{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Machine Learning project \n",
    "\n",
    "This notebook is a short version of the [end-to-end Machine Learning project](https://github.com/ageron/handson-ml3/blob/main/02_end_to_end_machine_learning_project.ipynb) provided by Aurélien Geron."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This project requires: \n",
    "\n",
    "- Python 3.7 or above\n",
    "- Scikit-Learn ≥ 1.0.1:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import sys\n",
    "from pathlib import Path\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pandas.plotting import scatter_matrix\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import sklearn\n",
    "from sklearn import set_config\n",
    "set_config(display='diagram')\n",
    "\n",
    "plt.rc('font', size=14)\n",
    "plt.rc('axes', labelsize=14, titlesize=14)\n",
    "plt.rc('legend', fontsize=14)\n",
    "plt.rc('xtick', labelsize=10)\n",
    "plt.rc('ytick', labelsize=10)\n",
    "\n",
    "# Check if you have the correct versions\n",
    "assert sklearn.__version__ >= \"1.0.1\"\n",
    "assert sys.version_info >= (3, 7)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Welcome to Machine Learning Housing Corp.! Your task is to predict median house values in Californian districts, given a number of features from these districts.*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing = pd.read_csv(\"https://raw.githubusercontent.com/kirenz/datasets/master/housing_hml3.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Overview"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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",
      " #   Column              Non-Null Count  Dtype  \n",
      "---  ------              --------------  -----  \n",
      " 0   longitude           20640 non-null  float64\n",
      " 1   latitude            20640 non-null  float64\n",
      " 2   housing_median_age  20640 non-null  float64\n",
      " 3   total_rooms         20640 non-null  float64\n",
      " 4   total_bedrooms      20433 non-null  float64\n",
      " 5   population          20640 non-null  float64\n",
      " 6   households          20640 non-null  float64\n",
      " 7   median_income       20640 non-null  float64\n",
      " 8   median_house_value  20640 non-null  float64\n",
      " 9   ocean_proximity     20640 non-null  object \n",
      "dtypes: float64(9), object(1)\n",
      "memory usage: 1.6+ MB\n"
     ]
    }
   ],
   "source": [
    "housing.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<1H OCEAN     7274\n",
       "INLAND        5301\n",
       "NEAR OCEAN    2089\n",
       "NEAR BAY      1846\n",
       "ISLAND           2\n",
       "Name: ocean_proximity, dtype: int64"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing[\"ocean_proximity\"].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>longitude</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>-119.573125</td>\n",
       "      <td>2.000624</td>\n",
       "      <td>-124.3500</td>\n",
       "      <td>-121.8000</td>\n",
       "      <td>-118.5100</td>\n",
       "      <td>-118.01</td>\n",
       "      <td>-114.4900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>latitude</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>35.637746</td>\n",
       "      <td>2.133294</td>\n",
       "      <td>32.5500</td>\n",
       "      <td>33.9300</td>\n",
       "      <td>34.2600</td>\n",
       "      <td>37.72</td>\n",
       "      <td>41.9500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>housing_median_age</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>28.577156</td>\n",
       "      <td>12.585738</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>18.0000</td>\n",
       "      <td>29.0000</td>\n",
       "      <td>37.00</td>\n",
       "      <td>52.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total_rooms</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>2639.402798</td>\n",
       "      <td>2185.287466</td>\n",
       "      <td>2.0000</td>\n",
       "      <td>1447.0000</td>\n",
       "      <td>2125.0000</td>\n",
       "      <td>3154.00</td>\n",
       "      <td>39320.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>total_bedrooms</th>\n",
       "      <td>16344.0</td>\n",
       "      <td>538.949094</td>\n",
       "      <td>423.862079</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>296.0000</td>\n",
       "      <td>434.0000</td>\n",
       "      <td>645.00</td>\n",
       "      <td>6210.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>population</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>1425.513929</td>\n",
       "      <td>1094.795467</td>\n",
       "      <td>3.0000</td>\n",
       "      <td>787.0000</td>\n",
       "      <td>1167.0000</td>\n",
       "      <td>1726.00</td>\n",
       "      <td>16305.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>households</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>499.990189</td>\n",
       "      <td>382.865787</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>279.0000</td>\n",
       "      <td>408.0000</td>\n",
       "      <td>603.00</td>\n",
       "      <td>5358.0000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>median_income</th>\n",
       "      <td>16512.0</td>\n",
       "      <td>3.870428</td>\n",
       "      <td>1.891936</td>\n",
       "      <td>0.4999</td>\n",
       "      <td>2.5625</td>\n",
       "      <td>3.5385</td>\n",
       "      <td>4.75</td>\n",
       "      <td>15.0001</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      count         mean          std       min        25%  \\\n",
       "longitude           16512.0  -119.573125     2.000624 -124.3500  -121.8000   \n",
       "latitude            16512.0    35.637746     2.133294   32.5500    33.9300   \n",
       "housing_median_age  16512.0    28.577156    12.585738    1.0000    18.0000   \n",
       "total_rooms         16512.0  2639.402798  2185.287466    2.0000  1447.0000   \n",
       "total_bedrooms      16344.0   538.949094   423.862079    1.0000   296.0000   \n",
       "population          16512.0  1425.513929  1094.795467    3.0000   787.0000   \n",
       "households          16512.0   499.990189   382.865787    1.0000   279.0000   \n",
       "median_income       16512.0     3.870428     1.891936    0.4999     2.5625   \n",
       "\n",
       "                          50%      75%         max  \n",
       "longitude           -118.5100  -118.01   -114.4900  \n",
       "latitude              34.2600    37.72     41.9500  \n",
       "housing_median_age    29.0000    37.00     52.0000  \n",
       "total_rooms         2125.0000  3154.00  39320.0000  \n",
       "total_bedrooms       434.0000   645.00   6210.0000  \n",
       "population          1167.0000  1726.00  16305.0000  \n",
       "households           408.0000   603.00   5358.0000  \n",
       "median_income          3.5385     4.75     15.0001  "
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x576 with 9 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing.hist(bins=50, figsize=(12, 8));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing[\"income_cat\"] = pd.cut(housing[\"median_income\"],\n",
    "                               bins=[0., 1.5, 3.0, 4.5, 6., np.inf],\n",
    "                               labels=[1, 2, 3, 4, 5])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing[\"income_cat\"].value_counts().sort_index().plot.bar(rot=0, grid=True)\n",
    "\n",
    "plt.xlabel(\"Income category\")\n",
    "plt.ylabel(\"Number of districts\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Stratified split:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "strat_train_set, strat_test_set = train_test_split(\n",
    "    housing, test_size=0.2, stratify=housing[\"income_cat\"], random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Drop the variable \"income_cat\" from our datasets:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "for set_ in (strat_train_set, strat_test_set):\n",
    "    set_.drop(\"income_cat\", axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exploration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing = strat_train_set.copy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Visualizing Geographical Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", grid=True);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZAAAAEKCAYAAAA8QgPpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAACpyUlEQVR4nOz9eZRd13nYif72me98b80DqjAUAAKcAJCgSJESRUqWo0SSnXjZsZN2J046rSS9Xp5fJ35x3O7XGTpZcXeG7qykX9JOOq+Ttt2KPCi2Jcu2bImiKJEiQQLEQMxDzfOdhzPv98epKtRwq1AFFMAB57cWFqpu3XPOPudWfd/+ZiGlJCYmJiYmZqco7/cCYmJiYmI+nMQKJCYmJibmrogVSExMTEzMXRErkJiYmJiYuyJWIDExMTExd4X2fi/gbujq6pL79u2779dpNBqkUqn7fp0PGg/jfT+M9wzxfT9svP322wtSyu7dOt+HUoHs27ePU6dO3ffrvPLKK7z00kv3/TofNB7G+34Y7xni+37YEEKM7ub5YhdWTExMTMxdESuQmJiYmJi7IlYgMTExMTF3RaxAYmJiYmLuigeuQIQQqhDitBDia0vf/xMhxCUhxFkhxFeFEPkHvaaYmJiYmJ3zflggPwtcXPX9N4HHpZRPAleAX3gf1oQfhDRdHz8I34/L3zUf1nXHxMR8+HmgabxCiD3A54F/BPxNACnlH656yxvAjz/INQEs1GzenagAYOoKTwzkySX1B72MHVNuupyfqhAEElUVH5p1x8TEfDQQD7KduxDiN4B/DGSAn5NSfmHdz38X+E9Syl9pc+yXgC8B9Pb2Pv3lL395V9bkh5JS00UAihAYqgIC0qZGvV4nnU6veX8oQRH3ft3dOE/d8VGEQAiQEkIpSZv3vidYvu/dutcPA+0+64eB+L4fLl5++eW3pZQnd+t8D8wCEUJ8AZiTUr4thHipzc9/EfCBX213vJTyl4FfBjh58qS8lyIg2/Wpuz6WqvDGrSLF2Tq5pEEoJQ0pGcgl+NhIJ29+/7WVYqN72e37QYgbhBiqQt3xd8VqaLo+b90s0pEyV16bq9k8PpQjnzDQ1Lv3Tv7xt76NtuexD51ls/o57/T+H9bCsvi+Y+6FB+nCegH4ESHEnwIsICuE+BUp5U8LIf4i8AXgM/I+m0SjC3W+cWEGzw9x/ADCkLmah6ErJE2dtKkykEtElsgSfhByfqqCpamYlorjB5ybKvPc/s47CqrVikcALT+gM2Xu+DzrMVQFVRU4foCpqSzWHa7O1RCAcQ9uOD8IaXkBuW3c670I7Hs5th13o+BXryEmJmbnPDAFIqX8BZYC5EsWyM8tKY/PAT8PfEpK2byfa7Bdn29cmCFtaiy6Dq9cnmNsoYllKHSlLbrSJl0Zk598ZmiNUHODkCCQmJYKgKmpNBwfNwi3FH7rFU/Fdrk+2aD3YGJH52mHpkZK4p3RIqPNOmMLLZ4cztOdse5JMblLwXhT2/pe78Ui2+3Yzd0o+PVrCMJ4MmdMzE75IGy9/hVRTOSbQogzQoh/c78uVHd9PD9EEfCda/NU7YAQcH3JbNWmarvkkzoJXV1z3OrdPoDjB6iquOPOdUXxLAnjtKEhhaTueDs6z2aUmw7vjJV45dIcp0YXOTNWptL0MDWVIJArymAnLK9lq3tdLbA7UiaWpnJuqrytTLB7OXYz1j/nO91/uzW0vCDOZIuJ2SHvSzNFKeUrwCtLXx98UNdNGxq6pjBXcag0PBQBQggylo4dBGQtg3LDww/XCpLl3f65qTINx1/ZNd9pd7/ezeSHkkM9GQIpKTacbZ+nHbbr8/Vz09Qdn56MxVzN5XvX5yk3XV460oOpK3elmDRVIaGr2H6w6b3erUV2r8e2ww/CSPALVp7znRRzuzUsv74b7rSYmIeFD2U33rvFMjQ+//gA/+nUKH4QEkpJLqETSokMJZqi0J+30JSNQiSX1Hluf+eO/PaaqnC0L8vp8RIKAkNXeHZ/JylTvWf/f931sb0AVVEoN1wGCkkmSg1qtsd70xX+/Mf23vW5VUVsea/rFeNOLKl7OXY9q91Qjh9iew6Wpt5RMbdbw/LrMTEx2+ehUiAAQ51J/tqLI6RNne9enWOi5OD5AXs7khwbynF0IEfSuP1Y1gd7dyKUy02XizNVBAIJHO3Lrvj673WnmzY0LF2l2HBxgxBdFeQSOof70xzqzpAw1DufZAu2ute7tch2euxWgfZ2cY+m43N8OE/S0LZcS7s1JHQ1tj5iYnbIQ6dAANIJgz/3sb2M9KSZLDaYr7vs60rTmzE5NlRYESRBKHnj5uJdp+4uC7icZeD4ARdnqjsKbG8lQC1D44tPDvLrb49xfa5O0w050JNCSoHk7uMq213P3Vhky2zn2DsF2jdzhW1Xya9fw2sTD0nBS0zMLvJQKhCIBMjLj/TgBiEKEMIaYbaTdNZ23Kuvf1mAul5IiOTEUIHOtLnmPUOdSb70yQMM5hPM150Vy0lyO6Not9JlNxPod3vOrQT9drKqdsMVtlOLMiYmZi0PrQKBrQXIdtNZN+NeBNyyAPX8kKmyTcvzuTZX5yeeHtqgRBRVoS+X4JG+HF4QoqsKlVbk1qo7PqdHS9Qcj4yp89TejruuDbnbOpi7YTvK917caMv3tJt1KDExDyMPtQJpx7JgWRYpqxWA4HbWz52Ezr0IODcIcb1IeeiqQsq0WKjbnBkv86nD3WvOsayo/DDE0m8rKgX444uznB4rAVGbk9mqzZ8+MYhlrP3Y7yRMdztz6k5sV/mudkMtW5Hb+WzaWVMxMTE7J1Ygq1gvWExNWUlntZcydU6Plde4cLYSvncbJzBUhRBJy/NJmRZuEGAZ7VNNN1NUVdvle9fm6c5YKAjGinW+emaCpKHwqUf6ViyR7QjT3cycgjsrrJ0oX03dWXuYzaypmJiYnRMrkCXaCZayH/LJ4QJuEHJ6vEzK0FYE6LmpMkf6MlyaqW0puLbrZ18vVE8MFbg2V2ehbmMZKsP5FKrWPtV0vaKqOz4/uFlkrurgB1CzPRYaLjXb5Y8uzuP68KefGgTYljC9V3fRarZbhb5d5btT99pm1lRciB4Ts3NiBbLEZsVlIUspt3JtPKTS8jgzXiafMO45LtBOqHamTX7i6SHOjJcBUDW2FNrLimpZoHakTIY6k8xVHS7P1kjrCqaq0fJ8fufdSU7uy9OTS2xbmN5L1tUyOxX221G+O3WvbWZNyTgJKyZmx8TRwyWWBUtzqUCv6forr7drZQKgILbdPmMztmrt0Zk2+dThbj4+0slz+zs37NTbDZNaFqhZy+Azj/SRNBQcN6DqBQhF0rADyi2XH9wsoUDbFi2btXDXVOWONRZbsdOWI9thp21mlq0p2w8oNhxsP4hjIDExd0lsgSyhqQrD+SS/d2Eazw/RNYUR7fYOeL0L5/hQnosz1XuOC9xpB73ZLnwzV9BqgdqVMTjSm2Om5FBuuViaRtXx6M1azFRbuEHY1jV1euLen2c7thNL2Wl21N2413bDmoqJiYkVyAp+EDJWbnJiKI+iCMJQMn/11kpWTzuhsxtxgbsJUN/JFbR6XUIIfvSpAb5yagJVAV1VeXIwj77UruVBCtM7PbO77dJ7t21mYsURE3NvxAqESCCXWy6OF5LLWGt+tr72YLXQ2Uxw7WQXfTeK6E5Wy/K6lt1b05UWh3ozLNYdutImKUtlqCO5Unj4IIXpVs/sXmpNYoUQE/PgeegVSLnp8u5Emabtc3WuTrXDpSdjrYyJvZNIWi+47mYXvdMd9HasluV4ha6qKIrCoZ4Mphb1yzrQnebp4Y4112k3XOl+Fdu1E/b3o0tv7KKKibm/PNQKxA9C3rixwFTZptxwef3aPHMNh7ylMVBI8tmOkDdvFjk2VNiWK+VedtHb2UGvForbsVrcIMTUFJ4aKuCFISf35VlsuJzcWyCbuH0/7YYrbUcRLo8GThvahuLEnXK/uvR+mEbyxsR82HioFUjT9bkx1yRtaXzv6hyXZmo4PsyoDtNVhxdSUQNE2w/59JGebaWUul6IqaoEodzR5MI77ZbbCcWtrJbVczL8UKIrKnXHw9LVDd2GN9S/eAFnx8skTW1TRXhlusLvnp0iCCFj6nzh2ABDncntPvq2974bMaUH3XYlJuZh5qFWIH4YUnVc3p2Y5/REjeVkUj+AubpPww2ZLLWoOz7PHeggmzC2PF/T8bkyV0MVgoSusacjgXaHXfR2dstbCcVkm53/+jkZC7U6sxUXKaKBVg0nIJeM1tTOdRRKScsPKKTMlddWK8LLM2X+x69dpO4GGIrCUGeC3zo9wV998cCOLJGdKsXt8KDbrsTEPMw8tH9R5abLO7fKfPu9Gf7gvSLtKhG8IKTl+MxWnA1TCtfjByGXZmsc7c1hGSoNx+PsRJlDPekNsYbl4Padxrsuv7fp+nesn1h+r+36a86ZS2jMVVyODGR4erhALqGvuUa7OgpFCBJLbqQgDKnYLmLpvbbr87Uz0zTcgO60SdrSmK60uLlYp9zytv38N7t34J5qTe52/HBMTMzOeSgtkOXYx2+8Ocrl+daW752qNDm+t7PtlMLVLO98O9ImiiK5Mlej5UnOT1axNI1cUt+w4x7pTm+6Wy63XM6Ml1EQSwIx3DQ+sPq8XhjiepJcR2QtKYqg5njcmm+iKKApCh0pfU2dSbvhSseGCrxxc4Frc3WEFIz0pmg4AV4Y4EvQVYVASgxNpWa7SF9iaNsv575flsJutl2JiYnZmodSgTRdn3fGinz3SnHL9wkBacvgkd7MBlfR+rjF6kr20cUWpqZiZFTSZrSzPjlc2OCGujpTazvLu9p0+eo7U4RCkjY19namkEiajr9BKK53bzVdn9NzJXJJDUNTqDZdbi7W8IOA4Y40CMlYqbnG9Gw3XCllqli6yrE9eRJ61ALlzESJp4fyZE2doY4kM5Um9aaHH8Lzh7rIWlu7+Faz2w0aVxMXCsbEPBgeSgVSaXpcnm7gbvEeTYClqWR1nWf3r0153Sxu8cRAnrdGFyk1HfIpg4NdkeIpNhzqy26odTvuwz0Zri/UVxTD0b4s37u2wFi5QcbUKTVdXC9kpCfN8eH8irJaXs/6nXzS0OhMGbx1q8hcucVbo0VmKzYIyFo6nz3az1P7CtTd29P72gXx3SAECYoQXJyu4ochTSfgcG+GLxwb4NffHsP1AhDwiUNdfO6xgR0J6p1aCndTob5yH6u+j4mJ2T0eOgXiByE3Fhsc6k3xvasL+G3eYwl4fChDxmrx4nA3mVUpr1sFtHNJnU+MdCEQpM0o22l5Z502tA07bgSkTJXjgznsICRtaLhByGixsdL5FwE3iw32dSbbxgbW7+SbrsdEqUmt5fHHl6aZrUcCVAAt1+Ub700ihEQAmaTO/s4UY6XmhnbuhqqAgEuzVVKGjq4JQiRXZ2o8Opjl+HCBA10pDF3l2TZ9urbDdi2Fu0nLjVN5Y2LuPw/Vtmy54twPJC8d7uXZkULb93WmdYY70iQMlULaWONWuVNDQMvQOLm3Ay+Ua5r1WYa2ponfQt3G8UK+e3WB//jGGN+9PM8PbhWp2B4qCnsKSfxQ0rA9fF9yZDDbNlXXDUKO9mVXzltp+VSbPn94YWpFeQBIwJMwU/X5/o0F3rhZ5OxEmd86PYGuKOQSBkg4M1FaOWYon6Th+rS8KDZxtDeHF0rOjJfJWjojPVl6MhYXZ6prGjruhDs1aLxTosFuHRMTE7NzHhoLZPWM8atzUbbUn392L1PVFjfnbeC2Nl1serT8qCvv0b61gnt1rEMRglDKDb77zXbWq1uMnBkrY+oKZ8bLzFVbTFds9nYkaNo++7qTzFRsujMGrq9xsjNJfzbR9n6Wd9hH+7IkDJV6y+P/fuMmk5V2tlVEsWFjaiqLNYday+exPo/ZWn3FTXUgDHjj5iKuF6Kh0J+z6M1a+KEEb2MX4oYTZYqtd6/thM1cVO2C7ZWWR7nlkk8YH4gJijExDysPhQJZvSPNWQaKIrg4U6E7ZZA1DVKGgyoUHD/ADyCUkNQVTE0hsTQJcJl2XXs///hG/3+7yvJlIQmRRSAlTJZscgkDxw8xNY2bC02+eLyflKnhuAGmoXJ8T2FDKvB6N9rFmWpULKcJGrbPVvOR5ushpYZDNqkTSLg6V6MzbaFr0WjcWtmnoAhyGQtFEVyaqaKpCqautO1C3PIihSjhrtxFW7mb1rvoFusOl2dquF5A0tJ4fCBHwlDXKJ77GaCPiYm5zUOhQNbvSDtTJod7MjzSl+b8ZIXRhQYNNyAMo8wrAUwUbURuo9Bp17V3tNSgP29tubtdLSSjzKsQAUhkVGMiJAEhoQzJJXReGOlquyNfdsO5XkhuKetp9Q4bwDLVdktYQQKvXp3luX1dfPxQN8WGQ8uLAtkjXRnmy1H67+pn9eRQbmXHvzr4jQBFKFHVurbzyu87VY6vvl6l5XF2ooSmKowWWzRsj7dvRa1mTD16X8pUV9x6F2eqcSpvTMx95KFQIO12pIau0JtN8Bee38+l2RqnbpVQFVAFdGcshBAY2uZN/3KrUlaLDWeDe2R9c8L1QtL2HIJQUkgaTFdbCAR126cna+IFsq0Fs6yEnCU3nKIIOlPmmh227Uapx3lLpWwHmz6ThhMwW2vx1N4c81UXZSnQ7/ghQkC4NJZw+VktB/hhrYvOD0JOj5U3uLS26y5afp6aIbB9H11RVmJK611/C3WHUzcXmS07FFsupYaLpas8OZTH0lRevzFPUtdWLKFlt16cyhsTc394KBRIu5TRo31Z3CBkqCPJ3/vio/zib51D11VyCY3OtIXjhWjK2kTf1f2ltnKPbKdg0NJUTgzn2d+V4qunJ9BUhWzCYG9n8rY7ahO3Vc4y0ITCxZkKh3syGEu772WlM9iRYLAjgTfXoOG3d2YZukpP1uLmfJNnD3RycaZKpeWhqoJ8Ql9JAlBVwXA+yamx0gYX03IK8HbdReuVqhuEhEFIpeVydba2cr6erLUhu0NTFVqOx4WpCo4fnUNVBC0v4PpsnRPDBS5N1TmxL09H0lzr1ouVR0zMfeGhUCCwdtfcdHwuzlTXBKB/6mP7ODW6iKIIBPDCSBdqrbxy/Pr+UrbnYC2l2R7uyay8r51LZrOCQdcPub7QQBGClKEz0pUml9TbWjTr3XAdaYNDcq1rCaI6kKf2FBhfaLJYczE8n5K9NvvIVCFnRS4nRUDCUNcVEior3yvAqbHStlxMW7mLyk2Xs+NlWn6A6wVIBFJKJsstinWXuuvTnTEpNz2qLZ9cUuf4nttdkP0g5Np8g86UxUzNRiKo2tF0xabr84Nbi4yXGxQWdIwelbSlbbCE4hbvMTG7y0OjQOB2Mdk7s7UNAeiXj/bQmTaoOR4ZU+fJoTzvvnVtJfVzvVJoOj77u5LcXGhyZbbG9YU6Twzk0TWxRtBriqDlBzzWn+NWsbHGAro4UyVtqnRkTARwa7HBIS3ddgffzg1n6sqGTCRNVfjYgU4uTFUoN12mKw10TaFU91EUCIG0oeD5IaamcmOhyTP7A5JpbcN5NFW53Ydri4ymO9Vz+EHID24uMllu0XR8To+VyVk66YRGRte4vlCnP2dxYarKxw90oqsKqhBrFJUbhCiKwiP9GVq+j6ooGJogk1CZKkcDs470ZVEVwfX5Ood61z7HuC4kJmb3eagUCGye4pkwVD55uHuNhdJ0fd64ubjGBRWEEimjIPiVuQa5hL4meHxyuLAi6F0/5NJsFdsJsXR1TcZQ0/Vp2j492QQHuzJcW6hRbjrUHJNn9m50u+ykcjthqDy1t4M9+QS/+uY43RlBdybA8wPGF1sstkJUQv7gvWk+82gv37s2zw8/2te2k+52M5q2mmfSdH2uzdXpSBpMllpYmkrD9QHJpekqXiixNBUZSkYXGvTnExiqQssLVhSVsZQFdrQvB8D1uToJXeHjI10IITjQlaLlhm2fY9ziPSbm/vDQKZCtBOJ6C0VVBJamrrigFuo2Y8UmdcfHdUOGO5N0ptZmQoXAEwN53h0vcW6qQkJXOTFcQNfEik++7vicHS9zdb7ORLnF0b4ch3vS1J2AF0Y6N22Jvt3K7eV7LDZ9+nIWpqYQhJJzE2VaUQgHgEoz4DvvzdGyQwSC5w920Zk215xrfRYUwPGhnWc0CSnwZZR5Zmgqbiuk4ngEoaQ/ayGQzNZsFuoODTdgpmrz1HBhRVEtr+Pd8RJ7O5Ps7UrwxECerrTJqbESfihJW1rb5xjXhcTE3B8eur+eZUG0XLm9XCm+LEiabtSwUFtKYzU1FQkc6Erx7kSZSzNVbi40uFVs8J2r85y6VaRu+2sUUS6pc3w4z6HuNMf2FNBUgbaUXdRcareeNDWeGuoAAafHSth+yMm9HXecp3Gnyu3l9xzuyVB3PTw/ZKZqU265FJsOKqAroAgIgMWmz0S5wZXZGl95c5zFurPhfLmkzpG+DJKoBcrFmSqV5trW7avb1K8naWiM9KZwliyKhKFQSBmkDB1ENGa3L5cgZWp0ZSw60waqgNFiY835JBIpQBWCpKGTsYwNFf5eKDc8x7jFe0zM/eGBWyBCCBU4BUxKKb8ghOgA/hOwD7gF/FkpZWnzM9w7m+3kl+ejX59tMFlu0RveFjYpI7JI9uZTnJsuA4K641G1fd4ZL/LEQI5jQ7cL/pKGRojk3YnSSsX6YCGqJl/eDZsaPDVUYLZmc2Iov2bM7L1SSOpkDJ1nDnRQarjMVltRa3hFrrQ1gUiJzFQcpitRW/tXr86xvsGLH4RcmqmRTxhtaz3uFF/QVIXn9ndhKAopU2ex5rKnkGC83OTTj/Sw0HSoNFwSmsqnDvWstIWfr9nUXR/L0FbcUClDW8myWt2DbCvLLG7xHhNzf3g/XFg/C1wEskvf/x3gj6WUvySE+DtL3//8/V7Eep/9agF1YrjAxZlKFKdwfI4NFRBCAoLpegtVUUjoUTwkaagMdyQ5PrxRAShCue0vEiAQG1xofihJmVrbyYL3Qgjs7UpSbHgkdJWutMliw+G9ydqa+hAFaLk+r99YpCtt4AYhX+xZa0Vs5QKCjQkG7eILEomiCjqTBn0ZiyMDWT6pdnNxpkomoePmfYRQcAOf2ZpPreVi+8GK1XAnN9SdZsrHLd5jYnafB6pAhBB7gM8D/wj4m0sv/yjw0tLX/wF4hQegQNazWkCZGjw13MFYXVlRDH4QsrcjyeRS59qmDBjIJRACzHVzxpfPZ2oKTw0V8MIQXVGotLyVGMlu74bbzSfJJnU60+aKBdSbsXgjP8/vn5/BC0IUAV4AtheStcBUNKq2T8sN8FfFB7aKG20nvtDOerg+X+e5/Z1rhPrB7jr/+jvXsJ2AhhdwqDvDb5+e4iefGSaX0BFAxXZJGxp+uLEH2Z1ot2lYXZcSExOzM4SUW3VN2uWLCfEbwD8GMsDPLbmwylLK/Kr3lKSUG9rkCiG+BHwJoLe39+kvf/nLu76+uhM1SBQi6lPl2U1y2ds1HkEoKTZcQikJQtDUyLzoSBkrMZOtzhfKaEDUMqGMYhH3ShBKWt5tqyKhR+62dq9LCROlJg3XZ/VHrypR5b2pqWRUn0wms2Zty+cKpYxG3i5dQ8ql+1Si2SGb3WfT9VFXndAPJAlDXXluQSipOT7VpoezVH+iLRULZiyNlKnRdH0cL7J6TF1dcSvuxjOTbotMJrPFER9N6vU66XT6/V7GA+dhve+XX375bSnlyd063wOzQIQQXwDmpJRvCyFe2unxUspfBn4Z4OTJk/Kll3Z8ijtSaXqcmyqv+PKdsfOsvo4fhMxUbC5MV2jaPhOVFvs6UlhpY4Pf3w9C5msOV+ZqIO+uyeB28IOQN24uktPUFevA9oMVF9J6y+TabJV/8P97i5rj0vJCwjAS8AM5g85Mgpce6SEfjPHiiy+uOb7p+Lw3VaXlByQ0lccGc7h+yIXJCuVqk+myzUh3hnzK4PhQfk021/IaraU1LtYdLs1WOdyTQdMVjvZlOT9VYW66ypuzRSbLNpaukDJVUqbOkVSaR3tz9CaMpRTqaJbKCyNdbefNQ2Q1hUv/r7fubNfne9cX6TZVkoaO4wfMXH6HT3zyxYfOtfXKK69wP/6WPug8rPe92zxIF9YLwI8IIf4UYAFZIcSvALNCiH4p5bQQoh+Ye4BrWkO70a7LrA4UG4qCoyp8bF/HigDaLKgsgEN9GbrT5qbuk3sRWjuJDfhByKnREklTQdcTlOsOjh/ihSEhgu60wf6uJIli1JBwoW5zZrTMQsNhtNjgqeEO9hRSLNYdvvLmOLeKFd6+vkDDC9EVlXzW4qdO7uWiXl2jLNenAl+dq3GkL7vSx+v0eAnXCwFBd9piumLjBQF+qFJI6PghVJsu81UXPwzXzHWHyLqptDxOj5W4MdfEDXxMXeNQT4ZsUluzlnLT5dRokYtT1ZWpkWnrdrrvw6ZAYmLuhQemQKSUvwD8AsCSBfJzUsqfFkL8E+AvAr+09P9vP6g1tWOzNuyrA8UV22ViusVwRwq4c1D5+nyd7lU78u0omK1YrXx20rrcDUIypkbC1NF9n0UpkYQkdJWXD3eRSRgc7k5zbTbgjy7M8PsXprk8XWF80UECX09P8FdffgQp4K2b83zr6uqZ8iGTVY8/Ss7wV148wLvjJY4P51dSjpeVc7nlIoi6/C4/OwWxdO8SXRMM5BJUbIeMqaIogsN9KSZLNtmETi5hULNdri80eLJmc366ytW5BldnapRbLoP5BJWWSy5pkE/odKYzK8p9+bPJmDqFpAlIri3UONwTuTLiWEhMzM74IBQS/hLwFSHEfwWMAT/xPq9nA+t3+WlDQwpJ3fGWZnlsP6i8Whm5RJXq5yerPLYnu6b302a0S5ndKii/XtlomsLBrhR/cGGGphsuCXOdd8YrDOYT/PL3bvLxRMB7YyW+/d4crVUJWVP1gL//u+9xcl+W07eqG9YWAGfGFpgq9TFbd7GXZnasbr6YTxgYurKhM/K+rMV701H7lbrn0ZU2Ge5I8+RQjhPDBU4rZRabDjPVFrNVm4Sm8punJ9EVlawVxUdsN6Rh+yhCpdL0aXkBiiIIvNtzWKJOyhoj3Wmuz9cpNx3qTkBCV2PrIyZmh7wvCkRK+QpRthVSykXgM+/HOrZLu9TbQz0ZAnm7Y+1qob2VRbC6ffnFhTopQ0Mh2ND7qR1bteTYrK5l/dTCMJC4QUAhpaMKF1PXMHWB60dFfhlDwwtCXr06v0Z5LBMC79yqtp0lD9D0okLDwUKKzrRJyw94d7zE8we7Vu5//ayO5e8/fqCT5w500nR8HD/k2f0dZBNRpX82qZFLalycqXKgK4UfQMP1mam1OJRIo2kqqhrghqCpEi8I0UQ0r2X181/+bNKWxqHeNDXH5IWRTt6Y3YVshpiYh4wPggXygaddIdqz+ztXhhetFtp3KlpbVkb1pSaFKFGVetrUqbTcLf3wW1k366vT2ymbM+NlfCkxNG1pBrrA8UMW6h65hE5n0kTTBNJjZcfejs2H5UJSB11R2VNI8t5Sx+OGG805WWi4G0bwrrbalmespIyoI7G16p6eGMhzarRIywmwkhqHe1Ncn68zXWkRSuhJmziej+eHJAwVU9XozVl4oVzz/Nd/Ns/s3bx1TExMzNbEfznbZLNCtHbCfquitdU9nRquTyglR/ty+GF4x7qGncY71isb8BBSIkXUENINAgxNQUqQUlJxPBKWggRyCZ3x8sa2JgAqYCrQXKdjFODk/i72dSYZKzZIGRqoEl2Bb12a5+m9eXKWQdP1ODNe5oWRzm1ZbcvP9IWRTiSSjKmTNDT2diUptRyqtk/W0jjam2Fvd5KOpMmTQ3kylr7y/JddeSlTjQsKY2J2iViB7IA7VTtv9725pM7zB7s41JvhylwNNwgIuHNB4U5acmzW/n24kOVXvn+T63N1glCiKoKujElfziKfMAilQFcFf/rEHnRlktOTtTXnVYD+rEFHxuDGTJ36qqGHArg4VaHW8rBMjc50goSu0ps1abk+iiIoN12uzNWotzwkkhNDBRKGuq0RtJah8czeTs5NlSk2HDRV8F8+t4+m63NxuopAIBQ4MVRYk0Yct3KPibk/xApkB/hByFy9SbkR0JPRSZrGmtjGZrMwVpoMCtCU280Q+/MJujPmlrvh9em+223JsdkUxlM3ixRtD12N5mkEYYjrh7x4sIfj+/KoQjB3ZZZMIcHPfe4oF6cr/Ppbt5gqOegK9HelGconAWg4PvaCveLSCoDxisd4pULOFBzpz/K5xweRSG4t1JktN/nBaIUgiFJxG7bPr789zqGezFKr9juPoF1//xDFXDpS5oqiXD2JMG7lHhNz/4gVyDYpN11+7Y2bfP3cLJ4XoGsKn3uin5Ge9Erb9/W723LT5Y0bC5ybqHB9toYvJSPdaZ7e18mzS00At7JUNts5b9cSWi9s3SBkutqiagf05qKxvU4gaTk+aUsha0UZZRIYnW+iaQJDU/mhxwaZq9r4UuJ7ASGS+aoDyE3jIRVHMl1p8datBTrSFhlL5/fOz1BpBuSTOoWkzg9uFNnblSSb0AhDueLWgqi2Y70iWa1Ml1vH3Gng1WZxo+WCQ2DX+5DFxDwsxH8528APQv74wgy/eXoKUxW4YUjDDvjq6Ume3ptnX2eaFw5244fhmpqDdyfKXJ2t885oiavzdaSU3FyoE4SgK4Kn9xVWrJH1lsZu7ZzXK5ukoSKlBAFpU0PxfDShYugKU5UmhqIghODRgRxj5QbVlsd8zeWTh3o4N1ni9eslFhotbE+iic0D7QC2G1Kqu+STJvmMSd328ULJcFcKGUouzVTZ353CdgNuFZuUGy51xyWh65iaskZpbqZMt4oLLc+wD0PJTLVFw/ZouVGDxslyg5mKg6EqHO7LooYPrqVPTMxHhViBbIOm63N+poIfSFQhqNoBigAFge1F7U1sLyBlamsKChu2z+hig/GlKXyKEPgBfO/aAprKyvjc3qzBZNlGUaKpe+1G4+7GECRNVfjU4R5+//wMF2dqICWWrvDcgU66MglkKPHCECklSUvhaF8GP5DUWh6vXZ9nseZSbNiUGx5+CMEdZK6uRhaMoQkCX6JpCr3pBK4fEAQhgQwpJHWuLzTQFEE2YTBbsQlxODGUxwskZyZKPLuvY0tl2i4utDy0a6Hh8vrVOV6/sUip6eEFUVA/k9A53JtlX1cKRakx7K1tIBkTE3NnYgWyTVJqlLJrez5hKHGCgCCIGgA2XJ+67aOpYk32kKZGBXNSyqigLZToKtRsl8lKC0NVuTxXpVx32d+TZqQ7w+Ge7JrRuE3XX+mmuxtDkHpzCf5fnznMv331OnU/IGdqPDmUJ6GrpE2dhbpN3fF5e7REytQYzCUQQiy5uzxKS4OkNFUgArkyV2Q9nQmVY0MFhjqS+KFkoeFgu5HizaUt6k2ffV0prs3VuLFQpyNl0pkwuLXYQFMVxotNhvIpfBnSnTZwvXAlzXd95b+uCU4OF1Z6XwH88aVZxhebvDdd5fVrC9QdH9+TBIAbglvzuKXXURSYrTXpKQQU6w49ucQ9Pd+YmIeJWIFsg6ShMdKfofeGyWSpiR+EBFJG2UtZkyCEizMVju3Jrxkq9fTeAu+OFTkzVqblBCgK+GEUSM8ZGt84P0PVdvECGCykmK3ZGKrCno4kITCcT/K1c9PYno+la3zxyYFdaftedX1+6rm9hFJSari8dnURxwvxl2o2hpUoE8t2A07dKiKAlKkxW5VoqsDxJAKJqQnUUJLQBVJK3BAsTaU/l2CoM0UuqZMwNMotN7rnhODt0SJv31qg7oR0ZgxcP2B80VmJpahAztL41JEexsp1Al/yh+cDDD1qa7LcP0tVBU3H553Z2hq3VtJQqLZcrs3VSRsaxbqDFApeEMVrlvWdB4wVHaaKUarysWMBv/ifz/Hf/tAjPDqYu6dnHBPzsBArkG2gqQon93XwvWuLHO6NZm5Xmi6KUNjbkeaJwTxN11vq/aSuBIA70yZ/4YX9lJsB704UkTIaHqWrCt+5Mk+x4QJRauyZ8TLPH+ikansrr12crSKIajZ83+fcVJn+vNU2ZrJdloPKHSmTIAy5MdcgkCHvTVcYXWyyWHf4mZGAzqRJPmlweqyEZSp0Zy2CMOS9qRpCRCm7TU8SErUHGchrDHWlKdV9DvVnONKbxfYCJkotHhvIkrM0fuP0ODNlBzf0CQK4PNvcsL4AKNo+r1yZoS+b4NGBHIsNj6eG0lyaiTr4GksZWxdnqm3dWhDNYIdo/rquQBBEVfTrDSaf6I9AAW4u1Pn3373B3/vRx0gvVcDHxMRsTqxAtkl/NsGnj/QwttjE9UPOjJXJJjVMXcGXIUlLw/VDzk4urtkRZyydTz/aww892k3NCchaCv/wa+8xXnHXnN8tN7kwq9PyAj73eB9Nz+d71+a5OVensjRB8N3JMvs7U3RnTS7N1DYElLdSKss/U7hdtCeR2F6AKhRGizVURSzNOpH8hzdu8dy+DhaaLi8d7mam6nCwJ8OnjwT84Po806sKQDxgtOwzWi6zJ28wkLN4ariARPLqlXkGchbvjJcYX2xhBz6BBGcz39cStWaILmxqrSRNN2C2ZnOgJ82jgxmSevRru1VV/khvivFig0LKYCCfoG57lOz2Qf9lxRJKqLkepZYXK5CYmG0QK5BtoqkKL4x0Y+lFzo5VOLE3j7U01vbSTJU/c2KQS7O1DTvik8MF/DBkshzNJL841eT6gr3h/E4Aruezp5Dga2enyCY0vnlhhnLTiwrkpOTmgsI//sYlDnenOLa3QHfaRCz10DrSm+HS7EalAhvTgfcWUoyWGktxjZCOlE6pFRX77cknARs/CFlsuPRmTN64UWRvRxJfhrx8pJe5aoPpem3DPQBMlF1+cH0RXVERCthewO9fmGW02MDxo5btgRcStD36Nj5g6DrVls/je3KMlZv0Zg2uTNeJhguzMvJ2ffbV8gx2S1fpTFn0Zi325pN8/9Yik2VngxUSEg3Bajg+KV2jsIuz6WNiPsrECmQH5JI6J/cW8IKQ3owFgBeGVFvRtL3NdsRhILHdaITsfNXdIMCW8X0oZAwuTlV541qd+aq3FBtYOiIIOTO2yIXxIt+9tsC+riT7OpPs7UrTcnwKKRPNiPpsrW5guD6DabTUWAk6H+lP85U3x2m5Pq4f0pO2EAJ6syaDhQSCaHpfKMFUVWaqNmfH2iuPZU6PV2k6PvmUyUDBYk8uwWytRU/aZLzcuGP21jJZSyVtqZSbHmEoQSgkTW3V4KyQhuu3rV6PWp904QYhrufzv3/nBgP5BA3Xp9IMWG+LCCBj6fzUs8Ox9RETs01iBbJDkkY0XtUP5UpnXlNXSBta23qESsvjwnSFUtMnlCGJRPuurxqgqjBXtZkq21xbaLQt0ms6El2V3FhoMFZs8CpQSOi89EgfLx/pYaZurzQwPNSbIZfU2yq2EHD9kJsLTUZ6MlRtn3MTZUZLdY71gu1KxopNdEVhX2eKJ/fk0VXB185OIhTYyoQIgZYX4DUcZBgyttiMlIaAnGWC9Kg5G4X4alSi9OnZqoPtBeSTBq4fLvX0iu7D1BRODOVXZsCvd9utroF5pC/L5dkauqJgaAG2f/u5f+xAjs50nU8f6aaQMrBdP26wGBOzDeK/kh2yvu5geSDU6iaJiw1nZezruxNlKk2frKmhaQrztSb9WZ3pqrfmvIYWzU2/NFUjoasgJSob5bQP+EsvBuGSsK55/NY744yWanzhyT1omoLtRS09nj/Q2VaxKUSFjqoQDHek6EqbmKqCpkGi2SRpqKiIyLKSEktXqbseOcPgUE+KdyYbWz6nlh+S0RSKLQ+EiGpBltKZcwkNJ7gtxNuhq2C7AY8NJhksJOlMmLwzWqI7a9CRNPGX2rSv70K8nuViwkLa4IvHBqm3fG4s1jDUEF0T7O1Is78zTbVV4neuTvD26CLH93Ty0x/fx/7uh29mdkzMTogVyF2w3CJkeeb5lZka19U6w/kkUoCQIEWU8eT7IYP5JBXbw/ECNEXj5SN9zJabnJ8qU20FGJrgYHeGJ4cKNFwfP5QkdY2aCLZ096zewdshfO96mYyh059P0pO1uDRV42h/tm2hXbHpcmGiStJU0RSFwXyClKXxxJ4cC1fHeflID4sNl0M9aa7N15mrtrB0laNDWQa7EhS/dZVbxY2xHICEBmlTj+IUXogiJY4r0BRBseGSNhW8LZSHBggBnSmD7oxFbybKPGt6PqduFNF1lUf6Mrww0t12cFa7eSiOH6Iq8PGDXTy1LypStDSVb56f4lffmuRvPREyUw+Yqdc5N17nxkKDX/rxJ+nNxnUhMTGbESuQe+D60kAoU4tSd792borHBrL0ZBP4YcjVmRqapmDoguFkEj8Msf2APbkEiiI5OJaJBh6JqPbD9aOsqIrt8PGRDl67tshs1V1jhWhsPY/jjZuL/PUXO8inDRquz9WZGs8f7FrTE8sPQt68UcHQBQlDBSm4Pl9DVRT0JeF7ebZKEAosXWF/V4rnRjpJGhqVlsdr1+b44pODzJSaLNoeSQNOj5Zp2j6hEBwbylNzA2w3oO5IWp6HgkAAYRCwUA+2DKKrCnSkTQIJN+frjC02CJFkDI3OtIXtB9xaaPDsUspuuzYnKVPdEPuptQRHBtJMlGyyls7NuSpXFjcqQVfC6dEFvnN5jh97aiiuTo+J2YRYgdwl65v0NRyfG/N1NFUhqduMdKeRwNG+LF4Qcn22gRTRJMNn93cihEQQ1Yq8N1NFEYLZahTXuDnfRCLpz1u8eKib71+bRwpB0wtQgJrtE4aRoFsmmigerevUeJGn93ZwbE8BNwjWDJwqN13eHi2tZIxVWh6GquAEIT90tJfZik0QSoIABvIWiojcWElDo9x0OT1WYnS+SSqh8aMHhqi0PL57bZ7PHxvkVrHJiT0FFCG4NFNloe7g+iFVB1QBTTvYUvlBFMze22lxbLiD8xNVLs1UCUIwVcFQZwohBL3ZBHPVFq/fmOeJwRwXJ2sU0iY5S1vJfntyMLcx9qP4PNKV5eZciwXP4TuX5zddhx9Cww3uqXVMTMxHnViB3CWrm/hpisKNhTqWrpIxNRShcHGmwkhPmu6MyWeO9PLxA5HoXN08MWlpSKA3bfHtK7OcHi1FAeOUQRhI5msuHQmbgY5UFG9puggBSVMnCH0my95KRlcIaAJ0VSFtqUxVbA71+pi6stLeY7lBY9pUyaeMlQyrfV0phISR7jTdGYPSDZUvPj5AuNR0seEETFWa/N65mWhdDZeRZJrrC1FK7f6uNMOFBFnL4NpCnY6EQcZSOdzdwTcuzGA7d07bXaYzqdBXSHJ9tkHTD1CQaKqCApQaDheny+iqQqnh8McXZ8indFxf8sy+Tp7Z10naivqRAW1bwQzkEhwZyHB+okJfIcHFuY3FjACdKY2BbOKeW8fExHyUiRXIXbI6mN60HRw/5KXDvUzXWgS+T9PxGSokV96bXZUauuyvP9qX5fxUhWtzdbqTJvmkTqWlEIagqAoCGC01OdyT42BPhoyp8t50FV1RuTZfpi+jM127HYxXBBztz9KRtKjaHu9NV/jzH9u7soNuLqW89mYsDnZluLZQo9ry8IKQE0MFpsstzk9VcfyQt0aL6Etr8IKQ8VKDs2NF/ECStDQmyk0KSR3Pk+SSOrN1B0tXado+12dqjC7WadqS9jMN21NYmoZYrEZTBmeqDu6qQI9adZmt2OSTOuWWh6aq1B2f/kIyUoyWxmMDuZXg+nA+ye9dmMbzQ3RN4fOPD2AZGkf7slyYqtCVMklo0FpnFiUFvHCoj0cHcivPLZ5eGBOzkViB3APLwfSm62PpKklToytjMFu1ue5GfvqpSmvLor6RrhS2F5DQVM5OVajaPk0vJG1oWIZK1lDxg4DpSoOqprG/M01/zqDuuVSbAQhBQlOo2i4daYtAQsuLLI+hQjKKcSxd992JMtdnG0yWWxztzXG4J2rL8lh/hh/cXOCVy/NoisIxTXJ9roahqRztzzE6X+HX3ppeE7Tf35ng+FAeRRWgJHHcgG9dnObyfPvA+p0QQHWpUrzcbJDQWKM8IMpIa3ohYdPBCwQgcQNJteWRNTXmajZ7WgmeGMzjByFj5SYnhvIoiiAMJaOlBv15i+6MybHBPHs7kpSaHmcnSij4ZDR4cjjLTz93gI60yYXpMjcXIisxnmQYE7OReEt1jyxbF8eGCth+wGLD5eZig0cHsnRnLCxN5dxUeSWddDmw25EysTSVG/MNLF3F1FWO7ymgiqhJoO0FdKcMKi2X719f4PXrJf7o8hw/uDVPwtR4cjBHT8Ykk9AwdZXDfRlsL6DpBhiaSlfa5PpsDdfzV66bMjRODBdAwjvjRRwv5PhQniuzdUaLTdKmTspQsb2QhboTrdkL+O0z0xtqNm4utjjQneLPHBsiDEN+5dWbd608lgmI0ncVBeqbBEvCMIpPqIrA9qOZ8rWWRz6lc7Arja4oXJmt8b3ri1SbHklDx9I0kkZUD7Mc0zg2VCCfMDg2nOfPf2wffbkEX/rUIT735BD9+SSmpnFjromiipXPavlzjImJiYgtkF1i2Ropt1wE0JmKZnKvbz0eBBLNiISfrkQum8M9Ga4v1Dncl8b2urg210BTwZchk2UbN4CEIQil4MZck//0xiifeKQHRYWCaTBZaTFfd3H9gDAIuTxdpu6E6Kqg5Yf82FN7Vq4rNcmxPXkW6w7Hh6MivJYfoAsFJExWWgxakmLDQ0iFG/NTm9ZrnB4rcaArzR+cm2Dr2vQ7s5xd5rfpeChWvRQS1b8kLYWmC7YTgBHNVs8kdTIJfSkrzuPqXI3OtEnS0Gi6Pl4YruyYVs+lvzRdpXZrDE1VGM6nUBWFSstFCkl6qaBwN+axxMR81IgVyC6iqQr5hIGhK217NEHUv+n6eB0FQYhkTz5Jd8akO2MyX3PQNYWUqfFHF6exvdvFdk03JJCRIL0w16TiTLInbzJVdSg3PHpyJqqiU2m5vHOrQtJUMDQFN4jGzz5/qJPrC2uvuzzKNfBDRotNFus2b4+WefxAwHzNJmNqEIZsNqzvvYkKxabL5Xm3/Ru2iSlYmSuiqeD5kdLQlUhZLAfgBZAyllxXfkBXyiBhaBwbKvDCoS4mS/ZKpXrS0BkupKg5Hgs1m/Fyi+FCilNjpTWjgROGGrnhBOztTuIEAcWGAwIO9WSigkWFDZ/jMnfbFTkm5qNArEB2mc0m5C1nXgGsdAOUIFdtt9+dKHFmtMQrVxaYLjeizrjLP1wnxCcqHhOV2wF0v+Qw1Jmk0vRxJDh2iCDECxokdJUrszX6cwkURWy4rqapdKUN3h4t4iyVuXckDGw3IGXq9Oc0JiobzZCK42PP35vtYSjQnTVpeh6BHylKoUBXUiOf1Gk5PjXbW6pg12l5IQoKuiroSJskDIVsQuUbZ6cZ6c2QWtUrK5vUOD6Y4we3SpwYypM0dJqux6nRIi+MRNMMl117TVWhO2PRcP2l92o0nKDt57jMZmN2Y2IeFmIFch9Ydmet35m6QYilqTw13IEXhOhq5CpZnnT41o1F3hkrUWl52L5caVmyHewQrs7fTknVRDRyttgKsUp1hjssju/J05EySZn6ynUBTE1hX1cKJKRNFSRUHI/FlkdHQmWmulF56AooQqBs2hpya1LA0wcLvHCgBw/J1bkqHz/QyZnREtfn6wRSkDJUZmSLUEYWgiqiee6KFhU4NhyPSkPSciUJXVnpU7Za4CtqVAGfNHRqtsf1hTrlhotE8thAm1oRx1/poZVLKm0/R4DdmlkfE/NhJlYg9wmtjUtjuXbED0MsXV0zWe/UzSLnJqtU7CjofYd+hXfEXyXXa7bPty7O8854hUOdaX748X46Mgb+kmAUwNWZKot1m9m6TzAkmaq4KEC1AUld0HDlmvWEIQgVEobGlk2t2tCX0enKmvTmkqSTOooQuB0pLF2jM5MgXOrBZagqiw2X7pSGrimMl5s4fkDGVGm4IZWmh6WreNgQCr55cZZPHemmZ6lTcnIpAy2qB4mUhwAKSZOMqXN1pgaCFaurnZuq3ecIGwtJ4xhJzMNIrEAeIO3cW8uT9RKmRl/WYqzYoOZ4OPeiPdZRcwECSnaLmwst3hxd4AvHBqg2XTIJg56MwXevLDC7LvUpJLJsDCHIJVQqLX9FiWgK7CkkGO5MUarP09xmclJXUuPk3k5UFa7ORu4vS1M53JdeClhLFFUwlE8xWmyQS+jM1lr0JxN0pXUmS5Ji3cPQBV4Q4gUhYaiSsqJK+TevL7KnI7Um9fZQd5rvX19gvurQk7EY6U6TNDRsL1hJYAhCie0HG9xUm7G6kLRdrCsm5mEgViAPmPXureWdbNrUSJoaPVkL25fI0Me5TxmjZVvylR9Mcn2uwdPDHYwX67w7tXkso+qE9KYUerI6gS85MpDm4we66UibtPyQfErnK6emtnVtL5DcXGzQnTVImxpD+SSWoVBseBzuzfDxA1385jvjfOP8FL3ZBKoisDSNWstnvuagaQJCgR+CE4KpQqgInCAkhWCibDPcnSahqUxXmvza6zdw/CjmM1Vpcag7Q3qp5YmqipUEhlfHtR25n7aKdS0TB9hjPurclQIRQpwERoCvSSkbQogU4Egpd+bLeEhZ7xZRVUHLD+gvJCg2XJK6xnStScP2KTW2bjx4t7jAhYkyNSfg/BbKY5ma45O2dJ7a18GPHNtDKqEiJPih5PJMlWeGc4zOVlh0Nne9KYAbLGV4WSp7CkmO781jqApv3SqiKAKJRFUiN18QhvhhuKRkQYbgI9AIySd06pFmQAHyCZ2MpaIKqLVcfvXMJBenapRaPoP5BH/yiX4e6cvyvRvzmIZC0lQ3JjfskM1iXRAH2GMeDnakQIQQvcDvAM8Q5QUdAm4A/xywgZ/d7QV+1Fk9R0QFOjMGHWmTw30ZRosNpkstpspN6t4dT7Vjmh5MLd5ZeWQN+O+/+BgCQcbSURUY6UqRMDReuzpP0w5wAzi2vxtNU5gsNWg6AeOLLZylWIwgcomJEDzfp9RwySej6YsHezPomoLrh1yZqyEEZEydQEb1KP3ZBDXHJysk1YZPNmnScDwsVSFlqeSSJpap0JEy6M1ZfOPcNBcmo/iGIqBme7x6ZZY/c2KY/qzF0f4M/bnESnPJ81MVmq7PGzcXdyzo28VI4gB7zMPCTi2Q/wWYATqBsVWv/zrwL3drUQ8bq4vafnBzke9encdQdT5+oIv+nMX5qQoTCw3eHi+xWPd3zSLxgeIdmlVZAl460suLh3tBSL5/bYGbs03OTlR4pC+LqghGelMkTRXblVRsj4xl0JUWCEVQrDkstoKVXK1mCE1bIoSNIhRaXkC56fFnnxnixkKDasNlruZgGSq2G1K1XUxN4dGBLJ4f8v3ri2QNjYypo+RASskjfVncMHIFtpyA96areFKSs3R8GfXyankhs9UmCVOjO22uWB7Lgj5ylam7IujjAHvMw8JOFchngM9IKUtCrBnNeh0Y3rVVPYRoqkJ/PsHnHusjZaiYmko2oeOHkqyl09iT57OP9XNmvMy3Lk8zUb4PJsk6FOBHn+qjK5PizFiJC1NVxooNHE8ihWS81KQ3Y/GxAx0UGx7IgLId8vhAloW6y6HuNP/2tdG25y62QoY6oC9rMVe3ySU0XhjpZKHa5NS4jGagA11JC0MVzNYchIT93SkGcglUJSrWLDU9bC9gsW5HlokbYqoKtTDAUhWEpTG+WEdRJNfmavyF5/evSau+H4I+DrDHPCzsVIEkiNzn6+kmcmFtihDCAl4FzKXr/oaU8u8KIY4D/wawiDbF/42U8s0drusjg2VofGx/F+emyhQbLiGS/pzF758rUWn52EHIscEOwqDIVG1rJWIJyKdUdFVlvLLzavGCBt95b4aBgsnpWyaLTRc/kBzqz2EIhVsLDcaLDVKWyjN7C3z3+gK9WYuudALXD/lPPxjdcu75jfk6ni/JJgzmai4HewwMQ8NQVFIJBUE0jGuuYnO4J0XTjQZumZrCCwc7+d61RSxdQVMFtxYDHN/mkZ4MGUtntuowWozOrwhBUteYKbf4v75/k+lyi08e7iGX0FcEPWxebb5TthNgX00cbI/5sLJTBfIq8DPAf7f0vRRCqMDPA398h2Md4NNSyroQQgdeE0J8A/gHwN+XUn5DCPGngP8ZeGmH6/pIkUvqHOnN8O5EBRlKXrk0z0zVpitjkhM6ZU3wSF8GXakxWtlciSgChKKwcBfKA2DRB3yYaTmwqjH76OIcaUtBU1W6UgZv3ypRangMZBM8sSePpSn8+ps3uZORVHPhxmKDoULI185O8VPPDJG1DJ490MFMxUZTBdWWx9HBLJ9+pBdNFdRsn3PjZRquT9aKCiKFFJiaiqHBb58eZ6HhUHPkivLSgJsLLXQNbhUbBCFMVWx+8pnhFUG/0zTeO7FVgH01cbA95sPMThXI3wa+I4R4hsiS+GfAY0AOeGGrA6WUEqgvfasv/ZNL/7JLr+eA7eWDfoTxg5BLszVyCT1qOSJAVZRoUqAM8IIQTRMUUuaWCqQZQrO6+64uHyjbIRDSmdLpyZos1B1ODhfIWBozlSbX2oyKbYcioS+bZKbS5MxEiYxlcLQvh2VEs0Wyls5QRwIhwNQ06gRomkpC0zB1hV49QXfGxHZD3hlbZKJiEwRr58UvpwYGPrh+yLX5GiPdaU6NFvnMkV6e29+54zTe7bBZEeLKuuJge8yHHBHJ9R0cIEQf8NeBp4nc5O8A/5uUcnobx6rA28DBpWN+XghxFPgDokQdBXheSrnBcS6E+BLwJYDe3t6nv/zlL+9o3XdDvV4nnU7f9+usJ5TRECN1qW9V0wuwvQBLVxFErpa67eOFkmCzTof3QG8CZlvbe68gmoKoKoK+XFQB3nIDZqrbVCCAZaiRm8lQyScNvCBESgilZDnS5qyqm0noUdDbDyRVe2kkrx/i+AEtN7hjcxVFQNbSsfToeroq1nzWoYzec79Z8zkvEYSSpKE9kOvD+/c7/n7zsN73yy+//LaU8uRunW/HCmRXLipEHvgq8DeIlMJ3pJS/KYT4s8CXpJQ/tNXxJ0+elKdOnbrv63zllVd46aWX7vt11uMHIW/cXIx2pppKse5yZqKEIiKhc3G6wuhCg+mKTdne/SqRv/WEzz87t33j1FRhf1eSH3q0n7/24gGmyi2+8C9eaxssW48hYE+Hxd7uDANZi+dGOnlhpBM/DDkzXiWXiJojVmyPWtPF1DX6comV428t1PFlwK35JuPFBr9/bobmHR6JpcHPPL+fnpzFwa40zx/s4rXvvsrxjz3/QN1J6z9nxw+w/eCBWiDv1+/4+83Det9CiF1VIHeUEkKIF7d7Minlq9t8X1kI8QrwOeAvcrt+5NeBf7fd631U2RCE1QQ//dxedFUwW2txfb7OcGcKKUPK9jZNhfu5XgE96QRT5RYVOxru9NlHu/j6ewt3PDYU0Jux2N+RIpfU+Ob5aRYbDsW6y835OsW6TW/e4khvHjcIGexIUGmppE0dPwwppI2o465VYn9XitPjZW7ewX2mKVGvraO9OdwgWGkq+SDdSbbrU3d9DnWnuTpf31awPSbmg8Z2tpmvcLsBOdxuLL7+ewB1s5MIIboBb0l5JIAfAv4nopjHp5au82ng6jbX/pFmsyCsH4YYmkBKhZGeHDXbZ/I+xDnuhEL0wZsaDHWlSVoatufz9TNTfOviNFe32eZdCSFAYjse3782T812eXeywlzZprUSyKjQkVjkTzzRh+0FTBRbqEJhpDfFc/u7SCd0Tu7t4FuXpunJJhBCMF1u4fprq+J1wNAFfXkLXVVQFImKQCGqqA+9kJwVza7fTkrv3WZPjS7U+caFmZVZ7X/i0T56c1achRXzoWM7CqR71dfPAv8U+EfA60uvfZwoK+tv3+E8/cB/WIqDKMBXpJRfE0KUgX8hhNCIUoG/tP3lf7RpF4TNWgYvjHTz/RsLLNYcOrMWWUvj4tz9tUQGEmCYULOXWoqIqJ17xjLpTpk0bQ9NF/yzP7jCHWoT1+ACb96q8OatyqpXNyrEYsvnj9+b4ZOHuvmTTwxEletugKkJ/CBECEnGNHh+fxfFpsNoqUmt5ZLSdUotm5myQ3fOoidroSK4Od/gSF+GR/tznBor0XIDJudqKIqgM2VGqb2ClVHE6z+Hu82esl2fb1yYIW1qpDI6DdfjD96b4Wc+vu+ulUecBhzzfnFHBSKlXFz+WgjxPwI/K6X85qq33BBCzBGl3359i/OcBU60ef01ooB8zDbQVIVPH+kln9Cp2C5BIHECyT/46vmtC3HukakWsEpH5SyFTx/poT+fIJTg+5Jzkws7Uh47pW77zNUdzk6U6UybVFseLT/E1BWEhMtzNUZ6U2RqKp1pg/Fik2f2ddB0A16/sUh3xkAVKkEYUnN8gkByabZGR8pAUyOX1sWZCod7MrhBgCIUTo+VNyiIe8meqrs+nh+SykTnsjSVq3NVvn52gieH8uzvyu5ICcRpwDHvJztN430UmGjz+iRw5N6XE7MdckmdTx7uXtl1TlUbGDrYD9CTVbFDZqsNfvazhzF1lVM3S7x2de6+XjPwASl5d6LCJw92kTI0xktNTFXhYE+GuYrDVDnquHukN8f+zhSWoVJIwSN9GQCKdQ9NEzzemSOd0Dk/VeG5/Z1IGT3XQz0ZHh3IcmWmRnLVdMPVCqLp+jRtn3Q2EtQ7qWBPG9Fsk4brAYLffmeMM+NVvqKCoan8xNN7+BufeWSNstrMuojTgGPeb3b6W3YB+LtLMQwAlr7+H5Z+FvOA0NRoAp+mKnheiK49+M78izUfU9PoSllkLZ39Pcm271OB44Ptf7YTTAPGF1tMlRrUbY+WFzBVtrm10OT8VIUD3Wk0RaXlB1xbqKFqCoWUSV8uydPDnWiKIJvQ2JNPcLQ/Sy5hYDsBb40WaXkB74wV8cOQpKEuxXdutzgJAokbhJSbLmfGylydr/POWJG67e+ogt0yND7/+AC1ps9rV+c5O1klaap0pExUVfAb70zw7cvT+EvXeuPmIm/dLPLGzUUqzbU7hJVWLG3WGRPzINipAvnrwMvApBDilaVMqgmi4Pdf3+W1xWwTP4CkuWn+wn3j8b058gkdTVV4bDDHwZ4cnYmNBQx/7cX9fOboAC890sGBnMpQTqH3LvRJ1YVKy6XpBjQ9n46UQcKIwvmzS5XrQx0Jju/Js78zhaqIFeHakTYY6kyiqoIghJvFBsW6i6oJNCGQckkghzJSBCK6luuHVFpu1NmXKFMraWo8NdQBAk6PlWi4/o6yp4Y6k/zks3vY35nAVBWSpo4QCqamIqVgvNii6for1kVHylxp9Li69fzqnluwe61YYmK2y462rVLKt4QQ+4GfJnJZCeBXgV+TUjbuw/pitkEhrZNP6MzXHO5DWUhbjvam+NmXj2IZ0a9QwlA5PlTgycGneeXyJBcmK5iGwt/87GPYXojtR+myuqoyvtCk6drczdDeqh2StQTvTlTJJUy6UiauGXJ5tsqFqZB9HWkuz9boy1kkltxPpqbSdD1mqw7HhwpMl21ars/56TIjXWnyKZ3ZqgQJ1+fqjHSmcbyQc5NlZisOvTmTR/tzTJVtnKVMLVODp4YKzNZsTgzlySZ2FnfIWgaP9OZQFIHj+SSWRhwLIRnqiAz8OzV63GnPrZiY3WbHfg8pZRP45fuwlpi7JGsaPLYnz835+p3ffA988lCKkc4CLx7u5vmDPSvKA6LdsKErWJrKj588wOee8AikpD+f4HfencJUFS7P1smZOmdbHg03QGXnKiQATF2hI6ExWW7Qm0lEdR0iqoS3DIUQiaZEVtHFmSoNx8cPJcOFJD0Zi86UibfkIgLJu+NlugLJXNXB8QO+fn6Kk/s6yJo6uT4dz5eMLzZ4b6qCoSr4fSGdaQPbD0loKklj5+5DTVV4+Wgv5ybL/Prb4xTdAENT+Imn9/DyI/0kDXXTjr6r4yLL6d5NN2rYsjwHPibmQbDTgVI/ttXPpZS/dW/LibkbQuCZvR1cnC7x3kSjTRLs7vDdqw1OX2vwxJ7Chl3u6t1wEES74cf7c5yfqkStR4SgkDSYrLQIAokiIGkqtJyQnY6xvDLf4sZCCyEhZcJje/Ic7c8RhpK0qTCQS+KFkoShrtTSKMCpsdKKQPZDMDWF7ozJH7w3S6cBpq7Sl7M4P1nC1FSmKjYpU2O+YpNL6jRcHz8MuTBdwdJV9uSTPDaQZb7urMwY2Qm5pM4vfP5Rfuq5IW7NN9jXlVyThdXOuqg7/oasKy8MOHWjSMl2UYk6FQ92pNZcK071jbkf7HTr9BubvL5cTBhvf94HDDUShC+M9DBdGqfS8pECwoAdC+c7UZfwt37jHKfHi/y//8Rja1JG2817R8KefJLXri+wUHcIw5C+vMXYYogiBHLLhu+b4y/9xpUd+N71Mm9eL6MQ/QIOdBr8yIkhnh7OU3RcGnZId9pYI5DtpbjBrYUGSImuCka609h+QLkVoKmCTEKjafvcKjZ4Op2n5QXkEhrXZ+sc6E4yVWmiq4JrCw0e6c3w9N4CnWlzR/ehqQqHenIc6slt+Nn65wncbn2ylHX12rU5zoyVOD1WYrJiYygKv/XOOL/4+cd4YigfPaM41TfmPrHTGMiarctS8d8J4J8Av7iL64rZAZqqcGyogO2HzNUdXrk0BxJShsberiR+GPD9G5U7n2gH/MoPJjm5t4MvHNuzZke7ofhRwES5yZHeLHvyCW4s1Cg1PBw3YK5mo7DkllJAKIIwlAgBCR3KOyhsWW11XVt0+V/+6Dpv3lgkEAIVhZ6syV/5xIEVd8/p8TIpQ0NTFPZ3ZXCrM7RsFzcIONKXwdRV8lJQbboYqkLLj5o4Xp2pUbZ9psoOThBSbHp0pS0U4MZCnZ94eqitErlbC2D182y6/pq4iKYoXJyqcmGyylzdJWsYSEWy2HD4P753g3/4o49jGVqc6htz37in3E8ppQ+8JYT474B/DRzblVXF7JhcUufTR3p47kAHf/mF/Zy6VSRt6uiawpWZGp4Hp8Yrd+xUuxMuTlf54cc3r33QVIXDPRnOT1ZQhCBhqnzhyUHmajYNO+C7V+eYLDeZKDmkDIVi08XQos66I505DA1manUmigEKkasugG3ZLBJ440aZE8M59nSnqNse/+61G/wPXziKoWsgb6fpPjVcYOKiQjptkNRVGrmA7rSJrik81p/hdWsBXRW8NVZasqKg5niEoaCheBiKQmGoQKnl8PZokU8f6V3zTHbLAlg/6bDuRLGkYsvFdkMUK0ALVDRVwfYDSi2PTlWJx+vG3Dd2q3igDIzs0rli7hJNVcgmDB5NGBzuza74/g/2pLixUONjSo7TYxXcXdIi1ZZLqeFgez5Zy2grkLozJk8M5FBUQdrQ8ENJT9bi+NEcvTmThZrDL796g1LTJWXoGBp4jZCxSoOXD/dxoC/HfK1FZ8rk9esLTBTtbTu9QiIXnheE1GyfYtPl25fnefFwzxpBrGuChKFybKjAjcUGegBnJysMF6K034N9Gd6brLBQdZBSYGgCENhBQEJGLeGvzFYJJMgAntiTp3+pY/BuFvutz7oKQ0nKUOlJW5TqLo4X4siA3qxJ0tAwVSVy68XjdWPuEzsNoj+1/iWiHlc/D5zerUXF3DuaqqwEXGstD8vQeOlIgePDHbx2bZ7ZSoOF5r1pklcuzzJWbNGRNPjUkT4++2jfhp31snvt3FSZSstb2YGnEzrP7u/izESJE0M5vnVpjoShogrJ3kISO/BxAx9D1/nUoV76CxbPHejk+kyNb16a49ps/Y7JAqoAISUT5Qa1pktn0qSQNDg/VWGkK831hdtdcBO6ymipScrQ6Eia5JIaxbqLrikM5hPMVx0GO5KoQqHccpESCimdzmQ0TGt/V4q9HUn8MOT8RJlCQscytG1XrW/XxbU6LuIHIS0vwNBUbC9grNhAVRQ6kiZPD3VwcaaGqgr2FlKMlhpxqm/MrrNTC+QUazvzLvMG8Jd3ZUUxu8LqnW86pzHSlWaq0mK4kOSzj/Qy13B44/o8N4p3371quhay0CiTNBQmyjaWpvC5J/pvdw5eEoopU23bWTiX1HlhpIuMpXJltk4gJaGU6JpKStU5ua8Dzw9puB6HujvozCR4ariApik4jwSMl+u4vmS6bHN2qr7GPZcx4dieAlema8w3fQQwqdv85qlx9veksb0AQ1HY25VkIJfg++NixdVTsz1uLDSYq9qoKBzbm0PTFPpyFtdmayQNnVLD4bGBPMeGClyZrdGTsXD9AEUILs3UQMJQV5Lpks3V+ToT5RZH+3LomthgAezUxbUcF/GDkGxS59kDnTy9t4OFuk3d8ehKG3SmEysWx2ipwcnhAiHEWVgxu8pOFcj+dd+HwLyU8n728Yu5C1baXCz5vk8MddCwZym3XFRF4PoBZfvuajGWEYCQ0LBDzk5U+cP3Jjl5oEBXymqbbrqZUGy6IX/+uWF+/