLcKiDJIThE1pVFTncLphEzGIJ83cEo5XC4IBk36+w36RAHvcVG/I4sntnTB/3sOsnnwOKEvB2IrRLvhro9DxRkKtE3vwr0PQD4PN/4efPyyEwtbERkHdrhnLCxdCn6/9QHC5vynSIaV42CKXTQI5Mc+zocZW5zZ2EwEpklg8B2mZlwI9ONJ7STV4efh7E08KEpUl7Tz+1WP4JTiFBtJ5rMEg1+g4yPLczi5Y0yXD4UsD7LmZggETt3W6FRkVJFNmzPkc+1YH3dLiMWqefHFwknF2eQycDkgkbUiZ7Omgq8IwlfDpbWWT1okLHPvvQZPPpkf7odpkM+LyLJIcbFJNmuyZImLumKJPf3Hjm+aVhnbs7sgl4caP7RsNdmx1eStXpOScqjwiNx19ehTkF3d8Cdft9LAPj98/z5IxOHG6z94rBMPTsahCzSwZ0+ObdtyNDY6WLrUPS49Py8ESkpg5cpzPQub0yWmwfqBsY9jpzVHxhZnNjbjgVAKjouh8Lvh1/OgsIuuUDWtWT/bY6Xs7Z7LoBBB12XigxH+NlbD9xv+ASUkEKSEBAEMEsgoAJiYdNPEAO2EKKWaaYicXlGVxwN33gkdHVBZyRkbr76ywSSfjwEZBNHENNrRtBTh8MKTnuNzwxdXwiMbobXfknRTq+H6i8D/3loCgbvvLue224p48800hgHbt+fZvLmAYQjU1zv57ncjhP3wyiAMFiDiAM2AQwmY6ofNMfA6oecA9DVBvNPEMCC5D/75Xwzu/LQ06lq7//kZtLVB0Ac5FeobYOceuHIASibI1qynR+PBB5P4/SLbtuUIhSSmT3dOzMVsbMaCndY8a9jizMZmPBAEcF4FjmWAALoA7MSBREE26MzU4pZUvHKGpBoEQyAi9vEuk3AJXSTU15jk+Bjlkh+ZKgDi9NDMVjz4aWMPEg6qmHLaUwoGrW0syJKI06mRUwVMZEBHENLU1VkLBk5WIF9fCn9+FfQlwClD5ATiUBQFZs1yM2uWpdhM06SpSSOTMWhokAkELCF6ezX8phdaMrCvFciA0w9eEdIaJAbAEK2Fn15ZQHOaJAYgnYXACfoAqip0doHTCdVVx6763L8XqsqgvRe6+mDBHCuKls2O7X08Fem0iWGYFBdLxOMGyaRtwW5zflLkgJXjsGapKMnwCm6bk2GLMxub8UIQQBheQigCweU0JF6hU+sjTIyNwnIkQQcDIp5+Plv5GMulraQHJvFCfip+x1bWFs9lurMWAJUMAiJOPGgUyDAO7o+j5MrVAg9Mr+HArgS6rgIyZeWVdHQkeeihPDfdFEIUTyzQJBEqRlGfIggCjY0fLO6qdsNddbCzD37WAkqVZda7JwaNTmgOgRmHkiDE+0x0w2TuPBHvCRw/Egm47wHo6YH9BwwqSk2++dcCdXVWiG3JYnjrbVBj4PPCwR6oqYGK4RxMKgUtLVZkctIk60duGCbbtuXp7dWpq5OZOXN0Ua/aWplp05xEowUqKyWmT7fr2GzOT2J5WN839nGuyNtpzZGwxZmNzUQRuQq3ZypzC6285ekg0+Qlk/HiEAvMr3iHeY6dZPQyfO528mIbOwr1uGO7aCxrxIGHEKXIOEgyAAiUUn/Wb2HhAol7/qOaf/9PN02HYjhlB7feEkaWTfbtyxOPG4TDZ6cXi0cChwiabmVFwkWwqgI2CnAgLRCYIdJXAtU18PO7T9w8fdM7EItDV6fB7p06W/LQ3qLxyMMu/H6RFSvhiRfA6YGMDm4/3HC9tSAgHod77rEEnmHA6tXwiU/AM89kefNNFa9X5NVXVa65xsvy5afvJuxwCNxyS5BUysDrFW27DpvzGzuwe1awxZmNzUQhCOCdSglTuSmboXNwP2+kAvgmdTE/1MwMZ4QWPUYuLzKUCNLV7ucN2WCpNsTyKg8eAszlCtLEcOPDS+ic3MbKS2VWXlpOf38x//Zvg5imiapaKU2X6+wJidogpGLwy3ett/b2S+H6JbBoErwzFfr7BabXwiVzwH2S4FNWBYcMg4MGomTi8wvE4wI9PQZ+v4huwOLFUF0JB5vg5uthxiTr3H37LIHW0GBZlaxfDytWmGzcqOL1SgwNQVGRxPr16qjEGVgp3mBwbCL34MEC69fnkSS4/HLXeddhwebCp8gBK0vHYRwVy4ja5qTYv702NhNMSxv85BdevDQyV+0husFJ76oS/j17NZHJhxjwhNm8aRGZQR8dzixXPSPz8U/28b1VLuoJ4sJ7rm8BgJISmbVrAzzzTApZhnXrAniP97kYZt8QRBNQ4obFpcP2GmNkXwe4C/DpmWAa0NQG8dmgVFrb6TB/DmzeArV1Irv3msiGyeJFBcrKrFTkjClQUwVdvTC1EWZNe/9cp5P3THgLBSua5nBYqc7Nm3VcLpFczmD16rPf5aG9XeOnP00TCokYBtx/f5qvftVPaandYdpm/IjlYX3P2Mex05ojY4szG5sJ5tU3wOuB2kiQ3N4AezYWqF64By3jZKh/Ot09AdK9PuTSPJmMJcR29bTyUNrNF32TqDhPxBnA0qUeFi+2WhidzO5hax88fAj8DqtgvzUFN4yDj9VgGjwOKB5+O1pzkFIhfIKi/5NRVwt33Aa79ois+bhJVYXB1Ck+AgFLUHm9cOcXIZmCgJ9jUqOzZsG0aZajvSjCDTeAyyWwcKGbt9/O4HBYFiDLl5/h0thhBgYMHnssz+CgweWXO1i27P06PNO0Fie4XMfO7dAhDUkS3ut7eviwTkeHboszm/HFZHzSmvZqzRGxxZmNzQRT0EAe/k0bHBRwG06a31jK4k+9xWBGRMp6cTpypAeCZCUn6VwAwy0woLYR91WdV+IMOOkCgCNs6rP6agadVkul7QNwdT24x/i0mVQKL+yCoTTkChBwQUng5Menc9CdBJcMHhN27gelHmprrM3qrfVB8SJJUHSCDLLTaXVaiMXA7baEHMBnPuNh/36RoSGD2lqJ5ctH2YrhOB5/PE9vr4HTKfDAAwVCIZGqKmv/E78R2L1HIpGQmDRF5M7fhxtvgGBQIJ83MU0T07QWKXg8AroOBw9BLgd1NRC2+7WPGV23xPlHxIruGIqcsLJsHMbpBNSxj/NhxhZnNjYTzLJF8Iv/tR7qHrfVWjLRWsOLv/gElYuaIDhE1uGlr6sEDAG5ooBUmSPk3U2J4QXxwnLp9MnQp0IQyBtWSnM80poNpXDrJbAxanUEuGKW9fVEbDwMz+y1Ik2mCQc3Q7UTigLwN3dA9xAM9kNDjbWw4HQRxQ8a+kYiAt/8povBQZOysrHX4cXjJoIgsH69xMGDOlu35iguUekYdLN9u9OyadGgr8dg7z6Rt9+Ff/uek9mzNfbt0zBNWLrUSWOjzCO/gh27rXl73PAHt0H5OPxxPZs89VQfO3emuPXWSqqrR1fLN968+SY8/7zlG/iFL0BV1Tmdzlknlof13WMfx05rjowtzmxsJpg5M+HWz8G2nVYd05orYPNWaNNCFNcu4PnWIYZqBAyXiZg08FwSR/W6MJ0l+NkBXFji7BO1cM8+eCdhZS9um3RicabrljeZcxSBpulV1nYqWofgN7ugpggcw4Gx3cDeHrgsAj9/Ef79weHifh/82zdh8fzTn8OJ8PkEfL7xCaVccYXMv/yLTnOzjsulEwg42HvYSXufAAHBaiBvAn2QTcBL62HffoGbbvLS328gilBcLNLVLbBrD0yqt6I8Xd2wcTOs/fSx19u2TWfbNpPSUrj8cgmP5/wKCW3fnqK3N0dbW+6cirPBQXj2WUuQJZPwxBNw113nbDrnBjutedawxZmNzVlg5jRrAygUDNZ+CjYdEnluJ0xGJe4w0T0igldEDJkMmWX4tD5Eh3JuJ34GuB3giIBTBacEr6kwfdjh/wi7W+GxjZYtxqUz4OPzxi9NtK3Dqk1zHJWx/NhlsPMQfGIVfPMeUJNQUgT9GfjJL2DROF5/rCxY4OArX5H4xjcKuFwCJoJ1M4JhPbHzWF/9QKKAVoDmFgfz5gqUlX0wTXvkvixPtmO/d/CgwUMPGRQXw4EDJokE3Hjj+fVn4YtfrKS9PceCBafIYZ8lMiq8uQUGBmHqZIP+foOSkvPr/ZpIipywsmIcxukGcmMf58PMR+f/Khubc0g6XWDHjiE2bOghHrc6/pZWBch5a8n0hXGVdiBnfLirksiiideXYrJUjyx88hzPfPRsTkDGgLnD3Qk6c7A+DtcM+/NmcvDo76DIB+0xeOh3MLUSJo1TniOnWQa4R+N0QVmlVXMlC2BKkFTBL1opP9M8f8QZwIoVIl/8osDTTxdoVExiW2UyBYGeFJYFgQBoJi7vIGoqTyRSxfH1cxXlMH0a7N4LsmStLF229NjrdHaauN1QVCTg91sC7XyjpsZNTc25TWfCcDrbBe2d4PMavLszw//9uxS33hxg6dJRrEq5gInlYX3n2Mexe2uOjC3ObGwmmK6uDD/96UHSaY3SUjf19dZqvqEhFb1lL1P8FSRSJYizeinUCoDAp4oErpKvQ2DibBn6+w1efbWAacLq1Q7KysbnWikDXEcN5RHh6I5Eat6KmOU02N4F6TT0JsdPnM2uhC3tUOJ7X3AlVAi6rS4Ca38PWn4JhgqzPbB2DaPuwXk2uOUWBw0NBnv2aNxYA819bl5806StW0AuGLiMbrwBkaKQwdRGg+PFmSjC56+HvfutllWTGj7YH7S6WkBVTYaGrFq3uXPPwzfiPKKsDK65GsDkV782yOUEOjs/Qn2I7LTmWcMWZzY2E0g8nucnPzmILAvvibIjhMMuwmEXbW3d1Ib9lFZVEcDHFZMFas6gg08+lcLQdVzB4EltLo5QKJj85Cc5VNV6SjY1Gfzpn7rHxVR2ugc2JsCvgyjAoAZXHrVKsMgHUyphVyv4RKiugBmnWVg9kIMDSUv8zQqB6wROEVNLYX41bO+w+nrqhhVJmz0DvtcCOyQwPgWZJLQ44OE4/OQhmF4Lt86GhlEsEJhIJElg2XI3s+ZBWQQGY/C5T8MLr0FHp8jhqA/RSHLH7UHKy0/8KJdlmDPr5NdQFJGbbpLYutVk7lyByy6zrTdOxaqL4anfgiBKLF/mZvkCg8suO/fp1rPFuK3W7MVKz9ucFFuc2dhMIG+/3Y+q6tTWnjztkZrvZEfDIJNKs6xyl1Jkjn4J2OFXX6Xp5ZcxTZOK+fOZce21iCfqX3TkmimTRMJ8r6dkW5tBMmmOjzjzwfWl8ErMstJYWwwLjtKlogifvwT2dliWGNOrIXgabiH9OfhhFFQddBMahz642GAoBy93QdwLsxQoMSHkgYQbXomDKcDuNPTrJrEuODQAb/gFGADXNniwFX64Eq6oOfVc2vvg6d9BWoWl02HF7PGPvuXy8INHYCAB110Bi2fCJUvh4sXQPwiyFCYyDt4Yc+dKzJ07DhP+CHDxUqithnQG6qqdeL2j66N6oRPLwfq2sY9zBVB+HpURnI/Y4szGZoIoFAzeequX8vKT18vsKHh5oTKH3xPH6O9kd0xlc3eYv1jTSanXh5eRq2+TnZ1EX3yRUG0tgiDQtWULpTNnUjbr5CGTQECgvFygpcUATMrKREKh0T8t+3OwOwaNAag5SmAtCljbyXA6YF7D6K61OwY5A+qHde7hNHSpUDt83VQBfnQQVA18DjiswqJiWF0L/9gMCVPj3bROT0EnudEB+ySIA6IJ80VyhtXN4S/fhtdKIXiS6GUyAz95zroHj9MSaW4XLJl24uPPlHwBYimrG8HQUT3vRRHKSsb3WjanT231uZ7BOcYY+ZARsbPnI2KLMxubCSKZLFAoGDidJ45gFUyBTQQYUCUm5fswByXCkSi70k5e69zLRUqGaj5OgLqTXkMjSyrbiSDyXqRMkCQK6fQp5ybLArfd5mbLFg3DgMWLZRyO0YuzB5phIA/OPvjr6eCZwCeKLFqROLC+mljF/Uc4nIJ4HhqGo3R+GbYOQmMYmjSV15MaQzkHyW4nZIdXAYhAQYB9BjSIaEnoSMHuQVh+kpZQfTHLWLg8bNW0hQNwsO30xZlhmLS0ZGhtzQAwebKPmhrPB1LRAR/c+hno6YdFM0//fbKxmSiKXLCyeOTjRhxnADutOQK2OLOxOYd0ShKDz5bRt6gcfzhNoimEy4zTNVSFQDM5Bk4qznLpZg7nH0NIvU1p2QHUgUYy2lxESaKooWHEa/v9AqtWjc3N/mwyPwxbhqAlbX14vygCFaexiG/IyLG1kKUv5SPnERGGTFyLUzjXqJgFgcK7TnJbvZazvlMkMQRPR2Fp+QdXfap52NUJbxwGZxeEveAXYOHU07uHgYE899zTRk9PllBIBEx03aSx0ce6dbX4fMc+kqfUWZuNzflATIX1LWMf5woZyu3o2SmxxZmNzQQRCDhwOETyef2E0TOHYBIfMCErsvf1WXiDKum4j6rJHSgf34SIEz/1x5xjYrKTAaJDB/Hs/F+U6NPUmK3kK3zE9AID4hSUFV/FV3Z2bOBvnfR+WvNUUbMcKt10EKSIMKf/0VulQC8pDEz8sovVFV7eiAl4JVhReqz9RYMfQk7oylhpzQHVYErNTpr9h1BCYZr6lmHKAr5FcRxmAQoiBYeMuVDCOV0l1+4BSaRgwP374d0kfH8FhGUIucHQ4SfroX0IFiiwr8WKoiXcENNHtuNoaTH46ldbGRjQcLsDFBcbLF8OPh+0tmb52aNt1H+6lpYBqJVEFpeKVJwnixNsbN5jPNKaNiNiizMbmwnC4RC5+OIy1q/vpqbmxAsCSnJ50iaoGT+67kAvSBxOTmahv5x6XEgcGxrqI8vGdDPdrz5Gwp2mJlwglXXi7clQUpUkvcxHoPrsFcWUuGDVaVhg7GMn/fQgIbOc1bg4dcjLwGAnXeyl5719vTmTfXkv5eIkjIKbe7vgrqr3zW39DviDKfDbDtgxCGXBASojbcRkN7WBPmo9nRyWy3GW/3/23jxKrvK8132+PdU8dnVXz62h1BpBAwgJMLJBONhgjG2wgx3HSexDQuzrOD4ny9cZnHNOTnyTnNy7rpM4g2NnxU5irkcMGBzbzGIGSYDmoST1PNc87trDd//YbUYBAmSBoJ61akm1a++vvq5dvfev3+99f68JUxrCdQjTolqXWDEDRXFxj4HbgEYJDvnhD5+ASBHetxI6dZjIe22kAJZ1g73Y4WD3CJy/FJa9hCZuteArX6kxPQ31ehrbFkxNOdSaddZuULAUg+/P+gje5hLwKzi4rNfgkgGFazeD7+wJcLZ5CxP3nSYT2gLwNnIgeS20xVmbNr9ENm9O8eij8xSLLeLxF1d2fTxe4svlCDg6lumHMHxoKyyLnKTzNqCi4JTKlKM26mwNLAsDGzSJ0mgg1QiCN18ZlIaGBBSUU5rfXqbZxwydhFAWs4f31EFRmowbR6G8irKt83MffCTtWXYAJHwQ08CxIVdX2V+ApSnoDZn0RV0mTQunodOZXKBRDKBJC5FwKZBE0R1cQDrQ8nneYDvHoc+BH+z0OietfU4emqHDL85o2A+7TjxfnO0/BD/+qZfQv2IpHD9epVCIUS5Dta5jiQDZapQnijYNzaUZ1+jf6LBknYLfhWnbZddxBUOD615gHvtmoGLC0ZxXIRvUYFkC0uFXPq7N2UuxCTtOvP5xtvsh3XZteVna4qxNm18isZjBJz+5gm9+8yijo1U6O/0Eg96vXaFg4hQr/PkyeCwxxDFT5cMbXW7YVGYKQTfRZ4TJL+jAz2XdG5gp34cSqDFaGiZV2INu+LBjK0gb55/65GwbVPW0WuO7XrOhFwmwlawjRZoQEQxe3sStTouDzNFJGGVxHClhqgHzTT+6r4qqzlN0NW5tzbE7b3J+zKBb6cJ1o9xV0ND8NVLK08zNmayNTRPXuvlE3yjT4zBmdSF8LpFwGWxBYb4DEZDIBhB2oaVg+WGh7BVylgS4AqwGKDps6nnxR+bXofCcGoy5ebjpB9DZAeEg3PMAFEoC2xGUTR1b0XCkAFthvqhASIUFi5F5lVxB0JoW6C04loADR2HzIAy9RMTiiZ1w//2gavDeK2DVqld50l4llgM/OwaPTXqFGZriecm50hNo166GROCXO4fTyfh4i0rFZc2aN74LwZuetgntGaMtztq0+SXT2xvk935vDXv3eu2b5uerAAwOhrn66kGGh6NomoJE8hDHeJAiIMnQxXksfdF4K5UOfnvVr3Ef32fBTVE5tI7eOYHas4VA/OKXn4zjQKMOD98Ne3eCz49874epRxJIKQmmUi/rj/ZSLFDnSeaZooKGyioSrKMT36JrvYZOmlPzb5unCshnhBnA4TJYLRAqqMJB9D9GAhef1mBKSL5v+wnK3fTUZnHdKIcqS8gqsCwmWdHazZp6g5yIckOgh/9t3kC+3oFbVGjVDWxXQwlJ3IaK6rNwfQpIHaEAmneRDHaCOQ8H5zwB8kLxUTVh5aJ4khIWcjBvwUTF82TTohBJBKlNuRAQOA0BfhWCgK6h+S1WnneAZG+OvePnY84nMS04sAALFfiXW+DPbnzxZ3X0KPzwZq9Vk+vCv38bPvsZ6F6cy9QUfO97XrPuD37Qa+H0enBc+O5+ODAPA9HnF0xICdNV+Ofd8DvnQfws0To/+EGJmRmbL32pi3C4Hc55OeL+02RCW8ZrQ9bmJWmLszZtzgDhsM6FF3Zx4YVdWJaLEKBpz4+KmdhMU6KLCBLJcRbYxJKTLgP2sYpf40ueFcQaYHkTZkehtACJ5189a1QwW1kCYzfhe+hx3DGLVsHE3LiZ0tHDPPnRr9FIDhPLrKZ7wwbO/djH0IOeeVhpbIza/Dyhzk5igycvG5yQFR44eAfdY9MMp3rIrV3LXjHOrF7lCnUZ6qs0NXKQz/vDuuXAkTIs8UNeLZAPnwDVxhDQFJKGohGyyqRas+TCcQb7p7l8+mc8kbqcwWgBq7WAIReI+d7NqqhK/8Qc87EE+XAcVygolsScNpCaQLVtlKBEmjquAarw8p+rEowYjI5CzYLQYvDPULxIUsuGZT3wvYOwdwGOjcNTdVimgq7ARAP6LgljGibOXhXqmte4PAC4LoZqcsS3ltTKeXo2TFK6LYocM3BrMJuDB3d6HQKSLygQGB3zPNYWTxe5PMzMPCvOHnwQCgVv2wUXwAuLeF1XsmtXk+PHW8TjKhdeGCAafWmBcmAe9s3B0viLo4dCQDoEkxW48zh8+Cyx//jQh2KUy05bmJ0CxSbsWHj942wPw0s0tWizSPvjadPmDKPrJxcrBioRfOSpIZGkOMX8MduGO/4F5idB0eADvwOdfWDW2D97E7tDewlqYwyPHsKXqHN83RB1XxyrfJiiZWKsdMgf20d2x1ECN/+AfTfdxJrrrqPzgnM5+NDNoAnUBZUN136CrnXrnvfWk9T51s5/4YK77sAMGATMCH0P3YWycQ3jgyGO9OYYNta/qLABvEjLuCWZcRxSumRQ09AQhF+w7LlgQt1SqJoO1cg8Ps1GColUWtTcMI4jQDoUieI4ghPhHn7FuIfe8DiqCOG6OVqapMxeNgRDfESb5GeFKOOEmaiBbUq0gIPTkOAKDMOmbnkXRwFYCvSGPR2cL8HjM9D0ea2RBlToUeHStXD7CDQc6PTBE1XwpeFEEfol9A3C8aZCZtjgSNPBruANKPESowcldt2gMJskvKyKttzFGgN0kD7YPQpPHoPt5z3/M+zo8NzqXdf7PB0HotFnX1+zBvbs8XpCdna++Kvzk59UeeCBOrGYQrMpefrpJp/+dJJw+OTf0R2j0BF4+ZXw7hA8PQNXLH9pI983E0NDby+X/9dFe1nzjNEWZ23avElQULiElRxlFgWFYU6xE3ijCvNT0L0EZkZgbgKSafKPf4UDnXuQBUnFMNi15Fz2x9dQretc4D5J2Jwgv2U5xQ9tI3hwBPvz99Gyq9Tvv4/81AkiH11K8rolNEMhrIaOc+RO3vsCcfZNdhBf2EtjmUZnYZ6Gv4p/xE/9PcuoBOr83HmCAxxnNdsYlJ3o6PiEoOXCt/OSW9wi83oDo2ZxSVDnv/m7mJ0Kpm0bkQAAIABJREFUMdOKUe2uE/Hr5Joae6fiKHqJVq2XblXSFx9hwYkz46ZxpMaU1YdftPA1avROH+A7D2dYufQ4vi1JCnqclFvFIUhDunxw6R0UD65kpU9jJAoH8g5Wo46KhYiqOM0I0SQkdM+aY8zyug4EdbhgPTgqaEVoNKESgN8/34umVRZgMAblBsxWoaVCIwqzAuw6GALKeRU9KtAaXqUnLuBTaLRCyKCkVTSYrvZilRcFgwE0wBbwVzfDigEYXAyM7tsPP78TTpyAg4dgeAVc+V5YtuzZ87NuHfzRH4FheGLyuZTLDo880mDpUh1lsaJiZMTiwIEmF1zw4n5adctbthw8ea3KM/xiqXOmenaIs9NJs+kJ5NBLd2s7q4n7Ydtp6E4Rr3J6RN5bmLY4a9PmTUQIHxtepiPAyQ+KQn8GJrJgBKB3KTTLVMxJ5oNRHEXQWZknn4xiKyqRchEjZTO1bJjJ4BpwXWpr16L/RQTjj+9ErU7hpppUYk0OZYZoqX7itTKj3TbLmWcYLwRzglmOM86y7jiNTj8zhS5WHT5KI+hjOuIw5eugRwkyKxvc2poj26qRaKW4waixwb6dna0VjBsrELMW6xoPMhIK8OfKhai7BikywN7gDGsum8WsdOBIl3AkR0qbw9cq42tUydtLUP02quvQUAIowqFj915sYTPfitH8uUtd38zQO67ivc1vkbBzCFp0xZbxmQsGuGkfxCzY0qlSsyLkWjZCqqwaVLlyFfy8ABULUgJGSt7y5NoU7LVhaDEVcLQJyRgcOuFVbx62PTE354NuB0pFKDhQcyGkeTradBUUFS96IAAF5Dxgu7gxlereKIwp3s2rBmiQSEM0AA/sh1/rgpER+I9vQ7oLLt8O45Ne4cG73vnir0fwJfqWWpZECJ4RZuAJuEbj5GEN91VEO4R4dfu/Fdi7H35wsyfO3nkJvHv7Gz2j00+xATtmXv8422OQbgcsX5a2OGvT5mxHUeCKX4fcNIRjnlhzLISWwGiO4W/UMSJN1EiYlc4h9uvDVKWfajiJLTQS5gK6sJlaNkCsK0YwNE5vqMGxrWuw0QgqNdygS4IKD3OCJSQxULmZg9jS5cnuDXSfmKXbN0NPc475y7YxGYyj+DVyepCbzGFmG1Gw4IRd4S/NPL/nKowaPnyNOXxohGmgVk32+Cp8ICUJCJV9c534SoKGXkeqFgm3QK81wiQdHHJWsVQ7gV/YoAmcJhywhtHqDWqRJK5soqVAPThNbttFHAp+mE6OEBM9DIqPERV+Pr/VW3bcOwe1lkLEZ7A+7UWGFAGrn9NTvG57q5CKArkpON7wdNVQALoNSAXg3+fBUcAE6IWZHNTHoSsMNXOxAbuCd6CKt5z5i9VDU4FJBSa8Y5Gg1sFQwR+GkB86wmAsXrF37faiM7+I0AwNePln4+Ow9MU1JCclHlfp6lKZmbHp7tZoNl0sS7J06cnvmgENfBqYtvfvy+HKt1fUzHXhhz+CjqRXdHHvDthw7smXks962hGvM0JbnLVp81ZA0yA98OxzVce/+bPIqb+n0TtCMR6lJXQG7VGGzQad06NoIYfJQB/Cr1KXfuqBGAOZANssBeV9CfZm0uiWjVBdUFVUXEClUi1hVEwmUzYNO8SU20tpeZynS+fy+Ie3ENODuKrNUlfh1laGeQI4uoIQLqphU6lJftpcham42IpkTu0iaKyioej4lCSzRYHPp9CpaHT7E3wm1Ms/TTSYLtjMGH2oPSWCisu7nfuZoI+qCGJULO6duJwDyjk4Uy5hLUendZhlKUG0WWPF5Bil8AB9vR9CxQslqQpkkt7jlQg+50r5yR44UveiQ8MBL6KWSkB5HJKO19MzrkIpBZEZUCVs7Ye5GiS7YfYEWGFQLHAtnnVc13gmF0cJwDmrQTRBap4IkxIuPdd7XUpOmo0oX0W0SlUFv/7rcb773RKjoxaGIfjoR2MMDp68pFNV4KIBuG/Eq9R8KcomdIeh523keSblsx0ifpGP92rOxdlC3A/bMqdhnDrtTgOvQFuctWnzFiUZ6iK24kaa/IhudtIgQtgaoDdnEQkLVhXvw9T8HNcyVAizubafKy8cZsnmS8lnb6d/Yoo9K84hIBokqaCxEjVv8tTf/x3StChsPZ/prV1EtRKadJiy+mipMaJmme7AUZ5igAYOrhSLXcpBugpFNcaCK+lxxzmhD2DpLfbpQwR1wV+G4kzli4yYI1yx4Sd0s5c7G13oK4ZIWgGWmEcp+/3kxsPYjQq+ZIUTLOX41DCteoi6Ecf1SUzCWBaMRpby/hP76CjvJVHy0dd13eu+6gVUWB95/raQARu7IFeCfBM6g6C6cP554MxBbwCWrYXHp2EuBPsOwbwPKiqepYCDp7biXqQsEYYrV3mVqq7iRfI+/UFILeZ7bdoIO3dBpAF+v2fdEYt5hbrPbSNlO6C9TBFiIqFy441JTNNF18XzljhPxuZeeHQCCk1InMQqw7RhoQ6f3HBa7fPe9KgqXHM1/OhWL4p28YVvzahZsQE7xl//ONtTkH4bRVZfC21x1qbNWxQNhatI8xjXYBJliAUygWuJX3Q+rdatuMr/5OPN2yk3g0QLHUSjH4f33wiWoPOR9bzn0B34BsaZDqRJyA1E1XPovP1B/L4AhSUZjtX9ZGYO0QjGKVejfLz4byS1HDev+QCaT4W6TcCo4GoS29Ho1yYJKRVKwTh+GSTnBgiSQ4YD0FQIqw3+X6tJeOUkJdXlEbEBW99Mp7FAhAq4NlXHj/9nh4k8WGKBaXz+CWa3XISablGTAZyWjqNqSL9Ccbmfjsws95e72Bn4HMup8aHK47wvNky4EkHV9WcsQ14vvQb0BKDLD0EBeQdSOnw8DoUSdCe9pUkehfEIDPbBTx4FuwrNAggf6F3Q1wOdSbhkreSj5+eJBCV2IUlHRCH+HEE4EQHjCph5ApR5WDIEcgn83jdhZSf8zrvhrj2wbwT6U/DxyyDyMj+qz3dqdidRnye8vvU0jJYg6YeA7tmJ5BrecuZH1sLwaUgaP9vYtAFWrvCKp2OvUDRx1iI5PRGvt2BU8XTTFmdt2ryFCaFxGQPAJ57daIBf/xBOqwzGw0TUfkTqV0Fb7YU7dNC2X88yrmcpDlUcWjiEMdhnPkzdcZjVfEgqrA0dwnQdlhXGWDE3juKTPFK6gEZXCNtQEVIy6I7QqeUoqxEMYdOvHqBPm8A6oDPT916CwRo+XwunpRAojnAiMUDSyrMQTmMpKlU7QkbLslocpGfPAQr3jhPuS2AlUkRX65gySNkfpk+fQNMs5kq94Agsx4flGAR76uSLHVSsKLNHpskX/ppzHq2j2Gm61qxhxVVX4X+dd9OgCp/qhltyMNuCFQHYHoJv3A6lOiTD8Jlr4PqN8MM98F0bYtvBn4f8OOgN6IxBeBCqHfBTo8hP9yywtXOCzeEBfis4/Mx75Vvwn7NgdELn++HyBDw+Dn/5t1Cdg5/W4b7bIbMRNq6CiQWvkODKzd7x1aqk2YREwlvafLX0ROBzWzzPs4fHIVcHvwbbhrzuCcmzqDvA6eatWqX5C+JB2Db8yvu94jgm7WXNV6Atztq0eRsihIrm+xT4PvXy+6ES4dl1seGrruKpb36T1uQEzrpVBJsLaGWVQXcav9XkkRVbySdSaIpLQDPptqZ5p7KDKbcHn2sSd0t0mDkaQT+cC0a9ga67DChjBHxNklaOWiGEFdDRsFBcm7oSoo6fjtYCXUcPUwpFcLJ5Bt5v81TyUizhIxYpobkO0XiR2pEwVTMOfkEpF0epQ19snPM6d9FpzzGjaUT33kJ8028wnRuj8N2/5eKP/jpqqN/ziTtVpAvWGDQOAi069X5uSK+mpkgcYGHOR7musSQNo7OQK0N/p2dBd3wSkio0x6AxC0UbJg97Is23DtSCjin7CGpgmiV66jAc9ew3lvdCjx+eLHjLlsdL8J8/s5nxmZiKjmZqPPqUwnQRNq32ihisxSTuXbtcbrnFRUpBfz984hMKweCLBdr0tGT/fhdVhXPOUUilnr9PQIfzemFDWpLL2USjKn7/qzMbbnP2Uayfpt6aaUifJR0k3ija4qxNmzanTKS3l4v+4A84p1bnptkaU7NxVnWNUQpHOZ5ZwoPRLczqaaQjiNUX6J7N0u2fxAobBEImOjaWrqPZDq2ATqc+TaeeI04RW2gkO4osaZ5gj7EeIV0UqSIUScA1WekcYzTVi13MUeno4ZHBdWjdAUJmg3yjE9MJEArU6EjOU81FIeoi/JK4P8em1E66rUnW3PMkq57Yj2o3+U5lkqc+dT7JYJEDx/9vPpJaihv9GAtaFKEpRLVZLFEmQJQEvWiLbc4bmNSdHL7S7YSbJ0DxgdCYMe9jV8MhK7opOTo2OsWNyxkf30qmL0VHDB6aF3zyHkk11GDab+MWAtTRkWUgAGYOrBxoMR1FsTmxp4siaaaqUJmFC4bh0++DG5fB/9rnGd46LhRp0VA1pF/gdkuMUcjPwolpSETgHWugUpHccotLOi0wDMHYmOSBByRXXPF84XXggMO3v+08E1W7916Hq69W0XVJLCZIJiWTkyZDQ36+//0CR46YWJbGunUJKhXBkiWCTZtUenufP66Ukv37q8zMtFizJkxv76klHbmu5NixBj09BuHw2XnLqtUks7OeaXAsdhYn47VNaM8YZ+c3vU2bNm8YqmEQNwz+lN385e4tFNwOYrEqY8pyZpReCq0EDRlkrhqnZOu8q/UYaWueGhEszasEdAWAYJVxCB0XVbiY0qDDKZCM7iKf6+CYP4OrgSFM1tn7aCo+0uc3CTsKuqvxdCPG0kaBgeAIdRGhUQthOyr4wBiqE4xVSAdnWW4cB8Wlo7hAcXOabLCGevAAyx59hLmDq8htXMF9Qxs4cWQ/zo6/ZW/vMN2raqT8JhuMBB1aAHdhmr5Rk2K8zHRvDJ0CjibpjiS4qBXjmJvjp3aEVtnBsGfY39hC3k3gDzXwrbuHHc75fOvuIebGFKp+CCcamEUDO+IgSwokVGgBKrjzYNk+MDTsoo9ot0Z5BiZyXqeCgOG1jYrr0HIhqsPAcpda3aU150c6AkPCORn4Pz/i5brpGszPg5SeMAPP/6xYfP5dUkrJ977nMjkpqFYFiQSAy3//7yYbN4JtS8rlecJhhxUrAhw7JpmcDPLIIyq33+5SryvoBlz4Dptf/6jKr/zKs9G0ffuq/Md/zOD3Cx56qMTnPjdAPP7KzT7Hxpr83d9NcumlcT74wbMvy75YlHztay7VKmia5IYbXixczxbiQdi28jSMY9MWaK9AW5y1adPmNbExYvKlxg+5+54wM+Ew5Z4ihas3UJERdMXBjQWYDyzlUGs9W81HGJcDVJQIfruBa+jomCi4KMLFlaDioKoWPmHx5yNf5DsTV3EkMMiAPsHVQ3dTCcWQIUFxyxKWzC+gOAcZbOQYDQ/TV7+Nkfku5nsyVGWQXneSuuHHVnQKMkZMLdBqGYxFB8kqBv41BkYgiBVVCUxMURvqY7R7GVu+/DdEqnEe3/QBHt52JTu75nhH+CFWRw4ysjpC0+ejaEnKJAlSw6+U2SMmqdSCJKoLhByLshalIzDHmNpPSYQJ2TXM6VFGxvpwNQOqQEElpNWp9/kxizpUXE+cNRQog0wBXSop3etMUO6FoAlGE44fhSVdcO0A/NsJKLbgY5sVdl90lL23pVHvS7NhG/yP/wrx59hZJBLQ0wPj45JgEEolyTnnPCueXBf+41b4xr95HQW6O2BhQXL4sEs4bLNli0Jvr8KPfuSwbp0kEFBYWFB58kmBlILOTkEuJ8i3BA/sEVRaLqtWCQYHPSEyPd3C71fo6/MxOtqkWLRPSZx1dxtceWWStWvPzoSu48ehWISlSwVTU/D00y69vWdnH89iDXZMvv5xtvdB+vTU4rxlaYuzNm3avCYCzU6WbQoR6jO41VV5ePhS8rIPVTioeK6tBaWL75q/yibnSS4sPMTjXRdg6ypBUWNUDjLkjgEuTTVE0s2jOQ4rCgeIjo7ykYl/5MQejWJJkvxqkpCoMxnsIxSzCCVU1jTnKdgdxHZmMeNRltkjpL+3l8GtF3E4sopwQ2fWl0IoXo7VvbFLmWv2oXfkKfcKXH+AvuYc4UiNel1QFt3c+pkvcvzo+ZgzBtVjXZRrXTTXaexsbUJdcOmLT7IycgDbVZkUQ1hSJaRXiVtFWpZCUUtQikTx2U1aNRWnonkeWCjIE4AfaEF1IgqOhHEBOWBWwoLw8thcoFOBrTATBVeFsAHqClgfgB2Pwzu2QLkCvzEA0SAEdT87RZrBz4YZ+OyzURnHkc8sT2qa4Dd+Q2HHDpdiEd7/foU1a54VZ0dH4Z//1RNYriZpWmBVLXLzDrmcxT/9U4OPfSzC+vWdXH+9wtq1Afbvt+nsdIlEFAIBBduGZsOlUHZ5ep/NP/0T/NmfhdA0wdq1IR5+uMjoaJN02qC7+9Qs4v1+lfe8p+O0fW/PNJGIJ3zLZUmjAcnk2Rk1e4Z2Iv8ZoS3O2rRp85oI+NegOj46ky0Sahw3EaFhBmkpBj7FpOUaNJpBKiLMF2N/zjW+n9GhzjCndZNz4oTcGmWiaHaLweJx1jUPkiJP9NgERq+gOCEIxV3MqsvUblizdQG/26JLhBBBF5ouPmGSm6sQqE0zfiKI8uAUHcUysxcbLASWoCQckkqehUaKSWcIXZjMlFfTTAlSlSyT4z3Uq12k189huEWKxhDm2jDB+RlkKsyq9CFU16XU7MBvNNk7v5GKEkT325woL6FciGPmdda1DtBhFZgPduKvNTnRuYxmwYd7wqBZCdDIBZAHDAgBMRbbDQgvYjangFy8YYvFx6yExwUsg7koGBGIROEnex0+eUWLW4+rPJY1iPvhC9vAEAoX0/288+O6kvvuK7JpU5hEwotQhcOCK6/0ojZTU/DEE16j9OXLYccDMHIcRFLFlS7zDjiqilRcQFCuqNx1V4M//MMEmzf7sCyJpimEwwqRiFd4sGwZ1PbXsVEYTLrs3y958skWmzf76Ovz87nPDVIoWPT2+vD7z87o0aslk4EPflDw9NOSjRsF559/FouztpXGGaMtztq0afOaULQgXdHfZG7hH9lYO0SnO0tT0ZlxuqlYEVypguISClfRjTC+2Pv4eNNP8c7/zVOdkiOr0oh6jehd++i55zGGrmjSca5Lw5AsjCqUcwLXEaAb2I+XqQ36iZZLhHw1CuMOT96h0L0mTyZoMX5rk9xDCRxVoD7yNEu/dQDnkx/HuvqdqEmXqXo/WtSiWQlSc2K4ScjlhtDKIFNhpmd0ulZqNEw/uILS8CDrhg4TVGqMtJYRDZW9iKBiUdSTRIsl5nZ2UyglifaUKSSi7DuyAdWyGUiMYfs0XEOHZVB5PMT8/n5PdPnwli99eO2bOhU4CDR5tq0TgCJBk9AA9sLElKDjvS7qO5r8+3iLdZ01WppBtx5HiJNHoBRFsHlzhGj0xZf5e++FO+/0nFOkhO5umMpBVxqKk4KAogCSqqNATMVvWxg+QbJD59prvffTdS/5/9gxSbXqiTwpJXbLJeIDn67Q3e1SKDx7N08k9GeE4tsFIQRbtwq2bn2jZ/L6iYdg25rTME5bnL0ibXHWpk2b14w+fDk9gV6iD/8DV43dy3cHrkEVDqYSwFJUTN1Ph9/kPf4Wv6ssYdnhnbjHQ6yZbFE8XOHpEya63IjRUcfetYcZXZLP2Rz5VxNfUKKEdNAkDaFT+0+bEd3FMpocudkmf9hmPqkibIdaAWL+BWqmQNUEbixO59wcdz99HnbUj3+ghiN13KJC3Yqg+F0avRGCiSqK5eCWFIQiIRqkcTyGEbCYXuhD8btEhvLMNrsp1eNEY0U0xWa+2EVhLAUuVOph5s/rpmUaaIZgf/4cgokyalyCBq1iAEdRII53xbV4tveSvfjwL24L40XVFvtrsmRx2xKXXNYm5/ogFGDPjx2u3X4bm9JlFPVjQNdJz8/JhFmxCHfdBQMDnrM9wJEjkKvCwCDMVaBc8UJ4igp6p8NwVKDrGtdeF0HXn438vOc9KgcOWOzeLXBdMAyBquo4joWiQDwOq1a9vcTYW5li7TRZaSyF9NmZQnjGeEPEWSaT+Z/AZYtP/ySbzd6/uD0AHALOy2azC2/E3Nq0afPqUAbWEPnVr/K5+Um68g/wk2iKBX8c25+kQ3X5VS3GtWoCAxWiSRQpCDQMxkabhCP9qIbByOM+tIHVJJ4s4ARn0CMKtq3TvyZBfNMgc8dnmZ2dRp2zOfgTk8aCpCMJSdVhpgFC8VZbIj5JS4AMwQr3aS6OPcquzvMIRyoURRLLb4AA1bKRaKCCU9Qxgiaa6qC0HKSj0JeYAAdsRSeq1PDHxojYVdKBGSpOGGkrGKoJhtf7sjofQmgudcVPU/rxizqq2SKoN9A6LdzDqhcFU3k2aqYCFTwxpgFpoMP7fzhVQlQE/maD+XSXt29Zf0bU5StRvv+Tq+m55lY29z2KbLwfRYHwKSRZLyx4ETP1OauKfr9ErUJHHGIJgeGDfBXicYVzl/jYOJQiFITrPvR8L7P+fsEXvqBzyy02d98N1SpceKGPTEYjk5Gcd57B4GA7BvCWoW2lccY44781mUwmBExms9lLMplMBPgOcP/iy/8VmDvTc2rTps3rx9/Zx291Xs810mVOumgIBoSC77lNFpevhQ/+Nq1igcmbfkgskaBZKuG6KtOVpczX+mk2dezALMnMMEPXX0rXuctY0igxve8+Ju8dp/nDQ5h2la4QNMrgOODYoPlBBMAfUKk2QCSD5Msd+JaYmBU/cV8eo7fB0dk1NKphb9mwFkTXTEJdZVquhqn6oAjBeJMGfgQuCaNA2CixydhJwG1wvLiM/dFzUQM2jlRRIw7OURU1JpCmSjyZJx7JIwxJsZ5gvjPlRc1KeAoyiBctc4EU0IcnvlYCjkR3LIJWEzcsuCj1MLdq14AuvGPAu7GZCrWFILftXs8j9wQIBSwGWyoXDSt8+ApPfNUbEDqJWOvo8JYyLQvGJl1uuUcyXoTokGRVGoa6FBZqCqtXw5WXwXu3CCxL0J0+eVui7m7BjTfq3HijZ7WhKKAop5bs3+bsIh6CbeechnHO4rS7M8UZF2fZbLYG/PPi09V4heVkMpkBvEvY/jM9pzZt2pw+kkIhKV7GLb5/OSRqSKEgpcQIh/FFozTyeYSq4lg9xJesZsOnriCych6bCZRAiP41n2burvvRQtOIpo3ZaHqNvRXwhUENgGuDVZJM9K5gZ/JL7JzcRm96EkNvYmoGhVyChh2CiABLQt3BiWqUT3TQLIWpliOEZQXHEtiOSkdinggVBqwRFNeivzKJGraYtXuIdJSoFiO0DhoMLh0jFZtlYmYp80aK2swglVAYM+fHyflgpYBJoA7YElThCbIkEFms1LQAS2K1NEqBKFt6HuZgeBWo0stJSwovctYARsAOaUzv6eKA2YE7IvGP2Hy7Irltu+DKa3T2HhZ8/EOw7gW+VIkEXHYZ/MM/Sn7yAFhhgR6Q1EuCPbrkmmGXv/4jQX+/IBLyEv1PFU17+951pYRmEwJv4fZVxSrsyL7+cbZnIB155f3ezrxh8eZMJvO7wBeBLyxu+iPgT4D/57WMNzc3xwc+8IHnbbv++uu5/vrrX88027Rp80vACIWIDw3RyOcJJJMMXHwxhRMncFstVMNg4KKL6F91HQASF4ECIdj2xe1oaoQT99xD/sBTaPE5VE3Fb9rE1wiSQ5Knll7GnsHf5tDUVmRFZebnPSSXzdMSAaqxEKJXIpsu+AXMqzgxhVIjCTnJUOo471x1D4lQHh8mY2KIoFJBcV06c0UK4SRu0mBjYTdpc55JZxBjg0kkXUK6CoOpSe62rsCQXuTLLQoc0+8VAaTwBFhYeiItJ7womFzcVpZgKaCA6fp5oHQJMqyihU2caQM5KcASkAccgRxTmZ0Y8MReEKo1i3rR4ce3Smby0NWvcf8Oh1RMwXEUOjt5xoB2+3a4/acWzkMCo0dAXVArC2RBcPuEpCPo8uUvqa9KmL3defAxuOtB+PwNEH+rNj6H07Os2eYVecPEWTab/cdMJvPPwA8zmcw0cDCbzeYymcxrGq+rq4tbbrnltM6xTZs2vzxWXHklO7/2NVzHIdjRQWp4mNrcHAjBkne965n9BM8qBCEEWz//edLr13Pkjjs49ONvoyZMwmk/ypBC38UO/1/hnbh1P0vPO8LIo8uQrkqtGKFZC+CGFIQAYYAQLj6lQVXE0MMtFJ+Fv7POLnE+ieYCPfo0CblAKZbghD2EmnDoVmYxXQPFkGw6fxcXGY9w1MxQU0IIVeJYCmtn9qAFbfoTYQ67Kxg5HAGpeFEvXSIiDp1iHjUqcaVgwenEMTSoCPDJRasCgbQ1T7hZKv50C0UR1B4OgunCqICy8K7glcWImqXgOg4tU+XALpdYwGRmTPCnf2qjaRrvepfCRz6iks/DLbfAQw+VwDFQhJ+WouO6IFywGvDILsE/fN1bTU0k4J3boL//jH493pQ4jouUoGkvVq39vXDuagi8hXtGxkOw7dzTMM5rUB6ZTEYBfgN4LJvNHshkMjHgG0AnMAvckM1my5lMZh3wt3jZnA8Df5zNZmUmk/lV4P/A+636u2w2+/1MJiOAvwAuxEsc+L1sNrv/pcZ+XT/0q+SNyDn7NWA0m80+iHcZUoH/AeiZTOZDwCpgCLj0TM+tTZs2Z45ofz/n33gjJ+6+m9yRIwB0nXMOSy+7jGAq9ZLHqbpO5oorWHrZZWz67A3cee/nkflJ6LXZ9/UpOsTP0D6QJhxViL2rROX+GHbRQFFcNNPEyeu4uoZsQVWPQczFjUnwC4oyxkXyIbZpD5AUeeadTu5tDFALhBkPD+KUdEKtKkbYRrSg7gZRfQ5hq0pJjeIc0enOzfDwwBbG711Oo+FH7WwgulXsSS+nME56AAAgAElEQVQPa83gfoYao1RqEcLpKnPpNLuf3owUYlGYSbCFd2tRQXEkgZTFZ99Xw1wS4itfFzTLeBEMB0+YuSA0DSWoIG0oFFzm513C5ynMzDiYpiQchmPH4Ktfhd27IRAFUpKmpeD6JDQESkNiBKBehnvvg3ddDCOjcPjr8Onf9Sw3zgSuCw8/DLOzcNFFXmeDNwN33z2FZblcddXgi15bOug93soUq7Dj4OsfZ/tqSEdPff/FYsEf4MWcK8AB4M+Ab2Sz2Z9lMpl3Lz7/feBvgI9ns9mpTCbzZeCaTCbzKPApYDueOPtxJpPZAVwEyGw2+85MJtMD/Bvw7pcZ+4zxRkTOfgr84+KHpgL/ns1mv/aLFzOZzDeBP3gD5tWmTZszTLSvj/Wf+ASOZSGEQNFO/ZKk