e0JgiAqOhzIGPzzb16hYfsg4LffmeRvfu4RFATphE5vLsmezhTlhsuPPpVkb2eS1y7NU246HOnPs68rxe+dm+LseAlTjVJ2fSn55qVZPqNInhoucG2uzunxEo/2ZdGkxFAFTdfj+kIdAXSlo3qR63M1hFAQCDrSBl1pi4G8yYm9BT57pJeOpIEfhIyXWhi6gpSSm4sNvnlxjkN9aR7pyTJWbnB6rMRje7IcX5UGfS8urjWp06GkM2Pysf2dXJmtrWlv0nB8QrirepWYmK3Y6W/UXuD7S8HzFZaysZ7f7kCpmPvP+oCrokDaNHhsMIupK/zK6zexPf+eguoS1sRTfufsPJZ+mc8fG8TxQjpSxh2F4rKiO9yX5U8+2o+qKsyXmnz13BR124/Gu6pwc7HO//yN9/jhxwZ4bCDPxekKE6UmfhDSlTXpzST50suH8YOQpuvz+o1Fak6IUDUsFQIp0QW4vqTS8Hnr1iI35mpcma3yRxc0/ot9Nh9Lm4yVWpQbLtmEznBnEl1ReHeiTEdKxQtDnhgskDBUHunNEISSqhONFn5vuspEqcnBngyKErnEdC0qrJyutXhyMMdiw91Qtb5e0e80yN0u1ff6Qn3HMY+4TiTmbtipAvk2UcxjfdvV3NLP4jqQDwjrA65eGLK3K0UhZWL7Pvu6MqTNEk1vd8sOf/fdKY7tKVC2PV4Y6QIioVhpeZRbLvnE2mD7sqLz/BBNV9AUgdBUEFFtRspUcYIQRaj4oaDWcvn62XHGSg6uF6DrCgNzDRYb4/zw0V6mqjYNx+fqbJ2OpI4qJG4g0QR4SwWM05UmFyaKlFa8dy7FHp9f+M13+Wd/7jgL9Raji01ato9UYU8+wcl9BToSBqomyJp6JPil5NpsnY6UwScOdfHWaJEwBF0IVKFgKAJNUZZG1YakTG2DFbBe0d9NkHt96vQTA3neHS+x2HBIaFFywFZKIa4TiblbdqpABLTdtHYCcS+sDxird6erK7F1RSFjagwXElTq3q7N8BBEjR3fnSiSSei8dXORgZyFrqvcWGggAENX1ggoTVUYzif5vQvT1Fo+iw2Hw90ZEpqKrYT4gcTzQyQhli7IJEzeGS+jKiLa4asqo6UGR/QMv3V6gscHs+iqiq4KhKHz0uFevvHeNI4jMU2iPleBv0p53ObUeJV/+LtnqTQltaViw960gaGpXJgqYXvgBwF2IBnMJzjck0FVoo6/AMcHO3h7dJGqHSAJeXp/gZlKC8eXhIFsK8jvRz8riUSKyL0oN/a23EBcJxJzt2xLgQghfmfpSwn8ihBi9Z+fCjwOfH+X1xazC6zend5uNSLpyyc4PtTBTKXJRHV36tUlUYX461fnKbd8HB80FYY6EvyVFw/SnbE2CCg/CBkrNzkxlEdRBK4fYnshf+dPPso/+cNLzJQdfBkymLP4iaf3sth0yCV00pZG3Q7RFKi1fK7M1ZgqtfjulQXSlk5P1qArbfLZR3t5dCDDufEKffkE5ZbHdKXB9fn2Ybu3bpbpSlt4fsBU2ePmQvS+V6+VADCA/T0WHVYv+aTOhekqnWmdpKGja4In9+TpSpu8cmWOm/MNVEXw2SN9HOhJbSqQNxtffDcsx1SWs8nupBBCeeemjTExm7FdC2R5KqEASqyZTYcLvAb8211cV8x9YL1FkkvqZE2Nf/7ta7t2jaQC46sUkuvD5bkWv/X2GP/tZ4+SMLQ1Amo5BrA8i9zSwA8cPn6kh2f257k8XcfxJW4Y4noBF6YrQNSS3fECmkiCMGpuWLF9TF2h0nRpOT62F/CXPrGXl4/08GZvEV+GXJ2p47qbK0zbhWsLm+eEuMDlOZvr86PU/aiN+2LdpaEHGPrtBo5P7+1AEYJQSqZrLfry5sr8lnYsv748y+NuhfdOYyqKiOtEYu6ebSkQKeVfAhBC3AL+ady6/cPLaovk+J4CXhDyaF+S92aa93zuDkvBNBQaqxTIss/z1M0Kf3hhmk8e6kXVbguo1bM30qaOH4YrAiyZSdKViQaH2K7P964v8rnH+zg7UeH0eAmQdKUNetMWTTcgaagIoNKKYj5V2+WVS/N8/ok9UVbW+Wlqto9QFU7syXB6orbhHuxtVin6En7rzUne7SvzkyeHGSwkONqXJ2GoSwox+tOqtTzOTVSoNKP4z7GhQtv4wv2qVt+OQohbwsfcLTvthfX379dCYh48uaTOJ0a6EH/iUW4sVPn6mUnGig00AY90GaAo2G6I7fvM1reWrBrQm09AGDK9pEBWB8yEAjcWG3Sky/zkM8MrAqru+DheyNW5GkIKRnpTPLe/a4MACwFNEeiqSiFl8Oy+Tuq2z4+e6Ges2OLSZI2bi3UcL0CKEF2N/P/vjJbJWiZZS+PEUAFFCFqezzfPz7JQazBeCdfcw06ceS5wcabBv/7WJT5/fAiJ4PkDHfihpOl6mJrG6fESM5UWCUNloeFi+yEvHupaU5PhByFnx8soqiCX0PFDuWvV6ttRCLvpQot5uLijAhFCnAU+JaUsCSHO0T6IDoCU8sndXFzM/ccyNE7u7cDUFQ50ZWk4PsHUBY7QwXvTZQ70JHE9n/l6fcsWIj5QbTjk0hYdlkLRDld+UTQRVW0/2R9NCkwszaxY9td3pAxeGOmi7vqEgSTVZrqioSoI4NJslZShkdA0EobHbM3l6b2R0D4/XeHybA3XFxSSGns7U6RNnfemKxzty9BnJtAVwWLd481bCzRchUJSwfVDBNvrsdWO2abka+9O4YchTcfDDyUXp2wSusa5yRInBjvpSJq4QcDZiRICiaGpK8K96fqcW4pbqKrgYFdmZTTt3QjzdgrhTmm6G5pgxsRsg+1YIL8JK4k6v8kWCiTmw8l6gfMfr77Db5+dAeDqJsHmdlgafOJQJ+MLKcaLNa7MNkFALqnxucf6yaZ0kpa24k5Z76/PWQbFhtNWcGqqwqG+DOcnqygEaIrC0b4cbhCQMFR++NE+jg5k+LU3Rjk3UaE7bdGfTyAlyFByY6HJTNVBAcZKdaSUKAooQuAuXUPl7pXIXMPnq6cmeHe8TH82iR0ETBabNL2QqbLDp4/00pOxmKu6mJpKIRUFuN8dL+FLSUJXSegaCMnF2QoHu9Ib3E47qdVYrRDiNN2Y+8UdFchqt5WU8u/d19XEvG8sC5zfPHWLhhsSTQDfGaZu8sy+To70+ihqL/Mlm8vzDXJJjc6kxWAhsaYKe6f++u60yWN7sqhCrMRLAm6/vzeT4Gc+vp9ffXOMYsOl5YX0ZA2CUPL4YJZzE2XeGS8zX7MRikBVBEhBEIRRC3lDQbo7H3C1TM2HdyfrvDtZxxCQNVVUDcYXPX7zbYfPP9ZPb84kaarYvo+uKLT8ACHhaF+O6/N1/DDEdkIO9WV2paPvbjZzjIlZz06bKX4L+DEpZXnd61ngP0spP72La4t5wNiuz79/9Qaf67274zuzOpamcrVa57GBLPs6Mjy5t0C15fH0vsKGjr3t/PVH+7KbZiJpqsLxPcuNGd1Np/T9xNNDXJ2rRZMPVUEQQD5hsFD32FtIkdQ1UqbG+YkyDdslaWoYasiffHyAt8cWKTdsFlr3Zmi7EhbsACPSUTi+y5X5Oi8d6ebsZAUFQYikL2uRMjUURXKwN4XjBSAE3atmityLErjXSveYmK3YaSHhS0Sp8OuxgE/e82pi3lfqrk9wl52x0joc7s0yX7OxvZCbC000xWZfZxI/lLh+e4G82n3WdH0uzlS33GVvZ0rfZKXFi4e6WbajTo2VmCg3ma60SBkqSEnG0DjSn+WJwRwC6G3dZLC/m8lqEyklTmhT24UKS1eCJsGV0f3PVGzySQOEQBESVREMFRL84XuzeH6Iril8/vGBNcL9XpTAblS6x8RsxnYLCVe3cX9SCFFc9b0K/AlgcjcXFvPgSRsaezrSwNYpvX1pFU1Rma266Dr0Z03+8osjFJImQkjyKZ2EodJ0A3773QnCAN6bqvLoQI7nR7ratnwHeGemtq1d9lZT+to1Dzzal+XLb4xF8RBgqCOF6wcc6E7x408P8oNbJeq3QuaLTcIwyh4LQwVdCQnCu4+LLBMSTVwcLdbpyZmkTZ2m40Ut91s+NxYaKxlioZSMlhr05627dvWtf1YftDTduO/WR4ftWiDLbdwl8Idtft4C/sZuLSrm/cEyNP7qi4d44/X1rc5ukzYEezpSzNUcOtI6Q51JXn6kF8eLdtOaonK01+LKbJXr8zVmKjZ7Ckkars8rl2dZqNl88Vg/+ZS15rx3u8vejnBNGCpHB7Ps7Urxg9EiTS/ADQJ+8tFeFEUhCCPNYmgKvVmT8YUGKUvD8gO8MMTxJZoCUkLzLgIkIeAGUKy7fPviLP35BA3bx5eSzqTBn3l6iN49iZX3r08kuFcl8EFK040D+h8ttqtA9hNtzG4AHwPmV/3MBeaklHfbFTzmA8SJvR1cPWtgEK5kJ1lAR0ZgKBr9nWmSpoYXCsIwILPUWbblBTzWn+NWsYGuCR7py7BYt5lSo5YapabDqdEib48WeetWkb/2qYM8Ophbue7d7rK3I1yjcbiS7qzJnz42QKnl0rJ9Fmou46UWt+abDOsKTwzmsTSVcxMVlDCkJUO8IKrWtr3N297rCvjh1umJAVCzQ1QRUm/VyKdMdF1loeHx+rUFhjtSWLpKKGXb+75XJfBBSNONA/ofPbZbiT669GX8KX/EcYOQbELnn/65I5y6WSJrGSAkn320F1NV+J0zk5ydqCCARwfyHO7L4AYBR3qy9OUsMpbOuakyjheiqgodKZ1AhvzgxiI118dUVSbKLf6/r1zjl37sCdKJKKR2L7vsrYTr8o7X9SSn50oMF5KkLI3Q0EiaGtmEzmS5hdMMaTg+5ybLJE2VjGlyZaZCdRvzf9M6BELFUCJF2tikwbFPVMHuBODVHfJJg7SpUXd9fnBjAXOpBfz6GMgyHwQlcC/EAf2PHjueMLM0++NjwDDrAupSyv+4S+uKeZ9Y3vkO5JL82FOpleK+xwZyaKpCT87k1cvzJA2d6aqNlBIZCI4MZNFUhVxSWRHmjw9m+b/fHOPqdJVi06OQ1MklTHKWzq2FBpdmquiaymDepCuTvKdddjvhunrHm+sw6Ezr1J2AJwaznB6r4AchfgCHezJMFSWnbi0iFMGnj/TyR+/NUGpuL/phmjopQ0dRoDK3vZYwXgilpguEuH40Nz6Z0FCEWBMD+SjFC+KA/kePnabxHgF+l9surWDpHB5RsWGsQD7kaKpCQlex/WDFT726DXnWMujKWliaSmc6ck0pytq002VhbqgKP/7UEH98cYazE1VSlkY+peMHIcWmzS9+9TyKKtBVhZ/99GE+82jvPe+ylwVuGITM111KDYehQgqApKFjeyENJ+DcZJnZqo2uqPTmTAY1hSP9WcZLLWYqLTRFISD6JVfYempjX0YnkCoKcts1JJJIiczXfQ71wnTdgZqDqgo6kyZuEO5oquOHgQ9iQD/m3tipBfK/Am8Dx4GZpf9zwL8G/vtdXFfM+4iqiE0tgWUh8PqNeW7MNZFCcqgnQ8MJyCXbF74N5hN8fKSLS7NlJktN3MCnZgcM5lQ6M0mqLZd/8a0rHBvKrDRPvBuWrzlVbPDd64vYboDtBRwfyvP8SA+6JhDAtdk6uqqQNjWCAGbKNoMWqAp4YYgiogmGqoBAbq08Mhp0pKOg+ELD2XGbBgmcnSjx8f2ddOUsXC9krNTA9Qq8PVYhbarkLKNtvODDaJ18kAL6MffOThXIM0R9sRpCiBDQpJTvCCH+NvAvgbgX1keErSyBlKmS1DWeHM6RNrQNzf/aBUufPdCBHwa4QYgbSC54ZaRQkVKSTRiUWi6TZaetAtmOoFy+poLg+9eLXJmuI1RIaQqnRstoqsKJoQKH+jKcnSiTMjR6Mwn8MGS+ZuM2Q+yWx8Rii4FcgoPdGYQiuThdJwg2T+Wt+fCdy4sc7E3RnTa5vkUr+M2oOfBrP7jOxw70kU8Z7O9M8b3ri9yYb5BPGRzsypC21rbB/zBnM33YYzkxt7mbiYTLTt55YBC4DEwAB7c8UAgLeBUwl677G1LKv7v0s78B/D+I4oxfl1L+7R2uK+YB4gZRo8TlGR6qQtsZH6uDpemExstHesmndFwv4JcWGjQdl0JCp+F66KrCYN7ccK3tCsrlazpByI35BpYeCam0pVJuenSnTY4P50kaGiqCcsMlkBJTVZirOvTrcKAnQ90JcL2QJ4fyHOhJkdTnSRoKuqZycqiDd6cWuT7T5PJck6WekDgB3FpocOixnk07+mb0SAltFmCfqkm+9d40P/b0EBemK3yxe5BC0gckl+eqHOhMRRMdN1HQcTbTWj6M1tmHkZ0qkPPAMaJ03jeBnxdCBMB/DdxpKpEDfFpKWRdC6MBrQohvAAngR4EnpZSOEKJnh2uKecDcKRi6/udN10MB0qZGQtfIJ0x+/MQevvz2GOPlBoam8rOfPrzB+tiJoFy+ZtPxo4K8JWeSIqJeIglTJWloTJaanBotcnq8TM322JOz2NedIaFpaIrCSHea81MV8gmNUtOhJ5vA1BQOdKcZ6cmy2HK5NW9jqFHdjJSSQIQoSNKGyqeOdPPHl+bXrE0BurMJWl6AJjwqm2R2VT34g/OTHB/uxg8lI91pzk2UuDJXp9x0OdqfpeEE6JqIs5m24MNsnX3Y2KkC+UdAaunr/w9RQP3bwALwk1sdKKWUQH3pW33pnwT+OvBLUkpn6X2bV7HFfCC4UzB09c9nqzbjpSbDhSQhIcWGi6kpPDaU4/947CQ1J1jJwlq/a9xp2udIVyT8BwsWE+UWYQiVpsdQp8XzI134QcjvnZ2hYnv05Syylo7t+VGQPAw5M1HG80M0FE7szZNLGTw2kGOm4uAGAVfmq/zIk4OcGS0RSPD9AENTUMJoBvlE0cYyVb7wRA83ZsvM1lx6UiqhYqFpgpSpUddVKoutDWtfQQhMTXBxusrJvQUURXCwN80zezuQwLmpMieHC3E20ybE1tmDRUh5b03jhBAdQElu40RCCJUoCH8Q+N+klD8vhDgD/DbwOcAGfk5K+VabY78EfAmgt7f36S9/+cv3tO7tUK/XSafT9/06HzR2ct+hjArt2iFlNDBKUQSKiL4PpSRpqJFlsIoglLS82+HqhK6iKiI6XgjEquPTprblsYqIjgtDiRCCQlLH0BT8ULJYd3D8cOWcXhAiEGRUnxY6pqZi6QrLv82aKmCpBUoQSlKmhuMHTJVbtLwAAQgEKTO6p+XsM9sPkFKiKcrS9aLzOX6I4wWbxlRMVZBLGniBRFejs6dNDUW5fa/JJcun3fPaKR+13/FQRu1tVj+L5We2+vF81O57u7z88stvSylP7tb5tjNQ6ne2cyIhBFLKH9nqPUvV6seFEHngq0KIx5fWUACeIwrSf0UIcWC9QpJS/jLwywAnT56UL7300naWdU+88sorPIjrfNDYrftuuj5v3SzSkbod2yg2HJ7Z37HSpwqiXeMbNxfJaerKjtr2A57b3xml3E6VN3VHbHbsi4M57CAkbWhYS9eyXZ9/8UdX+MFYkbSlE4aShuuzvzvJx415wq5HaEg4uCfPYsNBIsknjA1rinpYuVyarrLQcOjJWXz3ygIzZYekobInn+DsZIWG7TJTdQhCCGTIDx/pxw0Dvn15jmuzjQ3ZXRkDPnm4lxP5AoamMlBIcGmmxr69eUxNo+54BFLywkjXrtWIfNR+x5d/H6w2v0urn9FH7b7fL7bjwlrc7YtKKctCiFeIrI4J4LeWFMabS9ldXaxtlxLzIWS7hWPrXVWaotC0HZquTy5pbOi+23T9O7q5FFWhK7G2cbSmKoz0pLkwU6Vue8gQTF0w0pNBaS5gaAotN6DueJi6wtG+LBdnqm3ddOmEwckDkVvse9cXyFg6uX6DiVKTizNV5qstqo5PIWXiBj7z1YBLM1X+m8+MULd9FBniBQF2EOB60JnSePnRAYp1j6lSi88c7SOX1LG9gJmKzWTJ3pAyHWczbSSuNXmwbGeg1F/ajQsJIboBb0l5JIAfAv4norjIp4FXhBCHiarbF3bjmjHvL9v9Y16taFwv5NJslZYXYOkqx4YK5JL6pqmrKVPddjzADUK6Mxb/1fMjnJsqIwLJzXKDg91p/EmVWdfHdkICKTk+WNhWzYIbRE2wlgdCDeQTWHWFgazFt68sMLFYZ7RoIwSMLjaptBxSlkFXJknV8ehQFTRV8F88u5++nMmZiTK+H2LqCo4fRG1XAknnsNk2ZRqiXXfTjXK/koZ219ZJu2M+jNlMca3Jg2PHrUzugX7gPyzFQRTgK1LKrwkhDODfCyHOEzVm/IvbiafEfDjYzh/zsqI5M1HiwkQVy1Q4ticPAt4dL/H8wS6ATYOj291xLisqS1P5xMFoBvuBZpqErlJFcrArzaG+DN1pc01CwHa6Aeua4PHBHHXHw+1K4Xkhb95Y5MKijbqU7usH8PZohR8/OYjtSyxDxdDgU4d66M2ZGJrKwa4MF2cr1GwPQ1c43JPhymxt05TphbrNa1fnmShFSupQT4YjfRnGSs0t3X6rLTpon7kkkR/abKbYOnswPDAFIqU8C5xo87oL/PSDWkfMg2c7f8y5pM6JoTy2F5DUVW4uNgiCKEZxqDdDLqkTBFHK7Fi1hUrUmLCdm2uza622iJaF4vMHu0mZKq9OaTx/sKvtscsCN+rqy5prrD1npMCeHu4A4LVrc7x+q4wIAQGKstQDq+VwtK/AYsMhn9R5/mA3t4qNSAFq0UTFhKGuCPjrC/W2FtZCzeYrp8YZXWigqyp7OpJcm6txebrKk0N5cgkDPwzXWCzrFUUQyraZS2cmSnhe5GZbqDlMlW0uT1X4yWeGVxpgxsQ8SAskJmYNtutTd/2VQHfS0EhoKlfn66QMDZRowNKVuRrP7utgfLHO185OM12xsf2A3lyCYsPl808O0LnKatiKzSwiRWwcoQu3d+aVhst4ucVwIUU2qa3Zjbc750SpxsGeFBpRu3dVVbD9EAGU6h7llouUkqP9URfjvpy1qQJsZ2EBvDtRYb7a4up8nSAIOTVaZE8hQdMLkFLQkTYY6U4TBHJlTPB6RVH2grZDuS5OlvnutUXeGV1gYVVTyW++N80/+YmnGeq8+5YzMR8dYgUS874wulDn987O0PR9kprGF44NMNSZ5FBfhvOTVRQCNEXhaF8ONwgoNhy+f2OR+bqNH4RIKZksNvj1U+PMVW3+0icO0JneWMneju26N5Z35rqiUGr6pE2NxaZDZ1rfEIdYfc7/67Wr/KtXb+F5AQhoBmAQpfIO5gwEgoSu8MT+Dl4Y6V5zjna0U1BN16dYdzg1WqLc9AhllAl5fb7O/q4UZduhO2tycabCSE8aY5OEg2WW40iaolBsOJyeKHNzobZGeQC8cavKv/zWJf7Bjz65kt3W7rl9GOIPH5Z1fpCJFUjMA8d2fb56ZpJy08VQVWp2i986PcFfffEA3WmTx/ZkUYUgber4YUjF9nn9xiK3FlsU6z6274MEy1BRFMFUucWp0SKfOdK7q4JgReCqAj8MySUMKi0XRREEXti2oHGiVONfvXqLpK5iJXVcv4HnRR1793dl6c0n6Ezq/PSze+nNJba93vVKTwFGiw1AIZs0Waw7hEGAKlQeH8xRanrUbQ83DDnck1k5dn3CAUSB99UNMuuuR90OaDrtewufGS2x0LTZY2yso/iwVIEHoeSNm4sf+HV+0IkVSMwDp9zyGC82Gcgn0RUFL1QZKzYotzy60mYUOJ6rUWm5UexAKOQTOuWGTdn2VzretloBHbaHZUSZSrvdymM5QB4uFQQ2XC/6Pmw/NRDg+lwUvE6ldabKdZpLva8myh6IOp0ZA8tIoGmRFVF3XRwXCkkNQ9e2vRsOgaFCEk0TmKqCgoEmorhQylTpTJns74qaRnRnIsusXVZcQlfRVIWUyUqDTF0I5mpRHUzb56KriHBj0eL9rgLfLYvBD0JaXhDVDsXV6vdErEBiHjiGJlCFgu+H6Eb0vyoUWq7H967XaNg+ioCD3WlUTXBttk4gI3G2XqTNlFsULI2kpe16K4/VArcjpTNWajJcSOGFckOm13IqbW/WRFGg1LCpLLl/FCCpwnzdoT9n0ZlU+cdff4+pxRqXphs0g+g9B7p0fujoIH/uhX0M5lPtF7X8DFWFvnyCF0a6uDJTw9QVKk2f40MZwkDQXbBQ2mSkrXeHvTYRKYL1DTJ/6Ggv1+brLNQqrG7dlTbg6X2dbd2F93Pi4G5aNsvxoGUXXtxL7O6JFUjMAydrGTw30sHp0TJVJ+pF9cz+AhenatxcbDFba1GsO8zXHR7pTVN3Ao72ZVeUh0qkSEKiTrgJQ+PxgdyKYNhNIbBa4LbLwoJIuL1xY2FlPsoPH+3jd96dJFhaa2faQCJpOB5vXp/jwlSkNNZzacHj0ndv8WunRvl3P/MsT+3t3HRdmqpwfE8B2wvQVQXXDzjUm+HZ/Z0Uknrbda4+dtNmlK6HokTtX/7S83t54/oip0cXmK8HpE2FR/sL/Mzz+9vGP+7XxMHdtmyW1xP3Ert3YgUS88DRVIXPHOkjnzRo2B4pS+dQT5r/fGaKSstFFYIrc3WqLZ/Zqk3O1BlbqJPUoj/w5UmBKpAwFE7uy3Nxpnrf/NlbBd39IOTdiTJTZTvalQtJwlD5f376IP/m1euYKoRCUG16hCG8Pd7YtA/WMsWW5Oe/8g7/53/9/JaWSC6p85kjvXz8QKRolosI7/YehwtJfu/8NJ4frsxm/8TBHt66uUjV9jBVhecOdtGbTWx6jvtRBb7bls3qqZtxtfq9ESuQmPeFXFLnxUPdK66UKJU0xPclczUH2wuwXZ9aM6CkuoBksJAkmgqw1NwQ6EobLNY9cimjbd3D/cYNQpq2jx9IVEWgKgotAga70vydzz3Kv/zWVUoND0NV2dNpcG5mezPTxxddvvXeLD9xcnjTbCeIhGF2XV3G3Vahj5WanBgqRO3wpWS01OC5/Z380KN92z7f/agCvx+WzVZTN2O2T6xAYt43Vu/sk4bG4b4M37kyR9Px8f0o0GlpKpau4gYBF2caG85xc9Hmjy7NcGyoY2WeR3AfAuqb0XR8bi42mSg1ma3a9GQtVAUSmspnnurl2N4c/+7VG4x0ZijWXc7N3NzWeW3gvZkKr15d4Nn9neSS+rYUw93GCpZ3+TkrEglBKCmWHRYaNl0pa03zyzux21Xg98uy2WydcXrv9okVSMwHAk1VeGGkmzCU/NHFWTqSBosNF00TBESCrdRqP538rVsLnBjuQFcVLkyXGepI8iD+7P0g5NJsjSO9WRaqTU6PFjFVwTMj3ezvSqOpCvs7M3zmaD8T5Sa6JjDVKG5zJxRgfMHmSr6GRPL03gKXZmob+oCt7oEFm7d72UxQhjL6f30/stPjJUaLDa4tNDjcm+a5/V3va5rrg+pv9WFJQ/6gECuQmA8MuaTO5x7v5/hQgVeuzPK/v3KdQEYt1R1vc6nbsn0W6g4J3efmYoPOlMmpsdJ9/+N3g5BKw+U7V2b5wwvzhKHE0hWePQijpQb9eQtNVXh2fyf6qKDa8vjikwP85umpTRJkb5NNqAwWLMotl8vTVQA6U+aKYnj9xjxhILm12EIKyZ6CxVAhSb3lkStELq2tYgXlpsvZ8TJ12+ObF6d5YiDP0b4s56cqnJuoMFNp8WhfnoShMllqcUYvrbSRvxP3awd/v/tbxcOodk6sQGI+UGiqwp6OJD/1zF4Gc0n+7WvX8QNJ2lQZXWy1nTe+aMPvnZ3ipf9/e28eHdd1Hnj+7tvq1Y4q7ABBgjspUiYlUatlWZIlZ7Hj2Ek8bXccj9vJeHqcnqQnSU93ptOTpJNzptPdOc7SiU9nuqdtTzyJ7bQdJ5btOLKtaKUkSiKpheIOgiB2oBbU+rY7f7wCBIIgCIIgNt7fOXWIevXqve9WFe93v/ttu9vpzcbZnI0jubJq7XKjAaeGpnjyrbGws6GuUai6fPVIP1uysZmJOx0zuas3gxMEPLijhdZkhG8dG+BiYf4G6TEjVBatybAsSd0PCHxJxNAbtaskpwZLWBGN5kSEgckSX3juAlFDYJg6P3F7N3s6UzO+Ao2wZth0FJkGvHh+glPDU2RqHt978SLfsof4sf1dHOxpolBxiFr6jPKtuoK64y9qW3A9r+BvZhjyRkUpEMWaxNA1Htnbzh2b04xOOWg6/Ptvn+B7J+av9H9mvEqu1McHDvZwbCDH3o70TfeFBAAalBxvpuMimmBsyuHF8+M8tLttZmspZhnEIwYgeGhXO01xiwvjZYZKJcYm64yX6tR9QdTSMXWNjnSEkuPh+QF39jQRsw3GS2FfkELN4fxkmR1tCaQMePlCDtvQaU5GSNg6T7wxSNLWSURNNjfFONKfo1BxuTBRoTMVwbZ0jlyY5FKuxt22z2TZoVB1efr0KEhJMmIyXnZwfB+kCLe6AknN9Ra0Ktb7Cv5mhSFvZJQCUaxpmuI2TXGbmuOxvS3FttECfRPuvKGwuRp8/aWLoMGedptPPrj7pvpCLF2jKWYiGn97ASAlUhKWZR8uzkyehh42qDp6MQ/A3o4UHzrYTSZqMl6u8+LZCdJRi2Ld4dJkjb7xMnHLYF93indvb8ULAr72ykUEYOoaW1piDBdqgKTuStIxA1MTtCeiVB2fba0JNmdD5WFqgoFchdFilaFCjdaExZsDBRK2iZSh7HU3wBCCM+MlfvquTbiB5PToFLW6T933GS/XOTNaZmfn1f0hi1nBr2UHtWpGdf0oBaJYF9iWwYcPdvPMqVEszaU2jwYJgFIQ/nHkUo1Xv3KM3/lJnw8e6Lop2yiGrvGeXa184fk+Ros1fAmGgK5MlF2dl1tA+YrDieEiAgiQ7Otumsnm7tA12pui2IZOezpKd1OcXZ1J7t6SIRW1ZoondqVtxkoOEFo0FcunVPfxZICpCTrSUcqui23qdDWq+5brHvGIzqVcjXTUou4FRE0dKQSe38julxCzw5ImhhCkbZNH97RxqLeJH5wY5tX+IrapUfBdzoyUsE19Xn/ItVbw+YrDsYE8UxWXuu+zpz1NZ1NkZoxrAdWM6vpQCkSxbtjdmeI3P7SP333iBCcuFS8rsTEfAfCFp9+kJWnwvr2dN2Uy6G1O8OkHt/Hd1y8xVqoTM00e3NlGxNRwg3ASmr21k7Yt6p5/hXUyd+U7d5WvAYOFGomIQdwyKTsuTTGLnznUxSO7W/mrVwcYLlaxDI1/fM9minWPk0NTnB0pE8iAYq0OUhKxdKKWTmfapitlY1TGQwViGbQmbXZ1JGcSEg1NYyBfxzY0mqIRXD9guFhnW21+v8BCK3jPDzh8bpxj/TleOjdB30QJoQsOdGX54IFuHt3bfoWSXy1rZa00o1rL1to0SoEo1hX7upv4zHu28trFPM+eGma8VKdchepVlMnpnOSV/hzv2pSls2n+DOobwdA1PnxwE11NUYbyVfJlhx3tSdwgmJk8Z/fb8INwi8uZU81XF5LudJS4rZGN2VdMGAGwORNjsuxSqDoYmkZvc4xExOKebTFu60yRq7oIITk7VuHZ0xPYEY2uJpsfnBji6MAUuibpaophG4L37myjKWaSPz/AQ3ta2JKJ0Zq0OdCTuezehhBousANQpPPD4IF/QLzreA9P2C8VOe1czmePDnC+YlqYwtS8vy5cXwkTTGT9+x6p7T9Qs749TCx3ijT4y9VXaquzz29WbqzC9dHWw2UAlGsKyxdw7ZMWpI2925v5+3hKUp1jzcHp676Hk1qnBqdojW5uKZT87HQpJWOmTyyu+2q9bKmt3amneBV18OXkgM9TcQsg9cvTvLlly7ieAGWofHJ+3q5rTt9xbhTMZPmRGQmU3zawgFIRC1sy+Dw+Ql0IYhFdAxdcPjcBFVPsqMtQcQQ1L3QivjEfb00JyI8PWzx2XfvmLd2VpjcmeLM6BRDhRp+IGlLRbhrS3bBz3H2Cn56IsyXHY5cHGewECoPQVhNoObBq+cneO+uNu71m2cUztWc8aW6t26jvBbL9PgvTZb5/ttj1Fyfbx4b5Fcf283tPU2rLd5lbEz1rdiwGLrGwcZ/opa4TW9LnK3ZGKkF3hOP6NSdsPPedNVcr1F4cfr5QuQrDofPT/Dy+UkOn5+gULky/NbQNWKzOitetopvONBPjkxRdT1sS2dve5oTw0Xy5RpffukiSdugtzlB0jb40uE+SlXniuvf3tVE3fWZrNSpu/4VDt5pJ3YiYuK4PmdGphjIVRibcohZOm3JCJYhsAxJxQ3HrIn5C0RO3/Perc3s70rzwPZmHtndys81FM9imK0ImmImCTuCH4TKA8LJRwCBhP6JysxkNOOMn1Ut1/clFcebuV42HsE2dF4fzM98lxsFxw8oVV2+//YYMUunJxPHNjS++ML5K34Xq42yQBTrjuZEhI/e1cNrF3Ps7kwikGzN2vzx0xeuONcEqk7A6bESngzQNQ3b0NF1weZMjP5c2L+jVPcoVNx59+GXGpo622qJWjo725KkogampqE3Ov+NTjk4XkAyEib/JSMWEyWHXNW9ove4RCIFCAnyynYcaIAbhApRCA2JwDAETsnlpTMFRqvvnDtZcnn8tk6MmsvL5yevuppPx0we2NFyXVtG0+P2GorAIeDMWJlM3CKiC9zgndL8OtAUt9jeGsfxA2yu7owHbok8DUvXqLo+NdenNWHjBQEJK2yuNt/vYjXZOJ+64paiORHh4V1tPLizhbt7M1wsOsT0K8/bvylFNmFxYFMTl/I1zo6UEQhKVZcvH+4jX3JIREw0IeZdzV5tNexcY9U712qpOj4RU0MQFlysOB5uEJCNG1iGxlQ9XFlO1R0sQyMTnV+RxS2DzqYYccu4TN58xeFIfw7HlbzcN8FYqUpL0qI5anFqpHKZ8gD4zptj/PWrA9TdgETEnFnN1xzvMgsN3rGu5k7Sc625ueM+2p+nUvd4e6RI1NQ5sCnDPdubaYkbmBpEdOhusnl4TxuFusfR/jyFijtjbdW8sJVxzQutrZhlzCgWYMPmaRi6xj29WTRNMFGu4fuSWETDNvUrfherjbJAFOuW6b32kUKNvz8+xJz23bREBT9zqId9XWkmKw4nh6cYyld58q1BxqYcinWXH54c5bbONO/LyHkTD5eSXDaf1XJiuMjejhQnhouMFKpczFfZnInz9kiZjxzcxDeODjBRcmZ8IHNXmdOKzLC0mR4gvu/NKLLp3u22oWHpGudLdd4azHPkbH7e7H2AZ89O8niz4LX+SXpb4uQqLk/Xx0JlKWBXW/KqfqPZTm4EbG9JYJlwrL9APGIQsQxc36fseJSqHhoCU9f4Jw9sZ7RYxTYFl3I1pmoeTUmLve1pTEPMWHdXC6e9VfI0urNxfvWx3XzxhfN4QYDji3l/F6uNUiCKdc+Z4SLleQyC8aqkVHPCCXyowLnREsP5MqMlD68RteV6FYp1nzsjDrYfXKEYlpJcdrWEuqilc2hzhufOTnBHTxMxy6Tu+dQ8n3/1o7uZqvtkoua8k4RGOGmfHi1iaDqBlHRnouHxqsPEVJ181eP0yBSGLshEDJ4ZLFFb4HMLgJrrc6w/x9OnRpEC7ultZnd7ioF8hTcuFbi9K82BnsxlW1s1x+PIhUmSERNNSl67mOPrrwyAlBRqLhFDI22bOEFAyjZIWBY72hJ0NcXwgoC2Jpv7tjZTccJe9+1JG10LP8/ZW1LzhdNulDyNxUSS3d7TxG+17CNXda/6u1htlAJRrHuOD+Sv+trElEOx6nJquETU1CjWvRknriHA8aBcdak6PmNTNcp1n3RMm/kPrgFCSG7rTGJo82/lzGUhq6XieHhBQMS4vOChZRr0xO15rzedgHd2rMRk2WFTJo5lCso1jxf7JnHcgOfOjpONWkyU62hCMFkKs9SvRd0LePbsBE1Rgz0dKcam6owUx9jXlUZrhPDO9vnkKw6vXMhxYrBIKmpRdcJSKFM1l2KlzrGLU0yHGIQNv2BXa4ITw0V+bH8HXdnYjAKeLu/iBRJdW/yW1FrJ01gq11MvLBG11qTimEYpEMW65z17Wvnjf5i/z0Z7OsaBzWleHyiClJi6jhf4uB5oGvg+aJqGrgkyMYujAzlaoiYvnZ/kQr7Esb4chgxwpY8vBZtb4hzqbWV3Z5Le1jhtiRjAZavJaavl1QuTnC4Wqfs+d/dmGMpXODlc4u3BIv12hf2dTZiGWHDSnN4O04UgG4/QmY4yVffYmo3xzKkx0lELS4dixeHEUAFDN+hK2TTHLer+tevGS0BD4ng+p8dLVN0wTKq7KYppCmxDo1z3Z5zir1zIYWmCaETH8Xz6JsoEQcBgrszJ0eplKssHSg68eqmEKUoMFyv8nx+8nXgktMyWWjpkPeeBrPd6YXNRCkSx7rlnaysf2N/OE2+MXHb88T2t7GhPYBsG+zalkFJi6hO4foCOxPfDbZyIEXao84OAb75ykWfOjDNWnt9z8PpInSfenASgOx3hsb2ttMRsUnGTrkyMe3rD/fvxqSr//dV+XurL4XkBUUuntzlGdzZORyLK6ZEio4Uqd/ZmuLMnS8XxmCjVmCi5tKcsWpPRxhaTR6Xm0ZywMTSNiuNzcqjA37zaz1vDlZmaYLYeRjNtazUbRRh9muM2yBql+Yv+ziA0ganrSB8EEteTvNw3yaEtWY5fKrCpKUbF8Th6Mc+rF8IS8DFLZ6RYYzBfxXUD+ieqC9o7roQL41U+9/dv85mHdnB3w88Rj+i8q5Hzshjrbj1X+4WNV/FXKRDFhuBPPnGIT5wd5U+fPIlhCj6wv5fethg1zydmGdy3tQXbDJPrvv36IJWaR67qkImZbO9IkYgU+Ps3h3nm1BiT8xXamodLhTpfPDyAAJIRne2tcUYOVXl4Tyu//a3XefFMHikauRZBwJtDU+i6YHLKoVBzGcqXuZir8Mq5HBfzJY5cKIAE29S4f1sL927LMjoVbg9l4xYJy+DZM2OcHi4wMKcUfM2H4aKD70laUhE60hY72pLs6UwxVqzw+kCJ+fSIJqArHSVXdjB0yf7uNIgw6dHQBUjwgoC3LhUxEAzlK+SrLlN1D9cPsDRBMmriLKJJlisluYpLrlrn9cE8e9qTvD0yNUcZXF9wwnpbvW+0ir9KgSg2DPdvb+O2zgyvD+bxfTkT/hn25NB49/YW7u7N8rP39XBxssbJ4SLJqMlosQ75An3jZRx5bb/BXCThyvLsWIm/fnWAwpTL8YsFXBnmbDiA60t04XN2uEzF82e6Kw4UxsjYGjUvIKLrmIaG40uePzuG7wckYgaXchXGig6e7xO1DHILmBTjFRfTkIhAsre7iVLdJRmz6W0N2JyNUqy4DBZraFLgIbH0gEzMIhk12NeV4r7tzZwYmqI1abO7PYlt6owWq/RPlnlruMjJ4RLluksqahE1NSKmTj3waY4LRsoLf3YGELV0ihWPRMTjpb4JmuORmfpg11IGG2H1vtEq/ioFothQLBSlM+2fiFkGTTGbcqPnendTnP6SRnvapm+iwmKcz7PRG9cWAsbLLifH81Rq8rKS8z7gS7g0dWUmca5h8ZgGOF6A0ED6gqOXxsnlPPKzLjRdAuRqSGCw6OF4HqWzZaTQ6GpK8NDOVh7e04bnw1uDBQr1OjvakpijJ/mpnd3oukbE0Kk6YVTYttYE8YhB3fPRhOD4pSJRQ5COGSAD6p5PR8rCkyCloD0dZ6RcWvBzSsdM3ruzjVwlTJQ0NEEm5tCasKi6PqNTdaKGYHd7al7H8UZZvW+USDJQCkSxAVlMlM7slaDve2hC8L69HYwU67w5ODUT5rsYNC3cotI0jeaYia1r824XXYti7fJ9oPHqlecsVqzxyvRfARcLRV67UORSoUC1LtjfkeQf37eVTZkYzz5znnv2d2LpGvmqw9GLeXqzCU6PTlF3fVIxk21tCVov5vD8sBdJoe7hemDpNWxLBykJZIABV805SZmQjVu8eGECHcF925oRCI70TXDkQo6JkoMfQDyiceeWDP/s0Z0cnFXYcdpxPp1LM3v1DmHHxdmT8WxHO3BFnbK5LNYxv1wO/PUeSTaNUiCKW5bZK8GXhgzes78LXRN887UBTo9M4bkeNR9K88yKOtAc15iqB/gBGJrGjtY4H75jE2PF2nXaMDcfB/jum3kA/uFMjj95tp97NkX4QGedF77zFrt70oxOOvjCJx6x2NYcQ9fDvBWv0VK35rokTI20bVB2fdJRA8cLiEZ0iqXqvE2+IHTwSyHoG6/QnLTY1BQjbpmcHCnw5mCRiZKDE4RlZyr1gFf7JvgP3/X49Lu3c9/2FiTyMsf53o4UUUtHA3IVl6MDuVCzCtjWElasPTdeBgnlmosnwfd9LuaqdDdFaU3a+ME739BiHfPr3YF/M1AKRHFLM3slmI6ZfPiOTTy6t41cpY4MNCwdXrqQ4/uvD3Hs0iSZqMH7dnfx+MEumhMmQ/kar/UVMXVBdybK3VubOT4wifbUuatOqGuFlwbqvCfj8Z9fvwgvXLzsNR24tzfNS2eGOTowyasXKpdZVZmIYCAIKFRdAk9SXKAeZc2Hui+xjbAAZt0PODtepOr6SAKkBFOE34XjBdR8mJiq88ZQgUBKYrZB3DIuy+rf057krcEixwfyaJpGe9LizMgUX3v5AqZusKMtyfbWOC+cn6RU95gs1xEIjl8qcHtXE72eR83xMHRtUY75jeDAvxkoBaJQzMLQNbJxm+yspL6uTJz339aBFwRXJBN2pRMc2JS9bFtjd2eSrc0WZyfWVuXU68EHnu8r8HxfYd7Xc3VJrr748Umg6sFIsUxPNslYsU6x5lJrdAWThNFe0x0So7ZJWyLCydEpdrclycbCCsARQ6dYdXmtP0fVCeibKDNWcjg3WsQNBJYhSEdNDE1wKV/B0ASluke57pOIGGjAm0MFmpMez5weY/+mpkU55jeCA/9msGIjF0LYQoiXhBDHhBBvCiF+e87rvyaEkEKIlpWSSaFYDIaukYpaZOP2vO1X5xYbzMZsPnH/dpqjt+7EcjUGix4v9eV4/vQ4nh+wuzNBxNQIJDOl3tO2waO727BMHUOIGce5H0gKVYd8tc6JwSKHz49zYbxCqeZSa1gzlh4Wuzw9FvZz9wOJ50ssQ8NxA0qOhy4EQoRK4PTwFAiuWaBxtgN/ofNuNVbSAqkDj0opS0IIE3hWCPEdKeVhIUQP8DjQv4LyKBQ3BUPX+NDBbvIlh2+8cpb+q/e6uiWRQCWAVwem2Jq1+cidXRztz7MpbVPxA3a2JUlETIo1l10dKe7akuHlvgnOjVbwCSjXPKqeh+P6JOMm/WNlAgQGGhFTkLBMynUXJ/DZkorhBzBcrFB0XFK2hRACy9BIRU0KVZddbUnOjpcWDKtdK+G3ay0Lf8UUiJRSAtNxfmbjMe3J+hzwvwPfXCl5FIqbSXMiwicf3Epbk80fPnmS0Tme+KgG+zal6W6KcnasxBtDC4fAXit8d71yfrKG88YQmaRNPGJwoD1J1ZEU6y62obOlOUbc0omZYTWBsyNTPHHsEqVaQM1zycQi2KZOh2nj+RLPF7h+wPbWBD//0FZyFY9tLS5vj5j4nmRkqs621gQxLx/W4NIFrckIrcnINSfmlQy/nU9RrEUnvpBLSJxa8s2E0IFXgB3An0gp/6UQ4kPA+6SUvyyE6AMOSSnH53nvZ4DPALS3t9/1l3/5lzdd3lKpRCKRuOn3WWvciuO+mWN2vIBC1aFc9wFJU8wiFjGouz6aJtAQVFyPYtUlCN7pEhhMRwqJUH1IGRY/XE7aozAyT7jwamBoAk0IUlGTRCMHRUqIGBpeIAmkJF9xcfzQ8d74VDA1DcvUCAIw9NC6yMYsLCOceMOPURIEEMiwZL9fr6JHokRNHV2bpzvXPAQy/G5uNn4gqbrvhHRPy1iqh+HmQoR+okBKEpHrswEeeeSRV6SUh5ZL1hVVIDM3FaIJ+Abwy8D/DbxfSllYSIHM5tChQ/LIkSM3Xc6nnnqKhx9++KbfZ61xK477Zo95vhVloeLOZM0LwlLm5yfKjJcdPDfAk5J7tmbZnI3x3MlxcrU6z52e4NRYedmskV+93eP3X18bsTStMZ1ACLrSUX5kbwfppEWh4gCCl85PErcEL5ydoFALne0GYJrQm4nxwM5W9nWlMHWdO3ubyMQiM5/13JX73o4Ux15+gYceemhRVsRKrvw9P+Dw+Ykw2quRLFnzfN7Vnea1/jzZ+DvthCfLde7emiVmLf77E0IsqwJZlV+OlDIvhHgK+ElgK3BMCAGwCXhVCHGPlHJ4NWRTKG4Gi+ltUa776LpGMFzEsyW725I8sKOVdMzkts4UJcfjUw/08kffP8O3jg2yyJJd64ZSzceydKbqHqfGimQrEQYLNe7oyZCOGrw+kCM/a9Ae4LnQN1GhK1vmzs1ZIqbG3x4bYmdbkoipzSQezm3upTXChq/FSofvXi3aC1iTWfgrpkCEEK2A21AeUeAx4PeklG2zzuljERaIQrFRuDwPRePRPW3cty0LXF6d1rYMbMuAhM2vf+A27t6W5RtH+jl8obhqsi83tQDiGkhfYhhhZFZTzGKkUCVfccmV6/O+r+rDM2+PM14o05lN0pYK63RVah6XJiq0pGzS9uX9V4JFmnArHb57tXItMctYE078uaykBdIJfLHhB9GAr0opv7WC91co1jzTIcML0ZyI8NN39vD4be186bk+/uAHZ1dIuptL2JtEcFdvlge2NnN0oMDYVB3H82mOmdQWqA/jAMeGqhwfeqesvA6YOvz4uzr4R3dvmekAqesCuUhfxkrX35ov2mtvRwrHD4hH9DVXQ2slo7COA3dc45zelZFGoVjfGLqGbRp0NUWxBdQ2TIiWhxv4jJUcujM2rh8wXKgyWKhhG3Ct3MW5Da18H77+2jBTNZcfu30TLXGLAz0ZXhtYnDSrEb47e2uzWHV46fwkNdcjHbO4a3N21SOvZrM2vGcKheK6sXSNZMxge3ucN4fLqyLDprTJVM3D8yVX6cF1XTgyLAlzcrjIVN3FMnTevb2VoWKF8XKdaq6GswTfz9MnJuhMRnlkb8d1v3c1qucausZ4qcbnf3iaUyMlDF2nI2mTrzh86ED3mrA+YAUz0RUKxfJi6Br39LZwaGsLMWMF4kvnoAE/cnsnzQmbQIRbRjeK9CWuF7CjPUlnKkZPJsZgoYIvBe/f28H797ezJRO59oXm4AHDpdpMj/frZW61gQXv5QdUHA/PX3qUw3ipxp/+4BTfeWOEM6MV+ifKnBkt8dTJMYq1tVMiR1kgCsU6pjkR4bOPbAcRcPxCjqF8meFrNHZaLiRQrHjELR0BGBrIgGsWkbQN8LwrS7/HTOhtSeL5ks2ZKMcv5gmKAY4XsKM1QXtTjId3t+Hc2cPp4SJHLkzywrlxyvVwu2ohTAPKNR/XC/CFIAgk3ixH+HJleC9HyK/nBxw+O8HbwyWCABK2jhdIJit1IkVB1fEhvmQRlxWlQBSKdU57KsovPbqbl89PUPN83ro0xV+8cJ4pHyzg4/f28Nn37eT8WIk/f6GPF06OMrGUhiVzkEDc0vnAwS6++FwfxaqLc43wJktAZ8qiJRHFtgQnBvK4HqRiOt3NSSxTZ7Li8vTpMXa0xjk9XsL1JUcu5ImYOmcNjc1NcfZuauLhve38t+fO8/LZcSarDoIAMCjVwzL802hATzbK1pYEJ4aK6Jqgx/E5fH6C27uarigXv9Q8j+UI+fX8gAsTJd4YKFB2fBBQaoTxSgJiVoKotRy23vKgFIhCsQFoTkR47LYOHD/gg+/q5jPv7aV/skpL0qIrHcfQNdpTUQ72ZOjPVfj/nu/jCy9evPaFF6AjZZGORdjdluKzj+zgqZMj5EoOUzWP0aka5bq8zMqwdcjETHa0p9jb0cRwsUrVlVTqAS0Jk6rrk4qYRHSN0WKds2NldnUk6UhFqXk+pVpApe5zYqTARw52c3qsxE8e3MSP7uviUr7CYL5Kc9zi/ESJcs3nwmSZYs1lSzZONh6hsynKhckyD+1ohRGQgeTw+XEsTSMZNW84z+NGQ37zFYdjA3mODxTI11yyMYt82aHs+GF0XsRkW0ucmLl2pu21I4lCobghpnNKao4HQuO2znSYOzIL2zLY1Z7iNz60n//hnh6OvnyYGAGVq1xzIbTAZ0uzzV29GXZUExwbyNOdjuMEAW9dKnBqZApvliUggFjEQAK2qbGrPUl7KkLEMHF9n6FClVzZZV93inTM5MxYGUvT0AW0xGyycZM9nSlcP0DXBb4vSdsGMQsycYv2lM27etIkLAPHD6i5Hq/25YnaBnFLp1B1mSjVePFCjt2By98cvkBrwiIeMXhgewuRRJj9PVl2GCpUaU1Ervj8FuJGQn6nrRddCJIRgz3taaquz2TZRdddOlI2921tZk9Xak31mVEKRKHYQFwYL/GdN4dxvQDT0PjA/i56mmNXnGfoGrd1Zxg9HeXwbz7AicE83z0+yGv9k5wcrVK9llMByFV8Kk4wU0qjNxsnaZscu5RjuFi9bBtJAJah0RKPUK379LbESUUNTo6UqDk+d23JcvRiDk2r0pqwMTSNvokKFdfDNnW6EyZR08AyNIQGCcu4YrK2TI2mRrl9G0hFLe7fYTZCcH1kAPmqRyZmIgNJpeZzeHSCrnSUs2NlPnqoB88LePbsOCcGC0Qs/aqf33zcSMjvtPWSjloYmoapa+zvSrMlE0MguKs3Q8TUcYNg1bPPZ6MUiEKxQag5Ht95c5hExCCeNCk7Lk+8Mcin7u9dcCWdilrcu72Ne7e3Uai4fO+NQf78ufMcG1k4NFjXYX9XaiZCaVdHimMXJ3n57Dj5ypUxvYEfELV0opbGD06MsCkbo3+igifD2ladTTYSGCxUmSw77GpLMFaqs68jTdFxycZN3CDg9q4m7Hkys6cT7oBZ2f2zcypcXruYZ2yqRjXweXu0iKlBW8qmWPP41rFBDF2wpzNJezI27+d3LWf7UkN+p60XLwgrCZ8YLuD4AXu6UuiaQMLM2NdKCC8oBaJQbBhKjofrBcSToQM4bpnkyg4lx1v0Vkw6ZvKRu3q4b0cL//Xps3z58EXm87cLwhDePZ1pAPKVGodPD/Plw5eYr+CIBCoe1F2XmqsxOeVwZqxEU8yiNRmhu8mmKWrxwLZmvn70Ep3pKHHL4NDWZiSSD/V2ounaZZPy9GRdcTwKFZc3BgsgucIRPr21pwExS2eoUGVHEoSUgM6FiTK7O9KMlar4gSBf9UhGvJnPL191SQGVusfbI1MzxS93diRpTUTm7R1yvZP8bOvF9yXb2xLsakvSmgxDltdS9vlslAJRKDYICcvANDTKjkvcCi0Q09BIXMc+PoSTWU82zm/8xH4++Z5e/uHEKE++McyJoQIlBzIxnUf3dfLZ9+7Etgy+d3yAX/nKMUrX2PbygSN9RWwLOlIxuptiJCIGharDi+dzdDfZbGmOs68zTdI2MRuT5WixStAY31xKdY/jF/O8Plggaurs7UhjGmJeR7htGezvTvG1I/2QBNeHVFSjWHMp1xyaExEMoeH7ARfzFbpSNr6UvDVUBAmnRqfY257GNDTeHinyxqUi+zalOLgpsyzZ4QtZL2tNcUyjFIhCsUGwLYMP7O/iiTcGyZWdGR/I9TiCZ2PoGtuaU2x7MMXH7+llZKpKse6RsgzaU1Fsy2B8qsJ/+Lu3r6k8pnEB14Gp8TCzvDtjsyWbwDbCff++yTKGFva8CFf8Raquj23qHOi5fKKedjxruiBuGURNg7NjJfZ3p/H9K6OfPD+gWvfZ3Bwnata5Z1uWvokKmgwIhOTR3WGW+vNnxpgo1YgZGpuzMVK2iZSgC8H5yRJCQtwy0PDRxfzKaqksxXpZTZQCUSg2ED3NMT51fy8lxyMxXcF3GbAtgy3NySuOX8rXGS/NXyX3WuSqPhWnTDpqErV0upqaqNRcDmzJcG6szJsDReyIxoFNTQSB5Plzo9y1JYNtGMQakVah49lE1wUIiRcEFKp1vODKMhuOH2CZOndvaUYWJ9E1QWc6wgPbW9jekqApbhIxdB7d285Yqcp927OcHq4QMXT8QBI1DYpVB8PQsKWBoWkkIiaFqrPoUN211pL2RlEKRKHYYNjLqDiuRXsqXJ0vlboPhbLDZMmhf7yMpoc+iHu3Zqm0eiQiBm8NFTk1MsWFsRLfSg2yvS3F/u40d23JNBzPkh0tSU6MFMiVHSqOR29znCP9uct8IZYedi68vSfNxGmd3ckkpq7xM3f1YGgarw/mGSlUuZivsjkT58xwhZrnk6vUqXs+zYmwT7vj+pQ1l70dabwgWHSo7lpsSXujKAWiUCiWTCpq81N3bub/Ody/5GtMlKo4vs6YcEnYBv/l2XOcGZmiJWXj+wGDhSoXxssUaz5Cq5OJ1+mfKGMbGvu605wYLuL7kq3ZOM1xi45UlJhlXJEUONtRbRk6+zeluaMnQ3MidFQf2pzhubMT3NHTNFP6/e2hAs+em8DzJVXPZX97ip0dSTIxk4rrgQsHe64dGbXSjalWCqVAFArFkrF0jUf3dzBaqfKt42NLusZESWLoHolomNvheD5nx0tsa4vzd2+OU6y41H1JJm6FWepTDpsyMaqeT9R6p0eG5we81p+fyUuZLxN82lH99EWDh3a1YejazLaS5wcYmiBmhVaBHwQ8e26C3myco31jHB+u8tqFKQAyUY1P3N/LHT1ZTgwXr2lNrHRjqpVi/UquUChWnelV/eN7OmmLLu0aDuD5odN8quoghEBKQb7i0p6KkE1EaEkYFKsuXhCAkMhAEjX0GV9CzAr9ItPJhcBVM8ENXZtpaZuvOBw+P8HL5yc52p+n5vkz758o1Ql8SeBK3hiuXnaNXDXg6y/1EQRgNra/Fqq+OztLfSHZ1hvrW3qFQrHqpGMm79vbzuO3b1ryNRyg5MJoyaPmuBiapFR12dqcJBu3qLiSquOSqziYQmNLa5wDPZkrQl1v72qi5vlMluvUPH/BxLvZ20rZeIRYxEAgKDsek+U6lq7TlrK5kC9dVj5k+mrjlYDvvXWJZ06NcXG8Qr7qXFWJXK9s6wW1haVQKG6YRNTiQwe6+PbRAXI32K5itORT6cvz1vAUt29Ks605gakLAhlnczZOT3OUR3e3zRsocD2Z4PNtK0UMjdu7UjhBgKVpNCcsfuOvX7vsfdMqQgbw7JkJDG2Cug8TlToHN2euup11vVnqsyO2puVda9FbSoEoFIobxvMD8hUPbZkqjfsyoDMV58xoicFclQObsmxpjnFgUxO+DBYsKHitXArPDwhkaEnMradV83xeODfB+fEKpZqL6wecGa7Ne52IKQCBqevYhuDJE6Ps60ov6BxfbJ5HvuJw/GKequfjBwG6pmEb+pqL3lo7qkyhUKxbHD8gV3OYql773MXgB5CvuAjCpL1trXEyMYs3BvP4Ui7ZdzDt86g4Hkf6c2zJxGe2lSp1Dz+Q9I1XyJXr9E1WeOHcKPWrhCnXXInvB/hSIkTo/C/XXXxfztTkWgqeH/Di+QnOjJcYyFV5/swEZ0bKpKMWtqFf09+ykigLRKFQ3DCWrmEJ7Youg0u/nkAKSd2Fzc0x6r7PxeEqFcelqylKue4Tjyy8rTM3aW+2z0PXBLahcyFX5tDmDEHj/OdOjzNSrBOzNaKGThBcvVWwCxTLLoauYxkS15fYpnHDzvGK43FmtERLIoJEYhk6I8UaNdcnHjHWVPSWUiAKheKGMXSN2zelyUZhfBmsEF0X1FxJd9rm/m0tVBqTp46gPRXh8PlxbFOft3gizJ+0Zxpi3lDaAIhZBp4foDUq4hroSCTZpAkjV5ezKgEZUKpJHtjeDIJlcY4LKUAKDE2gaeC5ocWx1qK31oYUCoVi3dOTjfHYvu4bvs7WTIQHd7TyoQNdfOyezTRFTYpVF1PX2NWeImLonBktoQtBNh65YltnbnTV9OuzfR5w5WRs6BqHtmRpS0WYrLjYhk57Ik5vxp5XTgGkLHj0tjY+emcPj+5t48HtLTfsn4hZBtvb45Qdl1LdIxuN0JaKUHG8NRe9pSwQhUKxLNiWwS8+soszo1Mc6S9e9/tjOvS2xnnPzlbaUlGEBpl4hPu3ZdF0jUREJ2YZFGoOQgoSkXCinpuUd7WkvQDeKZkeyHkn4+ZEhJ+7r5dXLuTwGttfj+xp4/Rgjs8/fWFmi84QoAuIRkyaYxHsiM69W1uWpYSMoWvct7WFo2aOuuMTsXT2d6WJWrqKwlIoFBuXnuYYf/4L9/PawCS/+VevcGpycc7erc02P3v3FlrSNr3NcdwgwNQ0ClUXrWEZvD6YZ7JcRwDb2+NhHSrtytaxC7WWjVnaTCb61SKlmhMRHt3TNuM/Kdd9sgmLSCTCX7zYx3jZQRPQFDX56KHN7O9puqwkynKQjpm8e3vLmgzdnY1SIAqFYlmxLYP7t7Xx7V/9Ef7w707wx0/3LXj+vo4oH79vGz++v4O3hqfwAoltGPNO/LMn9au1jr1Wa9nZmehXY3a4bToW3vvOzRk+dk8350bLeFKyrTVGKmrftAl+PZR2VwpEoVDcFAxd41MP7eDYYIGnz+TmPSdhCn75sT3EbJNU1LrmxD93Ur/aCn2prWUXGst0yZSW5OJ6pN8KKAWiUChuGs2JCJ/72F186ZmzfPXVfoamQge2ALqbLH7u3q3EbHNGUVxLMczmWiv09bCCX+8oBaJQKG4qzYkI/+v79/Cz7+5louzgBxIpoTMdIRax5m3fqib+9YFSIAqF4qZj6BptqRhtKbX9s5FQal6hUCgUS0IpEIVCoVAsCaVAFAqFQrEklAJRKBQKxZJQCkShUCgUS0JIeZVi92sYIcQYcGEFbtUCjK/AfdYat+K4b8Uxgxr3rcZuKWVyuS62LsN4pZStK3EfIcQRKeWhlbjXWuJWHPetOGZQ415tOVYaIcSR5bye2sJSKBQKxZJQCkShUCgUS0IpkIX5s9UWYJW4Fcd9K44Z1LhvNZZ13OvSia5QKBSK1UdZIAqFQqFYEkqBKBQKhWJJKAUCCCE+KoR4UwgRCCEOzTr+uBDiFSHE641/H53nvX8jhHhjZSVeHq533EKImBDiCSHE2433/bvVk37pLOX7FkLc1Th+RgjxR0IIsTrSL50Fxt0shPihEKIkhPhPc97z8ca4jwshviuEaFl5yZfOEsdsCSH+TAhxqvFb/+mVl/zGWMq4Z52z6DlNKZCQN4CfAp6ec3wc+Akp5e3A/wj8v7NfFEL8FFBaEQlvDksZ93+UUu4B7gDeLYT4sRWRdHlZyrg/D3wG2Nl4/OgKyLncXG3cNeDfAL82+6AQwgD+EHhESvku4Djwz1ZAzuXkusbc4F8Do1LKXcBtwD/cVAlvDksZ93XPaesykXC5kVKeAJi7qJRSvjbr6ZuALYSISCnrQogE8CuEk8pXV0rW5WQJ464AP2yc4wghXgU2rZC4y8b1jhvIAikp5QuN930J+DDwnZWQd7lYYNxl4FkhxI45bxGNR1wIMQGkgDMrIOqysYQxA3wa2NM4L2AdZqwvZdxLmdOUBbJ4fhp4TUpZbzz/HeD3gcrqibQizB03AEKIJuAngO+vhlArwOxxdwMDs14baBzb0EgpXeB/AV4HBglX4/91VYW6yTR+1wC/I4R4VQjxNSFE+2rKtIJc95x2y1ggQogngY55XvrXUspvXuO9+4DfA97feH4Q2CGl/N+EEL3LLOqyspzjnnXcAP4C+CMp5bnlknU5WeZxz+fvWJPx7zcy7nmuZRIqkDuAc8AfA78O/O6NyrmcLOeYCefETcBzUspfEUL8CvAfgZ+7QTGXnWX+rg+yhDntllEgUsrHlvI+IcQm4BvAJ6WUZxuH7wfuEkL0EX6GbUKIp6SUDy+HrMvJMo97mj8DTksp/+AGxbtpLPO4B7h8q24T4Yp8zbHUcV+Fg41rngUQQnwV+FfLeP1lYZnHPEG4Av9G4/nXgJ9fxusvG8s87iXNaWoLawEa5uwTwK9LKZ+bPi6l/LyUsktK2Qs8CJxai8pjqVxt3I3XfhdIA/985SW7uSzwfQ8BU0KI+xrRV58Erndlux65BNwmhJguXvo4cGIV5bnpyDCz+m+BhxuH3ge8tWoCrRBLntOklLf8A/gI4SqzDowAf9c4/htAGTg669E25729wBurPYaVGDfhylsSTiLTx39htcexEt83cIgwsuUs8J9oVHFYT4+rjbvxWh8wSRiBMwDc1jj+Txvf93HCibV5tcexAmPeQhi9dJzQx7d5tcexEuOe9fqi5zRVykShUCgUS0JtYSkUCoViSSgFolAoFIoloRSIQqFQKJaEUiAKhUKhWBJKgSgUCoViSSgFothwCCG+IIT41grf81NCiJtWWLNRPfVTN+v6CsVSUApEoVgevgJsm34ihPitxZbEVijWK7dMKROF4mYipawC1dWWQ6FYSZQFotjQCCEiQog/EEKMCCFqQojDQogHZ73+sBBCCiHeJ4R4UQhREUIcEULcOec6nxZC9Dde/1shxGeFEHLW6zNbWI2tpt8E9jWuLae3nxp//8yca/cJIX5t1vMdQoinGvKeFEJ8cJ5xdQsh/lIIkWs8nhBC7FyeT02hWBxKgSg2Ov8e+EeEPR7uICxN/l0hROec8/4vwkKBdxIW1Ptyo+4VQoj7gf8C/AlhgcG/AX57gXt+hbAs9kmgs/H4ymKEFUJohIX8NMICd58GfguIzDonRtiXpQa8t3HeEPBk4zWFYkVQW1iKDYsQIk5YjvwXpJRPNI79U+BR4BcJa19N82+klD9snPNvgWd5pw/ILwHfk1L+XuPcU0KIu4H/ab77SimrDWvEk1IOX6fYjxH23dgqpexvyPPPgWdmnfMxwhLz/0Q2ahEJIf5nYBT4IOu0wZli/aEsEMVGZjtgArMr6/rAC4ST9GyOz/p7ulR7W+PfPcBLc85/cfnEvIy9wKVp5THrXsGs53cBWwkrBJcayqoAZAjHrFCsCMoCUWxkphtBzVcxdO4xd57XphdY4irXWApyllzTmLP+nq951Vw0wkrBH5vntcmliaVQXD/KAlFsZM4ADmF/AwCEEDqhz+B6ejycAO6Zc2zu87k4gD7P8TFCn8i0PO2znzfk6hZC9My51+z/q68CO4BxKeWZOQ+lQBQrhlIgig2LlLIMfB74d0KIHxdC7G08bwf+9Dou9UfA+4UQ/0IIsVMI8fOE/RYWog/YIoS4UwjRIoSYdoL/APhFIcQhIcQdwBcIneHTPAm8DXxJCHGw4cD/HODNOufLhD0evimEeK8QYqsQ4iEhxO+rSCzFSqIUiGKj8y8Jncr/jXDb513Aj8qwy+CikFK+QOgw/yVCX8mHCXum1xZ4238Hvk3YkGgM+Hjj+K8S9hd/Cvgrwuiu0Vn3CgiVk0bo+/gSYQ/y+qxzKsBDjet8jVDhfJHQB5Jb7LgUihtFNZRSKJaAEOJzwGNSyttXWxaFYrVQTnSFYhEIIf4F8PeEbUAfI2z1+n+sqlAKxSqjLBCFYhEIIb4CPAykgfPAfwb+UKr/QIpbGKVAFAqFQrEklBNdoVAoFEtCKRCFQqFQLAmlQBQKhUKxJJQCUSgUCsWSUApEoVAoFEvi/wd+sCUGry6PawAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", grid=True, alpha=0.2);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmAAAAGxCAYAAADF4QrHAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAEAAElEQVR4nOydd3hURffHP7Mtm00vJAFC7713RBDFjiI2bKAo9u4rFmygYlcU6/tTwfaq2LEjSEd6770nkF62753fH7MhCaSThOJ8nuc+2b137ty5s7vZ755z5hwhpUSj0Wg0Go1GU3uYTvQANBqNRqPRaP5taAGm0Wg0Go1GU8toAabRaDQajUZTy2gBptFoNBqNRlPLaAGm0Wg0Go1GU8toAabRaDQajUZTy2gBptFoNBqN5oQihNglhFgrhFglhFgW3BcrhJghhNga/BtTpP2jQohtQojNQohzi+zvFuxnmxDiTSGECO4PEUJ8Fdy/WAjRuMg5I4PX2CqEGFlb96wFmEaj0Wg0mpOBQVLKzlLK7sHnjwAzpZQtgJnB5wgh2gJXA+2A84B3hBDm4DnvAmOAFsHtvOD+0UCmlLI58DrwYrCvWOApoBfQE3iqqNCrSbQA02g0Go1GczJyCTA1+HgqcGmR/V9KKT1Syp3ANqCnEKIuECmlXCRVlvlPjjqnoK9vgMFB69i5wAwpZYaUMhOYQaFoq1EstXGR6iY+Pl42btz4RA8DgPz8fMLCwk70ME559DxWD3oeqw89l9WDnsfqYfny5WlSyjq1db3mQkhnNfV1ENYD7iK7PpBSfnBUMwn8KYSQwPvB44lSyoMAUsqDQoiEYNv6wD9Fzt0X3OcLPj56f8E5e4N9+YUQ2UBc0f0lnFOjnJICrHHjxixbtuxEDwOA2bNnM3DgwBM9jFMePY/Vg57H6kPPZfWg57F6EELsrs3rOYFbq6mvp8FdxK1YGv2klAeCImuGEGJTGW1FCftkGfurek6Nol2QGo1Go9FoiiFQFprq2CqClPJA8O8h4HtUPFZq0K1I8O+hYPN9QIMipycDB4L7k0vYX+wcIYQFiAIyyuirxtECTKPRaDQaTTEEYK2mrdxrCREmhIgoeAwMAdYBPwEFqxJHAj8GH/8EXB1c2dgEFWy/JOiuzBVC9A7Gd91w1DkFfV0OzArGif0BDBFCxASD74cE99U4p6QLUqPRaDQazWlDIvB9MGOEBfhCSvm7EGIp8LUQYjSwB7gCQEq5XgjxNbAB8AN3SikDwb5uB6YAocBvwQ3gQ+BTIcQ2lOXr6mBfGUKICcDSYLvxUsqMmrzZArQA02g0Go1GU4wCF2RtIKXcAXQqYX86MLiUc54Dnith/zKgfQn73QQFXAnHPgI+qtyojx8twDQajUaj0RSjwAWpqTm0ANNoNJqTlJycHA4dOoTP5zvRQ6kyUVFRbNy48UQP46QnLCyM5ORkTCYdmv1vQQswjUajOQnJyckhNTWV+vXrExoaSjA+5pQjNzeXiIiIEz2MkxrDMNi/fz9paWkkJCSUf0ItUJsuyH8rWmprNBrNScihQ4eoX78+DofjlBVfmophMplITEwkOzv7RA/lCLW5CvLfihZgGo1GcxLi8/kIDQ090cPQ1BJWqxW/33+ih6GpRbSFUaPRaE5StOXr38PJ9lprF2TNo+dXo9FoNBpNMfQqyJqn1l2QQgizEGKlEOLn4POXhRCbhBBrhBDfCyGia3tMGo1Go9FoNLXJiYgBuxcouiZ5BtBeStkR2AI8egLGpNFoNJrTiClTphAeHn7c/cyePRshBGlpadUwqlOH2q4F+W+kVgWYECIZuBD4v4J9Uso/pZQFkYf/ULyQ5glnxW4Y8R7c9gmknjwLVGqcjIwAP/yQx/bt3hM9FI1GU0W8S5aQcfXVpLRsSWrHjuS88AKBf5mQqAyNGzfmlVdeKbavb9++HDx4kLi4uBM0qhODXgVZ89S2OH0DeBgoLSnMTcBXJR0QQowBxgAkJiYye/bsGhhecXwBWLcfuoeCkDDtZ2hfv3ibvLy8WhlLbRIIwPr1XgIByc6d0KqVDYejZgNET8d5PBHoeaw+TvRcRkVFkZubW6VzpZS4H3oI3+efg9sNhgFA7vjx5D7/PI7vvsPSq1d1DrdUAoFAle/jeHC73QCVuraUEo/Hc8w5YWFh5OXlVev4SsLtduvP778JKWWtbMBFwDvBxwOBn486/jjwPSDK66tbt26yNrj2MSm5TkpuVJt9jJQHs4q3+fvvv2tlLLXJjBn5MjJyq4QtErbIceMO1/g1T8d5PBHoeaw+TvRcbtiwocrn5r79ttwXFib3QYnb/ogI6T9cM5/rM888U956663ynnvukdHR0TI6Olo+9NBDMhAISCmlzMjIkDfccIOMjo6WdrtdDh48WK5bt+7I+R9//LEMCwuTP/30k2zRooUMCQmRAwcOlNu3bz/S5qmnnpLt2rUrdt2C80p7vm3bNjl06FCZmJgoHQ6H7NKli5w+fXqxcQPFNinV+wCQh4vM17fffivbt28vbTabTE5Ols8++6w0DOPI8UaNGskJEybIMWPGyIiICFm/fn350ksvlTt3Zb3mwDJZS9/XUkqag/ypmrbaHvupstWmC7IfMFQIsQv4EjhLCPEZgBBiZFCgXRt8o50U/P5lkScGhNkgLqz88/7ZAte/CR/OrJlxrV5tsGBBAL+/ZqaqfXsbUoLFAg6HoH//2slF9MYb++nceSUDBqxl0aKcWrmmRnO6IQ2D3AkTID+/9DZ+P/n/93+lHj9ePv/8cwzDYNGiRbzxxht88MEHvPHGGwCMGjWKxYsX8+OPP7JkyRIcDgfnnXceLpfryPkej4dnnnmGjz/+mEWLFhEIBBg2bBjH8/WQl5fH+eefz4wZM1i9ejXDhw/nsssuY9OmTQB89913JCcn8+STT3Lw4EEOHjxYYj/Lly/niiuu4LLLLmPt2rW88MILTJw4kcmTJxdr9/rrr9OhQwdWrFjB2LFjefjhh1m0aFGVx38i0DFgNUutzY2U8lGCAfZCiIHAQ1LK64QQ5wFjgTOllM7aGk9R3B544VPYug9uOA/O7a32t2gEGWtBRoLZBp++CNZyZizXBYPHg9MD3y2B5Dg4t3P1jfWhh7y8+24Akwm6djUxa5YNs7l63YNJSRaWLGnIjz/m0aOHnbPOclRr/yWRmupj3Lg95OcrV8nZZ69n6dJOtG1b89fWaE4n/Js2Ictzu7lcuL74gshHHqmRMdStW5c333wTIQT169dn7969vPbaa1x88cX89NNPzJkzhwEDBgDw6aef0rBhQz7//HNuvvlmdQ9+P5MmTaJfv35H2jRt2pSZM2dy9tlnV2lMnTp1olOnTkeeP/7440yfPp1vvvmGcePGERsbi9lsJiIigqSkpFL7ee211zjzzDN55plnAGjZsiVbt27lxRdf5O677z7SbsiQIdx1110A3H333bz55pvMnDmTPn36VGn8mtOPkyET/mRUTNgMIcQqIcR7tT2AEU/Bi5/BF3/CsEfh7+WweD2skYAD8ANuuPJhWLOt7L6cHvAHCp+nZFXfOD0eyRtvBHA6IS8PVqwwWLLEqL4LFKF1axtjx8YeEV+GIfn223z+7/9yycgIlHN25Tl82HdEfAF4PAbffZde7dc5mQgEJFu2uPH5Thqjr+Y0QLpcYDaX3y4YI1UT9O7du1hi0T59+rB//342btyIyWQqJkKioqLo0KEDGzZsOLLPZDLRs2fPI88bNWpEvXr1irWpLPn5+Tz88MO0bduWmJgYwsPDWbZsGXv27KlUPxs3bjwiDAvo378/+/fvJyen0HLfsWPHYm3q1avHoUOHqjz+2kYH4dc8J0SASSlnSykvCj5uLqVsIKXsHNxuq+3x/LIQ3MHFfi4PTP0OLhwGzn9AbgI8EDAgzwUPvFl2X4nR8NgwiAyFvq3gyuP4sbNkiZu6dXcQGrqNiRMzMJvBWuTdHAhARETtZE8eOTKNkSPTuPfeDDp1OkBubvUKP5Op+H1YLAKHo/y3508/pXPXXdt5//0UAoHjEzJbtrj47LNDrFtXuuumOjnnnK107LiR/v03V9m14vFIvF4t4DSFWJo1Q3rLWb1sMmHr0qV2BlSEst7nlckEbzKZjunL5/OVec5DDz3EtGnTmDBhAnPmzGHVqlX07NkTb3lzdRRSylLHWnS/1Wo95phh1MwP5ppAp6GoeU4GC9gJJ+BChQkCOOGTFyTpWyW4gUxgNRD8bC9cW35/T10J2Z/AjCcgNKTq4xox4iApKQHcbsmECRns3OljyhQrdruKz7r3XjPt29fcS5iREeDHH53MmOHk88/zyc+XOJ2SnByDhQs91Xqt5GTbEcFltQqioy3ccENCmef8978pjBixhbffTuGBB3YyenQ55skymD8/hy5dVnH77dvp1WsNv/ySUeW+KoKUkjlz8vB4JEuXOvF4Ki+iFi/2EBu7h9jYPaxYUb2vh+bUxRQdTeill6p/EqUg7HbCH3igxsawePHiYgLpn3/+oV69erRt2/ZIbFgBOTk5rF27lrZt2x7ZZxgGS5cuPfJ8z549HDhwgDZt2gBQp04dUlNTi11j1apVZY5p/vz53HDDDQwfPpyOHTuSnJzM9u3bi7Wx2WwEAmVb+Nu2bcv8+fOP6Ts5OZmIiNIW+Gs0x6IFGGBORYktP7BTIg1Q+j9IAAiGVMRG1t648vML/7mYTOr5VVdZyMuzk59vZ+JEW41c1zBg1C1e4uvsZ/jlhxk27HCx/+U+HzRoUL6LozJERpqZObM9Dz1UjyefbMCaNZ2Jjy/beD1p0gGcTvWL0uk0+PzzQ1W2JL3yyn6cToO8PAOn02DixH1V6qeiCCF47rl61Klj4fHHk7DbK/9R/PbbfJxOJYp//PGEhE9qTlKiXn8dU3x8iSJMOBw4Ro7EVoNpKA4cOMB9993H5s2b+eGHH3j55Ze5//77adGiBZdccgm33nor8+bNY+3atVx33XVERkZyzTXXHDnfYrFw3333sWjRIlatWsXIkSNp167dkfivgQMHkpGRwfPPP8/27dv58MMP+eabb8ocU8uWLfn+++9ZsWLFkeu6j3LDNm7cmHnz5rF///5SE68++OCDzJkzh6effpotW7bw+eef8+qrr/Lwww8f56ydXGgXZM2jBRjwyB0QlgFhqYALiomvAsxgs8D9V9XeuF5/PR67XRAaKhgyxEGnTkpwmc0Cm63mXI9TP5NM/SgDaRgE/JL8fInZLKhb10zdumbefDOWtm2rX/z17h3Byy83Ydy4BiQklN9/TEzxL5fQUHOVC9omJFixWtW5ZjPUqVPz/zYeeSSJQ4c6MmFCvSqdf9114cTEmIiNNXH11RVYnqv512BOSiJhxQpChw8Hux0RFYUID8eUmEjkCy8Q9fbbNXr9a6+9lkAgQK9evbjnnnsYPXo0999/PwAff/wxPXv2ZOjQofTs2ROn08nvv/9OaGjhauuQkBAef/xxbrjhBnr16oVhGHz33XdHPt9t2rTh3Xff5YMPPqBjx47MmDGDxx57rMwxvfbaayQkJHDGGWdw/vnn07t3b84444xibcaPH8/evXtp1qwZderUKbGfrl27Mm3aNL799lvat2/PI488wiOPPHIk4P50Qbsgax5xEmV9qDDdu3eXy5Ytq9Y+5y6EdRvhzpslxwgwO9AR+jaDeZ8pa1QBs2fPZuDAgdU6lqKkpQXIzTVo3NhSZXFRWW6/R/Le5AMgC2IqQoE44uMFf/5ppiZCR6oyj2vX5jNgwFoMA3w+yaeftmD48PgqXT8tzcdZZ61j3TonzZrZmTWrPQ0aHIf/+ARR0+/HfxMnei43btx4xOV2PBhZWfi3b0fY7VjatEGYavZ398CBA2nfvv2RtAy5ubmVcs1NmTKFu+66q1YSn55slPWaCyGWSym719ZY2gghp1RTX72hVsd+qqDFaZABfdX21KOStMNFjyjRY98Ar79VXHzVBvHxZuLjq9fdVx7XXwPvvRMKgYIKUXUAE2lpcOmlsHt3rQ6nVDp0CGPXru5s2uSiUaMQkpKqbpWLj7eyZk0XvF4Dm61mXuTDh328/34a8+bl0aSJjTvvTKBDh9rJsab592KKjsbWrduJHobmFKPABampObQAO4p/Fpno0csgK9NACGjR3EydOoLHH4ciq6JPa/r2Fvz6cxS33+HnwH4PPm+h5S37JKuHGRVloVev6gt8rSnxtXGji759t+B2G7jdErMZPvkkg3feacCoUVWz2mk0Gk1NUeCC1NQcen6PolkzOJxq4tAhE3FxYKuZOPdyMQzJrFkGYWHQp0/tWsAAzj/PzK4dahXinXfCRx+BlPDii7U+lNOCUaN2k50doMDjHwiAyyW54469XHppNNHR+qOoOT043lqGo0aNYtSoUdUyFo3mZEYH4ZeA2Qx165448QVw990+Lr3Uy9lne3nrrbLz29Q0b78NGzfCrl1w660ndCinJOnpflatclFSuKXZLPjlF112SaPRnFzoVZA1jxZg1cDSpXDZZTBiBGzZUj19/vhjgPx8cDrhm29OfPK+xo2hjOoc/0oCAUlKihvDKHshi9crS40dlFJl/ddoSuJUStypOT5OtgVxehVkzaMF2HHi8cCgQfD99/D119C7N2RUQw7Pm26y4HCA3Q633FL7Lsii/PSTh6SkTJo1y2LVKn/5J/wLyM/306nTXzRs+Bu9e8/G6y39izIpyUK9eiX/DgwEJEOG1GJyOc0pQ1hYGPv378fr9Z50X86a6kVKSXp6Ona7/UQP5QjaAlbzaHF6nBSteWsYaluxAqpYL/YI48dbueIKM6Gh0Lz58enkQABefBWm/wqNGsKrE6F+/YqdaxiSq67KR+UrlFx7bR7r10cf13hOB+bNS2PPHhc+n2TjxhyWL8+kT5+4EtsKIfjgg4YMHbodl0secUU6HCbuuCOe5OQT6OvWnLQkJyeTlpbG7t278ftP3R8+brf7pBIWJyt2u53k5OQTPQxNLaIF2HESclSqKK8XGjasnr47dKgeA+VDj8IHHyl35pJlBnPmCbauFYSHl3+ulEpUFnCivgdyc3307Tub/v3jeffd2q9hdzRt2kRiGJKQEBNCCJo1KzsR6uDBkcyb14pnnjnIsmVO6tWz8p//JHLFFdG1M2DNKYfJZCIhIYGEhLJLcp3szJ49my4noO6k5vjQaShqHi3AjpOICLjvPnjpJRW8//rr0LLliR5VcaZ+psQXfjeGz0lKPnz4cQT33l3+x8tsFnz4YRi33