6jrdK87hwuQfcDT7Y/zHb+XoSIu+1mMs2ddPc8MW6DfIXZzCbBjMPNWPHmnhlMHWJVZABwlauIU/XMPRVKQQ9BRniPiqjFSXEFJqrFCP8xN7LcuDx6irQerVEOnGNKGxOmrDwRzSmetMo1Zcmsf85DuTjD20DLuq4xgq7lED/R01jPNtWocD9DcnKMwkkTHPhqMzNYtPr9FMBGBB9XLhfDakhGfvoUsMJOuVOFd+THLQsrnjyxp2cTF6o7rQAMUPrq6ALYmFXQQwvyBJpeA3f1NleFjhq1+Fri4Y2p7nQIdJx/Em5nyFwuE0RFScoKDWkkzMCi66AMJh7zE1Dbt2w1VXvvT5KBbBtuFldPUps2cP3Hab996HD8MXvgCv4qvxS2PTphSu+zYuNXzjTGgd4NeA5+Yurchmsz8DyGazd2Yymc9nMpmlwKFsNju1uM9XgL8GEsDXs9lsCyCTyfwL8F68INAfLI4xnclkjmQymSUnG/vV/5CvjzeiICAHfORlXv/NMzebNm3avBlQ9dfuhbW0YztKa5Qx526kOotVaHHJ/tvIfe8o4RuvI58ZoDoawTdoMZ4bpNHyEwg3EboLQy6EBa5QMWjh05vMdPawx2ejNiXhVg2huMyXUszGeulPT1Av+1l+53E6WrNoQUnv5AzH1g5xyFhLtQXjvkH0uo2muDSEVy4p0dCwEHskzUt8+JbVwVII9ZWwFvxQAE3Y2AHwk0cJSOp6J9IHlmOglQzuekrniSKkXJXVlwoOZ0EuWKBIrLyGUwEViR6Hyy/XqNkuownB+vUa3UtUhIC+PnjgQIPC2llmH/TTc/QRGvUgpnEh9WYKVInwSXwK7DsOmaUQCoCmQqPx0ueg1YK//wfv38//vudv9npoNLxChFjMs/5w3yQtg1Kpt/Ca5SkQD8O2Da/+uKce+w5PP/adZ543+95H3vGfcjx0UVS1XpD29MLsNwfPkGbqOcfNZzKZjsXtR56z7xRwCZDMZrPzL9je/RJjn1HeBH+LtGnTps1rR5EaE3/4bcracbSERCtCT7yG2HsQ/03fJ/+Zyyl2xVhfe5pvFX6Ten8IGXAIdpeJdJdJBIqERZkZp5uov8pxZ4i0NY0bk5TNMD8uv5+WNNhvriZnxhnwj7FNfZTxeB9DhROEaLJu/BALg73Uw2EU3SWSKjM/lsa1FQh44QYRlgS21Dkmh9nYsZOor4RquDzdXIeMatjTPlAFzXjCyz3TFKiDoQjSnYLHJ0BMQmVK5cgEuD5giQoxSTgAekliVAUXvEvwVx8T3F+Ao1WvuPPOUbhuGK6+GiLnmHx9VkEtzeK4CgVzCX6nRF10gt8lGpsgavmZKUQYnQyxfABKVVi1UnLTTS6zs3DttcozDc3Bi2p1dUGtBv7ToF/Wr4ejR2FiAq691mvEfrqZm/M6JVx6qTf3Nq9MsQo79r2GA/XrWfqOZ4vz/LFHScby069zOi/s/6Xi5Yc9I/oymUwnXgnN87bj2TzPAvlMJpN6jq/qL7afbOwzSluctWnT5qxmevdunvzpHjpWWWh1cB2wTAjJGlF7lFWFh5ks9iOAC3qe4K76u3E7NIyoTadvgT53lEiwgun4UDWXlubjLnE5AbvJbDPNfLUXDYuS3UG41GRBNdm5chMbjjxO1fUzUM9h9vtYos2Q6+5gwBnDWGmyoKfQNROW2wjNyydzWhpFM8W+I1vp6RmhFvBhDUnMO/0QEOAIsH3e3+7+xXCRT3A0D80cqFOLESxt8eFTwJFUpYSkZx7bOyi45UE4WITYWphuQs2FSBAu6YZzVuhEaWEmosgxCIsZxvStEAFfwkRNSFBnsEZr3PZkitREjFXnw1/9DB64GYoFwf/1dZcPXK7yJ/8Nhoa8KNcN/8Wzk3iurd1rJRiET3zi9Y/zchw7Bvfc43VKaIuzU+TNZUJ7LJPJXJ7NZu/KZDKXAdlsNnsik8msyWQy3dlsdgb4LHAr8AjwzUwmc+viu/8WXg5aGS+X7E8ymUwaWLk4xovGPi0zfhW0xVmbNm3OWqSUZP/zP2m1BFP7IOiHRgVKUxA+N0DsV1LU5wL4aiZ1M8Q7l+5gS24XX859kVK9g/PWPMaQdQxfrYmRbnGYtSg4+PUmLdXAKSuEg0Us/CQjs5wbfoqWrTO2coiEnKf/vlEajRp2Mk1cVOnpLdJRfIAfpa+ka9k0JT1KwwkiLIiMVvFFdCL+Kj1dk6R7Jhmx13DgR+thSoGYAJ1nHy0F4YK0oBYEpwkUFl8LAiae/1lTLvbpBEeDpyYBFYaS0DCgYUJHGB6YhZEqfHI4yGXxMA9fWWDePA+rpGNVI+BAPJTHshSaAZ0Nn3qMcjXBxNgwB0bgyEN9VBaMxZuz4Bs/cPmPmwV/86eC66/3emueDmF2pjjvPM+Qd8mSN3omZw/xCGzbdBrGeQ1ecJlM5gd4xYJ2JpO5CPgS8M+ZTOaP8czrf2dx188B316s7nwM+NFitea/Anct7vMPizlmNwNbMpnMvXjf7F8k/b/U2GeMtjhr06bNWYvdaNDI5wn1DzC/t4iS8ARCbgQ6r4oTmTPpUsYByU+jlzGtdDPn9CARJJjFOeagR2qEB5pgLxDX87hCYU6k8dFgVc8hZss95KopfKqF4wpM6QMFJs8ZIuLU0bM2ttWgEXEZkEepd3fTEwKpGkyIAA3VwufABd01NmQe5alShMmJXg7PnM9sLUlt1ocCuCW8v+kNvF6bBsgAOBEvGkgL7/ah4YkyHU+gKQJqEpLgqJCvwZpL4b9shb/YD9sT3me1YMH+EuRNwfs7XO6ITHNHrJfyoSj4JUhBs2zQsTRPevkM3UOT2GWd5clD7LjnHTQLi/NDLraRkjRt+MMvSxYWNH7/9wXBU2gf9WbBMGB4+I2exdlFsQw7nnr942zfAOnEqzsmm81ed5LNL8pfz2aze/GqMl+4/Tt4HYmeu03yrNfqc7cXTzb2maQtztq0aXPWIhQFLRCg94ILqE1NUMsV0HRoOXBiV5Oe9ZJJ0hQCabrUAkeMNTxYvRA3LxD9goKRZiHYRbJ8AL3isszdxeyK1cyJboQNLXz4RZOELFFvhpC6StCtk2aedHOeWLxBaAhilQn2hDI8uuQSSr4AWnOUbtfGqF9Cqhll2AjxdKGPe/f0kVMLRIItiiMR5nYmaTZBFoAAXgQsiCe8CkAOnDioEZB1cJN4ZgIFPAcmF0+NSgEOCBVMB5amIODz0tYcF/Y2YKQJZRtGG7Ap0MWXL7iHNaEFvpG/nPlcDEfVsGyBHmnQpWU5cWwpjWCM4pMxoskCda0HbBdc6QlFG3Agb8r/v737jq+rvvP8/zr19qurdtUsWeW4YjqmGlNMKE5CCARCJgmTEGZJNoWUzZTdncdkHtnJ7Mxs2sxvd8L+QjKTZBJSYIYkkAAhgAmh2MYFG7fjKlm9XEm331P2jyuCAWPZSJZk+fN8PO4D++je7/3eL7LOW9/Kg//ucPbZOu985ynUdSbenjmyOGO+k3AmhDhl6cEgVR0dGOEw5330Tl6+71uMjmSIeuBtH2PUW0Bd9QAVSp4D8XYKjklowThGOg2be2GwE2XXVsLX2DhWE1THsfzfEVRy5NQwHirBUIEXRy9lPFPBnvxiFgQ7yflpFqu76dPraKhX2Flo46cd70VV4OBoO6lIFVreIZTvpvL5YToblpMpLCA7XkVDLMqBlwvYz4RxvYnNaUOUe8NUYJDyQEoFf+gt03rB2wGeMvG87MRrApRDUgjIQbgezm+B65aUM9vaBfDgAdidLRfdFIa0CzoxWriDe84YpfVv9rLr2To2bI6zP12itrWfAb0NLa7hdmlkR8IEm/IkE32URgyGnq4p9+BpQNEBV2Ffv8KPf+zyzneePreUVMojl/OprVVPm2OrEjFYfcE0lBOZehnz3enzL0kIMS+1XX01G+69l+iCZi74wp+y83v3kTtwiAsWKqS/00PXn61krDHJvso2jGSWv8rsZHOpmw0DadqUTayufJZD+Wai6WGcpbWMeQFWaNvZrS1B8X3yhklT9X6M3iIjVJEtRLk8+jua3U7UkEp3vpEHFr2Pld5Wouk8g/5eHvRuZChUzVgG9EVxPj14mCdLC+jSoDBm0r/fxA1R7iHLUQ5o7UAc2AMc8CHgodaWiLamKQ2G0Ns01CEdT9NwcgoMUF44YAIONFTCH62Cz10D5sTOJOfX+sSCHtaAxovjsDACZ05s/qn6CqrnEK8qce27x7jy2jRPHE6x6bBPPqeWzy9NB4h1jDK4u47SsIkeK6AZJVzHAN8Fw4dckVzBZNs2Bc/zUdX5HVQKBZ+HHsrx6GNFtm8ziMYU/u5/6px//vw/7D01Bus2TL2cNRdAXdXUy5nPJJwJIU5pidZWzvrgB3nlgQdwCwXab7uD3OAAWe0VFlWNUtzcRVfEx7CqudZoYEliJR9YZeGszDK4t5L+PXsIBmMMLDVYWDNCnhC4PitKmxgeCtCv1XPGpq2cM5Zm7xmXozcH6fZq+bb5URTXp3K4i0u9Z/GDOkNmJZQc1mYf5f7Y+ymiEkiYvOPMM1n3eHnK1lgKMknQmstzyXwF6KR8CHoEuNDDHM0SimUJLCugJxRcz0XZbpB7xSSqKyzQg6TGHUpOibFMEA2dVUn41CpompjLU8Djl/TRGyuwNBbldrcaU1EwXj15aPRHhIqv0JG4jl3aKJ09UZJODbXRMCm9B7fgQp2Ho6j0OAtQAw6qxkT3HeWlmT7gu+g5H9/3T6kFAW/XE0/k+fFPCjz5dJBCVkfVFe7+eIHHHtWpqjoNDiOVYc0ZIeFMCHHKS65YQdWiRQzbNoXRUQLxOJUdHSihHBkOA7tpoEg1S6mkAwUFIxChYfl1hDdtJPbsL+garsapGWDfpR0YfonithTu8yMULj8P/eEtVPn9GC/3wjl1jK8+g4wbxtw7xvm1GxgNLyDmj9KsdnHIbEYvuTi+hmpA3bZ+KpdotFXBK4Pl6WK5atCGyh1PRR3UpiLhkQzh+gLZOhO9Oo+iKjhhA7/SJxD1iDc7vGOtQ/cOhf7tHs2NJaprXLpwifdUcOUiaD5iS4heCvRQoIEAO0hzgVZBhCM2+1UjKEqApcoS9u+qYOeLOhHV4I5LXXoWRujKpVi3OUnnM02EqrOUSJPdFwIm5px5PpRKBHWNgKFxwQUKyiyns0LBY+PGAtu3F4hEVC66KEhHx/T1aHmez9NPF9iyTcF3FRQFPMdnJAUvri9x/XWBaXuvuSgRg9UXTk854tgknAkh5gU9ECB5xhlvuBqigioqOPMtXxd/3xco9inE9jxPdryKs7e9TOc1jfSoJurvuli0ex+lPhdtLE/kwAECP4qw6d/aCI3kqE3twW0wCOWyhIoF3IhG0MiTciLERsZYtLuTd6+3+VXbFRwYC5HKQb9XnqrlR8DJQbCQpzrQx0WjG1jatwct7/DDllsZTCbwUVANF13JMx422RtVufodGtr1I0RcD1cvEBmuZmkJzk2WF26+qgIdA5UeClSgE37jPpqxWyB2I6piEvEgMnF+enNYY03VMgA+8TH4ug4vbgsSrqzksstGefRplXUvKORGDVRDI+B7nHmmz2c+ozE66vPMMx6bN4NhwMUXK1xyiYJpnvzQ5jg+//qv4+zfX6KqSmVgwGPr1lFuuSXGypXTt7N/Nlve16261iE1ooDvUV1TwnXn/+00NQbrnp96OWsuhrrqqZczn83/7yYhhDgGJRCg5rN/hrl3J7a+iUwsTVXxFZLff4JtB8cp7s4x3u3jlyDqQGBhnOa9+1lZ2ImfS1Pbneeg345RKOF4GsVKg8DGvXww+AB1T5XYnbdgIMjyOohmh1m3Y5xCXSPpcQM1CHFjjIQzzuLWUbSkRqSYoZoRsloc11Ew1QKGoxLW8sS1HM85daxCxxvdw+32dmJVHSjta0B5/Y/zBAa3Us8QJRoIYPCGITdFoTxhDS5dAqYOIRMWHbGPekUMvvSp8pmZmqagKAk+c5fPX/2PHC9t9qDoYxqwdq1OW5vGP/+zx/h4eVNX14VHH/XZv9/njjvUkz4Xbc+eEvv3l2hre613MBZT+dWvMpx9dmBaAqKqKqxaZfLs73Ok0gqJhIsZhGStwsoLToPb6dzahHZeOw2+m4QQ4tgUVaVi0XLOZzkOJTQ00vcMkVf+ka6nfs9o74uo0SLRcY+Y69LYv49SrUnl8gLVqWEMzaGnqpHCuEZl326GX9aIbu8hkInRcevl5CrKwaCp1MfasS0sbrqYLUta6S+4XPjcLzh7dBsstPBVl+2NFsFCDtXTiId8DN3FVEoYmktYVSkCu8dGWTaynwIu8b1PghGF1ssAyLrwL4fL22jc0WBSpZkMF2BrDtojMJKCRzaUd8V4xzmwuKm8gODSpeW2KJZgeAzqj+jZOPLQ8YEBD7/octMN5Z44z/M5eNDhuec8Rkd53bFOra2we7fPgQPQ3l4+I7O7G2Kx8rmZ06mzs0Qg8PoAFggolEo+qZRLMjm12922bRm2bctSU2Nwx4cNHn/Cob8/T1Wlz1/9ZS3J5Iyf8DPjEnFYffH0lCOOTcKZEEIcQZ+YlxUL1nL5x79I7yVbsB99lGKxQK77EG2/fYDcSDXjdZUEPIdMJIwxVKQ1d5AN6gLSD/ZiNeu0nA3V29vp7NvLwSXnAmBaFlWVCS6pruFCHYY6N6PsfZRw70HS1RX4JZ10NEwpHEALe6iKRokIaddloVbAVCIYPhzOe1Tk4mQUqA3E2NvZy8YMrF4IeQ3258pDlF0FaAnA/90LI0VoMmF0KxgaaBp8/yn47Luh+oib5dOb4PEX4Z73Q1Pt0dvIP0rPx969Rw9cmgaHD/u0tyv8x3/A+vXl8zfvvhvq66f2/+pI1dUapdLrK+a65b9Ho1ObqL9vX55/+7cBYjGNzZvTXHddFR/4QAXf+EYa8Dn77NPjVpoag3W/n3o5a1ZBXc3Uy5nPTo/vKCGEeBsC8TgLL7+clssuw8nn0QIBNnz8w9Ste4BAqAVthUImHKU/EsFFxxs0aHpvhHB9gIAzgrY8xVhlxx/KUw0DtX5i3DB0gJqlL5M9UydY3UC1n2c867A/sYDBSB2xQhE9GKKERkTVyHsmJR8KGZeDvUFKPWF+9vQgd6/K8hBnMurAYBY+fgG8JwnPZ+C+YWgzy71pugrDaXAdqEuUqzCWLV87Mpwta4VC8fXXjpRMqixdqrNzp0MkojA+7nPZZQalEgwMvDmgeR5Eo+U/b94MCxaUDzTv7p7ecLZsmUk8rtLb65BMahSLPt3dDqtXhwmHpxbOenuLaJpCTY2BYSjs25fjqqsq+MIXGnAcH9M8DVZpggxrziAJZ0KIU5pHicM8h0OOJi7FZPqXgimqijFxNtGF936P4u8H8X7yPNorKrl31GEGNXLpANX1BdyQQSCukRs3CVUfoDn6OCOFc99caLgTVU8SvfNj+IEh9nfdyMP6YbqSGqbj4JtpSkCQEJU65DzIepAedfCDOgsi9Yzkogxb11AabqeQh/poeVHARQl4JAstJuwvwi0tkMrBkjD88BD0DIOulR+1bwhhC5Llx1tRVYXbbw+yfn2Jvj6PlhaV884z6OqC9etd8nmf8fHyUKiuKxPHJJWHG1etgqeeKge46T7TMhxWueuuCh57LMv27QVCIYUbboiwatXbOMjxCOPjHocPq4yP+3R3F8nlXFatKjdaTY0xyavnl0QcVl86PeWIY5NwJoQ4pWXoI4WNgkIKmyRHCULTSdUxl3yShR8aZ/t3NpOoGKHUomJoBYohCFd6mHoRZ9RHy2XRo4eOXk6+HhI9oGdIj9XxrQMlUm49ejpPcEGWRnWQ6uBhio5F1ouS98D1gaiOOZ5D2xykqrWK+o4FfKKj3GvWMtFrZShwTgg252CBAWfFwJz42seuhSe3guPC6hWQiJ54E5imwmWXvX6LipYWuPlmla9/3WXnTpeREZczz1T45jeDRCLlcHbttbByJYRC5aHN6VZdrfGBD8TwvOi0LUB4/vkSv/mNS2trJStXeiSTBmeeeXpucZ8ahXW/m3o5a66AumP8AiAknAkhTnEBKjCI4FIgTN3rv1jIglOEcAXTukNqzQ2YgUOELqvjwJaDZLwAplqkoWaIiOIxFooRSWep9lLs9tqPWoSSscCJgVri3pfqGCpBS+M+FtftQom4DJRq0EIFsqQYdqK4Phws+sSjcGd9jAuvDNPRHiYQUAkA8TdssfW+SlgZAsUrT/5/deStJg63rjq+j9lVglcK0GbAouPYwmvlSpVzzinR25snFAJddxgc1GhsNP8wWb/yDQdeDw05jI97tLQY0xaopnNl6NKlOsuX61x+ucl5551ePWVHNR3DmmJSEs6EEKc0kxiLuBkfF50jumM6X4Fnf1yeZNVxPlx4U3mDqumgmBD9GItvaiBpP8nBnMvDrkayOML1nb+hxR/FGHN4sWYtu0vvI3G0IlCgUI/nQycO4UiKpQt3ksuaxL0cZy/cQq9fzzgGjuoS0SDrw01ukD9JVjASUnj5MBh9sHwBRN8werd1FB7oBvxyMPvoQlgQPv6POObCt0fK04OeBj5VCQ3HkU2uuUbj+edVBgYcWlvhsceKjI9Dfb2OZamv29JiYKDE5z+/i+HhPHfd1cZ73zv3Nr9qbta4557Ts6fsjRIVsPo4g/1k5Yhjk3AmhDjlaRjAG5LD+ocgUglmEPZugEUXQXXT9L2pGkaNvY+qs28gNHyI4W9+h28nP8gW4woazX0MjSfQqm+mjca3LKLTc3lEy2Iuc9F7XKLaOEvqOgmYRWrUAa7Qnue3hSoKXhONnoHiDKBW7OWX2Sgbn6unlA3iZ+I8s0Ph7ne8FtCyDjzYDUkTAhqkSvDTw/C5Rcf/8dLlbcxoMeBQCcY9aJjkNTt3wf5DOv/7f0fp6ytSW6uhaSr33VcilSpx1VUaa9e+9v/p0KEcu3cPoao+L744NCfDmXhNKgXrnpl6OWuuhrq6yZ93OpNwJoSYn1QNPOe1fR+mq9fsTe8TIVSzjOW3fBDzwWE0v54+NUndhedRZTSjvXHzV8pVerFY4vGGYUpKgZjnQKRES/UBFM1DN4u4ukZSHWOpsYN+vZaQl6IU34LnFtg6ViRWHcJtX4ZWqGXg5bPY1W1w/sTC0Kxbfo/AxNZbcR0O58rXjnd0t16HC0LwQgYWeNB6HL1mG1+C9Rth5fkqu3eX+N73xrj77jjhsMLYmI/5hpOUVqyIcMUV1ezbl+YDH5jGpZvi5JGVljNCwpkQYn669DZY9wPIpOCMq6Bysn6fqWk45xzOSuUp5ApUVgTRzLeepLXHdXi8ppdMl46XCWAkfJqbuwhEs6QJE1PyGIrDAbWDjoBNsJQnHR7G8CspuGOohkN1b5ZSYZSheh134XaGVQuXMBoqCQOqTOjNl//bnYOzTnDanarAzXHo/w0c6IRnL4WrVh77NTe+Cy65GJoXQP4ck1/+Ms0//dMoX/lKLUNDr9+gFiAQ0Pj7v19xzDJd12fXriyO47N4cYhgcP5v9jpXJRKwevX0lCOOTcKZEGJ+SrbCe/8cPBeMmTmQ+nIryEM7gtS8xVnbPrDN83lQ7WdsWwQnrYKjUEgF6Q8U2WmuYE9+CQo+7ZE9vKvqcaKGR42h4OU8ekYT9KWX0Fjqp6iOMOIF6dNyYO2kswKeJMoVtGGoGn+8EH7eDT15OD8Ba99GNvV9GByCkgtDo5M/PxYrPwAWLw5w110VbNyYJxRSaGt7LZj19pZ45pk073lPxaR7hD300CAvvjgGQGtrkLvuakDXT5N9xeaYVArWrZt6OWvWyLDmZCScCSHmL00vP2bIGUn4xS5wPdCOkh+6gCdHRkntC5IbiOHnVZSEjzZaYMBI8lLkAqLhcRxNZ2duOW35vQy7gzy771L2D7USMbKMBeJs9s6noVLhnPoB4hUDJCNBmo0IfYxjM8QyklSZ8JHWt/c5cnl4/AXoGYBzlkBVBZx1AvPVXrV6dZjVq9+8CiEUUkkmdTTt6F15mUx5k9qmJp+NG8dpbQ2iqgpbt6bZsGGMCy6IS0AT85qEMyGEmCYRE85vhE3d0HSUFWl7gNGuAXL9C/EjoGouShpoVkBXGVdj+DpoqovvKbxUvIBil8n+nYsp5nQ036domtQ0D5KOqWwdreTKxj6SRnnTqAA6GYpvet+MA3vGIajB4lh5yPJYfrEONu8qh7JnNsGH3wnRE1jpOTrqcviww7JlJspRxlIrKjSuuOKtNwv+7nfh0CFYvlyhuTlAd3eBvr4iO3dm+NnPoKurwPveJ10vM02GNWeOhDMhhJhGV7bCjgEYyUHlG7a3SAO+UQLAUEt4hooXVtACCnqyALpCxouAo+ArkMrFOJRfRDYYxiwVcQuQHo2wuGonZy/cQEhT8LJB4uZiXDxyONTw+m0fii58ex/05sADrq2DNZPMvd/bBY215QPRMzno6ocV1vG3wfr1OR5/PMMXv1hNTc2J3WZ8H8bHy/Pj0mm45ZZaHnxwhM7OEpdfXkFTU4CtWwKlGNUAABpRSURBVNMSzmZBKuWzbp035XLWrPFlWHMSEs6EEGIaJULw0XPh/99Y3rW/5ogepwog2O4RTOXwcip+EySr+1lx1laMaIkhv4rufDO+phCLpOjsb6egGBR1k1LSZOnoDhbFd9OcPMTBnlbqalQWmgMMe1vpzZ/HAqcZ30jgBV/rHRsuwkAe2qKQc2FzavJwtrQVXthWPj0gl4fWE5yvdsklYdrazBMOZlAOZXfeCbt3Q2urx1e/mubllzU8rwJNG8d1C1x6qZz/M3tkF9qZIOFMCCGmWX0MPrESvr8FDoxAPAiVQViswPZ4AzXv6sdNK5ixItdU/oZzM5sxxx22hxazKXEOg2oNeSeMqvgU0iGIaCwPb+ddtb9ksb6LmDnGo6UgFBeSydUy0J/nt4c70Cv7qQjuZZkS42NVUaoCHnEzQsxQ2Zd1GfJKXFGjAiaDGQjoEDvKWol3Xg7xKPQNwdpVsLTtxD5/JKLS0fEWqyKOQ11d+fHSSyWef96jvl5lYMAkkajiE5+IsGDBzCzwEK9XHtac+ukLMqw5OQlnQghxEtRE4NMXwd4ReOYA7Bsp9wotNip5Np5DrcuyRNnJdeO/ARVKmsE7ck+BofCEcTWRTBoclUElSVwdo03fR79XS3Wpn6rAAFdHnuIx5Vb6zAEwAlTU7UXXVfKOzqbgYf7LuM9qo8C5Wi13tS/iH4cHqTLy5KqKbB1u5f6NBmED7rnkzQHNNGDNha+/NjYGzzwHtbWw8tzpPQ3rrVRUlCf953JQKHi0tZm0tEzPoZwDAy6vvFJi2TKDZFK25zge5WFNZ8rlyLDm5CScCSHESaJrsKSm/OhPQ18G8iWV83yTHxf7CKl5omQYVKvxFFAUl3Z/H317TcxX+ugNtdFbXc/i6l101OykSAB9rETEydAc7ma/spVOr4Vnu6+h14uhqBrNDZ2YwTxFT2F/yeBwoIdEoJqOhnFUFHL4pIoe+8fgUBoqKuHjZ4IxyeLHR5+EjZvLoawhWd7L7GT4/vdz/OxnJRYt0fnyXwf5/OfD/PSnBc47z+QjH3kbp7S/hR/8IEtvr8tLL5X43OfeenGCOJLP9Axryk62k5FwJoQQMyAZLT8AVpLk0s6f8sPRAsWYTnVxiJKmEyODmR6j4clnCfYMU5HZiv4BnVxdIwGK1NFLKl7BK+lFNGzfQ2NVF98NfoJxvwLNHCdTCnFwsJbWxixOySSnuliBKOsZ4hKq6SFLM1GW1Ab4YQKuboTuAnRnYOEk+aQiBr4HZgBCoWM/9+06dMjl3nuLqGGNf3tYRTWKZMdVFDVAY+P0bp1RWanS2+tSWSlbchyvREJh9eqp9zImEjPQ7XqKk3AmhBCzYJXbROO+v+S5pYtp8PqJuBn2VLSya7CRrDnCcEMN2aoawtoo2VAT21jKWaXtxJwxUgcdxl5UiOVtUrdFMfUCJc9A0TwcVyebjxJ1gzSEoI0AY5QYoMD1THR3aXBdO6wfgOoA1BzHSOHVq2FhM1TEoeYkHYGpquWeOc+FYt7nmw8bFFUV0j4/eqDIr36V4bvfj/Kj3yqMZuC2K2HR2+zB+6M/CtPd7dLQIEOaxyuV8li37s1btZyoNWs8GdachPzKIIQQs0DVm6nNNhPLpdmtWWzaU8+ObTGcjId5aJCDNSvY2bya/lqL0UKCEaeGHfoi8n0quT4gHqbLqaXgK+ScAMVSBMcx8H0DvxQipKosCBioKATR6PJL7PBK+BNnjb6nFe5ZAZ86AyLHcW6mrsOSRVB/Em+qCxZofO5zARpqfWjTKUZV0HxIKpA0ePhhhV//zqN/BAIm/Pz3b/+9TFOhtVUnEJBenBPjTsNDTEZ6zoQQYjbULCKSuJgzfvMvjCzTGciHyWgmPNbJcOtitlZeR2m4Ci2wl9yBKErbKEPxJFvMCwm19pMdyGFfczFhVyflG/gohENFEmaWGk2hrcIlqZVTVxaHvV6EXX6Oz2oR6tBQFag7gY1lZ8rNNwehPsiv/9aFEuAp4PmgKngeVMZ98l1QGoWlLbNd29NLeVjzOJL8cZQjjk3CmRBCzIZgHH31PRDspGu8xMBz/XhRF6XgYq+6nuF97fCKQiYYpbJyhPy+IMXWEiNqJd2BRrbXrCCfDeKlTKLNGTpqTTLFDJXuOLVZg6vrAxgoFPEo4HGrGqfg6cQ9lTEfotrkJwXMlkgA6hIK6SLlXWlzQK9LMulz3aU6ySRk83D+4tmu6emlPKxZmHI5Mqw5OQlnQggxW4IV7Fl1C6Njr5AyhqjZb5O4qIJkYBwjU0JRFPoON6KrDtGKDCE3z4G9bRze1kopa8I4oEC6N8qWM/LU1oVYZBbx3Rw7/HEGfZegonKD0sCZSogXMwpfGSmvlWs04UO1EJ9jdwHHAXcIrmxVqcgW2b7NxU35tLT5/OiHYTQNzlsEYzkIvv2t1MTbIqs1Z8oc+2cphBCnl01dGSqGbOINDuHlcbpjLRSGNYxggaISxncVerubKO4wSC7o4aDdgT+uQ9aHDIACWWA0yMAlOi+3jdBSOUpvXidCgbhXyYvBPKaT4TcjUZoMMFU4XIQHh+Ajc6wHY9NW+MlD8NzGIl2dHhcvc/ny34V45AWNn6+H+gb47Suws8unIQEfvx4C5hztApxnEgmV1aunvgFwIiHT3Scj4UwIIWbJyIEDdH7vYa6vfZ5Ky+G5yDW80HMpOwvL8eo01JJD7lCQaDZNe+seUqMVmPkCJdXHK2qgTdzkVMpB7aAKrQ5jAY0VbGOlsQ0fhcPF1WxwL0YlijnxknoD9h3nCJXj+DzwQB5VLc8J07STF4aGhmHLbpfdO1xwfZ7+nc9n/kuBNe8NkS8oHOiDl3b7bH7aZedOlYfv8/lf/1Nl4QKFihnermxoqLyRrWnC2WebBIPzO3SUhzWzUy5HhjUnJ+FMCCFmyZ5HHqFu/UvEVqcYP7cDTzUY7UtgFkoU3CBGex6/XiGdD5GuitD3SD1OzkBrd/Gqdej3aPIOEwmmGfUqGMkmKKZNotooy5QdDPsJVBSajefJ+83s9UHxNZqUSlKOSt1xzu0eH/d56SUHVYXrrvOJx09eODvnTOjtccHToJiFUpHNT0G41mRBo05vJ3Tu9ti4XsX3Yd0LCh/5M49bb9L4/IfKqzhnwsiIy7e+NU4u5+O6Plu2FLnzzhi6Pp978WRYc6ZIOBNCiFkSqqykct8wg5eEIRIj5wdRXZ94KEUhF0AJuGQI4yom/ek6aDBwkwZunQ+OTyBaQO1yGc/GqG4YojbRx8BoNQG/hIdCeUcqDY0SdaFelsYr2DJuMoJJkxrjlkn2K3Pc8qOyUuWuu0IoCsTjJ7d3qC4JQ70+KEDAhZAKaYcXnktz5WcSbH4ZFgU9HktrVMZgGEiNKpQc8LyTWjUAtm/PsGFDhnxeZXxcpb29nHAPHiwxNORRVzd/900rD2tOfQdiGdacnIQzIYSYJUtvuolXtj7DzoCNpRlUuinqjF58Q8HIZ+ktLSDoFfHSJpliDN11oAYwgJiPWuGi5YvEnVFiLaNEill63SRFP0S/Wk+bcgBdUVHU5USUCq6sytMcHaXF07jMiBE+Ro7Y3ws/+C0USnDlWXDNucd/uxgZcRgYKNHeHpy0J8l1wd4PzY0QDkO+WB6tLTUp4GvgKrDQwG0x+PEBj/d3qFx4hcZ9T8HAIYgZ8Kd3Krz3XRCanmM3j8rzfO6/f4D77utj8eIQpZJGoRCktVXHcUBRFILB+dxrBqmUy7p16SmXs2aNK8Oak5BwJoQQs8QIhYj+j9vQ8o/QlRmFoIGvqNSVDtPUs5+nqysZHgqi6D5aj49a9MFzwNHABVdXqFk0QGDAIRnpYSRfjdU6wGWRw8SUJC4NVNNOlhrCZBlinAY9QH57FV/bBQEDrjsbzmp9c90e/D2EAlBTAb/dAme3Q23F5J/JcXzuvbeHoSGHG26o5OqrE8d8/u598E/3wU3Xw7VXTtTpvQYPbXAhYYLrQJMBB3UOhX2KyyFcr3Lrn/sMdsMfr4R3n3/yQ9GePTmeemoMRYEDBwosXx7CMBQ6O11U1efGG8N/OKh9/pJhzZki4UwIIWaR4uWJejlynoZSgjODWzg80MxosAoz7WA6DihZ8l6EaCSNV6zAd0qEAlmKJZORbIIVNTsYyVQxGmrgpuYR4spSmoiiEkdBJUeBc+igBo2nX9Z5+mWVlmoouvDD30E0BO11MJoDx4PKiZEr3wf88pFKJxJ/FEUpv0Ypv8rzfLJZn2j0zeGluRHe/Q44a3n576oKf/15lU13w6GMCokAjChQhFKnz4+/49PfrTCEwoIFcNWKqbX/iXymeFwjHtfp7S2iaQqf+Uwl0aiBYUAoNN+DGSQSGqtXT/3w+URi/g79ThcJZ0IIMYuWassYyz7MYHcvbn2Mc8LruSC8gYd6biRoZqkr5CkUA+SHQ3gxnfB4lkLIRK8tYVLicPcCxuMJasNpLrx8E+eZdWi0YJOlAo8MJaowqCOAicrWA9BUBYZefoQDsOsw7B2Gp+xynZbUwbsvhp88DaNZWHNOuQftSL7v/yF8HUnXFe6+u57BwRJtbeVxxmefLfLoo3k+/enom+ZkRSNww5rXl/HUc/DBtfC1f/QpbKc8jBsAtQgD+Dy5TuHP/zN09oJTKH/tZLOsINdem2Dr1gyLFgVZs6aSaPT0ChnlYc3RKZcjw5qTk3AmhBCzqF1dSLTyT9j5yBcZ7XkZrSXIYmUf7dpuNvWt5If7PsiefUuobhmg8qIU434FftSnOKhTHAhCpULHCpvL23ZwdtTjDGUBaSL04uHhsYIw51OBOXGUckCHogPBiZWaRQdGC7ClC1oqy/O9dvTCkiT8xW3lnrTAEas6s1mf732vQG+vx223mSxf/ubbSCKhk0i8dr2xUWXJEp1I5Pj636oTsGW7gmGq+IaPUwLDB1UrT/w3gIOH4dxlEJ96R85xUVWFa6+t5NprK2fmDeckGdacKRLOhBBiliXNs0je8SOG7Y187SsqKf9vWdH2AinzCnp2NzHQm8QtqLRdsB8NByXg0NjSQ8+yJJnmBDeHtrNErWKRMsZOatnKOEEUCqhcTpgwr/Xw3HAu/MtTMJ4D14NoEDoaYNvQa9umBfTyEKemlR9H2rvX5eBBj5oahUcfLR01nL1RR4dBR8fxn8l483Xl8Lj+aZ/OMYWsUT5qyimCqsPaK+FLn4JgoDzkKmaKhLOZIuFMCCHmAq2KWPs10OzSWXMFO378F/w08m720QFtCkPVdWzcdQFLV+wg5ObxTOgrNlKPQ9BdhKKkqOUifk0VTejoKIzgsJ08Hby2jHFxI3ziWtjdA6YGZy0ERYXATugfB0ODggOLkkevZm2timnCwIDP5ZefnFtIOAS3rIXe/fCNf/Lp6VMouoACq1Yp/MWnTu7KTHF0iYTO6tXHsSpk0nIGgamf0TmfSTgTQog5wjAUzjtP4UdPQGrxasb21IFF+eDvkEffYD2DP6sl1J6jYtsIwcsKLKqP0KOexyW6QjUaFQySwaMCjRw+UY4yCb+m/DjSn1wKT+yCvAM3ngltb7EHWn29yj33BBkb82lpOXmT4BVF4eMfV7lgpc9//NwnX1K4/jqF1ZcohMMn7W3FMaRSJdatG55yOWvWlGTO2SQknAkhxByydq3KS70e9x88k1R/FBwgooCrQsZBNT2yqSjprhiXXtVLk16PocByoxyU1lLBv5OimxJ1GFxE5Ljetz4OH1x5fHWsqlKpqnqbH/AE6LrCxRcpXHzRyX8vcbxmYKdfIeFMCCHmkmBQ4b/+J40DTwT5xQjkujQIAZ4Pmk5J06EPqHBpSzSQMOH2kEZoYvJVHQZ3UUMBjxAq6gltgiHEWysPa059QUQikYKJ8yvE0Uk4E0KIOSasw3+7IMng0D42/MJjqD8B/Tp/GKE0fD55o8afL1Zo0njTlhY6Cjqn1zYP4uQrD2sOTrkcGdacnIQzIYSYg5ZUqXzoXItQKc+mJ6CvCxxPIVDhc88tKl++TUGd//ueijlFVmvOFAlnQggxB6kK3L4EllUH+f3Z0DsMDUG41lJY/BYrKYU4mRIJg9Wr32KlyAmVk6E8mVK8FQlnQggxR+kqnJ8sP4SYbeVhzf4plyPDmpOTcCaEEEKI4yDDmjNFwpkQQgghJlUe1qydhnKKTE/Im78knAkhhBBiUqlUkXXreqdczpo1RRnWnISEMyGEEEIcBxnWnCkSzoQQQggxqUTCZPXq+mkopwc5W/PYJJwJIYQQYlLlYc3DUy5nzRpHhjUnIeFMCCGEEMdBhjVnioQzIYQQQkyqPKw59U33Eol+5GzNY5NwNs3uv/9+br/99tmuxilN2nDqpA2nRtpv6qQNp26utWEqVWDdus4pl7NmDdTVKZM/8TQmJ7NNs/vvv3+2q3DKkzacOmnDqZH2mzppw6mbm23oTsNDTEZ6zoQQQggxqfKw5nScrTkElKZeoXlMwpkQQgghJlUe1jw05XLWrNGpq5OBu2NRfP/UXzXxyCOPdOm63hSPx2e7Kmzbto0VK1bMdjVOadKGUydtODXSflMnbTh1k7Xh8PDwN9euXfvZmajLI4888pTnKVeUSlPv0zEMB1X1n167du2VU6/Z/DRfes4GHMdheHjYnu2KBIPBhuHh4Z7ZrsepTNpw6qQNp0bab+qkDadujrXhZlX1CQSmbThy83QVNB/Ni54zIYQQQoj5QgZ9hRBCCCHmEAlnQgghhBBziIQzIYQQQog5RMKZEEIIIcQcIuFMCCGEEGIOkXAmhBBCCDGHSDgTQgghhJhDJJwJIYQQQswh8+WEgFljWVY98GHbtv/hiGu3Ap8BFOBJ27b/8oivKcDzwCdt294w0/Wda463/SzL0oFvAR2Uf6n477ZtPzMbdZ5rTqANFeBvgUsAB/iMbdvbZ6POc83R2nDi+jWAadv2IxN/14B7gfaJp3zKtu1XZrSyc9TxtuER11XgI8APbNsuzlhF57C30YZyP5mnpOdsCib+wfwf4LYjrlUBnwSusm17FVBjWdYlR7zsDkCOZeCE2+9uYJNt21cBNwJfnoUqzzkn2IY3Ab5t21cAHwK+MQtVnnOO1oYT178OvB9Ye8Tl64Fdtm1fDXwY+KuZqudcdoJt+Kr/CqyXYFb2NttQ7ifzlISzqdli2/bNQN+rF2zbHgautW3bmbg0RLmXAsuyosAq4NczXdE56kTa717gnyeuZYH0TFZ0DjuRNrwJ+NrEc3qA3ZZltc5sdeekN7XhhL8F/uYN13qBJZZlhYEzJv4uTqwNsSzrq8DtwN9YlrV0Bup3KjjRNpT7yTwmw5rHybKsS4G/P/LaRK/Em9i2XZwY/vgsULRte/3El/4UePWH0mllmtoPy7IaKLfhl05ebeemqbahZVlVtm0PHPG0bqAeOHCSqjznnGAb9h8lvO4HLgKeApqBu6a/lnPbVNvQsqzbyl+yv2BZVjvwbeDqk1TdOWkavg/hNL6fnA4knB0n27Z/T/m3lElZltVE+R/Nd2zbfmziWgflOQM7Lcs6eRWdo6bafhPXbwbeBXzetu3TrsdiGtpw2LKsGtu2Byf+3sibf0uf106kDd/CV4AP2ra91bIsA/i5ZVlP2radnZ4azn3T0Ia3MhEobNveZ1lW58QvDsPTUsFTwFTb8HS/n5wOZFjz5Pga8OkjgwVwD3CFZVlPUZ4Ee+/E3CDxZm9qP8uyzgIut237ztMxmL0NR/se/DnlnjQsy6oDlti2vX82KncKi/Daz00VCAPe7FXnlDTExPwpy7ISQNvpFMymidxP5jnF92Uu4dtlWdaVwKeAy4BngX8FngT2AUeu4PrAxByfV1/3JeCXp/vqmhNpP+AW4D8Br/4Q32Lb9j0zVtk56gTbsBf4O2Al4AKftW1720zWdy46Whvatv0Ly7L+mnJbLQY2Ax8FqinPfwwCJvBV27Z/Nhv1nktOsA1DlIcyKyZe/ue2bT8345WeY06kDW3bHj/idV9C7ifzjoQzIYQQQog5RIY1hRBCCCHmEAlnQgghhBBziIQzIYQQQog5RMKZEEIIIcQcIuFMCCGEEGIOkXAmhBBCCDGHSDgTQgghhJhDJJwJIYQQQswhEs6EEEIIIeYQCWdCCCGEEHOIhDMhhBBCiDlEwpkQpxHLsloty/r1bNcDwLKsb00c9iyEEOIIEs6EEEIIIeYQfbYrIIQ4dVmW9X+A/w6YwN/btn3HLFdJCCFOedJzJoR422zb/s+2bQ8DQSA52/URQoj5QHrOhDgNWZa1DPgWEAL6gI/Ztt1vWdZTwF5gKVAA3mnbds6yrE8AdwNjwCHAtm37SxPPvx34MnCxZVmfBf4D+JZt29dPvNdO27aXWpalA/8fcD4wwhE/fyzL+hjwScAB/tm27e+e7DYQQoi5SnrOhDg9/V/gi7ZtXwh8H/iHI772qG3blwH7gWsty1oK/DFwMXAlR/+l7i+B523b/sYx3vNOoGjb9krgfUALgGVZiykHv1XAZcCHLctaMoXPJoQQpzQJZ0Kcnmpt235x4s//Dpx7xNd+N/HfPUAlcCbwuG3bedu2PeCxE3yvV3/OnA08BGDb9hjw+4nrZwGNwG+BZ4C6iecKIcRpScKZEKenfsuyzpn48zuBTUd8zXvDc7cB77AsK2hZlgJcc5TyfECZ+HMKWAhgWVYTEz1kwFbgPRPXo8AlR1zfCFxm2/bFwMeAB97m5xJCiFOehDMhTk9/AnzVsqznKA83fvGtnmjb9g7gB8ALwNOUg9gbA1w/0GhZ1mdt204Bv7YsayPwdWBg4jn3AVHLsjZQDl/7J8rfDfwCeM6yrGeB9/Na0BNCiNOO4vv+bNdBCDHHTcw722Xbtm9Z1j8AW23b/v5s10sIIeYj6TkTQhyPjwAbLct6EWgDfjK71RFCiPlLes6EEEIIIeYQ6TkTQgghhJhDJJwJIYQQQswhEs6EEEIIIeYQCWdCCCGEEHOIhDMhhBBCiDlEwpkQQgghxBzy/wCaV5m58wr+3gAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 720x504 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing_df.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", alpha=0.4,\n",
    "    s=housing_df[\"population\"]/100, label=\"population\", figsize=(10,7),\n",
    "    c=\"median_house_value\", cmap=plt.get_cmap(\"jet\"), colorbar=True,\n",
    "    sharex=False)\n",
    "plt.legend();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 203,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x504 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.image as mpimg\n",
    "california_img=mpimg.imread( 'reports/figures/california.png')\n",
    "ax = housing_df.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", figsize=(10,7),\n",
    "                       s=housing_df['population']/100, label=\"Population\",\n",
    "                       c=\"median_house_value\", cmap=plt.get_cmap(\"jet\"),\n",
    "                       colorbar=False, alpha=0.4,\n",
    "                      )\n",
    "plt.imshow(california_img, extent=[-124.55, -113.80, 32.45, 42.05], alpha=0.5,\n",
    "           cmap=plt.get_cmap(\"jet\"))\n",
    "plt.ylabel(\"Latitude\", fontsize=14)\n",
    "plt.xlabel(\"Longitude\", fontsize=14)\n",
    "\n",
    "prices = housing_df[\"median_house_value\"]\n",
    "tick_values = np.linspace(prices.min(), prices.max(), 11)\n",
    "cbar = plt.colorbar()\n",
    "cbar.ax.set_yticklabels([\"$%dk\"%(round(v/1000)) for v in tick_values], fontsize=14)\n",
    "cbar.set_label('Median House Value', fontsize=16)\n",
    "\n",
    "plt.legend(fontsize=16)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 204,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "median_house_value    1.000000\n",
       "median_income         0.687160\n",
       "total_rooms           0.135097\n",
       "housing_median_age    0.114110\n",
       "households            0.064506\n",
       "total_bedrooms        0.047689\n",
       "population           -0.026920\n",
       "longitude            -0.047432\n",
       "latitude             -0.142724\n",
       "Name: median_house_value, dtype: float64"
      ]
     },
     "execution_count": 204,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_df.corr()['median_house_value'].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We see a strong correlation between median income and median house value. Next let's look at the correlations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 205,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x576 with 16 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "attributes = [\"median_house_value\", \"median_income\", \"total_rooms\",\n",
    "              \"housing_median_age\"]\n",
    "pd.plotting.scatter_matrix (housing_df[attributes], figsize=(12, 8));"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 206,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 16, 0, 550000]"
      ]
     },
     "execution_count": 206,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Let's isolate median income and median house value\n",
    "housing_df.plot(kind=\"scatter\", x=\"median_income\", y=\"median_house_value\",\n",
    "             alpha=0.1)\n",
    "plt.axis([0, 16, 0, 550000])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Experiment with Attribute Combinations "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 207,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing_df[\"rooms_per_household\"] = housing_df[\"total_rooms\"]/housing_df[\"households\"]\n",
    "housing_df[\"bedrooms_per_room\"] = housing_df[\"total_bedrooms\"]/housing_df[\"total_rooms\"]\n",
    "housing_df[\"population_per_household\"]=housing_df[\"population\"]/housing_df[\"households\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 208,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "median_house_value          1.000000\n",
       "median_income               0.687160\n",
       "rooms_per_household         0.146285\n",
       "total_rooms                 0.135097\n",
       "housing_median_age          0.114110\n",
       "households                  0.064506\n",
       "total_bedrooms              0.047689\n",
       "population_per_household   -0.021985\n",
       "population                 -0.026920\n",
       "longitude                  -0.047432\n",
       "latitude                   -0.142724\n",
       "bedrooms_per_room          -0.259984\n",
       "Name: median_house_value, dtype: float64"
      ]
     },
     "execution_count": 208,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# measure correlation again \n",
    "housing_df.corr()['median_house_value'].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 209,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaEAAAEPCAYAAADrvntcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvqOYd8AAAIABJREFUeJzsvXmQXNl13vl7uVdm1r4vKBSAh7UbaDaa6JUUyG5Si0Wb7XFLasfIY9oOeZFNWxOOcNhhT8TYHodjbI+HksfyWJJphTzjkYI0TYlUS1zVTbLZO8BGd2N9AAoF1ILat8zK9d3543tZmVmVVVlVKDQA6n0RiKrKfHnfve8l7nnnnO98xzLG4MOHDx8+fNwLBO71BHz48OHDx59e+EbIhw8fPnzcM/hGyIcPHz583DP4RsiHDx8+fNwz+EaoDl566aUvvPTSS1+41/Pw4cOHjx9HhO71BB4AfKStre008Pfu9UR8+PDh4wGDVe8A3xPy4cOHDx/3DL4R8uHDhw8f9wy+EfLhw4cPH/cMvhHy4cOHDx/3DL4R8uHDhw8f9wz3jB1n2/bXgaT3538A/hj4LaATuA38kuM4i7ZtPwz8GjKYPwT+seM4xrbtXwD+DmCAf+c4zpds27aAfwk8BRSAv+s4zge2bTfXGvvDWquP+x+mWIBCFkJRrODu/bfY6ri1jqt8DcCkF/R3ok3HVLy3k3OU/jZWEMsU171ea7y1c6r8/NpxtnJ+k03pzVBU7xULEAyBFYR8GmJNBCKxmutxV5YhNQWJTqxITGN5n7eiiQ3nbqxg1bmsaELvZRYhENHPfAYiMWjsWj2/m8tAalZzA8iltPtEE7CyDMvjEO+CaEyvhaIaywpqTaCfoSikFyC7BIkOCFiQy5Sva+nYYgFMEcJxcHOaWz5dPV4JletIzYJr9FnXQHEFXAvcLDT1QTis85kixJp03mwKCnnIL0OiG0IBKLiQmgSCkF2AIkAe8imINUOiExqa11+LYgEWJqCQgi+cPhr4dXNhwy8l95aiveA4zmdKf9i2/avAbzmO8w3btj8N/DPgV4BfBX7RcZwx27b/BfBZ27ZfB/4a8Bxa+tds2/4e8DRgHMc5bdt2L/A7QGmsWmP78IGbmoWbZ6GYh2AYBk9ixVs/tHFrHWeMKb+WW9F/6ptvg+tCUzem72FIdug9y4JwbFvnMO37YOY6LM/A7A1Mxz6It5ZfrzHnqjFK5y3mYWYYk2iH1MzqOGvnUfP8t96F2xc1VjELxSKszGstmSVoHYCGFtyTLxDo2Fe9nuF34Af/URuoMZiBR2BlARbGoLkPM3gSDp1eP/flGZi4oE03Patjm3q12abmdEx2WQaisQfsp3E/9jd03d/4LzB1GWZvQj4rg4AFbh5S01A0YBWhbR+0DoIVgEAAMgsQTkBDEzT1yADNXodCTotp2wsLo5DPidCcaAdjNH4wBsUMtO7RecMxvR5tBCskQxJpgC4b09gLczdg8gpMXQPj6twGraehFaJx6DoCuUWIJD1D5cL8TVicgEhca2rfDzNXNaflKc2zmEeWKACBEMRboLEPwiHIe4YuGITUPKzMyXDCa0DLZv9P7mU47knbtv/Etu2v27Z9GDjoOM43ABzH+RZwyLbtfcBFx3HGvM98AXge+BngNx3HyTmOkwf+k/fa88C/9cYYBy7btj1Ua+wPbZU+7muYYkEbTziG1dgJ4Rhm5Ixe/xDGrXnc8Ftw421tOIlWmHLgwh/rqbm1D25fhqs/0OYzNwKzN3TcVs8RDMHZ/6Y30zMQS3obTUCvB0Pr5lw5BolWnXf6OixNah6j7+rn8hQEQlXzWHf+QAjOfEnGLtGhTX/ikv6ONcKtc3qtWNCYZ74sL8SDu7IsA9TQBB379BR+5ksyYI2d2qRnrmGG36qeezAEy5OwPK1zJdu0SZ9/SUZ+/qYM09IENLRonPHzMj5v/VdIzcg4ZBZh4ZYMYC4F08OQywGuNvzZGzB5WfdpaUqb9+ywxrt9Ea69Cm5B13JlDq58z/NCUhp7+mrZSC3c0gY//BYUMjB3E9yiDM3kJZh2ZMDmx+H9r8P4B/KEAOZuyVguTwIWZOZkAK++IgOUmtEcb1+BhXEZzcyirvvV70PeM66mKEMoV0jrdPOwPAcz12DGM8qFFa1zaVzrKxZhCzbmXhqhZx3H+STweeD/orzCEopAN1AyQDiOMwW0r33d+70HaPOOWft6rbG3jMnJSZ5//vmqf7/7u7+7nSF83K8oZKGYxwor5GKFY9o0CtkPZ9xax+XSkEvr90Je/+HdAoQi6Ck04HkNC+Wn7UJ+y+egFI4yrsaNNWrjcb1wmRduqhqvcoxCXuc0rsJW4RgUcxBu0DiBYPU81p4/ENTmjatxKIJl9ERuoXFDEW184QZ9PlMRPU9N6bWGZm3IoYjOl8/oSd6yFIbKpavmrhBfVkYQA8Got1nmNE7OC3UZFBazLBmdpWkZi2BQ192ywPXm4roV6wACYc+LWVFoa3lKczdFKLoyJMbVNTBF72e+4mZZ3r0oeve5oDELOc3beCfOp3XNgmEIRuQBFjLl+xgIQMBobm5BnmYuLUPh5vW6KXjX23toCUW0nmBQa7BMea7rEPA+W9T9M0bX1DVag0Xpmrg1PlyFexaOcxznhvfzum3b85TzQyUEUf6mt/SCbdudwOza14E+77VZ27Y7HMeZXvP62qtY66puiK6uLr761a9u5yM+HhSEogoP5TNY4Rgmn9F/7FLO426PW+u4SBxAv4fC2oQCIW1EoVB5o2ho1iZhgFB4y+fAy9vIgIUU+gqG9Hso6m0srB/PG4NQ2DMYAW1c+Yw2wvyKxnGL1Z9be363CJEEEPA28SAYyzNsaNxCTqGo/Io+H2sqryfRqddWFiCa9I4Nyxjm0toQA5auY8XclV/xDA+WNuZASHMPBHW8KWoD9cJ8WBY0duj4pcnyBl16fA8EyusIBGTQAgFtxpY3B+NCNq2/QzGtzy3qvG4RrHDFzTIVOSHP2Lt5z0AUyp81KBy3uuEH9XfpPrqutv9iXvN1jWeEvZCfsbxwXmkc4xm6gI4xLmRXvPtTq+ecCybgPbAEPYONrjtGv7su3K+ekG3bf9+27UPe753IW3Fs2/6U99qzgOM4znXgmG3bPd5HPw/8PiIx/JJt22HbtkPAX/Fe+wO8XI9t293AYW+Mq2vH/pCW6uM+hxUMYQ2ehHwGszQF+QzW4Mk7Jidsddyaxw2dwho6pc09NQddB+GhP6PQyNwY9ByCAx9TLqVtr/6l5rZ+jmIBTr6gNxMdkFmGZCfg6vViYd2cK8cgNadzduyDpm7NY+Aj+pnsBLdQNY9153cL8NjPQ8d+rSmWhN4j+juzpLGiSW2ouRU4+UIVOSHQkITTvwwriwoJRpMaL96i8Fc4Du37dR0r514sQGO3jEr7PlieVYL94c9Ac4/WlGhXnmNlXuP0HoMn/hI88YvKwVmWjH/rHhm9aAK6DsgwY7S2hhZo6oLO/fo9FNZ5wxHoPgoHP+49VGQh3gYHT+uYSFJjt+yRd5pZ1hwCQRh6XF5h26CObe7VZxNtQECfe+Sz0PcQJNtlaNoGdGysESxX+aBYHPqOQXZRa+0+DB17IdokAx4IicAwcFLEjESrDE0ohnwWCwjqwSjZCp02dAzqWoTjuofN/Z5xD8IWPCHrXnRWtW17P/DvgQa0sn8AnAd+AzHYJoG/4TjOvG3bx1EuKAC8Afwjjx33IvC3vCF/3XGc3/PYcf87cAqF3H7FcZz3bdtuqTX2Vub60ksvvdzW1nb6ySef3JW1+7g/4bPjfHbclthxi5MyNMGoPKlS6O7idzTfZBdQhIkPYOgJz6vKy3vZ97TG3IwdZwVh5E0Zj6DnZboGhk5pky+x43LLyp25eV2vPSexWgeq2XHFrPJNY+dkqAOe59L3MAw+rvOG43DlT8re4+IUzNyQoSSgHFl6HroPQqCBKnZcQ6tHiKm4FuvZccfqsePuiRF6kOAbIR8+HgzcrQeJEtYy/CyPAWiyKYzzfZEuSnOZvq4NOhCqOrbuGmqNtTSFZX8cK5qoPrbOet3UrIzQzTMwPwrNAzD4KFYFa3Dt+YxbgIvfhT2PyXMyRSgWsA6erjrHRteiBuoKmPoq2j58+Hjgcbdo9iVUMfziLZh8BjNyxgul1cjrxVth/zObeoY1sY0cpRUMra8XWjvfxk54+GeVP8tl4NhPYlV6lmvzdcUCtAzALe9ahqJw8oWq+W92LXZi/H3FBB8+fDzQuFs0+ypswnbcKP8XiMRqhgU3Q9VYCxOQnoP+E9vf3CvmawVDWMl2CEdkFDc639KU6qdijbDvSTj0CRg8CeMfVFHkd5tR6ntCPnz42Bbudthr2yhtinHVRFrhGCazpNe3Mb9N11XHQ7HirfKKduG6WPFWTN9xuPGWGGbDb+IOPU6gIkRXF7XmawW0xmKhan6VczfFAlx/DSuWxKwsqN5peQawMAee1rG7zCi9D75BPnz4eFBwt8NeO8IubIr11mUFQ1KyGDkjA1fKg1Ru5puEx7YDUyzA2HsiEsyNiLU2fh73qc9t2RCtm29J4eL6a5hgGNN/AsujsJcYhARDYkYGw5jsMty+pMGS7RBNVofc6lyL7cAPx/nw4WNL+FDCXjvAndLs16lBYFbVFqrOE29Vgt7+uH5uYHxLrL8dX5dCVqy4mWHVByU6xK679tq2xizNl31PibXW2Kn7VsjBa7+Nufwy5sormPRc+TOla5lZ8jwgoOcIViy5GnIzxQKGAPR/BPY9tem12Ap8T8iHDx+r2DQktUthr7uBOwqHrSoqWDB6ThTszDKm9xhW60D1eep4O7viKZY8uFxa4bjJSzJCbhEzeHLdnDZDab7GuLpfbkHSOgGvtsiy1pEKrHgr5vCnAAuiSYXmPO/SZFNw/puel2Sg5ygcOi0ixg7he0I+fPgAtIGaK69gnO+ve0IGqsJeUENR4R7D2qA+qC5K6hGj7+n3ktLCyJnqhHwd7JanaAVDKk5dnof3vg6zI4ClOp7x89v3sCrvW8ETn43EFUbbgFQQiMSwDjwNbrlwmf4TcOtHChE2dapQefZGTa9xO/CNkA8fPra0gd4tdYl7haqwWfuQFAqyKSlCYOQVXfrOemO80Ri7yRozpVYMngQSyJjsYLwqtYuVBY3ZsU8Fw5tRwNeGHyNxT18voONDEXlUJY2+HeLB/Pb48OFjd7HFUNtussDuJapaO8zegLY9WmdTHyyOS3ImEl+fkK81Rin01n9iV1hjYqi9DrEE9D/iCZx6bTMwO/I8qxhwQ4/DzbOY2ZsQiVOSN1o3h9I99opkDZS18ApZzcl1qzX6doAH8xvkw4eP3cUuFUluB/eK6l3V2qHUyiI9Jzmbmz+SB9LYuZqQN0tS7TZQLVm0pmCT0XMyRKPn7og1ZhbHFRpcHJfqd3pGIbT0AnzkL+z4Wq3mhzbwWlZljbIpsfNKvZ8qmHTseVSyQNNX9aFOG/qOQyGLWyysK851f9lqDfy62diVxDdCPnz4YGsU5N3EPaV6l4gIIU9RO96qEFxDM/Qf13vJjvUJ+euvl+fbfbim52hF4jv2FFe19Ebfl2GM2nD1VakYtO+FYz8NM9dxG7t2lvuiwgBHE1jJ9lW1A9N3XPmezJL6Vw2cwGrswixNiknXe0ysupIyeGO3tO2KBfjhFzFN3ZCew7QPSVR18KQa78GjwHc3m5NvhHz48AF8eKG23ZZ92TY8r0/9fCpaWbhFUZlL3szSVDnMNnqu2usZP6/izxqe4048RTc1q0aGJS+j/zhMX1PjPYOUvsMRuPYaZJYw8ZadGe5aYdf0PFz6jlpVFAtSJg+GMLEm0cQDQV2XKUctKaIJrb+YlZp2MAQjb8P+p6SK3tSl+zn4UYDwZtMBn5jgw4ePCuyYYbYd3K1GgltEVWuHylYWXguKQGPn+oT82vkaV20edoGkYYoFuPyK2o4v3Yb5MRh7X6GvjgPyuoJBePf3YX5CbbjdfF3mXc16pVoMR7cogxdLql1FLKnOrZlFkQ4iDaUR1cXVuDJE6VlYvl2mZy9OlpXAi6uN+io79tWE7wn58LEB7jt5mi3AzWW0eWzSAuFurmsrbSCMFdxRAn83523FWzH7n9G1OvYzWAGratxKb8b1Op2azHJViM5q6oGmnprtMbbaVsNYQXkgt95Vj6BgCLoPKSfUdRi6DslIXH9TPwdOABZMXhWjr0aNlikWMAvjMmrGXR/u7DwAt85hAkEV6PafUFtwLBm7tr2az8qSiAftQzJEhZw6y0bjajZoLI2dW9E4+XRpApX381K9e/Fg/M/y4eNDxn0pT1MH7uRV+NFXVjdB9+QLBDr2VR9zF9e12djr3uvYD9PXtpx/2u151xxvTauEquM86RzTsQ/irdXzLRmrLc6xipk3cUG08BtvQUMTtA+qP09Tj9QImrrKPZfCDfJYLAtWltWUbo3hXg3rjbyj3M3ACQhGynmfq6+q0NQUZYyGHpdB7jkqlmCpbftDPwNHPqVOsaPnlDPrOACpGRg543muXhfgYlbK2+l5aOzxclj74NqrAA8Do5vdCz8c58PHGtyv8jSbwc1lZIBiSegY0s8zX64qtryb69ps7FrvMX1NrQ7qSODsZN71ZHO2Op4pFrShY2Qc9j2uue9/Zt18tzVmiZm3PKmQViGrpnPpeZj3GHHB8GrzQiuakLJ1SQHbLUAwUK4fWjt2IKD7H0vCxEXlvfIZEStKhabNvbB4W8cD1qHTUj9o2QM9R7GOPEsg3lwVmuToT0HfCRmY/hNw4OMylslOnevop8H+GOx/Bma8fkowveGN9eB7Qj58rMV9LE+zITKLml+sV3/HGvWknVlUN0+4u+vabGyozSQzxZrex7bGrle7U8sb2eJ4ZmFcHkUsCVjyBLDWtUPY1hwrmXn5rAo+C3l5EqkpiCT0ENE6WH2elj1w9QfQ1KuQWd/D8jgqxy+NnWjVfPM5eTKZ5dV7sFpoClWFpla8FQ4/WzOUaAVDuJlFuPZDkSaiSXmyiTa49Cdqx97UqfncvgSDjavXYistU31PyIePtbjP5WlqItak+WWW9HdmSX/HmsrH3M11bTb2nZ53i5/fsse0hfHcXAZGzkIoplbZM8Nw7vdh9D1MLr3jOVYx88LRCtpzTAZm4IQ29YZmTLGAuziJOfc1ePcrMHtTLcH7HlZobu34pbGXPe9q9F3lljLzkgGKNZYLTQu5dYWmG5FSVq+rQeG46etw8dtq4R0ISRg1ECoTTKDqWtSDb4R8+FiDB1GeJhCJwckX9NQ7PayfJ1+oIifczXVtNvadnnernzfZlIxvwCMXbMC6q9c4zk3NwqVvw9g5cPMw8YFIAYEQ9B4RfbtWqK/7MGRTm86xipnX2C1vItaomppkh0gBKx4r7eoP4LX/DLcvQnOPam+Wp+DaG5BN1W4l0X9CzDqQsTrxGYg2SoJn6JTGX5xSKK5tL7XUEtahpOo9f1OhuFAYsssiM3QflL5csYBJzYMVkCEryQRBR737e//+r/Lh4x7iQZSnCXTsw/3E5zdlx93NdW029p2et97nVxPyExckqukl5Df0mIIR6D6qNtZIPduUCixvnpVhSLaXKccdB/Th5l4l6SvCYFUhQCsAfQ9jNfVsuMYqCZ3jf7ZsJENR/T78hijQxujf/Ci09CnM1nVQyf+hJ7DizevHjsRVWNrQLMJHMLSq+GDFWzHHfhr2Pq41RWKYUFSG0wquUztYZfC5BjIpmL0lo+wW5MV12jD0BAy/Va2qnV1aXaOB1+rd2/v/f5YPH/cIuyVP82EiEImVc0Ab4G6ua7Ox7/S8G32+UgWA/U/CrXPyFgZPsvZJf9VglApOB45jJTvLBbODHy3nM3qOwNgHoiDnVmDfR+XBVBi2WoW33L6khH0NrNVks6DqfhlTxBi3TCaINGjTz6UUGsQSYWGjXFooKkKAZa0TKF2nl5fsgOVpTKIdUjOrzD/Tf0LnnrggwdPx85BagOvfFwmh6zB07JVxjLXoug99VIa7WFgtPDaZRYDHgW9vdl8frP9hPnz48LEWlaSAcAyz/0mxzNZ4C1XN60JRKQFMX8c0tJaJBFCuYYo1YfqPq6C1oVlEAtdVqAnKDLzdJE14nglj78lby61AvAWW50Qk6DlKybDWqknaSH4JqNbLCzdIpqdjv3JHXQcV6gvF4Idf1BwjCXk+6VmwDOz5CCxNi5odiqmVQz4NxsWKt+scgRAms6TQ6I23ASL1bp9vhHz48PFgY434KsUCxBrXewsVxsq4BXkZuTQU8/o7GNZn1m7iD/2UwnTehm8yi3DllXL4LZ+pW3jr5jKS3IkmN5UqMqlZ5XQWxySJ09oPg6fg4CeggjiwmUGrFbo02VS1Xl4kLnJCMCQGXTgm4zftiLwQiUEkCrcuiQ2HkXcWblA4sOugjHisqUxCCISUi7QCClmOvANwoO7tu8Pb78OHDx8fGrbz9L8uJ7NWKbx9SGKhKwsKp5U+s0H+yeCRH66/oeR8olUGL5dWXmWN5+GmF3TeQhZuvCmF7mQ7pueIvKw1HpPqkt5UWKvtCcgsAAHNLRIrt1So9OhiSWnJDb8Fh5+tqfhQufZVvbzsMmB5hihSIhHIUMUa9XsgLIOSS8tote6BqSvelUDXKxLDDJ7EXHq5nBfqOgS33vHCh+Tq3VPfCPnw4eOBwHaf/tdivbGKwFOfW21TsI5pViuXND8GV16WtE6sCXqOyBgMPaHPlDylc18Tq8242uj7jyusBjBxEdNzbL3HVOrRY9xVgVQyC8ovrT1ui+3IK9dj+k/A8JsyLmMe+WL8ghh1uRX1VJq9KSWFcEy5tWSHzuMiqZ5Dz8K+J6qJF9HG6rxQZgkuvlzKdT1U7776RsiHDx/3PbaivL0V4sNOWHpVKgcrCwpPLU1BvE0bdc/R1TDZqsrC3IhyJsszCsOlpqBtSCGs3Apkl7EOPF3FRDPFggxP0XMeinmwaqypsh15rBGIqOZn/DxmA1aem5r1DFZRIqnHPyN6eIl+bZ/GCliqgRo9p/xXz1GJtCY6Vhl8NcVtC9mqvJAp5OHmO1KZgFS96+sbIR8+fNz/2AW1h8pQXokObWBrdTKlfIpltDGPvq96nmIeeo+VxyhkFb4KBESDXp4WnRlLBiO3Is/j8HNYHiuuysNbWZBRaN0DGOh9WJ7O2nW2D0lvzhiwqK2gQEWPohtvy1sJRZXXWRiFpm6sSANmaQorYMnARBOYEn28RNsOhlbnuvY6WsGQRFjdAia7LA9q9H3ljWLNsIVWDr4R8uHDx/2PbXR+LaFyszSZxfJGn1tRiCkc25oY6tp8inEVhus6CCA17cpjI3F5Jrm0vJqmPr2X95QKBk+u1nCt8/AiDaJP9xwVI88tyCh566yimOdzej/WLCp5295q1YfSsZklacjtf0Jzq0HIqPzcqkzPzbOYNaHPtSFR075POnH5jEJ7TT3g5qD/YWhoBDhf79b6igk+fPyYoJ5w5/2Ozea/XdUFNzWLufIKxvk+5tJ34cr3ZHQSrQqVzd4QAcGT9nFzmfrnruw/1NQNgSBr65CsYIhVZYL0rAxASy888ufUBnvwJFZTT3mt2ZQ28GJenl04Jtp0MS8lh4p1VhESGjvEXluclFEs5soCp6whL7T0yvDcOidOQfuQjOTKghhx3Yerr12JyRcIVckfublMtSxSIARn/5s8pY59kgZqaFYfpP6HFPqDJurA94R8+PgxwP3eemJdCGfN31uZ/1bzOeu8i9S8Ci8bOxVCM0a5mWJe4ai5UbjwTRWJRuIwdGrTc9dSF1h37PHPYA59Elbm4PZlbcjBANbeU9VeWamNw8q8NvWWfnlBh59bf45KinluReG9ln7V8oRicPsKZnFC5IQ14UszcAKu/lC6bw3N8NjPiWwwdRnG3sfcviTShjESKq3F5Mssls9fLMiry6agkMOECuq1lF2WksLMMDT3A4zU+274RsiHjwcc97xddh2sC+G07NHmh0Jipkb77I3mvyXVhTUbMLGkQnBXXxUjbuqKVKmDYW2a4+fVyycUBtdVcv74ZzY8t7WFNVvBkApl482YloFyLgpUYxSOieAwfkF5o1gT4ML8Leg65GnurVG+qBRJDYWlvj0/CnseWdXLK5ET1tVO5TPKUeUz8gIzizA7IsWIRk8xYvgt73p5kkVQzeQr1QQtTcrILE7KgFpAU7eUF2Zu6HP5jIwjrNS7Vn44zoePBx33uF32ZlinbJ1Nw7f/DUycV1ismJNWWmmzZBfmv0bRmnxG7Q8CIf1sGVAjtuVp9fDBFX063qoNeOJCuZHcHa69NM4qe65SZLWYVygtFIbuIwrXdXpFoDXWXhmSJDUnLyjh6dsVslLg9lSy14m0jr6vPE1uWUSJ+VuAkWJEsaBrnktrbsZ4HlZR7L7sstqeR7wurKPv67jlaRh8VMekF+DCt0XaSHZo/MXbADN1b9cdX2kfPnzcW+wgaV8Pu9ZKe61KwcxVbXLxdpEDSmGbQHDX5r+uHsgtQs8xUYYLeW36S9Ow95S8g/ELsNr5xsCWfJ3NUSu8aIxRoevouwqL9R8X1doKyB2wLK+tQ1yMs2xqUyFYYwVlOAOBVd02XLfcmqEkIpqaLX1aBIVIXMWqrQNlgkI+4yljX4D0tGqJWnqhy65i8q0KpOYzuneFHFDUtS3mFOorKUnoMu4B3tzsWvlGyIePBxxbVgzYInY1v1TplRijTSsa9/rpxOWJBAJKao+e25X5Q43N+tqrUCwoB5TPyDNLtAFIqHT2BljpVebblprtbYCa4dHht5SPWhj1Oss6yhcNPALJNm3ogRD0PqScyrVX1zHTVtdWERY0Q6cUukzN1bxuVjAEiTZMMAzj7+vcgaDH4DMyynO3tP6VZVgah3BCIc+5Meg+Un0fSkzB25c0RiCo+zg/qlCnW9Q5SkW68BPAf9vset1zI2Tb9peA3wO+BfwW0AncBn7JcZxF27YfBn4NPSv8EPjHjuMY27Z/Afg76NHl3zmO8yXbti3gXwJPAQXg7zqO84Ft2821xv5QF+rDxxaxEy9kt1o07HZ+qdJAShrGUgvo5WlYGNeI501lAAAgAElEQVRGtecxAo2dq/UpO53/avirWCjrrHlK1aZkpJdn9MS+/5nyOQ6dlpHw5Gk26rGz5ftSq6ZpYUL9d1r6lAuKNStc1fsIzF6DSFKb+95TClWWckaZ5SpJnrVz2KpShOk9BiNnpIK9MKZ5FAvw0M/C7HUYeFT9kwrL8oI6D5TzSF7t0eq5uw9prMZOKUg090GxCCf+LCx6/Zna9opsAXWfXu6pEbJt+zRQ0pn4Z8BvOY7zDdu2P+39/SvArwK/6DjOmG3b/wL4rG3brwN/DXgOGaGv2bb9PeBpwDiOc9q27V7gd4BPbzK2Dx/3Fe7EC9mVFg13oQV4lVfieTwUi5Ca1VP/xHlMJKbj7sR7u/yKuqEujkJLP2bPSTh0Wg3d4q0iCJz9sp7Wp6/jnnyBQMe+TVtbV42/5r5UiprW8haqwosBj0hw+5JCbsaI0TZxHhrbsZLtOu7mO4AXlhv/kQxBIYPpPYaJxMs1QoAZepxAY+fW7nuiQyHJSAz2P6WczfSwCCKTl2HvR70WEMFqurcnabSuZ1L3QbVxONCgMF4uAx0HsLoPl2uzchn4L3/lYr17d8+ICbZtB5Ah+S3vpYOO43wDwHGcbwGHbNveB1x0HGfMO+YLwPPAzwC/6ThOznGcPPCfvNeeB/6tN8Y4cNm27aFaY38IS/ThY1vYcnvqu4m71AK81Do60NgJ+58RY83+GFaXfcfrXJXKmbkOhTQ0dsmrmb6OGX5LbbJzGTj3B5Kq6dyv85/5sl6vmN+GHtDa+3LpZcyl76oO6cormPRc9VrX1DQxdArC4XL763xO/4p5MKZMDsCSgb72htYzf1Oey9UfwvXXVdszMyxdutd+G3dpqu71cVOzXjgyq3HOfxMuflc5m4YmGZrx8yrAbWjVw8HyjHJGvceqa47irTJUBhmq+VG49a7Gdr6HWZxYNcqBhiTAf603v3vpCf0S8NvAoPd3cc37RaAbKBkgHMeZsm273Xv9csWxY8DHgTbHcabWvN6zwdhbxuTkJM8//3zVay+++CIvvvjidobx4WNz3AUvZLvY7fxSzXOYIiYQwoom9fedrrMklWNcPaVH4qIgG0+1oJD16lmyEOvVZ2KN2mgzi3WbAK7qq4WiXlfWkIzA3sdXPZh1OnZrwmQUsqI6L96GlVnIZbVxv/+H0LUfEu1qKheOQdcQvPcH0JAsF6+OnIFQRAWw4ZjUGrIpGH4Dc+ynt1QzRfugjFpuRSy2eAtMXPJ6Cp1TD6ZgCA4/5ylDoLYSblHXMdkOt88pjJdNwaMvwORF2Pe4jhl9D0bewQw+VllrtVDv9t0TI2TbdgvwmOM4/9G27c95LwfXHBZE+Zveis91ArNrXwf6vNdmbdvucBxnes3rtcbeMrq6uvjqV7+6nY/48LF93AWW205w11ub7/Y6S1I5VqBseIwpG6RQVE/voaioxSWl51DUq8/ZHCabkqcQ8MZr7kVacJsb0cowmQF5YYk2NZNri0mxuvdIOal/6z146nP6vX1Im34kLo9peRLa92q8SANMXpEgKtbmxnttgWswDNGgZpRdViFtdtFj5gXUmTYUk9cFUsZeWdL55m5CvFnXzbgKJQaCOv7mGV2PQAACAT3E7H8G4FHgu5td33sVjvvrwKO2bb8M/EPgnwJh27Y/BWDb9rOA4zjOdeCYbdslcabPA78P/DHwS7Zth23bDgF/xXvtD/ByPbZtdwOHvTGurh37w1mmDx9bx3alae76XDYIT+3K2Lu4zlWpnI79YnYtTWrz7thHiWQQiMTg5AuS3Jke1s+TL6zW7pRCgWulg0yxoC6n/Q9rzNwKjF9UTsT1jqljRFcT+v0nYH5CagSTjjqUNjRD+z5J3fQew4rExczre1ikjcyiGIQtA/I4jGc88hm9VuoSuxHWFri6rl7vPiovyC14LSmOysiEYhXN+lZg+C0V92YXdV1LnuXACRkg0LUsFlB8zyq3Jld77/tTwNRxnH8F/CsAzxNaRn3If8O27X8MTAJ/wzv87wH/r5dDegP47x477j9T7l3+647jjNu2/RXgCdu2/wSF3Erkg/9lg7F9+LivcNe9kPsEd7LOmo3tKqVyKtlxFeMGOvbhfuLz2hxjTZBPY0odUivFOCvJB8GIPInGLkyiTeSClQVRq29fWtfIzqyp7alK6GeWFb4KRuXNeO0X6Dqo81iB8mcrGXteOI9QHI58WjmYQg7C0ZrGe931KbETM3mvUDcvQ9bSJ8MYa5SBmrioOUa8LqtzN2DPSXk3yW4orKhhXbxF1zjs6vM3z+r4zJIKYUfOKDy35yRAvu53wRhT75g/1XjppZdebmtrO/3kk0/e66n48PGnHmtZatY2a5hKG/Rq7VA45oXTliXaOfiRcssF1wX7J6qPy2fkuR08rQFrqXSXjFK0UUYuGJIHc/VVmHLUnmH+ljZ8Nw8HPgZtg1hrNOuqVMBnRyQWujwDi+Mw9AR02VWfMcUCZmFcOnnGrbo+Ve8V8yI/pGfVNC8Q0FoT7fKEpq6opml+FPoeEnmh54jOHY55yhNh6D+h4lUrKGr2O7/nhQvlhRIIw699qjPw62Z6/Z0o48fzMcuHDx9bwq4pI3wIqEqy16ihqYcqA+a1SLA69knJYXlaOY5iHlLT8hJcVyGyzYgaa9Stq2qrBj/qSdrMqAne1R+IebbkMc9ijQrHbWBESzklUyzIQ+uyVdMTTcDkJWgbXCVEmMyiGIIj78gIDJyAYGT1fUBU7GhCxjS9KOMaisnIBEPqMxRpgL2P6+f1N+Tx9B7z2n43gf0TIpZkUyouLoXu2ocU0ku06RoFQwq1bkE77v7+1vnw4eOu4X5X3l6HyrbWFSytzdpal7DOUHgSNSYYVdjp1jmpDkTHoKFFRqO5T+Gyw8/K89nIWG/EaiwWpEQQaZBnkc/Ki8gtKZFvXHjuV7A6hjYvCi6x82ZvKGyXaIfUjFQXOg/KINw868n3JGWEJi4qHFapwVciKKx4Om8XviE6e+sAPPwZGZNCDqupW9er57C8t0svKyTYcwSrsKL6qOuve3VFllhxw2/JkO15BCspQVSsAECEOt1VfQFTHz4eUGzWf6deb6H7oiapAm4ug7s4uVq3UxOVba1DEXkEkQYpR9eb91qR12hSDdiuvyrjE4oo8T/vqTjkM2KuVQqC1iBqmGJBRZmFnEJ6oJ+FHORS0DYoryszr1xKwNN7S7SJkLA0Wa4R2ki0NRQFjIpIw15DunCDJ4vjpVOKeXlWgRCqNSood+UWFS4rERQyy6pBcl6Wp+e68sw++IY+G4lLJfvmGSk8LE4qJHfwJxReHH7LU6XIe1T1SzpvLCmVhJvvSh1icbIkYPpL9e697wn58PEAYjMvZksezi7VJO1GOM+dvAo/+srqOCUlg7Uoy8+841GBQwo75bP1572WFj7pwKXvamOPNop23dijMFxTt/TQIglt5jXYZ6s5luE3RV/OpcGyMM29MmQYsercAvQ/okR9IKzxAmEIFiCfUnhugw6nVeseekLiopEELE9JMgcLhp5QS+6gN3bPEXl1yzOaU8d+6dD1n1DzuuE3VRNkIfmd2RHlc7Jeo772IXjtt2Usg2HRwqeHZVCM6zXBO6T3MktaXzYP09c02WJBxnX2hlTSoW41rW+EfPh4wLCZvhuwNe23XajV2Y1wnpvLyADFkiokzSxJyeATn19tgV0Jq6lHxZAbKEdvhKoi3OUZuPgd6D2q5HyxIFWCSFJtCIzRhlwsVOV/VkkN2ZRqfW68Je20nsMKgY29L+JBNKG2DNE4LE7JW2jbC6l5Jf0zRh5cJAE33pFxaOrZlKYeaOzEffwX1XDOekiemyfbA5QZcMW8GGyNC9DSixVNyrN57bd1nnwGmnq9At4lr9HfAnTsVV6s65ByQA3NELDgxlm1Du9/SEY/HFFt0Z5Hde9XFsvXwCs+Zsop07whV+874BshHz4eNGzmxcCWPJw7VUbYNaHTzOK2lAysYAhqKEfDenr0us+WWhvM3ZQRaeqW8VoY1ebctgcO/AIkOtZ1NV01uPmMjE3rXs9oR6RCDfq9kFXeZmFMXkk0AY3dku05+Eno3AfX39R5o3HotvX7/mdW2yXUgpuaLQubYqoNENWUd1MsiARhBTH5rNdyIQMz10QxT89Aa7/yOIGgWp4f/4zyO7Ca67FCMentXX9duTELUbyXp2Wo7Z9QwezZL+mzpfqhbNqT9XEB6shR+EbIh48HD/W8mC16OHdUk7RbEkOxpm0rGaydt8ksqlvpFjwyKxjCNPXKexo5o3PlVrS5PvRnSnpnVahi5RUyCk/N3vCESANlPbhgWN5AKKxCz5xXO5NLyxgFw/J+ug5AvE1zMAUIN8joVZ6vsvV5LiMPKNaIFe9RXmf4TdzDz1V5i6tsusXJssJDIChvJTWjHFiyQWsoFsH+JAQDYD+j+XnXvpoNGIKWQYg1iFI+dR2cVxVeTLSJ/LD3VLVnGnZh6ATqH876uOoa7MgI2bZ9EHgE9YmwHMdxdzKODx8+to+6Xsw2PJwdK2/vkvROIBLDPfkCnPmyPKBQFE6+UDMUty7/tBk9ehOPzAqGMF226oIKOYWNeo9u7ImUWHnRpAxQLCHxzqYeharwJG+6DymJP/aBQlJL04CBvSfLjLHskgzAyoI8p5b+1eu2rs7HCijHNHVdbRaS7ZjmPnlZS1OQX8E9eLrKI6pSeJgZVjuF21dUtxNp0FqSHRBtUo3S/ChcfU3fgb6HRNsePIl18LTmcvMsBIzXuqFLnVmT7XD9NeWPxs/DI88r/1PZ0yjeinvspwE+qPcd2Pa3z7btvwz8T0AXMAL8AvD3tzuODx8+do7NvJjdUF2oRzjYTaHTtUoGtQzQhvmnNR4ZwRAsLWGyKax4c+0Tljbix/9HJdrDUUjNYtILCgFu0JpBxaUFGZ+JS5C/gfojnYahk2KEGRcGH4NHf06fnTiPlZSRsMIxTCQBp17Uxj95GZZnoe8hFaNOOeU6n/YhmLqmAtDuo2U23IVvQPOAR9G+rpYUj/8iVkNTWVmhpPAAIiE0dqs4NhSWB9bUDVNXVQ/U1KdwWyShcGQ+g7n6Kuz7mDrAxhI6fmVBhjbaVGb6JdpkeEbfhaM/jRWwVh9CTDal9g6wt97934kn9LeAjwHfdxznTdu2/48djOHDh487xGZezJ30Ftoq4WA3JYYCkdiGatabEjEqtdEKWdG3cyuiGq9RIFhFyahgIBjU2EszkuHpPADxVoynBlAlfXPxuxrf8ipbWgcUNuw6IC+uspBz7D3lj25fwoQjZU8oGBYLLxgWAy8UVp3S2Puw7wkRNIJRMfc69nvtvqPa7OduieQwfR32PQ1NXTBzA177ImbgIwoX9p/Q9Zgfg4vf9lh5QTjyKXloZkY5neyy8kZzIzJQzX3QNiCixtwt5YuKBb3WthfGzktbTndebMLMkj6bX5GRPPA0ppAtf3eWpgGO1L33O/i+hJHxMl4n08gOxvDhw8d9iO3WD91NodNVrK3xqaipWRVDzaZU4Q+w/wmIJjAjZ3BzmXX1Uus+U8iJ9RWMiIqcW4HXfhtz+eVyr6Boo3IeJz4jJpiFju0+ghVLan4emYGx93T9mnsUFrv1nmpn8hkZidSsanAakiIFhBoUOguGxUBzi/IKJx2F3SavKqQGyr2k5tT8buSMwmmhiNhs4Zg8n55j+plZlpfXsU/nDEdh8FE48gkVzF5/TeKomWWFAC98CwoFGahEm0JvrtczqHUAWvaoIV4wJEM2fkHsukQ7RJNSr7jxtqe+EJOBUofrTbGTb86/B15BbRK+AvzGDsbw4cPH/Yj7oKfROtTJP1nxVsyex7TRtg1ihb2Q0PwYXPo2pqR1VuHRrX5m5oZyLCNv62k+2qjQUzCkzT0QKkvwGBerdQ8m2SnvopiXka6YjykJeZbaPDR2qbZp7ymtZfScWjhcf13hr2ijapNK4/UcgeG3YWFCXWcPnZYBun0R9j0lsdPJKzJOjd0iGVgBsAJY4SgmPa/XWvbIeBTzMpaBsM7R2CUjG2pQSC7R7mnBRTRu+z55Rcl2ESpyaREbQmE4+RdkBLsOKYc3d1PK2nsfA7wWGpklGa+laV3TLTgp2/5WOY7zRdu2vw+cAM45jnNlu2P48HEvcacFlm4uow3PCkIktmNPYKfzqPwcePF30DhrqMXbRq0N3wronMXCpuNutp6SggNQdb0qBUUr5776umsgn9bT/cR5GUQrUO74WchilmZg+HU9zc+PYAZOyijMDMO+x1Urs4aw4C5OKhzlfL/cKM7LDVHIKecRjMgYRRuh46CuQ+m6dNpw810Zg1AYhp4QS+/66zI009cwg496Y4T1Xbn2mggN6TmF5G5fkkTQlAOHP6Vr5xZFcIg1lQkRrYOwdBtaerTp9z0Ck+dV1zRzA1rm4MabmKSX+0kvwPk/khFzC8o7pWelwD0/Iar38JsyLkHPRuQzMlBuUSHA2VtemK5fxri5X4bQGE8lwcsVhcK6ZiM/krbdwpiYdtklrRnqNmzaCTHhJ7xfp4Be27Z7Hcf53nbH8eHjXuBOCyzdyavw5v+jxPTKLPQfV/OuQ6e3N84O51H1udyKQifztyC7AqEgpvchycLsUAduHeEgt6JN6fprqsrfYNy6Cg6XX9HmhcH0HFWrAmP0mdQszAxj2ocg0VZuqTBzQ5t6Y6c260eel7GYuKANfWZYc7rwLXkeuZQ274nLcOiT0D5Us3uruzgJr/9nheMWbyvRbnleQkMzLIxD31Gd6+YZeS6zIwprZRowubQ226YebeidttaxOKkanFBUXsbKPPSd0PV747/A+T8uF4cm20USaO7zPIcJhbyKGREGim/qemWWlG8qFEVDz+dklMNJ5ZGiSVi4Ja9naRL2Pw1v/1dRyG+eg4GPSOy0kIG5URnBQEDvu3l9xgqIqm0ZGcSVedVOte8DPAr37UsiJRhXKhOuq3za/JiXE4rC8Z+V4Zz3DNjyFChitil28rj0F72fAeAUat/6yR2M48PHh4o7LbB0cxk4+2XFw4NBbSjTw5DsxkTiW1Zz3uk8qupVYknRY6evQu9xsaWyXugl2bmzwlEPq0WdXvvoVeXlDeZZV8HhxttKgDd5UjOzNzDXXve6ckalWh1L6meyTS0LBh4V66rB2/giDVJW6D8h9lhqWk/ol77jtb2eh8YOz3MYUNI/llgXwjPpBRmgqWsy4LGENuOGZiXbkz3Q1C+22Ng5eS3tQ2LTzY3ICBSy6jCanpE3sjSlp/8rL0t/LtmuXM/cmEJUS5PgvCKZnmyD1j1xSeG1tkEZrKBHUHBdye6szOn11IyuTdG7BpkpXcNYUHmp+VvgdqpoNJ+Ed/+7jg83QGERLn8HOvfru5pNwcwt0cKT3t+ZRc8wxdRBdeGWClqxVHQKniSPpf5KIKN1+