ZZPaKjg44+LCw0pJT/+mMm2bR4uvDCaNm1qJq9Vbq6fdetysdtPrDu2gEaNHCxePIi//z7MuecmkpBQ/i/8rl0d/Phjs1oYnUaj0Rw/WiDULHp+q4Fnn4Xx40EItZ1sHLH++wvrnv083VMhAQZw3XUhXHddyVnhn356Hy+/nILHY/D443tZsqQdnTpVf1mcevVCSUm5gIiIk+ct265dJO3anZj4rZQUP7t3++jUKaRKdSQ1Go1Gc2LR/7mrCZPp5BRfAK+9CI5QEBYluEwmuPaa6hEykycfxuUyMAy12u+ee/ZXS78lkZhox+E4eQTYiWLuXCfNmm3jnHP20K7dDnJyAid6SBqN5jRDAFZL9WyaktFTUwl27zZYvTrA4MEWwsJOUrVVAldfAU0awex5DrIybVx8gaBv3+p56YXZChTmKdu3Ty+brwjr18P27WoFbSXK5AEwYcJhnE4JSAxD8tNPeVx3XVSNjFOj0fw7EQIs1aUQTt01JDWKFmAV5OBBgw4d8jAMaNfOxOLFFYhgP4no1RN69az+sMoP/685l16yAQhgsdjoPziRa+6A7p3h/luOtQpu2BDgjjvcpKZKLr/cwtNPh2A2nzpitjr48Ue45hoVMxgXB+vWQVglvLb161uxWsEX1L2JiSdHXJxGo9FoKo4WYBVk+3blZsvPhzVrSrfybNqUyy23rKFVqzDee68jFktxL29enmT+/ABt25po2PDU9wBfMjSUPXs68u23eSxeE8InX6og/P99Dj/PhFlfFbZNTzfo1y+f7Gy1uvK117xICc8+e+KXqH/2WT4TJ+bSvr2VDz+MITy85l6bt98OLooIsnQpDBxY8fNfey2RAwf8rFvnYfToKM4+u/pj7jQazb8bIcCqf9vVKFqAVZDevc2ce66F2bP9TJhQckA6wAMPbGD+/AxWrszmkkuSuPjiwvTxXq+ka9c8UlIkhgFLloTRtm31vsM9Hsm+fZLkZEFISM1Ylg5kwwX/hQ0p0K8J/DTayn33xWCKBCQqeEDC7L8gNR0Sg+mxliwJYBgcyYPldMKXX/pOuADbs8fPmDGZuFywfbuf5GQzr74aXWPX69EDFixQ928Yqv5oZYiNNfPnn9WU60Sj0WhKoFpdkJoS0dNbQSwWwbffOspt16NHFHPmpCMltGhR3DKxZ49k/36J06lWJs6aFahWAbZ3r0HPnvnk5krCwgSLF4fRuHH1W3Ju/wbWp4DfgEW74Ok/4NVLQAYotqxD2MDpKnweF2cicFS8eELCibcCZmdLhFCq0euFw4drNo7tmWfA4VCuxzvvhAYNavRyGo1GozkJOfHffqcZTz/dij//7M3atWfSunXx6OpGjQT16wsiItQvi8GDq9f69eKLHg4fluTnQ1qa5NlnPdXafwF7s5T4AvAEYHemenzVjcEGAQNcbmw+NwF3YfRljx4mLr/cQlgYREaq7d13T7z7sX17C5dfHorZrAThE09UMiq+klgs8Pjj8L//Qf/+NXopjUajqRJ6FWTNo6emmhFC0K9fbInHrFbBypXhLFgQoE0bEw0aVK/+NZsLg96FAGsNpTG+b4CyghkSTALu6Kf2f/KaJDbGy7vPB8AQuNMlnTrlsm9fJDExZoQQfPxxKLfeGuDwYUmvXmYSE0/8bwAhBFOnxvLeezGEhIDJ9O9aFKDRaDTHIAAdA1ajaAFWy4SFCYYMqZlpf+yxEH7+2c++fZJ69QRPPFF6rNrxcEMPaBoHK/fDGU2hc7CuZK9eh9i61QdGDOrTC243fPRRHg8+qNIkCCHo0+fkfNuFhmrhpdFoNJra4eT8JjxJyXbCK79Ceh7cNAC6Nz3RIypOYqKJrVvDycyUxMSIKltydu9T1rTkuqW36d9UbUW58spQXnnFR35+DhCBylOVS3Z2zbr0NBqNRlPNCLRCqGH09FYQfwD6jodth8Drh6nzYcETJ3pUx2IyCeLiqm7J2boTOp2rXJhb5kD9pPLPKeDRRyNxuQK8+moOTmcaAA6HYOjQ8hcvnAoEApK//vLSvLmZZs30R0ej0ZzGaAFW45z4AJxThB2HYHe6El8ALh98v+zEjqkmKEgTIaV6XFmeeiqa+++PpGFDM23aWPnmmzp0714zrtDa5rHH8rjssiw6dcogJUWX/9FoNBpN1dH6toLEhSsrWAGhVqgbc+LGU1O0agar/wCzCRrUq/h5gYDkm28CWK2C8eOjefbZ029y9u0L4PWCxSLJzZUkVcI6qNFoNKccWiHUKHp6y0BKmD8fPB6VqfztkXDHVEDCGa1g9ABYMP9Ej7L6aVmF2LZ77/UxZYpSqA88YGH8+BpagnkCmTQpkuTkfLp1s9Cihf7oaDSa0xi9CrLG0d8iZXDzzfDVVyoeqmdP+OsvuKYPuLwQW82lIFeugTkLYPjF0CC5evuuDebPN8jPL3x8OhIfb+LFF/WCAo1Go9EcP1qAlYLbDVOnciRz+z//wLZt0KIFhNpg7krYewiSqsHQc+Ag9D9fuThfnAQHNh5bxPpk56mnLIwY4UMIePxx/baqKocPe4mNtf7rCpRrNJqTDB2EX+PoIPxSsFohNBSwASHgCsB5F8Mjj8FLn8D5D8JtL8GGnZDvKq+3sknLUH+9XvX46HI9pwLDhlnIzLSTlWUvN8P/t99CfLzKhP/SS8WPSSm57rr9WK0bufHGA8iCwpH/AiZM2EHdunPp12/piR6KRqP5t1MgwKpj05SIFmClYDbD2GdBNAVCQXpgxxZ48SUY+xw43ZDnUlarFZuP71od2sL9t0PbVjD1ndorgLpiLdz6CHzzS/X0FxpafgHw/fvh+ushPR1yc2H8eJg7t+hxP9Om5eD3w+efZ3PoUOlq1DAkX3zh55VXfKSmnvpCbcaMDAIBWLYsh0Dg1L8fjUaj0ZSO1qZlcDAHZEBCllBStUBb7AB8gE2lajhei5UQ8NRYtdVU+aCj8Xph4JWQmw+ffQdNGkC3jjV/3V271D26glZDKWHLFmjeXD1PSLBQt66F9PQAiYkW4uJKtqb9+KOT2+41SHGFIvzw6utudu2wlysAT2bee681Tz+9gyuvTNQuSI1Gc+LRQfg1iraAlcEZ7X3gkyCkEl8FG8AeYCvggnVbj+86H38M4eFq++yz4+urovj84Paqx8IEGVnV0+8rr8HlV8KhQyUfb99eWfiKxridcUbhY5tNsGZNU37+uQGrVjXFYjlWiHz3nZNhl+eTkhkG0ox0mDnksbJ376ltNWrbNpyvv+7I5ZcnnuihaDSafzvaBVnjaAFWBlPez4K9qVBSHlEJGGprcxyrFqWE225TFimvF8aMqVo/r06GvufClC8q1j7MAf99AVo0gVGXw+D+Fb+W0w3nPQyRF8F1zxdaAHNz4eFH4Ief4JNShGRUFCxaBMOGwXnnwR9/QKtWxdtERpo588wwwsNLfnv+34depIwDp4BMwCeQZkHDhtVrNfr0C/jPY8ptqtFoNBpNdaK1aQk4nQZ5eYayvgSAukAu4ASsqF8GHtXWYoH+PY7vehaLEl8FjyvL/H/gyYngdMGqtdC3J7RsXv55I69QW2WZ/APMXg0eH/wwH77pA1cNUha8a66Gpcvg4gtLP79lSxWIX1WSkooqYgleaJzowmarvtwgf82C2+5ROeBmz4Wlp2G+N41GoykVvQqyxtHTexSbNrnp1WsbLpfE50sAcxLkARES+gKtBSQA60EchphkCDmOSjtCwJdfwsiR6vGUKSoFht1e8T5criIuPQEeb/HjTheMHgt/zIO6CfDZa9ClXdXH7PaCUcTb5/EV3stnn1S936JIKcnKUqLOai1u2Xr1FTtffGXgcRsgIMSdzftvVm9iNqdT/f8JBNT8aTQazb8OHQNWo2gX5FFMn56D02ng80mw2cAhIBC0hO0VEI+ygnUC2R3SPOA7ziD8iy+GjAxYtw5Gjob4JNi4seS227fD9z+Az1e47+yBMGoENKgPD9+tVlUW5fZx8MMMyMyGDVvhrGshJ7fq473zEmheTwmuLs3hyoFV76sk/H7JhRd6SUx0Ex/vZvHi4oldY2IEmYfN/Pf9AG9P8rFqRSTnnFO9qxcuugD+cz9cejFMq6W4PI1Go9H8e9AWsKM499wIHh6bDoSD1wlmB1hCIC9o+foL6F38nOpasLZlq7J+AaxeA23aFD/udkOXHuD3w913wosT1X4hYPLLaiuJmQvB7Sl8bhiweQf06FSxca1YAVdcAdHRMH061KsHG6aA1we2IronPx+GXaZWNU75WJVvqgq//mowb56Bz6eE5u23e1mxorhJMDQUbh5dc0tGTSZ46vEa616j0WhObrQLssbRFrAiHD4M/ywPBWss6t0nwZOtDgZFVlQMCLc6hAQRgCxn9Vz/jP7w5Dh44D4Yflnp7QQqeL+iRISiYtY8gKFETf1KFJJ+5BHYsQNWr4b33ivcXyC+Zszw0b17Ni1aZPH33y5275LcfU/F+9doNBrNSYZeBVnj6KkJsno1nDFIJVbFF4JK9AWYrYCEWAFmyLWDTENJVwm0hrmb4dJuZfcvZfnlhUwmeOTh0o/b7bBiCaxZCxdfVLH7SjkEO3cExwoIP7zxBNSrRKaDnj1h4UJ1D507F+7PzoFPPnNzz51FFagLi1XSrZuj4hc4igsuMNG/v4m/ZhmISAtteloqHRen0Wg0Gs3JjBZgQcY/q9IoAGCKApMVHIDNAXZBeBQ42kJSfVh3ULnxCogoQxjszoLBH8POLBjWBr66EszHYXds3rwwaWlFSM8s/jzcAWOuqdw1x4+Hvn1VCol+/dS+H2fAiHvAtfnYCHW/2cPq/g6y3BBdwtxM3wbfb4GWMXB/Dwg56l1osQh+/dXGbQ/Dx1/Dt78LOvwfPHJX5cat0Wg0miqiXZA1jp7eILYQZYEyDEAITPYwjAiVg9VihSvPhXF3gd8KvZ5RljIJhNthUJvS+33odyW+DAl/bIMfNsLw41iBWFnatABhAYIrI7t1rnwfJhNccEHxfTc/Aq7DgMkGAQ/0scFIh8qN9pmTtelw1XfQLRqGd4RuwVxpX26A0b+B0w92C8zZC79deew1hRDExSixKgSEhx3bpiJWxdrkiwVw9xS44xyYUMI9aTQazSmFXgVZo+gYsCDPT1AFosPDICYGnpsADhNIr8SXYfDR95IuF0FOGjw1AJ44H765C1okKoFSGm5/YbyWlOCpwULbXq88piaiyQSXXwL2KLXdc3P1XCtrnxuy0sFmglAB1zkg1ARhJrg5jICEP9fAxB+g35uQEfRSvrdKiS9QczNjF7h8JV/jqQfhuUfglSfh9hsK9/t8cNFlYAmHfoNUyoiTgcl/QkY+vD2j6n1IJPdyiI/Jrr6BaTQajeakQwuwIE2awJ4dsGIp7N8Nwy5USTgxUMscUyTZ2QH6XwOPvwJPTwBLfvn9vjAEYkIhxAwdk2B42/LPqSiBgMqi36IFTJokadfOQ3Kym/ffL65oPn4RvpgEf30Gw4Yc/3W37pf4D6ep9BwuAS4n3HUAnjkE+YZ6VwWAHMAEHgnZQU9lUlhw1WgecADMTrCV8isrJAQeuBXuGKWKoxfwxwyYM09ZFVethf99ffz3VB28NAJ6N4e3Rla9DwnMxsVC3NU2Lo1Go6k0Ogi/xvnXT81vc2HnfrjiXKgTq8QMQOMGICji4zIDhwJ4880YddSuz6bDyHIETbsESHkYMl1QJ6x6XWbffadqR+bnq5WKXq+BlDBnjuTWWwvbWSyVE15SwkEfRJjVdjQTZqFUlD8aOAhIpRx2e+HzLBgQBflm6Ih6hxmqkADAK4PgrwWQPpcjBc5/GQSRKEH5y3xIy4Qzu0GzBiWPLzq6MBGsEOr5yUD/1rBofPF9eXkqZYa5gqZ8E4LlNNSWf41Gc2LRMWA1zr/aAvbB13DF/fDQS9B1eGE5IFDWlxuvQH3TSwnOAJgFRo765neEQq+OFbuO1QwJ4dUfr1S0P78fTCYvJpObESOq3qfbgDM2QLNVUGc5fFRCUe0/cgVMrAcWgyPLK0FZvZZ54SUfpAT3BVeLbgp61JIjwbI62Nan5vzOl9SxC+6Bax+De16GjlfB3OUlj7F/X3jqMWjfDu66DS67pOr3W1Os2wjt+0NMc4huBi9Prvi5FgSCkyi4TaPRaDTVzr9agP30N+S7wOWBjGzYl1r8+EN3C0wBQAYgChXj5JV0bRpg4n1w61UVu46UsHmzynZfnVx2GYwaBa1bQ506Lvx+A8OAZcv8Ve7zg0OwPB/cUrkO79gFuUXi1tx+SAewCDjDDHWjIaxILSaPFUIE7EVl8vCC1YDB9QqbeI+K+XJ7ITcfFq6GPJd6TZxuuOOF0sf58AOwdim8MKFQiGZnwz//FFnNWg34/XDRUIipA19/U7FzfD44axis36wWa+Tlw9Mvw/Q/qm9cGo1GU6MIlOenOjZNifyrBdg1F4LDrlIz1E+EBkclJ23ZEhb+IQjxecBthsPKZ7ZrkZt7rq+YRUtKGH45dO0GDRvBkiXVN36TCSZPVmWLnn7ahM0GYWEwfLityn0e8inhVYCguABz+lHWq++AdAHx4dA4HqLDgVAQoRBhhRXAI8AUyVgLxBVJR3H/NRAWfB5mh4euA7/BMTafrEoIqQMHoHkLGHIutGgJh0qw3FWFDRtg5t+QlQXPTKjYOfMXl1CP0wnvT62eMWk0Gk2No2PAapx/9dRccxE0bQC79sMFA8BaQmWbXr2gfh3Jjh2F+wKBiuvWjAz45edCq88776rEptXNmDF2hg+3ERoqcDiq7r66Og7eSAGnAXYB3cKgbpF5ibWDfZOKOzvifTQJqB8FUQFIM0OaCFayBlaCf3/xazxxM3RoDis2Q/fWMPRM+GumErRCKNHqsMOIcys+7unT1ZhcLpVK5LffVIHz46VFC2jcWJVXumlUxc4JsRWpVOANqGKhFjP52SauvlqQlATPPKPyqmk0Go3m38m/WoAB9O6ktrKYPNlWJA+WwO22Yxhlp58oICoKYmIhLU3FlfWqovjKyjJ4+eVcrroqlI4dS7ZwxcVVzaB5OBdmbIBWSdCtEfzTDr5MhwQrjEk41tIXWI8SV0URQi31dFHclCXhlbdh4tPFm186UG0FWMww/yO48wU4lAHDB8Mzt1X8Htq3LxynNKBdNeVaCw2F9auVsAsrIRdZSfTuDvFxkJvqA5cfpVQDzPvDTiCgarwvWwbz51fPGDUajaZG+NcrhJpFT28FaNPGht0ujxTK9vsFfr/6Ii0PiwUW/wMffaSsKddeW7UxfP21k+efz2XlSi+//lqn1HZpaR4+/3w/I0bUJyEhpNR2BWTmQ/unwOlV6w0+HQ2XdYVny6gkdGY3+GNmkR0SOAAU1MgsKsDM4E9Uq03PH1D2WDq0gLkfljvkEunXD776En79FS65BLp3r1o/R+NyGaxe7cJuN9Gxox2TqXzr4q//QEJX2Ok3wUEzHAoAJgJB0er1wuLFhe2dTnj/EzVtt45Uok+j0WhOKAUxYJoaQwuwCtCoEVx4oeD335Vr6c47Kya+ip7/zDPHN4bLL3ewebOfa68tu8biCy9s49VXd7BtWz5vvdWh3H4Xbge3D/I86vmH85UAK4tpE+DWcPjlb8hJB7JRli8f6kNrBNSCBbuAJCVYvvqtfAFWEl4vfPI5pGfA8EuhebPS2150kdqqi/37ffTtu43MzACGAT17hvL7702w2Uq3NP40H0Y8A04PEGlWiWnNwMHC2lVWK3QtMsdX3gwz56rHcxbB9zpWTKPRaE57tACrAELAtGmwcqVyI1aXe6sk5s4N4HTCeecV/+kRG2vi1Vejyz3/uuuS2bAhj1GjSkmidRRt66oAeACHDfpVoM5khAO+eAa23gDtLgRfGGAH/AKQ4DaByQ/xFpCCUCv0KF8LHoOUcOEwWLhYCbHnXoTlC6FFJWphHg9jxuxj/37fEcvVP/84eeeddO67r3QL5LOfBMVXAWYBDSxw0E3v3i4SEhzUrQvPP69yhHm8sGwVuIPnLF1RY7ej0Wg0FUfnAatx/tWrICuDEMpqURHx5XbD4cNFArEryJ49Buec42XYMC/Llxvln1ACnTtH8euvvejWLbpC7ZvUgRn3w6i+8PwweOS8Co51H3QbBIE0VFZ7A/VuMgklxlwerOn5tG9k8OgtcPvVlb+X1FSYt1C56Px+cLrgywqmgqgIhgHPPgvdusOIa9RrVkBKJixf5TkivgBcLsnatWVnqD86xQZASKjgyy/NLFwYyo8/wnvvwZ9zIL411GsPzRpDqF1t91Ui7k2j0WhqjBOwClIIYRZCrBRC/Bx8HiuEmCGE2Br8G1Ok7aNCiG1CiM1CiHOL7O8mhFgbPPamECo6WAgRIoT4Krh/sRCicZFzRgavsVUIUQ3LtyqGFmBHsWCBsk7s319+25L480+Ii4PkZOUOCxwdrF4G0dGC2FhlZUtKqvhKxqee+pvff99WhdEq+jaHj2+Ee8+u2MICgAXBGCbD4Ng4AZNg8IVhePeHs/QHE2deALurUNowLIxieV5tNoiLKbV5pXn2WZj4AqxYAd9+C4PPhnFTofUt0PI2SBP2Yp8Qh0MQFhbCjh2li+OR56sVnEfOCYHbLhNcdVUIoshqhrvGqlJXXh8sXwO/fQWrZsNDd5bcr5SSv//O5Y8/cvD7K6nsNRqN5tTgXmBjkeePADOllC2AmcHnCCHaAlcD7YDzgHeEEAXfRO8CY4AWwa3ArDAayJRSNgdeB14M9hULPAX0AnoCTxUVejWJFmBFSE2Fc86BJ5+C8y8ov31JjB6tLDZeL8ydC7/8Unjs4EE/L76YwdSpORjGsV+ikZGCffvsHD5sp379iguwhIQwoqPt5TesRrp0KBSXZlF8paTNBm1bCFw+6PIBXPQ/aPcu/LCpcteIiIA3X1WC1G6HLp3gpmr8bfL994WFvH0+lU/thf/B5v0qIWygfTKEheBwCEJCBM2bh/N//xdCp0555OaWLILuuwIeuRbiIlVqtJsugJfvOLZdSNH1ERLatoSWZcS3jRq1m6FDt3P55Tu44IJtyMqaVzUajaay1KIFTAiRDFwI/F+R3ZcABVGxU4FLi+z/UkrpkVLuBLYBPYUQdYFIKeUiqf5JfnLUOQV9fQMMDlrHzgVmSCkzpJSZwAwKRVuNogVYEQIBZXAxjOJliUrit9/gwgshJSVoBQriPyoJfcFzl8uga9c9PPFEOnfccYj77z9MSZjNAqu1cnm87ryzJ717J1fqnOOldUv441sYfT0MGaxSPwAglJVqwv0wdzfsXgu5K8GVDs/Oq/x1xoyGlJ2weTXMn6mEWHXRvDkUNbGZ7ZJmyRKLBVonQ0yshWtfbMnMf1qyc2drhg2rCwgCgdItm0LAEyMh7WfI/BXeuh+sJfwD+vIDqBOnSlq9NgHqxJc+Trfb4PPPM8jLM8jLM5g3L4+9e0vwdWo0Gk11Ub2Z8OOFEMuKbGNKuOIbwMOogJYCEqWUBwGCfxOC++uj6q0UsC+4r37w8dH7i50jpfSjlo/FldFXjaND7IpQrx589y3MmAF3lGC1KGDHDhg+XOWGOvts+OADuC0YuzN5MlwfzJLfsWPhqrwdO3zk5Rn4fODzSX7+OZ9Jk0q/xquvBtiwQfJ//2cu5ro6mejfG+b8A5++AQTTXZnqwhWXGJw5IJ/Va/xgMoPDAWYLqwLwRyM4txKFwUEV266JgtuTJ8Pq1bB7j8RnlYR+lcV1g6zcmBdB/Th4ZhFMXCJYuTyE9aPg8ccttG5tpm1bE9HRx/eanNEHDlXQImizCcLDTWRnq/9LJhNER+v14RqN5pQhTUpZanIgIcRFwCEp5XIhxMAK9FfSP+CjkyAV3V/Vc2oUbQE7ivPPh9deK7COlMy+fWAOfv8ZBmzdWnhs+HAVB9axEwhTYemhJk2shIWZsFhULNEFF5Sd1XPqVIMpUyQeT+ltfD7jhLqipITxrwethcG63KFe+OXDfFav9imzWMAHudlgBAhIuOHGEzbcY0hMhM2bBQcPCPqkZmAe7KWp1Uxy0Bq1MVW5JptFq+dWqyChgYVxr0imfF17824yCX77rTmtWoXQtKmNb79tSmSkFmAajaYGqd0g/H7AUCHELuBL4CwhxGdAatCtSPBvQZG5fUDRpf7JqGyU+4KPj95f7BwhhAVV4TmjjL5qHC3AqkDv3tC2bdCwY4Zbby085nLB0EtUos0FC+C885Wb0uEwsXx5Q555Jo633qrDG2+UnsoAYO5cC3v2WLDbS7a0fPLJAUJDZ9G27SLy8ysR6V/NFDXOmUww7EzYuyeoxhDBTUKeqnSelgf1W8HPv52AwZaAEBAbC7NC41hlrcO1ZpVnLd8H09bCoET44RLVdsNGP4MHpjD9s1RuHHGAqZ+XoY6rmT59wtm0qR3bt7fnvPN0DSONRlPD1KIAk1I+KqVMllI2RgXXz5JSXgf8BBRE/o4Efgw+/gm4OriysQkq2H5J0E2ZK4ToHYzvuuGocwr6ujx4DQn8AQwRQsQEg++HBPfVOFqAVQGbDRYuhDVrlJuxZcvCY/v3Q05uYQoKl4ThY2HE4yBsFh57LJabborCbC7bhRUdLcoMxH/vvf0EArBnj5t16/Kq47YqjRDwwuMqfUJ4GESEwxP3QZcuJYzbcAISQ8KBg3D5DbA/pbZHXDohQpAsCq1K4TZYfztMu0Jl1gAYOzYL/AH14hqSxx/JKLEvrxdG3AkXjoTsnFoYvEaj0ZyevACcI4TYCpwTfI6Ucj3wNbAB+B24U0pZYIm4HRXIvw3YDhT83P8QiBNCbAMeILiiUkqZAUwAlga38cF9NY6OAasiZjM0awZ79xbf7/MXD9A2msOiDbBkM2zdA8s+rZ7rP/54E66/fh2dO0fQpUtE9XRaBTq2AjwqCX7depBUB95/307nzulAZLCVExUkVojHAy3Ogh/ehyFnlH+dB99VSUsn31u94y+LNkcZKbMyi6efcDlLTkfxz0r44U+l036eCdcOq6kRajQaTQ1yAiIdpJSzgdnBx+nA4FLaPQc8V8L+ZUD7Eva7gStK6esj4KOqjrmqaAtYJdidBd+uV3UTSyMiAkKiKGZ+lSjDybZ9pZ9XEstWw6atJR+78MJ4MjIGMmtWtzJL49Q0tz2o3K4el0rO+uFn0KmTjTFjwoFDCHEYyAfywHcIZEBttgAuH9z2ZMWu0zABGibW4I1UgAceiMDhEAgBYWGCO+8ML7Fdtw5qa9UMzu5fy4PUaDSa6uAEJGL9t1HrUxNMlrYM2C+lvCiYBO0roDGwC7gymIvjpCLfCx3fVmV7zmwMv15fcrvk+vCf++GlScGs6G4gFGwWuOeqil/vQAr0vABsVnDuqHiC1NqmqLVPysLn779fhwcfjOSKK1JZs0YCGeDZBr4UtTrBXgdIwl/B8LV7h1es3f33+2nfXjB6dPX/dBs2LJTffotnzhwPbdtauOyykqtmhzlg/nfVfnmNRqOpPXQpohrnRHytVyjT7cmGywduPzh9sK+crO4TnoBPPoXwdkDwO7pLaxhfiTIzsdHQrwcMHXLyii+AN1+A0FAID4f6SXDTdYXHWrYMoW3bSNQCk+An2chTm9kKhoFrjyQ3t/rGs2QJLF5c8RWKhqHi+bIrmKl/wIAQzh0eyYztDnannJzpQTQajUZz8lOr+rZIptvnUEFwoLLTDgw+nory/Y6tzXFVhPgw+PIKmL4ZHq6AW2lQLzCHgFUqK9b151fuenY7zPuhSkOtVS4cArtWwf6D0KblsYlS27aNRAiBlG2ATYAfZBhk+iEtBZc9kYULzcUzwx8HCxZU7i39yivwxBOqxueKChbCHvMCrN6m4v0+fKwKg9RoNJqTHW0Bq3FEbeaREkJ8A0wEIoCHgi7ILClldJE2mVLKY+owBTPnjgFITEzs9uWXX9bSqMsmLy+P8PCSY4E8PsjMgdAQiCq5yWlPbi5s21a0WkCAwkTHApPJQvv24PGUPo81yaFDKq+bwwGtW5fd1jCUmzUjR63gtFuhQT3lcjxZKOv9qKkcei6rBz2P1cOgQYOWl5XMtLrpnizksnuqpy8xllod+6lCrenbKmS6LYaU8gPgA4Du3bvLgQMr3UWNMHv2bE6WsdQEUkqmTXOyapWHzp1DuOIKR6Uy87/0UgZjx2ajltMkAjYQ0KpVgDvvMHPBBYJmzU7cPEoJGzZA06bKlVoar7wLj0yAgIsjSWcBhBlWz4cO7WpjtIUYhmTcOBfffOOlXz8L774bht0uTvv3Y22i57J60POo0ZRMbRoYCzLdXgDYgciimW6llAePynR72mEYJ3c8V0k8+GAmH3yQS36+JCxM8M8/Ebz2WmyFzt2508vYsenBZ5GA9Ujm1j17LOzeo1J5VATDgG/+gH2pcOlgaNqg/HMqghDK/VgWHg88OhECHpQBr0jxChmAye/D+2+q5243TJ0GTRvCOWdWzxhL4vPPvUya5MbphL17vSQkmHjxxZPIFKfRaE5ttAuyxqk1OVCFTLenDVLCNdeAxaKy6LtcJ3pEFcPvl7z1Vg75+crck5+vnvv9FXNbT37XQ2GZrVC1+jGIywV/zyr7fKPIZW5/Bm4aB4++Dp0vg+17Co8FDJi5HpaVkrKjMqQehrn/KCFVgNkMloJFlfnF25tMyn1ZwCPPw31PwSU3wqp1xz+e0ti+PXBkjG43bNp04qohaDSa0xCdhqLGORnsMSVmuj2VkVKlqyhg82b44Qe1f/16+O0kKcNTHqWFB1YkbPDnX+Gd/xaNyPcXO9FshoaNSj73w91Q53ewTIdec2FLHkz9EfJdKrWH2wPXvQPXTodvVkPM+XD2MOhxATQeDEtWwdSvYWMlBdnOPdCyH1x4PfS+qDBuzWKBaR9AfEEeMi8g1f+nhDrwnyLJYf1+VQITisa9lczWrdC7DyTVhVGjiou+8rjqqhAcDrX61OGAO++0l3+SRqPRaE4aTog2rWim21ORwy7o8Q3sy4M3+8MdHSAhoXjx7rLcbmlpsGEjdOoIUSe45J/VKhgzJpwpU/JxOiUOh2DkyDCs1vJjwGbOBrfHCtYElYCVNELsYQhhwhcQhIfBG68fe95/lsIrq1EixwZL3NDuN4hwqEz4oLLuL86CfzbAF78COzkSk7V7D/S9AuxS6b3Z30KPzhW73zmLVMJcpws2bIVDaZCUoI5ddA4c3qDqe44YAd4APPoo3DRSJd8tYOJjkB8DnRpB146lXysQgIGD4MABA6SL/31pIccbAtFwwUC4+cqyx9qmjZm1a6NYsMBPp05m2rfXPzM1Gk01cwIy4f+b0P+1q5lfdisRFpAwcYUSYLGx6ov7m29g4EDo1Knkc7dtg+69lXAIscGalZCUVHLbffsC7NwZoGtXK2FhNZePavLkOHr1srNsmYfu3UO4/vqwCp13zlnwwYfgdEUSGh7BR++CRHDDAxDwgTsa6tVTbbfsgPVb4JyXwH92kU4ygPXKmpiZDMIJpgDIpmA0Bg4DczkivgoISMh3qsc//VFxATaoH1gtqq5lq2aQEH9sm379YM+eY/cXMHUZfLVPbSPOg8TIwmNSwuJ1sGUd/PkLpB02QB4AAng98MPiBkiTid/nQa9O0KHVsf17vTDmHkhJhY/fNXPttfo/pEajqQF0DFiNo6e3mumXpIo3OyxwSZPC/R07qq0svv4G8vKUdcThgOk/wy03H9tu5kwPQ4dmYbEIoqMFq1bFERNTM95kIQQ33BDODTdUbhn5BefBw/fD1E8lGYf9XDPCgtksCViAJIHVBm63ZOzYXP5vqp+nnjDwn1kkun0t8DnqF5gf6AOyq4rFEi3BbaDqKWSjlnQUJTgVjlDo1bXiY26UDNsWwtad0K1j1RZMOGzBIQgwH3X+mOfh8+ngWkowE4eAFnUgNQtyXMVctNZSPpm/zYBpP6iFAZPehReeqfwYNRqNRnPi0QKsmmkRDTuug4P50CGucue2aQ0hIeAMWm9Ky0s1YUJ+sI0kEJB8/bUHkymUgQOhRYuqj706+eEHmPisxOMJ/owyg98iwCNp2hDefgpatswiNdWrdIdNglOCVYALJb58wQ1goYT64AkRhB4GkwOMA6g63x5UcLwJSISYRjCiB5x9hnIdpqVDahq0aVG+qIqPU9vR5ORATq4qNVUWN/aBpvHQIAbiwyElR5WxahYP0+eCy0lhCgsTyBAbJEQicl2c2SKLtn3iGNIfWpfipu7YLrgowAJn9it7LBqNRlNltAWsxtHTWwPUCVVbZbn0EnjtFRWkf9VVcEYpGfcbNjRjtfrwBcXJV1+ZWLgQoqMhJaXKw65Wpk8nKL4As4AICUgIEaRkwM2jDFJSilQ1N1G4YDKdwlytBZgFpEuwgCsLRBqQEzwWFKwYgAda9oS3n1O7Fq+AwVcq49LZZ8CPU6p2P+MmwLqNMOvnstsJAQNbqsfT18OVU9W+e86Au66ECR+CaA7touDq6wQ/L/eTsTmfrn3DmDQpmujosvtv0hj2bVQLERLqVO1eNBqNplwEOgashtEC7CRCCLj1FrWVxRtvRJCSYrB+vZ/Ro0PJy7OxcCHElxCzVFFmzdrJsGFf8e23V3L22U0rde5ffxksXiwZOdJEcrJSUYMGwSefSPxSQJQEKQAJVsCAg/uPilvzSOW3A4jhmLguAhKigAVAZ5B+IBbYQ6GbEiAabruw8LQPvyiMB/ttFmRmQUx0pW4PgMf/AxmVLBH/2mxVPxRg8nzIewFuuRTCHRAWFOj/wQJU7oWLjFRZ1TQajUZz6qIF2ClIbKyJP/8srNZkGGplXps2Ve8zEDDw+QIEAuXkTjiK9eslQ4cG8Hrhk08MNm+2AnDttbBrl+TJ5w2kMKlfUxLiEwzG3mfi2YcE2dmhKH8jKsHpPh80sUKYgMuA7wARVGINfbBAQJYVegC/AmFAUyAL5aqMhstuhht6F46vb0/4/HuVHiIhHiKLrFgswDAkJpM49kAREhPUVhnOaApL96o8ZV2Tg/1U0i2t0Wg0JwTtgqxx9PSeBphM0KPH8fVxzjnNcDofr/R5mZkSk0ktHMjIKNwvBIwbZ6J3X4MLr1UixzCDz2fiojOh988wdGgEmZk2kpN9JNU3Y4+34s4X4AZ6Ay2BXQbs98A/VjBZIRlohxJgACGoCkehEB4P1/YoHuc18gqIDIdf/4Y+PdU4zUXM6medlc/8+QH+/ttBv37V+3F4+lxonQAZThjVs1q71mg0mppHK4Qa5WRIxKo5henXT/Dggyb69xd8++2xAQNnn2Vi31rBD58KHA6B0w0bt8H6/eBpLIjtbeez7yKonyiYOkAQGolyNcYDy4FsE2x1gM2qxNbNYJFHBdMLVZOxfT345St4bLxaJQhKCE6fD1/9Dfe9CGfdVDyR7OLFAYSA1asrZ/mrCCYTXNMN7joDwkOqvXuNRqPRnMJofas5LoQQPPOMmWfKSIdQJx4uHAILp8Pm7TCgN9QbqLLaO91w9YPwv/FwZWP4exp8uAP8DcE8EPhL4K8D9AfOQAmzXyA8VCVNBYiNhEUfw6gxMHWBSuFgD4U+V0K2Bz6dAYFgHNjydXDgENQPZrWfMyeMFSsCjBplrZkJqgZ8Ppj1D9StAx1LWRmr0Wg01Yp2QdY4eno1NYKU8MEceOExg91LQBoGfc+UzP3LSkZ28baeIoshF84B32b12B4G22bAPeNgpRd2LgP/HjAOwR2joWGyxJ0PNw6HDWu97N5jJuBXyyk/WAov2wVCgLwcxHSQGcr9GGorvF737ma6dTPz8lswZwFMeAy6lpIo90Rx/mhYvFrF+k19GS4/70SPSKPRnPboVZA1jnZBamqEV/+CO++X7FokkAETSAsLZ5uZ/I6fOrHw0I3KUhVig/eeLjzvlqvAYYcwB1x7MSTWga/eh/UfQOtMiMhVx8/vI3nufjcP3+ImJjKXfv32sG3lTsjaTCDnIPu3B8h7H3K/ACMbHGeByQ8yEzoPhMNphdf8Zyk88xL8OgMuH3n0ndQMH38HY56EbbvLbldg/cpzKmvhZ6ddqXqNRqP5d6ItYCeAgAGZbogNLcy8cDR5TnjnB9iTCgM6wRWDVDzTqcJXyyGwEwqTeymWLvbD3Raeuw/G3qxEWKgdZs9Wx++6Hgb0UIW3e3cuPM9kgqVfw5K10Lwh/PV7gIwMtbqx8G2cDmRCWDPISlIrKL0C/oD889UhJ+BzwbtT4MmH1FkC8DtVlv24WLVv/nz4Z4nK6N+2bfXOzaJVcNez4PLAvOWw8ZfS21qtqizR2i3KqnjZkOodi0aj0ZSIdkHWOHp6a4AZK2DpdlhwQOWren8kNAimepq1G4Z9B54AhNvg18uhZ73i5zvd0H0M7EpR7rkpv8HSTfDyHbV/L1WlYzIsiwayi5QXQnDRRYVG18ijqhtJqUoxHR3nNG48PP8KDB4If/6ohGi3biYCAVAJwwoC6C1Ac3DbQBqo9PsSXAK2lT7Wm0aBcClr2y9fway/4eJLlfXp6fGwZgU0rVxqtApTdEFAacz6FKbPUnFr/brVzDg0Go3mGLRCqFH09FYzf6+GSyeAMwc4BJih4UK490nomwCjv4W8YAZ7jwvOmwapd4G1iK/92zmw7xB43EAu5KfBK+9C7kG44Ey4ePDJbw1743LYvBkWvCqPpPqKi3Ny9dUlF/OWEnr3hmXL4LLLYNq0wmPvf6xk1t/zIPWQZMd2LxERJl57zcx993nw+zNRwQqNAZO63j4n2AXEhoMFmqXCAXuwliSAAW437D0I23aCzxPMFVYH/p5dWA7Kboely6pXgPXpDG89rixhD48uv32oHa68oPqur9FoNJoTj44Bq0ZyPHDPAnD2BFJQyUW9QD68eRhu2ATyqHQEHj8cyCu+LztPuSmVvyy4MwDvT4Or7oZXPji+cbrdx3d+RYiww/wJgjWLBSNHBnj1VYPDh0sWXwAuF6xbpwLNv/8esosE6j90j3LFdWoPA4e4OHtIJr17H8LtdjNhgo2WLSOBUIq9nf2ANwSsAquEKS/DpkXQojG4XTDxdRhzHwy+DnxxQCTkhoHTBeeeowp5hwaz1fftU+3Tw03D4b8T1Hg0Go3mpKMgCL86Nk2JaAFWjVz/M2wtKApd1EJlBvKDsUb+4udIIPEoXTKoa9DCFTjqAkLVAPzgy6qPcdo06Nq10MJT03ToIJgyxcIDD5jLtNrZ7RATA2Fh0KmTKrdTwNj7Ydx/YPU6yeYdobhEAk4ZztjnQ8jwhLB2bTTnnWejWP0is0WpNiv4DbjjqQAel5/d+1T6C7cHlq6E/SmADYgFaYHDGdC/P8ybDW+8Cp9MhXsfg1F3woGDqutAAD6cAvMWlHwv8xbBrj3HM2vl4/bCA5OhYS+Y8m3NXkuj0fwLKYgBq45NUyJ6aqqRGbvAEwxHsvdxYqw14Q0LgcECayZcGAUXDIK7ZoDNBD4DPrsY7Ee9Cu2awIOj4Nm3KLSAmVAJSg9AfAwl8r+/4PH/Qq+2MPUxlbv0aAYNUiKwwLpzsmAywaZNsHEjdOx4rIv1i28gEBDqn4JJQkgEAWHi5bckv80ULPo1hs5dDrN9ewiYLGC1Q7jqREpY92c6rVpJnp5Yh+ffMCGAcQ/B9Hnwyyx1jbYtoEFd9bhrV0hIhNa9VC1JiwXmLoSty+H9L+DBByDgh+zU4nO5eDkMGAp1E+HAuuOfl4P5cMgpWeuEenbBhnx441fYtwa8S0HuhlsehUvPg+jSDYwajUajOcnQAqwaCbeByw8xEek8/eajmIXB3f/7ACkFXgNmHQxw/cB0NjSJZ1+2iRYxx1q/CrBFgegI8jCq1mE4EAGmffDUnfDWavhuO1zcCG7tCIv3wjUTAAl7DsOQnnDj+cf2Gx+v6kbWJhs3BnjtNS9mM4wdG0KTJibmzPExdGgu0dEm5sxRBRrDw48tqSQlvDpJxWiBVDtMgAgab4Vg/Sb49mcTmzclMOlNLzPmmfl7nQlP0PRtsUCdxiG0axzgsQcFo69X+xITYMRwmD5TWcQuHgwTZsDny6FOOFxdT7UDJVr3HYCG30BaOngD0LQ5hBzlUm6UDM2bQL8qlh7aexCufRga1oUnxkLnr8DdC4iWsM0LH1vAb1blmhqoKTHqw+rdcGY1r9bUaDT/YvQqyBpHT2818vpZcMvv0KHpaqwWHyFWL80StrAvrQUBIbAkZ/ACuxgSkcszEc3K7KtNXXBYIT8elf3dANNhGHEefOqFL+ardnMOwlMLIS8L5er0Q0DCn3vgxpq93Qqxb59Br1755OUpq9a0aT62bAnnuedc5ORAfr7BZ5956d8fVu2AVvUhtIio+e5HeOpZFbdmNksCrnQIhIAjXIkwKZEIdu+DyZPdjHvchRBw+U0RfD3HitkMzRrAzI+iSIyHGSvhkakq/cWbY6BnS7jkHHWt52bAS7PA6YOtabD2AATMgANEJBCAgyaQDYD3YYcB3f+AL/pBpA3qhkBSImxdUvX5ev9rWLASlq+H+p3Vgk4KCogvtoDPpDytVsAOtABDwK5MOLPql9VoNJpj0fFbNYoWYNXIte0gOQLeS41FmCSGhHvPfYX128exyAw0TcENrCSn3L6Gd4Xf1sLni8FiUl/wH94IYY3gvO858sGQfsg7hPq10hXYC0SBJ7qGbrKSzJzpxzCU4UpKZUlatCjA0KE25s9XAXFnnmlhdyqc+yZ0bgqLXyk83wio84SA3t1NJCeZ+eoLlxJfNjv4/NgjrTTvbObuZ8DlBZsF7rpWMHI0/LQUBrSHhDjYmQKXPg/OYJ3Is5+APR9CdDjkGJKPVoLTV+j7lAISH4CdEeqxzwZEAtkcyXyxOhPa/g42B5wdDz/0VK9XSXw0G2ashdED4ewOJbc5/wx49WMwwsDWECxzwb8bSBWwS0BroWIDd6OEmARHBAgrGBVIaaHRaDSakwMtwKqZMxtCoGEdpnIWMRwg3ZLMPa3CGEiA1xFIYCT1yu1HCPhwFNx3Ljy2GKLs0KcHPPcPuP0UrrDM48gXMXagnbKcXXqS1AysX7+4GvH7oV49E/0GWhk0yEpEBDRsaGbrV0pDpmaqdj4fjBoFX32lBFjbDvDlVKhTJ4av/5eJdHrB6cUeCpOfC+eOT81kJ9qhmwnpMJEVYmH4y+D0wkdz4HA2NIwrnu5DCNiRCpGhfjqluXHZQ4NWNSXC8nIg7wDK1ZeHisdrJ8EhlAgjqMOkiv2bnQ5fH4Brko+dhz9Wwz1TId8DPy2HTa9Cg7hj2/XrCvsXQ7+d0DgG6v0AWd8L/C5wNufIAg9TElgOg4gDXxcY+SWMnAiTL4f+RukiUKPRaCqEdkHWOHp6a4BB1OMw/VjCIS6nLj2oQw9gADEIIImQ8ro4wlsb4Pd96rMQY4ckO1hNaiUf24DtQLLa7Gbomgw3dILrOx7b15zlcOn9EO6AWR9Ai4bVcbdlM3iwmVGjrLz/vlpN8OCDNpx2M7EjoEOombyDYMmDp/8Dk2+FwcE6jE8/rdJRBIIrQXdsVc/vvlvQoYOZjRsD+Hzg88OiHRZyXShF1TAEiw1+Wwmu4AIGpwem/QOf3qVWRBJsajbBISEZtC0PZyACupngIOCTkCUgA9gnYa2AaKARyhLVURKSq8S010CtokTlfE0rUteyKHvSC5OuCgEpWSULMIDYENgYFNBXPwer9kCjuh4umO5m3Z5IzCZBp5awuiH4m6PckUnAbHDnwNOfwbM3VOpl0mg0muJoAVbj6N/JNYBAcBXNeJU+DJWNmbIbhsyHR5aF4HceK76cblixCTJL8ExG2MAs1BZhhRvagbEX9aW/GZXvai8QC2c0ggU3wa3dSk7U+uS7kJUH+w/Du9OOPV4TCCGYPDmUrKwIsrMjGD/eTrgdbE7YsEa5BbfmwMGD8NlECAu+I//8U+UGK8DphD/+UI9nzYpgzG0hWDo6CJwVzYdrTCRYwHIQ2ALudbBmMdiDq0DNAhatgbY3QYd60L0ZnN8NPn8Mhv0OOWvC4DMT/CXgAqEC3rNQ5q2gNYxsIAeIlZAvwAJ3NoRYA6w+9UGymWBoUsnzcGVvaJaoXpdzOkC3JhWbv7AQiG+xn+fDp9D36v8x8obf+M8ZB2jUbBu2tplgCy5KKBKAv7+MrP8ajUajOTnQ+raGeXsHjF0HzoAK2/ojFTYPgaigOEhJgy7XQX4wOerc96Fzq8Lzn+0DUTZVM/KhrrBoHYh0IAblgjSj3JEZMHVM2WNpEIMSFQJa1K3e+yyPsLBCRdi5Kbx1C9z+ZHBH8NDcuSoFxZo10KABrFxZaAGzWqFRI/U4L2Dii8ww/M1QuTwOeElZ7YEwA+qGIS0WFiyRnHOu4PctEPBBwA0e4J/14AiBkTdDRFwwrmuZRZUrypdK1KaXchPxQD5gBY8JJi1RiWOtJri2BzzZCRo7Sj41ygFrXgSvX8WoVYafWIoXPwgwJ+yhUfw3dLRmMmfFezh3GhAp4BvTkXn8j7Z+aTSa40VbwGocbQGrYd7ersQXKJ3kDMDctMLjH/4E6dmQm6+2CR8WP18aYM6DafPhwg/hsWngywO+ADYBO4ENwNdw2asQdQOc96xyzR3N9+8C+0BmwVMvwN79x7ZJzYSNu4//vstj5DBwSJSITFX7pITMTMnIkW7GjPETE6NSU4SHQ2Kickv6/ND1IcjMA/ID8EcWLMsEnxOy3LAxHXzKPfnbr16MXFTKhiI4PfDwf+GlNSBtAuFAFe42BdtGmNS4bKicY0iVBqQBgFDHcpX4AvAFoH4Amh9V27IkKiu+ABKIwhJcdeEzBGt3tWN7bjPyFkXCXhN96+xh5hPw/ljo2ALaNq/8NTQajeYYdCb8GkXr2xrGcdQMSwmhRd6QUeGqPqHPr1IjxEQUb3vW+7D6QDDwnqAeMKFcjwYqOBwgF/5ZC0j460e4KhW+ek1ZjvZmw+BPgWuAn9U5h/Og69mQul4lQQUVV9b6RnD74I+JMKCEOLLqIiQE3LuC91EErzePP/7wMW8ebN4cw4y/BFYLDB0KERGwPQUy81G/zra5Ic4OKb7inezKhaZRyMOGSuFQglXKHYD9eyDEAZ7mgrgsSEsDAhDaFVz1JGyWyn/ZDRXgJYOJYENQ/1QyOJJ8P+Ko/pduh6vfgoRImP4QxEdSZa6iHwAzczOZ8WdPUuYnq3E0k4gQyUJnYx4WsOxKmD276tfRaDQaTe2hLWA1zCsdwGGGEBOEmaFTNAyMLzx+y6UwqLsSXx2aw8S7Co/N3g7rUwrFF6icTzQGWlFY7kgATQEvmNIhkAG/z4Sfgxne5++F7ZngrE+xaj1phw2sUT5MJi+XXOLDMCQmlVoL81HvDCnh5Zfh9tshI6Pke50zRyV53bu3YnOTVEq8lMmkYqXW7YDb34Ixk2BrsE+fuzAsC6vt2HJNCKWu0ryqinUKx1jAAGQALOugRxKYrJAZD136Q3hfCNRFze8AAZcKaCRUkLtVqrl2AJFqjkx5YM+Ca9sX73/s/2DHIVixEz6ZV7H5KA07NoZwBr8G+pByQL2IJgEHRgm2X22iTz6c5Sq3G41Go6k4uhRRuQghOgghJgshfhNC1A3uu1QI0aUi55/GU3NyMKgOLB0EMw5BvA2uTC6eIiDEBr+8UfK5G1ILV+0VQwJnAX2AxUAzIA2sOfD6HfDg00ocdAjGkl3QHIzNqPimTJQ7DcAAIx+Qgp+mw5rVki1TBFl50OyoTBlz5yoXoNcLNhtMmnTssJ56SomwLl3g4YfLn5unn4Z77ilelzI0NJxx47xcdpmF174SuL0q/u3nudClDVxwN9AQOAxEmiEvgHobFygxs5ogW0GiNJQAsx97/YQIEDaVuFaGSHY7lFHRiwC7hHC12RPyEX5w+cIhy6xWnxrwYFdIDMCQVtAotnjffVvCku0qN1enRuXPRXnEYaZXtOTADYcYuTWeS5qYqRsGj/0By/6EFQJuLzu3r0aj0VQcHQNWJkKIIcBPwG+ob+SConTNgFHApeX1oae3FmgbqbbK0qV+0BLlo9iHoW4EeBpDhhloDwQgZjb87z44tytccbYSSRER8P7eoFvqR5S7z49a4ReDSiqaFbyYgAsnCBo2gESfjxU7fDSrL/n9XQcRYYJ6QUFms0GrIosEivL66/DZZ3BjCSn4Dx0yePTRXGbN8tK2rYWJE8MZPVqtRHjmGWXx6tYNrr7a4PvvJdnZAW66xsT/fhPYrHDluZCTB/tSUTFjvQGLUKni0z3gEYV5HixFTHgC9bFwG7DVr1I2tLYSEivo3hmu6wzbfJJNDSHfJPH5UK5FuwGJqi93IJSYpDRMtgD5m2LV9XNg0m44eAWkp8Ky9dCtbeHq0wlXwKC2EBcOnRtX4MUuBxuCX6in6oF2L9zfOkl5SUNtEO1Q+Vk1Go1GU+NMAB6QUr4jhMgtsn828GBFOtAC7CSmVQyEZUP+weCOWHDUgbeHwR8GfLJXpayq44Ddr6vVeAAJQRfn41vhjd3g2oASIoIjOatUKRsBDYUSYfVNpLkFaTuAECtYLaTukzS+wMfBGTZatIC1a+HwYejVq+TxdumitqMJBCR9+mSwd68Kjt+1y8vcuZmsXx/HDTeYcDgkoaEwa5ZBQoIXjwdWrQrQpYuJnEXqLSqC+io6Ag5nAn8DXgFhQOcIxD4X0hWAcKsSZimZ0CgaYkwQImCpF7IlxApoDD4LvDwf1mbCC9fAiEMSpxSYbX5aNtjI1kOtkZZg1lNAShOWiGC+iWggX1kyf5wPt40Fj1cJ3q0/QWKcGu/g9sfORXWQR4AwTAgEN/SFXk2hTgTE6GLcGo2mOtEB9GXRDvi1hP0ZQGwJ+49Bx4CdpHh90O0OOLSfI5nuLdkw+3YY1gEmd4BX28FjLWDpACW+1m+F+ybCpz8psfJ3BjgNkG0p/kESqHQKOwSkmKGuRQWpZQJXAzdJiFCZSjMCZp5+Rp02YyZceAmMe5JK8fffXg4fNpR1qeD+vJKPPnJx+eUBbrklwM6dkrvvNo4YsUBlwxei0KokBMx4F5o3UOV3rrgUnAsFrtkmTIkOaBgJsaGIiBCmTglnxAAQ2YbyMRZ4KHtZwaJi6fK98Pt6iE+DuJA8zMJHk7gtJCSn0rTppmC8nMRi9SFMATxpDszSB14QZoi2wbpVSnwB5OXDP+sqNzeV5RA+erGZDyhcStsqCWLD1Gue64LvF8GqjXAorYyONBqNpix0DFh5ZAL1S9jfFdhXkQ5O36k5xdmdCmk5FAonAS2SoEcD9dRigtuDyTwnfQJTfoAN25VwCwsFhx1ubgerc8FUD7zjwPsuyp3pQ8VQAQSEelxPiQoZTdBtJ2GvD7bn8trKSB7+j5XnJ0J6OrzyGjw7vuL3kpNzbJFCnw+ysiQzZkhcLpXS4fffJR9/bGX8eD/9+pkYMeLYn1+dWsLWH4vvkxJio4SyjAF2u+D3jSF8tUUiY0CsDdC4gwVLboCD8YK8IllqhYDpLjd1Gq6jkcgHwO8zs+efFlDXpMSaBbIzE7H4A1gDPgI5FppFCV5rC/kJEPEN5DmhS1s4p5dKczFnHXRoBMnxVCvRmLmcaPpSPOdFnhsufCmHofXhoQcleAV2K3z6Glx+fvWOQaPRaDR8AbwshLgS9XPdIoQ4E3gF+LgiHWgBVous3aJEUp9O0LBIkPumfLh4jTJH/twJWjigYQLERUIgG7xm6NgUvn/02D5/ng2PT4L8IqvgvD7YtgfGDoH24bDPDbcugbQrULnDMlDJRgsC/G2AA2Q+iPdBxgPb/bDkkKpziIvuPWN5+D8Oxj0Jt95Sufs++2zbkZxZBYSGwtVXh7Btm2D2bLX68sILBddcY+Gaayr3thQCfnsLRj4FLg/ceTU8+RkYUmWsj+piZsXXsDnFwsD7UQH5wbh9aTV4q24e0d54GtmcCCQ7UptBax9kh4BPYARUpWu/V2A4QqARBObDiPlqgUDiebD+rsLSQj0fgI371LEN70D9UkoOVQUbJp45qpaoxwcNbnWSlRvB0BggTUCoCnsbPQ6Gn1dyZQSNRqMpFR2EXx7jgCmo0FuBysgpUMLsuYp0oKe3lvhuBlw3VlmuJLDof9C+hTo2cTdsc6lX7uXd8EEbtTpyxbvw/XxoWhfOKmVR68ag1asodevADZeoxz2j1LZ3ADz8JXgzAQnmDhDYhhJfZwBWMB+Sat8BA1JziqWs2L7VSYtmDjIPw740mL8B+relQkREmBg+JpYvfpSQnkeo4ePFF8Pp3dvGd99Jvv5aEhYmCISZOed6uPEKuGZoBSc2SLe2sC5YXmn5FpCfFR5r2kRgtsGQcSrHGZuABMAlyV8qcNwucMc42JefjNXmITcsEos5gCk8B++BcKTbAhkCY79JLXrYCDtTOeLWdHlhyGswvDM8cjEsD65+DLfD+j1VF2D7U9X7ID6m5ON5qank7t/PG2u7kuUMhYMiWD4JlfbfATl++L+9cEst1P3UaDSnEVqAlYmU0gdcK4R4EuiCsqGslFJurWgfOgaslnjufXC5Idep3FUffF14rE8kOEwQaoLeUYX74yLh5gtKF18AF54JNqv6og4LhXefhF1/KRFWlHv7wV93giPYrlUbsLQAW2OOfMgCZtQ7wmkCa7TySUJwp4WcYK3Kfg/DgEdh9tqK3fv6rTBthgW/yYqtQTRpaXW4/XaVHdVmE1x3nQmTBZ6eJPhrAdzyKKzZWLG+S6JrC7jxPLUQMi4SLrsFGs2GnBHAxcFGa4AtAvIgcm8ecY50QiPcWGwQlpOHwMBkk9hi82G5hLUU5hPLolj+MX8ObNoLr/wG934GY4er3GINkqB/m6rdQ14+NBwMHS8tvc2CF15g+i238NZM1GtYINQK/nEK4EqYVVppJY1Go9EcF1LK7VLKb6SUX1dGfIHWt7VGUpxKMGoYYLeplXJSQo4Bt9aHduFK5vSLrly/bZvDsmnwxwJo3xwG9ym97RmtYf1UWLsDNmyFJ7egMuc/DA+9A6vWCgiBMLvEvdJMQCYBPkLsBiOuDmHYMNVPn9bgWQeN6pR+rQKcHsg1lAss1A4N6wlstmPbeX0QCLopTQIOHoaOZYiXD36F576CMefD41cXPyYETL4HJt0J/2TDkCXgBJWOogXBGkjKJydCDKL7ZRZqTSR2t5fuIUtYkN8f17YIRI5EmlGVtzGrmpD7KXThWoEAePywYhec3Q5CY2GvC0b+F6bdfez40zOgyxB48n64+dpjj9tD4MwekJxY+hwMHD+eg/uzcI1H5aLohFqheT4qXUUjcLSHy8roQ6PRaEpD6lWQpSKEeLOs41LKe8rrQwuwWuLdp+DcW2DrbujXFQZfDUlbIDOg8on+2hB6hpbfT0m0bgqtmsDnB2H4KkgKgaVOWLYdRDY81QGe7K3aNq6rtnO6KyHYrhkM7gS3DIKHV6lYMokgJAScAUGo3cZv8+COWRA+Dq7pAl88VFi+qCyyndDmScjIh0vGwDkJcOnZJbeNjYJG9WH7bujWAQb1LrmdxwPbt8O97yt34hOfwkPDwWPNJoNMGtEIX0DgDUC4DeZlqlioYlwMfA1kgmxVkGpC+VulAYbPBLkmOrjX8s+ygcS1SiVtZxKiuZ+o+GxkYoDc7TEYOcGPj52CDK5s3AdbUsAZXBn57bLCMlNFCQmBxg0gKaHk+7RYYFY5YZwhERHkh0dgQrk8cQIWsCbDW9dAqg16RcO5FRDKGo1GUxQpIKAVQll0OOq5FWiN0lUrKtKBnt5aomE92PhLYa7QelvgUNCNlR6A8/fA4ZbK+lMVJu+BR7aqtBOEA+uBParkzlO7oakDrgvWdnThZX7IZtpfI+hPK8DK7VcpEbRmC6xcAn/vVAswJ06ExxfApkNKY3y5CgY0hZHdSxlIETYchGyXsgzN2Qlf3VV6W7MZNs5QrrfwsGODxjOzYMt2uP462LcfLGFg664WJwQsLt5iEgYGdTP6c+/7Z+MNwOP9oW7TQkMVoJ5ECTgz+NgMh2bVpc7Ag8iAQBqC9PlJhI7Mp0fsYhJvTGF7oAVp1iSS2xwgxOHFi8TbwI5rfZEKkBFANnhckBiuCnQbEpKiVWUkCezKgdWHYEADSAyDud+XP4flYYuGLu1g+TrgMJjcsPHOYysZaDQajab6kFIOOnqfEMIOfAhUqACdFmC1jBBKJB0+qoZhvgEZAYiv4ivy1t6g+BIoX+ZuCpWHAc/NUQLMQPI8P5BKNgAL2cI4hiGE4Orz4erzoUNfiScAYdGCmRtgISDDVb9O4OYfICUfxp5Z9pi6NYI+TWHRDnjm4rLbgpqbiPBj9y9dBWddAT4PeFIAqSoF/TwWBvYGl/Dix49EMvdQFs7gooTn5kM/AxWQ7kMNPgCslSoPWhZQB3LXReHZHYp0gC/NRuuu64gMzaU1m0mMPMQvCy/HGuMBuxefSSKAsB7ZeLY4lLXMAkQbsMUEUhAXC8ntYc1eOBgFkS+jiqanqbFHtIUtt0JSCfdaWcasg5iz4dJQmLMa4qPVog2NRqM5LrQFrNJIKd1CiOeAP4D3ymuvp/cEECogwQIHixTZDjNB7HH428OPPtdMMdPP9nzo+D1MGewkNTIbXzCKfBeHceMjNJgi/88/DbatDmCymGnaCP5aLZBRQBuUgRVVn/KJGXB3HxXUXxo2C/xVgYIMWe6gC60EDAOG36csY0iUuJQgYqBJS+XasxLFVYxgP/uYv7KfcsnlqfqXc75BGYoPoUoIxUpoBGwQwbo9Et9gGxc9/AOd6q7EYvKREJ9KFDlYCFDHfBivJwSTzUd2Shw2hwdHdC5hXXOItmayY24rDL8ZVpiOVAnfsCs4V3EUBsPHoKxk+yDvIMzZC1dVMUC/KB92hL/WwQNbId8Mafnwz3ao54C0LOjaRqeg0Gg0lUcK8JsrEGtSIUoqanzaUgeo0M9rvQryBCAE/NYQEs3q+znODL83BLfYww4+IJ1/yjzf5YNJ8+DDJYWB65NaQ5gZwk1g8YOpM0qEBTMR+6JhXSbcuzGbQ0STRix5hBFBKPYCZYWq9SgkmA2DTXvAtRtMKTCmYWGpI3UTx//Fvns/PPFfSHoF1qRCpgs8UnJhTj69s/M46DdoMQ72FmR0LxAyXcFzDfT7L6QHC3m3pg0DAudwfkMHJi8wE4w9qHf4GiAXaAw0FqoEUybKGhYQsEXwR/5FmCIkcfHphOHEEhSoeYRhTvRhhFjJORRP+p66HNzcCJPPYO/CpkiXGdwmaCmgZXCcEmVdE0U2gq9FQxXY2qmU2K8CnB7IyC27DSjXcv2Q4vvWb4Y2l8CAUfDAy+X3odFoNJrKIYR44KjtQSHEK8CXlFyi6Bi0BewE0ckOB1uqVZCRJpDCzwJuwU8eJmx05T0iKLnq9a3fwLQ1SgBlOOE/A+GMGFjbB+ZnQb0Q2NUS/m4BES747xqlM6IS0gnrthRvML2+GwtNaYigUEkNGCj482/Bg+PNLFkrQEBoBozqB0npMGEOWMww6UIItZY4PNweeO8baFwPLj3GS67YvR+a9wK/B+gHRjPwBGBXwGCuP4AAbvjFx47mNhgn4AnAL9Vqv2ZgmCDHA5MW+xkzyE2UJ5yu78C2FGAJSgQV3FYI6jdJFCrnWQRQD/gd2AtcIXD5Q/l+5xWMafM2MqgsvdLCN1lXYxjmI51Jw4TPZSdldiM82aEgg6rUgsotth/l3sxDWcGOtuwJ+GQYtC4nN9iAJ2HtHsieqhZLlMUFHeG2gTB9FdSNgvU7VUJagG//gtcfLmx718fw0wr44GY4r1PZ/Wo0mn8vUggCluqSCN5q6uek4uj17QaqrszHwMSKdKAF2AlECIgKug4NfARwUuBn83C4VAG2IwPcfhWwv71IjqcmDrUVMDpoZWkcAuOWQ+MWezBZCoPPAsCvxkHq+rxcEWJjF25GsIX8XgEGPt6QJVfHYTXDyKugd3eI3gbvPAKfToLzSlmlCPDSVHj+Q7VSctFUVT7oaF54E/yu4O3OBduFcF5/8AdMnPeejf0dPczcbIb+4EjKIWJ1JpZQH0hwr3SQuzQG955QXl3mZdmgefhWtWZbRhMap+/k1uve4pmPnsWd74BDwYCxAHC1AJtQ1rB44DqUlbA5SMxkeOLYkN+efo7ZGEIwM3UI6/3tkcesxRa4AuFHXI7FiARcQF+Ute4QhWJQwpDGcH0Zc1fAxd2hSYJy45aHEPDKVWqbPRvatoE3PlOpPe4eUdgu2wnv/KUWgjzzrRZgGo2mbAJmnYeiNKSUTY63Dy3AThLMhNKMu9jNVKLpQiylf0tPvhSu/hwiQmDc4PL7HtsRHmwP/xVmfpKQ7okn1ZmEPdyJzeLlVlcudc0hfGbZTHbQZ7a+70HyN8cRai90NbZpAYdWlu96jItSqxolEF5Kao2WRd+6AgIuWL1aPfHeaCd8y0FkpIP4NgewRboxmeWRtvYuTkI6uMj6OR7/hlC80iA1LB1+aMK3X1xM68YbGTboO9p324Q/K+ifywL2ChWX5Sly7UDwWLxkt6kpHxy8i/iGqaRn1+HbHVeR2Go/QhhIeZS3PgAIo9ACBmCSysXZG2Vly0KVfQoDTGAOwKSjXi8p4c+FkJIGw8+B8KCAfuqKsue4LDq2hJRZKqVIQhFLW2QoXNod/lwDd59b9f41Go1Gc/xoAXYS0YCraMBV5bbrXB82PVxus2JYTBCe15Q0UzYr0nsQFZOF32JSCVIjsnjCt5NYSzommgFgJw+bPcB1WX6mefwg4W4HvBoVxo7ANC5d15otKa2ItFh4t41geL1CVXbHldCqMdSNh2YNSh7PPbfAuo3w52wYdmnRPFkSv1TiLWpIWnHxFUSYQNgk0Rel4ctPoE5eDH/f1hF2gzkkgDBJXM5Q/FlWjgSr5Ui1CrI9sKtIZ1IifAYy3AR2iUkEsAkv32+6gjoNUkmITmHbgTb4fTaO+DSFRNT1ITdZ1SoBw4SwBJBWk3JDFqQV24qyhnlAWGDc2dD6qJxcr30CT72jHr/+KaycVj1B82EOtRWbNwHf3X/8fWs0mtMfiSCAtoAVpbzkq0XRiVhPU3J8alVj0zCIKiUOqyhunPzIR8wOxLM6dSiG1UyI3VUkmarE4nPSzL6JSNLIIoYEXNyU25ovPQ4QSk+87oIW1nRe2tiJnQebg2HisAdGrJD8YlGJVkF90Z/dq+wxmc3w5KRcHnFZ+GlRKCGHIOEsP95PMsiMN2jjDyOtSXaZasRm9XDB5R8jZ7TGWGCFOnD59h9JenU/C9edAT0NGG2ChsA2IEpCiFDZ4rODnQgIteVS372PqLhcEo2DTFrwMC5rKE0abMEt7DRvuZYtu9tjuGxgAovDgz8zBHpKYnyH8WfbCGuSS/qqOviMoMnvEFi9KvsFXpWEPzni2Hv49q/CQurrt6syVRFhhcfz3fC/uUrTXXMmhIYc24dGo9FUNxKBXwuwozk6+WpplLKuvzhagJ1irMmGAXMLE7rOOgO6lVCsed0huOknyD8IzrU+nIHL6Tl6AbKpCcwCtzsUhyMPk5BYTX6ahu0AKRkYmE2eiGC5qTt/e8yFRp+gVWelawnph3rRp/4CTMJgxcHuRIVn8d+9dTgnoZxo8SL8ym4myw24zbBmTW8ejYO813OwxhkgYIXhx1LOZ98vbGy2t+brIVcyq9kydtKcbXtbsq11S+UGtBgq1sskoEkw91eahFihFJE7gC3Mg3N8FAdbSxyvbmVLXiuS2u8jLjaHB03t2CasfBayhe4tlyAleEQoB/cncziQBDaBMzqCmHZpeHeG4vvLrlycbiAXfFFq3go+iT0aHXsPV56rkt+CshqGF7FaBQLQbyxsPaCev/c7LH6lYlUINBqN5ngJaIlQjJKSrx4PenZPMe5bDdm+wuf3rIYFA4u38QXgnKmQkgvMAhpGgS2Kn1+/jIY3bWdP2wY4A2F0brgCYZE0EnsIEV48MpSGgb10C6xkkJjLJvN5HAgkHhFhUSKb1wOX8VIPK1/HXoyXEC5s/wO7aYQ54MDHTVixsPggDPkWGkbAohGqJNDRLCUNL6pIpKNhlhJHgcJ4daNiPyAwYWAx+bl29Cc8O2U8hEpwAPMDkC/hKosKtPcDCwX0kJAhSTSlkLErFu8MB5ghzxTNm87uTGm2jlUEyCeSukTRBzvfIHAj1aIJPCRIMzN9BtJqxuN0kL2nIYm/QOZekPWBbCWSrG7o3Bqy8mDcBTD+DaUFP39eFVAHuO866NAcUtLVitGiBr+dqUp8OYMxa+v3wL50aFhKaaEtGZDhVq+/9Th+uHq98ORk2L4HnrgdOpa8FkSj0Wg0x4EWYKcYR9c1dB+VUd8w4NyPISUTFQjeA5WGwQb0hj05zWAxMMjDsrzuDIv8gTDymTdjEFvWtOHTkNGcOfRP8uqG4bXv46rwWfySdRH5Rhi/mi7FIdz4pJ/4QBZp1jgiRC424cNsziedbJKI4+stkOuF7dmw6jD0r3/sfVxHC+bnZpOXZSVlWT1osxvXj5GExWdiiTW41OwuN5GKTXoYIOdgNgWIGXwYwmSwEoCAb/1KgHU0QSuTSuf/I9BTgCE57KqDMccC6UASjB4qGNBEsJJo1uBCIGhICNFYeZG2PMsW3Bh0W9GMNx9LwCRB3ACWFtA/HFJ+BbkCQlfDy29DfiT0bAa3vAsHM+HB/4P0tWAEYPNYeP56uKiLuo/Bpay3SIgu/txkgrgS3JgFDPofPBgP/7cGbu9SzuSVwcT/wpufqlQWsxbD4QXa6qbR/NvQMWDlI4RoCVyOCnQpZmqQUt5U3vn63+opxrNtwWGGSIv6+1y74se3psPivShTUibqLWFCpUcwoRKC+cG3IRSvtLEgvy9zfh3MmsVdceaE07LLRiIScmhs20Vn2yrmec7gzvi3OJDgoactlgAm0s0xHLaox1uN5kgJUhiYgx/WMR2gXRyc0wh6JpV8H82I5MLlZ7Hro1Z0ab4cq9VL/ab7iPk7jxc2xLDg1yZ4t9ow3KXHgJkwuEb+Dy82fqx/KSLOKCymGY1yBT7shUvc8IaE/gUnCgyLmchr06k78QCvPOfjv8MhHT8f4yaXCLKI5D0yAehNLD/Tm7/oy87pibi9EPBB10XwRjb82gKmfQH9zgZvS3hgHnRsAg4rpGRBvgfy3GBKBBkHaw/DZZNgd9qx91SUSAdMHwet6kPrZPj1SQizl96+V7D+Y/v4svstjz0HwR1M25OTB35/2e01Gs3pR4EAq47tdEQIcSEqzffFwE1AK+ACYBgq+KVctAXsFOOsBFgzGFZmQ6coaHFUwQO7JVjWJwvl1ktCpYeTRnBxnsAelk/ffnOIis4m0x/NgjVnYbhV3ojFs/qzeFl/zhg6gzZNN3BtyBfYpI8vzI8joi7G423JNmtTokQOaTKegyTSUuzAkAbTAv9wu/k8WsXC2pHl38tV/fYS2e8RAsKEZcEldO27GAMTi6yr2brsfLyTGhD7yCHsA/IxhRVxSRoGIcLL+MAThJPHuJxnWbW5B1IU+T1xlw3e9ioR2s0CPU2qTn0BVoE/wUbs4D1MESn8hYvzaYgf8AR/l3xPDo+RWGzM1wyG6YuUKFm1Ah5cCkvOhQkPwu7eEEiDgB8e+hr2HFJVC8JCwOkFGQkF/4t8PvjoD3jm2nJe706w6d3y5xLgu2EqD9gZpaw8rSiPjSlMjfH8fao6gkaj0WiKMR54Rko5UQiRC1wPHAA+BRZVpANtATsFaRYOl9c/VnwBNIyR3NzTwGwKCpbDgAe6N/mHmIh0zCY/Z134J4lxqYSa3CRZU2k/cJVarucDcgQcECz48ywW+PpRz3SAMJMzGAa2mpCAhybGTvb4G2L3WWhp3oGbEBbSm9dlfYakuI4sECiPJZbfCbG62W+tj4EJk01isQXIxk3jVlsh00TG2EQyHk3Es9KurGF+OFOE8pZMIM38JJeZf2Cm+WxyM6IoTH0P1DHB03aYZIcbLMXFVxBPjh1DqJRe+7HwObvxB2uWWYHWHLvk8NL+sP0z6FEPvPmQ74dZy+CCD2BfjjrRbIcDmZDrhoBJ5YCWFtQDA3VBH6xfXrF5KiA9HSZPhry8yp1XWZo1hL2zwLsa/lOuEV2j0ZyuaAtYmbQCvgo+9gEOKaUbJczuq0gH2gJ2GuHExzhmsv+iLC5r35Dc6V3ZnybZkiY5b8h0YsMzcHsdrA9pd8RaZBKS5DZ7WPl9r8LM7gYYeSYOBOqTZo4hTqicDRJB712LcbV10Feuprn5Pd5mJnNlN9KJ5UzrHM5Oepan80fzn7DBhIuyP3iLA9k49jbmly0XcZv98JH9EjC39lMQku+eHY57TjicBdY/4f6voFt72EkEr20/yO4VjZGBKiTPKpLJXgBezNxNJH+TShKRTKAweM0wYOd+VYapYV244GxYlKGOpYRA6h4KV4yaUQoueNxXELdnRhUAF0AOLF8HvFbx4U6dCg8+BFFRcP31lb/dyqKLeGs0/150GopyyQUKgkIOAs2BdShdVUJugmPRAuw0YiY72EcOEjAa76HNXfMYIg+wcmUnLHYfVpMPU0g+YSKPPBkOwoTF8BERmoOtrgtvip2Qy3OxtPJhuE0kefYTFupS6xElWDx+nst5kvnzzmRA4hw6tphJLvF4/TaEFW7hvziEizz7lzTLb0Frbyi/xCQQLkzk4CMCS7G6k/PT2jH/mftwxDqRQ2cig0IlEDCzz98YrgH+F1wX2RFYBjYzxAff2o1kKHtWNEYaJjhqcUJFsIR6VSJWDJWOAxOp7CCOTUFX5OVANE4XnH07rNqi0n+c1xfmHOSI/djtQ9WATFbP/QZkulFjKrhdEWy/G5WcNRsa96dS3HSTEl/Dh1f+XjUajUZTrSxGRRZvAH4BXhVCdELFgFXIBakF2GmEGdMRgSOlgRB+pPDTsf0KXKYwwsnDK0LowFo2i1Y4ZRi7RCMMzDQduYVtm1piaetDmMFkMdie2gp3ZAgek50Q6UGmWPnTfR7enXZ+2jiMnze7GXXRR/SyZOCVNhbK3vRgOWuy2/Nk+AQy7VEMzL+aB8KSmCR2cx3J3E1T3H649W/J/BmDkX4z+amR5B6IZM+8cESIZPvWluR2i4LhkshmgqGRcEtnsKeo0jqNgoYpAYQIgavgiSxagbtsLBYvPVouYpe7IWFWLxZLHpFYcLILL35CsLCXdJKI5tkPYeWmwsD0PxaB6+gQy8Axl1Aux4L4qRBgBiobvwmik+CrLwm+VnDPy/DTPHjsRrj1spLHHB0No0dX6PY0Go3muFBB+FoilMEDQEEg0NOovAPDgS3BY+WiZ/c04myaspT9rOcQsbioF9iPmQANsw6Q7aiPKyIcC35C8NGRdfgxY8PF7JCzSBMxyoJT1GJjM2FkWlgW2517XG8xzX81vj0h4FOmn9B8H0JKzCYDs+FnYvrjuIxQDMyEZLl5Ovwp9ot4tnq/xGTrQ4axiI2uWbT/ZBTGdjPJnffR9KmtOA+GIReYWPl+L0gEmkslWIQgT8LNDhiQCEfFwyMEfNFbcP1iiVdKfH6QRsUEmCFNbE1sRp4vnF65fhItMXTz1KFTUhxTxRzqEUNHGgKwfluh+AJwuVEefwtHyg6ZQyAQ1H9mEwRyOFKGCBOIJigLXwxgA4+dIwH5KzfDR9PB6YY7X4QbL1Z5wqSE2yfBup3w1RNQ/zhXN2o0Gk1lOI3jt44bKeWOIo+dwO2V7UMLsNMIG2aeYiAAbn8qy3Z/iAh46bFjPdaES5jbbTDbWUhAFcjBLAKcwXzOlHNwe8K4MftzrBFeTHY/Jp+BLyOUufFnkhmI5j+hLxJTLwPpKxQ4TmcYqTmJJEalctiXgFfaMIIfWA92Jh24D5eIYHVYQ96Ke5BmxlpWHOqG2DUK80E/LV7YhMkqiWicg22dGaKAdvL/2TvrMCuqN45/zszt7WULlqW7EVBBUUJFsbvF7hY7sQP9WRjY2BhYWKCk0t0Ny8Iu231z5vz+OHfZYJfdBVxF5/M899l7J86cmRv7zhvfV0lmCMAP5mIYuwGOHlz7OZ/WEkpaqgbiA+6RLOwqwV6PESYkZoIgd1YKxnYHk9warmbwAXB6Shs+7Nem2uaDD4Gp85WBBGCzg1EK0gPYQDfB7gEjAOhw96nw9I9g7kJ5xorBPQeGngKTZ6oxNA1mLICzj4eUZmFvngNccfDEF9A1FdokwpuTAQmPfQhv/MP6OIYMmDAdSrxw+XCIqqPxuoWFhcW/DSHEJFTF4w9SykB929eGZYD9S3HZkzky9nFY+wAf9ruDaYktOI0etMHPNpYQwsYG2uInipO1z2kbuZhkTybF22N5svPdtI7ZyoxWQ3jr+2sxUm10HbacMlcUMT3zKFrZDCFAd4RYEehJN3MVWSIZWSX8J03IzE/FHh2kLCeCdgkr0TWDKauPxyjR0XaZyJAGdgMZEsqwS5EqpbEPKn/KC3wMcxuYDJ77h4AlQThPSWrgqlHkWxGhjBFQrGNkqO3MAJR7gCj41AfxO+CqZtAjnF5524WwejNM+EFJfBgRaiytHDwOaN0cdsVCyAu9YmH5LyDnKDX6IOqY5SFYngWH94YV68Fuh0FhsdQWifDnu3Dqs7AtBx79SO3jigBhqFqBiAb0/Gxq7ngf3p4KhglfzoFZT/zdM7KwsDhQWEKs9eIFJgBBIcSXwIdSypmNGcAywP7NJAyBI2czj/eQ+PmTzTzN9btXp5NDGX6asRyfvoaf2x3DS4W3kuLMRAgYGPUnn5iXkrM+EeNoDacepO2hmyhttYuQ144npYQ4s5AjxGxybc1opuWSZyRghHSkoaGnhsAteTnmBny6Cw0TPw4IgFmks+zq/rS9cQOla6MJ+HNgE3AKKnfqd+BlIE+o/ooN4Nl74fwryjD+yIbB0bjPTCAYoT7iZhGYs4BjUYnwJpVNGiWqfVGyko14OQ/eyYfp7aG/RzUOf/cReOtBiL0oLAORqfa78hR48mYYeAbkb4UVAlZFq/Bh0I9qgWQHzQPeRJgfAlsnpf+VWiWkGh8H2/JBBivn5PPCFSNVNPahSxv31jcFM1dVtklavHnv21pYWBxcSLCqIPeClPICIYQHOANVMjZVCJEJfAJ8JKVcVd8Ylg7Yf4CLGUx7krmY6nG8CGzM5U/m4wHcxOsF3N3sadyaF9MUhAwbxd4YpCkQmiRGFqBJg8jkEmLa5BPpLOUx93200nYS621Bv8iFNNtSgJxvR37sJDQugsgfvQS8Sk9raslxzE89FCIAGxTMTWDxRQNZ/2RYzl8X8IuAMwXco/TIhIDDBtR/ji9vhVudMOLraAb0dtBqdQmz+gYJng/B8+GXzuDIRMnk7Qj/3Sphi1RuqgSqfRvKJNyfVf0Yug6jhoLYChSBLIbxE2DWfCgqALMEEEqyghCVYriF4BBQIsAUEHDDQz/Agi1qXNOEuMiwPVjV22fCtafAuNEQU4vmWwWGCWNnweO/02ANtgPBrSeB2wEeJ1x1bNMd18LC4t+FEMIlhJgvhFgmhFglhBgTXh4vhJgihNgQ/htXZZ97hRAbhRDrhBAjqizvJ4RYEV73shBKUEcI4RRCfB5ePk8I0abKPqPCx9gghGiAjLhCSlkupfxISjkSSAWeQynjL2vI/pYH7D/AYXTgMDrssfxNPqaAIiSx+OlPf+aBlBQRxabCjvw89yTuPOFxeqYtRwgTf4kTudrO931GYrpsdBE7WcsAyklkRXEKtua7SIvdTuZ7rZWlgaBgdhIXp08k5cIdzPIOxetwK1HUcgmrhEpSj5FKN6uVhC0CtlfO0eOG0beq5z8uhrd/g+0rYOkSaJEEU96B6OZw11rwm1AQ1Hj+kzYc44Kpa2DjAjijLwwfImnvC7E2ZCL/1OEDXbUqAnBKaCuoeYl2ePe8lk+eD2+8UFn0WO6D5ybCx6/AhS9BcZISYBWbQBax28vm2wG0Y7eRJyV8MQ9OegJyi+HwjiA6gNyMcmwD9mTo36n+93fCEnhoqjLk3j+0/u0PFKOGweBuqtVSj1ZNd1wLC4umoEmrIP3AMCllqRDCDswWQvyE8i79JqV8WghxD3APcLcQohtwHtAdaIHyPnWSUhrA68DVwFzgR+B44CfgCqBAStlBCHEe8AxwrhAiHngY6I/6xV4khPhOSlnQ0MkLIVzAMGAE0Ilq/8XqxjLA/qNIZNj4UolR8+jLCbzFfPE+y2UJRqzg7hOeQCB3C3Jq0T6KD7PRa/pqmvc5kry4QraRxI7slixY2JkBx+ey6tPeYGrKiMgBWa6xLKMvy7r2ho66qvw7WmJr58fsqGNm2cBjQpSEmShllTAeD5xwnErAX7QJznoevCmomFwQ0jPg+kfhszeqF29m5ELfd1W+lq7BK7/DiVcHWdcjiAxqcL8DSiu2BkJSfa0/RRmCAAGQW1Ff7ypERYKnM5Qkqm1YDdN2QtxqyG4J5UHADXp3MKKBBeF5CeVBC4UNMk3A6z9DaZl6vXAztO0DGXEQCIFLwB1HNOy99NjDMmNa0zfNbldHr08LC4uDm6bMAZNSSsK/yqhfYTvKGDoVwpVlqk5qOnB3ePlnUko/sEUIsRE4VAixFYiWUs4BEEJMAE5DGWCnouQiAL4EXg17x0YAU6SU+eF9pqCMtk/3NmchhAYcA1wYPoYRHveYhuaCWSHI/ygCwSH0wIEdB3Y60R4PcfThbJqJQg4RS6sZXwA6JpGinMghBdz+8mCmftWHlNWZlE6KoTwzkhlfjKAsO0r1X8xid/4Tm4Fx4Egowh5TBrqJHqkTXa5zYgdB20QdHAKnJrDZIDIS3C7ofwh8+Q3ccTcs2QrBLqiv4qnA2YAX1m+ABAd82Bv6RcOVreDXn6EsoPowlvph2Xb4PN9UocGtLkhX3rmqV4NsYDHqK2QAS6Dt+j2v27sLIdgLSELddw0DUuH71WHjK4wh1PLIRHUuD94CrRPAoalI6/Fd1PyIACIhYAd7JjwzDC7oAS+fCI8dDXMWQmpf+HRS3e/lOT3hvTPhjVMhKaKhnwALCwuLJiNBCLGwyuPqmhsIIXQhxFLUr/EUKeU8IFlKmQkQ/psU3jyV6l6mjPCy1PDzmsur7SOlDAFFqAzjusaqj53Atyj9r8uAFCnl1Y1JxLc8YP9RMtlMKTkUEk08CZzHyQBksIgem1fga2uvsxWNnRC9zpzPXZc9y0Dvn1zBx2RGNOfwS+ZixmiENtqVyyeskUWEgEwNuUJHPyyA7g7ytBnDLWPUAfICMOU3GHEqFA+D41vAdWfCzaNhzjxYvgquvw3MOahPrMbuxPzMDKXLdVZz9QDoWuO+RQhIytAhy6Gak9uAk4A14UcFJcBsYA64TXjw0T3P/dW54KuIP2qAgN5tYWMe+ELVt432wG13wNl9oHsnWHkLZKwEoxx+XA5mDyrtQB3KNbi1Sgix3Acf/wo7C2HhCjj5RIispTG2EHBOL/V8+vQ911tYWFjsCwfQA5Yrpey/tw3C4cM+QohYYJIQosdeNq/tv1NdStwVmbH7ss/eeAiYKKUs3NtGQoiWwE4pK3q9VGJ5wP6D7GIrX/ICpSykPSvIIp/fWQtA/LczGDR6vqpkrOUjaKJhCI2RWT9xeOkc3AEfUYFSWhdt5akZ95J8xI7qO0h2twkydyijTugGj7fM4AZ2sMzwc+ynsCMHvpsB0xfCPd9BzCj4uAgSj4fobrBpGxweYUCZAV4TFhigmdhuKeX84hLWGZXWzxVHKnkIUKE+CUxZaodSoayVC1A6xVVlExIldATaQY+LJF89ZeKLkRTXUHfx1JCD8Djg3EOq9HusQtCAC4cq4wvgp5ngzwc2g3cN2EqqbGyD7UE44gUoLFeLht0Gby0EjocXSiDqCbDdCQPugc279jyehYWFxYGiIgTZ1M24wwbNdFQYcJcQojlA+G92eLMMIK3Kbi1RHqkMdjeFq7a82j5CCBtKeTJ/L2PVN8/x9RlfYVYDbWpb0WQG2F6qHPoIIeYKIZaGXZNNmEb832ELQZ4inx8pI5t0ADQkAomDSisj6Y8tRG8vRcs2sPmru3R0X4j2Czdz2OvzuezpD3EHvLvvE5xmkJT8TFJSMqC1VJ8sDaXrFY7sa90DhDY6EEWgOQ0+LRD0T5cs6WBWestaoEKY8yShWbBzpWTSBsnxk0PM7RhE71WO5gqgXxLA/VsB/nN0vg3Z6ZnjZ1dYw+GO4+CZM+DwdnBSL+h8KOj2IC0Gb6X1YeuIuyMb1qEi/DrQGuVRM4AAbJCSkX8Khv0GHSZJdpRXXoOnRygjTNfAbYPUaLhhIBzfGdxVjDO3HU7oAh0TK5d1bA0iED5PGRZqrcApQcCfW+G6r2HgmzCvPQSORhmGEUAQDDcsyoGjHqquzn+wICU8+yKcfgGs2/B3z8bCwuKfgBAiMez5QgjhRuVWrQW+AyqqEkehQn6El58Xrmxsi/qVnB8OU5YIIQ4P53ddUmOfirHOAn4P5579AhwnhIgLV1keF152wE6vrhVNGYKsq8rhUWCMlPInIcRI4Fkqk+4sDgAmkpPZSQEmLgSv0xUnTrxIAjhpTRuOC2eb/z5qIEcs+IX+3y4nOr2EVdd0obB1NDYjSLtZ2+j46lbENhD+sO1lQqktgjNbfcGv0SPgIwFDgRIJQQEOCe+A/YEygosjECaEcOPr78Gc7II4AcMlJAJHoD6RP8Luz2yBgLUSMmyYuRqssUORUMZInwDSUPcQIanxtVHKdbY4hIAbh6sHQNKLQRKP24mrXTnCBrEtcvF2jcCXHAFHAR9KiDXgTx2EwN8NEAITKDAkH26Ce3qqsQa3hXnXwQ/rINoJl/SFCAd8fhG8OBPeXqBmfskhsLUYOr8AyZHw4onww+twyd2wcDqkJcMFt8DjUyR+jXDfSGXNfmaifk5Whd13NtS3JxtIVMKsxV5YswP6tv2rPjV/DYuXwiNPgdcL2Tnwx5S/e0YWFha1IRFNqQPWHPhACKGjbt0nSil/EELMASYKIa4A0lHZv0gpVwkhJqK8SyHghnAIE1RLoPcBNyr5/qfw8neAD8MJ+/moKkqklPlCiMfYXTLFoxUJ+X81TWaA7aXKQaKaz4ByCdbr+rNoHAEkRZi7g9o5uLiMJymhgFgS0ap8yWZ1D7Jk2pVcM/p9IkvLaNN8M1LTVD/DoyT+mXbK5wWJSwBNB8MQHP3gVDbntINZmnLmRqEkFxyABOcXBZgFDtiBUr9HIj+xwxuoDZ4GOoB9kJfgDPee9wtSKNmK/kHEsSGwgZxjI9JeQoHpINIsoQVZdBY1mkWG6do1l80xQUTFpz0gsH0UhG6AJuFPwJsNrW1wdhLkC0iQIAV2DZo5q4/XI0U9qmLX4c6h6iElHPcuzN6m8sLW58JRb8HiG2HahMp9Zi6B9j/A6oAJpZoSC+sMdJQQqnERCoBZQG9AQMgOka463vB/MIkJKiwc4YEO7f7u2VhYWOyNppKhkFIuB/rWsjwPGF7HPk9QPZGkYvlCYI/8MSmlj7ABV8u6d4F3Gzfr/UfIJlRuDFu3i1CKS+OklHcLIbqi3H0CZfkOklJuq2Xfq1HaHiQnJ/f77LPPmmzee6O0tJTIyL2oZP5DyMFgFwYuBO2w1xl7ziUPkzLisgvRCWEk6MgqG+uFJmw1MTWwa+ATLtYldiJUagcJUZ5iIj2lFMh4fKYLzRkioWgrwTJBQUw7VI8dCeWi0tROg5aOUnbYPaolUYaoVKqv+FQIoIWEyPDnVYKt3KCVJ51YWYSq6wT0JNCrF7AUhUy2FhvocQZIkIYgsN6pxgxJdf8kTcCEWJvSgKjoaxiuJUh0QpqnYdc6ZKq2Q9W+WgKaR0GLqPA2BqzYFBZtDa8HVCi04tg+VFhUoLxf4euheVSCf/ta7M2D4fPo96vCiZho6iz0+CdwMFzLgwHrOh4Yhg4duqi+RPYDSaf+UfLlhQfmcCeI6U06938SQogSoHfV5t0VNGkVZB1VDlcDt0kpvxJCnINyEx5Ty77jgfEA/fv3l0OGDGmyee+N6dOn80+Zy4FgK9ksKXkYPWcph324mPy7o5HhnorCZxLzShlbH/HickC7OJjV6yjusP+GYdi44JgPeOzCe3C6/BSGYpmTPYjlR8+haPMWhCkpj4vnzw/fY2OfPmSFWsCvAvwaNBOMLZvOE4d3oqNvI6XJ0ay+uxc4tUojqa+BOM2PqOIRf7zwEY7XX8Wt+3Yvk8KDiLoOmo2tdl6xp22jLDkFe0EQ3yIP0iugMKAS+tWeoBVClwQ4zsH558K3GVAedmp7DHitK4yqEfKTSOZRSgdcJIRFxHYUwcnPV6+KFMC9R8MFQ9TrP5bDI09DcVmVDWyoe72uEmxhA7WiiOF9oEy1t3z+ZejeGmIjoUvVdFP+fZ/HvxPrWh4YrOt4cGL1gjxg1Onl+luqIGtUOYwCvg6v+gKwkvD/Jmb7l/O4/1NWlTuIcpew5LQe2P80ICghIHEuDRLxvZeO3cHnB9OhsX5cK5wRXkBy3amvEHLZmMyJzLIdhdbcoG/7nQzuLXngGnjqgnw+MUZxX9xjuLRyGCHhWAOiDYTTJCa+iEtavM/1A14m5Z50GC3hJgnXB9Fuq258ATwRcxf5trhqy4Qsh5LXwCyttvyY+ARC74fwzo1ABjRVtrjb+IKw+w7cNu7oBQPiKkVTQRlic/P2vGZfk8/VbGIUlRnlLaKhRzI4qszXba+UigDo0Q7sNiWcarepECbRqHDoDKEaWVSxDUkAbHD7PXD5cDj5cbiwuo1pYWFhccD4u6og/4XU6edvyirIuqocdgJHhzcbBli1UX8Tn+/4Hpw2tkW0pmxliI5Rmaw74iyST8wl9aw8EkcXoZtg0yHyMA8TvzkJb5KTy25/FWwSb8DNKroTxI6BDUPqtLysLYMHK/FRTUDqH4WcmP8DryVcg10EsLsDuJqXEeko4TZeoL9cyAZfR+a4B9N18AYSeuwkvl8+KZqBVhF9DP9NsOXyY/yxzIweWCNZ1A7BTdXObeLbHpqn6Krp9mWArYZol6ZBagSRbo3RJ0NahLI7K3BqEGXAW0thY5UGFcnYMZGk4iBEEImJEPDr5TCyMyR4oHMCfH8J9G5euV9MJCx8Fy44Do45HDwlwCKwb4dvz4KZF4OoyJD0gzgcPBfBq9nQ/Hl4/Ep4/9b9eLMtLCwsLPYbIUSCEOIwIYSzjk26AXukVUHThiDrqnIoBF4K63L4COd5WTQ9ER/PxXvncDRvgEUb+uP/XGPNhx9w5CESvbzSGhECmmnlbDlrJsa6YhKk5Nq0L3nq83u54e53QYDdG6D9tk20OKKU4LEC28cSrZfaN2VHPoNa/MEZcRMpMOPoZy4gRaaRav5BzrYknvr1YZwRBn82y2fabdcS2LiZ+CMHM+3FcXzqt5GuSSIo4az4r9gk2pIu08ixJ3Bm3vfhGQbA1rzauWmaYPY0F11PlQRaASl2yPPDyTbVIqlcgkdQ2ttkVpSfuSVuVUxQrPY3y2HcHyj5CKD5IPBFwAnR0Uxp1YGZ2mu8xhY0dIZyId3dg5h0Ud3XusQLV7wOc9Yrw7QsRy2PccKtEnoVwAX9YFI6lKeDdITDoeGQ6COLYMfRdQ7PH+mwNg8u7/PPzrOysLD459KEVZAHHUKIKFTK1FmoW+WOwGYhxBtAlpTyEQApZZ19IffJABNC9AfaAz9IKcuEEBGAPyzvXyt7qXKYDfTbl3lYHFhG+noxu9sTROLmsllzePvm1kjDoMQuiDbkblFT3QVvLRaEykrQQipOlpS+hPgxo3i56xccecgcXr7/TgSSYMjB4+ffyW39x0FY7stlBNB9JqneDLJnJrPsmD4cFiogcXUR/RavQW6B8pkQPGsgRb8LkJLMzEwGbVjPE3Pnkh2CucFdLMaLXzgICjub3Co5S+JAuIapZHxgUxn8lAMxdji9FXzymOCs1cAAARc4wSdUlaVHKjddoeSCDRoJhQYyWldhwQAE50Cwym/Rlo1ALLy3Df6MzmbEYJ22bSUGIabzCcm0JmEv3SzOfwH+WAf+ivZFbYFsKE6G/AyIagNLjoRftsMpH6g6AXyoN8ANpUFYkwPdk2of/4afYNkuOKUTJP7N7YmkVN0OmjksY9DC4mBBNm0z7oORZ1Atiw5B9VCp4AdUdeYj9Q3QqBCkECJZCDEPmA98AlTUYb0APN+YsSz+eRz1xBOMXrGVGzdsISo1lQH33IM7IYH1Zx1OoDmEOmp4j3OwahRc+ovk8g9MOj/Tgt6/dKbdA82x2UKkPPADL95xG6XeSEq8MfiCbu7/ZCxFRlSVqkBBemZrXj/jVuLnZPDB9quJ8RXTMi+Tsg5u5AhwnQ/xLnBEqJ3MQIB0M5cfiv5kiX0lbT0amohEkwZ2M0DH0k0EZATC0YfyxNf4OPgyXVetpvvyMkbnlHHDzkLSppl0GgZteppwogCvpoyv8JyQwAJBaKuDooQSQCJM0GeidLgqMIFcYA7IzbB2eTteeu12lq/sEx5JI4c6b3rYlg2/La9ifIHSQesOIQ+ckgXzBinP2FEpSvSVYmAVSvUmT1VaxuxFhuLD0+Cbc/fN+CotNfn9dy9Ll/rr37gBXPwHJE+EU+YfkOEsLCws/gmcAtwqpVxK9UT7NSghpnpprHn7P1Sb5WYQllNXfAG80sixLP6BOCIq/2Mf+fjjHPn442STxtQLB1Mc1YwRuZPp6AEcsKtPW1JtcUhNJ+aISFyd3KQ/uAOvjKWabS8k4/68jruPfB7DrbHB1YaV09rweskw+u1YT7PVRYQidd4adDFBzUZEoJyztW+x5QU4ZGYMyz70MOOiSynvksJ891okYEcjWqRyhEwk0VtET9kRR+ojBOxb+VbewzWL36TMH6m0MgyJH3Ak+DjmcUFeADjVqdwxNetTSoEF4F0ZBS1MpE+DSAMSNMgWYAqwSfXXh1LSLxMQEnzx5fn06rEUicSNi8ncTgRJHMWd1bTWVqSD0w6+IHtgSli2GVzhzSMccE53+HRK2AsmQSuDI9OgZfSe+1fQM1k9GktWVoh+/TIpLTUJheCyyyJ59dVmjR+oYrxi+ORb5QWbGgQO2+ehLCwsmhCrCrJe4oBaSrOIYneyyN5prAE2HBgupSwQ1WMJm4BWjRzL4iAhh7aURcTh151ExgQxhIaGSb49HimUoaVH6CSdHkdqXhTOZeX4iiJ2Gzh+v4sFnfoycuDX+HARH8glt30ixhU2jt46g0c2PE2JLQqfTRlFJc4I5nQeQNusdPRmBvMfuZairGQGv/cn6QNakDGgJQGhkUuIn0UWD0acQlxEM0yZgc8czvdF/6PcHwGOsIxFuAglEHCRM8JEnlgGP4XgtgjIEdXbsUrgTwEdNdil+iMZug0yUSKoP0iYL9RX78jwPhlqf5/dRci0Mdt/FO3sBRTbdlJEBl7yiaCyJ1FSDBi19I6sIDmm+uu3TgKnCe9+qeTKTjsa3j+ncn0gANffC9PnwCM3KW0xbR/La556qojsbINQOJng3XdLufXWaDp0sO99xzowTLALZTxenVbv5vtFhYfVCnNaWBwYLANsryxAecFeDL+uuJ2/BlXPXi+NNcDcUKVxYCWJKH+Axb+QNfQk1+nFI0uZ6hxKtp6MhkmyzMQjKsNUfr9OrxsL6Z03jwXXHoUpbSBBzw8gTjEpExEEQ05WFh+CX7MTFV/M5DYnkRmVyqnLxe7/nFLTKbe5yYxI5oWUW0jXWkEHWNO+G2VLo4j5OZ/7ZjzO10+dhV+E+Ig53MdJSEoAjSyzOdKm1VL8K8AjYLgdfgzCuHK4wq28WcUCFgJBVM2KHlZgTRHK15splaEVb8KxGiSHDbdylOJ/UCJEiEeefYzSDbHMOqyUr68cTJSWzIasBCLs0DHsSBrQAZpFQWkt35gIJ9x8YvVlThu8dYZ6gGrjE/QD4Zqbsa/DJ5OUuGlOHnz4JYw6h32isNDcbXwB6DqUlOzFWqyH1FiYczPsLIITu+3zMPUyZSGc+TD4QzDuZrjyxPr3sbCwsNgP7gN+EUJ0R9lSt4efH4pqclcvjb1PnglcWuW1DFc13g381sixLA4CMtlINj4QGs20fLL05kihYQgbWaIF6bIlG4Jt8QVtvBdzNVuK2tEsIZ9hX/3E0Hd/5Oj//cyxv01GCIkZEixbM4CtGR3Zmd6W7RvbYQqd5bE9cQX92Iwg9lAAmxGk945V/NpyOMm2LBL1bIQGmm7i6VPCopT+pBe2ptPMdQBsIpt8StHogo0z6BO5pM5PttQ06BpeudKA20phYUiFFQehGnNXGG6RqOLhDUChUCHIdRpsFDAXpU6fCsRL6GwSbOuk9H9xMElj1/NRzPz6Bnw7zmLQu4Leb8KOcEXlT7/DNYdBlFuFIiuIcMGIPnDuEXW/H+np0Lw5JCXB1Klq2aZtyvgC5f3amtGot7ga114bhcejLoDTCW3b2ujZ07HvAwKHtISTulf3TB3oDhyjnlGVpYEgXP+S+mthYbHvVPSCPBCPfyNSyj9R/zUcqCjgcJSs1kAp5eKGjNFYD9hdwAwhxADU/ffzQHdUD8e9/NuwOFhZyq+7/aohbNX+iW6kPWvpCjYoJYI48umWtY4yPYqlkb0IxdghRuU1bfa2pbg0DsOwYdOCtEtcT5wnn2CxRiDSga3U4PR5k8lrFo8ISd7qeCk73Km48ZLGdnJR5X6aZiKxsyMplUhdycjb0MihhHgRiUd/h8u0fF51BggGapFlCZiws8Y//zkBRBebarkUT6WPV0eFHkNUiqJWWGcGsAVIA1ZLUr7ajhZnkLc0Bf/kCMgTvPM6jDhCOcq0sA5adi6ccql6/tMXMGUt/LgQWqXANcfBif2UoXL/FzBpEYzsDc+eWxlSXLgQgkH1+OUXOOYYuG4UfP6d8lbpOlx4cu3v5U1jYOUG+G1C3SHKgQNdTJ+ewmeflZKYqHPjjdHYbAcupvd9sIzLNhdzeLM/ifYEedh9FJ1Fi/0eV6+acrjfo1lYWFhVkPUjpVyBEpPfJxp1daWUq4UQPVHdxv2AC5WAP05Kmbmvk7D451JENhX/0qIpoZB4QGAiyKL5brdGnFnAIf5FDAwtYPimmfyvzY3Mi+mPKTS80kO22Zwsb3PcupfhXX7GpZeTqu3EI8sJoZMd35mnBt5KumhNC3ZRSiQmGjZC6OF8RhnOJxM2A0drPxuO6KiWA04qXUk9RTzntyziw602pFn97ksYAm1KsFqGpDPLwNgSItTepu5lAqhzDqCC7kV1XBwDVZISKZF5GlpyiPix2WRObgsm5G6Bvs1h2TXgsqlekCE3DOoPRSUwoBu88QKs+BrGfAEnD1DDfjEfXvoVyvywLRd6pcEl4XyzE06A446DXbvgppvUsv69Yc0MWLEWHBI6tK1tsrB+K6zeWKNHZcWpSPVwaDBggJMBA+rSFNx3PmILL3vTGZKaQbSnEE2DseYPvCGuRN9PTeiP74OzHlGFDa/fAo59S1mzsLCwaBBCiG6AIaVcF359LMoYWwU8G269uFcabd5KKbOAhxu7n8XBSTNakiczQCgPWAu2s5OWBAIuknKzyG8ej80IMfyP6XTpsIroUAFbl+vcUvQ89mg7htAo0qLpZFuKsEu6tlqG3eanjdiKjRBCgB0DTUhOfuYXOk3ZxFsTL0PGSwLChV0GyKQ5hqlhGDrbtrXhkLYL2NazssrXjk4r4qvN+9WEfALeTXyZ1RubJrBJgU0I3mkj+eRone++C2Ga0KaNRkaxk9APNrADbST2YYJgebhheGugQIIX9vCtaKhbkD4awYANmwxQLiJUWuaPEBuuUuwUzv2SUnmoZk6qHOKoo2D+AujYoXJZZqGSmQAIGrCzivK+2w2TquxfQWQMNGsJZTvqfi9/flfNoab3Kz8I3f+A4hD8cSj02Ut15f6wjmLiPXm4TN/uOZgiRAhjDwNsuxduXqH0w8Z0gaEJex/7qN6QXct1sbCw2HesJPy98g7wErBOCNES+BbVYvEGlILkvfUNUK8BJoRoUDIZgJRyZkO3tTg46MsINjIfE5N0WtOdlXSTq+n+1EaiMsrZmNYGDUlaVgZrb++Iww1tehr89CCccH4Adwy4NR+rAhdxTK8XSHbswiO86BjV/uUKJJNGn8qUbiN5e9RVbL+qObtOTKC7fzU91q/jy5gzcIQCzG/fF2mr/Ng6sHEyfdCqjBaklIXiOi5vVcaZzZPZWXI5XbSRDI0Gu6ZxxpceJnwvue4J2G6Gk+0LgSDoO+CQFJi3SECchDKgDbAZ5RGT1SatvmZFgqJpCZTF+vF7I+A24FB4sooMRMiE9t+p0OPGkytDZjfdoB5VOf9weO5HKCiDKBeMGrz392jDTjj0DhXqfex46FYAKXF7bidE7RWCG8uhKKSirPOK/joD7Ha6ciNlZJU4aBmrEtUGim44xZ7uqmPnwMZS5WQ8aR6sGwYt3X/NvCwsLPbEkqGol65ARa7X2cA8KeVIIcRQ4D0OhAGGsuhqFupTy2vAerf+bSSQxjG+PsxyzKaNuRVTahTboiiN9+DZ6aXD9q0AhOw6zc1dkAnaFDixDMQEkIZAFEoSo/7g9I8nscg/AOGu+DhVj4VpukHqSVs5z/icjXe1x1dsp1n7YkJC5wrjA8Z2ua2a8eXExmG0YwQ9qo3jIwsZTtqKse8iLf5rDmPk7vWl5XD146JSCDUSFWaU4BCCDV+iKh9tAvqZympqBuSjAu8CFapsC2yVsB2MHXaMUruqqDwDbIOqC61KwGfsKT32+wzYvBWOGgSdVESVxGjY+BxszYXWzcAVzoH/4Qf1OO88GDKkcoz3f4OicuXdChnw2Uy49dT639sKBkTD/e0gyw8X7386Vp3E4eBj2yB+ii4hI+RnsN1GFy12j+2khA2llWl3NgEbyiwDzMLC4h+FTmXG8HDgx/DzTVSK1O+VhhhgiVWeHwaMRcnszwkvG4gqx7yrIQe0OPjo4DyVVuWjMTQ/QpoQAO1YARkCo1h5kIpOjyIhswBeBL04bJ0HACTBOBvDRv3G4nn9iW+WTdTgIkxNoFHVihdkieZomLjal7ErMplXXddw69JnaeUrYMes5iSP705+ZBCJpC0JjKQ3XWmOqBEajKAVDuLCDitJC6prEvj8Ne4adHBFgisWip+FfA/q0z0O+FPCFQK2SfWVMoWyDGxAqYRcUSnOsgyIkfCVINQJrl0BwzpAqzilB7v9NHU8W9j7dd8j8PIblXP59Rs44nD13GmHzlXaWS5aBOeeC+Xl8OGHsGIFtAtHYdskgdsB5X5lvNz/GgzuDP26VD9nIWB7AbRJUA3VKxBCGWBNxQn2KJRWYe0IAcckwqw8VTNhF9A3ps7NLSws/gIsD1i9rASuE0L8gDLAKjxeqaheKfVSrwEmpdyt9CqEeAy4RUo5pcomm4UQ2cCzwOQGTtziICIUfBS0IHq4mWOJIwJ/Zye2RwySVheRsx1iEwoJzQYtBASgalTp27STWeQcQDDoICsrjbl/DMbsp9HevQmX8GOiEcBOPpGApGu75eT0b8bUAcPYMCGPce4JRGT5uGZVIrYhw+qdr4aDw3mXXObgIolYelVbnxAHF42Ez35RBuCRg6HwVNi5DvJ+Qnm6OqEMq+46FEtoL2A74JNqJxP4XagkfInqBnYZkCRgKnjCxues3yWnnyDweASOKr9lhgHPvUw1za0xT8Gv39Z+Tps3V+ZuaRpkZFQaYJcfA5Pnwffz1LzKS+DWF2HWG2r9LS/BuEnhaswUGNQHZtwD/gDYbfsu2vpX8u2h8OY2KAjAFa0h1kqqt7Bocv6tEhIHiLuBb4DRwAfhikhQWcANarzW2CT8big5yprsALrUstziX4CU6YQb4QAQ0FVX5ZBLx4wWJHWRLP0atn0Ox7uAIlgUgAWZkBwBd1/wAkFZqSWVtTONyVlnMvzoHwkl6phCpx0qXieQpETu4uPXzuUU7Tu23N2JX7MPw3tFEqOK4mmoI8RGBCkcU+f6tx+CG89VHqPXgvBLBkrbKw9lXC0BTg6ftinAa0IroZKS5pvg0ZTiS0WcbBUqPGmTaN0F5xgmnz1rcO2r8HxHWLTIRnq6YPp0aN0ajjxyz3wsfS+/dSeeCJ06wdKlcOihMHBg9f1GHQ1Tp7M7WSDcoIDF6+DtyZXK+2YmzPLAI6/CE29CdCTMmAA9OtZ/TZsSlw63NKFXzsLCwqIxSClnCiESgWgpZZVSKd5ESXTXS2MNsFXAw0KIy6SUqi5MCDfwUHidxb8QTRuCYc6k4jMVESij3O7BUxhANyShAHTpCcueg8JEKMyAaT4ISSjxw/aoPXvQSClIKM2jNMlDKVGAREiTWFGAm3Ji9ELc+Gjv2Mqs1BO5MjSe72J/5mL67Pf5eP2wZDMM6qpeP+WHNCc8UkilQRX25NERyJJohxiwzIapCeioK8+XLbyNhlLCi5MQAHMyfLhKIHOULMKSJRoREUrBHtR+kTEQDPeStNuVbMLjD9Y9Z49HaYD5fKoSsiYnHwGxFdapDlkF6jx9AZXCVpWnz4D77lVeuIJiGPMafPG/xl7Ffx6mhJU5EGGH9rUUIVhYWDQcSwesfsJSEwU1lm1t6P6NDT5cBwwFdgghpgshpqM8YsPC6yz+hej2O9D0EwEnGOAsDZC8upCY7HKQkLUIPrhQNV5+bwMUhkCEE5sMCck5G/YcVAiMWEGimU0sBegYpJFOc5lFHIW4pQ8dkwhRTgexidvsL1FobmCp3L7f5/P2FBh6P6wPSzYkOuH29kAKlWUkNiABVVD8DQxqqfPRaRC5HfR1qKrJEUBLVDJ+e1Qro1cF/CwxtoMZtEGSDTwaXg3QDRWjFSalZVJ5q0JgBiE+GjrU4/ERonbjCyC7EHKLK19n5cOUBdCrPcTEg4gA3Q3PXQujR0JUhDpHuxO2lMDIl+Cd3+GoW6D7ZTBxeqMuaZPxax70WwBDFsOassrlQQMGTYDDJkD3t+G8T2Fb1t83TwuLg52KHLAD8fg3IoT4bm+PhozRWCHWBUKItsBFqJCjAD4GPpFSlu11Z4uDFiFs2J0TkTITlnaF8qJqae/xieCMAH+JsimmG+DWVHhPaHDnrke5K2kChrCRumEe7Vf+wkW3rWKU8TW2PIOQBrONsdj8c9nobI9dGuiiSv9BAVGU8qZ+HUmBG+ns+BJ3LdIFDeWiIZAaDx2rVPxF2eD2i+CFSagcsFbAbNQJbRDEfCJYlArmDjD8KEOtL8oDVoDKF/tIKMOsYtIaEJCqZ4REZd8Xh5S1oAs4SYd4gVEEOxfCq2/C/ftYyuKo8U2WgNsJ934AeV6QAhxukHYIhiAhDUozIShhaQEYK+DnyYCh3rfLnoFuraFHHaKufwfbfXD6CihXqYgMWQxZYYHaEyfCvJ1S6bZFwOc74asLYeLDgtNrCOkUl8Gr30JuEVw4HPp1auozsbCw+BeQV+O1HeiN6o/ydUMG2Bch1nJgfGP3szj4EaI5RJ0D5e9RNSfMEwcXfghPHw/SAJ8Jh54JsyeBaUDmBwvpftkkStp24sLHh2AL+LjiRWWfmAi2RrTCq7vo7lhDamgHk8wzaOHYgR52o2mYlONBYPJY3gOsXnst9w17AWeDM8KqExcJZwzac/nzA+DyzjB5E7ADjjwBHnHA7wth8jvwSwxobQE7CAPkRuDGsKBGAfAnVKuvdIYfhlAGm5AQ1JQFEZLKOJMC4sA4Fsa8DXfdpkKSDUFKePND+G0WXHUhPHQpCK+SrTimHwzvBw99qsKQAN4ALNwAC9bAroJKsVcjB2gBskpBgKbD82vg+uYwwNXwa/tXsqFcSVKAusr5ISg1YGMuzEyXcDiq/kgDukJoAYx6DE6vUjIUCMLAW2DTTiUT8uZkmDYWDrUyWC0s9uDf6r06EEgpL6ttuRDieaCkIWM0KgQphDhjb4/GjGVxkJL2AOiR1FSFt0d4OOnJoWh2Ozg15k2tTARP2LGBMx4/h0de6YPD8IGE0mxlQGyLaEGBMwYQhDQbkbYyFuQPwIebIDYMNJbQl1KiEECPuFVs7NibVUzYr9MIBCAnZ8/l3aPhrr7gkjDqZZg2C4wdQBGE0iGlWLUVkkFUo+7XQEyGcR2hfWeAGl2gtbAnTKBiiM4KC0Io3eTxEl4HpkmCPSSPvQ7bMmDrVpPFi/0UFtbdzeLbn2H0o/DlZDj9Cjj/aBVyXPsRfP2Eqm489yjwhLsKeZxw1pHQIkHphRGeEkmo9L40dt+SlZnwSTMYsh3WB/Y89t/BIVFKkkJDXcbekcpzWRoAm43K+Wvhv8dBeQ2//LLNkJ5dqdFW7ofxVu22hcUeWM2495k3gesbsmFjPWBf1rG84rb/P3el/3M4W0Hv+bDpBiieoawsLQJS76bvnXcgL5nIH9+8hJQGkXlFZD66HtNUnrAtSyuH+eA0uHo6FMdHIkXlfYBA8lTS3YwOjsVpC+DXXPhxISX4Ct189eIFPDr0fna0yOeQ/fi0Pf44TJkCc+bUvn70uxDcwh61LKFd0C4ZVmehEu/zQNsOFzwDh74LRx5vw58VAOyqfZFLVDSrVH/LKtxOkt3qrynR4LPBZsljy+CxJ3yQnQMI3G6DmTNT6N9/z96MW7arcCIoY2tHptL3ap1Suc0tp0JSDPy5Bkb0g5MPU8vfvQ8efAt2BqA8Ojw3Heis8sUYAYE4CGEwJeijkyOisZf4gBNrh0UD4I0dEGmDm1uq5YelQutoWC2r6EUbQBmMPLL6GFHuyopQALuuPKIWFhYWB4jODd2wsTlg1TxmQggbKhPmOeD+xoxlcRDj7gg9foVQCZhlYE8Eoawhd0oCqdc2J4lthIjFfsVJRJ0zi60riygtAUPXsJ3SioJvt/LZJXDYLz68eqVxIaXgkGWrWJx7JDuczXmq0538njyE8qIIdr7bmlDQwXMz7+WpI+/Cjx8n+9Y0+rrrVGPrurjgaJiwDWQNIy8hGbp0hA3bIJivlkVGKzmH/r1hxyqN1esdrF4GZUG483WBmWtCnqGMAklYDt+nXiQ6oYWu7AY/qgozvxDCzcW9XsGNN+Yxd+6eEvUXnA7/Gw+7cqBfLzi8H8yeXX0bIeCCoepRlfOOhXGLYctmqjvtdJAeGO6HeZqJ213EEZ5/jghXazc81aH6MocO80cJTpppMj0NFdoNCM4pEXz2TPVtu7SCS46BD6cqYzXaA3ee02TTt7A4aLCqIPeOEOLlmouA5sAJwLsNGWO/rq6UMgQsEELchwqk9N6f8SwOMmx7Kpq3JoII/kDDQCJo0zyfxO9W8sNVt7Lu229xu0KcdJXkyx91ts4wME7aQbfP3SoeKSUtNmcRl6vC5y39mbyy4nZ2rU7iaDGTkN8ONknvpKXka81YzmIGMLCWidVP8+bqURfv3wrPXwy9j4Ad21BGih2W58O3d8HmDFi4EprFwPfjK8VMm8XD4MMFg8OK9kcMh09+1vjmY0HGJomOSbDMD8GwZVehESHCjxDqWlQJ8RaXSH6dBX27QWKzyjkmJ8KWeVBQqI5bVVds9kK47mHVc/LNx+CwPmq5PwhbdkGMB+ZsCjviKvZzAjGqVuBwB0ztoAHxZGTBi7+C0wEXnqSMzdpYvAzOvgJ694CJb4fDgk3Eu9Ng/qc67mjJyMGCCWeCp18tjS+BN26Fa06CwlI4tDNEWC2OLCxqxcoB2ys9a7w2gRxUN+C/3gCrQiGqEN/iP46PT9BRCUYCiU6Qgrh1ZHz5JtuNF+m19Bf84+5BCxgYwPapIbYnrqXLyz76R6eTnFdNUgUNSDay+Z92G/dc8Air03vSu8tsNmlppLF6nw2whtCsGayeDzE9UL0fw/+o0zMhNgE0DziiqxtFNZmdAe9tB/sQwSdvCM7trzFwYAlz52pABORINa5TwvYQPQ6zc8ENHu67twQQ6HqQTWVJnHOLsstmfwY9qzi4dR0Sahzf64MTrlA9LwGOuwzyFsCybTDiUWWEBUMgbaiGGaWocGonVU15WEu4PXxZt+6APmco/TFNg7HvwtJJYRmLGrz8FmzeBjuyYPU66NW90Zd8n3l/BpQHgFzB77+C5+y9b9+3w97XW1hYWOwNKeXQ+rfaO41Nwj+kxqOfEOIkVNLZkv2djMXBh49CpnMH33MOK3kPgZuqqYC7SOAEWvIaBfys+/iwdxd+fO0SPHdWaaCtCYh2YvfWnnCuAYPFLPq2WoKzczm5L63HtXgLNv7kO/NEfvEPY8v27rDlAghsPKDnFx0NzVIAFyBV9ePG7TBnGZgm7MqD0c/Xvu8fm+ChyVDig/xyuOxD2JYHU6fG0KJFEPCC6VANvdf5uPg8G0t+hXvviWHjxmQmToylWe9UAnYPRSVQUgYPvVj/nAuLK3PDQBlkuYXK+MorgVIf+EPhKGgZ6vZpO9jWwOyLYOalEB82Nt/4TB3XH1TCrtn58P202o97xYUQFwsD+qgwbVNyWn+IcKrHiCqdp6bNhRaDwN0DzrtVFV9YWFjUj6UD1jCEEC4hRA8hRHchRKNqxhvrAVvI7mYn1ZgLXN7IsSz+BazgLQpYj8RgE9+TyA1oTEKGm8R/yE2Uou8WrRhom0W8nk/o8cOIzCjnPPdmVi2D8pIg+R8VE3sKaLV8KotcMezMTeXosmlErt/O8NRtRBcZGFLHF+thdWoK2q4ZtE7vBam/gfvAecY2ToUL74b8Anj9YVi1uXKdlMoQq4312dW/KA4bbMmD1p00duxIYO7cAMuW+ejd28Zhh7kQVWKI7dvbad/ezs1jUbljmvriSUm9pCTCwL6wMNyZ7KgBUOBTEgxVkQAelI6ZCTFlMKCG7pcpoaqyRjhSXCuDB0J+LZq7dZGbrzoARNfdl7vBPHA6HN4Rynxwcj+1rLAYTrmm0hP43W8w5lV44vb9P56FxX+Bf7vxtD8IIezAk8CNqBiJAPxCiFeA+6WUwb3tD403wGrKMppAjpTS18hxLP4lBClF7g45CkwiSWIufqYhiGQt3QhR6XbYRivcwksiOcx7/D5uff8qNmfYKPEarPsUUoZoRMSb1QwXPzbWbmvPm6edxpLkNLQh5STHpiJCEjRo+0466y7qyPqEdrQumw3ZV0Dr1QfsHGOjYfLrla+7toe3voI/lioF++fq+Id+ZPtK26UixatXauX6ww93cPjhjlr2hM1ZcNdzkLUlAAXZoAncbRMxcxxExUJaGnz9BXSpRb9KCPj1Pfj+dxU2PGko5BRDIFRjQwlUcTqmJu051jXnwJsTodyncsOaxcLJ++14h9uegNc+VnN98zEYtZ8iNkLAsTUyMrZmVG807vXB3KX7dxwLCwuLMM8A5wPXomS7AQYDT6ECN6PrG6CxBlhr4M9w8v1uwtWQg6SUMxs5nsVBTjcuIZdVmISIpg3JHIKGHQ9nAdCfHNYQIAQITFbTgzV0AyHwpTmIaluIlljOW75PWFUGq++3c8ZRAVoOlOjNoMgZQf7iWBL/N4eCEpN2uVvxfdwV6dSQ4QLIgpNi6PrsetbdH07sCW2GUBbYUmqfdCPZVaAS1/t1gK+nws4c+PJ5yC6Daz+FIS9Dr47w3EnQq1Xlfh2T4Otr4YEfINEDY0+H+AaoOSzbAgPvBG+ZCWKHqjYF/JsEU3c2x+sVrF0Hp54B6+qwM+12OGOEer5+A/w8BU7rDT+shDK/ivq6HEC5UhExHXDPtXuO074VLJ8En/+sEvqdkfDNLLjgWJVkLyVM3ACJbhi2Z8vPWknfCW98WumRu+GR/TfAaqNtWnVvndsFg/sf+ONYWPwbqdABs6iTC4DLpZQ/Vlm2SQiRA7zNX2CATUOVWWbXWB4TXme9W/8xYmnPSD4iQDFuEhDhtMIX82BMDvSJjCM6tYRSfJi73Vqa8gz5watH44h2EBtn48bnBJ7mJs4UCQJEIcR+W8bGrwPYCoOVCYuB6jEwI1InfWQqu8xEcvRmJBolu2Ux9pfNWdD3FqUdlRoDO1YoEdOn34ZsO7AFiICsX2DqfJh2DxwV9kp5Q3DlUihMgu02SN1Lsn5VPpupVOsJBCG3dPdy0zTxetVFlBLSt8O3P8KPUyA+Di49f8+xQiE49CjVCLxFc3jqefhlidIGu+9MiPdAjyugqByufBFSU+CoGrXMrVPhrivgtLtVf0mA3xbCBw/Csly48BflTCu9DtwN+EWx6dUNo7+qWjImCn56By66A/IK4cwRcL/VsdbCokFYMhT1EgNsqmX5JiC2IQM0thm3oFpGyG6aodJ5Lf6D2HDhIWm38RWQMHoXFJqwoMTGDcXJ3O59hQ7Gpt2fHiElvRzLie6aS3SgGKfNID5eIiPUXZcA0EFzQLt7j0Wr0oXaMToDUWYgfCZSQokzko8iR3Hf9BfouGEDJ+R9TU5hcfX/8qEdsGMAZJ0KsuGZ2H+uUcZXmR82ZEOZF/wByC4A1qJUOGyAA8ylcOdnlftuLoE8P5QGJIV/mDz2gkFOzt6TuFauLOfXrzPRMcFpU26nMJrw4XKp/V1uiEiEsy6F8R/A2Feh79GQl199PNNUieeBAJSXw00j4Yf74d0boUNzlZBfUKpCjL4gzFxe99xmLlXblfuUAXZfDlxWBD2T4Mz24GqgzdsiGR65WRleHhd8OLZh++0LR/SDLdOheCm890zD2zxZWFhgJeHvnWXAzbUsvwVY2pABGmTeVunsLYGPhBD+Kqt1oAfhTngWFnagmQ65hvrA9LA5Gej7gJHuSXwrTmEBh3Kc+JU2YivLuvchf14yWyLb8sl5pyEcEg1JsncXbWdsY8OTHZDOYsqGHErCg2vwTMkjsjCWFuevZdlX3THQuX3OONYVdiUk1X/XX/0j6JBfSob9PKKGf6rU+ss+h8BSECvBvxBctTSDrIXj+kJMhKoaPLoTzMkCUwdfHtX9vQIwYHke3LYYnukNnWKgexwsesbAv0DyqgafvmKybp2NyMg9NapCIclRR62moMBA62wQ0S6RsrapsH47AM7m8fwwQTDxC9ieDT9NC9uY0iQUFIRCgm0ZyghrFq/GdDhgyg8w8Su4YtSe59cyEXq2hTXp6vWpR1Rf/9E0+OIPZaydPQw+/hWQcPFIeCqsGHLtEHg9uUGXczf3XAOjr1A5WlpjbwMtLCws/n7uAn4UQhwLzEH9uxsItECJsdZLQ/2LFV2/BapmyltlXQCVgPZWA8ey+JcjBMxrCxMK4VAPDIqwIW2fEDJu5lTbD5zKDwBMlcPw604izizAs6qU9Y5OICCOfHBL8o6Pxy5CaNLE1g+yf+zHpyXnIJY5eGb9nRjCxsKcQ9lQ1Gm38QVgShs+w80roY7clzUTmg8Bz2lQ/AboKeDo2+BzSYqFrW9DcTk0i4aFq5T358GXIChRn/6KPPpU8KXAm5vBqcONzQJsvWIrMtcHOPHThtxcG+PHS047TdCundrt+++DvP56gOHDNUpKVFa8uW4HScFcMvQ+BNvGAuATUGbAG69Bi64gMUHzqz5PxV5weECqkOTF56qxA0GYtha222HaaujRvbrBo2kw+2VYuA7atYCU+Mp1706Bm8arfolOO/RtCz89r0KIA3tCwS6YWg5X7ltP9CYVarWwsGgcFTIUFrUjpZwphOgE3AB0QdlHXwCvSSl3NmSMBv0EVnT9FkJsBcZKKa1wo8VeaeOAh6pU1QnnaSxctpk+vV4hJGzkyGY8JB/DFILjE35FErFbyr1QxtFnw0p6pK8hs1UiWzu2AiFwEmB4xDTu7PMM29t8yFPafSzJ7UfA3FN6JWA6mRx5PPdVCGDY20Ha+n06F5uuvGAA/btD787w2QxYvgPMIKrvfSuUH7g9eA1YmA8nXrKN3NyKAmE/sJVAoBMPPwwPPggTJ0Lv3ibnnOPF54MZMwyOPjqFOXOyMU3Jww+l8tVs+O1PKA/f8px3M9w3RnnkiAFCArKylBHmLUOakoULfVx8rov5K+HqJ5V3K2DAz/Ng7Xa4/2aI0SEq/NvqsMOgKrJsFbz/mzK+QOmALdqkig0qrsUbjfR6/V2YpvpoiT2djhYWFnVgJeHXT9jQ2uc2jI1y/kspx1jGl8U+YQYwNi/j3Clf8EjwIR40HkMiaEYBEZRXk52QCIKGnfjCIjqt2kLKZlXzETJ1dqa3pHR8EouX9ycvM54YRyF2zb/H4TQMkp3FkHJU7fPx50PpNpB1iHiF2bwLWt0Ezkvg8jdVyM9ug1mvwujT4Lh+cMtVMOMV8PRUUg0eHS5uAxs31pyXel1aKigvh4cfhrIyudswEAKuv745c+Z0Z82a3owalcikN+DOq1SulJQq/+rhryDfZar7rawdEAyGz8MH0uTNV7N4/gOTI6+AZRsg4AckeA+FNwZCq1UQuxLafAdtD4dr7wDDgFWFMH49lISrE1slKuOzApsOEY2SGfz7eeZ5cMZCUitYtHjfx1mcCaWWiKuFhUUVhBAeIcQgIcRpQogzqj4asn+9HjAhxHLgaCllgRBiBbUn4QMgpexV1zqL/zjCxqltZnDN56+xbk13+p4yD62VSaRRis/mqvahshtBWuZnhp8bODNClKV5SC9qzSuL7gC3RmBJFPeveo5rr30Jbd2eH0mHHuCObj1V/heQwfds5ys0nHRa7yBu7nhVKRndAY6fDs74PcYAuO9z2FEQlluYC9cMh8M6QKQHnqlRUTdzGEzZBYfEwXEp8PYhLmbPLq+yhQtdFxiGCv0lJkLnzjq33upg/PgAxxxj45RT7Nhsldpgug7XXggvvgduCX4JRlcgV6gKTKOGuJc0CAaCPPxKiCCO6n0ez1R/K7RVt7UAjof334FhQ+CKEgiZMD0LPjkKxl4Oc9ZBVvj8P7q9ukFWVqZyzP6pie35+fDQY6oSNDcPrr8F5s1q/DhZpXD4O3DXIHh82IGfp4XFPxWrCrJuhBDHAJ+iihBrImmAKkRDru5XVNy6q+cN0OK2sKiB0Ijq9hsfnvgTF/10GoW/JnDWlV9w+Lb5/NL6WELYMdAQUtJv0xI6ZaqWQmXCzaelF/LkxAcq/bXRQIFgW6gtC0v6c1T/KUxfNAJQCfzShBu6bWRLdk/eWgwlSVtZ0roDhfqTtNa3cWWb8YxapRNZ5IWidTD/Nhj8Qa3TdjlUIWLIUEaIcy/fmH7x6lHBl1+25qyztrFwoY+4OCcPPdSaqVPhu+8gIQG6d5c88USAzMwg48c7OOOM2t1LKYmwdDL8OA0iW8FnAlblC9LT/RATB4Xh0keplFVNM5GyPCChsmlFwsAcvLgoq9o83QGMBP9WyA+ovDVTQnTYoEqJg/Wvw/ZcSIiGyCpNq598AR5+Wmlr/fIlDDy07uvyd6HrVPMuOvfRe5ccAe+fCke1PnBzs7D4p2PlgNXLS8Bk4L6G5nzVpF4DTEo5psrzR/blIBYWADjbc8bg9izuVsa0qFfRtXLK27kZXv47cCYZtKSDXE+ae5sqpQzBpKjTeNa4a8+xBGiaSWZRGq26bePcER+QmZuKYWisjenEuJWtMZZJjHgDz6GRoEcCsNHsyAPmE3Rru56hS/8EMwCFq+qc8tPnweoM2JAFN4+APm0adqpSSrZvN3n33dZ07FjpIrr2WjjrLPjpJ3j++XJUI0bJ++/Deed5+PTT2j1xbVrC9Rer55cABf3ghFgH835ww3IdQuWoGy4H4ITtIYi3Y7MH+ebW0+jSZg1/ZBzB5NBIJjrPVzlrGqoR9ya4Nx8ePgniAnBBFUFVXYc2NXK9pFTGVygEJaXw4JMw9ZuGXZemJCYG3hoHo+9V3sZ3Xq9/n9oQAi7oWf92FhYW/ynaAKfsq/EFjRRiFUL8DpwhpSyssTwa+EZKaTnoLeolrlkmbiRBQOoa/kgXKRRxPp+CkJgeG6KlcrWuC3QgpNshp8oA5UAIAjYncSmqQNemG6Qlp2NKwYpANwKr3JghgbtvKejV25eGsPNa0rUM5U/Q3ZB8dJ1zTYmF+Y83/hwvuyyXL78sxzThjTfiueQS5XkqKFAesGAQVPZ+pUP5s8/LufPOSA45pPb2RFWJi4C5YwSrzvEwYkQKO3dKpLSx+0IZAvL8jLpgAs1ScukzYRkCiSF1YsoKKCqLUx1cMwENCstgdBAiBkGfROjtqfvYQkBSAmTuUiHIDu0af32aiosvUA8LC4vGYXnA6uUPoDO1i7E2iMYq8Ayhsui+Ki5UDyQLi3qJobJFkEAnWiSjYQ8LuUqa52djAn6Hk5vWlXDa5s8BE3IkZEnIArs9QLeey4mJL6TCiDFNyA/GMWXBySSHlCGiR6gmSNURrHV3Bc0OaSdDvycP6PlJKfnoozLKyiRer+Tll0t2r3NU+/bUiOZLwao1ey8KqEphEXw9VefcK9xExARA5AEhIFz2Vy5o3j2LFxbcQWkwgpJgNOWhCIq0WPhOwi7UL4AJLJEYn0CxAaethvHz4LGZMHFV7c23p30H558BN14JTz8Mp1+nihCOOh+KSvbc3sLC4uDDEmKtjhDikIoH8AYwVghxpRDisKrrwuvrpaFCrFUH6yWEqKq3rQMjgB0NPQmL/zYuIjmZ+1nKd9hx058zmc9SOjOaLeIZ1nZsj820E6+dQPseD1PyRzldBiymeEscxgonjlCAvr0W0bnraorLYzCcEqkLHDLErzeeTNd2m3mhw22cn/sZxi4btugAssq9hsCgeUQmZZf4iGj0PUj9CCHo0cPOmjVBbDbBUUdVJh9FRMBjj8GYMWAYEQQCxaivUAJg49qrg/z4QwFvvx1LRIQyHEMhuHw0TPoZOreH796BFikw9FxYuQ5CuRrQDCJAyfOXQ/d4yNf4Lv1UOtg2VG9hsS78osIu1VAes1XACtgaC9csU+sj7DB3B7xwXPVz7NQBPg4r/43/DH6ZrZpdz1sGT70BT9/ZsGv1+JOwciW8PR4iIxtxkS0sLCyanoVU//UEGF/LdgcsCb/qQSXway3rvcBNDRzLwoJmtGI4N1Zb1pyT8dCSfDEDt94aW+AUHtkCf/jd+NepewBHNz8ntpmEVhbif9/cQ8jrAAOiooo5Z8gEAqUunl87mmGeqbzf5QruLhxHIFSOYdMxEQgkHq2cF0rvZG10C/rZ+v0l5zdtWgpvv11KTIzGFVdUtyzuvhtOPRUyMqKYOhVeeMFJMGgDBOXldj77TGPu3Gw2bkxC1wUffAlf/aS0wJauhmvuhUlvwbI1IHOl6qwthHJVCTvEASkaFAuWv9wb+RQ4t/iRIYk/6IDtZageSjU8gwaq3CZd7s5eLwvCm4v2NMCqUlKm2jWBKlZoqAcsGIQHH1aCrJdcDCMbpB1tYWHRFFg6YLXS9kAO1lADrC3q13ozcCjVM3ICQLaU0jiQE7P4bxJDX2LoS4YX+vwB2W6JbCaoMBb8hpspG0+gZGOsWuYAQlBSEs37k68DXWAGbPy26Dicp7cmM82FlM25JfQz8w03LdnBk+WP0MbIQAQXQj0GWFEJREc2XsQzJkZniYjh88kw5k/47XHo0rJyfZcu0KWL4Jhjovn+e1i9umKNAHS2bw+xZo1Bjx42duWq/pOg9Lp2ZCmjxWZKguWAR4STCYS6RUqOB7cAl4R0wYore0N8LkQVQEkAcgKg9wQZPqmKv61RBtjvAZhbosY61INzkJs9w7iVtGkVNsAEuJyqxZCUMPF7WLkeenSCc07e8xra7fDqy+rchw1t3PW1sLD4a7Gace+JlHJbY/cRQkwGrpRSZtZc11Al/IqDWl3bLJqEK1fALlNChNjjU1eSEQdS4i4vxWn6Kc+IIOBzYbTWVReu7SBNwR+/NWfupV4GCg+v2I5GFiUjZGl4FA/Yeu91Dt/NgNNuhwtPgA8bmYj/82L4fr6SdcgsgOtfh9+fqH3bO++Eyy6rmvtVhqaJ3a16zj8Fnn1D5bgZBtx7g1oeLA4BOpQL5eyuGMLUle5XS2CDVOHFnHzIKag8hLEcRBKQqgwtBzAAeMMPayq2E/BjCSWLJUXXR7B2F/yyFA7vBMf1UVvkF8Goh8FwocbxwIrN8OSr8Pn3UFYOER6YOhveenbPc7/huj2XWVhYWPyLOApw17ai0eatEMKG8oK1okZCvpRywr7MzsICQCIxyCXf72Z6fiQ4Re2OlyC0aLONpF6ZSEMgNMmm97pQsjmO3TJXhqB0hYc/KGEgHhAeRMxvUHIlyGLwPAj2w/c6nzKvOnzxPvR+CFbRR5USAqG6t730Uli9OsD//ucjFPLjcBgcc4yLzp2V+99XZvL9eMgu1OjcHnp0ho8/BoqrfH2r+J9dyTCwPcxYJjB7S1gdgkDYRbU7EywUVs8PL7saKAY2FIfXhy+8CWaWl5//iODyD8HrB7cDPr0djmhv8PUPAaRfB6FEX/0BmLMUPp5U6bUrK4cPv4bHRkNKuD1VSYkKQcbXrrphYWHxD+DflED/T6SxMhRdgO+pDEka4TGCqOCFZYBZ7COSbZyCn+XggDEDT+ax15+gzB8FkZrqMR9OpXJEeknuvRPNXlme1+b8Dax49NBKyWAAE2Kr/oDYD4X45Q2e0fnHw4Bu0Kp5489mZH/o3xHmrFFiri9eufftn33WxYgRglmzbLRpo3PxxS6EEDz5ZJAnngghJdx+u0a8W7Je2LnySp1K67QiPVMQGwc/jYNeLaHFW+AvFeAxIeBEFStX9NOJxtM9GntCHr6TnPi3uGC7CaJmyaMEm+D39ZLy7RJyBeWlgqeknwVfbcU0TaQUkJgALRNwOqBvZ6WYX/Wt0PXKfpbbM6BHfwgEYOpkOGJg46/v/pBTCLe8BDvz4IFL4Jj+TXt8C4uDAUuG4q+nsR6wF4FFQB8gK/w3BngdeOAAzsviP0aQLLxyJXahehyO9PzCp5dexMaoDsgSge+zGMyBNnomLuXsLh/xtXkmVWUcdHfYBbS7PlfiSA1yaHEkb6+DODec2BlcjWyb06HVvp2P3Qa/Pw7ZhRAbCc4GHHf4cCfDhzurLRs3LkR5uJvRk08GefXVIoJBHSmTqTDAdB0OPzzIE09oSAlDeqpwpYwFfECsA3xtwFeCElErRzg8SF8+xQtcyEUaHOqBTAlxHsguomoBjx6jMf4un1K4kIDdztzv7GBUXH8JOTl07B/Fk7c7OX0ojGkBm7YpT6DdDq1ToXU4B279BggFlWdw8dKmN8DOehDmrISgAQvWwtoPIe0gaSxuYWHx76GxBtgAVF/IMiGECdiklIuFEHcBrwBWL0iLxiMl3lAxdlEZpwtpNlrE7GCT7ICIlrjOL8I7I5bb+z+Nrhu4Q178phOhgRkUFK+JVer54UbSwik5o4eNw8ba0IXqvRjlgAU3QIvopjktISA5bv/GGDRIY/JkE59PIh2SIk8ymCau0hBO7Pj94HIJ3n7bSVoafPEFdOwIHTpAYAuVxdAmIKKBaJASqZt4y0xI0sHhh1llENTDG8ejLFkDMAnm1NCHCAZBqykHqJO+y8vxRzjQdcHML1W15rLV0Kc7vPGkMhQBhh4Nd92u+jNefknDr0WuFzw28Oxn78lVW5TxBap5+qadlgFmYVETqwryr6exSfUCdQsNqhIyNfw8A+hwoCZl8R8jPxOvdOOvklKoaSZr6br7tYiQaIEgQkrshLjENoG48gJCRTr5yxLY8mdH9IBfRcxskl4tBN/Pd+ILKSmFEj9kl8H9tYmoNDFLlxbTuvU0nM6fueCCpYRCdYuvfvSRgxdftBMRUQ7xblX+aLfjTAzywANw220wZ46qqrzqKtWAeuNG+OUXKh2EBkAQpFflfemoGGGZHUqEihUGq4Y0QemSmWB31d5tO7CrygEEkIB/icExw/IJBiXxsXB4T+jaSv2Nj63cVdPg4fvhlReULlpDeGERtHgTUt6AFTn1b783LjgWIlzgdkKEG/p13r/xLCz+rRjYDsjDonYae2VWAr1RchTzgbuFEAZwFbDxAM/N4r+COxKz0GSycQJH6n/gNTzcv+MJsuOSELqyGWShxuDZY7Gdp4yVWIq4MvJthGGytlU3IruVEDAdvHT/GJp7onn7Ghj8OipQDhAPISfM3Pp3nWQlp5yyiO3bfQB8880uxo/fzvXX197p2ekUXH21jbIyB6OfCWFKHZCMPE7ngRpB/+nToV9YVaO6en05yApxLg3szdhtbAWBsgo5/JoHt0OPZrBFU926d1OkChnQwuNEA26QkqVLSpg+PcDPs5y88b7K+5o2G3blwNgxex6ioby0GIKmekxcDz0T92Osm2FIH9hVAGcNgai9tF2ysLCw2E+epEpyTFUaa4A9QVhvG3gQlZA/DcgFzt3X2Vn8x/FEE5FbQtFvkTw27CHs/iAjX/mW5Vf2RksxkPkad0x7gf5tvia4qx2hFjpSCGwEidDL6ddsIekiDUIaz1+TxTmdoknPBe8GKu2KEqAd9E7ZyzyaiMzMyvR0r9dk06byvWwNn31WygMPFGD6BfFpsZx/nouXHnfusV2vXpVaWxV/lSHmrbKVVA3IqVDnFxBng1w/1T1gAnolQ7QOEQboTvAbUJ4DoaLKsWhJ1Z+RipDoV99XJt2Xe+Gr76sbYBuzoDwAvRqYY3dGBxi/Qh3xuNpt1QYjBJxRd/tPCwsLrCT8hiCESEO1YUyiRkRRSvlC+O9Tde3fKANMSvlLleebgG5CiHigQMraOsZZWDSMyDYdOO6Km7mtQCCCElsKXL/yHYxjXSQ5cjAQfH/pcRSnRKJJk2bkYcNEw0ln/UYCbCTOkcTR3TqgAbPXgEMPqy8ASHD54JFh8PsKsOswqHNlXlJDkEhmkEkuPo4njUj2LRnp1FOT+PHHHLxeE7db48wz67YKN28OcvnleXi9qtKxLDMfozASXU/YY9sJE2DSJBXW69VLqe0/+CBhlf2K/DoJjipfeweQICDfD3lOlBGmQZwX4mNU+LKzTSXcb8iD4qIqR6wqayGp0MLo0sVG+7aQkal0y3Qd2lfRj/5iLox6XRlCo0+EMWfXf81eGAIXdYMEN7Ruohw+C4v/MpYBtneEEBcC76J+XHOo3txXAi/UN0a9BpgQ4rsGTgYp5SkN2dbCoiaa203Hqx/EnP0Y0YDcDo68EpxFJYgkWHZYH4pSYtCQSCHIJpFkSunC9cQwjFMZiV7lBiQxWhlZgXBSvsMGDwyBofdAeRFoOiQkwMzHoXVSw+b4Kxm8zCpMTGaSxcsM2qdz/fTTPowbt43Nm8s599wWDBpUd6b+6tVBHA7whr1Jfj/MmxeoddukJEhNNbj55nWMGJHA0Uc348gj4cEHPcyeJwkGTHB50Bw2pA2k20APeZG+CMzUGISzAGkIiIwBLQZ8ErZlKSVZtxM6pMCOoirxTR0Vw9RQ8hYFgIfzzy/ivfdjGXm+YPVaSZsWQZ5/pCLBHybMAm/4fZkwq2EGmBDQz0qUt7Cw+OfwKPA88OC+dgJqiAcsb18GtrBoLC0efJTCHVfx8Av30jtxNke1SCcyLZrYodfhbdsG+B2o8NFITGy8QpAtTCYWJ//jWGJQobkTDoFT+sOkeeqf98h+8N4UyJ+JKhkB0jvCVa/Drw83bH7bKCWIgQlkUFrv9nVht2vcemvDWop16WInUMXecjphwICaFYiKlStL2LChjKee2syLr+7gm+/7M+UHwbRpymslnBHomp1Qkbp+QmRjGEDQQEuK4JhT4pk1W+D1oe7f1hZCbq7yfvlDsDETIhzgC6INTkZLcWPMykdmFIV3cAMac+cGyM0O8dnr0POQLDaV2enT28cLz8dy222xXHAE/LZKvY8XHLHPl9HCwuIvxqqC3CvJwNv704axXgNMSnnZvg5uYdFY7ksNMHfsaH4N3kKrT5Yz8MJLwG6nPyWkM4cgyjqIxAsMZTsGIUyKCfAnGZxAe0AZXZ/cDtuylWkQHwmxJwE7qMwL2wDT5kJBMcQ1IKx1Km2YRRZ5+LiObn/J+dekQwc748c346qr8ggEJIMGuRg7tnb5+JUrS5A2Oww4Eq8ngpMeh+C8ypJB6S9HhuxgRGISQNMcIOMhG0RRAakXeNC1cG6YC/QiH4ZRxateVI7dUYh5bHeM1BilbHFSCtFtJcUBE+YUwo/5lJUJZsxwcd+TXkgLtzqSJrffuYNbb43h/EGCvq2hzA+HHNDWtv8Ntm4t5NJLvyE62smECacTG+uqfycLi0Zi9YKslx+Bw1BFifuEdXUt/lEUYRAQEpvDTo9LR6GHP6IuojiL18hlI1GkEFXupPCHh/jw9OZg0xEC0tjTiqoIL4YMJRMWqMgzjwNaQigPko5T6u0fPwYd95IUnoybD2n6rtEXXRTJhRdGEAioqsgKflkML36njM07ToPVZUnEON0QqfoxBQ2U+FlZECRoQpCSolFUBKGQjs8erWQo3GDYY3nvUZQS/ggBSWBkx+D8ORe/T6Lr4PEItNSWFCWEr/Ov+ciSMtWqKQG4PAk2+WBdOaNH52CmpinNCVANv6Ojds+9SyoW+8jdd09l1qxt6LrGuHHzuf/+o/7uKVlY/BeZAjwjhOgOrGC3CqVCSvl1fQNYBpjFP4qxtOFjchhIFLE1Pp4OPLSo0Pr95jZif3+dp9b9zKwL76R7u5H0oG5tApsO910NY5YrW4BWqNQlqYyzBauh9/mQPhkSYv+qs9t3hBA4qxQ+/rgQznoavOHw5LRlYJbaePKsGjvGxEKxHWwSu+lmx04VUtAidUQLiSwOwWG6KpScZoTV7nXQNWjuIfacdni/KaK4uJCSEh+sK8RZnEfn+30s/7ADuJqB3YCdZfBcFnRT4VHTBISm8sXCJZkiPhavT+Bxg2HCrEyItEP/BubgWSg6dozHFW7p0Lbtfir9WljUgZWEXy9vhv/eV8u6CgnsvWIZYBb/KJrjYDQNcI94YkCz0T4jg/bbJbRrUe8uD52r8sgvv68yOb8qXj889ha8dOc+TPwvIBCAj7+GwmI4cyS0alm57ukvK40vAF8ZiJqZCF5glwB7JJQoFYkKzJJ8WJcNQ1uBO0K5B1tpsNGEKQaMUp4rT2oE5TKC3YJqEoLFGsvfPBTiHMq4MiU4HFCQA0uygCCIOGXIVdHF8Lhh/Rbo3RVO+AHm7FK73tILntx7X3SLKowZM4SePZOIinJywgmW/rXFX4dlgNWNlLKxQvZ7YBlgFgcnJ90PMSlKqX1Qw/rZCAGnHQaX1iU8L+C3BQduivuDacIx58Ki5cpD98jzsHQKtA2HSI2a52DUFF+loj+3ynkLUV3mi2z1J7MUEsJKpHnhQcvVAeIjNd48B057CdRPhZKyMLt0ghxHpXGlCdVxnAJ2N/uWhVCUDYnJu7czTEHzJNhaArMzwRs2CF9cZhlgjUHXNc49t8ffPQ0LC4v9xDLALA5ObHYYem2jd3Paw2lJtdWtyH9OT8DN25TxVSFmahrw2bdw703q9W2nwtItUB7WdNX0cNivKh5UblZu+HWFQQbsbpy5Nh8yIyFgB29Y10sI+HAD/p6d6XwHnH02fP55J3z+reA2IdEDxey2tdQEgPjukL8LSAdMKC6E2ESwayBg3COC5AQo8ldxjAEplhK9hcU/DisEWT9hHdTjUUkt1crTpZSP1rf/frvQLCwOJmw2OGMI2Gu59XA5QbrBORCiD4XPfmjy6e0mwqNETCuw2yGqSt/Edu4QCRk+bCUGzbQQ151oEumuZaAWQC8gCpVgr/RcgVagxwEeKNqF0p4wAD/IVZCUhK7BU2NVg2+fz4WwdQFHRyhD9et2oH5BNKCrgEgNJQgNyrRyQfo22LEWtq/DKCgEIMYJk46HbnFwaBJMPrH2a/D9OnhzkVLAsLCwaFokSobiQDz+jQghDgc2AGOBx4DLgfuB0UDNbNxasTxgFv85Xr4T5q2C7AIo8ypvjMcFqS3hlymAqaolz39EyVccN6Tp59g8Ge6+EZ4dpwoIOrSFy89T67ZsMRkwwI9pCiBAHpKPZpYSPazuIgRXP4lc7MVfbAPs4NLp3C2aU4ab9OihM2FCMWXlmczf5MCMbA8RUQQNKMyG8nCnJBkEfH6YlQOHNFcVlq2FMu5KgZ2grDMbyvUm1EKfio1efXURXbr0YvBgN8e1gqd3wZoMsPn2nO+UTXDe1yqsujIbXjnhgFxWCwsLiwPFc8DHwC2omMAw1A/gp8A7DRnAMsAs/nMkxsGqz+GzX+H7WRDSIakTvDsF5QSq8LiE4H/j/3oDzB+A3xfDwO6qMfTsuRAXC2NGK6OrqBi6dVLeO4BnnvGGw40V8URBcaGT89OKcNghyg0l4dCl0MGhSVqmbyXLDGA4JN2Ob8PlZzs471gXycnKCX7BBW6Wrk9m1iJ4+DVVBDn2DuiSDN98pSQtDFOC4VWNvRfZgFRYKcFpwjE2OMaEDU5I7w7OIJSupjLuqdocPfxwPr//nsq4H+HuDyEQgse/hNUvQcsq3ZWKwqHVoAmFtRhoFhYWfzWWDlg99AKukFJKIYQBOKWUm4UQdwOfoIyzvWJdXYuDGiklZO+ChEREHY0dDRPu/FO1Oxx3FETYwe2Cy06B+I5w/hcQ2AbSRfVuXm5o1gQ5YXe+Dm9+C33bmCz9LoTfZ2Kzmzz/jIebr95z+/T0IFTrQymR0mT5fB/nngof3w9fzIB522F9EJ4/O8Qdp/jx+5WeV0ROPndf6eJu4PbbXTz5pId7X4EXPoabzoXiOZUj78wFbQAY2SDsAeTKikSzWHZnMPglJEtIE+hJOqf1s/HVAi+U6iiLNp4KY/GPP31s2moy8U+NsrCR5QbmrIezqxhgZ3SFDfmwvQgebXrpNQuL/zxWDli9VM2C3QW0Btag4gH1l+Vj5YBZHOQEb7oGX+c0/IP7I43aMuvhjyx4fRV8vhEmbqy+7rJJ4A2pbju0pPJr4wIxCMaN+Stnr0iJh1AIFkwGP3ZwOQlpLsY8XlLr9iedpKFpIVR5owlIbLZSDjlE5YCePAgm3AurXoV1T8M1w2ykpdmIjBQ4HIJFizT8ftVX8oUXfOzaZdIiEcyQZNKbeTiduaSl5ZCREeSPlaBHq+siE53hWzYdKEEZVxJ0AX9IeLEQ+UU6k37aAQU6KjbpZneDbzQCAUmfY0s5pBXYwg48XwD6toUZMwzS0rwMHOijIF9y75Hw2omVRZo12ZUHP/2hPIgWFhYWTcxiYED4+XTgcSHEKOBlYHlDBrAMMIuDGuO7ryEUQq5eCXm1ty3tEa8q7Tw2OLJ55XKzZnhLAIeB53w47z4oeQZiGtCiaH+59yL49C6QJiohLVwi6C2rPft81KhIWrUqwW4vAoqx2XKJipLcdVdMte1sGnRqBjabYOHCtrz7bgu++qoVul69l6Rpwm0XQQ8jm/RNEAhoZGRopKXlkhQVqlYM4OgbAUQAXhDZ0DmgNMP6lkHxCkxvOmbJJijdCGIXdEijmh6hlJSml/Pu8z7kdgm7QGyAb7+Hm24KkpEBixdL3ntv75n3oRD0PAfOuhMuur9h19nCwqJxGOgH5PEv5X7Cma/AA0AO8Aqqz0otsYs9sQwwi4Ma25inICER/dKrEEm1S6rHu2DLxZB3BXSMrVyuadCuRltFpw5nd4dPz4KIRrTY+/pHOOxEOP86yC9o3DkIAb27VEozVNCnDqmnkhJ4+eVEbr3VzdChgptuimL58hZsybaxZB1cWUvxc0yMztlnR3P88W4uuMCB2w0uF1x7rZPmzdXPwKpVUDWvDOy8/lwmd5wLRIIWCZ8+H8m99zqx2crQUkrRj7dDDIh1WWELEsCEUKmK6W7Xw78ykt2CZIECitdvw1i6DbYa+PPhtQnQq5eGx6Ny3bp23ftPU8iA4lIlnrt9V/3X2MLConFIhFUFuReklAullNPCz3OklCdIKaOllP2llCsaMkaT5YAJIVzATFQ2rg34Ukr5cHjdTcCNqPTnyVLKu5pqXhYHN/bLrsJ+2VX7vP+k82HouxAylSp761h4sZEVd2s3wMU3Kc2uJSuVcv1P9aZfVqdzB7jjOslzrympiFh3GV98ErXHdrNmBTnhhBJsNuUF+u67ZgwbpvLBJk5XNtBv8+s+jhCCt96K4J573MoAbVf54+jxBCgrs6GMLwkECYUkfTuD26Fy6SYtgKT2zcnMScbjgHt+1vh8KbTuYGPhUqFy8gCVoxYHIqjkL/YQXjMh6AW9FBwxREbAu+/aGTlSo0ULwZAhOj+sgqU7oWMCnNOnuoHqcsJPr8Lk2XDjuY271hYWFv8shBBpwAQgBXWnNl5K+VJYZ+tzoA2wFThHSlkQ3ude4ArUj8vNUspfwsv7Ae+j8h9+BG4JJ8o7w8foB+QB50opt4b3GYXyYgE8LqX84C8+ZaBpk/D9wDApZakQwg7MFkL8hLpIpwK9pJR+IYTVGc6iyeiZDJtug0U7wWWDAalgb+QN24YtUJH/HwzCqnX7Npdnx+g8eq+k3CuJj9vT+AK48cYyysoqX598cgGFhYnY7YIbzoFvvpOc2j2bsWMlV1zRjLi4yq+4lxCLyeUQkUCHDnt+9X/4IYahQ0tQAl9BoIgnn2xH+/Yw9nL4ZAZ8Pls5tPxBjVevhadGGLx4mkZRUUuaf5eN3x9AGW+J6q8/tPeOaJEucMKVF4PDIbjgAjWvu76H1/4AbxDcdvh+FXx4YXUjbOgA9bCwsDjwyKatggwBd0gpFwshooBFQogpwKXAb1LKp4UQ9wD3AHcLIboB5wHdUZm7U4UQnaSUBvA6KgQ4F2WAHQ/8hDLWCqSUHYQQ5wHPAOeGjbyHgf6oH69FQojvKgy9qgghlgNHSykLhBArqF62VQ0pZa/6TrrJQpBSURp+aQ8/JHAd8LSU0h/eLrup5mRhARDjgmHtYFCrxhtfAEceqqoqPW4loHrlBfs+F5dLEB9X99dy27bqGefl5SYPPqj6NO7KCpCZ4WPcCxncf/9O+vRZQ2lppefpTdbwCIsYx6paxx4yJJpduxK5444gt9wi2L69PZ06OdF1uH6k0kQzDOUtLCqTnH76JmJiltGixQry8gweemgATmdvVF5qrBpUloNZuzEJgN2G2wXt21QuKvbBizOhLKC8kmUB+HoFbMqtcxSLJmbKlCw8ni9p1+4Hdu2ydEL+rTRVDpiUMlNKuTj8vARVTZiKcs5UeKM+AE4LPz8V+ExK6ZdSbgE2AocKIZoD0VLKOVK54yfU2KdirC+B4UIIAYwApkgp88NG1xSU0VYbX6GcSRVjfLWXR700qQyFEEIHFgEdgHFSynlCiE7AYCHEE4APGC2l/Id05LP4N5JOEBuCFg38+KfnwJiJUFwON58Ig7tVXx8XCyt+h+9+gbRUOO7oAz/nChyOPJR3qYIcvv3WzdNPw6ef5mO3S0IhAElBgcHUqSWcdlosAN2JYyo76EFcneMnJTkYO3bPCuqSEoPsnzbhWBOg3zntOL2ryahHSjAMyM4OMWZMJhMmtMXjieabbyR5eeVs2eKlrMwDpj0853xUtEC5seKSojn0SI3De8IJR1QeqzygCiur9ku3aVDix+Ifwv/+tx6v12DXLh8//5zJqFFt/+4pWfyzSRBCLKzyeryUcnxtGwoh2gB9gXlAspQyE5SRViVClorycFWQEV4WDD+vubxin+3hsUJCiCKgWdXltexTDSnlmNqe7ytC7tHB969HCBELTAJuAj4DfkepyQ5AxXvbyRoTE0JcTbiyIDk5ud9nn33WlFOuk9LSUiIjI//uaRz0NNV1LMRkOyEE0BY7EYi9bm+YsDJdeX2Qqu9051TwOP/yqdbK5s0+CgpMlPNaTSomxkGHDnays0NIWU5GhjIsNU3Qvr2D6Oj9T4LNzzfYti2AaUpiY3WaN7ezbp0f05QIIUhI0GnVyrHHfhkZkl27KsRY5e6Hza7RvZu2W1y2Jqt3gS9Y6d936NCjOfW8WwcW67tdN4WFQTZvLkXXBd26RWO31+21ta7jgWHo0KGLpJT9m+p49v69ZPzCA9OPLVu0btDchRCRwAzgCSnl10KIQillbJX1BVLKOCHEOGCOlPKj8PJ3UOHGdOApKeUx4eWDgbuklCcLIVYBI6SUGeF1m4BDUS2EnFLKx8PLHwTKpZTPH5CT3wt/ixCrlLJQCDEd5ebLAL4OG1zzhRAmqo9JTo19xgPjAfr37y+HDBnSpHOui+nTp/NPmcvBTFNdx+vI5lvKEMBNxHAP8XvdfuoyeOgdKK5QlgfuOxMev3D/5pFBFtvYyQB64qgmqrp3+vYNMXToGpYsKUXTbERFNWPRojTat7eTmRniyy+nMmZMClLCIYd4+O23jths+2+2bNzoY9SotQSDknHj0hg5MoHFizN5/vlsiooMpLTRsaOH6dPb0KJF5c9K//4+Fi2qeZMXYutWD61b120Y9iiFKyfCogzokgTvngtpdTvu/hKs7/beKSsL4XBoezW+wLqOBysSgWE2XQVjODf8K+BjKeXX4cW7hBDNw96v5kBFilIGkFZl95YoSYiM8POay6vukyGEsAExKLd8BjCkxj7T65jjFvaS91UVKWW7+rZpyirIRCAYNr7cwDGoJLhSVA+l6eFwpAOwsj0s/hKuJYZZeHEiOJe95CaFSY5VbXgqcDmg+d5ttnoxkbzMR5hI8iniZBou9R4TY2Px4p5s3Rpk+3aDXr0cxMSof4CXXOLn+OMd3HtvW/r3FwwbFoWu77/xNWdOEXPmFPPVV63o2jWStDTl6YqOjqWwsBTVBi3Ihg1F9Ou3jszM7rv3TUwUCCGp9GdLYmNDPP2+TkkZPHIDdGgNl14KM2bAzJmQlgYJkfDN5fs9dYu/kIgIq5GKxYEhnIv1DrBGSvlClVXfAaOAp8N/v62y/BMhxAuoJPyOwHwppSGEKAk3yp4HXILS5qo61hxUs+zfw9WRvwBPCiEqbvGOA+6tY6qvVnkeCdwOzA+PCTAQ5VVrkPesKb9BzYEPwnlgGjBRSvmDEMIBvCuEWImS9h9VM/xoYXGg6I2TlbRu8PY9W8OtJ8EL3yndsEM7wJXH7N8cBBBHNHkUkliPB64uSkrspKXZiamivTpggI7dDqecEknHjgfmzvXHH/M4++xVhEISm00wcWJ30tKasWOHyZ13qkpJdUbK0MvK8rNunY/OnV388osPu92L2+0iFALDkDgc0HFINO98pbS8fpsLO2fAr79CVhZs3KgMMAsLi78ZCaFQk3nAjgAuBlYIIZaGl92HMrwmCiGuQIUXzwaQUq4SQkwEVqMqKG8IV0CCKux7H6Ww8FP4AcrA+1AIsRHl+TovPFa+EOIxoCL3/FEpZX5tk6walhRCvA88I6V8suo2YXmM7jSAJjPApJTLUYl1NZcHgIuaah4WFo3lyYuUEVYegNaJewqmNhaBYDSXU0oZccTUv0MtTJoEiYlw3XVV5vmki+nTtQNmfAG8/XYm5eVKYDUQkLz99k5OPLEZO3YoYyoQgJqZWVu2BIiJsXPqqTn4/QF0XXLZZQn07h3JWWfp9DxDEAwL3ecUgNcHs2fDpk1QM1K1cRM8+xJ06gC33VAp92FhYfHXIqXACDWNiSClnE3dKZ7D69jnCeCJWpYvBPaQsZZS+ggbcLWsexd4t6HzDXMGcEgty7+gbg9aNSwfsoVFA0iKVX9DJiwLq8P0jlXVefuCHds+G18ADz20z7s2iu7dPfz0k4bPZ+JyaXTrFhFerhEZKSgt9QBeKpPsdUaPhm+/NQkEigEDw4CPP95O377NSUlJ4PrzYex7yqM4/HAl39GunXrUZOhJsGOnUu33uOH6fdfctbCwsDiQlKFyx2p0GGYIUN6QASwDzMKigZSF4OipsK5Yve4UBTOPhZqpMH4/3PIIzJgLJwyBZ++nzmq/fzr339+a9HQ/v/9eyNFHx/Dggyp8GxEhWLAggk6dkvF6M1HZAxrgYdUqneeeK8HuMAmEpSO8Xsltt2VyzTXNGHOT4MSjocwLR9VTF5WbC1IqT9v2HXvfdvk6WLASDu8F3Tvu75k3jEBAsmVLiIQEjWbNLPecxb8H5QGzPtN74X/AOCFEfyolMQ5H5Zk90pABDtJ/CxYWTc/Y1bCqEHzhloeri9Syh2voHT8wFiZ8pUJr6TsgORHuvr7Jp3tAcLl0Pviga63rWrbU8Pn8KKl7d3ipAeTw4aQIAjUyOU1TUl5uEhWlc2i9GtGK11+EW++G1q3glutq3yYUgvufgv9NVIauEPDzeBjcH37/E25/AlKT4b1nISmhYcetybyl8MDz4HTA2PugS3tYty7IkCGZlJZKgkHJo4/Gctddsft2AAuLfxoSywDbC1LKZ4UQW1ESWueEF69B5bFPbMgYlgFmYdFA1pdUGl+gnk8tyeQ+ErFX+SotWqGML4ByHyxe2cQTbUJcriBeb82lAQJRSVBYuUTXoVMnJ1FRjftBv/RC9aiLch8MOh2WbwapV1asvvE5HN4bTr5K9ehctQFueAi+eK1RhwdgVw4ccxGUlivjbt5S2P4nnHNONrt2mbsrPMeMKeK449z06fM3icRZWFg0KWFDq0HGVm00WSsiC4uDneEp4NYr3To2PYAnZTmf8HO17S46Hex9gLuBcfDj6XDqElhb0qTTrRUpIT+/Inl+/znpJFftK9x+Im9uiT1CQwjo0cPFzz8feLX04dfCsmyQVTRgdQ06tFJVlsGwnH4oBHmFdY8TCknefNPgiScM8vOru+7Wbq5M/pdSGdc7smDjxhBV67V1HdatCx2YE7Ow+JuRUhAK6gfk8W9FCOESQpwlhLg7LDCPEKJ9uL9kvVgGmIVFA7msHZzQKQNdC6FrIXp2WkKndstZwjrMKtp8v3WG4K2oOpwYKHXCd8XQbSHMqbW4uWnIz4dDBkLzdhCdBB98tP9jXnddJLUVL5lrCrlGSgKlPQgGe7J0aafd+mEHCn8A5q1G/YpVTMEEhx2WboAtO+DaM0EPQrNY+N+DdY91//0Gt99uMmaMyTHHVDeiundUPSlBFQ5ERkBac+jUyQGuZuBOgYgkSvQ0zrvOzfGnSYr/Aca2hcX+ITAN2wF5/BsRQnQA1gJvoKoxK4yu64BnGzLGv/PKWFjsJ0bYoNKrGBdCwBV902nZ53NM5G45ikoVLFhRBp8Usuc3S4AUkpOWSfKG/j33PTfdAavWVHqFrr6+lP+NzUDTJE89lcqIEdENGsfvl1x9dTHffluKlCH2vI8TmJqLxctUvPZAiMHWhsMObVvA5kUmZJjQSoMogdcQfD8DfvwU7OXgEjDiKOhdeyobAPPnQ3m4bmnNmurrEuJh1ucw5iVwOuHJ0eAPwrbyFLCjij8jpPqAGCa//BYgsYvGzv+zd9bhVVxbH373zByLuwIJwd2luBVKoQIV6tS9t+5y269ut+69db11oy2FAqWU4u5OIO5yfGZ/f8wJSSBoE6Sdl+c85MzZs2fvOcnMb9Zae60VduL/YtJeCwuLo5ZngamYgquszvZvgbcPpAPLAmZhsRufMJPzeY+eLObV+hWx6Esn7MKGEtIUdjQG0R0RkmAv7GTv2WwUQYkUPOXLb7rB74OVq2rFFzKAv3Ijy5a5WbLEw8SJm1m/3ntA/SQnF/Peew7Ky+OpqIBaCVpHiio2/MqBCbpDRQh48mIDduqgCYgU1HwxUodgEXjcUF0Nn30G5eV77+uOOxRcLlNg3XjjnpfFbh3gy1fh4+egZXN45G0oLQzNV/GbgxHC9H9qdvwBhevuaqKJW1gcDiQQVBvn9fdkAPBUnQSwNWzHzM6/XywLmIVFHbZxJ/15mz4olBHD1bzDcCJphxnrlEAMN3Me3/Eb1XjoShuG0RsDgzVsxp+4mjHRsL6wI1tKWtGQGvvPH0EmDw+QeBA1IBuD4UNh/UbwegHDU5u6CzN+afFiN23b7iWmK8Qnn/gpL4+j9tktHdhSv5FQwBXFqOFNf3n55APDnIOigKxzrgW19coBux1crgY6CDFmjMKOHYLqamjefP8Wu4ISzEIk5YDQao+th06qIZn++4HNYdMmN9dfv45ffy0lPFzlqquace+9LfdbY9HCokmR4u8snhqLhi7iLTCvDPvFEmAWFiEMyrHzBgIzBkhFZxQ/k09H2tVpl0I8lzFh13sdndf4jG3sJDY2QCzQKn4D2RUZfL9qAlLWvYgJvCtdlA3XD7sAe+xBKCyEb6dAdKST4pyQGMMsE9S16z4USojXX9epf9lQgCiggvR0Db9uQ41IYPyJNu68sWlcj3WJiAiNwY+ZAaMmHkyAoy3EV0GYE954wxRh+yIuThC3H5fhtD8hpwCumACfTYfqHDCKMI9fF1UlNXn/4y8pCdCv3wJKSwMYBng8Bk89tY2tWz28994eybyPWWbMMLjzTp2sLMGrr6pERTX974bFX0QCQet72gdTMWtBXhJ6L4UQUcADwA8H0oElwCwsQsjQv/qXnACd9uOpn8NStrKDQEi4SQkzSo5nbVVH0xBdKqFamNaY9ZLotAAZNG5A+oHgdMKH79S8szNtWhbXXZeNrsPjj6fTseP+BdiJJ6rMmLH7Vh2huHjjjUTGjnXg9ZvnwHEYsjHcc4/KRx8Z+HzAZiATcJgGsSfvhevOabxjvfwJ3PaM+XPbDNj8DUz9Dc69RYFCw7T8ScMUgJrCf+7ff59vvZWD261j1Elv4vEYfPZZAU884SMlpWlPotsdoKzMR1ycE6ezaW4HUsL48TpuNyxZIklI0Hn+eevWY3HMcxMwQwixDnACnwKtgQJq84LtE8vGbWERohg3a+hMAA0PDiqIJIIAuaza535/sGSX+ALY4m7Fhup2SENF6oppIApKqJbY5ht8fXws9qPgT2/UqCjWrOnE+vWdmDAh5oD2ueUWO05nFebjsQTKQU1AijROPNnGyDOCRJ8O0WfAi9824eBDZGUJZs8247dEUMIGcG2G319tXPEF8NWvZvb+ag8sWw/hTjjnZBh2t4DxCkQCdgWSFZ5+EkYM3n+fy5ZV4vEYe2x3OBQ2btwjwVqjsXlzGaed9i1xcS/TuvVbxMa+xIUX/kR+fnWjH0vK+ulASksb/RAWTUWwkV5/Q6SUOUB3zILhrwELgduAHlLKwn3suosjfxewsDhK8OFlOQOYwjhmMYyfGYuNID7Mejo6frYykw38SBV5dfbz1evHY4ShGyG3WFCi6QGIkFBhsOZhlW5Rh9/61Zi43ZHccks58fHZIPyAZlp/UPj1BxV/EAJBuOkNdhXdXroSeo/Wic0oZ/i4ckpKGu+q3KePYMUKwb/+Jbj8cvhtFhx3XKN1v4vzxpnuzIgwGNANXKFwuf8bCa4+wPXgvAv63wc3nH2gY48iLGzPy7DPZ9CuXVjjDb4OmzaV0avXh3z99SZ8Ph2PJ4jXq/Phh2vo0eODRhdhigJPP60QFmbW+/y//7Piio4JJJYA2z/RmPFeK0MvO3CREOKAap9YdmALixCJpAKCUmoDgTQELWiFToBfuIMKdpox37zLSB4mjla0JZOFrNyVCyzDtRkMhc5RSzgx+TvCtSrcehi/JI0hK2XAkZlcIyKE4MknY2jXLoLLrtjtZl3HfxvUwX4KKG3AcAeg0gtFNmb+5iC+XZCwNgZhWdAlXmNAO4XbJ0Nk+KGNqVUrePbZQ57SATH5FOjYCnILYczA2u2Dm8FvZ8JXGyE5DC7vumsx5v77nJzGo49uxe/3EwzdqMLCFCZPTiUxsWmE+jXXTKeiwo9Rk9wsRDAoKSz0cO+9f/D668c36jGvu07luuss4WXx90EIcR7wJuZVrxSo+wclgf3W3bAsYBYWIZy4OJuriCAKgYINOydxLomkspP5VJKDB4kXiRuDOfI1Hqzys9PdF03WBtSHa9X0TJ3LhLTPiLRVoghJhFbNuIzv2ChWH8EZHjzbtsHkyTD6VOh3KfS5DD6Zbn528skqAs3M+SCl+WoeNJ8BBUgH0EFiFPvhnQKYVw6eUvAbUG7HvdBG0Vc2ZiwQPPqepPcFtSWcjlb6dIaTh5s1IevSOwUeHgT/6gkHE0oVHa2xaFE/zj03lYQEG1lZTh59tDUvvti+cQceorjYw8yZO/YQXzUEgwYffLCGYHBPt6jFPwzLArY/HsZMuBoupUyRUqbWeVlpKCwsDpYUmnMtD+DHhw37rvxeQTwEdj3gmKkGitjGY95yOjnW0t7Tnl5hRWyTuQgMxrm+x6bUv/LYlQBzmE4bOh7eSR0iHg/06weFpWD0BIoBAZc8BokxMLKXYO4fLs44w0deYYBAOxVuspvpGcowc0RLAX9UQCB07kSEGQgkQlWz/cASidFFsmkHfPij4NIJDY/n70pamoN33ul0WI6Vm1uNw6Hi8+2euqgWXZdUVPiIi9v/ogyLvzESCOy31T+ZKOAdaWajPiQsC5iFRQPYcewSXwAp9EDZbX2kgWBU/HTiIooJc65DyJXcvflTnlj5EOn+nAb7raIKgG9zIPUHiPkOHlhDvZqCRwvr15vZ4Q0H9XKsun0wbaH5c79+Cuu3uHB8Egb3OSBCQD6Epkl4dCWJbfIJJesCWQVGCej5tZMOAssFuhceeFYelecCwDAk779fypNPFpCff2zemZKTw/YpvsCM2YqMPLbjFC0sDgMfAuP+SgeWBczC4gAII54TeIxfeAg3FRhSYZOexbzy/hT6krApfs6J+YDW0QmcWLWEqE0l5LRORnPWqglF6jQTEWx3w9kLwB26Dz65HrpHwykHZLQ+fDRrBrqOKZDqaM8wJ7RrUft+VQW7yjIhgT+BPmCP8zHxmo/J65TIL7+MBKOS2jAJHaQbRLhpJfMb4FbIq5IUFEFy4mGY4EFy5515vPhiEcEgPP98MZs3t8dmO7byJCUmhjFoUDq//rq9QaGraYKzz26PzWbFa/3jkZi59Sz2xk3A10KIkcAKdrMXSin/b38dWBYwC4sDJIZMzuBNenANpSKVqZUnUuRLwEDFZ7h4t+RiZmvHERQqd157EWU7w/B7zRuZLhXCgm6S5HTWVULd+7Zbh2UHlDf58KKqBnfd5SUx2kdErsShgabCOaPggjG17ZIcEKgJGSoEKgEVUrrsRLUFMXQbGCr1Y1Qx39dVAV7QJERHNum0DpmffqrE7Zb4/ZLi4iC5ucemFeyll0YQGWmvFc0hVFUQG+vkoYcGNryjxT8PKwZsX1wBnIBZkmgCcEad1+kH0oFlAbOwOEjMWDDBVn9L9DrZ7A0UZlUP5/WW2cgOLv6MH0yayCVGL8enOBF6kInyHogKEh1ZjPDbKKuOxaUK+h9lRZvXrQswcGAhgYDEMKBLaxu/TknE4RB73Libh8HAeJhdDH4fUAKEQyBgBwXiuxdh5ik0qH3mEyBCeRx0CSIIHo3JpwlyciVZLf+aZckw4P7/gy++hN694KUXarLmHzqTJkWzaZMfKSXNmtlJTz+8lQwai3bt4pg//xxuvHEmv/6ajaYpBIMGJ52UxbPPDiMt7S+eKAuLfwb3AjdLKZ851A4sAWZhcZB0oi9rWUKSVkSxXrcuIrTwZjMsejbfP3sipcJJnr0ZeTRDoBPuqGZtoAMLnS9y1lA/fmmQX5zJoKozGZ18dBmjL7qolJISY5eBaulSP6+8UsWNNzZsnvq8H5y3EH7xh6ryCMhV0tmZ14K0xGyIElARAxhm4UmXC9w1vk03yAAUe3ntuWpee05w662xPP54HEIIqoPwWT5sdEP3SDglCfZXJvH1N+HpZ8wYtk2bwZDw/jt/7ZzceWcSPXq4yMsLctpp0ajqseV+rEu7dnFMmTKR8nIfRUUekpLCrLgvi/rUrIK02Bsq8JfSTVsCzMLiIHESxrncyMgonYwiP/6QSonXS3gweD+JRh4Ou7+OpUiiYiCFwgxtODrVGIpEBTKSttI1aSHQ9wjNpmG2bg3W8w56PLBx496vxjF2+H4AlPih43TInw2cKfhl8ziS3swjrmMhJWuSzMYC8JSZMWH2VPAHqB9wInnhhVJat9YYeV40x80DtwHVOkSqkLIR/uwHcfswQC1cZIovAJ8PFi065FOxCyEEY8dG/fWOjiKiox1ERx+GmlH7oaoKioshI+NIj8RiF5YA2x9vA+cC+4312htH12O3hcUxRIpNxZviZEGCytQEydZknaxAJV6c3OZ+EpesRpE6GkEceAlIFSnsGKJW2QQIspP8IziLhunb147NBuZV2IOiVLJuXRULFuw7P1ROPlT6MVdBvgfMEhSEpVKyKhn8wqz+XVEAwYApvvS6VQRqY6q8XsmHH1Zy4UooDpjiC6BSh20euHO9+X5bMdzwAQy4B05+DL5baLofTz0ZwkJZFMLCYMKpjXFW6qNLg2yWI/eIbbM4WIYOhcxMWLXvql8WFkcTYcBNQog5QohXhBDP130dSAeWBczC4i8ghKC33QbYgObQbgmRuTeSn1DJBN9XfOcYj46NtsYaBjIXIRJYRwJVmHE2NjSS0CjjeVwMwUH3IzmdXfz3v7GMGlXIsmWlSBnEMCTTp5fRt6+f++5ryQMPNPzsVlhRxz0YBNaFfu6IWagDFzhcgAS/H/QSzOfAALsvuXKGCX4tNyPH6uKX8L98GBGAsx8361/XNPp1JYztAZ/eCJ98BF9/A716wZWXH/jci4rhqVehSxYUFkNi/J5tZm+DxQU+BvXZRDJtsGPlzPordO4MubkQG3ukR2KxC8sCtj86AEtCP++eOfmAnsosAWZh0ZjY0gn3RNB+w0pyu6YwXvzIYqM7J4spKOhAMQlyHUtFV4ppRhYtyOBOSimmjOdozgJUjnxEfny8yqOPRzN2TCG11xIJuHnuOQ8PPNBwzaA+rcDfwNJ1JQsS3ODeCbExkJpYwfx566mVVy7MQH3Tb6uqcPNtcfy6lxuAkHDeS7B7CsRqH3y3QPL1Apg4XnDS+IOZtcnQ02DDZnj0Vmg9GO66G26aBLY6V8u+6dAsykVLGi9r7KxZbrZtC3LyyeHExPyz0kC8++6RHoHFHlgCbJ9IKYf/1T4sF6SFRWPi3QqFH/NF27FIBN8a45kovsYuAmjCQBM6mtDpKleSSBEXcgYKVYCOxECaIexHBTfdo7PHkkfMTOl7I8IJz10ALnttPcRwB1w9GvKXQ2UxbN8EP0+LJmpgW0RCNOZzoMQUYwaKInnhhQRGD3cxOMaMdK2LXcApsRDcS+oOny644YWDny/Ar7/C6nWhIuISKsrggbfg+ufqt3No0LIRrTWvvlrGuHE5XH11Ab16bcfns0oBWVj83bEsYBYWjUmwHISNSjWceIrxCBcO4dujmYKBjUp+4zU68TjwLeGcikbK4R/zXigus4OigV5HFCoqKSn7Dtq+bAT0bQXvzAJPACb1h2G7VV9auhGIjUZ2iYZKD2FbcvGU+EhJUXnmmSQmTYoG4O3OMGA+VAah2g/KZjCqoDRz32PPLjBThewNKRvUllx/PaY3tCbA32bOYcqf+z7eX+WDDyqprjaFbUGBzubNQTp0sFYlWhxhLAtYk2JZwCwsGpOw9qBFMyJ7DiVGLKrUCco9n3OCUuONH65m7AeX0+fbviyqOpvIRnRnNQa9OkmIywRnFKh2cESCU2Hr1hzuvbdgn/t2y4BnLoBXL4HhnfYUOx1a1OZgDUtwcdvTWeh6e3Jy2uwSXwAZLtg8GN7sBD1LQJRB0Ac/b4KIlns5eFDi9DT8kccDJ08CWyxEpEjGnypZtqz28/BwoALwYhrkuoHdBf33U6qxosJgxgwPK1YcmgXzhBPCCAsToQwdChkZ1rOxxRGmphZkY7wsGsQSYBYWjYnigG6/M7rKIHFDNV39K/lWjscn7RgSDCnwGg6+yT6F0t6RNDtzE/I4P5Nn9qSU7CM9+np88F87cQ4/RCZBfAbYA+CuIhh08/TTJWzceOju0uQ4mPsC3HImPHct3Hu+uaChIRwKnJkCejUEQvFl3iCkp5uuznoYpqr76smG+7rrAfhlBugGVLsFP0yX9OxdTEWFud8d94CIxvR7qiB6wYCR8OZte5/L5s0BWrfewamnFtC/fy7XXVd8EGfC5O6743jttSQeeCCehQubExZmXZotLP7uWI9ZFhaNjTMDus3gUgymupfz3C9JPJTRhdEtp0IAWqob+THyRBwxXoQC9lgvYpDBjzlrOSet+ZEe/S7i4gQ71kdy4YXr+OqrHQQCRUBzIBxFgYqKv1YorlNLePLKA28/vjWsyIegBE3A+d2h6wC44R3YUWxa1IZ1Fbx2ObRMbriPPxeYmTB2IcGQkilTvJx1loucAnA4Q20MOLkAvnyxNp6tIW68sYSiIgMpNcDg9dcrufjicHr0cB7w3IQQnHfe3yvHmMUxjlULssmxBJiFRRNRVqZw0/jubN8BQZnEojYD8eGgZeImbB/5CZbZyHu6Ob5tLkiTnK9m8vaYHbw8NII2xBzp4QPgcgk+/rgdX33l4rbb4igoCAOgSxcn3bo1LDCqA/BnAUTaoE9iw7FWh8KK5UAR4AB8sGIF3H0NjO8FpVXgtEPYfnKK9u8DS1fUEWECbGqQFi1Mi9OgfrViS1Fg0sh9iy+A3FwdKWMxL6cCv7+E++/fxjfftDvkue4NwzDHZWHR5FirIJsc60/ZwqKJDJ8yRwAAZY9JREFUuOXfsHELVFWD16Ph1V1IQ2VzbluCVTZyH29hiq8+AlopGC01ft8Rx7XBOUw7ityRiiI47bQMVq7szptvpvH222nMnJnRYCmeAg90+B9MnAojvodJ0+vX2/4r/LQCgqVAnvn/D6HYLSEgLnL/4gvgkX/DqGGgKhK7zaBZQjmPPBzOgAHmzl07wa9fwT03QVYGnD1x/32OHh2BGbWvYAb+h7NhQ+khzXFveDwwaARokTBuIgSDEAjAA0/D+PPh7U8a9XAWFhaHAcsCZmHRRKxeZ+YaBcynyTwBcUAAct9sjn+HEyKFmf5KAxD4vE7KSyP5OHE9ozh63JFgBodPmrRvN9ljSyDPA4FQFoUp22FOPgxqhMWdiZGQXVL7PvkgPHYeLyxfC906wHf/A8MQKIoA9swl0a+X+Zo588D6vummCJ56yovPB2YajTLuuy/zwAd3AHw3BZYul0ifmx+/00hI0dAjBD5DEAgKZvwBDgecs5d1HG43lJVDSrJlQbM4QCwLWJNj/SlaWDQR/XuDs65VphBYDwTAvzgMdFCNIJnJm4iLKDLbCFBtAWLlka/PdygU+WrFF4AqoGzPLByHxKfXQJQLIhwQHQafXL33tj+tgY6PgXozpNwHrY6HEefAkEnm540pQuLiFGbNcnLaaQo33KCyY0c6Z53VuOlEkhIl1WUloGlIXaG82KDKbYovALcHpkxveN93PoS4DGjVDTr2gfx9L2C1OACkhP/8B8aMgZdfbjwr71FFjQBrjJdFg1gWMAuLJuKRu2HFapg9L2QJ82HWSGwHAolSFeSGRx8nMbUARTV4f8bFVEZEYIvyc17ujRAshpSpYN9PDoSjiIvbwRdbwK2bKcQcauNYvwCOawN5L8COEmgW18AKyBAzN8Jp74A7tPw9vwLYaf68ZBU8/T+441YIVkFiAvzxI7TO+mtj69dP4fPPG1c067rku+8kc+eGai0lhptW1Br80nyEDgWpDei9Zx87c+DqGwlZ52DTFrjqRvjyw/rtysslX3+t43TChAkqdnsjBe79TXnjDbj3XtOyOGcOxMfDpElHelQWxxqWBczCoolwueCXL2Dncjh3LGhe6NkTnr4TnHZBi25bSUwrwOnwYdcCjO75I9u8LdlIG9r5N4CeA4UXHulpHBTD0uDsviDagsgCe1so3S2peyAId38Eg++F+z4JZZ0/QFx2aJOyd/EFcM+UWvEFmFe5rqBEwv23wG13QbASkFBYCIPHHcQEDxPBoGTkSJ3zz9d54gnJs68IUHd7Xq7QwQMYpqAf0n/PfrJ3gK3OuQoGYd2G+m0qKyXdu/u45poAl14aYNQoH4bxdzTpNB7z5pniC6C6Gh5/vIKtWxvJ1Hs0YVnAmhRLgFlYNCFCQEI8vP8ubNsG8+fD2QPN7eWlsSiqqU6CukqhJxFZpmHoApcMLdMz9lJv5yhlZhl8XAZSgC4g1w+nrq7f5oa34fFv4Pe18PBX8K+3GncMawsb2JgFttEwYJCZSb8uefnm6sKjiW++kSxaJKkKjdUfEKAqZhHMGiRm0tiQAHN79hRN7dtSryywy2UuQqjL1KkGRUWS6mqoqoJFiyTr1lkCbF9MmmSeS1U1czUsWZJLy5arWLq0+kgPrfGwXJBNjiXALCwOA0JAWppZZDo1BqbcAsKXwPuzLia7ogUr8rvz2ZJzEBEGJ1V+hxRRIFwQ+0iTjKe42OD99338/LMf2YgBLIuqzDxdNRjAanf9Nh//YSZCBVP4vD2z0Q4PQIek3TZoQDooGZCVCWl1M+grkDoMHl0Ejy+EOTlHRzzP778bu8QXAD5pqtpUDRwChGJaxOIEaGAYBklxeybGjYmB6d9Bh3YQHweTJsITD9ZvExVVf86GAZGRlgtyX4weDdOnQ5s2RZiBnabweuYZK8DO4sCxYsAsLI4AQ9tD/mtw6Vs9eTa/B3oyKFE6YcJD99LLEGk9QGsBtjpqoWQb/P4quGJh6HVmjZxDoLjYoHPnciorzbvuRRc5eOGF8MaYFhkOsAkzPKmGZFv9Ni6nmberBm23z/dFZQC2uyEjDCL2st/DJ8LY10NuSBswwPw/oEKrOcCdoDwLhh0YBsVOuPc3U9M47ZASDh+dcOBjago6dFAID9eprjGoSFDzg2T1VsmLUPH5QnGF0gApSXZsIT2tVYN99e4Jqxfs/VijRimcfLLKl1/qSAl33aXRrJklwPbHccfByy87GTGitu7VxImNWKH9SGOtgmxyLAFmYXGEKFO9+C6dzyA8jCSFs6q7EmOLINEBMBSAKvx4CJLo1eGJ3uAuBdUG66fDNT+jBwL8ctttbJwyhfi2bUn+17/2e9wffghQWSl33dxffdXH88+H7bUU0MEwMQE+LIBfSs0VkIaETzrUb/PUZDjveTCCIDR44wCz4f9WAONnmz8L4KehcFxC/TYVftgGXDYefloA6+0gHYBS514igJFABKCCPwBIkEFwG7A5AMM/g9eawa2fwcndYHDbQzodh8w55wgeftjM9eX3m2MOd8IvHwnS0uCrH2HKrxDuNOjappKzTm+JzXZoDg0hBB99ZCc3V+JwmBUQLA6M4cMjWbSoPT/8UM6wYREMHhx5pIfUeNTUgrRoMiwBZmFxhLjAvYnNrkikiOJL6WZcRAltiN/1+SoKuZ/ZGEhO9IVzie4HqUNQh42zAPjllltY9MYbBD0eSjZvRjvhBOSoUfsUU4mJ9T+LjhaHJL4MCavKISMcokLWKEXAlx1hbgUUB6F3BKTutjjw7P6QkQBzNsGg1nBcw4abPThrLlTWeSI/ey5sPan2fZEXenwPpX7TpSZS4Jy28GGd3GHowBYJfmCjMG8ylUA00BJTlOngWQkFUfDU7/DyTPjoMjil+8GcnYMnGJR4vZKICIWICMHixRrnXKrzyzSJEia48/9UMjLM7+nMk82XeQlvHKtLaqolvA6Fnj3D6Nkz7EgPw+IYxIoBs7A4AmzxSdZpBuVrYsibkk7RpgSeKdpcr833bMSHTgCDKVE1PjsBqh2a9QBg/Q8/EPSYLhAZDBL0+fCV7ztw/4QTbEye7EBVTWvHl19GHNIczv8T+k2D1j9AcZ0FYELAgGg4KX5P8VXDgNZw65gDF18AxbuFOBXutujs38sg3wvVQTMNRnUQZmyFXRkVDKBQQhlQKExLmAKEAxswQ3l8mJqmjkfW7Yd7voLb3oOkCyHyHDjxQVhS/+s6aPLyvCxeXEpOjofp0z3ExGwnNnY7EycWoOuS+HjBay9ppA20kdZT45yT9y2QVq/2k5dn+YwsGomaWpCN8bJoEMsCZmFxBPgoF3bOzMS7yRQ/5X8m8E3zUt4+TnJRZ/NG24kEFpGLAbQQkfx09w/oa6cyqMBN5fGDWCnPoO2P6Yjbt7P4xwB+r+lOskfu2w0ihOCll8J58cW/5nb8KQ88uqlhVlfA4MRD7uqAODEVfsoFrwEuFcan1f98Y0X9JLBgJoE9JdXPNyVB/JtdZqx0nqh/5dMwKxTkAWlA6p7H3pALG9aCL+SS+XElTL0PTu8Hd58KXfZRtMDvh2tvM8tSvfwkCFnJlVcuYe7cEhwOBb/fQNe7EAioAEyd6uGrr9ycfno4mWmw46f9n5v8fJ1OnXJo00Zj/fpm+9/BwuJAsPR8k2IJMAuLI8CTG4UpvuoIoMrtsdyj1wqwcbQmgTAKqOYLNvFCTCFG/578NxDkhlmPMOiFlWixQaonO+neLcBbT4UT17o1iqoe0Bj+aszX/Z3gtmXQOw76xu27bSnFKKhEH2SRcQNJNT5sqHzU38ZlS2B+BRwXDa/1qN92SDL8XmBavwBUITml2+9ktV1K7/xO/DFnOEQJ0xJmUGv/NzAtX07Mp/UAplsSQDUXCRiVZjwWaqgdZpqNTxfAt8vg/AHw6kUNFx7/5Ev48DMzW/15l1WxcdkMKiqCSAk+3575L3QJ83fqDKuQJEQd2HcUF6dwyikuevY8NisoWFj8E7EEmIXFEcBTiGni3/3+Wud+LBD0J53pbKcALwYCELTPWcbAaxaheg3QwFEegNMVbs/dxG8L1xy2OVzX1nztj/Ws4kveBwRncykZ7N/vGETnG1YyhTV4CSCR5OX0Za6vHXan4DMvdM2Fm+sYe27rDHMLYXoeKBJ6Zi6nR6fv0EWAEUm5/KEMN895OmZm/LoCrBzoAjglvBGq2TkQRJwZ62aEA2GYwmy378zjhw/+gG4t4OpRe84lPWRRczkhf9sKKiuD9VNdCBVECRjxEK7gjRE8NVLwnwU+jpvr4MULBN1a7Pt82WyCr79O3u95tbA4YKxVkE2OFQNmYXEEOCcB8FKbJFNKEPDU4D3/JHOoCXYSpJHDxdnvghbaMQgiJ3QPD9uPGeoIsZWNBNEx0NnB1v22D2LwIL/wNSuowkcQg3JPOL9tb43XEGYCeAPu3gLbvJId5JFNHqoi+W4EnN0MdB/MX9eZX5cNAsBh9xPRrNxMUhYrTVdjKZCLeZPpEvp5lTCtYKF0ThIwamLFDPYUzCHcfnjku/r5tKSE/34AH30OF50Dj90bpCA3H8MIB3qD2h86j4Q+J0Hr7nBuCtwSB18lQKSK0Ubn98gggx6EFdkHf94tLP4SViLWJseygFlYHAFeHgbfrIHSbdL8K7TBmcMkE7oEzTd1GEAq77MGgU4LuY3q7i70KBUMHUWXyMGQm5TCSmUsfiaRh0IKQ47EtBqkD4PYykZUNLrRZ7/tZ7KBLRTjrxO9W+2NQO7mrfPpkq4zKjih1wxaJO3EKV2cqJ/Oe+uT0KUAVH5dPIbh3X7DkIKTRn/BabYvuGnKS2TbWiCTVfgcsz5nzaFsQDsgk9og/Zrj7pnntB4FFVDpNQuGA9x0N7z+nlmyJswFJ40BVRUgWoNUzIynNs1MnJanwYehy/EikJmYZYYUSdVSuOBxWPLifk+dxV8kJydAaqrWKClZLCz2hyXALCyOAC4b5F4t+G0nCClJz8jnGfETVxKkH1lcyXBEyNzSigguphcvs451sh0yXLD+x+ZE/eZGBhTCdZ3VQ9oh0ZFIlvMwCfRCo4HkqoYB774Ac36Bzr3gqrvA8dfihnQk88hlNjtQEAyjOb1IRgmNP5Z4LufmA+7ve1bjq/PYLCVsWNUew1B3s9kLKsqj+WLORFKHbGFc9c+srrgVVX0DPegADFIcuZxR8RVOj5uqRA1dUfjyjHGM+uh3ynxxpuDy1unSDnSiVpDViDA7pluyiHpu4rpICY46V9TX3gFPqG+3Bz7/TkXTVGgeCTsD0DwK7GFmMNmu+72En4EhwrTQ+QAHLJ0KH34L5558wKfR4iB5990SLrxwB48/nsJtt+1eTuEfiJUHrMmxBJiFxRHCocHxGQCCO5iNN3S1W8w21pNHuzrL8c4inUmkIRUooh9bYn4menxfmm+qYEf0CqT6K9RxVfqprBVg/i3I5R8h35hCYNEqtLJKVGmgz/6Jn557llUVGs7YWI5/8kk6TJiw65i634+7qIjwpCQUreFLRQCdh8p+QFu+kIKEKDZ1zGIuOXQmgX9zHOohRDkUU7+eXmFBCvk5aaalqG7KqxIQDp2wEeVclf8m1+e8TLjhoXXqVs4u+5hCZzxpx20juSoH3S6oFAkgBOE2NwOb/cYPG0+B/gJmY4osCfSl/k1HAEmAC3N1ZEtgEQ26VYZ3hC0V8OYyyKkyqwfVxUAQe+ZA8rzRMM8NCeFmeSE3kIIp7BwCooA8A3yKOYDQ13rH400nwMrKdP7804PNJhg40IXT+c+LTklNtREdrZCRsY9K7/8katJQWDQZlgCzsDgKkMjd3u+JCNnEkuhIEh1N0eDaSMLdVyGebQ5hGiAIpxmuQDRTvC+yNGIr0mbQTNnJwMgd5L3TGnc7F1IKgs9tYumdOQR18JSU8L/TTqPFoEEMuOUWopo3572RIwl6vbji4rho9mxiW7asN56tFHBn/nQ2BprjSB/C/U8+RFp1LlG+Krb1aU55xwJi29yNaHvJXucdlObCwroeHxe2eu7HdWs6ogdVU/R4MXfQoUX0ZkYO/xHN7ueile8Rbpj50IY6ZjMrcwh9es1hs8zgXs99PBCoXwDxih4vMXXLiQRS7HASphsyAlNwFYXqLoJp+XJRa3lzgJIOxrb68wh3wLA+0PMdMxVG0ACGAdNrv1DZBfLUGMgR0CrCDPyviQO0Y7o9wRRiscJMi7ELSU5B07jFVq3yMXToNgIBiZSQlKQyd24miYn/rNvD6NGRlJV1PtLDsPgH8c97zLGwOAq5mME40FARdKcF7Ug5sB3feRDX2u0MuGQRLT/MxiHj6Fd+F3/8cgLLI9bTUSynt1jIx8a5dO66los2fUC4r5q+voVk/MvBiPKutH6mOdgVkJLts2fzyamn8sGYMQT85dibGbhL85hy9dX1DltCFbfI2cyJ6cX2Zi3Y0Kotl/7nVcLyPURGlmNcF+SXEzrzTouFrCJ7D4G52CPJzPbg2ubGvsFLz9xCtkofhgFdSjqAvzYOrqw0jl2XqlBg8EVdXqXHCXP5xX88X5WdzqNtb8ZAoAdg+QzBwh8VwvIL8QknH7kmYfgVhJS7ouRbx27gvZPOpHnEFnBIiJcINUi4q5zMnhtrB7rbFVIooMRiikCb+X9mKnx/Mzy8GDzBkPiSmIH9ZwEjgBOA9phK045pVatJh7E7ClC2u9gSGFFw9mNmIYQaNm2CG2+Gs86Bzz43PcwHy+mn76CkRKeiwqCy0mD79gBXX523/x0t/v5YQfhNyj/rEcfC4iilHam8wmT8BAnjIFwgCWlgcxC+w0O79wrIvSsObdZbLB7ShqHiN6KoYHt5BjNXHY9Pd7GzrBnt7WtRVZ10PYcVrs60vz4c0bYzG8YtN/uUEn8r8M65Aw+Czp4lBK7aWe+w81lPnhGBz1Y7Vk0PsqxzV5qdsJVPnWdRRQRSEfwmp2Ho0WQXjuXcMAcn235ksGcAejjIP5xcvf0VznF+wu39bmbNNxPYsKkLckgW9tPdRCqVCKW+eBuYNoOunZbwqucqctzNMKTCu7YLucH+PNOvyaFgG3jFDia/OJgP5v2CbBHPHNsARubPIDc+Hp9mo9ybRvfYpcw9pw9BQ2VGyXCWGt2ZvnY0q+d1JTIGhAuc7SBYDaphWrZcGvg7YYqpKsABJ3WAKgW0umKtRgilUOteLMQMrE/BFFnO0PsDQQCR8O08+O/PcMWJsHQpDB4GXh8Eg/D9FPhpKvz39QPsM8TGjf56qzcDAVi82Lv3HSz+GVhpKJocywJmYXGUoKEcnPgCuOg+OOlS6DsGnvkFEAQ0gV36iKICFQObEqBu/oRgwPyzl36D8rmVKEjietZanKSAymuGUq1E4lYiWBR+HCmv1696PYN1RMoqlCqJd2cYulslqNnI2LmNb/ufRDnRBLATFDb8QuJXywiP+55fiz/hxopipAr6EgeOJTrP2G+hv5zP/fPuIzelAm9AoI33IYVCtQwnNq0URdTcCSQXD36dCKpos3IOqseHCOpEbsnmrfKBFOwQBD0Sze3FXl5JjxfeQBdOVkd1pNCZjOK2kWK8QOewhwhTTdWhKTrHJ0zjFOVbtizoyY09NYqvh3ZR8EZf2HQaPNgL7u4GC06GSBemeEqAsGjoEWGKr12GqYb8x2BaviSm9azm/d6oa8kSQCIQBm4fbMwxN99xN1RVm+ILoLoaPvoYtm7dR78NkJRU/zlcUSAz07aX1hYWFo2FZQGzsDiWcbjgxhdq38+cSenwSbSddjnGeIEqoFnkDm7u8whvrLiaZt7VfH4ydJ2os+l7A8egMsIH2Fg8JxMtNZpgbjmiYxz6ObWxMAKDCocTgwBKKEXGNvz4qqLIn5dh6g0buGM99LprKTF5JQxxTcOjuNgebIGKTpZtMxH2KpYmdiGy2g0KGLkanoDGcn9XOtlX8pN/DA+Muo075z+Nf5uGrWUAm0PjpnZB7tws8evQq9l8UASxS9fSb/hHyNOWUdyyNe1//pHVnTvS0XBhw20OXEpUfwCJQv/czthiOxMeM5pwWiDx4VCbEWQrSB8SF12j7qaqzmLNcBXGhUoM3dqldvu0HnDOKijww+RU8+XXazPw7y1XmNkpZjoLL6aoKsG0MtQVbTWWB4EZlxbPriu1XYNTjjN/Xr26gV8HO2zYCJmZ+xjDbrz3Xhonn5xNMChRFIHDIXj55QN0gVv8fbFWQTY5lgCzsPibEeNqzf/GTybWu41Jzs+xEaBvu7kktsklqXAzW270MmuBROiSs+6q4L3Av1h1cgc6nfULqgpGkRfz7h+q1yMFqYaOotZaRTa4e7N0ZxZO4SHVkUtuTCoeYa66LPXGMzPneIzEIAYaINmpp3OD8xniIor5NXsEOEFt7Sew2UafvAUk2fPJ7LGRj1ueQZ+HFnDP/55gYOpqmkem02znTq7rKvmm9ERaRG0BwP/FVnQP9H7/Db659k3euXUq6JJs0Q67XkVxRgcSs1ez/fIRRHkrGDDzWoQtHM67FACBg0SmUs27GKIIJ6Nx2Psf0PntEQlrdmtqV0G2BdZRW+GgRlQZoPjAXgF6JAREnTZOYBSwEDMoPwlYEzr1SaD6zaSySFA1ePpiGNTJ7HbQQPj0s/pxXz4/dOt6QNPYxciR4Sxa1JIpU6qw2wUTJ0aSlmZZwP7xWKsgmxxLgFlY/M2w4+RBMZFLHKsYUHYzQWmmM3BKyfNfv8PFC2aTMy/Iol7jeKblYKJyKjjx3idQBgyiVYKCUj2XPy54C/3NcQiHSrv8ZfRKfn9X/2WGZGVFJkMSZvBe+8kgJELCus87kbe9GTcOfobKVEedi4sgiMqaYAfG2H4m+dOvmXHqlSxqNQIxUkff7qQgMY6MTrDdaEFW/EaGXPUDK+nOGqooaNUGDZ3+zEYGFbw4wBlBSfMYfv/kTcrKm6FsEhiGxsIu14Xcg4J1x50ClZCwLZfvBg9Dj3QSrb/HIPV07IShEE4kV+95Ag8BRUBqEuSGY+YKC2CumNTgjQzQKyA1GlYUw4NTwSMwV1cOwlz9WFOdKQhsA1KhbVf49MIgH/+qMmup4JJxcNlJtcc8/Vb4/hcwfGbBb02D++6BSjf4cqBZasO1KRuifXsH7dtbdSQtLA4nlgCzsPgbkkAiXylD+Tmqkv96DMKxcbPTSderbyTg8xOVfhft+ZGLq6agRQ+Dd/8EJcrcuXAn3W3bKXduhdIYkmKfRBO1N+cpPh3F8PFe6mQiRG3Oro5nLGfNvLY8uvY2rmv9zB5jEkhsBGlzUyRtxYfo8lPmzglDf3819os6cf2IWRSJOJ6TNyGEJF3kkiNTiRVlzJEDSSWXDra1lBXE0jmiOcvn30WgNIKgRzOFhiGgGigD8oFMBdIl4T4f2Z3TsIkgeYFf2aHP5xzlMTQtolHP+WcdYMRy8Nekb1OhWRHc9CC47PDDQzCsI3y4GLYUgzuA6Y6swnRNSszx3yQhBjYokjtcUzjuyjV8xyUkUhuHt7gUztsKPAdDNsIIJ6ht4Kmn4d5Xza56dYHfPwebZcyyOBSsIPwmxwrCt7D4m6IgGKtG8XlEDO9GhNNVM6O/bY7bCbNtJEz8jBZbAbG/1oovgMR0wmOOI42zSYsdi7ZbpvxKQxKvFKHu5p8QwmDZcV2Zds5QWrvWIUKR5FKCXQYYos7CJgJo0TbUKBv2aMHgayrJYBuJ9/yP4pVBvg1OQFEkQoCGTrowI84z3du4ePr7XPH1mxQF4nnhX7ejJuikts+l7aDVDL3oJxw2t5lYDMybx1ZACvKqU1lLO/JlEr5tBuqY95l+eRayuvigzueCBTt55ZUF5OZWNvj5wGhY1wcGJZnB+a2dkF0M5adAXhLc9CpEOGD+DdCjJ2ZsVxzwIfAjMDU07mhACKRUmLpyPMu3N+eGRblsKIMKN/gCUBIwPZh+B8zoALenSG7ZYJB3epDgKTq6Jpm/HI6bCG9+DPOW1I4zP18yYUKQ9u0DXHddEN/uGWPrsGOHZMECA79/720s/sZYaSiaFMsCZmHxD0SoLUFtuf+GDTDGoXJ9RSIBacMlatMVVBmRLKrqQ747leb2bYyL/J4/jOMoqE7ljuhHiVfL6vVjIMChEH1/F96bexoflR3HePELSp2IdIHEpvv54LmLSCooJK9FMhvGtUFRJEgDQ1dpb1tDuM3N6pZdyStqXnsAKUFIeqQvIJ5ihIDKtFgq2mSw6f3VfJh5Cyuvv4wUcnlo1XP0TB0DmXft8ttJJLPKdlBQHYO2w8O5w98B4MEHf2P71mvRKqaDPxcczSB2JIai4HX+zL1tPiCgV/Dt6nHkus6lOhAJvSSpoUSq5yyBOQGDiF7lyOWCal80bBGQAKRj+jNrJ8FXUychqxU+/g3EQojVYNWz8HBHuG2Z6X5EEdDDgCgBaQK6GPCQyqKV8K9/m1N66yk4c7xkxIgg69ebqye3b5d4PDpvvln/VhAMSs49N8C33+rY7eb+X3xhZ9AgxUxlZhcYhimUc3MDnHvuVvLyAjz5ZHOaNYvA7YY2bQSJiQ37QLOzvXg8Om3ahFl1Fy3+sVgCzMLC4qDI1BT6K3n88Oc4Tuw/BafwUiEjGZCzkFIjBqlAXiCZpZW96B0/l2pvLCmx+bv2NxAspyu5pIIGaSftZH76NSgOBV3MQKmz9Er1BXno5ofI2LYDJWjQfFsOt3qf4z93XUMs5cQopWwjg1zSMLoZsATCnJXEJxZRWhFLMFrBnuJGEaY1TrErpBwXx8It/fjgopeRlQqK1MnulsZbyqXsnDKTK1NfoSwmlke9BnfMTkD16wjNifL0JKrv+IpgYSXFU1sgkl2E+ysJDwYwFDvzunfF6cwhXfWh2iVXdN7IqR0/4aY5L7I2twPrz9Y5+VeN77YLiBFU6THQFugHbMG0flVgxrDV+CYMgfQK0yImQEZDZRGszYFL2sKtC+t8MdHAGsUMMNNqRWxNPcqX34PRg2DjxtrUFR4P/PDDntatV14J8v33Ol4veL0AkhNOqEJKHSHgpJNgypSVpKTY6NIlkdmzq9B1OOmkTUBHQKCqgtNPF1x++e59Z3PTTRsQAiZPTuWVVzoc0O/dokWVDBiwmFtuac7DD2cd0D4WfwFrFWSTYwkwCwuLg+bNpC/59Od4/lg/CFe4h5c7XUVpRBTSEUQI0/jkDypsqWhDtRG+SwABbCGTPJKRIZWRY0snOb6Q3MpmfLN1IqdkfokQBkIYZM7Kofn2HWgB093p9Pros2ARfdYsYkvHlgSwsYPmGKg0S91J+HkeTkv7HAMFFZ3pOSOpdrhwSQ/+gJ3YOfl0Kclm1jM3E1qbQIRRyWfGOTQX2XQYvp53/RcxueoDDKngt6k0T9pBRq/NKFJHm9yBZO9OLgl/gSilitbqBmKCZYzL+5HEsHXY1AA+w86vBcfzrjGZksRo1GE+Mo31bCiOZ/H2REgQtQJrJWbQvQ+z9NDjwGkS+plt5E4FPNLMGVZtthvRAQa1B1WFvvEwryi0WC1bgXgJO4Acc5mlTYGADk4HdOsIkZFmsL7fbx5eCGjRor4Fav1WeOgdgTtcA3eN/yhAsE4K/u++kwSDURQWVpCbG0Cv540WgEDX4auvJMcfX/9359//3ozXa/4+vPHGTp5+ui1hYSr7w+PR8fslJSWWT+uwYK2CbHIsAWZhYXHQhPvTuOudexAGrGvfig1D2yF1uWvVnRAgNYNCTyIBYWepuwc9wxaiCkkZsaH0FCYyIOmycQq5yZezqbw9L628kXRnNm9ETSTmtlXYd0tJpeo6mRuy2dKxJXYCCCSK1AlKlZPSv8Wu1j62j242FR3JNDGKXFsq6jCDtUO7kuApxVHux4eT+5330zyQjWboYIN+ygLK3AkgtsBmjez1rch+uxUiRuf6S5/kglbvATBTH8JLvms5y/Exa5q3pb1Yx//J+9gsstB8OvNeGIzUFZxtq0k4JYfw7W4qFwIOzBxgPszFAhLIwcwNBvCBgI+ATpgB+u3FrqwgYZHw3X2m+AL4ehA8vx6mbQJZFKA4Yz09W4QzyN6S43+BqbPg3c+hd1d4/E7QNMGnnypMmmQgBISHw7vv1oofXYf+50GpXzVTYgigwI25WqC2XTAoiIuLomcvhQXLmmMG3OlAGrWJ0IL4/W7KynQWLw7Ss6f5nTdv7qS4OIBhQESEhsNxYKHIgwbFUFY2iKio/Ys1C4tjAUuAWVhYHDQJ6jikIhCGJCW3gH72uWx3n75Hu4BhR7gNPg6cT+uWG4hQq4gS5RTKBAxhXn6EP0iXl95k8UWDKWrZAZ/uIpkCvM+vYWcpdE4wE5DWoKsq2VnpgMCPjb7Mo0zEEieLCFfq1/ZR0UlflcMvnU5AKipBVH4TQ7k/7N/k6SkEK+xcu/1VtFA8vpwL9kU+pipdWHDFW1AtwI1ZTLtY47Vnr+f0Rz5HVXVs6w0m6++Tm5lEp/iVXKS/y9byTJQIibOZm/hzcin6oBne9eHsuLSNmZ5Cx7R+aUBnIBZIxswfVoOBmaB1OjA61AagGDxl8N7PcOEJcNdUeOI3sxTS3PMB7BTSijgcu6RSuyyJM5jLuHHxuJzmYorx41Xy8xXy86F5czOeC0BKycuvG5SWK6aCFoCzZimcSm3yMnA64T//SSe32MGvs/1A69DEasSXHpqEBAzGjClg27YUwsIUvvyyK1deuZbKyiDPPtsOVT3wGLDoaOuWddiwVkE2OdZvs4WFxUFj05LwDO6H4/d5RJdXcn31M3wdPI1AHWOG9GtQrCCCAmd0Ndu1zvTbMY12ch0F6YmUEwtBg6j/TMM5bS3yYgUwcAkPDyTfRf5aydYd0Ccd4iLMeuF+VWUT4azv2BohwSvCsOMlXhZRUhJP2cZymr/3OUqVBy7qSnx0OPOWH0dV23Acdv8uC50iJBdHvcVx2YvRiuokr28FYh70C25hY0lpaCVl7Zx0v8LMtwbyf2uewB80BY2mBml7w0bmbhiGEWZeUmNa5xPZodzsuFyYdSANzNxfnTD1TCDU9yLMuK/qUBsd0zoGsArojtlPW5B/wuVP6dyzsIAqVywSJz/WEW+JuPb4rlR1z3xgERGCiDpZOKSUTJrk54svDUjSIE4zjxllmAH+uzzI5sno3Vvl/PPtPPU8CFVhz6rivnonzuORLF8eoH9/BxkZLn78scce47Q4yrAEWJNjpaGwsLA4JFw3/4TesQu6XSFhZylfp4wjI7gTxa/g8vvJrNoG1YLM1A00a1HK1bmnMv6s2Uw8/SceH/lvej/+KtFZz2J7czGLLrkGLd7G4Ozv+G7ZEAZUzCVjpEA44M0/4buVML8Ivlio88U3JaT0eRxlawkEDfw+DWduJSnzNpA54l60V+ejvr8C7cSP+XhHf36cOJYcXzp57hSMIAwzfiWcarKMLdilH6GY9xqpY1qpAIQw49a0+gHqSkDno1kXEAxqpjCRgqBX48Y3XsII10AVoArKtiQTrAw93xZRq09aYT72KoANsxi3DmzEFGWldcYAhKdUkDVgPaotCJUG7Uq+QC8U5H6eQnCVH7UywI299/4dCSG45JI00tL2nWR11iyDKVMMDB3IDcJarym+Muyg1aTul5g+0SqefTYCRRFcegGkN6+xjtVFpW5NJl2XpKRYrsNjipog/MZ4WTTIYRNgQginEGK+EGKZEGKVEOKB3T6/RQghhRAJe+vDwsLiKCIiGttzy1DeWIU2qw3hWjUfpJ3Nb2kDudP3KMVr4+nV4Q/GZLr5iQGkFZUghIowJHYPBB/ZQOyOjURk59D/5ae5algrRp56KkuuXUzYt0H6Bw3iYs1s8itz4cdFsL7APLRjSTbNsu4jPe42jr/uNm5NfpaUa59C8fgQNanAvAZDnn8Wj3QhUfEEw9g5rzklC5JQqoNs2dKSjdEZbAtPRzqgqgT80yAgYVN0a0pdsdDLXFHoogpXoIrxGz+kICwdQ9HMG5QXCAooUExrVR2KZ6Wawisc00OXiRlMX6NLaq6+vUPbtlIb9CwkilOn+1MLaD9yBYMun46twsu6ookgTFefZ1Ek+k6Nrxb89Rxd8+cb+Hx1NuhAtg42AaOioU+o4rgWQVKzVHr0MMVlXBysXSx47XU7EZE6tULNhggl7xUCnnoqhsxMy+FiYVGXw/kX4QNGSCmrhBA24HchxI9Syj+FEM2B44Hth3E8FhYWjYDIaE/Wrb/gChTzRWAhv6h2cjJSOLtlOTcpPWknQm6xTn1h9CT47VvWKKmUVa1ssL+AH1ZPhU494bJzYfkyWLoGdmTvaWdRKr20O82OUCGxr0bl9mA9b1g3YyWv5l7HFWkvYfgUqgpjeL/gUr5650y8+WHodhX7eB8jkqfx1oTzqTxNJVCkMWL1TG71rocEOOm6L+jy2h90+XQO3fLnc+bJ3SlyJYNR198qoMQwjy0wLXOJYaZrscYrWKNNauLADEyLVxxwJbAiFGOVJAmLq8Q1wI0nLZwYtRRXtBsle7fZCwHbYEMnyb/eMFj0h0JUODx8DfQ8sMwOuyguAT1cNcWkMKDKgGwdVSiMmaDRfYCDT90OmqXDf18Bpc7UXS64/DKViy9yMnWqzi+/QFiYoF+/OEaOhAULNjJsWONWHbA4TFirIJuUwybApJQ19mswje82aq+nzwC3Ad8crvFYWFg0Lqm2eK61jeHavTVQFLj3vwD8OWiQmauiAYI6lJaD4RGohqT9eU6Sx8XwzQmVFC6o3qN96TqD9FEag19xkfNrFb5SiQBUO4y81CCh8n9c8Mj72M+uxgjYQBVU7Yw2d5bgq3AxwzaSjXobWoZtIZBsI35VkVkAmyD928zFdUcV7f63kkCUnXvnXc15438noDpqhZQN1JM9mPZ7iSaCeLfGQGFt4Pqu+uYlmCsh3ZhpKKqBqyW0lWbQe5TALSNxE0XZgni2bGhNnwFzcGT48K0Pq524DPVXCS9MF7AC2C75+S3J7TdD34EKr7wPT98LXdo3/JUsXgxjxwYpKJGm+Kr5noQgItzgi7dURo80Nz98996+WBNNE5x4osaJJ+67ncUxghUD1uQIuZeLYJMcTAgVM+S0NfCSlPJ2IcTJwEgp5fVCiK1AbyllUQP7Xg5cDpCcnNzrk08+OWzj3hdVVVVERFhPd38V6zw2DsfKeazIzqa6sLBBESaEIDYtAXuUDelUQVEQhCOkk9LNm/GWldVr71AgqrspGgwdKneq2EWAsEiJaoeg1FhW3M0UQC7M/z2Y7kMbEAmKMGgfs5oyI5ZqI5woWYndF4YvshozH79AGAZqVYBqNYJiLQHpNYPHhCpNQVU3xElKpFeFhqodCWpDpGqsYJGgJgbR/Q0/EzvDPOiKSmC9vf5Cw5r4Ghtmpog6KJpppEuIhYxmDXZLYaGZDX8PFIHdDl06NbzfwXCs/E42JnmFEAxAs7TG63P48OGLpJT7iPhrXERkb0mPhftveCDMFod17McKh9UpL6XUge5CiBjgKyFEV+BuzMXW+9v3deB1gN69e8thw4Y14UgPnJkzZ3K0jOVYxjqPjcOxch6LN2zg1W7dCHrqp41ACCJTUzlz+3YUtYGg7eHD+f6qq1j02msgJaoAp4DTHgTnrdEITfLdllNx7tQZ6/qEMl8Mp077mjn5g8z9e1ErYARo0k+WtoE7ez/EAmcGjxVfjEeGoRDkvZ2fkT1sCUiJgcAjwgjHzVT38czx9tnn/JSATj/PPGY9PhqCdV2VmBawDpgizAA+M0h4OBcjXqVkS/JupYhMbJEekkfuoJVnI7OeHQvrMXOH1WgnwZ7+WQz6jxe8+rgg6JGccUaQc89VePDB2vM6cWI5X33l2HPnRAcogjEj4KJTBR4PjB8HCYcQoXus/E42Jm0Gwo4ccG/ecwXqMcNhtIAJId4CxgMFUsrOoW1xwKeY0ZNbgTOllKWhz+4ELsF8DPmXlPLn0PZewDuYj1pTgOullFKYAYnvYV4BioFJUsqtoX0mA/eEhvKQlPLdJp7uLo7IKkgpZRkwEzgFaAksC1m/mgGLhRApe93ZwsLimCe+TRsmvP8+msuFLTwchMAeGUlEcjIXTJ/esPgKMf6VV7hg+nTS+vYl3AHtT4RVP0DglXKyj69g+AfTuLroFWxb/CR+VsScwoGgSLP4dd2boQC74qPcHsdli97l6e134JGmi0/BwC/toXYCHZVpchQbyaKluhkXe7pCa7vVSbblsfLpnpAtwSdr3YXVwFKgEpSMAPaJFbg+LCfs5Ap8VXtfqSiFICg15v4+1FyZWUV9zSRp4GouufMynW4d4fvvDbZuhddfN/B44Mkn4T//gQUL3A1NwByrIvh5Blx6BVx7PWS0gl9n7HWITcaGDTB7Nrtl2z+y+P06V1wxm1WrShv8fN73sGXeMSy+4HCvgnwHOGG3bXcA06WUbTCz4t0BIIToCJyFmdDlBODlkHcN4BVMT1mb0Kumz0uAUilla8yQp8dDfcUB/8YsCNYX+LcQoibzXpNz2CxgQohEICClLBNCuIBRwONSyqQ6bbayFxekhYXF34uOp51G1qhRrPrf/6jKyyOpc2fajh+ParPtd9+Ww4dz2bx5fHH5+Sx64wOGXCCY/n+SrBhYtiKHR5un8cNFT7Nh5DC272hBIMJpPt7VZJ0Puevcajh+v5MgNiqLVGhmqhopBA7hYwndCRgaCaIQQ6gUyCTu1+7nG3FqAxYnEwF4p4dRsjke/Crkhj5QMFdExoL4U8d+VxUiFNJV5E1C7egzH0t3RzVwZlYT2GZDbeHg4g7w1lIZsnrVxJdJMHa/2wv69TN/uu46hepqybhxCtdcAx99BEJIZFosu2pH1Z2ArbakQVVV7UeTL4bth9Gq88MPcOaZZlja4MEwZcrhOe7+CAQMtm2rorjY2+DncYftFv73QEr5mxAic7fNpwDDQj+/i/nXcXto+ydSSh+wRQixEegb0g9RUsq5AEKI94BTgR9D+9wf6utz4EVhVoEfA/wipSwJ7fMLpmj7uLHn2BCH0wKWCswQQiwHFmBO+vvDeHwLC4ujDGd0NL0uu4yh995LhwkTDkh81WXCy2+TcnJPjBWS83rAxiLILYTiRVUMue0KVrRvT2TnKsjAdPmp0sw8D2BIolNKMVTzMii9Aip1kEFErIci4vlNDuZP0Y91sj0ZcisSeKrkJh7efiVO6Uat56MxUNBJd+3AtygC6d/NilezOjMDlJMCCFEreqQUOBICODOrsPmqufTufrRf8DVCM7DF+XEkeyj9IRlftcK6gMT2jrs2nk0ArhofpLHrNXp0JUlJKj9vhd9LBY89rjF0qMKmTeDzmUW2fRE2slpOC9U2CnUWFvoOwiWcJMk8fyMdb15GTOcS8vKgsnLv38fvv0PzFvDccwf1Ne6Vd98FtxuqquCnnyBwlOSUCg+38dNPYxkyJPVID6XpqFmx2xgvSBBCLKzz2q1Ee4MkSylzAUL/1xhr0oHsOu12hLalh37efXu9faSUQaAc0ya+t74OC4dzFeRyYJ/pj6WUmYdnNBYWFn8HFE3jii/nEzzVgRbQKXGDEdI1hg88hRKfrOPaE2ZeL/yS6MRSWg9ZTf7WdErz4klIy6Ncj8SbbOaNkELBEBoxlJJKHqow0AjSJmYDSU9P55o/BjF90g1sPGcCulSI1sqJc5UQYavG3TyK8uUxyECNCJNmklYhUTWdG/o9wxv2iwlgDw1LoiwxsGk+woa5qXo7lUDLMCJ7FyMMg9K3UzBCiV3nlAn4MhxuAcowrVc/YuquYh9UeRl2vMKPP0Tx8Dx4bD4g4MKO8OJI0/V40gSdYiNIm6zP2T76OBgpIVfAz5rZOAwIExCUFP2ZwMmvzqLbfYvI+TaLFSUD+P1VlaFDBP3713+G/3kq7NwJH34E11//17/f8eNNK5gQ0KEDHKQ+t/irNF4MWFEjBuE3ZH+V+9h+qPs0OVZmPAsLi2OaFW+9Rke/DgL6ZcDvIRdZSizERkHn4pXMU/qBVExXnapDjEpcpwJsWpC0NjtIa7PDXOFY0dZc2aiAYQikNNdA1iCQbNDa0+qhE7nMM4OUATfguPxPXJqPH8VYdpAOKGRM3kzpwgQCxQ7TLuVXIVVic/p56/yLKSaO6NWVVLYPx4cDsRTkBhuuUh/F/03lk4qvEIoOXpAeFVoK04eQhxlDFoV59U4G/MJcVz5HQpiEuBh6DhQoCvy4FaqDgICvtsElxdCrF0zbXsqEWSWUb2lG5eA005rWCrg4CFNC2WJ1QAqqNkfz2VfnYGgqLsXDkEsMjNmAKrjiMsHD/xbEx5vn59ZbICmRRktFccEFkJkJ2dlw6qmN06fFMUO+ECJVSpkrhEgFQmmY2QE0r9OuGWZgwY7Qz7tvr7vPDiGEBkRjLofZQa2bs2afmY07jb1jlSKysLA4ZtEDAb6/+XaqQqE4Q1rB5L5wZne4YByIX+F+730446tQwgOoCV6EB0Dg2+DChQcFHVUGsH0ZxPNdbS3FMMND/4J5lJbEsMXTEkMKAlKjSkTwrTaBvPBmHPdsBNG2ajShYyNIBNUgJVpEkJ6v/Unb25bT6rTFMCKI1ttLdPcy7t3yfyzQe3Ki/iOnLJtKwpwy+g/6g44TllH8QhJ6gQ28ApYqyK8U8xZxOTAJeB7Ix0w7sRH4CjNaZSFm0tdWTlDLePIucw439ACbHYiCEhUG/QBX/wGtiSXF4WFnn74h9yXm3cBJ7WO5HZIzcmnVcz3KJtA32KmaF42xxAG6DXwar70ICc3h4kuhrAyiouC666BVq8b7jocMgXPPhfDwxuvT4gCoWQXZGK9D41tgcujnydTmCf0WOEsI4RBCtMQMtp8fclNWCiH6h+K7Lthtn5q+Tgd+DeUm/RkYLYSIDQXfjw5tOyxYFjALC4tjlm2//YbuD/Dlcji3l+mFSwgHexjIdiCdMMY2jZeMa3k1+TIWr+2DLNbAD4UVqZzm+RTDENhFgC/+O4nAdjucJnmi6i7aBFvzftG/CWDnuMQZOG0eom1mAJTAoEKJJWFIAL9hQxEGI8U07NLHd/pJbKANQhF42rvIzUonMqqU7vZF3KC/xKMf3s0n35+Lrmu0HLaB9mNWoDl0qrdGmlWGQsiAgqPIjf89J9ITEkkbgZoA75pVapWYV3IzyQ+kR/PsLLhpOJzRDm5YDDke8IZWEb63ESa3Vnm3S3taThfQ1QB7qOC2l9ANU9Ki2RbOHv8exkQFVeh89/oEVj3WHapEfSeNV/L2p/DVl4K5f0D7vSR9tTjGqPn9OgwIIT7GtEQlCCF2YK5MfAz4nxDiEswqOWcASClXCSH+B6zG/G29JpTiCuAqatNQ/Bh6AfwXeD8UsF+CuYoSKWWJEOJBzLh0gP+rCcg/HFgCzMLC4pjFU1KCUBS2l8F/ZkGreAjoUH5qK9qOCmeYshxVwsWB9zmr4DMiN1fteiIPYGfKtJNJnJnP1lmZFK9OoPvJS2ihbuHKqjeZyyNEy0qCqNxR9RT/sf+L8Cg3AkmEUk0GW1kmulFQlUj3yKUkywIUIWmnrsdNONdVPEt5TDRxSiUqcCMDeODV/izLiQKh4oj30GbMGlSbGZ3vbObB8NdRYJpBZMcKbL2Kyf0o5HGJpDadhsB0mBQTKm8kYCeQLnhupcFNw82+iuvWeATcOvxRDDcmOXi+ZQn/WhZuujCDAhZqIAWqLcDogVOwq4FdCWZPOOc7Vl3frcHVlrglZfYgp5yisXbtMZ5+weKwI6U8ey8fjdxL+4eBhxvYvhDo3MB2LyEB18BnbwFvHfBgGxHLBWlhYXHMktCuHSJ0t/cHYXU+bCiCgnc3E1DNOChsZrYGP3bajViGYgsihEF8dBFnjfiAHtcupNeYRZz8wNeMf/cbeoQtQRG1BSUVdJIooKoqhgV5A1ha2Jubg0+yhg7MUIeR5MgjXLjZJFqxneZoQidSVHBP1CO4Znp44NEb+Cz7PFIYy+2TLmVwx99AgWZ9ttabiyvdQ8enl6I4dBRXkLDmbrq8tJisW9fXNmooPVpdsRMNKAZt02uTZvVLBK1OGynhu9Az/nVd4tgyzssFcypRzrLB5wKmw/ln/JfUhNxd+wSDKh+9OXnvdwxpLm7Yni1Z2EjJ048lAgGYMBnaHwcr1xzp0TQSjbsK0qIBLAuYhYXFMUty167EZGVRuGoVSEmnFFidBzIgyb9lOdufTaaFPx9DKnyROY6R8dMJD5RTVhWJEqHw5zftGa98zgl3TCVJL0Kt1Pk5fiRF4bFIBAFUDKGiJvspLEgxE7V6JHfzKCnJeagECTjs/MhYwHRNauiM4WfasJGx7g/pdMN6CFcQQMvkzTxw1l3c98lj+DLUXdavGpqfv43UCTsIlNlxpnoQKtjj/ObKTQOoCLkKazJOlGBa9CRgl9BSkprl5X/jamPZPh8BE6bDnAJAgC0WusTUHjNTi+bdy+Gp0+Cdz2HKglJs7vq+p7VrO1LobThLP2Cm98CDNxjGqRdozJ8O6Y1YhudoJRCQPP98JS++5GbrdhvYXbzytouXnvgbmACtWpBNjiXALCwsjmlO/+QT3ho4EH91NavygiRHQqITBi2VBH7xMXNYVxZpvYnaUE67mOVc3iERdctJLHvpObTSLxn12ypemH8hhZ3bED3ajlMIpmSMIHWTk7XJrVkf1op7yp7AI53Y8HPJztfQWnkJGDYcfi9b7K2QikDBCMkvjQX0YTCzGdlyulmssg4uu5fLj3+J5ysbztOgRehoEbUlmqQAHvXDFzYzkasdM3DeAayVtTUuMyH8V8nqm8KIqZN54w9XPr3HF3OTL5m5m+OJ0uDWrNCHld9B0f2Q/AKJ8QO49Qrodnws1/8xlFNSv8RuN4WYpgbMNBqDgNnUjw0SQKKE/HwQLckrhIuvg5+/OOSv9JhhwIBCFi70AzFAGHhg2Z8VmKZIC4t9YwkwCwuLY5qkTp24ctkyZj/yCCs/+ogCtwdfQgt2XHctXbWt5G2ZQafhm/DFRaAJG605GVfLODo+9X8EvNcieqRx37fvsGZ5O5474Uqi9VKElkqM6mRBbE+mFI+lywNPM6Awh7h/d+fxd59g7pY+FCXGE65XM3XcCGLCytBCvpZqwsknGS9O4vz5KJprjzGnxORRsCCF2IwiNMe+fTRlgRjEeUGYFESuVWG2DYRAFQadRq6mdGAM7vl2iv8vhaCmYtQxqq2gkifZjBeDBY5yPu3QnWbUGU/pc+BbDOX/hbABABzfEvpubM2U78czZOhMwsPdSL9AuCX0DZVBWhRKU6EBiUCEhFwXOAWGAes2/rXvtDFwuw2mTXMjJYwaFUZ4eONF3BgGnHSxPyS+wFw+qgAGc2brFBToJCXtvZzWMYNlAWtSLAFmYWFxzBOTkcFJr73GSa+9tsdn3Q03OeJPDBEklX446lgnbM4k/I+8R/Cmc2m9aR3PHX8rT8z7F+7wMHzl0HL5Rjqt/h/Khz+BTydj2+8o7SUDZ80HYFHPrqhSR5P6rsBzFx4CusaKnEwipy0korMDtY4VzDBgzY6O5CxpQfsTVu5zXsGAyuYZ7ZElLkQ/H0rXANF9imnm2okLDx+UX8zliS/hTwxj+aoUJreDJ3+Du0ZDpBPKCeDJcbH65bYESu3cdpzBB+eYpX0ASH4Byt+C2Ot2HVMIeHd0GCV0YD2x7Njk5OnJaeg6qAQ4L/NDpnQYS2EgubaMkV9CuzRQBDYvDBso+fRTybp1ki5dwOeTOByHzy03dWo1p52Wu2ueug6ffprKuHGNk8ti5nyYNquuGbACc3mqDvjYuDF47Auww7gK8p+KJcAsLCz+1mhKGC0YsdfP7RPOoSwlk/UXTKRiSz7De75MwWsDiFAT8V6ygLMmwZcSDA1kvptAa1NzCAHfLhyCrSSAzR4kaNPAMDAMhcDdc8h9bTEVdoOUC+NR4zXQDKSh4g04eGHKjQS9NpZ92ptukxai2ve0ggUDKjnrm1O03aydJGc74UQ31f5w1BgDQwo+izibE0UzTovK4I9T4YpPIGhAmQdemQT9iWXTsxF4i2yA4JvfJe+3hMkDQwdxdICkJxs8L3GE059W0Ap2ToOn34XScjsXT7yIp5rBqVdI5q6SZkaKKBUZUqCGS/LZNIMv3jeoroann5a0bBlkzhyNli2bXoSVl+tMmJCL210/ofkZZ+SyY0dL4uL+ujBKiAXhtNfZ4g69zN+LNm2sW6vF/rF+SywsLP7xxBw3gL4b8shjM5tYSAbRbJ/iY9lKlflLTXEkge05knemQ1wk5JZAlP81qk+6hf7N57OwTw8iqqoRPjfehFIqDD+uCo2dIwrot+AWPNoaXEprsvPOwyFbQBDyV6Sz0G+n48mLCIv3YiAQQNCjsWlRe7avzYJIAT7MGksFKqSbZomgsPO9azxz6IQQgsWhq7kQ4LDBf3eAJgTu0lqh4PYL1uebVrjvF0BhOYztBWnx+z4/yQnwxM31t/3+hSCnELJOAp+/drsuBe4wBTwGSPNY+flw1lk68+Y1/S3nhx+qay18dVAU+OabKi666K/HZ4WpHu68xM/LzzsoyK6T50PAueeFk5h4jFu/oHYVpEWTYQkwCwsLixApZJGCGaFeGTaT8S++xNSbbkJoGtpxXVgeEQ1fTCEnlMYhUgmwNKkrt//xGP0WLCLo0Pjp8uH4rmqBsrKU8xZWYdtZgFY8CRHWAoCsDFh5A8wohKc3gePfd9Dx6g/ZMWow0z58iapgOGWfpUKWAn0wb4QKUAbSkETaa6th+wV4MAhDZUAruHEUxDqgfSc4Y4XZpm97WLQevAGznyUaXPAMfDPP1HT2t2HJs5CZvKtbNmTDxDvh/kvgtOF7P18bt4PTXl+AQWjMdiC0lsAwYNkyyc6dkrQ0wV13wUcfwfnnw0MPHcIXtQ/8u4+lZkhy758dDK+/nscNN2xB0wTJyTZufrw1r79ezaZNXtq0DvDeu4etlnPTYq2CbHKsPGAWFhYWe6H3FVdwV3U1d5aXc+tPv/OfB59CU01rigK4TutKoJXKczP7s6ZTC2af3Q9pFwhFENvKgfM0N3TKhNi4PfoenggP9f+J478IkLTgBFK3rsKtR6JuL4d2EpKkmfdLwzxYDODSSAwvwrvWYE1bH0vjvHz4Vj55VdDhFXh2KayqhLYRoYwRGkSeBOMnYSZt7Q0/eeDTuVDlBbcPKj3w1rT6Y9uSAys3w5+r9n1+OrUC795EzW4JYDUNqqpgyRJ4/nnYvh2eeQaWLt33MQ6WsWPDCDYgHAwDxo//6zFgd9yxDY/HoLJSJzfXT0qKj7lzE+nWrZwLLgjblZfOwmJ/WALMwsLC4gBJ7NCBmwqK6dwDzrsBPKqb5pvmsOiCS1g/tC3F8XFMlcfzrXMiEV0zMCIVtA/yEI6cPfqqpJgFfAkRKrbOsaT9ehUebziXnDvBzHav7nYjVwQEVTR0sq8I4Nso0Uvh2qs2sHxbEN2A6gD8sQPahMOOIaDEwE9VMCUWho4BNQ5GJWHmEAuhqRDmqH+o0f1g8+fw2FX7Ph/xMXD7hRDurNkiTbNarlHvGAAuF7RubdZ0lKHwLCkbv8ZjcrLG888n4nQKHA5wOMDpFDz1VALp6X/N6eP17rmYICxMITHRxtKlPbjnnuZ72fMY5MjXgvzbY7kgLSwsLA4CV1wc46+8mMW3v0W3ofmsHdGS06u/RthV5tGPXFKRisrb4y+j1+uriZZVOLzzwNZ2t57qBIkrgsyEGMbPK+b7d98GPWRi2+0RWREGgYAdjOp6u/dJh0mdYE42vHyiuS1qt6v7U92hVR+IscETxXD/J2BTISUWrjxhz3m2PMBEqg9cCQO6wtvfgqoKsqJ0/vN/Rigk3Q8YuFw6L75oQ1UF7drBO+/Ahx+aLsg2bQ7sOAfDZZdFc/zxYXz5ZRWGARMnRpCVZftLfQaDknbtiigqSsTpzCMYlAwfHs2ECfsJoDtWsVZBNjmWALOwsLA4SLTJr9L+uWn8+O12Yu/7lgX3D2aEPgOf4kDWqCYJKzt2pKt9FZoavUcVoUgS6MF4lvIDYcTwxIquzBaZoGQCdTLe19nRMFSqK8LIeLWKLeMCKEWCJ59sRWyMxn9Prt+/IuDH1vBkPoyNgt51LE23nw5nDoKiSuiaaQbt/xXGDDBfJirJ4Qb/+pcXKfOBIAkJ+UyalLGr/Zlnmq+mJDPTxk03xe6/4QGi61BYaGCzhfHmm90ZN85GdLR1C7U4dCwXpIWFxd8SaRj477gZb+9OBF5+rlH7FjYbUfPWMPKue2j91moih71HqxnbufajVwn3uVEMnU7b1pDdPwWPcBJwNRzJ3puTuZTXqCi5kDnbBqI6gvXL/dSxcglFJzKylJwtLUnIjGXr1uOorBzCpPPS9xqH1VYDtQD+sxjOWwDldSwaLVOgT5u/Lr4a4vjjFWw27673RUUBevUq5j//CZKdLfdov22bn6yshWRkLGDDBt8enx8NOByChQvj+eyzGM4+2/nPEF9WLcgmxRJgFhYWf0uMr79Af/V55NrVBO++FWPFskbtX4SFkfh/D3JZbi73ztlMXMo4smzbeeOrq7l60Suktsgm2VPMt6n34hSRe+1nu9/g0fmxJIXnoSj1A6eSbHm0dq5D1QIkJOXitLmxIZhU1Q5blZ2+d0Dq5RB1ATz6Vf1+dQlDf4Pv82BjNXy2E8b/0ainYK+0a6fyySfRZGY60TTBPffEU1oKN98cpHVrH1u21J/n7bevZ8uWVWzfvprrrjt6q1l37KgxbpzjnxNoLxvpZdEglgCzsLD4WyK9HnYthwsGwePZ9w5/kfhuL2I/YQX6uLls7XMdhfZ+FMRew0XKhQ2PT8KduX6yfgiSnZdIs4jtJDnzcAgvYOAQXq5Mf54321xA/3YziQivpCwnkRRnIbEs56fvL+b8SVdy7qOv0rzLBh7+An5bXdv/djdkeyAYugH6DZhbAu7DFBQ9YYKdNWvSiIgQZGYqXHJJJEIIdF1n6tT6g2jd2kwUC4JWrf4GObQsLA6Af4AN1cLC4p+Ietokgk89itywDjHieESffk1/0Kh2RACX0HO/TW/d6ee5aj96RTgYgp0FGdzT6x7WlXWkNBBHn6j5dI5YgSEVepcu5qPsLtzS/WHCNC+Db/6ApM2FALz18PnE3lLM90+fxbJtrRjSMTQUrVZ81aACjkPQN6s2wRUPwbDe8NA1B75fZaVBebnBpZcWcNddcQwd6iQQgIkT6996HnywLdHR4PMZ3H13+732J6VESlCUf4gFyuJvjSXALCws/pYIhwPn4qPPnSUlPFmg8/RGYIUD1gCFkBuVTl7bdE5tv5svUQhOcEwhpmMJDpsfISBxWzF2X5CAXSN5awFbO2fQ/8xfmVqdRy+aMYAM4h1waxt4NlQYWwJPdN4zu8WBcP+rMGcZzFsJV54OzZL3vw9AYqJGmzY2NA2mTKliyZL6KwY3bfKxY4efoUMjufXWdvvs6+uvCzn33DUEApJHHmnJLbe0OPiJWFgcRVguSAsLC4vDyPXZcPvjgva/rCdtfR5sAsrA1byatb72eIP1k3IZEtwR4STYiygTMQBMv2wwfqdGYbN4lg/tDEBsejGOblt5kbmsJA+AhzrBjwPhma4wczBc0+rgxlpQAl/PgD6dQFWgc2tI3jOn7D6JjFT49ddmvPbanqrt+ecLuOOOPXOk7Y6uS84+ew1ut0EgILn33q1kZ3v3u5+FxdGMZQGzsLCwOEzs8MOrCyTJJXmc8Oy3PHvmnSAFrY9bS5e7FlGmRrJVySBLbsEIKtg1H37hoMidwMrV3ZipD2Nwh1kwFpaN7UIFUUgUpISgy7yc+9GZwzY6kwLA4ATzBaaYE5j1IvfHxu3Q53wzg3xQhyeuhxvPO7B9d2fwYFeD2594Ih2322jwMynhiivg66/h8cclwWBtO5/PoEuXP3n11facdVbKwQ/IwuIowLKAWVhYWBwmplaArDAYPekH3vBeiqIaTDzvE+67/14m2r6im7qcr8VEPhLn8JP3BDbprZi+aCSbPuzI8K2/c8n6d/n9uRHMmD6CMl80EoVgUMWQCsWY7j0FCGPP3BLPrQPX5xD5BXy3c/9jffYjKK+Cimpwe+Hfrx2c+NJ1SfPmG9i4ce8FGB0OhdjYhu0AhYXw1lvm///+t8Ltt7fA5VJQFJDSoLw8yIUXrsIwrGV2TUNNJtbGeFk0hGUBs7CwsDhMaALULIN2GWvpGptF8BIHJ57wHTbFXBXYiVXMdQ/g67VnEgzYOMX3Oa+r16J0NAjTPPgNjWuyXuGp9Tfz2TsTad95NQVVSUTGV5HZexMFpOHCxljqx1MVeuH25eZKSD9w7p9Qcdq+x2q3mTUv9VAeJ+0gg/eFgLQ0DU07tID5hATo2xf+/BMuuAAeeiiL889P4bLLVvP772VICZqmHJJFzsLiaMCygFlYWFgcJsZGAVEqVZGRpNt20nnicqpFOLoU6FKhjBiWre5DRVUMbl8EX3MmqqoTppkpNOxKkDDNw01t/0PzQC6fX3cuvz12PHmlaXQLrGPj1g5MX96fkeuLeDq3ihrj0O6rIQMNe/3qcesFkBQLUeHgcsDLdx7cXBVFMG9eSzIzDy3Tq6LAnDlmAe+HHjK3tWsXxkcfdWbQoBjatQvjm2+6/XNych12rGKQTY1lAbOwsLA4TCTa4J5UD9+XH8+pMZ+ymdastHekDwvIE6kspDeBYE1OLNBR8eDCRf2A8wjNzV1Zj/Cj40QISprHbMftU6iSdtp1XA7AjwLmbunD21mxpLpsXNsantso0THo1nMjef6WXPW5HU8QPjod4sLqjzU1ETZ+Ays2QnpS7crH0jIoKoY2BxnQvy90HW5/GAIBeOo+sIU0mxAQttu4mjVz8ttvvRvv4EBVlYHNJvYotP3PxioG2dRYFjALCwuLw8g9KeFcFVdBQUUqJ1b/wNmVn1JJNCoGzclmTOtvsQk/DrxcqrxJnChtsJ8+0QtYcll3ktvkMrTNdH7aeSJKmM6OyhaUqLH4VDvbYjYwonIRV7OAa3pUMeqk2Qw8ZQbRWdsYsi2XbwqCTC2Aa2ZAQ6FUYS7o16VWfG3Lhsxu0HUQPPRU452TOQvgxbfh9Q9g2uzQtjkBLr20iilT9h5D1hhMm+YlISGH1NQcsrMta43F4cOygFlYWFgcZibHjGWDx0/E+mdY16ElmvDzPadjSIGMV7i3/52Myv6NfoUL99qHXfjpmLSK788Yz535DzGtdCyiwlRR9mg3cW3yCXe58e4IZ2XkJq5iPj2c0SzFh0dCdVYAW9sA/h0qX+cJ3lsPF+47FReLlprWKq8Pvp4C99zSOOejawdokwmBIPTuBkuWBBk0qBKA//7Xz+tvhOF0CEpKJEOHanTv3ni3rilTvPj9oKowf76f5s2t26JJjQvSoqmwftMsLCwsjgBtbMORpSV4s21MzTqeIBqGMCPdV27pyklMQQph5mOoSxToikDkSuxqkDa2jUwvOwGEQBqmC81fHoa/yoUMUxCaeSv1ohOLk8foxQTKCKoaht90gkgJJQdQA3v0cOjWGdZvhIfvbrxzERMNK2bUvn/x+fpWr8uvDIJeswrAw403Kjz9dDifz4LtBXDhGIiPPrRjX3ttBLNm+UhJURk71nlonfwtsVyQTY0lwCwsLCyOBFoUYqGTzJ05RKdXYiOAz6kidJ24glKyHs8m/8EE4sorcDpD6sgG0g5CSKqcETg9PkoiY1FUA12vE1EiJIauIKUgMsG0JOnAHxRxG504Q8BHspq4oSWkzU6mU4Tgig77H3JEBMz5qfFPxe5MmmTnwQe9tdpTryvIbDzzjCSlm8H/faoQCMI7P8GKtw7tWFlZGosWHWBqfwuLRsQSYBYWFhZHCkd7jBWLuNzxFnmxacwZehzp2Tncc8cTON0+7v/l36yZ2Yk7JjxOxxarKamKJSK9CntkgKjqcuaIAbyVfAEJeh4FJalIQ8W0XIA9wocQkqiI2hiyKgnJgTx+0uK4RIkkLlYh4eSjLxS4Y0eN5cuj+O87fp79jwBZt5B6AAjjt3lBqr12ANZmH5Fh/s2xLGBNjSXALCwsLI4U5/yPwPODef/qHC7lDp5wgE2BgCp4/9LzeSbsJqhS+en9ExmSMoOR/X7mh/+exLr+rSjvZmaAH2j8SkxaAWXR4QgDWgU2I+OhRMThEm6cwrSeaQhiZRw+wAv0aCBZ6+Fg/vxi0tJcNGsWts92nTtrXPEvjWdfDEA996gAJHdcrjL7HvD44eYzmnLE/2SsGLCm5Oh79LGwsLD4pxCfhbx+BaXFgq8KYUEVbPfB8uFpPDbmDpimgAods1by2esnc/M1T/Ld+ydw84xLQEJ8Sh5b7FnkbsskcrMbvVBjm6sFZ2qfcKH6FmnKTrP0EBCBxmuiLatEEt9st3PaWng2B/TDmEheSsmoUTO57rrFB9S+ZQrED9SAMMzblQq4SEkJMqi7Sv6XkPsZPHpZEw7awqKJsCxgFhYWFkeQYocAu4Lu1fmlDNQWLrpOboEnxwXRQDm0TN2EYZjPy0KVTLn2DsiHUiUeI1IDRUC0hBzQCxReGXA16epOOskVbAy0YYevGS0jisklyOkrHWzxgk/CT2Wm6Puw7eGZqxCC778fTPPm+7Z+1VBcCucNkfyiK5Tl25EBSSDTTscOTsoqYf4meHEKnNADrh7bxIP/x2G5IJsaywJmYWFhcQTZlr2YjI97kNACEKBv9/DLBSXkxDSDi4ErJNPKj2e9vx26oTCvuD/LErri7FOBSNBhu4BFwDoBsQKjMgxUgS5UspVMwuxeukUup7wS7tDXstNnii8AtwGfF0PJYbzPDhmSRMuWEftt5/FCt7EGzz3gZfUsSc5aQUovB0VuhTnL4dVv4JTH4LupcN1FMHIcVFQchgnsBSkl5eXG36g2pZUJv6mxLGAWFhYWR5D5F1/KsDccfJtNTfw880++CkOqgIA0ie9iJyN2/kaqaxuBdDu2VDdIgf9jF5RJCArzcXoD0A8cuodorQIQ6EKjWobTLWoFO4NZpMZtQXNHUupOAMzd/EeJZli0yMe337rJaGmjODqc4hwdpAYhR+qSL/wofVWCukAEQa8GZoEB/DoF4lNhzCXw+ZPgdBy+ce/cGWTYsDy2bQsSGakwdWoyvXodxgFYHJNYAszCwsLiCFK9LBe3vT1Kl0T05YUIQA+z18Samy9FwVDt5PzRCqNERdgMREQQo1QDXUCUNJVUGbBeYu8eQNhlTUUjpFDJkykcp80hJSsbISRzNg1hZ3FbuoRD8pGJx9+Fxwu9xvpYOzsPDInQBKKrH6mEh1oIECqgYizSIUnjoYdg5EComxUj6Ibp82H2Eji+f9OO2TAk06bl4XKF8eijbrZsCaLrUFJiMHFiAdu2NW/aATQ5lguyqbFckBYWFhZHkCF33M2iz4KU/XwlVZf0J6KniwndvuX820cz6YGJ2GU1qCClwFBMq5gMqBjFdrNYYmcJI4HhQG9Qygx8hgNB3YrbBrGU4hax2LQAmhqkR/oKJsTB1I5mN0eSHXmwdrkbqUukBCMg0ddVQ1LINCcwq3MLFQwVDFMenDhqt45UaJkOfTo1/ZjvvHMpY8Z8zZgxfzJ9+nZ0vfZ85+frTT+AJsdyQTY1lgCzsLCwOIIMufdeepx1F1qpRuYbHWm9cBCJsxbTct6vtJ/zLb1/fh2ncKMRhMo6SkkK897WFtOXoQEZYAv3U+qNIVnmoxLEJv04pB+H0KnAtCjZUBkWTGXUDvh0Buwobvx5bd7spV27Raxd66Gyct834TaZMHKQbZcSVFQgWoN4G4hyEHUtMQKKJAldYXMmcCEQByIefp4Cq7+AmMjGn8/uzJqlA4l4PE7AwOEwk8U6nXDiiQe2yMDin40lwCwsLCyOMHG2L4laXU0iRfiFE9kzGWm3oSqScwf+wLUpz9K/+g9TcIUDNeFFVZg5snZljJdEtijhgvh36afMoz9zCRNuikQCG+lIb/rTnQw65/fk/huO4/q34MZ3oOONsGJb487pf/8rYtMmLx6PwezZ+4+O79k3HMIiiYlVGTrEwc75iaQlCOgbB2qdIDXTRMa2xZJtCyVqL7A/CC/OhNGjG3cO+6Jduyjs9jRAQ9PgX/+K5YQTnNxwQxQffZRw+AbSZNS4IBvjZdEQVgyYhYWFxRGmvTtIB2UJy/J70yp+I2EXt2N92CR8ZVGMaLWCvCUp/L5yCHTBfGyuuTd6gPlAZ1BsQaJLSxh9wk9UiygWchzraL3rGAqCHjSnL12Y8C6Uu6HGayaAK9+An+6Be36A1Xkwpj3cNNz0/B0Kp50Wz+uv5+F0KgwaFLXf9o/cIbjozDjatY7b5RJND0BOhWEG4htuEDaQBmhBEHa+el5CK1BdMPT4QxvnofLcc1lUVRmsWuXmppvSuPzyv1s5I6sYd1NjCTALCwuLI4ya+SzDcjpTfX85n5x4NcVaKmWbvKxLGs/XZypgA4YBnTGLOiqAH4iRkAiq4kbESYZ2m04AO3GUMpJhPEEpGgIDyTiS6EsMANuLasUXmLfanBIY9RIs2wm+IPyxGfIq4KkJDY95506DDz7w0bu3xsiRe0bxt2njYvPm3sycOZOoqP3falQV2repv23ZWiCgQVABNQi6F1QBSWG1ixR2guo09z+cxMRofPFF+8N7UIu/FZYAs7CwsDjSODKJ6z+Ds4Mn0e2TG/C09JJ2tY3z53zBrGGjYCuQAGwVoYB0oAKEIpHFAl1zokT7KA/GEmcvojdRPIikmigSUHmaVPoRvetwQzvCmp1mGR8AhwY9suDHkPgCcAfg3fl7F2ADB1awc6eBzQazZ0fRq1fj307+NRmeeUuiCwGucIgLrfass2rgrBPhlJHQPqvRD/8Px1oF2dRYMWAWFhYWRwOuPmjH57FyZDGTnlnLupdaMrTyF9PqNVgQMl6Z90UdCJPYEz1mFvxCBWO+i60FmdgI8hqDKccgCBSh8x7l9Q71yDkwuIMpvJw26NESnr8Yds8hGulseKhSSnJyDIJB00W5fbvRcMO/yJO3w9yPQTilWUk8KMzFBxIwJN3bCD5+2hRhFo2NtQqyqbEsYBYWFhZHER06CAq9aRz/wEJ4RYNkYbob1T1zRfiKnJAOZgp9Sf7ydHo3a85SapVUEMjezZLhtMNPd0N+memKTIszjUr3j4WHfgZNhaABr5/V8BiFELz+ehh33eXhuOM0xo9vukRifXoK3n7F4KJrJDJPMRch2KFTZ1j00353tzhkLAtYU2MJMAsLC4ujiB49BCNGCL6fKiEKs/50Q/pGAjtUSCXkyxB4iiM4MdiLDVols6nCh8SF4OQ67scahICU2Prb7hwNYzvC5mLo2Qwy4/c+zgsvdHLhhXsxkTUykyernH66ZM5ciSEE/XsLYvackoXFMYUlwCwsLCyOMr76SqXv7ZIlW3Vor4JNmMaIekYwAQVANRDKe6UiSDNieY5oXqKQNXgZTiRnE7vHMfZG92bm62gjPFwwetQRzhj7j8NyHzYllgCzsLCwOMrQNMGfTwiG/raAxWu74jecZsFDO2YMFJhlh3YA4bX7ZUQIomwgULiJv1taBIvDi+WCbGqsIHwLCwuLoxC7Ctek9qVb5jImDX+P1pWrYCmQD2wCpgBD2HUVd6nwRM8jX1bIwsLiwLAsYBYWFhZHKee2Eywr6s/zv/QnqALJwBZwSVBPBxFKuG5X4ZneMDHjSI7W4u+FZQFraiwBZmFhYXGUIgQ8OQiu6wbfbgZdwtgMaBtrrlJcXmq26xoLmuXPsGhUrEz4TY0lwCwsLCyOcv6/vbuP2aqu4zj+/iBE09RKgwxSKCjEaTzVcjklRWdNNx9q5R+ZYQ+Yzhnpysxl6ZY2mUoai9Uymiug5tQoKgwqGdkMHaAoAZFDCURdk2eNb3+c39UOZzdw3xfnPtc5F5/Xdnbd53eevteX677Pl9/vnOuceDRc84F92wYOgAkHuEvRzOrNBZiZmZkVeAiyv7kAMzMzswIPQfY3XzVgZmZmVjH3gJmZmVmBhyD7mwswMzMzK/AQZH/zEKSZmZlZxdwDZmZmZgUeguxvLsDMzMyswEOQ/c1DkGZmZmYVcw+YmZmZFXgIsr+5ADMzM7MCD0H2Nw9BmpmZmVVMEdHpGPpM0kvAvzodR3I8sLXTQXQB57EczmN5nMtyOI/leH9EHF3VwSQtJPu3K8PWiDi/pH11jUYWYHUi6YmImNTpOJrOeSyH81ge57IczmM5nMfu4yFIMzMzs4q5ADMzMzOrmAuwQze70wF0CeexHM5jeZzLcjiP5XAeu4yvATMzMzOrmHvAzMzMzCrmAszMzMysYi7AeknSJyU9LWmvpEm59nMl/V3SyvR6dg/bPixpVbUR11Nf8yjpSEkLJD2btru9c9HXSzufSUkTU/taSTMlqTPR18cB8nicpMWStkm6t7DNZSmPKyQtlFTW9yU1Vpt5fJOk2ZLWpN/xS6uPvH7ayWVuHZ9vGsIFWO+tAi4B/lxo3wpcGBGnAp8FfpZfKOkSYFslETZDO3m8MyLGAOOBj0j6WCWR1l87uZwFfBEYnSZ/OeL+87gLuBm4Pt8oaSBwD/DRiDgNWAFcU0GcddenPCY3AVsi4n3AWOBP/Rphc7STS59vGsbPguyliFgNUOwwiIgnc7NPA2+WNDgidkt6CzCd7IQ3r6pY66yNPO4AFqd19khaDgyvKNxa62sugbcDx0TEsrTdHOAi4LdVxFtXB8jjduAxSaMKmyhNR0l6GTgGWFtBqLXWRh4BpgJj0np78TfmA+3l0ueb5nEPWLkuBZ6MiN1p/lZgBrCjcyE1UjGPAEh6K3Ah8GgngmqofC6HARtzyzamNuuDiHgduApYCbxI1nPz444G1UDp9xngVknLJc2XNLSTMTWczzcN4x6wHEmLgHf2sOimiHjoINueAtwBnJfmxwGjIuIrkkaUHGqtlZnHXPtA4OfAzIhYX1asdVdyLnu63uuw+B6aQ8ljD/saRFaAjQfWA98HbgRuO9Q4667MPJKdf4YDSyNiuqTpwJ3AZw4xzEYo+TM5jsP0fNNkLsByImJKO9tJGg48CFweEetS8+nAREkbyPI8RNKSiJhcRqx1VnIeW2YD/4iIuw8xvEYpOZcb2Xf4djhZD07XazeP+zEu7XMdgKR5wNdL3H9tlZzHl8l6ax5M8/OBK0vcf62VnMvD9nzTZB6CPESpG30BcGNELG21R8SsiHhXRIwAzgDW+Jdh//aXx7TsNuBY4LrqI2ueA3wmNwGvSfpwuvvxcqCvvRYGLwBjJb0jzZ8LrO5gPI0U2beAPwJMTk3nAM90LKAG8/mmoSLCUy8m4GKyHoTdwGbgd6n9m8B24KncNKSw7QhgVaffQx2mvuaRrJcmyE5wrfbPd/p91GFq5zMJTCK7w2odcC/paRiH87S/PKZlG4BXyO4s2wiMTe3T0mdyBVkRcVyn30enpzbzeBLZnX4ryK7tPLHT76MOUzu5zC33+aYhkx9FZGZmZlYxD0GamZmZVcwFmJmZmVnFXICZmZmZVcwFmJmZmVnFXICZmZmZVcwFmFmDSLpf0q8rPuYVkvrtAb+Stkm6or/2b2ZWRy7AzOxg5gLvac1IukXSqg7GY2bWeH4UkZkdUETsBHZ2Og4zs27iHjCzhpI0WNLdkjZL2iXpr5LOyC2fLCkknSPpcUk7JD0haUJhP1MlPZ+WPyLpy5Iit/z/Q5BpqPBbwClp39EaPkw/f6Kw7w2Srs/Nj5K0JMX7nKQLenhfwyT9QtKraVogaXQ5WTMzqwcXYGbN9T3gU8BUYDywElgo6YTCet8le1j0BLIHID+QngWJpNOBHwH3kT1k+mHg2wc45lxgBvAccEKa5vYmWEkDyB68PIDs4cFTgVuAwbl1jgQWA7uAs9J6m4BFaZmZWVfwEKRZA0k6CriK7LmYC1LbNOBs4Gqy50G23BwRi9M63wEeA4aRPUfuWuD3EXFHWneNpA8CX+jpuBGxM/WGvRER/+5j2FOAscDIiHg+xXMd8JfcOp8GBHwu0nPSJH0J2AJcAMzr4zHNzGrJPWBmzfReYBCwtNUQEf8FlpEVOXkrcj+/mF6HpNcxwN8K6z9eXpj7OBl4oVV85Y61Nzc/ERgJvJbujtwG/Ad4G9l7NjPrCu4BM2smpdfoYVmx7fUelrX+86X97KMdkYurZVDu5+KyngwAniLrCSt6pb2wzMzqxz1gZs20FtgD5C+6P4Lsmqln+rCf1cCHCm3F+aI9wBE9tL9Edk1YK56h+fkU1zBJ7y4cK/93aDkwCtgaEWsLkwswM+saLsDMGigitgOzgNslfVzSyWl+KPCDPuxqJnCepBskjZZ0JXDxQbbZAJwkaYKk4yW1LqL/I3C1pEmSxgP3k11M37IIeBaYI2lcugHgLuCN3DoPAJuBhySdJWmkpDMlzfCdkGbWTVyAmTXX18guSv8J2bDdacD5EbGptzuIiGVkF9xfS3at2EXAHexbOBX9CvgN8ChZr9dlqf2rwHpgCfBLsrsrt+SOtZesuBtAdu3XHOA2YHdunR3AmWk/88kKtp+SXQP2am/fl5lZ3SndaGRmBoCku4ApEXFqp2MxM+tWvgjf7DAn6QbgD8A2sq+KmAZ8o6NBmZl1OfeAmR3mJM0FJgPHAv8EfgjcE/7jYGbWb1yAmZmZmVXMF+GbmZmZVcwFmJmZmVnFXICZmZmZVcwFmJmZmVnFXICZmZmZVex/LSw1Q85GOLYAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 720x504 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing.plot(kind=\"scatter\", \n",