TvyhLoO6hpFm8S0mxmG1iEpUiQ7QJ2wN8VOwnF/q/S7bdth4OvbHcOHj3uCO813ZBb1tB0IeqylhDyFYq7ccXIr4+x0HmtbNeN6Vemu1xAtorBKIKin0zvI46zW4Ri3ihBQc571FBxy6dWGbYCexFcWZEwjcbGwEq0eayul4/NpXddkh657uEGb+cpCuSgyGFIiPd4gIxRq0P2JNIho0HusqvEc/SdkVINhhdtyy94cGjzPMiWmWzShMFN6DvCKMMMRuHFVBisYlQGau6X2BYWsNmS3qBog8IREjR4SEi1SEAhF5Wm09GuNwbC8j8Z2eYMtXuhr7H15Y73HYGYEUpMyDIOPQjFbNg6zI/oZadB9X56WF5NoA3dRhmxlXp5Uy4AKY0FGJ9EuL8sCgg1a79JtkR7CMZEm5m95CuDzMjaAFUtiOvfBzRbdq3wWOg5IY25lTuu68bbumbq4LtT7rt1pprGNLbhbPnzcF7jTAstYkwxPak6x8dwyYCmu7tF57+o81rZqJuDRhQNemESJctzijgpHdzzPesdF4qtq1GBpc2polrF0izImCxNKdOczXjM19cMRScBTIIgk9LnSZ7zuojS0wcKkNnIsGYZwDKupRyGzkrJCadMMx6F1j0JqK8v6/dCz6q1z7Cf1+pkvKSSYmgf7aYU7l29rww1G5BVll/Q9CMcUOmwbVPfRtKdn131I3oxr1B47HFPIr22fQnG9D8sTW3kfYs1l5psVkKcdCMr4ud5DRj6rNRujNSVaJZa6PKPrG2+VcZ4f1TGNvarVsSwZzWJR9yIQUhgv0Q4Y3SfX1XFuQQYkFNFDwOK4vldP/VVwC+oRFI7DR/68cmVW0Gs1kRUrsLETHvpJeXULEwB1OQM7yQld0MyxgDTwv213DB8+7gXutMAyEInhPvbz8MbvaMNLz0D/8XKHyy2Os9N5rGvV3LFfm9rcTQgnIBbwnsgLm463VULEVudZ97ihU8qjTFwEDPQcxdqvTsVm5Iw25JGz2sQbmuHYp9Urp/+EKNSNnfI4H/t5eYEjZxROmr4Oh58TEWDPI0q0H3gGIol1jefc1Kye0Ccv67VQRIKesyPSQEu2i7YdDGFmrsO+J3Vvb54VO62pB2ItSr67Bmauep5wWnpwbh4e+znlSHJpbfZtQ/J8xj/Qxr+yKL24XFqhq6jnwbT0w+U/0bmSHTIEDU1llQa3qPs6d0Nzd/NAVGMm2vV5Cz0kddplAdFQRPNdvA0TjjyyA0/pei9PieyRW5aK9vyYp0uHvMrUjHJgrQMyztlFOPpTZRp6dglz6WXNeWEMEh16MLCfhmxGRlDK2s8B/2TT77Xf3ntz+O29f/zwp5kdt5P22Fud507ZcSY1KwJCg6dwEI4ptLT3lJ668+kqJQU3l/FCdHGsgFVm0IXjCjWtOYeby8ClbyusZrycS2ZZRmbvqVW1ASsYUk2R833VSJXWNHcLBk/BzbfKYqXjF8VWO/wJhcpcF+vws3qvsn24mxdRYvgNMdMau9RSu7kbTvw5GVKQhzN5WetOeEoQ7fvl6TX3K/cYaRBhoLFbnlhjt0J3bXt1nngnzHuU8+lhz0D1yojFW+D4n5fh2/u4zhkMySD+4P9Wj6FYQuHN+Vua4/6n5aG19ELvw1hHnsOKJsr37cK3JAQbaVCI8PoPvYeiCQiHda3f//ofBn7dfGaz71fdb75t2/+B1c5JteE4zi/XG8eHj/sFd6ImAKXq/juPQu90Hms/t6E8zRrslBCx1XnWU3CoNU8rGBIjzi1qQ7O80GLbXqxEm96vEBWtxcILxFuhIVn1XonJZ4wRk+7mj7QRdxyAoY+qxcLB0wQq5mSKBV2jCio2bgHiLVitfRB/VgWZubQ8BCuoMF0wTJUnHAyJAJHxWiX0PaT8UnpeHk5+WZTp9/9IYbd4hzykxg55UP3HZWRbBqV0EAyJTt7QrLzYlVeUjyncgo4haOxTA773vq581sFPQv5bHskgq2NahyDeqM6p3oMTAPFm3I/9TUgviukXCIoSnpoRCSM9LEM49j6m/5HyA0YhK4M5dVXswsUpPTysLCm3lGwVueT9r+9KOO53t3CMDx8+7nfcj4WoJZTaCFhs+Mi77T5Kw2/p9XBc49++pJBgx37o2F/eiFlj3PIZyKUx4Vh1aDHeCoefrfJCa3l+q6G/G++Ixt/UA7PD+nyXLQMEOtfCmEKCzf2AqzCjZSkMF0tKVDUU1Vzcojb4zoPyOAIhGTbLVY+f0XdFZR99D5bndC2buuTdjLypPGIgiOk7ofOX5h0I6nylMS1UNLs4Lg9z7Dw098Crv4kZOoXZ/7TyQfM3PZaiJ4NUyIkt2Nip16SYcKLera/7zXMc55V6x/jw4eMBwBaIBrvRKXXbKGT1FL3/SYW2QmEl6Gux8PKZVcXpun2UlqbkjWQWRR1Ozysk51YrydQybmRTMPSEro0p6nzBULV6d43rVB4rqhxMdlEht7lbWlN6Vvmt/ApglAOKNSl0NnpOXohbVD4mEK7Wrrv8fbHmEu26XvFW3b9EJ1z8JvQ9DOOXYGlM52poVZhsZVyGbfhNsdz+6J9jjjwL8TZM12FwfgDLE8oVFbIiJETigCV1hNkbYid6ckTcvgwnf17jF3JSR0jPS/mhY0hU/Cs/ANMKW5CG2wkx4QbQC4whZtyo4zh1e0b48OHj3qIegWA3OqXuCKUn6WIBK9KwIQvPZFPlPjmROKZjX1UbBNwCJru8qpBAKCKmWCSmUFy8VTTsfU9WU+o38hCzizByGbPmemx6nUoqB6Gozj9wAq69DsluKRksTaiotURrLmRl8BJtKsZNtHkEgQB0Hy6rQpSMs+XlcTBSNbh5Vl7M2Hvy0nJLMg75jEKG6VnllrILKj5dnBDBYvyCDPLVV+Uh5jLqGWQFRFIo5hVCzC5rjitz8pIau8QKvPkOpKa0rmhCYcbUlNbSc0Tzjybgg5ferXf7dyJg+grwmOM4Q8BJ4Ps7GMOHjw8FpYT4RgKc9xvu1nxXiQHRRqyDp7Hsj+unt3luV7h0s7ludw2rgqL5jIQ+03PQf2K9h1HqkxOJy5u49R70n5BczrVXtfFefxMzda0sFtp5QJtniZ7dMiBvq7KHT0UeCFiVKmL8ggxCohUwmOG3RHLY7DqVDKopeow4bxOfHfaEPZOeMUyLwmwF1Fo7FFY9zqHnPLmdIlz9IXz3C5gzX4IfflFhskMf19o++Aa8+xXVDeWW5FldeRkCURmXROeqYcctQLRZ3ll6QXVHI+94HVdzHskGGbh8TvNo2VPWpsutyJts7FJ4LhTT3+lFmB+R0GpqVnVas8Oed9aqewVfq3f/d+Jv73cc5z0Ax3Het237wA7G8OHjruOePdlvAbXCOXdrvltixG0zX7TRXHe6Biveiuk7DjfeAiwYPYep4WFYjV2YRJsMSWpWP8fPStWhY5/ERbPLsPcJGYKGZoWSSiG5qavQfQjr8LNlVl4+o806u6R+P8GwCkXH3vfaQ/10pIoAACAASURBVJzz6meWRbve5DpV0egTHTB1WcbPLXptGoLyJBq8EFxjt8Jf+awM0aVvw9QVjwa9LILA1DUVmgYCIhhcf0ukgPSciADG1VhzI6r3iTQoJBYMqI1333G4fUGtHGaGJThaKMDypAztyoLXL8hSSK77iNqR3z4vIzk3AkuzmmOpiDazrDDd7KikhiIN8rSSnSpd6HtIY6uWdFPsxAgt2bb9WWThPotqhXz4uK9wpxI9dxO1NmqijXdlvlu+DtsooN1oTLP/mR2vYdXTibfUlghaO7/MrMJIxbzUn/c/ofPGkpilSXBelieSWZTHFG+C3odUbxOOY7Ir8OpvermiWYi3q3fO038Vq2VAcxo/ryR/rBHwikanHSlrr85D7Q6MFcSjVlT1WTK5Z+G9r2k+t694if+QNvfUjAplgyEx3hYnxXLrtGWwrryjsN3KnNZ56U9kVDNz0NrnGYhbYtUlWmWUI3HoHFJhqpuHn/xHcOsscBTG39Vxk1dlNIIheUeBdtULNfVoje37JSsEMijL0yKLNNnyDIfflBdXzHoKEl7h8NKUDBSIINF9GKDct3wD7CQc91eBnwfeBV4A/vIOxvDh4+5ikx40d4I7DZdtGPbKpu7KfLd6HapCYktTkM9sXPC60ZiZxZ2voc48rWBI4bX0HGZuVF7KwHEZjlAEht+S4cosy7DEGvX6zLBCRrkVPckvT0mU9IM/Ur7ILejp380pX3LrXPl8vcc8b2ROOZOBE6sK3uQzCvsNvynyw6Vv4y5NVV/PaEJ5kUQbHPkp5UqiSYXfHvoZ9eZZmhD7LBSF9j1a880fecoIrphzgZCICrm0V+O0KKPQPggYeSK5lOR/Es3Q/6iMV2OP1lvqhtq+Xyy81gHA0jjT1+UxRZKed9aq4teJ8/DeH8rItO9TDVFuSdfUCpQNkBWUwQs3aOHR5CqZw0PdQtSdPGJ9BPhLjuO4O/isDx8fDu5UoqcGdiVctlHYC3Z9vsC2rsOWO6VuNGasaedrqDNPNzWrsBiWrn/bHnUrXVkAjEI/+RWFktqHxCy7eVbGKJLQZh+OQ8MBHT99TbptpqA8TdoLyZU6tAZDkucJhMpySIWswplNPZhEh0JnXbbCUvM5GL9Q1WrbZBalHn7rrNd8Lqlr1PewQmt7T8l7WRiDYNKrIwpAQ6OMXyAsBe9GTz+v1Cwu5NGh8ymx65p6ZegmLsqtGP2Rl8tqk5H40Zd1HZu69NroezKO4Th0HwQTgJAlCSALhTJ7j3rCsi0yNoGQaqJWFjS3aJMYdSYHgYgMeaunfdfgibcGggAH6936nXhCnwF+ZNv2v7Zt++EdfN6Hj7uObT3ZbwE7SdzXRKX+G6xutlY0savzLWG712ErnVI3GjMQ8dpLp+dXO4ludQ2bzbPq2jf3aFOevakGbrcvKQS196NSpY41ApaIChOXyo3bDAp/ldpzL45DzNNaW5yQIXCLMO1glqZEQBh7T95PvFkGyCNCWMGQlClWluDyy/K2UnMyKK99UR1ZL3xLxagz18WC2/cktPbIGwkENZ/bF3XubFr5HZNXeM0KQP9H4MDHoKnD036b9V4/rvUt3pZReOznRYuOt+g8rQMqaHUNRJrg0re0rvSCaodSs6qT2vu4lBBa9ig3FE0q7JZbkYRQ+359V1cWZMQDYYXbpq562nJhhdyCYf1r6oOf+ofwxOdk3Gau6RrDxXr3ftvfcMdx/rZt20Hgp4B/Y9t2p+M4j213HB8+7ja2/GS/FexSoeemNOndnG/lOe/CuLXGLHsrAEYb9jY8xaoWEsUChoCMxNr6oGhSvYfSnkJ0sh36jmHFmhSqyy5rky91K23s0iY7dRX6H/GozpY23PYDCs91DCmEhQVv/3/KHxVzIjuUiBArC1iRuFZnBaXRVsioJ1A2pdzU0JMaY/R9eSShmFhiiTZPFHQFaBJBobCihfccVa6pUFBY7ON/EzoPKSR25NPa0AMWLE5DW0Riq8tTCq3tOSGPykJGN94sckf7PkkFpVOQnpaRWJlXu4pQRDm0qesiSRRymkc4qvs2dwOme+Dkz8H5b3p07z3wyGdl3Effk1FLtkHrXuU0Bx8TaWPkbXlZsSb9hKF6930ndUIh4GeBzyHmw+9sdwwfPj4s3KlEzyp2Mby3mVHYtfmuPeddGLdyzJoFn6PnMLV6D21iDFdDWJUN8HqOra8PSrQpbBSOQTRZJiSMvSfDlWyHgx/X03t6Xh5CLqXcTy4vT6OY19g3z2hDnbiohH0urQ359iVMslNju57nWiIgpKa0joXbIhQkO0UmCIXEbrNcj8E2L024roNe11K0cXceUEuIicuw5yOSEsp67bR7jpWusOR8eo56rSu8thclRe6DH9McMotirc3fkvfRule5nqUZeXjhOMxelwGygvDc/+zRqmc8nbhlacUNnFDfoplrYtP1Pgyf/Dtw9qsybmPnZLzb9sgIukVp4O19TEYHdE3jrd73wniL2Bw7+VaeA74B/K+O49QtRPLh48cBd6rAXXO8D4ml96GoIGzBU6yXUzPFwvoGeDPXZBz6HpZMTKk+6KnPEWhIYg48rXuyMCGyQvcRhbgCAYWeeo7KS9n7BNw6o6f6hVF1Z3WL8iKSXrjOeM0BAiEvvDUE2WUZt5lh/X3tVdz+E8pBNXbq8yNvi0BgBWRYxj9QLiftSfakZkQo6HtYBiYcEe26bVDkgXwGrJiuU//xskhoywBcf021OQvjumapSU9Q9IS8mFBMng2W6N4LnlpCeknHAlCUt7MwBoOPi0RgBcH+mDzE6etShs8sSuk72SUPr/uwvKKmTnmCC+Oad6JNahLT10VKCEWxBk9iQlFd02xaoqojZwCOUQc7+UaecBxnXSDctu3fcBznr+9gPB8+HgjcjbDW3caHVitVx1PcElW8kPXUAJBRCAaV28ilZRRKm2FFWGw1hDd9VayyhbFyeCm/ArFJeTejZzXOuNcSOxIX42zivPJYN8/KWBnX8wgKokP3PQI33oB9jysMmF0WnToYgb5jcO7rMib5jDbmS98VCWFhTEYlvQBdR7Sg3qMKzY2dV7HojbdkOLLL8lIauygJoZpiQZ5V+5BCdc19Mq6tg5LJmbggj+vQszo3Rt5b1yGdPxyRMVlZ8JrzWTK2C6Pw6m9p/Y2dYux1DCnXtDSl2qaAJebd5EUZ5J4jcPa/i74djXvjjMnQDJ2C/c9gTFGhuoVxuPZD5eHEFny17ldnu9+1WgbIg09S8PFjg428hzvxYHbikdyJF/Nh1krV9RTXeEoEQ7C0hMmmyurapSfp25f1dB8IKrQTiVfow2UBU1WXA6ipXCypPEQ0rmr+3mOA1xwu1qRzBkIKxZWYZuk5GbTDz2J6vbBfPqtmdpYFw69pw9//pJh4ty9pcw0ENX7HPs21UJBByWdloMJReW2pGYXiQl7/n4ZmeVyRpAxSOC6PJtakvkbBEG56QQYxGNYmjwvzt2VMWgdECY/FocPWmD/6ioxVQ5OIGUuTMowLt8RUS8/pvXDck9eZU54MJLJaaoyYTcsIhxvkSabndczcLb3e1CPqdVOfvLMDHxOTzwrKG8yvKByKpZ/BCMBfoE7K5p48ytm2/U8Br/kG/wR4Dfj3iM6XAv664zijtm33A78JxIFLwOcdx8nZtn0aNdMzwJcdx/k1b9xfAf6H0riO43zPtu1IrbE/jHX6eDBxN7yHnYx5x/PYZdXsegZxU0+xkhVYyCq5nVtRjmfoVHldgaBqf+ZGtdFFG9Wp88rL2kyXp+HA03Dt1bKiQiFb9mAmLqr2p5DRZ9/5Pc8ji8ChT6je59YZhbGMC60DIjuEogRaBzBNPSJGDL8hgxYIiYI9crZsGBs75ZGMva97YwX13s0zon63DcCeR9XTZ+G2wlxHP62Nf3FKZAoL5WNKoT/jQmoKM/y2WHPG1ToGH9O1K2ZkNLPLXpbFu7YLt+SZhBtEdJieEqV6eRI6DqrhYTSpYtxjP6nC10LeEyYdlopC+16F2G6+A3OLMprX39S6wjGteWVBVPC+4ypgzaXk9dnPgPOK3p+/qYeIvMf2U2dVu973aicU7TuCbdsJJHr6ceDPAP8A+NvA247jfML7+//0Dv9V4B94r78N/LJt21HgnyNyxGnglG3bj9q2/ShwynvtM8A/847daGwfPtZh16jYdzjmrsxjAzr4TsgUbmoWc+UVjPN9/UzP1TxuI4r3KgU7m1K3VBBDK5oor6ukpn34WXj0BfjoX9RmvjwpBlZTl0Jn+RWpFpQ+V9JrC0Z0XM9R5V+G35QhaeyUN3X+m6oNsoLayHMpsdiu/mB1TatK2cbFCsf0+8AJJe+XvBxLzxHV53TacPyz8hosj0TQfbCsAN7YCe39oju37lHX1wMfl3pDJC7DYYpi7RmPUTc3IlWH5h7ll0bPqSankJcnMn1d488OyyNxvbbenTZ0H9M8eo6o3YPlqXTbz8KR5+QFFXLSz2vsVBiuuVdUa8uSR7Y4JVXtxdsyNpEGzefAUypqXZpQe/KBE+pmm01JH+/8N9Xob2FcXmk+U2rPkaAOdtMTqsuCAHAcJwX8hvfnUWAZeUXPe+9/YNt2zGPhhR3Hed879ovAV5FSw9ccx1kEsG3715B8kAV8wXEcAyzatv2HwFMbjb1JWHEdJicnef7556tee/HFF3nxxRe3OoSPBwV3o+fOTsbchXnsFplit8J6VrwVM/SEcjPNveXuqqV1VappNzTKaAa85+RQ1Ot70yhvCNS8Lpsqqyn8/+y9eZRk93Ue9r2l9qqu3vdp9My8WTAz2HeCJEiCoURLtBlHim1JkcPIimUfO5btk5woSo4dOctx5NiylYhaGEuKpRxJFheJ4iKJEAkuAIltgAEw65u19626uva3/vLHd19V9d7T6AFAoe45c3q6lt/7vVfV93v33u9+d+Ycx54bMWDwBDD9GlNmS1epz1ZfAyYeBsbPsMdm7g065VQe0LTWbKIN9S0YcabFfI8sMRVQc86t8bPom5QR2+ICp19jiqu+RNry6Y8yFTZzjsfvP0rwWLxM8oKZosPXdGkMNaJGTwqKxtPAyY8AN15iNJXp5bHm3mSUY72f16S6IiBzqCVCunQFGD1J4M70A9YojzF3gXUdhExBahqjx6juZojoayzFa5fpF2ZenSM35s8zips+ByrzKO4/nhFBVI2fA9CSkdjG9g1ClmWNbUhr/YvbfP/fA/Dfg9HJT9i23a4xtACgH0BE74Bt24FlWQAwBI6RiGwWwHDb/zc9vs3a83vd6+DgIL7whS/s9eUd+362O6C0sK81D2gfB0Km2AEQVfT8NiO9Nz6nJTJQ0Uwfw1x3XluBJiYfo/NWAesti68I1VknLfrG96BUyNeO3cv6TjTawUywfqKBDlU36SQDvzXCIZ4GzBg03Wyek5bIbAbvI4/znG68SNZXPEVnrOlMXXUNk8o9eppOPD/K2tbRx4BkV2v96ioBYPUWU2WayVpSYZoEhHiSaayeMT4/cBQYOAxUCkBlgU256R6CU2kWePBHZN5PGgh11qbO/iHBI54mUC7ZjMa8OqPAuYuMpIZPkjV4XppqzTQp5r7fImbkBoRqvsLrN/EAr3+jwqgsVEKC6BWl7iQjqpVbnK66bHft9vXaT5/QIwB+DUDWsqy/BeCMbdu/bdv2l29nHdu2P21Z1q8D+CwA07IsvU0KaBDAsvyMjhulDhcAtDfHjspjAOcczbQ9/lL03i3W7ljHNtlBU7H3u+ZB7uMt08G3AUTlVBkRbFGz2q6etdt5bQRNAFBDJ1hDqpcJXr0TlNuZvwB0j0BL9zX7kqLoTDNMhPd9EvjzX2StpFGRqOgSm1VjSRHrnCRAOBXOIxLCw3bg3Yzkukeg6fJYROX2OOobT/4U0KiyZ2fhCrA6DdVziMebe4OAWi2wXmTGKDjqFFujtVenWYPqmaDTd6o817U5EiOGT5E5qJlAdgBa3yTHic/8BjB2mizBwCPp4PTHuKdYgjUcM07AcoX2neoG7v0k8NxvEuSdGoCQgNU9RkA6/ARJH5OPkXr+rV9lym3+PNOMgUtqfLLBPR//MM+Bjcu7+tr9fDP/FVjL+TyA1wH8EoDf3uubLcv6cQA3bdv+Ns8WBoBvgMKon7Es6yQA17Zt37Is37KsU7ZtnwebY78Okhj+Z8uyftW27QqAfwDg38nyPwvgv7AsKyt7/OXt1t7HeXfsPWJvl8LAO7GP/diWEUqU/trrqG1R2dZU0JxptO1kUnlcNUotIPM91lsGPgZU11i8L04Ds69Djd9HtYQN6UqtexTq9MeZkkrmKcJZWuT+j74fOPQgMPUK1MIVRh39h9cRHjTDbEZ661Q449I0GoFXPAVYT0HTtRZwzpxjzWT5Otl0t86yJrRoMwrqmWDxXtMJBj0mU2uHnwAskzWZaLjdwnlRjIixufXWS1RUGDpOVQcjDxXR2/snmR70XVK1VdhSE5+/yOmnqW7uvzgt9PKqDP7r5fjwWIb1tzOfYOpv4kH+BIBLzzCCqq4A+XESJcwUP6fx+wDc5KC74VNc9yLe3O37tZ9vdcq27XnLspQw1YzbfP9XAXzasqz/FQSg/wDgtwD83wJQVQA/I6/9WQC/ZllWCsAVkB3nWJb1zwB8ybIsBeALtm2/DACWZb1iWdazIGvun9u23bAs6//aZu2OdWxbu9MKA+/kPnazLdNoGyMU34HarmYFbE7frc4Al56B0o1tZxqFpUWZJwQChVsDcgMEskYFWLzERs3Vm1IfygAwgPmLpFcbMcrpOFX+dBt0xppGAPJdAoZuUHVg4bLoxV0Fxu+Hlh8mYN54kRGP74gCg0cmn6YRGLwG4NagfJepsP7D7CWaeJDgWS1Q+y4/DJXI8Zzix6hQvXoduP4Sqc31Kj2gmwVSvYzU4ikeK91NJtq154DFa6LCEAOWL0md7Bp7hGbOIRy9hxJBa7NUPsiPUEIokeFeu4Yp0ZMdIOgtXGKkEwZMG9bLTNe5ayQzxNPcz8o1oHiTUWcyxxqT7xCQVMhr6pQYlSVzABQwfj/Zf8UppkIZaOxo+/l2f08ce5dlWf8tgLO382bbtlfAURAb7e9s8dopMKLZ+PjXwaho4+P/BhvYb7ZtO1ut3bGOdWyzNdNo0gCpJh+DnhsAsEGmB9i5ZtX+nCMD0CYfZd1kC2JDWFoEvvvbTWke5Ed4554f4bGTWcr1VFeZEnKrLNIv24wgeg7x7vvad6AqK0xfqYB3/Cs3gZE67/S7x9CcmprIcL+xFLB6CyrbT4d89VviSKc5LiIls56gUQoolmKNxjDXn9Olb3DNwAPmzkMZBvuBwpApsOUbVJwGGHEoHUj0kxLdN0FG3OWvM+XYcxdBWNN57Zwy2Xm6QZZbfpiU6kwvU6KJNHDPDwEv/yFgf4cgNnwauOtBHjsI+J6LzxBADJPMudVZRom1VcCvUai0XiLYLNkEsNF7AOhMJWo6SQ/Vggil+gQzublAeZFNq92Hoq9UYbfv3H5A6B+BqTEF5vv+z32s0bGOdexdZk0WnO8yZeTWOZ7gif+yCUSR7Vqzan8u9IH+w9CSWb53A9OPcj0v0JF1DfLx1WmCSKMCZESLLt0DjD/EO/n8KJDpZkNlfQ04/H5g+mVpgl0k6yz0yWwzDGDmPFlpjYqMejCgZfugQp/RR6MMzLzJkdlKsRCf6iNt2qkBtyRCc6t08DWZRHr4MahYkimvhUvUgEv3A4EFTL1GungY0JnPX6ADHzlJMFU+EM8B9/xVoUhXAShSs68/J4oEjzM6WZ3mPnRdCBUpGSS3wPONZwBorPmMniLhwNCZfnz8UwSraoHApcVZJ9NNpsyK07yO06/y2IFDoddagZ/Jt36NtO6uQYLjtW8TwJavU9HcjDGSWrSBm68QzBbtKIU3vtv3bj8gpGzb/veWZWkA7gEQB9DYxzod61jH3k0WqVWv3mKEkMyxNnHjBahTP7C592crEoFTZRqvfbqoZjBC2S5q8h0AWsuxmgk6xQELUAFHOwjIwYhBDR7nrJvaKh3p4HEKkwZeM1UIzWBKaPAYGV7VAlUGjn2Qr7vxAlTXIKV40r1MmS3fZPRx10NMu829SYZXLMu9BSEfy48xClu9Abw6z56Z7lEAilHGrVcIgIHH+snQSeC1zxOEirOyforXOtlFZlqlQIHQ/DBB1avztakeRnJK8Rx1YfwFPqC7THaVFgg+tSLrdP1HmLLsn2TjqArYb/XGVwA/AMIKJ6kqxVqQ12DjbZSqTKQIbLkBst4KN8nEi8WBI+/jDUA8JUy4GkkLKZns2iiRqJDu5jXYQ7PqfkDoc5Zl/W2Qkn2K3x58dB/rdKxje7a9yNe8LUKd+7Tvh70pzQCgmkoGnBuT5PjqagHI9G7ZhKoAqLU5SYGFTTYcEjlprvWbRIYtoyYzQYfWNynjtoskIhx+jAKfUZ0pkeF68RSQPc679ijlJgP1mr8vXSEhQDPY2xNLMW2nwlZqr1Emq2zJBo59CPD+jM52/s3W2O16lTTkQEClvMjHPYItirNAaZgF+v6jTPNF48B9j849JnTu0VPA2c/KmG8ZM1EpABk2IzenqsZTBJZUNyMz32G6LZXn8TSJcEZOcWz4yCmZZyRKBjnp6Xn9qzz31/+EeypOUSpo+jWmCAOHKcyFi4wY42mmE8tLjNDiWWDBJsEhmeXvpUWOBx+/n4DZqHFybSTtk+0jkAe+MO2wq8THfv4aDgFIAHjMtu3HLct6eR9rdKxje7a9yNe8bUKd+7Dvq70NniC1d+Eyf093M+rQDaadNuw9rBaofH3rZTqx8XsBI876SBgQDCBd/EefbPbxAG1RU5Tau/EiRTe9Oh3x/EWyyoQQoCJygN+gIx2wgGw/AS2ehIrWqC6TIl0tsFDfNQLcxT4faDpUtUjQGjkDXP02Qbe8REmbqD5SLdKRPvAjwPXvyEhsQ+R11rjPTA9BOpXnhNXhk8DZawQJt8Z0282XACjSm9Pd7Ot58Q+oQrByk2SLy18jWPoNKhYYOsFUhWwsrZf4fw3sD8r1ckheNNSvOM2oJ/SpFNGoAAsv87zcAeDsf2SkNHw3AU3XOYIh1cvo0KsB9QKP5dV58+HWAGeNNbKEpPqmzlHOKPQYtQ2eYMou08PPJdXVqhM1qqLufWcUE14E8F0AP21Z1hMAttbv6FjHDsD20q3/dgp13on9vyN7iiKfjTOAVq7TWcXSrKUsX2U9IN0DuHU6+RMfWT/xVNflTjlN4Bi7j134ZozOFoopnUgotJ16LaCsVBsJujhDMMv0yFwhsElz4RLvrlNddHALl4FDD1NFAaLIcOgh4OpzJBQMHqWTr69xnk7PGHBJCv/Dd7NvprLIOk1xluBTW6OTNWLAmb8CDBwB3vwSa0MqJKXZAF/j1gk8TpXXoGeC+64UGF14Mj7BEZ21oROirjDOc1i8wsghkvmpl5kicxsEN8/l7b5mAlrA1GNSY4R15RskWTSqMjV1hdcp0889Jru4v0SW6TszznPvn2T6TY9z2F26h6SFUOP5m3FW+2MJPg5FUPMdgnSkwweNUePAMdalIsUGr8GbD4TcQ2351m7fx9v+K7Bt++9F/xfq9I/d7hod69iebS/yNXdCaueg7F22t3WRT+iTStx/uLW38hKdzIkP8g5c1+kUb77IO3ynCjVyClrPePPckMrR8YQho4eqkALMTHQ3DGgc2Kac6nrgcypQV75J55bKM0pauMi01th9PL4CHanvMKWUOsX00eoV4MXfgTryBBCJoBomRxEoJY2tk2SWDR1nL1A6z2hn+SqB8tgHmM668DVGQ9kBsuiUz+iuuspUW9eg1Js8IJUFjj3NwXZOhec8dJL9PrU1gla1wBSaEQeCVUYW85cJFkPHgbLDwXC6yTWSOZIFDJMRUeDL5FXF302TzDUjTjAIXXmuxobSWIJEhsoC9d0SGbmJuMbIJp6l5E62n/UbDbxG5Xng9A8C579M0At9MhIrSwAC3ghUJUrSDBIgfJFA8hzAFfFYt0IQhSKADt4tY9ivvbjbd3I/igk/ucXDnemqHbszthf5mjshtXNQdkB726mmtNd606aozKkAcxda00O9BqMVQGRbuuhgVqfYiCjCnpg7D9U1zHNw64xQfId39ul+Ss2MnmGayBdnqcK2tQnKzdEIxTmuPX4fI6kbL/J9Tg0wDRbfFy7zX+EWneHaLB1pfhRA2IouExmokTPAm3/KO/tEjkSCRJZRXt9dBM3qKusbnsvifNcgsJxh5BZP8ZzDbtZuzDjPMyljGFJ9dNZZ0VlTPtW6Z98geQEBgbBRIbC6FTr/XD9TYI0qI7TKEutFySywtkgQdwoEEE2X2lOdsj61gowtl7YbrQEUZqSvJ0nH79cIoJlBptiWrzEyiaUZ6bhlphn7Jrin6hqj1fF7CGArtwAvYErNFcByHQKrVwOgcQ9hwOvg+4C2JBNrPe7LiAMIeW6ZHgBwdvtu7+dWbER+6gAel58dEOrYHbG9yNfcCamdg7Jt1QakC38ve9ypprTVc0jktgaljVFZIrtJckabfAQA6NQbooFWK7KIrQKmmzynxYiLRDtjMt8mPwIc/wg0vw51+dkWWaH/KHDoAYKEpkNVlglaES3bdYA3v8oCff8kRzkUb9EBazrv9AeOEthWrhOIDBOYPktnlx9t6b6d/AhUGABvfInv6z9MJ7twqSUMaibI/nLLBJFGRebqaIDjULk61c1IxYgD2SwByq2Rvj1/nq9XSkY+GCQcVJf5WcRS0h+UZF0qledMoHpZIgadYFdZkRSgDLFToaTLYgSIMJSfLsc5hEL80IQtF0vxPekueU5EUBcvce+Q+pJbbs1lith7Q8d5/LOf5/+nznHviaxMoJ3lHlN5nmvgA0Gda0KTKaprVFjwfAKypstrXe7nTkxWtW37X0b/F5r2M7e7jiCbHwAAIABJREFURsc6dju2F/mad4vEzVa2jq7sVMkS2yNJYaeaEoDNz0UNk20steb6W0VlmV4gktNpv27t9Op0r9R9cnREYdiiQseSLJJH51NbhaYCHvOeH4Yav4+6b7rB8+47TEc+fY5gMnqGDZVug13/gceI4cSHmUZL90u3/qhQfhVHTJdmKbiZHeNjKzfW67498NehJh8lZTlqpDz+IVGalhTS6R8k0NTXZNbPHOsbgERHo9zf8lVGB06VYBxLMZrwXKYpYwkCYnWJ18drMDrwA9Go88gyS6QlmgoI2plBoGuMk1rjWUZWboPvz+SBuKT/3IqMc/AJPrEkAI3MPQUCiNcgWPRbJDxEn5Gmt8ZcQON0VkXJIVSWGPGUZOZR4HF9My7MtzV+l8IAMJIE38CRYYO9PEdNyBpR/Ug3W2MqqmsAcHS3v4/9pOMG236dBDCwzUs71rEDs73I17wTEjd7taYO2fXv3h5JYaeaErB+Wmlbw2Qk6rlOs81MQNsqYownARDw1jHWDJOlg8lHuM+yaFFOPto6HyMGhD60eGrrVOPiFXG+OTrKs58FJh8F7n4asJ+TKCcNQCdZQJMx1G6DqTffBapCH05mGSH0TjDyccp0nLoJ9I/zHNuut9Y/CSW1K6UZjFJmzol8T5rsuiWbTra8CBx5stXnUlpkCmr2ddK1Jx+nQ168LNpxHsGpsiyjDvoAaALGJtNfuqTsMj0kQIQB6zS+Yl3HqTDKUSHTd5omUjt1rhnoAELWqpJZ9u9AkxESaSAW43tKC2Texbs4vK68REAKJU3bKDNdF3j8HFyXwUxxhiACMD0Z+DLArsjIMRo31yhTASGeoOiq8vmZNsoAPBInoKE5UTb0uQZTh327/W3s5y/299v+XwAFRDvWsY7tZvshKexWU4qG1hkmnU8oOl/R+ltptm0RMe6U8tPSPVCj91DVABojmuj5bdKgKvChlq4yUkh1ESh6J4UibHBvhx8Grn2XBX0zzumjizbrQqu3yCY78hjP67UvMBqoLkvzqYy6nnyU5xv6W9bZNMNE2M7G003grnvJIrv2HUYly9cJ3ivXKWraN0nAPPaBVuTiOcDQaQA6sHiRIqIahLGWZV1LAwFKKYIZdPYTNQy+ribU8DBgGiyeJoMvlZWIZJ5pQT3Gz9NIEZzMJAkBjSKjISPFPh5V5vyfRoUnGzj8/eo3JRqrMELRTZJEYgIehuwlcFkfS3Xx99AHQrM1aK/fAqqLAHym3bJ9AvwSSaXzrQgI4HlFs4iMBJDoBihmsKPtJx334dt9T8c61jFsPxJBRDe3SiPuSR7n0jdaI6GjMQG5wW012zQp4Ee2G41cBT4jgnRPc9+RyKe2hSJ2s3fo5oukPidzwnq7QOcVSsRixDm+OjsAnP9TOu7yEjBymnf4dz3MKGnlFh18o0jHl8ixblG4ycfH7oN28iNbEjZUNMlV15nG0jSy4kbOkP038wbTgPEEf1+6SgeeH2VhHgB8UAD06rcJRrde4jlkermmESOpIp6U99cYUcTTrZqZU6FjDgPuPZam8y/OAj1HyAZ0amyMzXbT2bsVINkH6ApoCMkil2ENyZWBc0rxWG6NacUrz5KQUV/lfB/TAxAC1RKQlDReIgvUSlS/7j0CrM0wfacbjNrcBgHbKzNajAbbAdyDESN4lXWKmOpxRo61gtSypGZUmgb2gDH7SccdBfAb4HC5OQB/17btq7e7Tsc69l6zLUkKfTI+QCIQ1TaYrV3BWkWpomRXM30GQBxyBrjrUd6RV5aBW68wctF1pq50Ayr0t428VG2Nzr+PopObXhdRsWNJKicEPnXG3BoH1I3dK1RkH8pMtHqHUl3SD2MzveOUObumutyU4sHoPcALv8O911Z5p750hdHI3JsEiyWbkYBh0iFOn6V8TDzDVNCSDXXsg+tGOzcju+Is8OaXCYLxNKOoeplTSqdfFZo02NCqGcJ6G6SyQKVAUCkymsTYGfbV9EwweqqtiRBpCBy6Hzj0EGtMVTm3epkpK6fKTcUSpFsPHiWYaiDzzxTadW2FkYURl5qbT5XqXI/oxknqbvIhglbgShrNA4wqgWjlmoCnIaKkDus7mpAfyitMpwWuAPkUU4IRlT7VA2QM7iGZadWECjcBaNxj1zBZgGac4FVfZT1Nj7GHKtnD61orA3cChAD8KoCfs237e5ZlPQTgVwD8wD7W6VjH3nO2laZaMwIpLQLP/xbHErSpE2xMlal2soEU2bVsHynPK9eZ2vEaLKq/8SU60XiKTLjIwYmFi1c5iXP+IpBIQ536AdY3NJ0RUDShtLQIvP5F/l6aB8buJxOuVgCe/RUZSW02xUHRNyFpoAQZbp4IZpYXyJKLJqBWCxJFxbn3WJLO8/Bj3Hdxhu8dsgiwXp3RXuEW1+sZZ9PllWcRnvlh6PFkK7IzTDrZ6LXZXuDyN+lIobOmEoJOu1YEeia5/vBJwHoK+Oan+f7SDCMOrw5oA6x31FcZSRgxnm+tCCRWgIn7WXNKdhNwbrzEupiSBs5aie/PDhOE6qJG3T3CKEuvsz/Iq0m9RufjZpIsP99lRNU9xgmsek2ippCNrKFP8ATInlMhH4tEWpXGnqP8CNNrNen36Rrkvpwq60l5IYJkBoCpV3h+kdWKQAq8pr4DVBeYkUskCWzlBQJSPA64zq66ovpuL9jCumzb/h4AyByf3D7W6FjH3rOmGSa0RIaF9MBj5BH6HLms63QCsSTUrVcQuo1Wqiw30HycmmxopfgaFVJvF6/QmazepFxLc0ZNjamnsXtbdSC3Abz6OUYrRx6nU3ntjzhq2q0B15+HuvIso5bCdWE+pZhiKs+L3P813gVn+1iPWJtr9acMn+Relq8xgjn6Pt5Zz5xrRXpJqRct2owUlLC/SgtUZk7KmIbl63S+TpVAunwDgIiFLl0FZt9k7Su6+w88rrV6kw7XiAHFeWBtCoBJgkAQMNLwGqJD5/Mu3zBZ41m+xv8nMoyilm+SNl5fk6g0y/TV8AnuuV5k2k6PAUvSmKppJBR0DTJyS+aYXqyvcf2uYQCKjaRQBEXfIcB1j/O7YMQJtrpJEdHSHBl3gcfzMFNM72mK/w+F5WYkeMzQ57WKxZmSS3Xx2igljbmijZcdoFZf/xFpSF1lBLgiKUro3IsjMkdrM1IT62cq0q0R0BJZUsZTPcAdioRWLMv6JIA/BvBD6IzK7ljH9mdtNSLKtYhwqBFjLaZRblJntyMzNFN8V75FR5ztI/CoEJg9T2HOQw/SYdXXGIFE1pC5MUlp/Tv0IEFM0zhMLqpb2d9iwXn8PnF8cZG4KfLuOqLl6oaAaD/vsM04+4Oyg8DQsdY47Lb96/Ekwns/ATzzb+i8a6tyHGly7Roik+7WqwSMUz9IoLv1Mu++ywuszWT7gUSWskKHHiLrzm9ITUajM4cmTK4QUIYcQ5pKByym6nJDwOt/TLArzkhkF2Pac/kqUOkiWSA/ynPPj7L51HeATIoRSizOx2Nprh/6dMqBy1EH/UeYnuybJKD0TgDTbxCEYymeZ7af13TkNOtxKmTqzTQZIdVllIQngUbgkDFnGqKgkGJfVW2NgK7HeL2CEHBWABikYJtJ+c7pwuDzeYyI7GCYbGANXZ5jKsf9JXNSj4oBjRWeq/IJeok0MHACuPBnAIWHdv4z2Mefzk8B+EUAvwDgNQA/vY81Otax97y114iamlv9hwlAEQtO1KGbDLhGmQ62LaXWrBlNn+VdfzzNu1LdYANnMstIK5ZczyBLdvH3arE10VMk+rWY1J18R1QNpuj4ho5JGqfI/WoaHW8Y0OEtXGZPT156bCIWWjQOewsatzZ0AuqBv876QjJPZ+1UAYMsOsSSUEffR/DpOwLMvEYHvnpT5GlidOr1EkkDjXIrReZUmcZzq60RD16DDtN3CaiGzsL/5ENUSli0SSSIppD2jJMw0H+E/Ty1FemDmQP8awS2w49zD4kE02RzFwjCUZqyvEIn79YZMRWusQ4FjdGDV+PrMj2sF9VWee1Cn/RraDz/0OHoikwPiQuaDnQJa80VanfPBOs8iW5+tpoGwCBhIKxLLcoDHB/wvGjkgsgmpXnstSWCkfKZtnRc7k8pAo0Cby5qKwQ9r8jPDsLmqxWiOpO329/BfthxcwB+4nbf17GOvVdtJ1mdqEaknCowepoyOoUpOumxe1pAFTHgIkVqp8wieXOdPNTYfSwge9KMefxDPH7bPJ724+vxJMKTH2XtI1JAeP9/DTTWWqA38zrTN8efljEEF+lsP/Az0EbuhrLeD1z9DkkEy9dZdD8sQirTrwEnnpaJp89BGTGCxgbFCM0wgSNPCBhXCSpHnwCmzjK9FksRTOprrEsV51k0HzhGZ5/uZYrv2nPCEAyB8QcYJd3zCcB+ls7Zc+n4b7wApqeSjH66RhgVXv46Gyw1xRpOPElgdaocpleaA+orrYZWtwLkjzJayfYBl58hAJcX6YhVCAyepnqBkeXxKiuMnOpF/r80L0PwBBDdOpDO8XMGqBChQsoN1VaBAASs4bsZGdVLIuejMULrPgQceT8w8wpBOtvD6NVvSPRkADAIbIEvKgo1vqa6yn3pCcoHeUmRTfL5T0uJWGwABIrXCRojOGhSn0wT8GurEOp2Zbe/j/2w4/4zAD8PoEnRsW17V2mGjnXsvWh7GePQVJWurLA4n8rTYTgVqEwvnXY7Ay70NzW5aoYJHH+K6Si3BsTT0CYf2V7CBwKOtQLwyN8Qiq7OFI3M/kFZ7q4nH2aa7szHSf8ev19SOQnoiQzUPT8MddejwPXngd5xOu2F8zyf1VmgPAtAY1Rw8mNbKkZsVLxQ0TiBW6/wmoQ+77gTaeDQfZxpc5WkDixekRqPONtLf8G5PINHKWM0cEyYgwUgN0IJm3qZoJTKt0gA9RIjhPIiazVmEoh7vC5Dx5hmuzYrsjoyhnxtjpHX2BmCwa2zTONlRekh1c3oYeIh3jiUFllP8xoCSHWhZgc8froHyA/wRsNMkGVWXqKMkQ7ut7oK3HqNPVPdo4yG6iWgKrWfJdHyiwCqLnOhFAg4oU+Q1aSfSYW8btAl3RfwtW6VhAeEYCQVY7py8Dhw47uMJFN5XvvVaVF3qMp03DoB/A6NcvjnAH7Qtu2Zfby3Yx37S2W7CovudQyFYTK1Ec9Qb23wGJ1M1yBnuECDlpfm86hetIFqraV7gBMf2byf3dQY2kZ3q/IS60ZRdBbVkEKfhW5TUnpeY31dqmsQKt3NHpNo/EIyx5HbZoL1JqcMfOc3gIf/FrTcwKbrEak0NK9JuofOvDgtzK4AWJEoI5lmuqr/CMFnxZY5RBnADAFojJLu/rjQpdcYucy9SmeZyMgU2RmgZ4Qip40SgKoMnHMBMw/0HgLyh/i68gL127L9fG11uaVsPXtelAu6uAe3xvWnX+PvN77H61crsM6lGYwcG2VR/da4/7JH1YOMDNErLjAFByX1nBoj5gRHpcNrcK+agPDcRdbPDENIETlQP0503SJB2coS9xXPMAWrFBUxQpEGyvTzNQrS+5PgjUrhBteNpQFnSXq7Fnh8zWMKrrQsqhEecIeICXPyr2Mde0/brlHObYyh4B95lB4RYcomTZepma1UEzaC4E7SRZsAcwc1Bs0wmeKbfITRVWlJZF50Std0j0BNPtpsem2mDa8+xzv8bB9rEwsXpZ9EalK+06xBRNdDOVXuWY6rnCqdczLHu/hGiWtoOh32kgifxjOMBErzBInKCmCsiaBnL8crFK632HN+nU41nibgq5AOVU9wvcOP0hGn8gBCOuK4AEfhJh+rFpuNxYh3MTqorwJBmuxAT4bGlRcApfM46T6CRW6An+lqlWu7NQAyAC8iYiiPNyGRzpxfQ3P8uWFyr0HIGlM8zV4cPUaatCs3BtGYBt0g8Jopar+FnpxvjNfCrfI9mT5g4C5J1+lkDQa+6JSabEbVdJIfwpAgunCZ31OvwXoZFFrD/DxAJXic0HF3+zvaFYQsy/o0mroMAIAYgJcsy5LEKmDb9t/fbZ2Odewvk+1pWN1tjKGAEnkVV2bK1IVdpkQEc4vx2FsNh9tODHVbwNxNoTzdA2V9kMX9yiLrJJrJu/+ps1AnWkoFWroH6sTTABQBxDBbd9+6yUjITIi6M0grrxXZrCtCm6rvMJtTb75CyRi3zj6fWKo1AA4K6DrEVFtpgUyuWkkK9yHTcLEUGzfT/Uwdjp4mA62xBjhFAoMKZY+ihF0v0rG/71ME2kCu/dJVwKsAqzJyQvmsiWQGKXKqQtKta6sATNZ8QtGDi0lUtHhFgEmAJup30tACIACAzsdcF3DmCQSJtERXMlm2MAWEjZaYrAbuJx5j3UZ5fDwMeD79R5iW82QuUn0NMDIyjM/kvuejaEp6i7wq9e+0kHvQTT6WSDEVFyoqWOgGgBDQky09QwgZgzcbu7YB7SUS+r09vKZjHXtv2R6inNsdQ4FMv0wkTfFnfhToXoV2/Ck6+LaaCQBKtOxBDHVHwNxFfVwFvkQiCUYWySxBLKrZbEgJ6vEk1NEnub5bBw4/QWrz6hQd0xOfApwy1NI1OnenyhTW+AN8/uxnqaqdyVOvzHfoTL06AI21mvIi97JynUSCZZtMPDNGUPJqdLr5YaayVm6wnwlgzcOpEhhz/SzkL9+QqARA7wAd9+OfItswCEhRL87wPT1jTF8Vphilua5ICpUE8Fab+njQdREj9VqNrW6dQKSZAKSu5MgwuNZFF0FTnaDjCoU/DIBYtgVggc+bgohq7tRBjaHow0hIjSdOjb1LX5cnhKIOxee9hqQipbcoluBNRiomrMcCX6PpEvmVeS2URD8KgFvkHiioB/hVQEsApFLsaLuCkG3bz+72GgCwLOuLtm1/Yi+v7VjH7rTtddDbvm2HKKf92EjkgImHAYANqjuMoVC1tVZDaDLHO2q3AhVwYml7qk051c0gWCtClRahEpn1x4pSfskslFunI2l4m+V7NlyzZvTkNRidqJAOqlFhakc3oWprHKEQyfuYic0kg8BnOmv5KiMR36fT7zsMXP0WU0ar08DJj9LBOjIi4NCDdP75cR5fN3n3bYhzTfUDl77FvhUjCUBRWSFQTH05a8DUyyQxaAaQ62MdR4k0Tv4QP6NsP9lmxz8cXQimnDyHvS6hx7U0g+m6xprM0qkBCUm9xVK85zfigOEzioCS8Qgy7qC8wqJ/qltqNDKQTgPXUqLzppmSY4oaRKUOF6XI4PM4KmCKzPdImvDaACiy3qNUiohnCGzFeUC1zZlzI/KaASDgmn5dBtcFlOCJyeuT2dbNB8DaHJTMGIrJOiGagKq8aOEd7SD/OvsPcK2OdWzfthdG2lu17aKcdSmyKH0SiVxOPLiOVt1uqlECbjxPqnO2j1HQ4hXWMmZfJ/1aIiIAm0GwvEjR0KmzBIfhk1BHn4QWT1MeKJqAqutM1fTeBZiJ1rWqFjiTp28SyPRCDZ+iXEsiCy0/DGUYwLmvAJe/IWCUYR1m+lUgDKAGjtKZt1/vdoArTrPW4jvA7Dlg5k0W1zUI4JY5UXVtjmuU5un8fY9RVKPIpk5DZ9rs4tdbox7cGgvmYch0ky61mEQXnaxTaaW8klkgPdAa811dBOV0ZLRCuptinzNvAFefY6OoZhAIApfXSYV8TDfolMOA+6itifBnjRGUFkhKSuexjBiBolEFKqsSXWhU0Y5nJCIKmO7T4owkIjDwPZmgKuoXfr1NwVq1mlabZrAm45aBpTVGdY2SkC5kRAQ/GfkpABb6gBZract5ZabkHJefh+ugFdxEgCPr6UZLnLb5/O52kCCkdn9Jxzp2Z21PtZoDso13/ACaKTIksi2W2JHHKe65W7osmSMAhQFwQWZFRoBUuEmCgNRgNMOEGrsXuPECp4jOS3Nk1xAARWbYwiWo0TOSBhIRTbXFcXWTEUIyy59GnHpwKgC6x6BGT4lDLwPHn2KT64WvcdzC6GmOtb46Bzz4owTAjecZRWKJLLBwjpGAmRCJl7Qw12ocOHfyYzxOowy88dVmxNUEz8WrFAst3AAbI+PUqSvOEQRqZWDsNOV1PGH3mXG+HxoBJJkGTv4nwMU/E0eucYroc5/h3X1liTcLa7PsIUpmgfwgMHuB1y+UaEFPS2oMBB7fYXQTCDDE0lynVhQZIZkn5EagCEY9bpUkhnS3UMXLPG+lSXQd5z4CR4gPRkuyJwi4Zy1g4ykAgkRA2nWtyLShYbTqRxD24JYuW1QQ2ggkaEhzrxtCwj2u4TfQTMHJXKkt7I6w4zrWsXev7Wdmz1uw7VJkyq1LTh+8izVjQJlMMC2d33bPavgkab21ZYLSwAmuA7WuBhNWC+zlAeiQckN03macTnJtpqU95jeY7jr2QTQnrtZWeWfsNfgez2GNZOUmI5LiLM+rKvWAAYs1gO4xUTOQa9koc83iDEcmZHqoQSb7VIFPsNP0VuOnkj2XFxih9U3QyZYXgfwQkDhMIkRU2E/lRQFCp4hnFBmYQnxIdbcihmMfBEbuZh2nssyifOEGR3YrF+iaZJ+TEaOzDQJg+QqwGMhEWsUUakNYZ/UiU5DFee558Bifv/ZtqmVDY4TSqKAZDRg6nbYRl30LBRsygTRwwTRbTIgKXAZ9R4SFF3250HL+q1NoEj7SvVxX01n3MTR+TgZIIY/MiBFAfY83F+vKMzvEDF7E2qsyBagi4oQORkxm2/tl88G2wgjadk9EdpB/lbserGMdu+O2F0ba23BsOphQ7pLr1DoTbTg1+cj69GD7npNdUGP38G5YKQpihtIz0n2oVWNpj/YaFabuYnGmhfwGnV0iS/AzYyCI1aFl5PVhwIL33Hk+V5yhc1ydag2Oyw0y5TVTB3pE68ytychqkeyJS1pON0kE8B1g0YY61iAoz74ugLNMavXCZQLdwGE653oRKCeBobsJJnPnGV2t3KCzT4pWm9eQ9KbOveTHqPx94yUSHEJJEWoaHXXXMKeAlhdl3EVeRkuItMzUS4wglm2Cl1PjGk4FiK1KGjVFQE1kgEw3o6qecZ5HzzhJELE0ZXoMkbRJ5xmNBR5rR7rJdRDyswmk7oNQVAekXqQ0kieUy6jFiOSF5LURNdut8/M1E6wdBgEbXpVEX1GEo8d53tkhGbin8zx3NQWm8oQUEfocoOeW0CIebBXxCIU8iKKsvaXigP2paG9nHZp2x95x0wwT2sSDgNegXI3X2MRIezuOjdoq6y7d44wQfIfKA4nMehXsrfasADz8N5nacSq8G+0eFzosWpGT6LtpySwwaDFtV1pgv0ymD+ibpGho4LPL3alCLVyhbI1TAV75faB/kk47N8AUXiwFQCegpLvZh9M9Dpz4MPD4T/KOvzhL5eih44y4EhnWu9wqIx23Blz5BvDd32ZaKd3TqtEMHiNBoDjNOkvvBNB7mFHDXQ/Tya4JlTk/zhpPVHPpPQw8/U94rPwofV2ul84v20tttFsvA69+niy1nhGeTwQiPWNcx6mSYuw3CD5BwGsagYTnisJ2gyk5pUQzrgDY3yToRQ2cbk1AP6qJKEnxSTQU1CVaFMDRonQWwPqPUKJ1nTcBgVCrda1Fh4eSFF5FalzVtuOErNkYMtsHUXQUl56kmwQjFYHDjt9gwEgxpatLlAlJPQKtiLz5cpPnoie4/0jj7jYACNifbM8/BvBPAJTliMq27VO2bZ+93bU61rE7YbvRjt/OY6vCNDD3Bp3C4hXKsQSbmWmb6ku+AzXxsAxuA51pNKZgq2gv3QMceZL6ZjOv0znOX4DyG9LwCjrLhcukQKe6Gf1UloGx++ikhk8zakt2iSLACu+EJx6Els5Dy/Uh/NA/bA7XA8A00MxrrO0oRTJDto8gWLhJVYDhVCs1mcwytbdkU05n+TLTaoY05Y7fCwyf4bVZuUYqtC6TSz/4M9C7RziC4tIzBOqZ13mc4ixnHN16gXsyY8Do/WTO9R3hngs3RW4ow56Z0jyjiTDkv0ZFogUlEUBSUncm96EkJRp4JErkRvjZJnMt1YJaicCiC6kAPoCoedOUBlJx6s0YQKKUCHxMGWkB8NrAFIo6uLcoutY0Xk8NPJ7vEJA8jzjnu7whUUr6dtpYcU3bQFIIakBNa/1upIT9Jns1k4Av56UU36t8pggz/aSJu2vr/iR2+5vZz1/n3wZw1LbtXTthO9axd8p2Ug54u46tAp9zZVLddBbQgOlzpANvSA9upEcrQFSvY1uqGWzFzINhQi1fA7J90GJjUN0jMrSsTocb+BzQtpAhWSKaMxQpBwCyL0WyQNcgcPQD60Zn6/EknXNk8VGoRIpkhIbosU0+TNdjxlt03ugYsTSjq5UbZINlBnjnHalL6wZ158yE6LxJjWP8XmjRwLpGiY/lBngOvk/Vgqhjv/ewvLckkj9rPHffYwRXFSZccZbXOHBbIGimqRoNjSKp2X6ZH1QGMjkg7CYINCqAP8fXpXt5ruWlloJ0GNVm5Lp6NabIDEmNwmSay3eAsAaomMxTCjmawvNIpQ5NXtN1NZhAouK2aC4hdG0lRItACAzxLH+W2ifuROAX6cJh/XN+XWjikpIMPQ7pq5cEgALS5KEI3ips9Uo1I729pP7kK7fnV7bsFkgK74BQxzq2k8nUU4zfy/pF4NPZjpxaF53tR81gq2hvU+9QIgtVXmadpWuYd+ylHCOy8fv52MJl6aCPESS6hilCWl6ho777B6Clsjue5jol8MAnrVzX6agDl+v03iUn6zM6uueHmDocsBjFDR3nXhIZgm69SOLF5GOss3h1qAvPsK4TeFLLupsptte/TEccsd9WbxFUUseYGk0NENiMODB/ieCVyEnR3pEozaBEj5mgMzViZJZF02HTXQSoJAiMZiRno7UiRkDkeOqAX5arIzUWM0nqczzGmwIz2WLsRdYoiVqGCJlWZbSGJjI7ofQQaTrP00wJnVsjwEbJa936AAAgAElEQVRNsFGTK5SQDBSQiDO9GKXOlNSPQg1Q0gjcBCSda4QB3x+TfiDT4PsCTY6jAdkcUK9yUmyjRPBrr03doUhoHMBly7Jel6Mo27b/yj7W6VjH/nJbJMljxNl4KekerWu4+ZK3omawKdrbKk3n1qXPptQaXbA2D1z6Bh3p8N1MdSVywPXnBQDWWEuorHDk99End+2z0mQCqYr2E2m0dR8Hjr6/qTEXjTXXVND82Uw/zl9c3/O0cElSWCZd2fxF4N5PQOudgHKrwEt/wMinNC8O2mCaMPBYN/FqUqOScefVZT63NiueK2S6s14goAAt9mA8w0ioJDWhWglwZoVmbZIEUZoVAHD4fhUSNMz4+tq9GUNz2qmWkPSdL6oIAR16LEFygi/D4+I5gpUrGm9hFAlJ/SjdD/TfBcy8yt4dQ+o1utSdQp/HjCXRnEirxVp9PJpBYNV0iqZGxIao1yeU6CsU4kS9yNqapgGpBEE/2SUN1SVg/g2ehy6sv8CHREO7Foj2A0L/6T7e07GO3RG748oIb2Ev6yR5AlExHtkw9WQXSvntpBU3pek0nU5x0GKdxK1RiDQ3SAdrxGWkuAGc/iE0x4QvXGLRO5kFjCTU1eegrKegSb1inQJ4+7X3HTqg8ful6dEA3GqrrynwN+1XM5jaUwCPP38ZeOUPpJ6xzDt8TZGlVl4EFq9wvMXqNNdP5YGBI63xC6kenk+9LLptVU4DTWYYwdRXWqxFXQcqDUldybhs3RRl6SS14VK9HJQHJYribTWbqNnWiDPi6zvBqDIUGnNUB1PSV5PuZiTXKDNlF8sD0Flz0ePyOStGJ/UVvrZeJgBFwKgbBJZMN6+LmSToBT5fpwKmB+slgp8m4+IdGecQ9QkpaaA1BTyrBamNtVOtTa7hC6AE0mMVSzHNWy+0xFURshYWRH1DcUCZQOhs7KLdZPv5qz2QplTLsv53AE/IHv41gGcAfAbAAIAFAD9t23bJsqwzAP4dmMh8DsDP27atLMv6GwD+geznl23b/o+WZWkAonV9AP+NbdtvWpaV32rtgziPjr1z9nYoI7zVvTRTVWtzbCidfQNq4VJrrwdMKW+PnlTgc8bPkSeA6y+w0O9WWZTPDbAp02sA85eBiYeo+HD1OTp4p8Ja1htfpOObehVq6DjrFRMPQvkecPMFAKIIET02d5538NUVHkOPQY2cadG1y0vA8lVRWBhoXSfDpErD9363VUdK58ksHD1Fhl7fJNcPfWD6dWDlKhl3oUfShgp5d374A6zFVZa5D6cuUYjUOPQ47+w1STvF00x3JTIEvUw3yRAICUC+Q6KFHuMsoK4BUUsQ9YRUXga5rQgo6YxszLgAm6gURPU2w+A+NA3NYXsmqJyghMqtyWwn3SAgxlL8TBDy/LvHSb/GRUYgymNtrbzIx5M5oGsMWJsmAzFScQgl8qyv8droOiekeo4wBBtoBS8B4KvW774DoIsA3D3Kax5CgKtdgcGQH3EgdHb1s/uhaH8ewFkA/wHAqwA+d7sLWJb1QwBM27Y/BOAjAP4pgP8NwGfksc+A48MB4N8C+Al5XAH4a5ZlDYNjxp+Wfz9lWdYQgE+C6cGnwOmvvyRr/MI2a3fs+9TWpbFyAxwBvYH6/K7ay6LUOzY8fyco5ZphUjsuGn2t6XSww3cDEw+wWD31Ch1cMkenOH2OKTnrKZIH+o4I40tnDaeppmCyNvP8b7KGs3oLCFyqOUy/ykbR6grvqgtTdJgv/g7w3L/nQLfrzzMdeO15nnP7ddINUq/jaUZr3eNUbdY0rjtgsY7kypRQaBQxra8RfBJ5gsjCeQKjrhE8UtJv5EhjbVS0j8YPpLsJTGaK0cbgSTrW6rK0xThAeY7kh+oqx3/Xy4yEjDiB0PPpnZJd7OfK9JJ0kekHEn1CoJDorrrK61Nf4zUOHTYaF6a5XjzN9SurbbR3R1JmJs+7ssAZRXFp5o1lCFKGyWho4n7S7E0BUyPOvWka05demaBZWeJ4iu7xVpTU+maDKbWoxgNS4vsPA4cekjEODWzqG9JN7imRA4CdC4rYHwjdBHBGHP1pkKhwu/YVAD8HAMKyWwVw2LbtP5XH/hzAccuyDgO4aNv2rLzvl0Cg+TiA37Bt27Vt2wPw/8hjnwSjqmgM+WXLsiYBHNu49u1sdnFxEZ/85CfX/fu93+uIi7+jtrFXJpZsUZ/fbXvZ5Xkt3QPt2FPQrA/w5x6iORX4UE4Vocum0G3Bd+iEyNkU0RwuN3CEOX2nwtRQ72Rzn5qukSSgKYkWDBbJExk0p5tOvcr/dw1yzZUbXMetMXrqPwyM3k1Hm+xmGkgFFCsF+D5NJ03bqUJVC9x/4LPO4tZ5R19dYcoo0y/KzR7rV0PHGWWl+8SxFzjB1Uwxolm8Sqq6bjIKhEZQ0zVhcwn4mBJh+B7VIhIZnqthAn1HgX6L0U8YAHUZOwGF5jgGt8b3D1okWmQk3RZR6pX0/ARV6R1bblG8nQpB0ZeoDzECiZlgRJPKSaOxiLV60o9kCp27usrPtVGRseNrvBaJLgLU5W+yEbdnAug7zqjTLYs+XfRdEfJAeZqpvFBre3wr83hjUVoEFi9KTmyLxFjoyvjyJQDYNaTfz+3WsDh42LY9Z1nWyO0uYNt2CCCUNNn/AeDTAH5mw8sCAEMAZtvet2RZVp88frnttbMAPgCg17btpQ2PD2MzX3Dv/EEAg4OD+MIXvnA7b+nYnbZ3Uhnhdveyh73eTu1nO9HR9nTkpvTggAXkR6Als1Dj97E7P5ZpCXAuXII68gTfn+nlP4DF8tCjE/UcpuCKU6I+0NXSRjNijD6iEQOz51lviiWBnkMy0E6G9UX1qsoKnafXEEKDAu7+GPDy74tcTAA8+uN8fd8kHdvcGxQ5nXuT/i+RI9gkkoAecNDc4hX60VoBGLuHIGGmWC8KC8K2a7SK/ggBo6ul9RbRlEfPAPkR4LUvSMopTVUKiFpEiqw9jshWXD/TQ8CrFWXkdYPgl8gAQaqlwM2L2/ap+gSk6gp/jeSNQp+svLjJRlU/aN3cKA8wBqUxtUwSQSJNgKsUJAo2eK2cBuBXhWLd/Ca1/lsrYEtAaZo856wBiyLrY+rb0A4kZcgnd/1S7ycSmrYs62ctyzosjav7mrJqWdYHAPwqgH9l2/aXsFny2wDrNyNt7xkAUNj4OIBReaxgWVb/Fo9vtXbHvo/traaxokgiiiA2/n67e8HYvUCtCLU6Qwc0di/XdSgcum6vTpURym3uMXqsKTpaXhBNugWmySS1tSk9mOoSyvEa1No8I4CP/lPWLVJ5gkP3GHDzJe537F46ykwfnfTwKd55l1d43PF7gb67mJZamyPQjd0LjN7Du/OFq6RXVwtM+9WLbEzVdKbBFq8w0rn+PF9/5RvA2c+T7ZbuAT7wM8DEQ4yiyotUWRi7n6m44ZOMjEKXd+XJDIvuniPFeBnNYMQJeLfOAjdf5DEqyzIkb5qsrsCl0+6dpHpDJKRq6HTk06+SWegHBGMIFTpUQCg9SeUlKk3Mvs5C/fXvAteeY+1KN6QuFPA61tfa0lcbv2eKdGu3zkjGrbJWFKXXagWClFcmASDSc6uvEqRDxTRjeYmflfL5PVy+xmvolvjZbQc0EVUd+vavaZoHwGkpKWxpURrvzrDj/iswlfbLAM6Bzau3ZVLT+Wmw1hNB81XLsj5q2/bXLMv6CADbtu3rlmWdsixr2LbteQD/EMAfAXgewG9ZlvVH4Jl+CqwRlQD8LID/UWpEJ2SNTWvv47w79i6z/SojbIwSVN9h1hb2SXBoiok2ypR0GTgK2N+GahvjoE08CG0ngsIue2y+LlKk9hxSluNpOsP+oy26MLCOcUc9tyt05oZOwPAaTGHdeol38vEUe3mqK6wzRAwyDbyr9ep0/PEUC93FGYJUVnpubrxARYJUN7BiAxOPMDop3AJuvkxJnqf/MfDq54DDj0tKDEzJmSaPuzYPvPA7wKM/QXBNpBmRleaA818lay83IIy3PjrpRBfBp7JI4KiVSGSIZwikS9dEacLlNQs9NBWmE23NqKEvJIYqsLYI9E8QxFanKApqmDz/UCR01qYltaXz+pWX+Ln0TciaRaatEt1AUJY+pgh4dnDyKgB8GRMRehyhoG2n1wZGQ34gk1dLBKVofbcmdRsZJ6HHQQDZwhpFrE8QNft83qodyGTVdWbbdgXAz+9rOy17GMDjAJ6xLAtgtPJ3Afy6ZVk/D2BRfgeAfwTgdy3L0gF8D8DnhR33mwC+Jq/5FUkNfg7AY5ZlfR28oj8rz/9P26zdse9zu11lhC3FP89+Fjj86L5GP6yLTOqr1DCrLrdkXA4/DoQyxuHIky2CQiwJ1aiQ/nziaSoRbLfHtj3BTPCOtVl8F8ruwgVg5EwrxRcJqeomazi6DnQP069MnSVgzpylgzVjUjAvcsJppPJtxrn+xa+R/lyaZ7G7OMO6TH6MAJlIUz7HjNEZ6ybrH/Fx0YWbYSSTzDJaSuVZy1iyWTdIZQhkuZB37Re/DlTmSWdPCCDazxE45i8SNJavExDrq61RCKkuoLhAQBo6zmK+W+P+fEcUakQMVJcRCY5DUGlIc2m6h78XZ5hGdKoCAoZMOHXpzJ2aNGai5eQR8Lw0DU35H9XWg8NvbPQpb/2FMkypXcmgOiVTSrf/BvK4zeF0besqj++HCcDdKKezwbaoUMSy0ux6e1pwG+zgmlUty/r/bNv+McuyLmD9FVW2bZ/a4a2bzLbtPwHwJ1s89Z9v8drXQQbcxsd/DxtGj9u2rQD8d1u8trjV2h17D9qGvhzohqQimKHdbfTDlr0xgYfm5MtMD5210pgzDzxo8RTXbJRaIxvqa7yzr6wAUOsbQnfoHdISGaiRU8CtVxgVFGfJKHPqQM84R0UkMqRb33qFz8+9Sac8fY7pLLdGJWvPYcpG04RBlyZIHrqff9nVthpFVrLcS9cJRD2HKCQ6+wZBYfZ1ssUaFTr36XMkLGg6ayuLlwgmU2fbFKAdRlhGDIgbTLNl+1jgX7ZJz9Z0rrd0nSC3cpPKBlAE34ak4nSddZ90np+HW6W6dG2V0VQg6hVajNFj4JPsUBXHrHxhpa0R7Nwa04GNNYJO6EAmhcp3pq39RbVFF0o01YyEqBjUpK9IkzRfdf3r202T0Q5GnKm3oI69RyPbAUWIbaOoHU3xukYAtn87OBCybfvH5Ofdb2VHHevYO2obSALNvgmRud+J4LBVigyJHP8fSid9o8yaSyDqyO2jHZJd6xtCATrdZG599LULkUHrGoaaeJDAeTRF1emZV6kerelQw3dDO/4UI683vsJUXSzDfpLpc/y9ITWCSNzSq/Bc4inWcuqr9H+lBZHod6XZspskhxMfZW/Pte8Cl59hJFUvEYhqRUY9uUGuUS8KEy1Bl1S4QTAcPEnwLC9KcR9AQWonDqWK4FSZjgt8khOyfUwxJbJ09K6AnlJ8XaPC2UpdI4C5RjXtMGDDaNAAIM2ZXh0kJKQoR+P4TNm5knpTGmtNjsjetDv5JqNt05eL18Ct81qZSe5PF106RHI5G03qMKYpmOFKNCSfz75ApN32G8lsOyPoQG1XELIs6yd3e41t2//vwWynYx27s7aV+Cce/BFg+RpJAxs02iLbLkWmHXuqFXVkB5gm6psUoUrwTjxaM56EihpCKyt0qMMnReNtab1Kwk66cYYJTD7CY9ZW2ZgZS7GJEhrPRdOBoVMc67w2xybLdB/n4Jz+OOsnCxdIavAb0u+SExbVNB1o9yijOlPSTxG1+tgHoUdioqFPH5cfBVZuEVDqa9R8G7LYk3T9uyzaz05xLypgKm8oJw2PUrjXNAqPKpf6dQs2u/890WorzkrUlORd+tqMyN2IRppbJcBUlwF3jKSF7jHWmuJp3tAHMsoBMm4hcJia0yKVaZ1EglRPKyoJGthTRBJpusXTBKLA5/tUSGDzahJdG4yuAq9VozLTTBWuGw630/iFaLbPW0qV7XZCOKC60I62l0hoIwX7CQB9AP4CwIfAGksHhDr2rrHdpHy2FP/sOdQakwBhtbW/f6cUWbtKQZseWlPxOdkFTWo+WroH6sTTgEzJ1BLZdZFOc++JHLSddOPSPVBHniQNuLLCyMVMML20cImRydQrrG0kc4DfxTpNlLZKZln/GTnN2kzkQE98mCBiJhjVve/vsHY0cJzpsCNPQs8NtK5JMgeMnZEO+YRMIk0ytVdZAmJChZ6/ROdcXWGa6s2viE6ay/TbxENCPOgG5i7x+sRltk1lCWjU6LDjKf6/sSaOXtSjNTDSjGepDTfzKqO2ux5jj08sBXhp7s+JaiNSB/F8UGQ0QZ+uArLnfFfUDvbyrTN4TeullmK3FnK9WJxranGCpi8pyNATtQNhgKhQGIQiqOq72D4K0rHHje3PjKT0VN15nepdQci27X/Z/rtlWX8B4CO2bXuWZcUA/Omd2lzHOna7tlcpn42Ehuj3bd+/Q4qsHfR0WXMTA69tH3o8CXX0SUY6bdGXapTWvUfbgaUXVgvA5WeB+fNk5EFjE+rUqyI+qbGOo2Q0tBGTMQpjwOw5KiK89sd0gMk8m0BL86wdXfk2qb2+MLN67yJBQDeA+fNQ8WTrmsSSwOBRIQwU6XAf/FHg6nPAtdeY2kt2s9Y0eJzEDT0GXHsJKE8xbebWWYNxRTU6JuOyCzfp0HsmGLW5Ne43ngPq00xZBU5rAqmZJejnR1uvffPLQkowCKJOZcvrSdFPgGiqANXguvEuYZ5JP9G2FrSYaU4Z61J4bgAkUwTJWALQB4DGMhAYbAqOJaVnq8zI0pD0sKYJNbw9GonGJEQgZKIFRm8xajG7AF9UdtrHhN9h20+fUJeoFACE6e4D3E/HOrZve6tSPju9f7u+JNUoQV15Fsr+Fn/WVve0j40qCUjk9rx3FfhUmV69xRTgyCmmtC79BZ1s3xFg5CRBpTjdSlNl+8hyCwPqyN33V4Gx00DfIUYog8eY8lq8ytTa2hxrJCs3gVQeWn6Y+7rxIsIaowlt4kGCSqpXopoBprtygwSQ8fuB4eMAdKYGdRlBXl9m1KKB4GB/myBUmud7x+9jVBZPkw7dqAr4lDkTKXSYKjM0UWTwRYVA5ic5ZQFjMKrQNPbPbBk9xLiXSD26vW4TTT2NpQEYjGaabYZtQ+nQ3oMjE0+b5rMmpelML6bzXC+eZiSZFeUJPUZyQiARIiACpSkgnge6xqXXR9ZsHqudffcWLGL77dn2Ax+bbT99Ql8SKvQXAXwCwFcPZCcd69hbtV0Uqd/q+zdNPwWAK89uplJPPLynfbRHY5tmAe20d99p9YCU5qWrPg4MyXydbL/Ucap0rDXRPIslWa+Kjp8fhsoNMHW0fIOO/srXCUgDx1iX0YTRBUC5Mlrg1iuAW4NK5ghCQ3cz8um5Sxy9oq5cPMMmy0aJNSGvxtShpgkxwuB5mDGhTsuAuK5hkhu8BvuMggDQpBfGKfH9ZlJEPuui2B0jWPgByRQintrst/GbHfybTTdFWy7S2gzRBJpQdNc8iYSioXGIo8Uak7Ha25o0ojolYKHI98dkBHfU8KqJUGl1VVhxkOPE0Bwap0T9Olpz3c8DMHW7IHQw9ajbhjLbtv8ZKLPTB+BXbdv+Hw5kJx3r2Fu1tpQZsDPTbb/vb4qDttGzN2nCAbe/j9vZuykKzQWRbYyl+JjfoNBn6DMFV1lkKis3RMddmGLKbPJRRjROhQBUWQLsb1KkM5EBeg/RoecGCWKeQ+C59TIlbDQFdI80oyJc+guSBEJhlulx3rWXFxmt1csEFC1GBlvoSbZKnGutyIhg6AyjnnNfpEK277Xm/XgulQQAADobZeNpNAfSJbuo/5brRzRCgr0/GoEokZZmTZ11GE2EQAE+X13C+igp5O+By/oThGTATwcEIEP+7dBMyi8D9+PLOA+/RvJEZVEOFfL58pJEIwYYH+j8TANF0C2vgAPo/nLZfuOpSHfiG5ZlpQ5wPx3r2L5tr1I+20n07Pb+TVI/msFGVKkzKK9BJxP4FL90qnuSFIrWxcBRoF6CKkwBTnXb9zRlgtK9jDSqy0D/JGC9n3f1PRMU4MwO0qnlh4HBI9J8mpDG0CHg6vPAhT8HXvlDPpYfIfVZj/F9RRnoNnScoBTVvpx6q79mdQa48SIdv5Fgcb5wEzAVa1Sew/15NdZ7ykvA1GsEF9+RgW0Bn5s7xzWrK5TWufkiMHdR+nkKdOLRNVaKgJ/IMfLrGSMohVF6Smb5RDTrehVNENFl1EAEQn5F0l/t7rC9qTQCp43uUthp+k4uUI8+NP4/9GSPMrunsSrjHoSmrelogVqU1nMEJN+qOO/+ldnvpN32rizL+jkAZ0AF7W+CUjqfOuB9daxj+7LdpHx2Iy5s9/5tpX68BjB3gSKiusm6xHd+HYDGGsvhx6B1DW8LQE2CwcJFprp0jamweHqXM9WZxsqPMhLqvYvRgPVBTi11G8DMa2xUrS5Lyi7JaOLNr1DhAJCJoyuklvt1in3OX6QsztBJ4NAD3NvISVKmL/45JYpuPA/AZPqoukSlgfyQsNmKlNPJDrJmJSKl8BoyqM7lfmIpoFZlZLVwBSgXgL5xXrt6mbRyzWBzpxZjz02qh3WbaFaPGZcxEyuU7FGesAE9wHVFsFNxXEUoZIFAdNfW2XaRTHt0tPE9kpoLPbQIAxssShtC5968EJvSWEGd84Z2TG8dROrr7R9zshfbTyT012zb/nEAddu2XwFw7ID31LGOvSVblzJrs70SFza+f9P7DJNSP7oJrf8w01uGjPKuFeiIuwZICpg7v+0+1xMM+hkt1Ir8F0tsS0wIS4vAi7/Lu+eVKYLCG18GnDI0v869p/Mc2wBI5DMMZIeBa98h06w0KyB1gamtriGmym7JmIaRk6xbAFJ7qbDfx0zwX2GKAqSl2VZT5uIVsvPqKwQmDZQK8hyCgu+wLqVprJG4VQAe/x9Ium3uItevr5JgoMJWvUSXplTN4HOBzOdZmxfVbamZuFXRXauCaTNZX0WjrRNopby2/RZt9Ylt8bsoEsSSjDKNhNSnUpQniqdlWmtS3r5dNHMn+33e3bYfENIty+oFoCzLaqeKdKxj727b7wyiDe9jD0c0GA3QklkAIaMgXWRmIo03t7b9+hHBQJcJn5rG90YyQlvsjcD1Ao+d6qGzdirN47Wz+XD0fcDofUyxRQ2aa/My+iALQFG4MtMrGnBdTMMdf5qNqotXCHaVZWDxOhtb9RibVvW4iLOarAVVVwlUqTzfW14gAGsyHyeWFDmciOq8sc8llOL9GnubogZPQ/po6mWmsXSDNZp6RZQQQjLh3DrfH3oEvKCdiLCBPaai5tNdKNd7NkXiQuiwfhNLCunAFdp5mlGrYYKEho61236ShL8A4FvgqOw/A/C/HOiOOtaxO2X7nUG0UepHmlGjuTDKqYj2WlYUCCTdE3XPb7e+mZA6Rih38aqlQ6eCLfemnKpopRnsvYlFkkNCPOibhKoWgEwv5X2sJ4GpLFNWyidTbm2eoxgWbKEzVwkelSJrKItXSDboHmUtxm1whlCo2D+i6ZS6iSKSaEqpYRDgirMiYxQTqR6NqcLKkjDh2iOKLdhdnoyZjueEXg5Jsw0ScJUAFkz+H4rOvl1mZlN/jdSJtgOmAzNXSHNha/2G4mcM8HqERhsDrmP7AaEXAPwagBwYBZ0G8KWD3FTHOnYnbDc5nNt5X1PqZ/4yGzsHLQJGpo/MNGjURzv0AJUUonU2rjv5CJRb43iHeJoOvWsICPxNewurBabvFq8wYmlUWG9pVCj+efNFKigAUCJiirF7gOnXAIhG3OSj7APyquxXCT3WYxIp3qknMsD5r4giQQMYOkb5n3iaEVBxgYPloJPuXbgBeKL4nBuWyEoIEUacQqTxNEkXbplK3RFtelszGa04RR7HMAEjC+Tl+E4FQNAq8AMgALUDT/QzqtVsrMVENOv2fpuDsojkIMfzIq05TSTkYlIDgrzu3VmrebtsPyAUKWDfPOC9dKxjd9z2O4Noq/eFRkLqJFIL6pukwz31cTpO3wFmzkHtoN6gpXuAe34Y6viH+YCZaMr+tO+tWZdKZIAjj7VqN+lekhJ8j0PmdJ01poGjrfERkdhpMsu6z+JVoFsaH+cuMPrqt1g3mbvAyMhMMaJrVBlxJXN0+mNnqLKdyJHMYH+T6af8CNN2xSkg6VMktWuUNSgokhLG7qF8T3lReoQa2FIk01At8U4zwQjLFKHWekH03Dysd97b6ZwFWK8yEAFR1Huj8ZqFkhK97V6Z7WyrVJ+SKNnj84ZE1e/dchCA/YFQw7btXzjwnXSsY2+T3e4Moq3epwKfCgCxJCMX3+Xogp4J6sSZCahbL205E2iriEiLZvhssEgSSAV+q5k1loQ6+j4Cw+o05+jMX+DE01QXASfaiwoYbd14kQBQuEHAiKWZSsv0MGqJxUkyiB7LDgGFawS6yhJ7hzK9osFWBx7+mzJrJ2yNbwhDNqGO3cu03vybBOi7HgZm3mDTafcoX+M2WqOo1wFEWwoy9Bmh+UIs8ETk1DCl5rPuSm34va2pUxd16o3RjnIAxFkLa5Sx7YiFgzQzCZg5wFmR8R/uLlHhQZlGtYcmyBpopQxNIYts3Ec74+/OiZnuB4S+KEPjLkQP2Lb99w9uSx3r2PeBRYSBeLqloFArApC797eq3oANtHBNZ/9ScwSFzwmn3aOtesOa9PUk0s05RTATUL7D1xduUKMsIWMdSnNkc2UHRK9MYzOrCgkeI/dQkSGZ4/PpbvqirmFABdBSWahDD3J66dybwPJVgtGizf6X2iqjH2gEas8FHvhR4LnPCCVcCAS+1JX0tNSQdNZ4YnGRyQlE7NOgTE/goOUQdQAxkHW2sc8ncqBb0KIjixiAm6R27pCFUYulULtDqW01ozoRmPUdtFS0D/ON2WoAACAASURBVCJVqADlUl/Pl1po4PBzjaVa5JVGcYdjRkDUvt+3bvsBoZ8E8IvopOM69l62SLyzZwJYugIEBf59Tj5GVW5gfyQIsa1GR8CtsZm1vATE09AmH+Frb7zI6CSaB1RZJjBNPsbFps4KiPQQgGqrvPN1akD/oMwAWmMdaOz/b+9Ng+Q6ryvB85bcM2uvQlVhKwAfiIUgKUICQYqSKVKU6abYYbrNsGjZDsnTLavtGHe73RMeT9uekHuiQ9Gbxz0zbXfb7hh7ehwjhylZUlvdou2WRFnmYkkEVwgEHnYUUKh9y/0t8+Pcl5mVlZm1ohJAfScCAVTWy/e+96rwnbz3nnvufZSWL0g95vhPULSQ7qNgYPwM031nX0IwcoLfs0yOTcj08xw3RfbdLdHT4gQw8jAwd5VEtvN97OuZvSFzljKiKowJSaY5WdUVqxvfl6goLR5wk1jyqdwEi/3duxjRlAsi2RY5txltHm2UC/K9FWevybViQhzrJIYgqJnWGpX+pQIqDgmWqAYjCblFt4aQNoqAhA+fKj5YbPL1ap0haq9T36Qbfq/Vs5IptGsgqfWQ0BUA/1+NiamGxqZjpXEMqz1utedZ63sMy2bD6qkvVhVix3+iMuaglQii1fn9UoHpKpFoL4mkygWRhtuA73GKascgTUIXJzkKoZSn8u3IUzAz/RVPOiS7q2ks3wO69gAqHDzn0/WgcyftePr2M02WGQDe9+MwLJNEN/qmfBCOA5PnOC31yA+THD2P0ZdpUEGXnyUxeT5rStFO9h517QIGj7CGBlDane6TtKDLGlTPbjpAzN8kIZbzPM7NU/ZccT6IAjBYI+rewyjMCOfs5AAzTpJzQ4udRrJsl2tfFQmJjH7dkYktKS9pNHazomwM12TJWsSlIZqWulgCrUd8rwVezd8+sDDJiDRoRaz1z6zV1i9u5WGT8CrYcz0ktAfAe0qpM+ELjuM8vY7zaGg0xGrHMax03GrPs55rB55Lx4R9D0lXvwfMXEHQt686fK6RmKHF+f3x88AbX6oSTfcumoRG4ghmb1A2PXCQG6FXBq69gSAkoNy0+Mld5vc6hxFE4zWTX126K7z5Va7birB2E0vTlmduDLjyXTpUm6ZY8GQq9xGMnGSUMT/Gxks7BsyPM8W36/0ADNaUFsSwtFjgM0n2sAYVTwFnvwH87X8m2fTsBXY+wFpRdoLKu3gHr5kZ4LVmrvB98BkxLElRRUXdB0YPsZSMrLD4HKIJpkctmW1USjCqWpLKA9Ym1fY3NuLAsGWzL8ro7HrUkIAdBUrzWD/hrQZBzWylzYIrZrG1F2mN9TSrPgPgcQA/X/NHQ2NTsFpXg5WOW89YhzW9J6z5xNIwogkYsXTD5tJa94WG55exCH5+kQQUTzMKSHZyTlB+DsHcGKOQnt3coOfHmM6KJphGOfcSSaO4wDRYfpb3c+V1rmHPcaaArr/DiG3gIEcllHN0zX7zy8Cll9m/Y9r8ZDx1memyy68hyM3AiKWqDad2jNFFNMHjd97HKKpY4EbfrxhRBT7FEN17uV7fk+mti+IL946o3GT0tWmTsMbPUdqdm2ZkFPiMlEyL6TBYQEyEECb4DDL9/GNFue1ldjBVaJvitFCmGMOOt/jti2HliCgc27AOrGVAnFvArSWgLcOKN7Hmp+k4jq4Fadw6rLagv9Jx6xEGrOU962l8rTs/XHGnDusYi9PcvAFGBItTrJ9YNjf9mSvcwA1D6hJgJON73LRcl5FAKG0u5xFOfg1GTrLx1Iww8oilGDWFG3dmBzA3ziinlAN6RoDhI4AVYypu5CRtgG6cZgQUTVCSXiowLZfpB4bvBUZdoGs3P/FH0yREV+ougcv3hS4HyS5eO9kLwKR4Yfw8iSzTz7Sg59ISyC1JZGaylgVIYd9k3SndLxY+N3gPls3Xy3n2UPllRmhBs+xQ6OBgkYciKYlE6j/IG5KSs4FEv6QVPayuBhJGcRtVma3nHLWGrFuKFS94e9qqamxfrHZzX+m49ZDEGt6zrsbX2nENpi0moj5VaoUsJ56mu7kZ52Z4TKqHm+eEQ9JauElJdCwJDB/jZts3QmHBxDlep2OQxGZHRdrtwoilEKR6uEl7nozZLjJKiKX5JzvDc82Mcq3JXm7aMj8I8QzwwLMkHRioDIuLpWCkexEcelzqP3FGLtE0MF5gX9DiZFV1B4NbUyQu4xgs9v9MmVTZdQwwGtv9IJ9NxzCJdfQtnssIADvJVF0QcDqrETDyCTze1/wYsOMQr9mvSIZ2lETvSZ9Obd+QEeHfJvj9Uui6HdaYhEAqPUo+U1m2yQjSj6B1rSTEZpDAekgovJe1XioqxN1CYdgaK77J+tznPreeE28bnDt37tOJRGJk165d7V7KtoBhmiyiz1yV3o2Am3sstabjVnue9Vy7cnwkwV6crp0w+g+0PPey82en6JEWibMWkuqW5tEzjFAWp9j307MbuP42p6J6JTHyjDEysWRDP/AhElDoAZfpI9kku0laM1dhpHthdO1kX9H1t3kNt8Am1f0nGZXk57mpZ6epbNt5P8eHWxHOKTJMrvvgR2D07mWNaX4MRoI9Tkaik2sIfNY/5q4D9z3NtfpSQzOM6kRR1yWZTl7i9U2ZDRRLUcDgu3w2+z8oE1qPADmZyFousCHWjrK25JV4b5EEkOjiOfwy7yHRJaIMkXnn5vjc7Fh1Uqkhzap+SFA1SjBLUoCmzWcRWgVZMpvIigC2zfSgYaNpBiqUm68aMt5hCSwZRdHoe2tBrWNDs3NZ8uzEHjRwa45dpZADQcn4+Oc+3+ooHQlpbBrWo0RrhNW6Gqx03HrcEdb6nrU2vobnD0KZ7sT5qmlpZoD/v4fuZTRk2cClv+X7OgcZybhlWvWMPMxP/fEOjm4YPsYLTJwnudz4AbDnQRiZ/mqj7P5Hed6TPyPRxwyPL+a4kT7yKfq1FRcZ7RQXGQHtfxiGaQOmjSA3y8gs1QPDjiGojxx7R4AHfpwCh5tn2cfklQH1Q0wbjjxEBd97fwFMXCJ5xFIkpt59JM7pK/wQUFxkVAQAV1/ncYceBy6+RvJOdgAHPs5R5Kke1rryIjX3fUZQPSMy7iJFkYL/Ho8tLpBUTHGSKBerJqgBUG3iBH9OiTTrSfk5kqCX57MKXN5jOU9Cd8vAxFkO56uHHQMMaVAFaiKyZr8stqyljCU2RH2HADPgh5jCasUL9aMifN6fafFnX86jYiFkRkjGlrije6KcM8QH0A8NYFeAEQGC4ooWFJqENDYF61GitcJqN/eVjluPO8J6HRXq0YyUQ4cEf/8HuVHP32QEUsoyWigssH8j0SG9PenqRm+4rI9c/T4/kVsRBDvv5zMf+4FsqGIcOnMNQcdQtbYlNRFDZORIdSGIJJiumr7MOUKSVsShJ0iU0SRTUACC+fHKaIogEmeUWO+p17UbuPgdksDoW5SNx1IiDXeZVvRFim1aQNdObtx2lFFW1zDJoE9x8ujRp5hKmxll79DBj5A8yjmu+eZZPqOouIKXcoyGZq6w9rU4TiJJdrPHqSDkH0lywikMIN4JLDiinAtTbwBQ4l7rgtGQHTCdmF9g+q+c4z3MjlE+biVISt27mTItzmPJxl8uMLLrHAImwtJ6i9SaIX1Dbs1UVxNA7ibFHjvuASYusjG4petCSED11zJINEZo7hrOR5JIL/Ak4JGeIssSuTuWnqNZFBW4AJBusbDK6jQ0NoT1KNHudvjZaQTnXkLg/DX/zs0sO8bM9AOPfJpD7Nwip40mMnQKyM8wcpi+Cux+f3XaaxhBxVKVZ43Rt4CBQ9yASzluHgMH+e/CPF2+rQg3wEYjxKcvk7RiacCyK6o6M9kJY+QErz03RnXdrvtgdA5WfsaIZWAcfAyG+jCw4wjw1ldIVBMOyWXmUnX2j1didDN5kS4LixPyCRx8LUwFxjLc27qGq5Lw3e8jOb373/i7VsgxAioskoiykzRqdYusGxWykkYzGBnO32Aas7Ag9j8+P6mXXAotYilwO2ySZirnma4sST0vKsRaLpCMIikgO06iz04BqX4SHcxqvQkBELFEOh4as9ZPZRV7HSNCMqiVpRs2CdZ1gdwU1xOJYeVtvNY5vO71oMQaoRlBtY9Kvo7E+Lcpzadunn8vuV6ziMiTPysHOjoS0tg4NsGi5m5CI7eDZr5xZqYf/sHHGNUku0k8+VluxsluoGcERqKjmsIrZoFrp5bMRAoKojTb837WVeIZ1lnO/HdukpEEcPw5mNE4gvrIZegocP5lbmq+K2KIvorzN6wosPckowrfg5Hur143N4sgOw0j1cNU07VTqIzszi9SpNDRT8FDbpJ1rlQf0LeX93vhZcrAM3QNx8I4p7EO7KMj9833WNva/QAJx4wwjQYw3VUuoDIuwy3w2QQ3JYVmVlV4xTnZTCPVuk9goDJhNT/HJtva8Qu8S1Q+6fugsWrgC4HJ7CfTkPMCKBWBIF8dtVEu8JxBOHLN5Wj0eIbr8Mo8vt4GxzCkibVu5pIVYeNqOce1W+IEYUVljQ0k4GacH1RKWSz3hvNIaKYlwwbjVQ4uFUhCi5M1zyJ8NmsSKNySZlUNjaVY75yeuxVrJGUjlkIgjaFIdHBjC+sa01c46sEtktjKBeDGaQSmCSMzwCjHd5nyGzlBsluYZF3lgR+lYsz3OHaie/eymlfguYyE4mmSXmEBmLqEICf2O9lpMUPdDcxcRRCJwkj3s3l29E06N8RSVKL5HlOLkSjTVrNXqfIL01fz49z0onF+qu8aZrTiuayHRdMkw6lL7DtK9wKnXyQRxWSUxILB6CjdT7L2PUYEhklxgGVzk8/P816MHBtMoylJL1lcS+Ax+inmpPm3JPY+taO/wzQVwAZTt0oElkQO0ajYJAWs0/gAyouAnRIyMbBENVcSl4TArwocluzTgcjvg6Xvg8HnVFwEDBnuF86WgkR1aEBCviukB/GFq0dZ+rd6+AGklOe17ZBEw+ewbmgS0rj1WItcebPECythq67T8FprJOXa54dkN3DlFM1Jk10s9F89xc3EitHiZtd9wLW3EXQO07Gg/wDgfBvB0FGKDwrzPHG6r7qRiOUP7chq1uoWEfTtY2osO8PNPNPPuUXJTqa5oglgYYw1iPC6516icm9uFOjbxxRcYZ7psflFFs2jSYoH5se44Q8c5PdvnKZYIAhY+E72knwjcQAuo6hTX+I9+z7JKZ4Brr3Fuk12lvUGQ5ygPUlXRWOyOedICMU5zjryPcCYlZETg0z3jZ8VNRuqYyH8RunjUAlmMeKIpzkXqVggaeXy8j6/ZrsVex/DahB9+DRyRcXWBks3+UY+bUJUoSLOD/iMokl+YCnJPTaCaZGsvVbihYA/F/ji0xfw52bY4q23hibb5dDpOI2twWpUZZstXmiGzb5OS6+3ZtdaYw9RRTWXnWYtIdUD2BEYpo1g9F2STej/NniYm/j4WW6K09eYfrvyfabkdj/IAvKZb5AkPA/oGkTQf5DRSZnqpmDkJK+b7GZkUVoExs7yk701yvPk5vgJOi/2Ll07SR4DB9lY6xZZz+ncyY0wEgGi0tuUn+PGbYCfsEs5Ojpkp4H0IICACrmrr5OE9pwg4YydZX3KjgCpnRQZzJmMArJT0owb5d8emB7zikAuR2KIivmnGWPUYBmMOjyXhJixQKKgB1/jEQ5yTDTOzb+cJdnlwoZXnz1CHrD8w74vfoKRZWclalNvMbm+EJEVrarn+NtXs6S42BKlmH4MPEaZS/zn6u7B9xgtBa1IyOTPPlw7AORlZEZDYt5caGGCxqah1qKmHlslXtjs6zQTGASeCz83x4ihwbWMZHelYG8cfGxVJGhYNusrMaZyDNNmum3uOjflSBxAAFz6Hqe5xlKsoSyMVSMW06yS4tw1buTxFD+Vv/lnjBJmrrCY/8of0pJnz3GSybW3+X71KK93/TRHdXsu+0VMm+o9O8bzFvP8dylH54CZa5RE+wEjgVQ3G2f9gLWZRCcjLhNAdoxF+d49JFU7SYJwXUZinQOsH1lxVDZG0wb7e0RCLI247PexRDpdJPkVF6ppLa/IT/NeXhp1RY2Yn2geQYQmouU8/051U0wQFFEZSue6UtNpBBfwW43wlq03qP29tEmuzTJYpngGhsSyGnIxIMc0M2k1a+phAMnXALycpOZu/XgLHQlpbA22SrywiddpJjAIhu9jw2dhgbLo/Q/zmLprrVseXhtF+S5Hh1sRGph6JdYCRk6SMEphTUM+zcczLPYHPqOVWJrvXZigKmvqfNUodP4m+5COPsXzlXJA1xDJb9f9wHvfEolwkZGSaVUFA/AZAWX6JfVkcgBdoov1m4VxrtX3gVQXkDzA9XUNARM5YHqU5+0YYD2oew+jt1Q/P+0PHiZhvPPnvN9EJ9NPoXIriLBu4WUlpVaSCEVGQhhSVwvFB2Fay82hYjhrRGsEAPWbrYgSYhlxYgi4DitJAjRsEpsRB4JmpqaNzhue3qwJcsJ/yOiKxm8QQgyoOjRNID/V5NgQ5ZprhOKIWtIKRRchEdavdWssfnQkpLE1qLWsAW6deGEzrxMSWo0SDeUCzTfDkdbRJHDtLQS+u2n3VBtF4dCTJI2pS7Tp2XmfTC5dpFjA90iGXpnebZ7LNSU6QVmvyU3GMKvGo2FzbDRZuU8jliIxhRFjqSA1kE5xvL4PGDjMiGf3A6w3de1iNNS5h0KIIGA0dPUNTlUtFyhS6N5LYurbD8CkWs8rkaimLjH9GEvRleHAB4GnfpXrnTxHccLISRExRKsSZa/EGlAizXMGoDoNAdOL8bRItGudAWQjDoUJlQ8IjQhIzFztaPUY31sqJjBMEZI0+nlLRLHk63ApMkjOCCeXrnazD1ARLPhrHUNeG+3Un7MZtqbFom2RkFLKBPApAK85jnNaKdUJ4A8A9AO4CeAzjuPMK6WOAfg/wN+ilwH8muM4gVLqEwD+R/Ap/p+O4/ypUsoA8HkAj4BP8B85jvNus3Nv6Q1vc6zLa63d12kkMJBP1SExBbvuBy68xugjnlnztVo1tMKyuXUMHaV/myG9JXvfL5NTQVFAuo/k53kACqgMu3OLjNRgMLIYupeO2bPXucH27KmQ5pLnlpuleGDk/SK9fot/Bo8CvSMwOocQZPqZrnG+A3TuoCLM99j/47pAopfP6sYPuMaunaK8u0iyyc0xNbc4DVx8GRh5lKQ2coJkc+zj9ITr2EHSv/AyI6qeDzESuvK9qpLLlWgnJlFKvAPI9DKKWZxkOi6co1QUV24/AMxmtRRx3rYj7DfyPab4Qll2yZW0nMWCvhXhh5JiFtLZSgL0pdm10SRSt0TShsFZS6UFLFfK1SLCeluohlsTwhlI9YSzNZHOSmgLCSmlEgBeAJADsADgNIB/DuAPHMd5USn1Mfn6lwD8OwA/7TjOdaXUvwDwo0qpVwH8fQAfBZ/kf1FKfRvABwEEjuM8ppQaAvD/APhYi3NrbCHWY6PTzus0IjSMnARG36qO2baiwJ7jnKjapB7WDKsVUBgdgwj2HOcn53gaFU+13e8nUYWedfX3e98zCO55nOeQtfn3/yjw6h+xXnTjXeCex8XRunupOAKo9AQF+x8myR54FBh9o0rKYV9RopMkd+1Nig7yc0DfHjZw5me5ee84UnUNnzjP44bvIzkMHmHdyy0B3/ht/jvs89n/KKOGZDdTUMeeYRpw9E0gGqao8iSBjkGeozANxJMkscAV81Qw0oulgIUpkSAX+UztBInGKwAweE/JDFNuxUV5rkkGM4UsGAXJuPPsFM8dSYo/ndRffK+m3uNWmz7d4vIoJqzZGBE0nwMXcA3lZqm/VgjTkdLwGkhDKn/KaDcZtSsd5wH4KQBfq3ntoOM4LwKA4zh/CeAepdQ+AGccx7kux/w2gGcB/B0Av+84TkkmvP4nee1ZAL8l57gB4KxSaqTRuW/x/Wk0QSvxwu14nXqBgZnpZyE/dDAoM/Iwk51rj4BWKaAwLBvGyAnuF7kZDqDLzQCXXmVEUFxoeL+GZcNMdlbWxp6gS4yc9p0E9j0MZKcQXHgVfm6OggrLJsEBCAqimPLYa2IkO5feu++TfHwXRryDpNK3nzWeZB+NWhduMvIqZYHe3cDhJ1jkdwuMNHpl7INlUTAxfpYkm+7lBv/X/xF457/ynueuA29+BUh0A/37GSV1Dlb7W7LTVN+l+oBEHwmwY5ARVjwjNkF7gFQnRQypHRLtWhR1RBKiPksC0Q4ZWd7HHiO/IAQg0VNQ5oeHSIzXM00x+pQNPaglGlNIrsZ+pxblMlCZutosyvFFer8ewghNRwO5Rm1d6JYT0IoXaEsk5DhOCUBJKVX7cr3MwwOwA8D1mvdNKKV65fWzNcdeB/BhAD2O40zUvT7Y5Nyrxvj4OJ599tklrz3//PN4/vnn13IajTsU9QKDVpHWqvuT1trQGkYpM1eB7/0JN/BoEujb19SNoeE1Szlp6OzgxjhzDTj710AphyDZxZHlUxd53I3T7CFKdlfTjHX3juJCNVIs5YHBe0h0V79Hshi6l39ffI0RlwESwdQV1pv6DwA3HW7mvjRhmibrRZEE6zem+JAle4HFm2xoLeWZevNdOi4sTlKEYRg0+Axcbtpdw3SFGD9PK6GZS/STA1AxKPVKYLrLZkQVSYmAIcXopDjPplO/diqrz4gLospzi9V6WiW6CHuF5Oum23EBK8cDnpxnPWq1W69wa4EV7bZvJ3Wc1eDrmwCGwheUUv0AputfBzAsr00rpfocx5mse73RuVeNgYEBfPnLX17LWzTucjRSvq2pP2m9LhM33mVdomOg2qPTvWcZedWTYeC5fM2W+TCLUzQsvXqKm3u6m5v1qS8C+x6C0b8fQYeM2d7/KIxodSLpknsPyTE3B5z/G0q0j30ceOWPSAhhp//iOHDTZgRnx4Gh+5hanGc0iSNPMtrxPTZzBh4dFvIiuoh3AphmDebdFzn36PKrkh4zGTmFs4SyEzKCQO51+ionxebmhIDCGo04Zkc7qyIBK0LFX266Sn52AijPojGLiIzbCz3Vwj9uTeorFCC0+uy7GqK4VUKBmkipDbid1HHnlVJPAoBS6gkAjuM4FwEcVUoNyjG/COArAL4O4DNKqYhSygbws/LaVyG1HqXUDgCH5BzLzr2F96WxDdBqdHfTFFt9Wm/PcfYfzY/DLzXI/bvi8hxNiMpNenSACnkFngt/+iqC975R6W3yJy4gOPcScPEVRhCRONc6JRLrnUeZNrt5hhuqwc9oRiwNmDZHRXgugmK24b0EhXng0iscynf9HUZXw0eBzl0AAuDCX5Ncpq9QjDAp4ytgsh506AkW6TP9FDGYJgUOpTwJa/oaJfFjZxl9TF9hGtKwWddxiySjZB+JKDtJyyG/AFz+PpthPZfnDQkCQGX7i8YlioqIn5vI2wcPU8lmxyhUaPah3i1RiBCEogGXxwaQ95Rx6whkMxDWjNqDdqrjXgCwF4CrlPoggN8A8HtKqV8DMA7gs3LoPwbwx6Kmew3An4k67v8G8FdyzO84jnNDKfUlACeVUt8EP3aE4oNm59bQ2Bw0G91dytEXrkFUtMzHbeoy8MaXKl/7x5+D2bevcnwg5ICu3eLLNsu6zMhDFB1kp9k8e+X7TNXtup8F/lNf5Bwfw2CPz+IU+326dwvp2EBQYkRiWpUGyDA6C4pZ4OKrDSO8CvnGM4xG3CJrQb0jwNR3aP2Tn+c+tzgBdO8i2bgFKsLiJ0iG8+Mkxz0fAHYeB2JdwOyV6iC8YgHwpwCjj19n54COPg62m7pAJVphjqR2/W1GTsOHSVhTlygMSA+wIRYAYEmqzAVKJSCZEJ+9Mg1CDYtrPf8y03F+C0GAXwDMVI33HGgcGlrtVBwZ2poWa4H1pvk2B20jIcdxnmvw8k80OO5tUAVX//oXAHyh7rUAwK80OHa20bk1NDYNjUZ3RxNszvTcpnWbMLXllwokoHgaiA8xDfb6C/A/8oswo/Fqqq+U46baswfoTgEjJ2Fm+qtkYJo8RzTJdFuoSgNIQHGZu1POA2PnWItZGKeMefdx4KGfAWauMDqzIpRlX/4uEEs3dgSvId9g8DBw/V0ZhleganBuTCyIYoxQCgusESEgQU44JLDCHAUNhTn2Fbl5dvJHU0D/Pq7VslkLS8jgu2IeiJsUDxSyHIMBn7WkkjhN2zG+L5oAenaypjR/ndc3TSA5gIoTN0zAleZNr0RBhJtv4aoAADLW282ShIyoCC1sINlDCbpfBufrhFJpjVrcTjUhDY07FktMSAsLyyeSruTaUJjn9+NS6oxnGLEU5hFYNiMc06TNTVirOfQkzLBWI2RQGRMe1mLCtF1YOLclvTR4iLY8nkmVWWYAGL4PRt8+psTcIiOgy3/L5tN0L4LBwzDiHUvvpba2Fe9AMHik6jIw+iYjnuFjjHrKBUYYyU7WfbqHeU/hQLZkF59DLEXV29x1EoJtU9HnFpnGsyNsEg0CITzpF1qckmjNYrQFg+8Lp6gGPrD3BDBznT+fjgESox+QOKIxIIiy32fuJgkxkhR7oAb+ckaUEWQI3+P6fDEuzc/S0QEBU31GmKJbDaJo6Iq9KbCxZCGWLQP92gNNQhoam4Qlo7trJ5KuRnQQ7+D3CwsSGSzw63gHgrkbTLHFWaNhrYK1mgqEDNh3c5jNpaU8My3HnwPGz1UbNXfdzw1zx2FaDpkWo4fcTMU9IQCYggvTbAAwdgbB4NEl97Kkl2r2OqO03hHe/wPPAu98jVFLxxCw4ygwe43/HrqX1w3drHv2cJAfxCZo14Mkh6vfZ92no5/HJbp5T31JyrGvvsHnHEuS/AASzfw4BQqmxfd0DfPr/gMksMwwjx0/Qyn47DVe3y0xDVcxEi2LZ5sNwJfZQQZ7iip9QCI8MKQPKJRkGzXNsEG5UmuDwQ8mFDPIOYy4WCQVZJsIcQAAHe5JREFUSGRWHCi6WH2arEFD7LJDEjWTUb3quls6bN96aBLS0NgE1KrRzGQnApntExQWmHYaOtry/WY0Dv/4c8DrL/ATvR0Djj9HZdvYD7ipR5MADHEvOLKE1JZEYl6Z3x86CqNjkOfo3s1RDzdOS5OmSZuf0POunijr02xjZ7iu4iKMAx9c2o+U7Eaw/1Hgvb+isk7GkWNxEnj4Zzn2YeI8o54jT9HpO9nNa81/gK4LY+/SlNW0SFrxDDB0iFGQ5zLqMS2q4ubGgP2P8OI9LwGXX+P3Snmm3Swb+JFfBS6/ztRbLMnRElaEqrnHf4lElJsDvvV/AQvf4euJLtat7DhJyy1TZOGXQNfsKBDrlLEHkoYD+HOJxEUlZ8tsIpukWVHGGQBMkostx1oWa0Z+QFGDa4oHXwfJaC11GisC2GmOrzBsLHUGjzB6TA+w6RhlVF0U2g9NQhoaG0RTafbBxxjFjP0AuP4OgpvvtZRtm3374H/kF5mSindwEmpt9DJ2hhtyKU+Cqa8vtehfMiwbRvcuBB2DjXt86u2N6tNsQ0clBfjRJXLtyvkDD4FpU1GHat+TkegAjj/H+wB47etv81mV8ry3sdMUDBgWI438LMnGKwOHRbodTcjG7lJ0YIkDQSRKZ/DOIUaKxTwwMwq8+zVKz6cuUunWK2nGIICR7oERS8HPTdNRO9kF5AIKPQIZqW3F6WM3dhoYv8geoUQ3r19apNGqV5bprgEdwQMDiFoy9sIngQYB2EuUYf0t3kVitKQfKrB4nmhGoqMSG3v9kLia5e9CbzqRhodD9gxL3CZk1pJhy0A/nxGfGQCBvTSN2Oz8prWKWUK2rKVpOm9FptMkpKGxAbQa5Q2A6aZYqhJtrNRYakbjlAyHCNNsVpTCgcIiEHgwOgYbvn8l5+5GPT5Nm2t3HGLDakhSBx5tSEC162zU92RYNoxkJ2XeVzj6ArE0hRLlHDB/g1HT5EUSQinLKMiKcyOcuQLsfYhpsatvMuVXXGRNZ/oK0L2T35u7WXXxjqR4X337uI8P3y9O2x4Cw2Jf09gZoPcAh+SZNgUUvXtp2GqYTGv27QemrgLTF/n9nExztSJAVpzCPQ8wF6vTX+0YkJ8GQhPUwGdkZ0erc5BCd/OykI7dITW2KGcX5RbCnxiWEpEM2DNAIYQp477dghCXTI61E7x/M8LzW0nAna85x0rwASu1ChKqSSk2xoo9mZqENLY9NjSFtZXzAbDhsRLL0mxWBMbeE5tme7Ri061hAsPHKmm91ayzqXFsbYqvlJdP7DKu2y9Xp6Jmp4Az3wTu+YhY5Uhv1PmXOaRv6gKH6FkxYOgYffDS/Yx8wv3VMIAbbwOpAZJWfpaRUmYHo6QAVP1ZEQoh5m9QTDF8jERWypLo+sXV5d4nuaFfeA0Yf4+bvhkBUODzM2V+Un6OqTDTqE51TfYxCuoYJiktjDGijcUpD48m+L3FSXFnCKTvSN5fK96AyfUVFkluZoTRTjg7KSqpPrfA1y2Jity5mp/WatQRAVCexyZ4y92etj0aGrcLNjyFdSXng/W4ItQg8FxGQfsfpRBhK8ai10V2uPkePdgaHVtD3ivZGQUeR0pUnkMgY7mTXcD4BW64EZNebKUsm1QHjwI7DnIe0uQFziyKJCiWWBznhNnFaWDiIpVuiW5g4BDw1n9hhJAaoxIus4OKuSvfJTn0H2AfV3GhSjxuUUaUz5G83v9JksfuPDDxnhCMC+w9CfzgL5j6g1GNVpPdJLTZG0C8B8ACCSE/y7WYNmtNMRmb7hZJNMlu1ttKMh7djosoQojFkFQbxHg0L4YwAcTRO/yeyXOEMCw+xw2RyIZdFO4o2x4NjS1Fq1Taajf6FSOADYyVaEiQoWP2rcIqPe2akXcYWYUOC7BjdFQIjy0XSAqRONNe09c4XC83BcCg4q0oPnRj71Jp1zFAdd/keZJH17AQGHhcYZ7HZfqZnjv3DabNOgZpv+OW6RaRfpppsIULrPUUFxjtjL4F2CmqA31Jnfke8O3fYzIpAMcopAdY37txhkQVSA0mCEgexSx7kdwy/fPKZUY7RoRkNHuD13TLlIP37qMqDyYjIENGoQdlmflkACiJu3cTBL40yYbmqjVY88yh9kCTkMb2xSZNYW0pCFjnWInNIMh1YRWediutbVk6r5QDMv3VyCqcDGtYwLf/PcUH01fZCzV5nk4OfXtJCOe+CajHgMMf5fELN9jTFKrdZq6QfCIxpsBiaVGYpbnx2z2AIQ7YC5OMDObHubbQx66QA/KjvMfZUbpuT5yi+3ffPq6/ezebevNzVKABUhuSGo1tkRDmx4HCLK8fLIiLzyLXBOk38lwAURIVLH4/7N8qzjO1ZoH35EVkTHgLd+1Wbg53ADQJaWxfrNdEtAFaCQIafW/FOtQtHIdee20AFeVaZRREg+itclyl8bXx2gJgKUFlZxk9dA0tOdawbJ7PK1MJ1zlMhdvrf8Laih1no+mN06xvlItUq116DejdT6FBYY5EsXCTNzYxyg3cd1kTKixQPp3qZg9RUeyDIjEap+Zn2TdjGNJrlGJN6sa7jKAicX6/uABcOcUUYGGekU0szWMDj++34xz9kN7Ba8yNil+dLePALSrqTAPIzQNGnuo50+YQwMKC1I7ikuazxAC2VOPEvZmS6hajx7cYmoQ0ti22atprPVZVh9pEgmx67VKe6ajZawAM9gPd89hyT7vCPHt9wvXuvL/52uo99OJpAEIIye6lxxrW0gbdRAcFB53iL+eL8mzmKr8PULF26En+++IrTM2Fg/JKEnEMHWHNJTdD8tr7CDCwn0P3Sh6QLgBzE7y+ZUktKs6/F8dlQqrH6bBTF5lu80qUNS+Iu7YVkdcAxKMURtgx4H0/DrzxRTa+emURMNhU6yXSnHkUjgz3Pd5jRJpI87NMxSU6GLEFonaLxqtraoq1CghuDwICNAlpbHNs1bTXEKtNs62VIBuNbqi/J79UAC68wk/xsTRHb086wK73UYE1fRnBhVcQ7H+UUVEs1VioMPoWiWj0La4t8IE+xaF4deQJ32WfTjGHoFzkeeQ+DMte3qD7I7/GFNzkJUYCQ4eZfjNNpucMq1IXC0Lp+oEPcTTE7DVg3GHEE+ugd125AOSngKsyEuLa9xnlFBcB+JRdF7MADNaQzAhQOEvimR9jbcm0GMF0DAPZGZJCaBVkSI9O2Eh8/V1JuflUvcFgvSmaZC2oVCBfROI8p1sSEkzyfIENwGRtDOC9WDHKtv1WRHN7jOpeDzQJaWx7rNRbs6lYQ5ptJYIMiSYoZqsNoFakOpiuJtIKggC48HLFBw49e0kegS/ppBhQnqRVT34eQaoHGDkh9jXL12tEk2zGvfEDWvNceZ1R0/HnOJKidtCdKY2PALDz/iVRX6MGXX/kIUYMnkuZdaaPG7gdARYmEWSnYaR6Ktep3Of9f1eivBIVfZ7LmlF2lpY9XTt5nwsTImEWh4KunSQc06qm4bwisChNp77BaGXqCiOe3j1U6vkeI6lYminB7DSNVL181TwVedamspNUAfplnsv3WIsq53gNRPhAbLHfiSVoHxSAEVxFon33QZOQhsZWYo1ptmYEWUmrlQusm+w8BiMzgKC4WBndUIm0Ln2Xb6r1gZu8iMon+SBgfePmWarAFnqAhZsISjng6I80XW/gucDpr9OQNPS7e/0FBB/5RRihh96l15Y062L0LQR1UV/YoBsq6gw7BqN7mF9PngM8F0Y0QfeJq28CvocglmJEVUfSwcgJBOf/htFNdooKtJlRIDdJ0UFukim8/Jy4T+ToY9e3D9j5IPDmnwElg/cYzzBFBp9pvSDH55ObpfOBFSHBeS4jGcMkgRUkDbg4ISk3j8/aLbIe5RbF2qf2Z14GYIrDj833X3sDgAGUF7A6bLinpy24nYbaaWjc9Wg2zG4tacDaFBkSnUxVTV1C4LtVE02JPIxInBttKUdLncHDPEluhiqwfY+wSXJ2VBwGFHtt4hkKCtzi0vUWs3RSAGqcv6VeE89Uem3CdBsCn2sI1+KVORyvbkCen51GcO6lyiC+IDfDb+w4BBSzCG6eA978KgBfiv4lRkGoEVRAosdDT5JYOodpDAufKS3fpUNBJE5Jd+8Ip9L2KuCejwI33pEIRgbuFRYAeCSOSIS1HcPm+5NdPH9HP4+PxIBUlzhxB6zteGVpwjX4MypmZbaSqORMA7CTWGIqEIij9+KEuC2shVRWe6y59JobRstzrVh80pGQhsYWY8N1qFrnAc9lvaGUZ8pKGlrDGThBuSD1CjTwgXuyqlKbugx8438nGWWnGC1In2HFB2/+ButIoQ/e4NGmzt8AGkd9pTxw6TUEgV9JFSKWWV4ne+9bVKuFKUO3yKbVziHWUaYuLRlrXklNGhZ97AaPAKdfRCXa699PM9L5cT6bRAfVaOUsoB5h2i4S47OauUYSj8aBYkmk5lHaAyHgvCN4lGwbIrGOJfkMe0Y4RwhCOr7J9VtRwJVheW5J3CEWeZ6QPKwoKNku8zXPrfZDrQqm/Mx8cBREkz4hO1EToYHvMYRISzlUbXhWG1mFRq1+o+M1CWlo3I7YUB2qfnPv2wdce5sppkicoxsmL1QG0xkjJwBgqcih1gculkKwMMZNPjstKb4zwOEnljbH3lzqg4ex0xzX8OaXlzh/hzOOlokrDJP1p3ovvT0fWKqos2yOGt/7EIx0L2Xes9cY9YXS8twsgACwY9XU5OIUxRU9u9l3dPgJ1npcGdn96D9kD8/bX6Xqzo6RbBduknzS/UB8lE2ptvi6GaFPW4Su23seBPY+SMl2qC4MvfC6opx4a9kAbJ6nOEeXbCsmUm2ThF3K0zk7qB3BELAmZFnV+yzlV/hlqJVaB1LD84GIDZS9mnOHbt42j+nqk8hsmtFdUuZQ2RGuPzfLn5Xvc97UwhQjyYrxqQEYMfmcEsixUiMzY0KePlDOjq7467zSARoaGrcXGinn8MinKRYIayPdu5dHWs2iL7fITWP/I1R3lYss3I+crB5XG335YhVTLsDoGkZQJyxYstaaqC/wXODiK0vSc0FB6h21irrCAgBD5N3g3+G47bkbNWPNT/L7V0/JxjnFY+fHuDnmZiiu8AMgPwejaxBG7AD8oXu53kgScF4i4YWD/ewY0DUoRJSg43U5J/5sPucchQRmRxn19O+TsQ2gaKGYpUoPHi2Iyjmey5aG2nKe6/VdRnu+x/SeYVIW7uZIbgvSVAuD1w+DDEvSX54LpLuB/KKk9yJANE2nhGgasF2q60yDJBEEPE9CzF0z/fzg4XnVWlX8EMUVi+PsfbIsulTcOAPMT1ZnNMVSJK7cDF3NE11MkyY6SOaxNMUbU+dzK/0+axLS0LgDsVJKr1Gk1TT6qnXqHjlBEvD9pU7dYfQ1e52uBl4JCAwEIw/BzPQvdf6uX2t4Xc9F0EDkYMRSyyOmwcPiHCCb9eBhkkb3Hp5UrltpeLWl5pPsBhZLvJdSngRkGIxWRPxR61TujzxEYcf8OI/Z97BELFFGep2DlKN7LjBxjrOQZq9Qfj18jNNj58dIRnERaAx0S2Qgzap2ojoyfG6MG7xLR2/EOykND3w2u2YGgZ5dVDGaNgnGMllTys3zHqIJRkzlIiXmEZkjFE2KyCRsRA4AMw24Hmtangf07pbG3Ayf7cHHOOqhaxeJe/Be4Lt/zPNkx0nG05cB9WGZODvKKDPwSHrdu4BdD3ANUw7X1DnEqLz/ADB1/m9X+l3WJKShcYdis6TlS0eTlyspvPq+paBrN/BX/0ZGESQB9aGGajegsSNEy96nOlJdNuvonse4cdaTbkiggcdNu7DACKV7D8lFUpTNxB9mph/+I5+mig9GdYy3WwJ69gHpHiGwgFEQxCfOtOiw3TcCnP4riRpsRmfZSfZG+S6w8xgbXDt3UW5uRYAdimQ0c00cGebpDrHzAeADP8nerfGLVdVhvIPEkZskKaX7KILIDJHYZkd5np3HmPZzXmI0AgCjbwOmL5FRhE7jPSMktWQ3I7iuYSDZSQFKLINAfYjfjyZI5KUCSTISB66dYmOwFeU6rp7iv7uHgGQHI9WOnZxbNHwMOPMXK+UTNQlpaNztWM2oilX1JE2cBQYUGyl9j6q6SHLV5qYrXWdVs44aRXchgab6KFjo28cNsy5F2ezZGNEkgkNPVlzKAbEoMi1g5jKjKdOgXdChJ0nAAJ0cvDJw8IeAB36MKbVrbzANlezhJp4XwjryUW7sN97l6107gb4DjC6OfZxEYNm0Ijr8I0x/7VDsd3KLrNWpx/n+PcdpReT7vH73HkaPhVmgvEhF4c4HGLF1DlP1F+9i7atzkBHXPR9lqk09BsM0lj4jmQqMvHwAUI/ymVx5nQQ2fp7RW7oXOPFJ1goBRkBHPgrAYP2MqsnvNP6trEKTkIbGXYy1jKpoGVm5RbBOkxFxQZLu18CazE1XvM5q11N7XG3dSdRxq1EdtnIpN5KdCA4/wR6rUg6IJmGMnICRSCM48CjvqXsPgAAYOcmIKiuWPv376GnXuZM1qvD7Rz8GjJ9h5GLHOF4i8IDBeyprDRYmgMWbjDzycxRjIKASceQE8OHPkOQArnlIFIpXTzEKNESoEI7DGHuPKTPDon9fdoYfJOLSZ5VIt3yejWqKgfoh4Crl8YjEGf1dewPoGoJhyn14bliz+/OVfn6ahDQ07lJsqhO3Hav210xdqhEHPNR0cB2wucarrRAS1mpmhgKrJMtkN3DoieVpxQabdOV8sRSM9FEE3XsoLjj00YpYw8z00x3iwisy0luiSKl9BWVxcZg8L64Wu8RZQaKbIz/Mke8DB5etKahZZ5jK5EDCe0lUqT5K11dJ0q1qikYshSDz1FIT3MnzFcPW2lqf8TtBdqWfhSYhDY27FZtICEvSXnURwBLcIuPVTccqn02zaGzZ6/Xni6cRlPPc8GtgZvoRHHu6ae0LQ0eB6+8Au+7n+HHPJRHtOb5U+t5KdNIq5bn+J9bwepVUb62X4BqNgDUJaWisExsaC74J718Rm0wIq2mybZcz+Zqx2WS5hvO1IgwAbAS2osDu4zLG21uqVFwF1ipaWc/v4rJ05s77V6zBNcJt9puhoXFnYKNjwTc8VnwVuBWEsJrNbaudydeDzX42GznfsmdaZ8xq7D1xS5/hen4Xm7qrryPVe/v9dmho3ObYaK1lK6emtosQttSZfJ3Y7GezWefbyp/Zun8XNzHVqw1MNTTWivA/YJ0xJxVkW/D+NcKQYvLtGJG0G5v9bDbrfFv2M1vv72JN+hHAhtKZmoQ0NNaKjf4H3MT/wBqbi3CcRK3D912Ndf4uboYbfGUJ61q4hsY2xkbrCXdM8X6bYSvqdLcbNlTL2qS0of6t19BYBzb6H/BOKN5vJ2xlne52w0Z+Fzej9nd3P10NjVuIjf4HvBOK99sGbWqyvV3Qzt9FXRNaBcbHx9u9hNsGX/jCF9q9hNsG+llUccc/i02s093xz2IToZT6uZWO0SS0CmgSqkL/B6tCP4sq7vRnsZmF9jv9WWwyViShuz/OFCilfgnA35Mvf91xnG+3cz0aGhq3F3Sdrj3YFpGQUupBACcAPAbgGQD/XCml9bAaGhpLoHuqth7b5Uk/C+C3HccJAMwrpb4G4BEA31rFe1Vvby9effXVW7m+OwbPPPOMfhYC/Syq0M+iCv0sqvjkJz+5e6VjtgsJ7QBwvebr6wBW6wg44bpu96lTp/zaFzOZzPWenp4bm7XAOwXxeHxoenp62913I+hnUYV+FlXoZ1FFf3//il2/24WEbgIYAjAqXw8D+N5q3vj0008/eKsWpaGhobHdsS1qQgC+CuAfA4BSKg3gaQCvtHVFGhoaGhowgiBo9xq2BEqpfwLWhgIAn3Mc51vtXZGGhoaGxrYhIQ0NDQ2N2w/bJR2noaGhoXEbQpOQhoaGhkbboElIQ0NDQ6Nt0CSkoaGhodE2aBLS0NDQ0GgbNAlpaGhoaLQN28UxYV3QzttLoZQyAXwKwGuO45xu93raBaXU50HvQRvAbzmO86U2L6ltUEr9JoAn5MtfdxznpXau53aAUupPAfyJ4zgvtHst7YJS6s8BpOXL33Uc50+aHatJqAnqnLczAL6qlHrKcZxie1fWHiilEgBeAJADsABgW5KQUurjAGzHcT6ilIoC+KZS6quO46zokXW3QSmVAjDqOM6HlVIZAF8AsK1JSCn1GIBd7V7HbYA5x3GeWc2BmoSaYyPO23cjPAA/BT6X7Yz/BuBFAHAcp6SUmmnzetoGx3GyAH5PvjwCYLGNy2k7JFPw9wH8QbvXchvgYaXUNwFkAfxTx3Hea3agJqHm2Ijz9l0Hx3FKAEpKqXYvpa1wHMcH4CulOgH8KzDVsO2ioFoopX4ewK8C+JV2r6XN+AyAPwSwp83ruB3whOM4l5VS+8APKh9rdqAWJjRH6LwdYlhe09jmUEp9GMB/APBvHMf5WrvX0244jvO7APYD+Eml1EC719MOKKW6ALzfcZxvtHsttwMcx7ksf18EMNtqiKgmoebQztsay6CUGgQ/8f604zjn2r2edkIp9VNKqQ/Jlz4Aq53raTN+DsCDSqlvgVHhbyqljrZ3Se2BUuqfKqXukX/3AxhsVUvXBqYtoJ23l0Ip9QKAvQBcAK84jvPLbV7SlkMp9QyA30I1VXvTcZxPtHFJbYNSqhfA74KpawvAf3Yc5z+2d1Xth1Lq0wAWt6s6Tim1H8C/B5AASz6/4jjOy82O1ySkoaGhodE26HSchoaGhkbboElIQ0NDQ6Nt0CSkoaGhodE2aBLS0NDQ0GgbNAlpaGhoaLQNmoQ0NDQ0NNoGTUIaGhoaGm2DJiENDQ0NjbZBk5CGhoaGRtugSUhDQ0NDo23QJKShoaGh0TZoEtLQuEuglPqcUur5Lbzet8RVfDXHjiilvt7ke2c2d2UadxI0CWloaGhotA2ahDQ0NDQ02gZNQhoaGhoabYPd7gVoaLQDSqkRAC8CuArgfwPwL8EPZWcB/JzjODml1LMAfgMcavg3AP6J4zi+UmoUwKsAjgD4QwB/B0AfgE84jnNaKfXPADwPYArAs47jzDVZw0U5rwIwB+BnHce5rpR6GBycZwF4Ta7rKaXGAHwPwC84jnOlya09p5T6BQAZAD/pOM4ZpdSjAP5tg/s74zjOYVnL1wH8QwCTAL4GDiT7uuM4/6vUfX4fwACAMXl/OOr+XyilDgEoAHjGcZyCUuqzcq4AwJ86jvP5uvs+Ao5HtwG8CcBoci8a2wA6EtLYzvAAPAVuiM87jvMQgLcA/M9KqS4AnwfwpOM4HwA3zE/J+zoBfBbAz4NjnZ8CN/n/Qb7/4wA+AeDHmhGQYDeAf+U4zsMA/hNIhJB//4zjOCcBZAH8rLwelXU2IyAAGHcc54dAEvusvPYH9ffX4v375O8PyzkA4F8D+H9lPb8j9xriRcdxPgTgMoCnlFKHZb0fBHACwCNKqcfrrvH7AP4nx3EeBfDnAGIt1qNxl0OTkMZ2xhUAPQAmHce5JK99EcBxAAcBfM9xnBl5/UvyOgBccxxnEtx4HcdxSgAuAUjL9z8Dbtb/QSmVbHH9Ucdx3pJ//xmAB5RSfSA5/bFS6lWQ4O6VY8Ydx1lc4Z6+I3+fA9CtlOpvcn/1MMGbeRvAnwL4PoC/J997H4BflvX8JoADza4H4D4Af+k4Tt5xHA/AVxpcr99xnO/Kv18E4K9wTxp3MTQJaWxrOI4zAaBHKbVLXvq7AF4HN9UHlVIdda+3hFLKAtDlOM7jYBTzwy0OH1ZKHZN/fxzAm0Ju7wJ4WiKkTwH43BpuacmG3uL+ACCplIoopTIAjsn6DwH4KoCHQMIBgFMA/pGs58cA/HSz6wF4G8DjSqmoUsoE8DSWP7cJpdQJ+ffHoPehbQ1dE9LQAP4BgC8IgZxHtWbyvwD4S6UUwNrMH63iXHEAv6CU+m2QhH69xbFjAP6Z1KeyAD4tr/8ygK/IJn4TTPu1SuuthGX3J6//OzDiuQJgXF7rBvACgBIYnQHArwD4faVUL4AigF+V8yyD1KD+EKx1AcCXHMf5ptxjiM/K+QIAbwDIbeDeNO5wGEEQtHsNGhrbErXCAA2N7QodCWlo3GJILaUen9jA+f4BGN3U4i8dx/mN9Z5TQ6Nd0JGQhoaGhkbboAuCGhoaGhptgyYhDQ0NDY22QZOQhoaGhkbboElIQ0NDQ6Nt0CSkoaGhodE2/P/1NAGpRAG48AAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# We created two features (rooms_per_household and bedrooms_per_room) we mild correlation\n",
    "housing_df.plot(kind=\"scatter\", x=\"rooms_per_household\", y=\"median_house_value\",\n",
    "             alpha=0.2)\n",
    "plt.axis([0, 5, 0, 520000])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 210,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>median_house_value</th>\n",
       "      <th>rooms_per_household</th>\n",
       "      <th>bedrooms_per_room</th>\n",
       "      <th>population_per_household</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16354.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "      <td>16354.000000</td>\n",
       "      <td>16512.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>-119.575834</td>\n",
       "      <td>35.639577</td>\n",
       "      <td>28.653101</td>\n",
       "      <td>2622.728319</td>\n",
       "      <td>534.973890</td>\n",
       "      <td>1419.790819</td>\n",
       "      <td>497.060380</td>\n",
       "      <td>3.875589</td>\n",
       "      <td>206990.920724</td>\n",
       "      <td>5.440341</td>\n",
       "      <td>0.212878</td>\n",
       "      <td>3.096437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.001860</td>\n",
       "      <td>2.138058</td>\n",
       "      <td>12.574726</td>\n",
       "      <td>2138.458419</td>\n",
       "      <td>412.699041</td>\n",
       "      <td>1115.686241</td>\n",
       "      <td>375.720845</td>\n",
       "      <td>1.904950</td>\n",
       "      <td>115703.014830</td>\n",
       "      <td>2.611712</td>\n",
       "      <td>0.057379</td>\n",
       "      <td>11.584826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>-124.350000</td>\n",
       "      <td>32.540000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.499900</td>\n",
       "      <td>14999.000000</td>\n",
       "      <td>1.130435</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.692308</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>-121.800000</td>\n",
       "      <td>33.940000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>1443.000000</td>\n",
       "      <td>295.000000</td>\n",
       "      <td>784.000000</td>\n",
       "      <td>279.000000</td>\n",
       "      <td>2.566775</td>\n",
       "      <td>119800.000000</td>\n",
       "      <td>4.442040</td>\n",
       "      <td>0.175304</td>\n",
       "      <td>2.431287</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>-118.510000</td>\n",
       "      <td>34.260000</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>2119.500000</td>\n",
       "      <td>433.000000</td>\n",
       "      <td>1164.000000</td>\n",
       "      <td>408.000000</td>\n",
       "      <td>3.540900</td>\n",
       "      <td>179500.000000</td>\n",
       "      <td>5.232284</td>\n",
       "      <td>0.203031</td>\n",
       "      <td>2.817653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>-118.010000</td>\n",
       "      <td>37.720000</td>\n",
       "      <td>37.000000</td>\n",
       "      <td>3141.000000</td>\n",
       "      <td>644.000000</td>\n",
       "      <td>1719.250000</td>\n",
       "      <td>602.000000</td>\n",
       "      <td>4.744475</td>\n",
       "      <td>263900.000000</td>\n",
       "      <td>6.056361</td>\n",
       "      <td>0.239831</td>\n",
       "      <td>3.281420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>-114.310000</td>\n",
       "      <td>41.950000</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>39320.000000</td>\n",
       "      <td>6210.000000</td>\n",
       "      <td>35682.000000</td>\n",
       "      <td>5358.000000</td>\n",
       "      <td>15.000100</td>\n",
       "      <td>500001.000000</td>\n",
       "      <td>141.909091</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1243.333333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          longitude      latitude  housing_median_age   total_rooms  \\\n",
       "count  16512.000000  16512.000000        16512.000000  16512.000000   \n",
       "mean    -119.575834     35.639577           28.653101   2622.728319   \n",
       "std        2.001860      2.138058           12.574726   2138.458419   \n",
       "min     -124.350000     32.540000            1.000000      6.000000   \n",
       "25%     -121.800000     33.940000           18.000000   1443.000000   \n",
       "50%     -118.510000     34.260000           29.000000   2119.500000   \n",
       "75%     -118.010000     37.720000           37.000000   3141.000000   \n",
       "max     -114.310000     41.950000           52.000000  39320.000000   \n",
       "\n",
       "       total_bedrooms    population    households  median_income  \\\n",
       "count    16354.000000  16512.000000  16512.000000   16512.000000   \n",
       "mean       534.973890   1419.790819    497.060380       3.875589   \n",
       "std        412.699041   1115.686241    375.720845       1.904950   \n",
       "min          2.000000      3.000000      2.000000       0.499900   \n",
       "25%        295.000000    784.000000    279.000000       2.566775   \n",
       "50%        433.000000   1164.000000    408.000000       3.540900   \n",
       "75%        644.000000   1719.250000    602.000000       4.744475   \n",
       "max       6210.000000  35682.000000   5358.000000      15.000100   \n",
       "\n",
       "       median_house_value  rooms_per_household  bedrooms_per_room  \\\n",
       "count        16512.000000         16512.000000       16354.000000   \n",
       "mean        206990.920724             5.440341           0.212878   \n",
       "std         115703.014830             2.611712           0.057379   \n",
       "min          14999.000000             1.130435           0.100000   \n",
       "25%         119800.000000             4.442040           0.175304   \n",
       "50%         179500.000000             5.232284           0.203031   \n",
       "75%         263900.000000             6.056361           0.239831   \n",
       "max         500001.000000           141.909091           1.000000   \n",
       "\n",
       "       population_per_household  \n",
       "count              16512.000000  \n",
       "mean                   3.096437  \n",
       "std                   11.584826  \n",
       "min                    0.692308  \n",
       "25%                    2.431287  \n",
       "50%                    2.817653  \n",
       "75%                    3.281420  \n",
       "max                 1243.333333  "
      ]
     },