    "             x=\"longitude\", \n",
    "             y=\"latitude\", \n",
    "             grid=True,\n",
    "             s=housing[\"population\"] / 100, \n",
    "             label=\"population\",\n",
    "             c=\"median_house_value\", \n",
    "             cmap=\"jet\", \n",
    "             colorbar=True,\n",
    "             legend=True, \n",
    "             sharex=False, \n",
    "             figsize=(10, 7)\n",
    "             );"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The argument `sharex=False` fixes a display bug: without it, the x-axis values and label are not displayed (see: https://github.com/pandas-dev/pandas/issues/10611)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Correlations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "corr_matrix = housing.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "median_house_value    1.000000\n",
       "median_income         0.688380\n",
       "total_rooms           0.137455\n",
       "housing_median_age    0.102175\n",
       "households            0.071426\n",
       "total_bedrooms        0.054635\n",
       "population           -0.020153\n",
       "longitude            -0.050859\n",
       "latitude             -0.139584\n",
       "Name: median_house_value, dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corr_matrix[\"median_house_value\"].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "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\", \"housing_median_age\"]\n",
    "\n",
    "scatter_matrix(housing[attributes], figsize=(12, 8));"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 864x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "housing.plot(kind=\"scatter\", \n",
    "             x=\"median_income\", \n",
    "             y=\"median_house_value\",\n",
    "             alpha=0.1, \n",
    "             grid=True,\n",
    "             figsize=(12, 8));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Engineering\n",
    "\n",
    "Experimenting with Attribute Combinations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing[\"rooms_per_house\"] = housing[\"total_rooms\"] / housing[\"households\"]\n",
    "housing[\"bedrooms_ratio\"] = housing[\"total_bedrooms\"] / housing[\"total_rooms\"]\n",
    "housing[\"people_per_house\"] = housing[\"population\"] / housing[\"households\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "median_house_value    1.000000\n",
       "median_income         0.688380\n",
       "rooms_per_house       0.143663\n",
       "total_rooms           0.137455\n",
       "housing_median_age    0.102175\n",
       "households            0.071426\n",
       "total_bedrooms        0.054635\n",
       "population           -0.020153\n",
       "people_per_house     -0.038224\n",
       "longitude            -0.050859\n",
       "latitude             -0.139584\n",
       "bedrooms_ratio       -0.256397\n",
       "Name: median_house_value, dtype: float64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corr_matrix = housing.corr()\n",
    "corr_matrix[\"median_house_value\"].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Pipeline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's revert to the original training set and separate the target (note that `strat_train_set.drop()` creates a copy of `strat_train_set` without the column, it doesn't actually modify `strat_train_set` itself, unless you pass `inplace=True`):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing = strat_train_set.drop(\"median_house_value\", axis=1)\n",
    "\n",
    "housing_labels = strat_train_set[\"median_house_value\"].copy()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's build a pipeline to preprocess the attributes:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_attribs = [\"longitude\", \"latitude\", \"housing_median_age\", \"total_rooms\",\n",
    "               \"total_bedrooms\", \"population\", \"households\", \"median_income\"]\n",
    "               \n",
    "cat_attribs = [\"ocean_proximity\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "\n",
    "# categorical pipeline\n",
    "cat_pipeline = make_pipeline(\n",
    "    SimpleImputer(strategy=\"most_frequent\"),\n",
    "    OneHotEncoder(handle_unknown=\"ignore\")\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# default numerical pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "default_num_pipeline = make_pipeline(\n",
    "    SimpleImputer(strategy=\"median\"),\n",
    "    StandardScaler()\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# custom function to make ratios\n",
    "def column_ratio(X):\n",
    "    return X[:, [0]] / X[:, [1]]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import FunctionTransformer\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# custom function to transfomr ratios\n",
    "def ratio_pipeline(name=None):\n",
    "    return make_pipeline(\n",
    "        SimpleImputer(strategy=\"median\"),\n",
    "        FunctionTransformer(column_ratio),\n",
    "        StandardScaler())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "# custom log transformer\n",
    "log_pipeline = make_pipeline(\n",
    "    SimpleImputer(strategy=\"median\"),\n",
    "    FunctionTransformer(np.log),\n",
    "    StandardScaler())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- To learn more about developing scikit-learn estimators, take a look at [this page](https://scikit-learn.org/stable/developers/develop.html)\n",
    "\n",
    "- Here is a template to build your own scikit-learn functions: [template](https://github.com/scikit-learn-contrib/project-template/blob/master/skltemplate/_template.py)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "# custom cluster similarity  \n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.base import BaseEstimator, TransformerMixin\n",
    "from sklearn.metrics.pairwise import rbf_kernel\n",
    "\n",
    "\n",
    "class ClusterSimilarity(BaseEstimator, TransformerMixin):\n",
    "    def __init__(self, n_clusters=10, gamma=1.0, random_state=None):\n",
    "        self.n_clusters = n_clusters\n",
    "        self.gamma = gamma\n",
    "        self.random_state = random_state\n",
    "\n",
    "    def fit(self, X, y=None, sample_weight=None):\n",
    "        self.kmeans_ = KMeans(self.n_clusters, random_state=self.random_state)\n",
    "        self.kmeans_.fit(X, sample_weight=sample_weight)\n",
    "        return self  # always return self!\n",
    "\n",
    "    def transform(self, X):\n",
    "        return rbf_kernel(X, self.kmeans_.cluster_centers_, gamma=self.gamma)\n",
    "    \n",
    "    def get_feature_names_out(self, names=None):\n",
    "        return [f\"Cluster {i} similarity\" for i in range(self.n_clusters)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "# custom cluster similarity step \n",
    "cluster_simil = ClusterSimilarity(n_clusters=10, gamma=1., random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Perform transformations:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.compose import make_column_selector\n",
    "\n",
    "\n",
    "preprocessing = ColumnTransformer([\n",
    "        (\"bedrooms_ratio\", ratio_pipeline(\"bedrooms_ratio\"),\n",
    "                           [\"total_bedrooms\", \"total_rooms\"]),\n",
    "\n",
    "        (\"rooms_per_house\", ratio_pipeline(\"rooms_per_house\"),\n",
    "                            [\"total_rooms\", \"households\"]),\n",
    "\n",
    "        (\"people_per_house\", ratio_pipeline(\"people_per_house\"),\n",
    "                             [\"population\", \"households\"]),\n",
    "\n",
    "        (\"log\", log_pipeline, [\"total_bedrooms\", \"total_rooms\",\n",
    "                               \"population\", \"households\", \"median_income\"]),\n",
    "\n",
    "        (\"geo\", cluster_simil, [\"latitude\", \"longitude\"]),\n",
    "        \n",
    "        (\"cat\", cat_pipeline, make_column_selector(dtype_include=object)),\n",
    "    ],\n",
    "    remainder=default_num_pipeline)  # one column remaining: housing_median_age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16512, 24)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_prepared = preprocessing.fit_transform(housing)\n",
    "\n",
    "housing_prepared.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Linear Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "lin_reg = make_pipeline(\n",
    "            preprocessing, \n",
    "            LinearRegression()\n",
    "            )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b {color: black;background-color: white;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b pre{padding: 0;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-toggleable {background-color: white;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-estimator:hover {background-color: #d4ebff;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-item {z-index: 1;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-parallel-item:only-child::after {width: 0;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-ed37a0bc-674a-4748-945a-08dbc3e2ae1b\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c0...\n",
       "                                                   &#x27;median_income&#x27;]),\n",
       "                                                 (&#x27;geo&#x27;,\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                (&#x27;linearregression&#x27;, LinearRegression())])</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"15b1b662-7115-4163-9eb8-9fc24feeec44\" type=\"checkbox\" ><label for=\"15b1b662-7115-4163-9eb8-9fc24feeec44\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c0...\n",
       "                                                   &#x27;median_income&#x27;]),\n",
       "                                                 (&#x27;geo&#x27;,\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                (&#x27;linearregression&#x27;, LinearRegression())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"d8e249d6-d4d6-4caf-8964-c713d9af8cd6\" type=\"checkbox\" ><label for=\"d8e249d6-d4d6-4caf-8964-c713d9af8cd6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)),\n",
       "                                                 (&#x27;standardscaler&#x27;,\n",
       "                                                  StandardSca...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;, ClusterSimilarity(random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"8a91fd1a-464c-42e5-8e67-deaa6b251057\" type=\"checkbox\" ><label for=\"8a91fd1a-464c-42e5-8e67-deaa6b251057\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"c13100e3-2ea2-4715-a8ee-92cb11f61c53\" type=\"checkbox\" ><label for=\"c13100e3-2ea2-4715-a8ee-92cb11f61c53\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4caa8be2-d1d9-404c-87f9-e4169216459d\" type=\"checkbox\" ><label for=\"4caa8be2-d1d9-404c-87f9-e4169216459d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"29ab7c13-eb63-404b-9d88-3e23e3ea3837\" type=\"checkbox\" ><label for=\"29ab7c13-eb63-404b-9d88-3e23e3ea3837\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"723a82b2-d972-40ff-86aa-ccdfa73f1bc7\" type=\"checkbox\" ><label for=\"723a82b2-d972-40ff-86aa-ccdfa73f1bc7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"83e74e58-42c8-4519-8118-999e5679ebb9\" type=\"checkbox\" ><label for=\"83e74e58-42c8-4519-8118-999e5679ebb9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"663cda20-af1b-48a5-bb88-728730ac8b68\" type=\"checkbox\" ><label for=\"663cda20-af1b-48a5-bb88-728730ac8b68\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"ea260bc4-3380-42e9-b729-231df43bff37\" type=\"checkbox\" ><label for=\"ea260bc4-3380-42e9-b729-231df43bff37\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"65f24303-c774-4a52-9ec1-4c7ca757ded8\" type=\"checkbox\" ><label for=\"65f24303-c774-4a52-9ec1-4c7ca757ded8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"a2f1d903-4bfa-42d8-a649-db5895269759\" type=\"checkbox\" ><label for=\"a2f1d903-4bfa-42d8-a649-db5895269759\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"0657720c-62ef-4561-8e00-ecee2536e7cb\" type=\"checkbox\" ><label for=\"0657720c-62ef-4561-8e00-ecee2536e7cb\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"3ae42b5c-a284-453d-8f0b-f98ca189da60\" type=\"checkbox\" ><label for=\"3ae42b5c-a284-453d-8f0b-f98ca189da60\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"dddef832-40b4-4ce9-be84-e8a5b810a956\" type=\"checkbox\" ><label for=\"dddef832-40b4-4ce9-be84-e8a5b810a956\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"af9d997f-b5ab-497f-bc1b-947825420b04\" type=\"checkbox\" ><label for=\"af9d997f-b5ab-497f-bc1b-947825420b04\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"b1c78137-3f4e-47a4-980e-3c88b7521fa0\" type=\"checkbox\" ><label for=\"b1c78137-3f4e-47a4-980e-3c88b7521fa0\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"d4b050fb-2af1-4f8a-9b1a-4c8ebf7962be\" type=\"checkbox\" ><label for=\"d4b050fb-2af1-4f8a-9b1a-4c8ebf7962be\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"dd6758a9-7bde-4303-8fb2-240a1c3b85bf\" type=\"checkbox\" ><label for=\"dd6758a9-7bde-4303-8fb2-240a1c3b85bf\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"39414bb4-e3df-4b4a-aac8-815d8bf68295\" type=\"checkbox\" ><label for=\"39414bb4-e3df-4b4a-aac8-815d8bf68295\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"159d2d21-a96c-487d-9847-3111b0411930\" type=\"checkbox\" ><label for=\"159d2d21-a96c-487d-9847-3111b0411930\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"0665ccd1-3803-4ac0-90ee-c55e84484459\" type=\"checkbox\" ><label for=\"0665ccd1-3803-4ac0-90ee-c55e84484459\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"b3f986b8-5ab8-4c9f-959b-3bf696a3e5fd\" type=\"checkbox\" ><label for=\"b3f986b8-5ab8-4c9f-959b-3bf696a3e5fd\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"9e8c78b3-0a85-4bbb-92ff-40b0fdc20559\" type=\"checkbox\" ><label for=\"9e8c78b3-0a85-4bbb-92ff-40b0fdc20559\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"7ff6434b-2ce5-429b-b655-58afa0f63b9d\" type=\"checkbox\" ><label for=\"7ff6434b-2ce5-429b-b655-58afa0f63b9d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"35cbc826-4e0c-4a69-a843-b5870074fcab\" type=\"checkbox\" ><label for=\"35cbc826-4e0c-4a69-a843-b5870074fcab\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"2c397e91-597d-49e9-be37-864cdef71c15\" type=\"checkbox\" ><label for=\"2c397e91-597d-49e9-be37-864cdef71c15\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('columntransformer',\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                              SimpleImputer(strategy='median')),\n",
       "                                                             ('standardscaler',\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[('bedrooms_ratio',\n",
       "                                                  Pipeline(steps=[('simpleimputer',\n",
       "                                                                   SimpleImputer(strategy='median')),\n",
       "                                                                  ('functiontransformer',\n",
       "                                                                   FunctionTransformer(func=<function column_ratio at 0x7fe110c0...\n",
       "                                                   'median_income']),\n",
       "                                                 ('geo',\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  ['latitude', 'longitude']),\n",
       "                                                 ('cat',\n",
       "                                                  Pipeline(steps=[('simpleimputer',\n",
       "                                                                   SimpleImputer(strategy='most_frequent')),\n",
       "                                                                  ('onehotencoder',\n",
       "                                                                   OneHotEncoder(handle_unknown='ignore'))]),\n",
       "                                                  <sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550>)])),\n",
       "                ('linearregression', LinearRegression())])"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lin_reg.fit(housing, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "housing_predictions = lin_reg.predict(housing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "68687.89176590106"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "lin_rmse = mean_squared_error(housing_labels, housing_predictions,\n",
    "                              squared=False)\n",
    "lin_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's try the full preprocessing pipeline on a few training instances:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([243700., 372400., 128800.,  94400., 328300.])"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_predictions[:5].round(-2)  # -2 = rounded to the nearest hundred"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Compare against the actual values:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([458300., 483800., 101700.,  96100., 361800.])"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_labels.iloc[:5].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-46.8%, -23.0%, 26.6%, -1.8%, -9.3%\n"
     ]
    }
   ],
   "source": [
    "# extra code – computes the error ratios discussed in the book\n",
    "error_ratios = housing_predictions[:5].round(-2) / housing_labels.iloc[:5].values - 1\n",
    "print(\", \".join([f\"{100 * ratio:.1f}%\" for ratio in error_ratios]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "\n",
    "tree_reg = make_pipeline(\n",
    "    preprocessing, \n",
    "    DecisionTreeRegressor(random_state=42)\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b {color: black;background-color: white;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b pre{padding: 0;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-toggleable {background-color: white;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-estimator:hover {background-color: #d4ebff;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-item {z-index: 1;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-parallel-item:only-child::after {width: 0;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-5f640a9c-74c1-41ef-be7a-c4bb71f0841b\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c0...\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                (&#x27;decisiontreeregressor&#x27;,\n",
       "                 DecisionTreeRegressor(random_state=42))])</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"de310c76-c790-43c7-a44c-ffc2d33c3251\" type=\"checkbox\" ><label for=\"de310c76-c790-43c7-a44c-ffc2d33c3251\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c0...\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                (&#x27;decisiontreeregressor&#x27;,\n",
       "                 DecisionTreeRegressor(random_state=42))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"66712af2-8b3d-4305-8c9c-e64ff65fab3b\" type=\"checkbox\" ><label for=\"66712af2-8b3d-4305-8c9c-e64ff65fab3b\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)),\n",
       "                                                 (&#x27;standardscaler&#x27;,\n",
       "                                                  StandardSca...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;, ClusterSimilarity(random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"00f7beea-273a-4fc8-9e71-30cf02cb2dc9\" type=\"checkbox\" ><label for=\"00f7beea-273a-4fc8-9e71-30cf02cb2dc9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"1199109f-8a28-40cb-a375-f097fe0758bf\" type=\"checkbox\" ><label for=\"1199109f-8a28-40cb-a375-f097fe0758bf\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"f7c921d4-95af-48a7-ac3e-bdf9c11d2c10\" type=\"checkbox\" ><label for=\"f7c921d4-95af-48a7-ac3e-bdf9c11d2c10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"77fa5969-5db1-472d-9751-f26cf3b3ecb4\" type=\"checkbox\" ><label for=\"77fa5969-5db1-472d-9751-f26cf3b3ecb4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"9a08e318-0f13-4c1c-89dd-3992db6f33e4\" type=\"checkbox\" ><label for=\"9a08e318-0f13-4c1c-89dd-3992db6f33e4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"69cca590-9c54-4818-ad97-d1a6d8155b77\" type=\"checkbox\" ><label for=\"69cca590-9c54-4818-ad97-d1a6d8155b77\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"70a98658-a6b5-4377-a3ba-b8ed2fbaa6d8\" type=\"checkbox\" ><label for=\"70a98658-a6b5-4377-a3ba-b8ed2fbaa6d8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4c748d40-76b2-4d86-8939-bbc1fa5d539a\" type=\"checkbox\" ><label for=\"4c748d40-76b2-4d86-8939-bbc1fa5d539a\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4bf72b35-37ac-4d34-b0bc-c3dcc038079d\" type=\"checkbox\" ><label for=\"4bf72b35-37ac-4d34-b0bc-c3dcc038079d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"3613802a-1dcf-487c-be5e-7a2ddccf422c\" type=\"checkbox\" ><label for=\"3613802a-1dcf-487c-be5e-7a2ddccf422c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"b780b624-da86-4034-ad17-050b35ca9b63\" type=\"checkbox\" ><label for=\"b780b624-da86-4034-ad17-050b35ca9b63\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4786a880-3947-4441-b0e4-ab12d17c5b4f\" type=\"checkbox\" ><label for=\"4786a880-3947-4441-b0e4-ab12d17c5b4f\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"9ddb9520-6404-4158-8d5c-d46b9d3cf037\" type=\"checkbox\" ><label for=\"9ddb9520-6404-4158-8d5c-d46b9d3cf037\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"7e0a6805-e949-4f51-85b2-8cd60583fa3e\" type=\"checkbox\" ><label for=\"7e0a6805-e949-4f51-85b2-8cd60583fa3e\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"bbd77670-9ee9-4c72-a7ef-d520da67b337\" type=\"checkbox\" ><label for=\"bbd77670-9ee9-4c72-a7ef-d520da67b337\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"8fa54bf3-8958-4d6a-bfb5-f2a2d6546389\" type=\"checkbox\" ><label for=\"8fa54bf3-8958-4d6a-bfb5-f2a2d6546389\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"86df491f-aaf7-47ba-b533-53b3879fcfa3\" type=\"checkbox\" ><label for=\"86df491f-aaf7-47ba-b533-53b3879fcfa3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"ea3bb3d4-aac7-4f4f-bca1-867672e7a066\" type=\"checkbox\" ><label for=\"ea3bb3d4-aac7-4f4f-bca1-867672e7a066\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"f4dd6397-6de6-4fc7-9ac5-169bc389f1fe\" type=\"checkbox\" ><label for=\"f4dd6397-6de6-4fc7-9ac5-169bc389f1fe\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"8b550aab-237c-46b3-a27a-21fe71dc4941\" type=\"checkbox\" ><label for=\"8b550aab-237c-46b3-a27a-21fe71dc4941\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"52910fc8-28c4-4b43-9225-acb8e526189b\" type=\"checkbox\" ><label for=\"52910fc8-28c4-4b43-9225-acb8e526189b\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"acb4365e-f3aa-44bc-8df7-059c51b5cd23\" type=\"checkbox\" ><label for=\"acb4365e-f3aa-44bc-8df7-059c51b5cd23\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"3ec38358-72a6-4901-9b8e-d9b96731a642\" type=\"checkbox\" ><label for=\"3ec38358-72a6-4901-9b8e-d9b96731a642\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"93444ce1-cd00-4f84-8300-48d00ac3c289\" type=\"checkbox\" ><label for=\"93444ce1-cd00-4f84-8300-48d00ac3c289\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"28d3314e-aaa5-45dc-b0e5-aecdd416664d\" type=\"checkbox\" ><label for=\"28d3314e-aaa5-45dc-b0e5-aecdd416664d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor(random_state=42)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('columntransformer',\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                              SimpleImputer(strategy='median')),\n",
       "                                                             ('standardscaler',\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[('bedrooms_ratio',\n",
       "                                                  Pipeline(steps=[('simpleimputer',\n",
       "                                                                   SimpleImputer(strategy='median')),\n",
       "                                                                  ('functiontransformer',\n",
       "                                                                   FunctionTransformer(func=<function column_ratio at 0x7fe110c0...\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  ['latitude', 'longitude']),\n",
       "                                                 ('cat',\n",
       "                                                  Pipeline(steps=[('simpleimputer',\n",
       "                                                                   SimpleImputer(strategy='most_frequent')),\n",
       "                                                                  ('onehotencoder',\n",
       "                                                                   OneHotEncoder(handle_unknown='ignore'))]),\n",
       "                                                  <sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550>)])),\n",
       "                ('decisiontreeregressor',\n",
       "                 DecisionTreeRegressor(random_state=42))])"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree_reg.fit(housing, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "housing_predictions = tree_reg.predict(housing)\n",
    "\n",
    "tree_rmse = mean_squared_error(housing_labels, housing_predictions,\n",
    "                              squared=False)\n",
    "tree_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cross-Validation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "# we only use cv=3 instead of cv=10 to speed up the computation\n",
    "tree_rmses = -cross_val_score(tree_reg, housing, housing_labels,\n",
    "                              scoring=\"neg_root_mean_squared_error\", cv=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count        3.000000\n",
       "mean     68282.891053\n",
       "std       1486.492256\n",
       "min      66810.075215\n",
       "25%      67532.990434\n",
       "50%      68255.905652\n",
       "75%      69019.298971\n",
       "max      69782.692291\n",
       "dtype: float64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.Series(tree_rmses).describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Linear Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count        3.000000\n",
       "mean     69778.756842\n",
       "std       1629.907725\n",
       "min      67980.530959\n",
       "25%      69088.686886\n",
       "50%      70196.842814\n",
       "75%      70677.869784\n",
       "max      71158.896754\n",
       "dtype: float64"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lin_rmses = -cross_val_score(lin_reg, housing, housing_labels,\n",
    "                              scoring=\"neg_root_mean_squared_error\", cv=3)\n",
    "\n",
    "pd.Series(lin_rmses).describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Random Forest"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Again, we set cv=3 instead of cv=10:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "\n",
    "forest_reg = make_pipeline(preprocessing,\n",
    "                           RandomForestRegressor(random_state=42))\n",
    "                           \n",
    "forest_rmses = -cross_val_score(forest_reg, housing, housing_labels,\n",
    "                                scoring=\"neg_root_mean_squared_error\", cv=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count        3.000000\n",
       "mean     47889.465303\n",
       "std        619.080587\n",
       "min      47392.624982\n",
       "25%      47542.700149\n",
       "50%      47692.775316\n",
       "75%      48137.885464\n",
       "max      48582.995613\n",
       "dtype: float64"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.Series(forest_rmses).describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's compare this RMSE measured using cross-validation (the \"validation error\") with the RMSE measured on the training set (the \"training error\"):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "17474.619286483998"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "forest_reg.fit(housing, housing_labels)\n",
    "\n",
    "housing_predictions = forest_reg.predict(housing)\n",
    "\n",
    "forest_rmse = mean_squared_error(housing_labels, housing_predictions,\n",
    "                                 squared=False)\n",
    "forest_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The training error is much lower than the validation error, which usually means that the model has overfit the training set. Another possible explanation may be that there's a mismatch between the training data and the validation data, but it's not the case here, since both came from the same dataset that we shuffled and split in two parts."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fine-Tuning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Grid Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "full_pipeline = Pipeline([\n",
    "    (\"preprocessing\", preprocessing),\n",
    "    (\"random_forest\", RandomForestRegressor(random_state=42)),\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "param_grid = [\n",
    "    {'preprocessing__geo__n_clusters': [5, 8, 10],\n",
    "     'random_forest__max_features': [4, 6, 8]},\n",
    "    {'preprocessing__geo__n_clusters': [10, 15],\n",
    "     'random_forest__max_features': [6, 8, 10]},\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "grid_search = GridSearchCV(full_pipeline, param_grid, cv=3,\n",
    "                           scoring='neg_root_mean_squared_error')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Warning:** the following cell may take a few minutes to run:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-70a0a955-0e25-49d8-bf93-c25302767c06 {color: black;background-color: white;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 pre{padding: 0;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-toggleable {background-color: white;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-estimator:hover {background-color: #d4ebff;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-item {z-index: 1;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-parallel-item:only-child::after {width: 0;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-70a0a955-0e25-49d8-bf93-c25302767c06 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-70a0a955-0e25-49d8-bf93-c25302767c06\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3,\n",
       "             estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                        ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                     SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                    (&#x27;standardscaler&#x27;,\n",
       "                                                                                     StandardScaler())]),\n",
       "                                                          transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                         Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                          SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                         (&#x27;functiontransformer&#x27;,\n",
       "                                                                                          FunctionTransformer(func=&lt;function...\n",
       "                                                                         &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                                       (&#x27;random_forest&#x27;,\n",
       "                                        RandomForestRegressor(random_state=42))]),\n",
       "             param_grid=[{&#x27;preprocessing__geo__n_clusters&#x27;: [5, 8, 10],\n",
       "                          &#x27;random_forest__max_features&#x27;: [4, 6, 8]},\n",
       "                         {&#x27;preprocessing__geo__n_clusters&#x27;: [10, 15],\n",
       "                          &#x27;random_forest__max_features&#x27;: [6, 8, 10]}],\n",
       "             scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"32bb9c7b-e3db-4318-bb10-7556ae690f83\" type=\"checkbox\" ><label for=\"32bb9c7b-e3db-4318-bb10-7556ae690f83\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=3,\n",