     "execution_count": 210,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# a bit of a sanity check, look at the new columns\n",
    "housing_df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**We can always return to this step**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Prepare data for Machine Learning algorithms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 211,
   "metadata": {},
   "outputs": [],
   "source": [
    "# drop labels for training set\n",
    "# here the drop method also creates a copy \n",
    "housing = strat_train_set.drop(\"median_house_value\", axis=1) \n",
    "housing_labels = strat_train_set[\"median_house_value\"].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 212,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 9)"
      ]
     },
     "execution_count": 212,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Explore missing data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 213,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4629</th>\n",
       "      <td>-118.30</td>\n",
       "      <td>34.07</td>\n",
       "      <td>18.0</td>\n",
       "      <td>3759.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3296.0</td>\n",
       "      <td>1462.0</td>\n",
       "      <td>2.2708</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6068</th>\n",
       "      <td>-117.86</td>\n",
       "      <td>34.01</td>\n",
       "      <td>16.0</td>\n",
       "      <td>4632.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3038.0</td>\n",
       "      <td>727.0</td>\n",
       "      <td>5.1762</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17923</th>\n",
       "      <td>-121.97</td>\n",
       "      <td>37.35</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1955.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>999.0</td>\n",
       "      <td>386.0</td>\n",
       "      <td>4.6328</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13656</th>\n",
       "      <td>-117.30</td>\n",
       "      <td>34.05</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2155.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1039.0</td>\n",
       "      <td>391.0</td>\n",
       "      <td>1.6675</td>\n",
       "      <td>INLAND</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19252</th>\n",
       "      <td>-122.79</td>\n",
       "      <td>38.48</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6837.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3468.0</td>\n",
       "      <td>1405.0</td>\n",
       "      <td>3.1662</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "4629     -118.30     34.07                18.0       3759.0             NaN   \n",
       "6068     -117.86     34.01                16.0       4632.0             NaN   \n",
       "17923    -121.97     37.35                30.0       1955.0             NaN   \n",
       "13656    -117.30     34.05                 6.0       2155.0             NaN   \n",
       "19252    -122.79     38.48                 7.0       6837.0             NaN   \n",
       "\n",
       "       population  households  median_income ocean_proximity  \n",
       "4629       3296.0      1462.0         2.2708       <1H OCEAN  \n",
       "6068       3038.0       727.0         5.1762       <1H OCEAN  \n",
       "17923       999.0       386.0         4.6328       <1H OCEAN  \n",
       "13656      1039.0       391.0         1.6675          INLAND  \n",
       "19252      3468.0      1405.0         3.1662       <1H OCEAN  "
      ]
     },
     "execution_count": 213,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_incomplete_rows = housing[housing.isnull().any(axis=1)].head()\n",
    "sample_incomplete_rows"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Three options to handle missing data "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### drop rows "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [longitude, latitude, housing_median_age, total_rooms, total_bedrooms, population, households, median_income, ocean_proximity]\n",
       "Index: []"
      ]
     },
     "execution_count": 214,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " # option 1\n",
    "sample_incomplete_rows.dropna(subset=[\"total_bedrooms\"])   "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### drop attributes (columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4629</th>\n",
       "      <td>-118.30</td>\n",
       "      <td>34.07</td>\n",
       "      <td>18.0</td>\n",
       "      <td>3759.0</td>\n",
       "      <td>3296.0</td>\n",
       "      <td>1462.0</td>\n",
       "      <td>2.2708</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6068</th>\n",
       "      <td>-117.86</td>\n",
       "      <td>34.01</td>\n",
       "      <td>16.0</td>\n",
       "      <td>4632.0</td>\n",
       "      <td>3038.0</td>\n",
       "      <td>727.0</td>\n",
       "      <td>5.1762</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17923</th>\n",
       "      <td>-121.97</td>\n",
       "      <td>37.35</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1955.0</td>\n",
       "      <td>999.0</td>\n",
       "      <td>386.0</td>\n",
       "      <td>4.6328</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13656</th>\n",
       "      <td>-117.30</td>\n",
       "      <td>34.05</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2155.0</td>\n",
       "      <td>1039.0</td>\n",
       "      <td>391.0</td>\n",
       "      <td>1.6675</td>\n",
       "      <td>INLAND</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19252</th>\n",
       "      <td>-122.79</td>\n",
       "      <td>38.48</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6837.0</td>\n",
       "      <td>3468.0</td>\n",
       "      <td>1405.0</td>\n",
       "      <td>3.1662</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  population  \\\n",
       "4629     -118.30     34.07                18.0       3759.0      3296.0   \n",
       "6068     -117.86     34.01                16.0       4632.0      3038.0   \n",
       "17923    -121.97     37.35                30.0       1955.0       999.0   \n",
       "13656    -117.30     34.05                 6.0       2155.0      1039.0   \n",
       "19252    -122.79     38.48                 7.0       6837.0      3468.0   \n",
       "\n",
       "       households  median_income ocean_proximity  \n",
       "4629       1462.0         2.2708       <1H OCEAN  \n",
       "6068        727.0         5.1762       <1H OCEAN  \n",
       "17923       386.0         4.6328       <1H OCEAN  \n",
       "13656       391.0         1.6675          INLAND  \n",
       "19252      1405.0         3.1662       <1H OCEAN  "
      ]
     },
     "execution_count": 215,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_incomplete_rows.drop(\"total_bedrooms\", axis=1)       # option 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### impute data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4629</th>\n",
       "      <td>-118.30</td>\n",
       "      <td>34.07</td>\n",
       "      <td>18.0</td>\n",
       "      <td>3759.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>3296.0</td>\n",
       "      <td>1462.0</td>\n",
       "      <td>2.2708</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6068</th>\n",
       "      <td>-117.86</td>\n",
       "      <td>34.01</td>\n",
       "      <td>16.0</td>\n",
       "      <td>4632.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>3038.0</td>\n",
       "      <td>727.0</td>\n",
       "      <td>5.1762</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17923</th>\n",
       "      <td>-121.97</td>\n",
       "      <td>37.35</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1955.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>999.0</td>\n",
       "      <td>386.0</td>\n",
       "      <td>4.6328</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13656</th>\n",
       "      <td>-117.30</td>\n",
       "      <td>34.05</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2155.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>1039.0</td>\n",
       "      <td>391.0</td>\n",
       "      <td>1.6675</td>\n",
       "      <td>INLAND</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19252</th>\n",
       "      <td>-122.79</td>\n",
       "      <td>38.48</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6837.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>3468.0</td>\n",
       "      <td>1405.0</td>\n",
       "      <td>3.1662</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "4629     -118.30     34.07                18.0       3759.0           433.0   \n",
       "6068     -117.86     34.01                16.0       4632.0           433.0   \n",
       "17923    -121.97     37.35                30.0       1955.0           433.0   \n",
       "13656    -117.30     34.05                 6.0       2155.0           433.0   \n",
       "19252    -122.79     38.48                 7.0       6837.0           433.0   \n",
       "\n",
       "       population  households  median_income ocean_proximity  \n",
       "4629       3296.0      1462.0         2.2708       <1H OCEAN  \n",
       "6068       3038.0       727.0         5.1762       <1H OCEAN  \n",
       "17923       999.0       386.0         4.6328       <1H OCEAN  \n",
       "13656      1039.0       391.0         1.6675          INLAND  \n",
       "19252      3468.0      1405.0         3.1662       <1H OCEAN  "
      ]
     },
     "execution_count": 216,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "median = housing[\"total_bedrooms\"].median()\n",
    "sample_incomplete_rows[\"total_bedrooms\"].fillna(median, inplace=True) # option 3\n",
    "sample_incomplete_rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use the sklearn imputer class, select median as method \n",
    "from sklearn.impute import SimpleImputer\n",
    "imputer = SimpleImputer(strategy=\"median\")    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 218,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SimpleImputer(copy=True, fill_value=None, missing_values=nan,\n",
       "       strategy='median', verbose=0)"
      ]
     },
     "execution_count": 218,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# remove text data, cannot impute \n",
    "# create copy \n",
    "housing_num = housing.drop('ocean_proximity', axis=1)\n",
    "\n",
    "# run imputer on numerical data \n",
    "imputer.fit(housing_num)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 219,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-118.51  ,   34.26  ,   29.    , 2119.5   ,  433.    , 1164.    ,\n",
       "        408.    ,    3.5409])"
      ]
     },
     "execution_count": 219,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# peak into estimators\n",
    "imputer.statistics_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 220,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-118.51  ,   34.26  ,   29.    , 2119.5   ,  433.    , 1164.    ,\n",
       "        408.    ,    3.5409])"
      ]
     },
     "execution_count": 220,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# sanity check values \n",
    "housing_num.median().values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Tranfsform training set "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = imputer.transform(housing_num)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 222,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17606</th>\n",
       "      <td>-121.89</td>\n",
       "      <td>37.29</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1568.0</td>\n",
       "      <td>351.0</td>\n",
       "      <td>710.0</td>\n",
       "      <td>339.0</td>\n",
       "      <td>2.7042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18632</th>\n",
       "      <td>-121.93</td>\n",
       "      <td>37.05</td>\n",
       "      <td>14.0</td>\n",
       "      <td>679.0</td>\n",
       "      <td>108.0</td>\n",
       "      <td>306.0</td>\n",
       "      <td>113.0</td>\n",
       "      <td>6.4214</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14650</th>\n",
       "      <td>-117.20</td>\n",
       "      <td>32.77</td>\n",
       "      <td>31.0</td>\n",
       "      <td>1952.0</td>\n",
       "      <td>471.0</td>\n",
       "      <td>936.0</td>\n",
       "      <td>462.0</td>\n",
       "      <td>2.8621</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3230</th>\n",
       "      <td>-119.61</td>\n",
       "      <td>36.31</td>\n",
       "      <td>25.0</td>\n",
       "      <td>1847.0</td>\n",
       "      <td>371.0</td>\n",
       "      <td>1460.0</td>\n",
       "      <td>353.0</td>\n",
       "      <td>1.8839</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3555</th>\n",
       "      <td>-118.59</td>\n",
       "      <td>34.23</td>\n",
       "      <td>17.0</td>\n",
       "      <td>6592.0</td>\n",
       "      <td>1525.0</td>\n",
       "      <td>4459.0</td>\n",
       "      <td>1463.0</td>\n",
       "      <td>3.0347</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "17606    -121.89     37.29                38.0       1568.0           351.0   \n",
       "18632    -121.93     37.05                14.0        679.0           108.0   \n",
       "14650    -117.20     32.77                31.0       1952.0           471.0   \n",
       "3230     -119.61     36.31                25.0       1847.0           371.0   \n",
       "3555     -118.59     34.23                17.0       6592.0          1525.0   \n",
       "\n",
       "       population  households  median_income  \n",
       "17606       710.0       339.0         2.7042  \n",
       "18632       306.0       113.0         6.4214  \n",
       "14650       936.0       462.0         2.8621  \n",
       "3230       1460.0       353.0         1.8839  \n",
       "3555       4459.0      1463.0         3.0347  "
      ]
     },
     "execution_count": 222,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert back into dataframe \n",
    "housing_tr = pd.DataFrame(X, columns=housing_num.columns,\n",
    "                          index = housing.index.values)\n",
    "housing_tr.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 223,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4629</th>\n",
       "      <td>-118.30</td>\n",
       "      <td>34.07</td>\n",
       "      <td>18.0</td>\n",
       "      <td>3759.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>3296.0</td>\n",
       "      <td>1462.0</td>\n",
       "      <td>2.2708</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6068</th>\n",
       "      <td>-117.86</td>\n",
       "      <td>34.01</td>\n",
       "      <td>16.0</td>\n",
       "      <td>4632.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>3038.0</td>\n",
       "      <td>727.0</td>\n",
       "      <td>5.1762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17923</th>\n",
       "      <td>-121.97</td>\n",
       "      <td>37.35</td>\n",
       "      <td>30.0</td>\n",
       "      <td>1955.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>999.0</td>\n",
       "      <td>386.0</td>\n",
       "      <td>4.6328</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13656</th>\n",
       "      <td>-117.30</td>\n",
       "      <td>34.05</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2155.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>1039.0</td>\n",
       "      <td>391.0</td>\n",
       "      <td>1.6675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19252</th>\n",
       "      <td>-122.79</td>\n",
       "      <td>38.48</td>\n",
       "      <td>7.0</td>\n",
       "      <td>6837.0</td>\n",
       "      <td>433.0</td>\n",
       "      <td>3468.0</td>\n",
       "      <td>1405.0</td>\n",
       "      <td>3.1662</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "4629     -118.30     34.07                18.0       3759.0           433.0   \n",
       "6068     -117.86     34.01                16.0       4632.0           433.0   \n",
       "17923    -121.97     37.35                30.0       1955.0           433.0   \n",
       "13656    -117.30     34.05                 6.0       2155.0           433.0   \n",
       "19252    -122.79     38.48                 7.0       6837.0           433.0   \n",
       "\n",
       "       population  households  median_income  \n",
       "4629       3296.0      1462.0         2.2708  \n",
       "6068       3038.0       727.0         5.1762  \n",
       "17923       999.0       386.0         4.6328  \n",
       "13656      1039.0       391.0         1.6675  \n",
       "19252      3468.0      1405.0         3.1662  "
      ]
     },
     "execution_count": 223,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# look at imputed data \n",
    "housing_tr.loc[sample_incomplete_rows.index.values]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-121.89</td>\n",
       "      <td>37.29</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1568.0</td>\n",
       "      <td>351.0</td>\n",
       "      <td>710.0</td>\n",
       "      <td>339.0</td>\n",
       "      <td>2.7042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-121.93</td>\n",
       "      <td>37.05</td>\n",
       "      <td>14.0</td>\n",
       "      <td>679.0</td>\n",
       "      <td>108.0</td>\n",
       "      <td>306.0</td>\n",
       "      <td>113.0</td>\n",
       "      <td>6.4214</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-117.20</td>\n",
       "      <td>32.77</td>\n",
       "      <td>31.0</td>\n",
       "      <td>1952.0</td>\n",
       "      <td>471.0</td>\n",
       "      <td>936.0</td>\n",
       "      <td>462.0</td>\n",
       "      <td>2.8621</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-119.61</td>\n",
       "      <td>36.31</td>\n",
       "      <td>25.0</td>\n",
       "      <td>1847.0</td>\n",
       "      <td>371.0</td>\n",
       "      <td>1460.0</td>\n",
       "      <td>353.0</td>\n",
       "      <td>1.8839</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-118.59</td>\n",
       "      <td>34.23</td>\n",
       "      <td>17.0</td>\n",
       "      <td>6592.0</td>\n",
       "      <td>1525.0</td>\n",
       "      <td>4459.0</td>\n",
       "      <td>1463.0</td>\n",
       "      <td>3.0347</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
       "0    -121.89     37.29                38.0       1568.0           351.0   \n",
       "1    -121.93     37.05                14.0        679.0           108.0   \n",
       "2    -117.20     32.77                31.0       1952.0           471.0   \n",
       "3    -119.61     36.31                25.0       1847.0           371.0   \n",
       "4    -118.59     34.23                17.0       6592.0          1525.0   \n",
       "\n",
       "   population  households  median_income  \n",
       "0       710.0       339.0         2.7042  \n",
       "1       306.0       113.0         6.4214  \n",
       "2       936.0       462.0         2.8621  \n",
       "3      1460.0       353.0         1.8839  \n",
       "4      4459.0      1463.0         3.0347  "
      ]
     },
     "execution_count": 224,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# clean index this time\n",
    "housing_tr = pd.DataFrame(X, columns=housing_num.columns)\n",
    "housing_tr.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Text Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 225,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import  OneHotEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "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>ocean_proximity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>17606</th>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18632</th>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14650</th>\n",
       "      <td>NEAR OCEAN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3230</th>\n",
       "      <td>INLAND</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3555</th>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      ocean_proximity\n",
       "17606       <1H OCEAN\n",
       "18632       <1H OCEAN\n",
       "14650      NEAR OCEAN\n",
       "3230           INLAND\n",
       "3555        <1H OCEAN"
      ]
     },
     "execution_count": 226,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_cat = housing[['ocean_proximity']]\n",
    "housing_cat.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 227,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<16512x5 sparse matrix of type '<class 'numpy.float64'>'\n",
       "\twith 16512 stored elements in Compressed Sparse Row format>"
      ]
     },
     "execution_count": 227,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cat_encoder =  OneHotEncoder()\n",
    "housing_cat_1hot = cat_encoder.fit_transform(housing_cat)\n",
    "housing_cat_1hot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 228,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1., 0., 0., 0., 0.],\n",
       "       [1., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 0., 1.],\n",
       "       ...,\n",
       "       [0., 1., 0., 0., 0.],\n",
       "       [1., 0., 0., 0., 0.],\n",
       "       [0., 0., 0., 1., 0.]])"