       "             estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                        ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                     SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                    (&#x27;standardscaler&#x27;,\n",
       "                                                                                     StandardScaler())]),\n",
       "                                                          transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                         Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                          SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                         (&#x27;functiontransformer&#x27;,\n",
       "                                                                                          FunctionTransformer(func=&lt;function...\n",
       "                                                                         &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                                       (&#x27;random_forest&#x27;,\n",
       "                                        RandomForestRegressor(random_state=42))]),\n",
       "             param_grid=[{&#x27;preprocessing__geo__n_clusters&#x27;: [5, 8, 10],\n",
       "                          &#x27;random_forest__max_features&#x27;: [4, 6, 8]},\n",
       "                         {&#x27;preprocessing__geo__n_clusters&#x27;: [10, 15],\n",
       "                          &#x27;random_forest__max_features&#x27;: [6, 8, 10]}],\n",
       "             scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"a8f5cbed-9d69-476d-8384-a652b6061d7c\" type=\"checkbox\" ><label for=\"a8f5cbed-9d69-476d-8384-a652b6061d7c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">preprocessing: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)),\n",
       "                                                 (&#x27;standardscaler&#x27;,\n",
       "                                                  StandardSca...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;, ClusterSimilarity(random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"8d836bf3-20d1-4359-8d6b-e2f3a64c9fcd\" type=\"checkbox\" ><label for=\"8d836bf3-20d1-4359-8d6b-e2f3a64c9fcd\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"bdd198fb-6687-4b20-aa54-420989e3cd1a\" type=\"checkbox\" ><label for=\"bdd198fb-6687-4b20-aa54-420989e3cd1a\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"bb2c9eeb-7b49-48e0-aef6-717dda9542c4\" type=\"checkbox\" ><label for=\"bb2c9eeb-7b49-48e0-aef6-717dda9542c4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"bfe918eb-c571-45ec-bfd9-b4678245da04\" type=\"checkbox\" ><label for=\"bfe918eb-c571-45ec-bfd9-b4678245da04\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"63bb07a5-2023-4052-9472-e73f4eded2ac\" type=\"checkbox\" ><label for=\"63bb07a5-2023-4052-9472-e73f4eded2ac\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"e0e61f71-baa8-4cff-a6c5-4806481bef9c\" type=\"checkbox\" ><label for=\"e0e61f71-baa8-4cff-a6c5-4806481bef9c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"7370a712-1052-409e-961b-a2070e0904a5\" type=\"checkbox\" ><label for=\"7370a712-1052-409e-961b-a2070e0904a5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"cc7dc796-c33d-4b51-840a-a4d617a83c63\" type=\"checkbox\" ><label for=\"cc7dc796-c33d-4b51-840a-a4d617a83c63\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"1ae4d189-b06b-4390-a74b-679632c5e01f\" type=\"checkbox\" ><label for=\"1ae4d189-b06b-4390-a74b-679632c5e01f\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"d6841fd4-e1f8-4eec-8dca-6ee2274ddbf5\" type=\"checkbox\" ><label for=\"d6841fd4-e1f8-4eec-8dca-6ee2274ddbf5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"1dd3570c-249e-4a15-8c08-56e33d71436d\" type=\"checkbox\" ><label for=\"1dd3570c-249e-4a15-8c08-56e33d71436d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"1897c35c-7121-4461-b7e2-a539b2d5fd00\" type=\"checkbox\" ><label for=\"1897c35c-7121-4461-b7e2-a539b2d5fd00\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"16282676-48d4-4aab-88a6-b9dbfe4092cb\" type=\"checkbox\" ><label for=\"16282676-48d4-4aab-88a6-b9dbfe4092cb\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"d14d9a7b-1925-44bf-a826-7b92a52a0e6e\" type=\"checkbox\" ><label for=\"d14d9a7b-1925-44bf-a826-7b92a52a0e6e\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"5a8ffb1c-deef-4952-b77c-84a62df45bf6\" type=\"checkbox\" ><label for=\"5a8ffb1c-deef-4952-b77c-84a62df45bf6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"993f7306-eb55-4986-a783-cde41d1a76a7\" type=\"checkbox\" ><label for=\"993f7306-eb55-4986-a783-cde41d1a76a7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"22789f3f-b165-49f7-ac16-c142d304d91c\" type=\"checkbox\" ><label for=\"22789f3f-b165-49f7-ac16-c142d304d91c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"881872e9-d48c-4502-a66e-b8e725146e2e\" type=\"checkbox\" ><label for=\"881872e9-d48c-4502-a66e-b8e725146e2e\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"97ed3bfe-0ccf-4480-a0f0-76f7b15c1464\" type=\"checkbox\" ><label for=\"97ed3bfe-0ccf-4480-a0f0-76f7b15c1464\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"c95e8590-1a72-44e1-9a06-5a844afe0f53\" type=\"checkbox\" ><label for=\"c95e8590-1a72-44e1-9a06-5a844afe0f53\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"cf8fda31-7bd2-4ee8-ad62-aeb70e705aa2\" type=\"checkbox\" ><label for=\"cf8fda31-7bd2-4ee8-ad62-aeb70e705aa2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"d459474e-cc74-492b-b8e0-8ad163953c88\" type=\"checkbox\" ><label for=\"d459474e-cc74-492b-b8e0-8ad163953c88\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"c5327aa7-4da9-40b5-a4a7-84ff7e70b866\" type=\"checkbox\" ><label for=\"c5327aa7-4da9-40b5-a4a7-84ff7e70b866\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"e1fe1db7-086b-4892-b181-e8fb82404fab\" type=\"checkbox\" ><label for=\"e1fe1db7-086b-4892-b181-e8fb82404fab\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"9a1738f3-e5e9-43ad-8d91-b2e85b0a472f\" type=\"checkbox\" ><label for=\"9a1738f3-e5e9-43ad-8d91-b2e85b0a472f\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(random_state=42)</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=3,\n",
       "             estimator=Pipeline(steps=[('preprocessing',\n",
       "                                        ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                                                     SimpleImputer(strategy='median')),\n",
       "                                                                                    ('standardscaler',\n",
       "                                                                                     StandardScaler())]),\n",
       "                                                          transformers=[('bedrooms_ratio',\n",
       "                                                                         Pipeline(steps=[('simpleimputer',\n",
       "                                                                                          SimpleImputer(strategy='median')),\n",
       "                                                                                         ('functiontransformer',\n",
       "                                                                                          FunctionTransformer(func=<function...\n",
       "                                                                         <sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550>)])),\n",
       "                                       ('random_forest',\n",
       "                                        RandomForestRegressor(random_state=42))]),\n",
       "             param_grid=[{'preprocessing__geo__n_clusters': [5, 8, 10],\n",
       "                          'random_forest__max_features': [4, 6, 8]},\n",
       "                         {'preprocessing__geo__n_clusters': [10, 15],\n",
       "                          'random_forest__max_features': [6, 8, 10]}],\n",
       "             scoring='neg_root_mean_squared_error')"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_search.fit(housing, housing_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can get the full list of hyperparameters available for tuning by looking at `full_pipeline.get_params().keys()`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['memory', 'steps', 'verbose', 'preprocessing', 'random_forest', 'preprocessing__n_jobs', 'preprocessing__remainder__memory', 'preprocessing__remainder__steps', 'preprocessing__remainder__verbose', 'preprocessing__remainder__simpleimputer', 'preprocessing__remainder__standardscaler', 'preprocessing__remainder__simpleimputer__add_indicator', 'preprocessing__remainder__simpleimputer__copy', 'preprocessing__remainder__simpleimputer__fill_value', 'preprocessing__remainder__simpleimputer__missing_values', 'preprocessing__remainder__simpleimputer__strategy', 'preprocessing__remainder__simpleimputer__verbose', 'preprocessing__remainder__standardscaler__copy', 'preprocessing__remainder__standardscaler__with_mean', 'preprocessing__remainder__standardscaler__with_std', 'preprocessing__remainder', 'preprocessing__sparse_threshold', 'preprocessing__transformer_weights', 'preprocessing__transformers', 'preprocessing__verbose', 'preprocessing__verbose_feature_names_out', 'preprocessing__be...\n"
     ]
    }
   ],
   "source": [
    "# extra code – shows part of the output of get_params().keys()\n",
    "print(str(full_pipeline.get_params().keys())[:1000] + \"...\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The best hyperparameter combination found:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'preprocessing__geo__n_clusters': 15, 'random_forest__max_features': 6}"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_search.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc {color: black;background-color: white;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc pre{padding: 0;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-toggleable {background-color: white;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-estimator:hover {background-color: #d4ebff;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-item {z-index: 1;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-parallel-item:only-child::after {width: 0;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-d03fa19c-271f-4e11-a6bc-42cd7ba692fc\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0...\n",
       "                                                  ClusterSimilarity(n_clusters=15,\n",
       "                                                                    random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe0f0a228e0&gt;)])),\n",
       "                (&#x27;random_forest&#x27;,\n",
       "                 RandomForestRegressor(max_features=6, random_state=42))])</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"56bbc780-ac17-4d5d-b240-63f0bd738c5d\" type=\"checkbox\" ><label for=\"56bbc780-ac17-4d5d-b240-63f0bd738c5d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0...\n",
       "                                                  ClusterSimilarity(n_clusters=15,\n",
       "                                                                    random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe0f0a228e0&gt;)])),\n",
       "                (&#x27;random_forest&#x27;,\n",
       "                 RandomForestRegressor(max_features=6, random_state=42))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"837b78c3-8d46-45b5-b508-da525e1050d5\" type=\"checkbox\" ><label for=\"837b78c3-8d46-45b5-b508-da525e1050d5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">preprocessing: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)),\n",
       "                                                 (&#x27;standardscaler&#x27;,\n",
       "                                                  StandardSca...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;,\n",
       "                                 ClusterSimilarity(n_clusters=15,\n",
       "                                                   random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe0f0a228e0&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"c7ad2476-6b92-4342-a1d5-dd8d6bbda3f7\" type=\"checkbox\" ><label for=\"c7ad2476-6b92-4342-a1d5-dd8d6bbda3f7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"81409fb6-3d70-413d-9c2a-ded658c8fca1\" type=\"checkbox\" ><label for=\"81409fb6-3d70-413d-9c2a-ded658c8fca1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"7cb3c597-f7e4-495f-b0d4-2b1d622fce0a\" type=\"checkbox\" ><label for=\"7cb3c597-f7e4-495f-b0d4-2b1d622fce0a\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"131acaf7-80a4-4f19-9599-a0cb25cc139c\" type=\"checkbox\" ><label for=\"131acaf7-80a4-4f19-9599-a0cb25cc139c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"247aa071-c4ac-4bde-bfd5-3e7d5228a38d\" type=\"checkbox\" ><label for=\"247aa071-c4ac-4bde-bfd5-3e7d5228a38d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"9a62c0ef-e588-4a12-a353-cf419d87ca01\" type=\"checkbox\" ><label for=\"9a62c0ef-e588-4a12-a353-cf419d87ca01\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"bc8a5383-0931-46dd-b895-3671dd6a19a0\" type=\"checkbox\" ><label for=\"bc8a5383-0931-46dd-b895-3671dd6a19a0\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"d9c143bd-98f3-4940-b721-18c62b1bc013\" type=\"checkbox\" ><label for=\"d9c143bd-98f3-4940-b721-18c62b1bc013\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"c65a4d64-ba5e-4bf7-a690-3166e1f5d7e9\" type=\"checkbox\" ><label for=\"c65a4d64-ba5e-4bf7-a690-3166e1f5d7e9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"a04a5d55-764e-44d5-a90e-ee2973c9ee2c\" type=\"checkbox\" ><label for=\"a04a5d55-764e-44d5-a90e-ee2973c9ee2c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"34bed58d-dd63-40bb-a9b4-c7bdcba99ce9\" type=\"checkbox\" ><label for=\"34bed58d-dd63-40bb-a9b4-c7bdcba99ce9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"4a241bee-d47c-48b2-834d-53dda7c54925\" type=\"checkbox\" ><label for=\"4a241bee-d47c-48b2-834d-53dda7c54925\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"012aac8d-34c6-431f-9c48-6fb083575163\" type=\"checkbox\" ><label for=\"012aac8d-34c6-431f-9c48-6fb083575163\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"eccdff01-bef7-4668-a0e7-f431d30ecdd2\" type=\"checkbox\" ><label for=\"eccdff01-bef7-4668-a0e7-f431d30ecdd2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"a2ed6e94-74d4-49ce-8c39-bfd5730e2375\" type=\"checkbox\" ><label for=\"a2ed6e94-74d4-49ce-8c39-bfd5730e2375\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"caa56f07-18d5-4a39-bf15-fbc01c8aa35e\" type=\"checkbox\" ><label for=\"caa56f07-18d5-4a39-bf15-fbc01c8aa35e\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"48dd7a63-61bf-484f-a28e-ea85f7a9e400\" type=\"checkbox\" ><label for=\"48dd7a63-61bf-484f-a28e-ea85f7a9e400\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"75cb1942-d21b-4a70-b4aa-d7a725b02757\" type=\"checkbox\" ><label for=\"75cb1942-d21b-4a70-b4aa-d7a725b02757\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(n_clusters=15, random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"3e712b0b-3197-420e-98d9-b70d6121ecd8\" type=\"checkbox\" ><label for=\"3e712b0b-3197-420e-98d9-b70d6121ecd8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe0f0a228e0&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"609cd95f-baf3-4408-9fa6-cc2828980ca5\" type=\"checkbox\" ><label for=\"609cd95f-baf3-4408-9fa6-cc2828980ca5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"09ba33ff-ce56-4022-924c-7c2a0d30f4db\" type=\"checkbox\" ><label for=\"09ba33ff-ce56-4022-924c-7c2a0d30f4db\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"be9c5516-7733-49c5-8479-5aa94929dbc3\" type=\"checkbox\" ><label for=\"be9c5516-7733-49c5-8479-5aa94929dbc3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"25f888a5-1ffe-4014-95ba-ad6ac385c193\" type=\"checkbox\" ><label for=\"25f888a5-1ffe-4014-95ba-ad6ac385c193\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"5379ce9c-4b9a-48b5-86f0-41ad5922dc7c\" type=\"checkbox\" ><label for=\"5379ce9c-4b9a-48b5-86f0-41ad5922dc7c\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"13ec80b3-cd1e-484c-9790-6121ec315e88\" type=\"checkbox\" ><label for=\"13ec80b3-cd1e-484c-9790-6121ec315e88\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(max_features=6, random_state=42)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('preprocessing',\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                              SimpleImputer(strategy='median')),\n",
       "                                                             ('standardscaler',\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[('bedrooms_ratio',\n",
       "                                                  Pipeline(steps=[('simpleimputer',\n",
       "                                                                   SimpleImputer(strategy='median')),\n",
       "                                                                  ('functiontransformer',\n",
       "                                                                   FunctionTransformer(func=<function column_ratio at 0x7fe110c04ee0...\n",
       "                                                  ClusterSimilarity(n_clusters=15,\n",
       "                                                                    random_state=42),\n",
       "                                                  ['latitude', 'longitude']),\n",
       "                                                 ('cat',\n",
       "                                                  Pipeline(steps=[('simpleimputer',\n",
       "                                                                   SimpleImputer(strategy='most_frequent')),\n",
       "                                                                  ('onehotencoder',\n",
       "                                                                   OneHotEncoder(handle_unknown='ignore'))]),\n",
       "                                                  <sklearn.compose._column_transformer.make_column_selector object at 0x7fe0f0a228e0>)])),\n",
       "                ('random_forest',\n",
       "                 RandomForestRegressor(max_features=6, random_state=42))])"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_search.best_estimator_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's look at the score of each hyperparameter combination tested during the grid search:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "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>n_clusters</th>\n",
       "      <th>max_features</th>\n",
       "      <th>split0</th>\n",
       "      <th>split1</th>\n",
       "      <th>split2</th>\n",
       "      <th>mean_test_rmse</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>15</td>\n",
       "      <td>6</td>\n",
       "      <td>43460</td>\n",
       "      <td>43919</td>\n",
       "      <td>44748</td>\n",
       "      <td>44042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>15</td>\n",
       "      <td>8</td>\n",
       "      <td>44132</td>\n",
       "      <td>44075</td>\n",
       "      <td>45010</td>\n",
       "      <td>44406</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15</td>\n",
       "      <td>10</td>\n",
       "      <td>44374</td>\n",
       "      <td>44286</td>\n",
       "      <td>45316</td>\n",
       "      <td>44659</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>44683</td>\n",
       "      <td>44655</td>\n",
       "      <td>45657</td>\n",
       "      <td>44999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>44683</td>\n",
       "      <td>44655</td>\n",
       "      <td>45657</td>\n",
       "      <td>44999</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   n_clusters max_features  split0  split1  split2  mean_test_rmse\n",
       "12         15            6   43460   43919   44748           44042\n",
       "13         15            8   44132   44075   45010           44406\n",
       "14         15           10   44374   44286   45316           44659\n",
       "7          10            6   44683   44655   45657           44999\n",
       "9          10            6   44683   44655   45657           44999"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cv_res = pd.DataFrame(grid_search.cv_results_)\n",
    "\n",
    "cv_res.sort_values(by=\"mean_test_score\", ascending=False, inplace=True)\n",
    "\n",
    "# extra code – these few lines of code just make the DataFrame look nicer\n",
    "cv_res = cv_res[[\"param_preprocessing__geo__n_clusters\",\n",
    "                 \"param_random_forest__max_features\", \"split0_test_score\",\n",
    "                 \"split1_test_score\", \"split2_test_score\", \"mean_test_score\"]]\n",
    "\n",
    "score_cols = [\"split0\", \"split1\", \"split2\", \"mean_test_rmse\"]\n",
    "\n",
    "cv_res.columns = [\"n_clusters\", \"max_features\"] + score_cols\n",
    "\n",
    "cv_res[score_cols] = -cv_res[score_cols].round().astype(np.int64)\n",
    "\n",
    "cv_res.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Randomized Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.experimental import enable_halving_search_cv\n",
    "from sklearn.model_selection import HalvingRandomSearchCV"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Warning:** the following cell may take a few minutes to run:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Try 30 (`n_iter` × `cv`) random combinations of hyperparameters:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 {color: black;background-color: white;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 pre{padding: 0;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-toggleable {background-color: white;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-estimator:hover {background-color: #d4ebff;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-item {z-index: 1;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-parallel-item:only-child::after {width: 0;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-32d8e27a-8357-491f-be8c-8a95ffdc3371 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-32d8e27a-8357-491f-be8c-8a95ffdc3371\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomizedSearchCV(cv=3,\n",
       "                   estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                              ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                           SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                          (&#x27;standardscaler&#x27;,\n",
       "                                                                                           StandardScaler())]),\n",
       "                                                                transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                               Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                                SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                               (&#x27;functiontransformer&#x27;,\n",
       "                                                                                                FunctionTransformer(func=&lt;fu...\n",
       "                                                                               &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                                             (&#x27;random_forest&#x27;,\n",
       "                                              RandomForestRegressor(random_state=42))]),\n",
       "                   param_distributions={&#x27;preprocessing__geo__n_clusters&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x7fe101e9d0a0&gt;,\n",
       "                                        &#x27;random_forest__max_features&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x7fe101f2dd30&gt;},\n",
       "                   random_state=42, scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"17b56534-973b-49a6-9faa-e07cb84f21a7\" type=\"checkbox\" ><label for=\"17b56534-973b-49a6-9faa-e07cb84f21a7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomizedSearchCV</label><div class=\"sk-toggleable__content\"><pre>RandomizedSearchCV(cv=3,\n",
       "                   estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                              ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                           SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                          (&#x27;standardscaler&#x27;,\n",
       "                                                                                           StandardScaler())]),\n",
       "                                                                transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                               Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                                SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                               (&#x27;functiontransformer&#x27;,\n",
       "                                                                                                FunctionTransformer(func=&lt;fu...\n",
       "                                                                               &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])),\n",
       "                                             (&#x27;random_forest&#x27;,\n",
       "                                              RandomForestRegressor(random_state=42))]),\n",
       "                   param_distributions={&#x27;preprocessing__geo__n_clusters&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x7fe101e9d0a0&gt;,\n",
       "                                        &#x27;random_forest__max_features&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x7fe101f2dd30&gt;},\n",
       "                   random_state=42, scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"5ba10565-45e1-4819-a909-8328af998d1d\" type=\"checkbox\" ><label for=\"5ba10565-45e1-4819-a909-8328af998d1d\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">preprocessing: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)),\n",
       "                                                 (&#x27;standardscaler&#x27;,\n",
       "                                                  StandardSca...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;, ClusterSimilarity(random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"10f753f5-8e8b-4678-b44b-ba5b3fbb1ad9\" type=\"checkbox\" ><label for=\"10f753f5-8e8b-4678-b44b-ba5b3fbb1ad9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"95e46d3a-6f29-4084-8529-eebac76f86ef\" type=\"checkbox\" ><label for=\"95e46d3a-6f29-4084-8529-eebac76f86ef\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"f2e772e8-97aa-4c0e-bea7-b233a6dd556e\" type=\"checkbox\" ><label for=\"f2e772e8-97aa-4c0e-bea7-b233a6dd556e\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"e9fab46b-4325-4c92-8f75-a1a275e820ea\" type=\"checkbox\" ><label for=\"e9fab46b-4325-4c92-8f75-a1a275e820ea\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"b2800500-2e26-4aee-bbf9-62668077e511\" type=\"checkbox\" ><label for=\"b2800500-2e26-4aee-bbf9-62668077e511\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"e284427f-099c-4517-a9e8-627c866a3f50\" type=\"checkbox\" ><label for=\"e284427f-099c-4517-a9e8-627c866a3f50\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"dc8d072e-8a7c-409a-a34d-7fcb6cba4af2\" type=\"checkbox\" ><label for=\"dc8d072e-8a7c-409a-a34d-7fcb6cba4af2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"347a9e7b-aa0b-421c-916d-b335ee2c0179\" type=\"checkbox\" ><label for=\"347a9e7b-aa0b-421c-916d-b335ee2c0179\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"69b00565-f9c3-4ece-a7bc-392a758351d4\" type=\"checkbox\" ><label for=\"69b00565-f9c3-4ece-a7bc-392a758351d4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"29912c6d-ee13-452e-b055-fbf190101d36\" type=\"checkbox\" ><label for=\"29912c6d-ee13-452e-b055-fbf190101d36\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"b00420b5-a315-43fe-aba6-d29ea0197701\" type=\"checkbox\" ><label for=\"b00420b5-a315-43fe-aba6-d29ea0197701\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;function column_ratio at 0x7fe110c04ee0&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"58d5b179-0b94-4c52-9651-5916ca018e15\" type=\"checkbox\" ><label for=\"58d5b179-0b94-4c52-9651-5916ca018e15\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"7414c9c5-3006-49b9-838e-fe65b7df23b2\" type=\"checkbox\" ><label for=\"7414c9c5-3006-49b9-838e-fe65b7df23b2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"065f4774-38a9-4581-a1b2-38a324ca9052\" type=\"checkbox\" ><label for=\"065f4774-38a9-4581-a1b2-38a324ca9052\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"40d2fdaf-9485-4193-b409-f22ee9dfb5c0\" type=\"checkbox\" ><label for=\"40d2fdaf-9485-4193-b409-f22ee9dfb5c0\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"77d1405f-832b-4c3e-9521-594c7672b4a2\" type=\"checkbox\" ><label for=\"77d1405f-832b-4c3e-9521-594c7672b4a2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"9a878a1e-56d9-4af9-a350-361e85a9b5b7\" type=\"checkbox\" ><label for=\"9a878a1e-56d9-4af9-a350-361e85a9b5b7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"38f2ddfe-ee46-44da-a136-26d35a0b7a57\" type=\"checkbox\" ><label for=\"38f2ddfe-ee46-44da-a136-26d35a0b7a57\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"8ede23c8-97c2-4920-9ebf-3af445ac9cc7\" type=\"checkbox\" ><label for=\"8ede23c8-97c2-4920-9ebf-3af445ac9cc7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"32fb9b51-8cb5-4a11-9988-585cfae87b32\" type=\"checkbox\" ><label for=\"32fb9b51-8cb5-4a11-9988-585cfae87b32\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"5b48b2e6-9046-4447-8d0e-46fc1666871a\" type=\"checkbox\" ><label for=\"5b48b2e6-9046-4447-8d0e-46fc1666871a\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"44b8df54-4682-4158-b051-c3d6d67480dc\" type=\"checkbox\" ><label for=\"44b8df54-4682-4158-b051-c3d6d67480dc\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"20ffd7f6-780c-4ece-95c1-c19310942e00\" type=\"checkbox\" ><label for=\"20ffd7f6-780c-4ece-95c1-c19310942e00\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"01c1b56d-d721-407c-8efd-c4413d97e52b\" type=\"checkbox\" ><label for=\"01c1b56d-d721-407c-8efd-c4413d97e52b\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"49adabea-c3c7-4b4f-a488-8023859899d1\" type=\"checkbox\" ><label for=\"49adabea-c3c7-4b4f-a488-8023859899d1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(random_state=42)</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomizedSearchCV(cv=3,\n",
       "                   estimator=Pipeline(steps=[('preprocessing',\n",
       "                                              ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                                                           SimpleImputer(strategy='median')),\n",
       "                                                                                          ('standardscaler',\n",
       "                                                                                           StandardScaler())]),\n",
       "                                                                transformers=[('bedrooms_ratio',\n",
       "                                                                               Pipeline(steps=[('simpleimputer',\n",
       "                                                                                                SimpleImputer(strategy='median')),\n",
       "                                                                                               ('functiontransformer',\n",
       "                                                                                                FunctionTransformer(func=<fu...\n",
       "                                                                               <sklearn.compose._column_transformer.make_column_selector object at 0x7fe102252550>)])),\n",
       "                                             ('random_forest',\n",
       "                                              RandomForestRegressor(random_state=42))]),\n",
       "                   param_distributions={'preprocessing__geo__n_clusters': <scipy.stats._distn_infrastructure.rv_frozen object at 0x7fe101e9d0a0>,\n",
       "                                        'random_forest__max_features': <scipy.stats._distn_infrastructure.rv_frozen object at 0x7fe101f2dd30>},\n",
       "                   random_state=42, scoring='neg_root_mean_squared_error')"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from scipy.stats import randint\n",
    "\n",
    "param_distribs = {'preprocessing__geo__n_clusters': randint(low=3, high=10),\n",
    "                  'random_forest__max_features': randint(low=2, high=10)}\n",
    "\n",
    "rnd_search = RandomizedSearchCV(\n",
    "    full_pipeline, param_distributions=param_distribs, n_iter=10, cv=3,\n",
    "    scoring='neg_root_mean_squared_error', random_state=42)\n",
    "\n",
    "\n",
    "rnd_search.fit(housing, housing_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "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>n_clusters</th>\n",
       "      <th>max_features</th>\n",
       "      <th>split0</th>\n",
       "      <th>split1</th>\n",
       "      <th>split2</th>\n",
       "      <th>mean_test_rmse</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9</td>\n",
       "      <td>5</td>\n",
       "      <td>45311</td>\n",
       "      <td>44727</td>\n",
       "      <td>46099</td>\n",
       "      <td>45379</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>45721</td>\n",
       "      <td>45397</td>\n",
       "      <td>46743</td>\n",
       "      <td>45953</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7</td>\n",
       "      <td>5</td>\n",
       "      <td>45887</td>\n",
       "      <td>45597</td>\n",
       "      <td>46504</td>\n",
       "      <td>45996</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7</td>\n",
       "      <td>6</td>\n",
       "      <td>45633</td>\n",
       "      <td>45815</td>\n",
       "      <td>46702</td>\n",
       "      <td>46050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7</td>\n",
       "      <td>8</td>\n",
       "      <td>45887</td>\n",
       "      <td>45820</td>\n",
       "      <td>46809</td>\n",
       "      <td>46172</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  n_clusters max_features  split0  split1  split2  mean_test_rmse\n",
       "0          9            5   45311   44727   46099           45379\n",
       "4          9            3   45721   45397   46743           45953\n",
       "7          7            5   45887   45597   46504           45996\n",
       "3          7            6   45633   45815   46702           46050\n",
       "1          7            8   45887   45820   46809           46172"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# extra code – displays the random search results\n",
    "cv_res = pd.DataFrame(rnd_search.cv_results_)\n",
    "\n",
    "cv_res.sort_values(by=\"mean_test_score\", ascending=False, inplace=True)\n",
    "\n",
    "cv_res = cv_res[[\"param_preprocessing__geo__n_clusters\",\n",
    "                 \"param_random_forest__max_features\", \"split0_test_score\",\n",
    "                 \"split1_test_score\", \"split2_test_score\", \"mean_test_score\"]]\n",
    "\n",
    "cv_res.columns = [\"n_clusters\", \"max_features\"] + score_cols\n",
    "\n",
    "cv_res[score_cols] = -cv_res[score_cols].round().astype(np.int64)\n",
    "\n",
    "cv_res.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Analyze Errors\n",
    "\n",
    "Analyze Errors of Best Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.08, 0.06, 0.08, 0.01, 0.01, 0.01, 0.01, 0.25, 0.04, 0.03, 0.04,\n",
       "       0.03, 0.04, 0.06, 0.02, 0.03, 0.02, 0.01, 0.12, 0.  , 0.  , 0.01,\n",
       "       0.03])"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_model = rnd_search.best_estimator_  # includes preprocessing\n",
    "\n",
    "feature_importances = final_model[\"random_forest\"].feature_importances_\n",
    "\n",
    "feature_importances.round(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluate on Test Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = strat_test_set.drop(\"median_house_value\", axis=1)\n",
    "y_test = strat_test_set[\"median_house_value\"].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_predictions = final_model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "44556.01747258438\n"
     ]
    }
   ],
   "source": [