      ]
     },
     "execution_count": 228,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# to see full array \n",
    "housing_cat_1hot.toarray()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 229,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[array(['<1H OCEAN', 'INLAND', 'ISLAND', 'NEAR BAY', 'NEAR OCEAN'],\n",
       "       dtype=object)]"
      ]
     },
     "execution_count": 229,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# view categories text\n",
    "cat_encoder.categories_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Custom Transformers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 230,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 230,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(housing.columns).index(\"total_rooms\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 231,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.base import BaseEstimator, TransformerMixin\n",
    "\n",
    "# get the right column indices: safer than hard-coding indices 3, 4, 5, 6\n",
    "rooms_ix, bedrooms_ix, population_ix, household_ix = [\n",
    "    list(housing.columns).index(col)\n",
    "    for col in (\"total_rooms\", \"total_bedrooms\", \"population\", \"households\")]\n",
    "\n",
    "class CombinedAttributesAdder(BaseEstimator, TransformerMixin):\n",
    "    def __init__(self, add_bedrooms_per_room = True): # no *args or **kargs\n",
    "        self.add_bedrooms_per_room = add_bedrooms_per_room\n",
    "    def fit(self, X, y=None):\n",
    "        return self  # nothing else to do\n",
    "    def transform(self, X, y=None):\n",
    "        rooms_per_household = X[:, rooms_ix] / X[:, household_ix]\n",
    "        population_per_household = X[:, population_ix] / X[:, household_ix]\n",
    "        if self.add_bedrooms_per_room:\n",
    "            bedrooms_per_room = X[:, bedrooms_ix] / X[:, rooms_ix]\n",
    "            return np.c_[X, rooms_per_household, population_per_household,\n",
    "                         bedrooms_per_room]\n",
    "        else:\n",
    "            return np.c_[X, rooms_per_household, population_per_household]\n",
    "\n",
    "attr_adder = CombinedAttributesAdder(add_bedrooms_per_room=False)\n",
    "housing_extra_attribs = attr_adder.transform(housing.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Yet another method \n",
    "from sklearn.preprocessing import FunctionTransformer\n",
    "\n",
    "def add_extra_features(X, add_bedrooms_per_room=True):\n",
    "    rooms_per_household = X[:, rooms_ix] / X[:, household_ix]\n",
    "    population_per_household = X[:, population_ix] / X[:, household_ix]\n",
    "    if add_bedrooms_per_room:\n",
    "        bedrooms_per_room = X[:, bedrooms_ix] / X[:, rooms_ix]\n",
    "        return np.c_[X, rooms_per_household, population_per_household,\n",
    "                     bedrooms_per_room]\n",
    "    else:\n",
    "        return np.c_[X, rooms_per_household, population_per_household]\n",
    "\n",
    "attr_adder = FunctionTransformer(add_extra_features, validate=False,\n",
    "                                 kw_args={\"add_bedrooms_per_room\": False})\n",
    "housing_extra_attribs = attr_adder.fit_transform(housing.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-121.89, 37.29, 38.0, 1568.0, 351.0, 710.0, 339.0, 2.7042,\n",
       "        '<1H OCEAN', 4.625368731563422, 2.094395280235988],\n",
       "       [-121.93, 37.05, 14.0, 679.0, 108.0, 306.0, 113.0, 6.4214,\n",
       "        '<1H OCEAN', 6.008849557522124, 2.7079646017699117],\n",
       "       [-117.2, 32.77, 31.0, 1952.0, 471.0, 936.0, 462.0, 2.8621,\n",
       "        'NEAR OCEAN', 4.225108225108225, 2.0259740259740258]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 233,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_extra_attribs[0:3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 234,
   "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>longitude</th>\n",
       "      <th>latitude</th>\n",
       "      <th>housing_median_age</th>\n",
       "      <th>total_rooms</th>\n",
       "      <th>total_bedrooms</th>\n",
       "      <th>population</th>\n",
       "      <th>households</th>\n",
       "      <th>median_income</th>\n",
       "      <th>ocean_proximity</th>\n",
       "      <th>rooms_per_household</th>\n",
       "      <th>population_per_household</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-121.89</td>\n",
       "      <td>37.29</td>\n",
       "      <td>38</td>\n",
       "      <td>1568</td>\n",
       "      <td>351</td>\n",
       "      <td>710</td>\n",
       "      <td>339</td>\n",
       "      <td>2.7042</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "      <td>4.62537</td>\n",
       "      <td>2.0944</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-121.93</td>\n",
       "      <td>37.05</td>\n",
       "      <td>14</td>\n",
       "      <td>679</td>\n",
       "      <td>108</td>\n",
       "      <td>306</td>\n",
       "      <td>113</td>\n",
       "      <td>6.4214</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "      <td>6.00885</td>\n",
       "      <td>2.70796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-117.2</td>\n",
       "      <td>32.77</td>\n",
       "      <td>31</td>\n",
       "      <td>1952</td>\n",
       "      <td>471</td>\n",
       "      <td>936</td>\n",
       "      <td>462</td>\n",
       "      <td>2.8621</td>\n",
       "      <td>NEAR OCEAN</td>\n",
       "      <td>4.22511</td>\n",
       "      <td>2.02597</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-119.61</td>\n",
       "      <td>36.31</td>\n",
       "      <td>25</td>\n",
       "      <td>1847</td>\n",
       "      <td>371</td>\n",
       "      <td>1460</td>\n",
       "      <td>353</td>\n",
       "      <td>1.8839</td>\n",
       "      <td>INLAND</td>\n",
       "      <td>5.23229</td>\n",
       "      <td>4.13598</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-118.59</td>\n",
       "      <td>34.23</td>\n",
       "      <td>17</td>\n",
       "      <td>6592</td>\n",
       "      <td>1525</td>\n",
       "      <td>4459</td>\n",
       "      <td>1463</td>\n",
       "      <td>3.0347</td>\n",
       "      <td>&lt;1H OCEAN</td>\n",
       "      <td>4.50581</td>\n",
       "      <td>3.04785</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  longitude latitude housing_median_age total_rooms total_bedrooms population  \\\n",
       "0   -121.89    37.29                 38        1568            351        710   \n",
       "1   -121.93    37.05                 14         679            108        306   \n",
       "2    -117.2    32.77                 31        1952            471        936   \n",
       "3   -119.61    36.31                 25        1847            371       1460   \n",
       "4   -118.59    34.23                 17        6592           1525       4459   \n",
       "\n",
       "  households median_income ocean_proximity rooms_per_household  \\\n",
       "0        339        2.7042       <1H OCEAN             4.62537   \n",
       "1        113        6.4214       <1H OCEAN             6.00885   \n",
       "2        462        2.8621      NEAR OCEAN             4.22511   \n",
       "3        353        1.8839          INLAND             5.23229   \n",
       "4       1463        3.0347       <1H OCEAN             4.50581   \n",
       "\n",
       "  population_per_household  \n",
       "0                   2.0944  \n",
       "1                  2.70796  \n",
       "2                  2.02597  \n",
       "3                  4.13598  \n",
       "4                  3.04785  "
      ]
     },
     "execution_count": 234,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_extra_attribs = pd.DataFrame(housing_extra_attribs, columns=list(\n",
    "    housing.columns)+[\"rooms_per_household\", \"population_per_household\"])\n",
    "housing_extra_attribs.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Transformation Pipelines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 235,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "num_pipeline = Pipeline([\n",
    "        ('imputer', SimpleImputer(strategy=\"median\")),\n",
    "        ('attribs_adder', FunctionTransformer(add_extra_features, validate=False)),\n",
    "        ('std_scaler', StandardScaler()),\n",
    "    ])\n",
    "\n",
    "housing_num_tr = num_pipeline.fit_transform(housing_num)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 236,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 11)"
      ]
     },
     "execution_count": 236,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_num_tr.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 237,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-1.15604281,  0.77194962,  0.74333089, ..., -0.31205452,\n",
       "        -0.08649871,  0.15531753],\n",
       "       [-1.17602483,  0.6596948 , -1.1653172 , ...,  0.21768338,\n",
       "        -0.03353391, -0.83628902],\n",
       "       [ 1.18684903, -1.34218285,  0.18664186, ..., -0.46531516,\n",
       "        -0.09240499,  0.4222004 ],\n",
       "       ...,\n",
       "       [ 1.58648943, -0.72478134, -1.56295222, ...,  0.3469342 ,\n",
       "        -0.03055414, -0.52177644],\n",
       "       [ 0.78221312, -0.85106801,  0.18664186, ...,  0.02499488,\n",
       "         0.06150916, -0.30340741],\n",
       "       [-1.43579109,  0.99645926,  1.85670895, ..., -0.22852947,\n",
       "        -0.09586294,  0.10180567]])"
      ]
     },
     "execution_count": 237,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_num_tr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 238,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now we can combine both pipelines numerical and categorical into one \n",
    "from sklearn.compose import ColumnTransformer\n",
    "num_attribs = list(housing_num)\n",
    "cat_attribs = [\"ocean_proximity\"]\n",
    "\n",
    "full_pipeline = ColumnTransformer([\n",
    "        (\"num\", num_pipeline, num_attribs),\n",
    "        (\"cat\", OneHotEncoder(), cat_attribs),\n",
    "    ])\n",
    "\n",
    "housing_prepared = full_pipeline.fit_transform(housing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 239,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[-1.15604281,  0.77194962,  0.74333089, ...,  0.        ,\n",
       "         0.        ,  0.        ],\n",
       "       [-1.17602483,  0.6596948 , -1.1653172 , ...,  0.        ,\n",
       "         0.        ,  0.        ],\n",
       "       [ 1.18684903, -1.34218285,  0.18664186, ...,  0.        ,\n",
       "         0.        ,  1.        ],\n",
       "       ...,\n",
       "       [ 1.58648943, -0.72478134, -1.56295222, ...,  0.        ,\n",
       "         0.        ,  0.        ],\n",
       "       [ 0.78221312, -0.85106801,  0.18664186, ...,  0.        ,\n",
       "         0.        ,  0.        ],\n",
       "       [-1.43579109,  0.99645926,  1.85670895, ...,  0.        ,\n",
       "         1.        ,  0.        ]])"
      ]
     },
     "execution_count": 239,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_prepared"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 240,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 16)"
      ]
     },
     "execution_count": 240,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_prepared.shape\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The new matrix contains the original columns transformed plus 5 more columns for the categorical encoder data\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 241,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['data/interim/housing_labels.pkl']"
      ]
     },
     "execution_count": 241,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Save the transformed data\n",
    "from sklearn.externals import joblib\n",
    "joblib.dump(housing_prepared, 'data/interim/'+'housing_prepared'+'.pkl') \n",
    "joblib.dump(housing_labels, 'data/interim/'+'housing_labels'+'.pkl') "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Explore models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 242,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load saved transformed data\n",
    "from sklearn.externals import joblib\n",
    "housing_prepared = joblib.load('data/interim/'+'housing_prepared'+'.pkl') \n",
    "housing_labels = joblib.load('data/interim/'+'housing_labels'+'.pkl') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 244,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 16)"
      ]
     },
     "execution_count": 244,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_prepared.shape\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Linear Regression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 245,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None,\n",
       "         normalize=False)"
      ]
     },
     "execution_count": 245,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "# instantiate model \n",
    "lin_reg = LinearRegression()\n",
    "# feed the model data and labels \n",
    "lin_reg.fit(housing_prepared, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 246,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predictions: [210644.60459286 317768.80697211 210956.43331178  59218.98886849\n",
      " 189747.55849879]\n"
     ]
    }
   ],
   "source": [
    "# let's try the full preprocessing pipeline on a few training instances\n",
    "some_data = housing_df.iloc[:5]\n",
    "some_labels = housing_labels.iloc[:5]\n",
    "some_data_prepared = full_pipeline.transform(some_data)\n",
    "\n",
    "print(\"Predictions:\", lin_reg.predict(some_data_prepared))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 247,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Labels: [286600.0, 340600.0, 196900.0, 46300.0, 254500.0]\n"
     ]
    }
   ],
   "source": [
    "print(\"Labels:\", list(some_labels))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 248,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediction: 210644 \t Label: 286600 \n",
      "Prediction: 317768 \t Label: 340600 \n",
      "Prediction: 210956 \t Label: 196900 \n",
      "Prediction: 59218 \t Label: 46300 \n",
      "Prediction: 189747 \t Label: 254500 \n"
     ]
    }
   ],
   "source": [
    "for pred, label in zip( lin_reg.predict(some_data_prepared), list(some_labels) ): \n",
    "    print('Prediction: {} \\t Label: {} '.format(int(pred),int( label)))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "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>Labels</th>\n",
       "      <th>Predictions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>286600.0</td>\n",
       "      <td>210644.604593</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>340600.0</td>\n",
       "      <td>317768.806972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>196900.0</td>\n",
       "      <td>210956.433312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>46300.0</td>\n",
       "      <td>59218.988868</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>254500.0</td>\n",
       "      <td>189747.558499</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Labels    Predictions\n",
       "0  286600.0  210644.604593\n",
       "1  340600.0  317768.806972\n",
       "2  196900.0  210956.433312\n",
       "3   46300.0   59218.988868\n",
       "4  254500.0  189747.558499"
      ]
     },
     "execution_count": 249,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame({'Predictions': list( lin_reg.predict(some_data_prepared)) , 'Labels': list(some_labels)})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model performance "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 250,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "68628.19819848922"
      ]
     },
     "execution_count": 250,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "housing_predictions = lin_reg.predict(housing_prepared)\n",
    "lin_mse = mean_squared_error(housing_labels, housing_predictions)\n",
    "lin_rmse = np.sqrt(lin_mse)\n",
    "lin_rmse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 251,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "49439.89599001898"
      ]
     },
     "execution_count": 251,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import mean_absolute_error\n",
    "\n",
    "lin_mae = mean_absolute_error(housing_labels, housing_predictions)\n",
    "lin_mae"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Decision Tree "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 252,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeRegressor(criterion='mse', max_depth=None, max_features=None,\n",
       "           max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "           min_impurity_split=None, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           presort=False, random_state=42, splitter='best')"
      ]
     },
     "execution_count": 252,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "tree_reg = DecisionTreeRegressor(random_state=42)\n",
    "tree_reg.fit(housing_prepared, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 253,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 253,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_predictions = tree_reg.predict(housing_prepared)\n",
    "tree_mse = mean_squared_error(housing_labels, housing_predictions)\n",
    "tree_rmse = np.sqrt(tree_mse)\n",
    "tree_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model Performance "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 254,
   "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>Labels</th>\n",
       "      <th>Predictions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>286600.0</td>\n",
       "      <td>286600.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>340600.0</td>\n",
       "      <td>340600.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>196900.0</td>\n",
       "      <td>196900.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>46300.0</td>\n",
       "      <td>46300.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>254500.0</td>\n",
       "      <td>254500.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Labels  Predictions\n",
       "0  286600.0     286600.0\n",
       "1  340600.0     340600.0\n",
       "2  196900.0     196900.0\n",
       "3   46300.0      46300.0\n",
       "4  254500.0     254500.0"
      ]
     },
     "execution_count": 254,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame({'Predictions': list(housing_predictions) , 'Labels': list(housing_labels)}).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fine tune model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Decision Tree Regression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 255,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "scores = cross_val_score(tree_reg, housing_prepared, housing_labels,\n",
    "                         scoring=\"neg_mean_squared_error\", cv=10)\n",
    "# cv expects a utility function instead of cost function \n",
    "tree_rmse_scores = np.sqrt(-scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 256,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scores: [70194.33680785 66855.16363941 72432.58244769 70758.73896782\n",
      " 71115.88230639 75585.14172901 70262.86139133 70273.6325285\n",
      " 75366.87952553 71231.65726027]\n",
      "Mean: 71407.68766037929\n",
      "Standard deviation: 2439.4345041191004\n"
     ]
    }
   ],
   "source": [
    "def display_scores(scores):\n",
    "    print(\"Scores:\", scores)\n",
    "    print(\"Mean:\", scores.mean())\n",
    "    print(\"Standard deviation:\", scores.std())\n",
    "\n",
    "display_scores(tree_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is peforming worse than linear regression "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Linear Regression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 257,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scores: [66782.73843989 66960.118071   70347.95244419 74739.57052552\n",
      " 68031.13388938 71193.84183426 64969.63056405 68281.61137997\n",
      " 71552.91566558 67665.10082067]\n",
      "Mean: 69052.46136345083\n",
      "Standard deviation: 2731.674001798347\n"
     ]
    }
   ],
   "source": [
    "lin_scores = cross_val_score(lin_reg, housing_prepared, housing_labels,\n",
    "                             scoring=\"neg_mean_squared_error\", cv=10)\n",
    "lin_rmse_scores = np.sqrt(-lin_scores)\n",
    "display_scores(lin_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random Forrest Regression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 258,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n",
       "           max_features='auto', max_leaf_nodes=None,\n",
       "           min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "           min_samples_leaf=1, min_samples_split=2,\n",
       "           min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None,\n",
       "           oob_score=False, random_state=42, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 258,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "forest_reg = RandomForestRegressor(n_estimators=10, random_state=42)\n",
    "forest_reg.fit(housing_prepared, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 259,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "21933.31414779769"
      ]
     },
     "execution_count": 259,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_predictions = forest_reg.predict(housing_prepared)\n",
    "forest_mse = mean_squared_error(housing_labels, housing_predictions)\n",
    "forest_rmse = np.sqrt(forest_mse)\n",
    "forest_rmse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 260,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scores: [51646.44545909 48940.60114882 53050.86323649 54408.98730149\n",
      " 50922.14870785 56482.50703987 51864.52025526 49760.85037653\n",
      " 55434.21627933 53326.10093303]\n",
      "Mean: 52583.72407377466\n",
      "Standard deviation: 2298.353351147122\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "forest_scores = cross_val_score(forest_reg, housing_prepared, housing_labels,\n",
    "                                scoring=\"neg_mean_squared_error\", cv=10)\n",
    "forest_rmse_scores = np.sqrt(-forest_scores)\n",
    "display_scores(forest_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Support Vector Machines (linear kernel)\n",
    "\n",
    "A low C makes the decision surface smooth, while a high C aims at classifying all training examples correctly. gamma defines how much influence a single training example has. The larger gamma is, the closer other examples must be to be affected."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 261,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "111094.6308539982"
      ]
     },
     "execution_count": 261,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.svm import SVR\n",
    "\n",
    "svm_reg = SVR(kernel=\"linear\")\n",
    "svm_reg.fit(housing_prepared, housing_labels)\n",
    "housing_predictions = svm_reg.predict(housing_prepared)\n",
    "svm_mse = mean_squared_error(housing_labels, housing_predictions)\n",
    "svm_rmse = np.sqrt(svm_mse)\n",
    "svm_rmse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 262,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scores: [105342.09141998 112489.24624123 110092.35042753 113403.22892482\n",
      " 110638.90119657 115675.8320024  110703.56887243 114476.89008206\n",
      " 113756.17971227 111520.1120808 ]\n",
      "Mean: 111809.84009600841\n",
      "Standard deviation: 2762.393664321567\n"
     ]
    }
   ],
   "source": [
    "svm_scores = cross_val_score(svm_reg, housing_prepared, housing_labels,\n",
    "                             scoring=\"neg_mean_squared_error\", cv=10)\n",
    "svm_rmse_scores = np.sqrt(-svm_scores)\n",
    "display_scores(svm_rmse_scores)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 263,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "118577.43356412371"
      ]
     },
     "execution_count": 263,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# rbf kernel \n",
    "svm_reg = SVR(kernel=\"rbf\", gamma='auto')\n",
    "svm_reg.fit(housing_prepared, housing_labels)\n",
    "housing_predictions = svm_reg.predict(housing_prepared)\n",
    "svm_mse = mean_squared_error(housing_labels, housing_predictions)\n",
    "svm_rmse = np.sqrt(svm_mse)\n",
    "svm_rmse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 264,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scores: [111393.33263237 119546.71049753 116961.00489445 120449.0155974\n",
      " 117622.20149716 122303.76986818 117640.09907103 121459.63518806\n",
      " 120348.51364519 118025.61954959]\n",
      "Mean: 118574.99024409598\n",
      "Standard deviation: 2934.1329433145675\n"
     ]
    }
   ],
   "source": [
    "svm_scores = cross_val_score(svm_reg, housing_prepared, housing_labels,\n",
    "                             scoring=\"neg_mean_squared_error\", cv=10)\n",
    "svm_rmse_scores = np.sqrt(-svm_scores)\n",
    "display_scores(svm_rmse_scores)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Grid Search \n",
    "- Grid search helps you find the best hyper parameters \n",
    "- In the case below there will be $(3*4 + 2*3)*5=(12 + 6)*5 = 90$ trainings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 265,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5, error_score='raise-deprecating',\n",
       "       estimator=RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n",
       "           max_features='auto', max_leaf_nodes=None,\n",
       "           min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "           min_samples_leaf=1, min_samples_split=2,\n",
       "           min_weight_fraction_leaf=0.0, n_estimators='warn', n_jobs=None,\n",
       "           oob_score=False, random_state=42, verbose=0, warm_start=False),\n",
       "       fit_params=None, iid='warn', n_jobs=-1,\n",
       "       param_grid=[{'n_estimators': [3, 10, 30], 'max_features': [2, 4, 6, 8]}, {'n_estimators': [3, 10], 'max_features': [2, 3, 4], 'bootstrap': [False]}],\n",
       "       pre_dispatch='2*n_jobs', refit=True, return_train_score=True,\n",
       "       scoring='neg_mean_squared_error', verbose=0)"
      ]
     },
     "execution_count": 265,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "param_grid = [\n",
    "    # try 12 (3×4) combinations of hyperparameters\n",
    "    {'n_estimators': [3, 10, 30], 'max_features': [2, 4, 6, 8]},\n",
    "    # then try 6 (2×3) combinations with bootstrap set as False\n",
    "    {'bootstrap': [False], 'n_estimators': [3, 10], 'max_features': [2, 3, 4]},\n",
    "  ]\n",
    "\n",
    "forest_reg = RandomForestRegressor(random_state=42)\n",
    "# train across 5 folds, that's a total of (12+6)*5=90 rounds of training \n",
    "grid_search = GridSearchCV(forest_reg, param_grid, cv=5,n_jobs=-1,\n",
    "                           scoring='neg_mean_squared_error', return_train_score=True)\n",
    "grid_search.fit(housing_prepared, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 266,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The best hyperparameter combination found: {'n_estimators': 30, 'max_features': 8}\n"
     ]
    }
   ],
   "source": [
    "print('The best hyperparameter combination found: {}'.format(grid_search.best_params_)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 267,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n",
       "           max_features=8, max_leaf_nodes=None, min_impurity_decrease=0.0,\n",
       "           min_impurity_split=None, min_samples_leaf=1,\n",
       "           min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
       "           n_estimators=30, n_jobs=None, oob_score=False, random_state=42,\n",
       "           verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 267,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# parameters for best estimator \n",
    "grid_search.best_estimator_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Looking at the score for each hyper parameters combination \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 268,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "63669 {'n_estimators': 3, 'max_features': 2}\n",
      "55627 {'n_estimators': 10, 'max_features': 2}\n",
      "53384 {'n_estimators': 30, 'max_features': 2}\n",
      "60965 {'n_estimators': 3, 'max_features': 4}\n",
      "52740 {'n_estimators': 10, 'max_features': 4}\n",
      "50377 {'n_estimators': 30, 'max_features': 4}\n",
      "58663 {'n_estimators': 3, 'max_features': 6}\n",
      "52006 {'n_estimators': 10, 'max_features': 6}\n",
      "50146 {'n_estimators': 30, 'max_features': 6}\n",
      "57869 {'n_estimators': 3, 'max_features': 8}\n",
      "51711 {'n_estimators': 10, 'max_features': 8}\n",
      "49682 {'n_estimators': 30, 'max_features': 8}\n",
      "62895 {'n_estimators': 3, 'max_features': 2, 'bootstrap': False}\n",
      "54658 {'n_estimators': 10, 'max_features': 2, 'bootstrap': False}\n",
      "59470 {'n_estimators': 3, 'max_features': 3, 'bootstrap': False}\n",
      "52725 {'n_estimators': 10, 'max_features': 3, 'bootstrap': False}\n",
      "57490 {'n_estimators': 3, 'max_features': 4, 'bootstrap': False}\n",
      "51009 {'n_estimators': 10, 'max_features': 4, 'bootstrap': False}\n"
     ]
    }
   ],
   "source": [
    "cvres = grid_search.cv_results_\n",
    "for mean_score, params in zip(cvres[\"mean_test_score\"], cvres[\"params\"]):\n",
    "    print(int(np.sqrt(-mean_score)), params)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 269,
   "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>mean_fit_time</th>\n",
       "      <th>mean_score_time</th>\n",
       "      <th>mean_test_score</th>\n",
       "      <th>mean_train_score</th>\n",
       "      <th>param_bootstrap</th>\n",
       "      <th>param_max_features</th>\n",
       "      <th>param_n_estimators</th>\n",
       "      <th>params</th>\n",
       "      <th>rank_test_score</th>\n",
       "      <th>split0_test_score</th>\n",
       "      <th>...</th>\n",
       "      <th>split2_test_score</th>\n",
       "      <th>split2_train_score</th>\n",
       "      <th>split3_test_score</th>\n",
       "      <th>split3_train_score</th>\n",
       "      <th>split4_test_score</th>\n",
       "      <th>split4_train_score</th>\n",
       "      <th>std_fit_time</th>\n",
       "      <th>std_score_time</th>\n",
       "      <th>std_test_score</th>\n",
       "      <th>std_train_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>3.354504</td>\n",
       "      <td>0.053489</td>\n",
       "      <td>-2.468326e+09</td>\n",
       "      <td>-3.810330e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8</td>\n",
       "      <td>30</td>\n",
       "      <td>{'n_estimators': 30, 'max_features': 8}</td>\n",
       "      <td>1</td>\n",
       "      <td>-2.357390e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.591972e+09</td>\n",
       "      <td>-3.773239e+08</td>\n",
       "      <td>-2.318617e+09</td>\n",
       "      <td>-3.882250e+08</td>\n",
       "      <td>-2.527022e+09</td>\n",
       "      <td>-3.810005e+08</td>\n",
       "      <td>0.172000</td>\n",
       "      <td>0.009551</td>\n",
       "      <td>1.091647e+08</td>\n",
       "      <td>4.871017e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>2.525017</td>\n",
       "      <td>0.050918</td>\n",
       "      <td>-2.514668e+09</td>\n",
       "      <td>-3.841296e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6</td>\n",
       "      <td>30</td>\n",
       "      <td>{'n_estimators': 30, 'max_features': 6}</td>\n",
       "      <td>2</td>\n",
       "      <td>-2.370010e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.607703e+09</td>\n",
       "      <td>-3.805218e+08</td>\n",
       "      <td>-2.350953e+09</td>\n",
       "      <td>-3.856095e+08</td>\n",
       "      <td>-2.661059e+09</td>\n",
       "      <td>-3.901917e+08</td>\n",
       "      <td>0.221924</td>\n",
       "      <td>0.002579</td>\n",
       "      <td>1.285063e+08</td>\n",
       "      <td>3.617057e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1.784167</td>\n",
       "      <td>0.058159</td>\n",
       "      <td>-2.537877e+09</td>\n",
       "      <td>-3.879289e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>30</td>\n",
       "      <td>{'n_estimators': 30, 'max_features': 4}</td>\n",
       "      <td>3</td>\n",
       "      <td>-2.387153e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.666426e+09</td>\n",
       "      <td>-3.790867e+08</td>\n",
       "      <td>-2.398071e+09</td>\n",
       "      <td>-4.040957e+08</td>\n",
       "      <td>-2.649316e+09</td>\n",
       "      <td>-3.845520e+08</td>\n",
       "      <td>0.122772</td>\n",
       "      <td>0.017129</td>\n",
       "      <td>1.214603e+08</td>\n",
       "      <td>8.571233e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>0.976491</td>\n",
       "      <td>0.028234</td>\n",
       "      <td>-2.601971e+09</td>\n",
       "      <td>-3.028238e-03</td>\n",
       "      <td>False</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 4, 'boots...</td>\n",
       "      <td>4</td>\n",
       "      <td>-2.525578e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.609100e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-2.439607e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-2.725548e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>0.295675</td>\n",
       "      <td>0.007139</td>\n",
       "      <td>1.088031e+08</td>\n",
       "      <td>6.056477e-03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>1.112599</td>\n",
       "      <td>0.019048</td>\n",
       "      <td>-2.674037e+09</td>\n",
       "      <td>-4.923911e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 8}</td>\n",
       "      <td>5</td>\n",
       "      <td>-2.571970e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.842317e+09</td>\n",
       "      <td>-4.730979e+08</td>\n",
       "      <td>-2.460258e+09</td>\n",
       "      <td>-5.155367e+08</td>\n",
       "      <td>-2.776666e+09</td>\n",
       "      <td>-4.985555e+08</td>\n",
       "      <td>0.100974</td>\n",
       "      <td>0.002301</td>\n",
       "      <td>1.392720e+08</td>\n",
       "      <td>1.459294e+07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.827751</td>\n",
       "      <td>0.020989</td>\n",
       "      <td>-2.704640e+09</td>\n",
       "      <td>-5.013349e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 6}</td>\n",
       "      <td>6</td>\n",
       "      <td>-2.549663e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.762720e+09</td>\n",
       "      <td>-4.994664e+08</td>\n",
       "      <td>-2.521134e+09</td>\n",
       "      <td>-4.990325e+08</td>\n",
       "      <td>-2.907667e+09</td>\n",
       "      <td>-5.055542e+08</td>\n",
       "      <td>0.077836</td>\n",
       "      <td>0.006335</td>\n",
       "      <td>1.471542e+08</td>\n",
       "      <td>3.100456e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>0.675495</td>\n",
       "      <td>0.022814</td>\n",
       "      <td>-2.779927e+09</td>\n",
       "      <td>-5.272080e+00</td>\n",
       "      <td>False</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 3, 'boots...</td>\n",
       "      <td>7</td>\n",
       "      <td>-2.757999e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.830927e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-2.672765e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-2.786190e+09</td>\n",
       "      <td>-5.465556e+00</td>\n",
       "      <td>0.073931</td>\n",
       "      <td>0.001319</td>\n",
       "      <td>6.286611e+07</td>\n",
       "      <td>8.093117e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.558351</td>\n",
       "      <td>0.021956</td>\n",
       "      <td>-2.781611e+09</td>\n",
       "      <td>-5.163863e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 4}</td>\n",
       "      <td>8</td>\n",
       "      <td>-2.666283e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.892276e+09</td>\n",
       "      <td>-4.962893e+08</td>\n",
       "      <td>-2.616813e+09</td>\n",
       "      <td>-5.436192e+08</td>\n",
       "      <td>-2.948207e+09</td>\n",
       "      <td>-5.160297e+08</td>\n",
       "      <td>0.039796</td>\n",
       "      <td>0.008723</td>\n",
       "      <td>1.268562e+08</td>\n",
       "      <td>1.542862e+07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.151661</td>\n",
       "      <td>0.052023</td>\n",
       "      <td>-2.849913e+09</td>\n",
       "      <td>-4.394734e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>30</td>\n",
       "      <td>{'n_estimators': 30, 'max_features': 2}</td>\n",
       "      <td>9</td>\n",
       "      <td>-2.689185e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-2.948330e+09</td>\n",
       "      <td>-4.371702e+08</td>\n",
       "      <td>-2.619995e+09</td>\n",
       "      <td>-4.376955e+08</td>\n",
       "      <td>-2.970968e+09</td>\n",
       "      <td>-4.452654e+08</td>\n",
       "      <td>0.144397</td>\n",
       "      <td>0.002657</td>\n",
       "      <td>1.626879e+08</td>\n",
       "      <td>2.966320e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.611461</td>\n",
       "      <td>0.023005</td>\n",
       "      <td>-2.987513e+09</td>\n",
       "      <td>-6.056027e-01</td>\n",
       "      <td>False</td>\n",
       "      <td>2</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 2, 'boots...</td>\n",
       "      <td>10</td>\n",
       "      <td>-2.810721e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.131187e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-2.788537e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-3.099347e+09</td>\n",
       "      <td>-2.967449e+00</td>\n",
       "      <td>0.043821</td>\n",
       "      <td>0.000978</td>\n",
       "      <td>1.539231e+08</td>\n",
       "      <td>1.181156e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.373621</td>\n",
       "      <td>0.023403</td>\n",
       "      <td>-3.094381e+09</td>\n",
       "      <td>-5.818785e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>10</td>\n",
       "      <td>{'n_estimators': 10, 'max_features': 2}</td>\n",
       "      <td>11</td>\n",
       "      <td>-3.047771e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.130196e+09</td>\n",
       "      <td>-5.776964e+08</td>\n",
       "      <td>-2.865188e+09</td>\n",
       "      <td>-5.716332e+08</td>\n",
       "      <td>-3.173856e+09</td>\n",
       "      <td>-5.802501e+08</td>\n",
       "      <td>0.079333</td>\n",
       "      <td>0.005578</td>\n",
       "      <td>1.327046e+08</td>\n",
       "      <td>7.345821e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>0.253212</td>\n",
       "      <td>0.007124</td>\n",
       "      <td>-3.305171e+09</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>False</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 4, 'bootst...</td>\n",
       "      <td>12</td>\n",
       "      <td>-3.134040e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.440422e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-3.053647e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-3.338344e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>0.097383</td>\n",
       "      <td>0.000550</td>\n",
       "      <td>1.879203e+08</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.280610</td>\n",
       "      <td>0.006559</td>\n",
       "      <td>-3.348851e+09</td>\n",
       "      <td>-8.883545e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 8}</td>\n",
       "      <td>13</td>\n",
       "      <td>-3.353504e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.402843e+09</td>\n",
       "      <td>-8.603321e+08</td>\n",
       "      <td>-3.129307e+09</td>\n",
       "      <td>-8.881964e+08</td>\n",
       "      <td>-3.510047e+09</td>\n",
       "      <td>-9.151287e+08</td>\n",
       "      <td>0.043096</td>\n",
       "      <td>0.000172</td>\n",
       "      <td>1.241864e+08</td>\n",
       "      <td>2.750227e+07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.129712</td>\n",
       "      <td>0.006625</td>\n",
       "      <td>-3.441447e+09</td>\n",
       "      <td>-9.023976e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 6}</td>\n",
       "      <td>14</td>\n",
       "      <td>-3.119657e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.592772e+09</td>\n",
       "      <td>-9.353135e+08</td>\n",
       "      <td>-3.328934e+09</td>\n",
       "      <td>-9.009801e+08</td>\n",
       "      <td>-3.579607e+09</td>\n",
       "      <td>-8.624664e+08</td>\n",
       "      <td>0.020992</td>\n",
       "      <td>0.000224</td>\n",
       "      <td>1.893141e+08</td>\n",
       "      <td>2.591445e+07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>0.216452</td>\n",
       "      <td>0.007962</td>\n",
       "      <td>-3.536728e+09</td>\n",
       "      <td>-1.214568e+01</td>\n",
       "      <td>False</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 3, 'bootst...</td>\n",
       "      <td>15</td>\n",
       "      <td>-3.618324e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.554815e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-3.619116e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-3.449864e+09</td>\n",
       "      <td>-6.072840e+01</td>\n",
       "      <td>0.081226</td>\n",
       "      <td>0.000395</td>\n",
       "      <td>7.795196e+07</td>\n",
       "      <td>2.429136e+01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.143291</td>\n",
       "      <td>0.007133</td>\n",
       "      <td>-3.716852e+09</td>\n",
       "      <td>-9.848396e+08</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 4}</td>\n",
       "      <td>16</td>\n",
       "      <td>-3.730181e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.734515e+09</td>\n",
       "      <td>-9.169425e+08</td>\n",
       "      <td>-3.418747e+09</td>\n",
       "      <td>-1.037400e+09</td>\n",
       "      <td>-3.913907e+09</td>\n",
       "      <td>-9.707739e+08</td>\n",
       "      <td>0.027455</td>\n",
       "      <td>0.001225</td>\n",
       "      <td>1.631421e+08</td>\n",
       "      <td>4.084607e+07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.137781</td>\n",
       "      <td>0.007999</td>\n",
       "      <td>-3.955792e+09</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>False</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 2, 'bootst...</td>\n",
       "      <td>17</td>\n",
       "      <td>-3.785816e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.061751e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-3.675704e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>-4.089667e+09</td>\n",
       "      <td>-0.000000e+00</td>\n",
       "      <td>0.022286</td>\n",
       "      <td>0.000159</td>\n",
       "      <td>1.900966e+08</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.177232</td>\n",
       "      <td>0.007945</td>\n",
       "      <td>-4.053749e+09</td>\n",
       "      <td>-1.105559e+09</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>{'n_estimators': 3, 'max_features': 2}</td>\n",
       "      <td>18</td>\n",
       "      <td>-3.837622e+09</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.196408e+09</td>\n",
       "      <td>-1.116550e+09</td>\n",
       "      <td>-3.903319e+09</td>\n",
       "      <td>-1.112342e+09</td>\n",
       "      <td>-4.184325e+09</td>\n",
       "      <td>-1.129650e+09</td>\n",
       "      <td>0.034350</td>\n",
       "      <td>0.001114</td>\n",
       "      <td>1.519609e+08</td>\n",
       "      <td>2.220402e+07</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>18 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    mean_fit_time  mean_score_time  mean_test_score  mean_train_score  \\\n",
       "11       3.354504         0.053489    -2.468326e+09     -3.810330e+08   \n",
       "8        2.525017         0.050918    -2.514668e+09     -3.841296e+08   \n",
       "5        1.784167         0.058159    -2.537877e+09     -3.879289e+08   \n",
       "17       0.976491         0.028234    -2.601971e+09     -3.028238e-03   \n",
       "10       1.112599         0.019048    -2.674037e+09     -4.923911e+08   \n",
       "7        0.827751         0.020989    -2.704640e+09     -5.013349e+08   \n",
       "15       0.675495         0.022814    -2.779927e+09     -5.272080e+00   \n",
       "4        0.558351         0.021956    -2.781611e+09     -5.163863e+08   \n",
       "2        1.151661         0.052023    -2.849913e+09     -4.394734e+08   \n",
       "13       0.611461         0.023005    -2.987513e+09     -6.056027e-01   \n",
       "1        0.373621         0.023403    -3.094381e+09     -5.818785e+08   \n",
       "16       0.253212         0.007124    -3.305171e+09      0.000000e+00   \n",
       "9        0.280610         0.006559    -3.348851e+09     -8.883545e+08   \n",
       "6        0.129712         0.006625    -3.441447e+09     -9.023976e+08   \n",
       "14       0.216452         0.007962    -3.536728e+09     -1.214568e+01   \n",
       "3        0.143291         0.007133    -3.716852e+09     -9.848396e+08   \n",
       "12       0.137781         0.007999    -3.955792e+09      0.000000e+00   \n",
       "0        0.177232         0.007945    -4.053749e+09     -1.105559e+09   \n",
       "\n",
       "   param_bootstrap param_max_features param_n_estimators  \\\n",
       "11             NaN                  8                 30   \n",
       "8              NaN                  6                 30   \n",
       "5              NaN                  4                 30   \n",
       "17           False                  4                 10   \n",
       "10             NaN                  8                 10   \n",
       "7              NaN                  6                 10   \n",
       "15           False                  3                 10   \n",
       "4              NaN                  4                 10   \n",
       "2              NaN                  2                 30   \n",
       "13           False                  2                 10   \n",
       "1              NaN                  2                 10   \n",
       "16           False                  4                  3   \n",
       "9              NaN                  8                  3   \n",
       "6              NaN                  6                  3   \n",
       "14           False                  3                  3   \n",
       "3              NaN                  4                  3   \n",
       "12           False                  2                  3   \n",
       "0              NaN                  2                  3   \n",
       "\n",
       "                                               params  rank_test_score  \\\n",
       "11            {'n_estimators': 30, 'max_features': 8}                1   \n",
       "8             {'n_estimators': 30, 'max_features': 6}                2   \n",
       "5             {'n_estimators': 30, 'max_features': 4}                3   \n",
       "17  {'n_estimators': 10, 'max_features': 4, 'boots...                4   \n",
       "10            {'n_estimators': 10, 'max_features': 8}                5   \n",
       "7             {'n_estimators': 10, 'max_features': 6}                6   \n",
       "15  {'n_estimators': 10, 'max_features': 3, 'boots...                7   \n",
       "4             {'n_estimators': 10, 'max_features': 4}                8   \n",
       "2             {'n_estimators': 30, 'max_features': 2}                9   \n",
       "13  {'n_estimators': 10, 'max_features': 2, 'boots...               10   \n",
       "1             {'n_estimators': 10, 'max_features': 2}               11   \n",
       "16  {'n_estimators': 3, 'max_features': 4, 'bootst...               12   \n",
       "9              {'n_estimators': 3, 'max_features': 8}               13   \n",
       "6              {'n_estimators': 3, 'max_features': 6}               14   \n",
       "14  {'n_estimators': 3, 'max_features': 3, 'bootst...               15   \n",
       "3              {'n_estimators': 3, 'max_features': 4}               16   \n",
       "12  {'n_estimators': 3, 'max_features': 2, 'bootst...               17   \n",
       "0              {'n_estimators': 3, 'max_features': 2}               18   \n",
       "\n",
       "    split0_test_score       ...         split2_test_score  split2_train_score  \\\n",
       "11      -2.357390e+09       ...             -2.591972e+09       -3.773239e+08   \n",
       "8       -2.370010e+09       ...             -2.607703e+09       -3.805218e+08   \n",
       "5       -2.387153e+09       ...             -2.666426e+09       -3.790867e+08   \n",
       "17      -2.525578e+09       ...             -2.609100e+09       -0.000000e+00   \n",
       "10      -2.571970e+09       ...             -2.842317e+09       -4.730979e+08   \n",
       "7       -2.549663e+09       ...             -2.762720e+09       -4.994664e+08   \n",
       "15      -2.757999e+09       ...             -2.830927e+09       -0.000000e+00   \n",
       "4       -2.666283e+09       ...             -2.892276e+09       -4.962893e+08   \n",
       "2       -2.689185e+09       ...             -2.948330e+09       -4.371702e+08   \n",
       "13      -2.810721e+09       ...             -3.131187e+09       -0.000000e+00   \n",
       "1       -3.047771e+09       ...             -3.130196e+09       -5.776964e+08   \n",
       "16      -3.134040e+09       ...             -3.440422e+09       -0.000000e+00   \n",
       "9       -3.353504e+09       ...             -3.402843e+09       -8.603321e+08   \n",
       "6       -3.119657e+09       ...             -3.592772e+09       -9.353135e+08   \n",
       "14      -3.618324e+09       ...             -3.554815e+09       -0.000000e+00   \n",
       "3       -3.730181e+09       ...             -3.734515e+09       -9.169425e+08   \n",
       "12      -3.785816e+09       ...             -4.061751e+09       -0.000000e+00   \n",
       "0       -3.837622e+09       ...             -4.196408e+09       -1.116550e+09   \n",
       "\n",
       "    split3_test_score  split3_train_score  split4_test_score  \\\n",
       "11      -2.318617e+09       -3.882250e+08      -2.527022e+09   \n",
       "8       -2.350953e+09       -3.856095e+08      -2.661059e+09   \n",
       "5       -2.398071e+09       -4.040957e+08      -2.649316e+09   \n",
       "17      -2.439607e+09       -0.000000e+00      -2.725548e+09   \n",
       "10      -2.460258e+09       -5.155367e+08      -2.776666e+09   \n",
       "7       -2.521134e+09       -4.990325e+08      -2.907667e+09   \n",
       "15      -2.672765e+09       -0.000000e+00      -2.786190e+09   \n",
       "4       -2.616813e+09       -5.436192e+08      -2.948207e+09   \n",
       "2       -2.619995e+09       -4.376955e+08      -2.970968e+09   \n",
       "13      -2.788537e+09       -0.000000e+00      -3.099347e+09   \n",
       "1       -2.865188e+09       -5.716332e+08      -3.173856e+09   \n",
       "16      -3.053647e+09       -0.000000e+00      -3.338344e+09   \n",
       "9       -3.129307e+09       -8.881964e+08      -3.510047e+09   \n",
       "6       -3.328934e+09       -9.009801e+08      -3.579607e+09   \n",
       "14      -3.619116e+09       -0.000000e+00      -3.449864e+09   \n",
       "3       -3.418747e+09       -1.037400e+09      -3.913907e+09   \n",
       "12      -3.675704e+09       -0.000000e+00      -4.089667e+09   \n",
       "0       -3.903319e+09       -1.112342e+09      -4.184325e+09   \n",
       "\n",
       "    split4_train_score  std_fit_time  std_score_time  std_test_score  \\\n",
       "11       -3.810005e+08      0.172000        0.009551    1.091647e+08   \n",
       "8        -3.901917e+08      0.221924        0.002579    1.285063e+08   \n",
       "5        -3.845520e+08      0.122772        0.017129    1.214603e+08   \n",
       "17       -0.000000e+00      0.295675        0.007139    1.088031e+08   \n",
       "10       -4.985555e+08      0.100974        0.002301    1.392720e+08   \n",
       "7        -5.055542e+08      0.077836        0.006335    1.471542e+08   \n",
       "15       -5.465556e+00      0.073931        0.001319    6.286611e+07   \n",
       "4        -5.160297e+08      0.039796        0.008723    1.268562e+08   \n",
       "2        -4.452654e+08      0.144397        0.002657    1.626879e+08   \n",
       "13       -2.967449e+00      0.043821        0.000978    1.539231e+08   \n",
       "1        -5.802501e+08      0.079333        0.005578    1.327046e+08   \n",
       "16       -0.000000e+00      0.097383        0.000550    1.879203e+08   \n",
       "9        -9.151287e+08      0.043096        0.000172    1.241864e+08   \n",
       "6        -8.624664e+08      0.020992        0.000224    1.893141e+08   \n",
       "14       -6.072840e+01      0.081226        0.000395    7.795196e+07   \n",
       "3        -9.707739e+08      0.027455        0.001225    1.631421e+08   \n",
       "12       -0.000000e+00      0.022286        0.000159    1.900966e+08   \n",
       "0        -1.129650e+09      0.034350        0.001114    1.519609e+08   \n",
       "\n",
       "    std_train_score  \n",
       "11     4.871017e+06  \n",
       "8      3.617057e+06  \n",
       "5      8.571233e+06  \n",
       "17     6.056477e-03  \n",
       "10     1.459294e+07  \n",
       "7      3.100456e+06  \n",
       "15     8.093117e+00  \n",
       "4      1.542862e+07  \n",
       "2      2.966320e+06  \n",
       "13     1.181156e+00  \n",
       "1      7.345821e+06  \n",
       "16     0.000000e+00  \n",
       "9      2.750227e+07  \n",
       "6      2.591445e+07  \n",
       "14     2.429136e+01  \n",
       "3      4.084607e+07  \n",
       "12     0.000000e+00  \n",
       "0      2.220402e+07  \n",
       "\n",
       "[18 rows x 23 columns]"
      ]
     },
     "execution_count": 269,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(grid_search.cv_results_).sort_values(by='rank_test_score')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Randomized Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 270,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomizedSearchCV(cv=5, error_score='raise-deprecating',\n",
       "          estimator=RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n",
       "           max_features='auto', max_leaf_nodes=None,\n",
       "           min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "           min_samples_leaf=1, min_samples_split=2,\n",
       "           min_weight_fraction_leaf=0.0, n_estimators='warn', n_jobs=None,\n",
       "           oob_score=False, random_state=42, verbose=0, warm_start=False),\n",
       "          fit_params=None, iid='warn', n_iter=10, n_jobs=-1,\n",
       "          param_distributions={'n_estimators': <scipy.stats._distn_infrastructure.rv_frozen object at 0x1a1f6500f0>, 'max_features': <scipy.stats._distn_infrastructure.rv_frozen object at 0x1a1f6503c8>},\n",
       "          pre_dispatch='2*n_jobs', random_state=42, refit=True,\n",
       "          return_train_score='warn', scoring='neg_mean_squared_error',\n",
       "          verbose=0)"
      ]
     },
     "execution_count": 270,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from scipy.stats import randint\n",
    "\n",
    "param_distribs = {\n",
    "        'n_estimators': randint(low=1, high=200),\n",
    "        'max_features': randint(low=1, high=8),\n",
    "    }\n",
    "\n",
    "forest_reg = RandomForestRegressor(random_state=42)\n",
    "rnd_search = RandomizedSearchCV(forest_reg, param_distributions=param_distribs, n_jobs=-1,\n",
    "                                n_iter=10, cv=5, scoring='neg_mean_squared_error', random_state=42)\n",
    "rnd_search.fit(housing_prepared, housing_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Randomized Search Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 271,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "49150.657232934034 {'n_estimators': 180, 'max_features': 7}\n",
      "51389.85295710133 {'n_estimators': 15, 'max_features': 5}\n",
      "50796.12045980556 {'n_estimators': 72, 'max_features': 3}\n",
      "50835.09932039744 {'n_estimators': 21, 'max_features': 5}\n",
      "49280.90117886215 {'n_estimators': 122, 'max_features': 7}\n",
      "50774.86679035961 {'n_estimators': 75, 'max_features': 3}\n",
      "50682.75001237282 {'n_estimators': 88, 'max_features': 3}\n",
      "49608.94061293652 {'n_estimators': 100, 'max_features': 5}\n",
      "50473.57642831875 {'n_estimators': 150, 'max_features': 3}\n",
      "64429.763804893395 {'n_estimators': 2, 'max_features': 5}\n"
     ]
    }
   ],
   "source": [
    "cvres = rnd_search.cv_results_\n",
    "for mean_score, params in zip(cvres[\"mean_test_score\"], cvres[\"params\"]):\n",
    "    print(np.sqrt(-mean_score), params)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 272,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The best hyperparameter combination found: {'n_estimators': 180, 'max_features': 7}\n"
     ]
    }
   ],
   "source": [
    "print('The best hyperparameter combination found: {}'.format(rnd_search.best_params_)) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Importance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 273,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([7.33442355e-02, 6.29090705e-02, 4.11437985e-02, 1.46726854e-02,\n",
       "       1.41064835e-02, 1.48742809e-02, 1.42575993e-02, 3.66158981e-01,\n",
       "       5.64191792e-02, 1.08792957e-01, 5.33510773e-02, 1.03114883e-02,\n",
       "       1.64780994e-01, 6.02803867e-05, 1.96041560e-03, 2.85647464e-03])"
      ]
     },
     "execution_count": 273,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feature_importances = grid_search.best_estimator_.feature_importances_\n",
    "feature_importances"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 274,
   "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>feature_importances</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>attributes</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>median_income</th>\n",
       "      <td>0.366159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>INLAND</th>\n",
       "      <td>0.164781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pop_per_hhold</th>\n",
       "      <td>0.108793</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>0.073344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>0.062909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>rooms_per_hhold</th>\n",
       "      <td>0.056419</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>bedrooms_per_room</th>\n",
       "      <td>0.053351</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>housing_median_age</th>\n",
       "      <td>0.041144</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population</th>\n",
       "      <td>0.014874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total_rooms</th>\n",
       "      <td>0.014673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>households</th>\n",
       "      <td>0.014258</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total_bedrooms</th>\n",
       "      <td>0.014106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>&lt;1H OCEAN</th>\n",
       "      <td>0.010311</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NEAR OCEAN</th>\n",
       "      <td>0.002856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NEAR BAY</th>\n",
       "      <td>0.001960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ISLAND</th>\n",
       "      <td>0.000060</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    feature_importances\n",
       "attributes                             \n",
       "median_income                  0.366159\n",
       "INLAND                         0.164781\n",
       "pop_per_hhold                  0.108793\n",
       "longitude                      0.073344\n",
       "latitude                       0.062909\n",
       "rooms_per_hhold                0.056419\n",
       "bedrooms_per_room              0.053351\n",
       "housing_median_age             0.041144\n",
       "population                     0.014874\n",
       "total_rooms                    0.014673\n",
       "households                     0.014258\n",
       "total_bedrooms                 0.014106\n",
       "<1H OCEAN                      0.010311\n",
       "NEAR OCEAN                     0.002856\n",
       "NEAR BAY                       0.001960\n",
       "ISLAND                         0.000060"
      ]
     },
     "execution_count": 274,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "extra_attribs = [\"rooms_per_hhold\", \"pop_per_hhold\", \"bedrooms_per_room\"]\n",
    "#cat_encoder = cat_pipeline.named_steps[\"cat_encoder\"] # old solution\n",
    "cat_encoder = full_pipeline.named_transformers_[\"cat\"]\n",
    "cat_one_hot_attribs = list(cat_encoder.categories_[0])\n",
    "attributes = num_attribs + extra_attribs + cat_one_hot_attribs\n",
    "# sort features in df\n",
    "(pd.DataFrame({'feature_importances': feature_importances, 'attributes': attributes})\n",
    " .set_index('attributes')\n",
    " .sort_values(by='feature_importances', ascending=False))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Median income is the number one predictor on housing prices. Using the information above we can decide to drop certain features. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluate Test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 275,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_model = grid_search.best_estimator_\n",
    "\n",
    "X_test = strat_test_set.drop(\"median_house_value\", axis=1)\n",
    "y_test = strat_test_set[\"median_house_value\"].copy()\n",
    "\n",
    "X_test_prepared = full_pipeline.transform(X_test)\n",
    "final_predictions = final_model.predict(X_test_prepared)\n",
    "\n",
    "final_mse = mean_squared_error(y_test, final_predictions)\n",
    "final_rmse = np.sqrt(final_mse)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_model.score(X_test_prepared, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 277,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "47730.22690385927"
      ]
     },
     "execution_count": 277,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_rmse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 278,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "prediction \t actual \t\t error\n",
      "495467 \t\t 500001 \t\t -1%\n",
      "262676 \t\t 240300 \t\t 9%\n",
      "235380 \t\t 218200 \t\t 8%\n",
      "211883 \t\t 182100 \t\t 16%\n",
      "135516 \t\t 121300 \t\t 12%\n",
      "147776 \t\t 120600 \t\t 23%\n",
      "63540 \t\t 72300 \t\t -12%\n",
      "439026 \t\t 500001 \t\t -12%\n",
      "106323 \t\t 98900 \t\t 8%\n",
      "100293 \t\t 82600 \t\t 21%\n",
      "369053 \t\t 399400 \t\t -8%\n",
      "81756 \t\t 78600 \t\t 4%\n",
      "279346 \t\t 212500 \t\t 31%\n",
      "205150 \t\t 174100 \t\t 18%\n",
      "221203 \t\t 258100 \t\t -14%\n"
     ]
    }
   ],
   "source": [
    "# print percent error for subset of data\n",
    "print('prediction \\t actual \\t\\t error')\n",
    "for pred, value in zip(final_predictions[:15],y_test[:15]):\n",
    "    print('{} \\t\\t {} \\t\\t {:.0%}'.format(int(pred), int(value), (pred-value)/value))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 279,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "18"
      ]
     },
     "execution_count": 279,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# average abs % error \n",
    "int((abs(final_predictions-y_test)/y_test*100).mean())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.6"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "256px"
   },
   "toc_section_display": true,
   "toc_window_display": true
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}