    "final_rmse = mean_squared_error(y_test, final_predictions, squared=False)\n",
    "print(final_rmse)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can compute a 95% confidence interval for the test RMSE:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([42373.48736315, 46636.51953908])"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from scipy import stats\n",
    "\n",
    "confidence = 0.95\n",
    "\n",
    "squared_errors = (final_predictions - y_test) ** 2\n",
    "\n",
    "np.sqrt(stats.t.interval(confidence, len(squared_errors) - 1,\n",
    "                         loc=squared_errors.mean(),\n",
    "                         scale=stats.sem(squared_errors)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save model\n",
    "\n",
    "Model persistence using joblib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Save the final model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['my_california_housing_model.pkl']"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib\n",
    "\n",
    "joblib.dump(final_model, \"my_california_housing_model.pkl\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now you can deploy this model to production. For example, the following code could be a script that would run in production:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "final_model_reloaded = joblib.load(\"my_california_housing_model.pkl\")\n",
    "\n",
    "new_data = housing.iloc[:5]  # pretend these are new districts\n",
    "\n",
    "predictions = final_model_reloaded.predict(new_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([429545.11      , 462980.09      , 108348.47761194,  99628.        ,\n",
       "       345977.07      ])"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exercise solutions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Support Vector Machine"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Try a Support Vector Machine regressor (`sklearn.svm.SVR`) with various hyperparameters, such as `kernel=\"linear\"` (with various values for the `C` hyperparameter) or `kernel=\"rbf\"` (with various values for the `C` and `gamma` hyperparameters). Note that SVMs don't scale well to large datasets, so you should probably train your model on just the first 5,000 instances of the training set and use only 3-fold cross-validation, or else it will take hours. Don't worry about what the hyperparameters mean for now (see the SVM notebook if you're interested). How does the best `SVR` predictor perform?_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-6 {color: black;background-color: white;}#sk-container-id-6 pre{padding: 0;}#sk-container-id-6 div.sk-toggleable {background-color: white;}#sk-container-id-6 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-6 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-6 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-6 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-6 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-6 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-6 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-6 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-6 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-6 div.sk-item {position: relative;z-index: 1;}#sk-container-id-6 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-6 div.sk-item::before, #sk-container-id-6 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-6 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-6 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-6 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-6 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-6 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-6 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-6 div.sk-label-container {text-align: center;}#sk-container-id-6 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-6 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3,\n",
       "             estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                        ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                     SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                    (&#x27;standardscaler&#x27;,\n",
       "                                                                                     StandardScaler())]),\n",
       "                                                          transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                         Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                          SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                         (&#x27;functiontransformer&#x27;,\n",
       "                                                                                          FunctionTransformer(feature_names_...\n",
       "                                                                         &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])),\n",
       "                                       (&#x27;svr&#x27;, SVR())]),\n",
       "             param_grid=[{&#x27;svr__C&#x27;: [10.0, 30.0, 100.0, 300.0, 1000.0, 3000.0,\n",
       "                                     10000.0, 30000.0],\n",
       "                          &#x27;svr__kernel&#x27;: [&#x27;linear&#x27;]},\n",
       "                         {&#x27;svr__C&#x27;: [1.0, 3.0, 10.0, 30.0, 100.0, 300.0,\n",
       "                                     1000.0],\n",
       "                          &#x27;svr__gamma&#x27;: [0.01, 0.03, 0.1, 0.3, 1.0, 3.0],\n",
       "                          &#x27;svr__kernel&#x27;: [&#x27;rbf&#x27;]}],\n",
       "             scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-138\" type=\"checkbox\" ><label for=\"sk-estimator-id-138\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=3,\n",
       "             estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                        ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                     SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                    (&#x27;standardscaler&#x27;,\n",
       "                                                                                     StandardScaler())]),\n",
       "                                                          transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                         Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                          SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                         (&#x27;functiontransformer&#x27;,\n",
       "                                                                                          FunctionTransformer(feature_names_...\n",
       "                                                                         &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])),\n",
       "                                       (&#x27;svr&#x27;, SVR())]),\n",
       "             param_grid=[{&#x27;svr__C&#x27;: [10.0, 30.0, 100.0, 300.0, 1000.0, 3000.0,\n",
       "                                     10000.0, 30000.0],\n",
       "                          &#x27;svr__kernel&#x27;: [&#x27;linear&#x27;]},\n",
       "                         {&#x27;svr__C&#x27;: [1.0, 3.0, 10.0, 30.0, 100.0, 300.0,\n",
       "                                     1000.0],\n",
       "                          &#x27;svr__gamma&#x27;: [0.01, 0.03, 0.1, 0.3, 1.0, 3.0],\n",
       "                          &#x27;svr__kernel&#x27;: [&#x27;rbf&#x27;]}],\n",
       "             scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-139\" type=\"checkbox\" ><label for=\"sk-estimator-id-139\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(feature_names_out=[&#x27;bedrooms_ratio&#x27;],\n",
       "                                                                                       func=...\n",
       "                                                   &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                                   &#x27;households&#x27;,\n",
       "                                                   &#x27;median_income&#x27;]),\n",
       "                                                 (&#x27;geo&#x27;,\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])),\n",
       "                (&#x27;svr&#x27;, SVR())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-140\" type=\"checkbox\" ><label for=\"sk-estimator-id-140\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">preprocessing: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(feature_names_out=[&#x27;bedrooms_ratio&#x27;],\n",
       "                                                                      func=&lt;function column_ratio at 0x1490f967...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;, ClusterSimilarity(random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-141\" type=\"checkbox\" ><label for=\"sk-estimator-id-141\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-142\" type=\"checkbox\" ><label for=\"sk-estimator-id-142\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-143\" type=\"checkbox\" ><label for=\"sk-estimator-id-143\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(feature_names_out=[&#x27;bedrooms_ratio&#x27;],\n",
       "                    func=&lt;function column_ratio at 0x1490f9670&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-144\" type=\"checkbox\" ><label for=\"sk-estimator-id-144\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-145\" type=\"checkbox\" ><label for=\"sk-estimator-id-145\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-146\" type=\"checkbox\" ><label for=\"sk-estimator-id-146\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-147\" type=\"checkbox\" ><label for=\"sk-estimator-id-147\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(feature_names_out=[&#x27;rooms_per_house&#x27;],\n",
       "                    func=&lt;function column_ratio at 0x1490f9670&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-148\" type=\"checkbox\" ><label for=\"sk-estimator-id-148\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-149\" type=\"checkbox\" ><label for=\"sk-estimator-id-149\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-150\" type=\"checkbox\" ><label for=\"sk-estimator-id-150\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-151\" type=\"checkbox\" ><label for=\"sk-estimator-id-151\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(feature_names_out=[&#x27;people_per_house&#x27;],\n",
       "                    func=&lt;function column_ratio at 0x1490f9670&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-152\" type=\"checkbox\" ><label for=\"sk-estimator-id-152\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-153\" type=\"checkbox\" ><label for=\"sk-estimator-id-153\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-154\" type=\"checkbox\" ><label for=\"sk-estimator-id-154\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-155\" type=\"checkbox\" ><label for=\"sk-estimator-id-155\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-156\" type=\"checkbox\" ><label for=\"sk-estimator-id-156\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-157\" type=\"checkbox\" ><label for=\"sk-estimator-id-157\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-158\" type=\"checkbox\" ><label for=\"sk-estimator-id-158\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-159\" type=\"checkbox\" ><label for=\"sk-estimator-id-159\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-160\" type=\"checkbox\" ><label for=\"sk-estimator-id-160\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-161\" type=\"checkbox\" ><label for=\"sk-estimator-id-161\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-162\" type=\"checkbox\" ><label for=\"sk-estimator-id-162\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-163\" type=\"checkbox\" ><label for=\"sk-estimator-id-163\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-164\" type=\"checkbox\" ><label for=\"sk-estimator-id-164\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-165\" type=\"checkbox\" ><label for=\"sk-estimator-id-165\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVR</label><div class=\"sk-toggleable__content\"><pre>SVR()</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=3,\n",
       "             estimator=Pipeline(steps=[('preprocessing',\n",
       "                                        ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                                                     SimpleImputer(strategy='median')),\n",
       "                                                                                    ('standardscaler',\n",
       "                                                                                     StandardScaler())]),\n",
       "                                                          transformers=[('bedrooms_ratio',\n",
       "                                                                         Pipeline(steps=[('simpleimputer',\n",
       "                                                                                          SimpleImputer(strategy='median')),\n",
       "                                                                                         ('functiontransformer',\n",
       "                                                                                          FunctionTransformer(feature_names_...\n",
       "                                                                         <sklearn.compose._column_transformer.make_column_selector object at 0x14869da30>)])),\n",
       "                                       ('svr', SVR())]),\n",
       "             param_grid=[{'svr__C': [10.0, 30.0, 100.0, 300.0, 1000.0, 3000.0,\n",
       "                                     10000.0, 30000.0],\n",
       "                          'svr__kernel': ['linear']},\n",
       "                         {'svr__C': [1.0, 3.0, 10.0, 30.0, 100.0, 300.0,\n",
       "                                     1000.0],\n",
       "                          'svr__gamma': [0.01, 0.03, 0.1, 0.3, 1.0, 3.0],\n",
       "                          'svr__kernel': ['rbf']}],\n",
       "             scoring='neg_root_mean_squared_error')"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.svm import SVR\n",
    "\n",
    "param_grid = [\n",
    "        {'svr__kernel': ['linear'], 'svr__C': [10., 30., 100., 300., 1000.,\n",
    "                                               3000., 10000., 30000.0]},\n",
    "        {'svr__kernel': ['rbf'], 'svr__C': [1.0, 3.0, 10., 30., 100., 300.,\n",
    "                                            1000.0],\n",
    "         'svr__gamma': [0.01, 0.03, 0.1, 0.3, 1.0, 3.0]},\n",
    "    ]\n",
    "\n",
    "svr_pipeline = Pipeline([(\"preprocessing\", preprocessing), (\"svr\", SVR())])\n",
    "\n",
    "grid_search = GridSearchCV(svr_pipeline, param_grid, cv=3,\n",
    "                           scoring='neg_root_mean_squared_error')\n",
    "\n",
    "grid_search.fit(housing.iloc[:5000], housing_labels.iloc[:5000])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The best model achieves the following score (evaluated using 3-fold cross validation):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "69814.13889099036"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svr_grid_search_rmse = -grid_search.best_score_\n",
    "svr_grid_search_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "That's much worse than the `RandomForestRegressor` (but to be fair, we trained the model on much less data). Let's check the best hyperparameters found:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'svr__C': 10000.0, 'svr__kernel': 'linear'}"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_search.best_params_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The linear kernel seems better than the RBF kernel. Notice that the value of `C` is the maximum tested value. When this happens you definitely want to launch the grid search again with higher values for `C` (removing the smallest values), because it is likely that higher values of `C` will be better."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Randomized Search CV"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Try replacing the `GridSearchCV` with a `RandomizedSearchCV`._"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Warning:** the following cell will take several minutes to run. You can specify `verbose=2` when creating the `RandomizedSearchCV` if you want to see the training details."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-7 {color: black;background-color: white;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-7 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-7 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomizedSearchCV(cv=3,\n",
       "                   estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                              ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                           SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                          (&#x27;standardscaler&#x27;,\n",
       "                                                                                           StandardScaler())]),\n",
       "                                                                transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                               Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                                SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                               (&#x27;functiontransformer&#x27;,\n",
       "                                                                                                FunctionTransformer(feature_...\n",
       "                                                                               &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])),\n",
       "                                             (&#x27;svr&#x27;, SVR())]),\n",
       "                   param_distributions={&#x27;svr__C&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x149abd9d0&gt;,\n",
       "                                        &#x27;svr__gamma&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x149a7c8e0&gt;,\n",
       "                                        &#x27;svr__kernel&#x27;: [&#x27;linear&#x27;, &#x27;rbf&#x27;]},\n",
       "                   random_state=42, scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-166\" type=\"checkbox\" ><label for=\"sk-estimator-id-166\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomizedSearchCV</label><div class=\"sk-toggleable__content\"><pre>RandomizedSearchCV(cv=3,\n",
       "                   estimator=Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                                              ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                           SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                          (&#x27;standardscaler&#x27;,\n",
       "                                                                                           StandardScaler())]),\n",
       "                                                                transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                                               Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                                                SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                                               (&#x27;functiontransformer&#x27;,\n",
       "                                                                                                FunctionTransformer(feature_...\n",
       "                                                                               &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])),\n",
       "                                             (&#x27;svr&#x27;, SVR())]),\n",
       "                   param_distributions={&#x27;svr__C&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x149abd9d0&gt;,\n",
       "                                        &#x27;svr__gamma&#x27;: &lt;scipy.stats._distn_infrastructure.rv_frozen object at 0x149a7c8e0&gt;,\n",
       "                                        &#x27;svr__kernel&#x27;: [&#x27;linear&#x27;, &#x27;rbf&#x27;]},\n",
       "                   random_state=42, scoring=&#x27;neg_root_mean_squared_error&#x27;)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-167\" type=\"checkbox\" ><label for=\"sk-estimator-id-167\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;preprocessing&#x27;,\n",
       "                 ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                              SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                             (&#x27;standardscaler&#x27;,\n",
       "                                                              StandardScaler())]),\n",
       "                                   transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                                  (&#x27;functiontransformer&#x27;,\n",
       "                                                                   FunctionTransformer(feature_names_out=[&#x27;bedrooms_ratio&#x27;],\n",
       "                                                                                       func=...\n",
       "                                                   &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                                   &#x27;households&#x27;,\n",
       "                                                   &#x27;median_income&#x27;]),\n",
       "                                                 (&#x27;geo&#x27;,\n",
       "                                                  ClusterSimilarity(random_state=42),\n",
       "                                                  [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                                 (&#x27;cat&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                                   SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                                  (&#x27;onehotencoder&#x27;,\n",
       "                                                                   OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                                  &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])),\n",
       "                (&#x27;svr&#x27;, SVR())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-168\" type=\"checkbox\" ><label for=\"sk-estimator-id-168\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">preprocessing: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                             SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                            (&#x27;standardscaler&#x27;,\n",
       "                                             StandardScaler())]),\n",
       "                  transformers=[(&#x27;bedrooms_ratio&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;median&#x27;)),\n",
       "                                                 (&#x27;functiontransformer&#x27;,\n",
       "                                                  FunctionTransformer(feature_names_out=[&#x27;bedrooms_ratio&#x27;],\n",
       "                                                                      func=&lt;function column_ratio at 0x1490f967...\n",
       "                                 [&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;,\n",
       "                                  &#x27;households&#x27;, &#x27;median_income&#x27;]),\n",
       "                                (&#x27;geo&#x27;, ClusterSimilarity(random_state=42),\n",
       "                                 [&#x27;latitude&#x27;, &#x27;longitude&#x27;]),\n",
       "                                (&#x27;cat&#x27;,\n",
       "                                 Pipeline(steps=[(&#x27;simpleimputer&#x27;,\n",
       "                                                  SimpleImputer(strategy=&#x27;most_frequent&#x27;)),\n",
       "                                                 (&#x27;onehotencoder&#x27;,\n",
       "                                                  OneHotEncoder(handle_unknown=&#x27;ignore&#x27;))]),\n",
       "                                 &lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;)])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-169\" type=\"checkbox\" ><label for=\"sk-estimator-id-169\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">bedrooms_ratio</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-170\" type=\"checkbox\" ><label for=\"sk-estimator-id-170\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-171\" type=\"checkbox\" ><label for=\"sk-estimator-id-171\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(feature_names_out=[&#x27;bedrooms_ratio&#x27;],\n",
       "                    func=&lt;function column_ratio at 0x1490f9670&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-172\" type=\"checkbox\" ><label for=\"sk-estimator-id-172\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-173\" type=\"checkbox\" ><label for=\"sk-estimator-id-173\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">rooms_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_rooms&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-174\" type=\"checkbox\" ><label for=\"sk-estimator-id-174\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-175\" type=\"checkbox\" ><label for=\"sk-estimator-id-175\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(feature_names_out=[&#x27;rooms_per_house&#x27;],\n",
       "                    func=&lt;function column_ratio at 0x1490f9670&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-176\" type=\"checkbox\" ><label for=\"sk-estimator-id-176\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-177\" type=\"checkbox\" ><label for=\"sk-estimator-id-177\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">people_per_house</label><div class=\"sk-toggleable__content\"><pre>[&#x27;population&#x27;, &#x27;households&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-178\" type=\"checkbox\" ><label for=\"sk-estimator-id-178\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-179\" type=\"checkbox\" ><label for=\"sk-estimator-id-179\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(feature_names_out=[&#x27;people_per_house&#x27;],\n",
       "                    func=&lt;function column_ratio at 0x1490f9670&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-180\" type=\"checkbox\" ><label for=\"sk-estimator-id-180\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-181\" type=\"checkbox\" ><label for=\"sk-estimator-id-181\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">log</label><div class=\"sk-toggleable__content\"><pre>[&#x27;total_bedrooms&#x27;, &#x27;total_rooms&#x27;, &#x27;population&#x27;, &#x27;households&#x27;, &#x27;median_income&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-182\" type=\"checkbox\" ><label for=\"sk-estimator-id-182\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-183\" type=\"checkbox\" ><label for=\"sk-estimator-id-183\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">FunctionTransformer</label><div class=\"sk-toggleable__content\"><pre>FunctionTransformer(func=&lt;ufunc &#x27;log&#x27;&gt;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-184\" type=\"checkbox\" ><label for=\"sk-estimator-id-184\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-185\" type=\"checkbox\" ><label for=\"sk-estimator-id-185\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">geo</label><div class=\"sk-toggleable__content\"><pre>[&#x27;latitude&#x27;, &#x27;longitude&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-186\" type=\"checkbox\" ><label for=\"sk-estimator-id-186\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ClusterSimilarity</label><div class=\"sk-toggleable__content\"><pre>ClusterSimilarity(random_state=42)</pre></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-187\" type=\"checkbox\" ><label for=\"sk-estimator-id-187\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>&lt;sklearn.compose._column_transformer.make_column_selector object at 0x14869da30&gt;</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-188\" type=\"checkbox\" ><label for=\"sk-estimator-id-188\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-189\" type=\"checkbox\" ><label for=\"sk-estimator-id-189\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder(handle_unknown=&#x27;ignore&#x27;)</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-190\" type=\"checkbox\" ><label for=\"sk-estimator-id-190\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;housing_median_age&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-191\" type=\"checkbox\" ><label for=\"sk-estimator-id-191\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SimpleImputer</label><div class=\"sk-toggleable__content\"><pre>SimpleImputer(strategy=&#x27;median&#x27;)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-192\" type=\"checkbox\" ><label for=\"sk-estimator-id-192\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-193\" type=\"checkbox\" ><label for=\"sk-estimator-id-193\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVR</label><div class=\"sk-toggleable__content\"><pre>SVR()</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomizedSearchCV(cv=3,\n",
       "                   estimator=Pipeline(steps=[('preprocessing',\n",
       "                                              ColumnTransformer(remainder=Pipeline(steps=[('simpleimputer',\n",
       "                                                                                           SimpleImputer(strategy='median')),\n",
       "                                                                                          ('standardscaler',\n",
       "                                                                                           StandardScaler())]),\n",
       "                                                                transformers=[('bedrooms_ratio',\n",
       "                                                                               Pipeline(steps=[('simpleimputer',\n",
       "                                                                                                SimpleImputer(strategy='median')),\n",
       "                                                                                               ('functiontransformer',\n",
       "                                                                                                FunctionTransformer(feature_...\n",
       "                                                                               <sklearn.compose._column_transformer.make_column_selector object at 0x14869da30>)])),\n",
       "                                             ('svr', SVR())]),\n",
       "                   param_distributions={'svr__C': <scipy.stats._distn_infrastructure.rv_frozen object at 0x149abd9d0>,\n",
       "                                        'svr__gamma': <scipy.stats._distn_infrastructure.rv_frozen object at 0x149a7c8e0>,\n",
       "                                        'svr__kernel': ['linear', 'rbf']},\n",
       "                   random_state=42, scoring='neg_root_mean_squared_error')"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "from scipy.stats import expon, reciprocal\n",
    "\n",
    "# see https://docs.scipy.org/doc/scipy/reference/stats.html\n",
    "# for `expon()` and `reciprocal()` documentation and more probability distribution functions.\n",
    "\n",
    "# Note: gamma is ignored when kernel is \"linear\"\n",
    "param_distribs = {\n",
    "        'svr__kernel': ['linear', 'rbf'],\n",
    "        'svr__C': reciprocal(20, 200_000),\n",
    "        'svr__gamma': expon(scale=1.0),\n",
    "    }\n",
    "\n",
    "# we set n_iter to 10 \n",
    "rnd_search = RandomizedSearchCV(svr_pipeline,\n",
    "                                param_distributions=param_distribs,\n",
    "                                n_iter=10, cv=3,\n",
    "                                scoring='neg_root_mean_squared_error',\n",
    "                                random_state=42)\n",
    "\n",
    "rnd_search.fit(housing.iloc[:5000], housing_labels.iloc[:5000])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The best model achieves the following score (evaluated using 3-fold cross validation):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "55853.88099808542"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svr_rnd_search_rmse = -rnd_search.best_score_\n",
    "svr_rnd_search_rmse"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that's really much better, but still far from the `RandomForestRegressor`'s performance. Let's check the best hyperparameters found:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'svr__C': 157055.10989448498,\n",
       " 'svr__gamma': 0.26497040005002437,\n",
       " 'svr__kernel': 'rbf'}"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rnd_search.best_params_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This time the search found a good set of hyperparameters for the RBF kernel. Randomized search tends to find better hyperparameters than grid search in the same amount of time."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note that we used the `expon()` distribution for `gamma`, with a scale of 1, so `RandomSearch` mostly searched for values roughly of that scale: about 80% of the samples were between 0.1 and 2.3 (roughly 10% were smaller and 10% were larger):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.80066"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.seed(42)\n",
    "\n",
    "s = expon(scale=1).rvs(100_000)  # get 100,000 samples\n",
    "((s > 0.105) & (s < 2.29)).sum() / 100_000"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We used the `reciprocal()` distribution for `C`, meaning we did not have a clue what the optimal scale of `C` was before running the random search. It explored the range from 20 to 200 just as much as the range from 2,000 to 20,000 or from 20,000 to 200,000."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. SelectFromModel"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Exercise: _Try adding a `SelectFromModel` transformer in the preparation pipeline to select only the most important attributes._"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's create a new pipeline that runs the previously defined preparation pipeline, and adds a `SelectFromModel` transformer based on a `RandomForestRegressor` before the final regressor:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.feature_selection import SelectFromModel\n",
    "\n",
    "selector_pipeline = Pipeline([\n",
    "    ('preprocessing', preprocessing),\n",
    "    ('selector', SelectFromModel(RandomForestRegressor(random_state=42),\n",
    "                                 threshold=0.005)),  # min feature importance\n",
    "    ('svr', SVR(C=rnd_search.best_params_[\"svr__C\"],\n",
    "                gamma=rnd_search.best_params_[\"svr__gamma\"],\n",
    "                kernel=rnd_search.best_params_[\"svr__kernel\"])),\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "selector_rmses = -cross_val_score(selector_pipeline,\n",
    "                                  housing.iloc[:5000],\n",
    "                                  housing_labels.iloc[:5000],\n",
    "                                  scoring=\"neg_root_mean_squared_error\",\n",
    "                                  cv=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count        3.000000\n",
       "mean     56211.362079\n",
       "std       1922.002809\n",
       "min      54150.008614\n",
       "25%      55339.929900\n",
       "50%      56529.851185\n",
       "75%      57242.038812\n",
       "max      57954.226438\n",
       "dtype: float64"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    " pd.Series(selector_rmses).describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Oh well, feature selection does not seem to help. But maybe that's just because the threshold we used was not optimal. Perhaps try tuning it using random search or grid search?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Congratulations! You already know quite a lot about Machine Learning. :)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.7 ('base')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  },
  "nav_menu": {
   "height": "279px",
   "width": "309px"
  },
  "toc": {
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": "block",
   "toc_window_display": false
  },
  "vscode": {
   "interpreter": {
    "hash": "463226f144cc21b006ce6927bfc93dd00694e52c8bc6857abb6e555b983749e9"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}