{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# tidylinreg Example\n",
    "\n",
    "The `tidylinreg` package fits a linear model to a dataset, and can be used to carry out regression. `tidylinreg` computes and returns a list of summary statistics of the coefficients of the fitted linear model, including standard error, test statistic, confidence interval, and p-value.\n",
    "\n",
    "To use `tidylinreg` in a project:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tidylinreg.tidylinreg.LinearModel"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from tidylinreg.tidylinreg import LinearModel\n",
    "\n",
    "LinearModel"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data\n",
    "\n",
    "To demonstrate Linear Regression using `tidylinreg`, we can use the [California housing dataset](https://scikit-learn.org/dev/modules/generated/sklearn.datasets.fetch_california_housing.html). This dataset has 8 numeric, predictive attributes and the target.\n",
    "\n",
    "Attributes:\n",
    "- MedInc: median income in block group\n",
    "- HouseAge: median house age in block group\n",
    "- AveRooms: average number of rooms per household\n",
    "- AveBedrms: average number of bedrooms per household\n",
    "- Population: block group population\n",
    "- AveOccup: average number of household members\n",
    "- Latitude: block group latitude\n",
    "- Longitude: block group longitude\n",
    "\n",
    "Target: The target variable is the median house value for California districts, expressed in hundreds of thousands of dollars ($100,000)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import fetch_california_housing\n",
    "import pandas as pd\n",
    "\n",
    "housing = fetch_california_housing(as_frame=True)\n",
    "X = housing[\"data\"]\n",
    "y = housing[\"target\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train/Test Split\n",
    "\n",
    "Make sure to split the data into train and test sets to avoid any violations of the **Golden Rule**!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=524)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### EDA\n",
    "\n",
    "EDA is not the focus of this example, so here's just a quick preview of the data. A more detailed explanation of the data can be found [here](https://inria.github.io/scikit-learn-mooc/python_scripts/datasets_california_housing.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>MedInc</th>\n",
       "      <th>HouseAge</th>\n",
       "      <th>AveRooms</th>\n",
       "      <th>AveBedrms</th>\n",
       "      <th>Population</th>\n",
       "      <th>AveOccup</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>3.3750</td>\n",
       "      <td>52.0</td>\n",
       "      <td>4.011905</td>\n",
       "      <td>1.071429</td>\n",
       "      <td>647.0</td>\n",
       "      <td>3.851190</td>\n",
       "      <td>37.79</td>\n",
       "      <td>-122.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19599</th>\n",
       "      <td>1.5500</td>\n",
       "      <td>17.0</td>\n",
       "      <td>5.425150</td>\n",
       "      <td>1.080838</td>\n",
       "      <td>672.0</td>\n",
       "      <td>2.011976</td>\n",
       "      <td>37.56</td>\n",
       "      <td>-120.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20100</th>\n",
       "      <td>2.0057</td>\n",
       "      <td>52.0</td>\n",
       "      <td>5.061728</td>\n",
       "      <td>1.078189</td>\n",
       "      <td>609.0</td>\n",
       "      <td>2.506173</td>\n",
       "      <td>37.96</td>\n",
       "      <td>-120.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9708</th>\n",
       "      <td>1.9385</td>\n",
       "      <td>28.0</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>1.039252</td>\n",
       "      <td>1717.0</td>\n",
       "      <td>3.209346</td>\n",
       "      <td>36.67</td>\n",
       "      <td>-121.65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20518</th>\n",
       "      <td>1.9426</td>\n",
       "      <td>32.0</td>\n",
       "      <td>3.957935</td>\n",
       "      <td>1.072658</td>\n",
       "      <td>2046.0</td>\n",
       "      <td>3.912046</td>\n",
       "      <td>38.58</td>\n",
       "      <td>-121.56</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19206</th>\n",
       "      <td>1.9932</td>\n",
       "      <td>29.0</td>\n",
       "      <td>4.329949</td>\n",
       "      <td>1.053299</td>\n",
       "      <td>990.0</td>\n",
       "      <td>2.512690</td>\n",
       "      <td>38.47</td>\n",
       "      <td>-122.72</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15131</th>\n",
       "      <td>2.3693</td>\n",
       "      <td>11.0</td>\n",
       "      <td>4.434608</td>\n",
       "      <td>1.042254</td>\n",
       "      <td>1472.0</td>\n",
       "      <td>2.961771</td>\n",
       "      <td>32.86</td>\n",
       "      <td>-116.92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5652</th>\n",
       "      <td>2.1382</td>\n",
       "      <td>21.0</td>\n",
       "      <td>3.708333</td>\n",
       "      <td>1.058036</td>\n",
       "      <td>1699.0</td>\n",
       "      <td>2.528274</td>\n",
       "      <td>33.73</td>\n",
       "      <td>-118.29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12733</th>\n",
       "      <td>8.6572</td>\n",
       "      <td>20.0</td>\n",
       "      <td>8.130435</td>\n",
       "      <td>1.027174</td>\n",
       "      <td>1105.0</td>\n",
       "      <td>3.002717</td>\n",
       "      <td>38.58</td>\n",
       "      <td>-121.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17402</th>\n",
       "      <td>2.2743</td>\n",
       "      <td>38.0</td>\n",
       "      <td>4.021419</td>\n",
       "      <td>1.062918</td>\n",
       "      <td>2601.0</td>\n",
       "      <td>3.481928</td>\n",
       "      <td>34.95</td>\n",
       "      <td>-120.44</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>14448 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       MedInc  HouseAge  AveRooms  AveBedrms  Population  AveOccup  Latitude  \\\n",
       "190    3.3750      52.0  4.011905   1.071429       647.0  3.851190     37.79   \n",
       "19599  1.5500      17.0  5.425150   1.080838       672.0  2.011976     37.56   \n",
       "20100  2.0057      52.0  5.061728   1.078189       609.0  2.506173     37.96   \n",
       "9708   1.9385      28.0  3.600000   1.039252      1717.0  3.209346     36.67   \n",
       "20518  1.9426      32.0  3.957935   1.072658      2046.0  3.912046     38.58   \n",
       "...       ...       ...       ...        ...         ...       ...       ...   \n",
       "19206  1.9932      29.0  4.329949   1.053299       990.0  2.512690     38.47   \n",
       "15131  2.3693      11.0  4.434608   1.042254      1472.0  2.961771     32.86   \n",
       "5652   2.1382      21.0  3.708333   1.058036      1699.0  2.528274     33.73   \n",
       "12733  8.6572      20.0  8.130435   1.027174      1105.0  3.002717     38.58   \n",
       "17402  2.2743      38.0  4.021419   1.062918      2601.0  3.481928     34.95   \n",
       "\n",
       "       Longitude  \n",
       "190      -122.24  \n",
       "19599    -120.93  \n",
       "20100    -120.23  \n",
       "9708     -121.65  \n",
       "20518    -121.56  \n",
       "...          ...  \n",
       "19206    -122.72  \n",
       "15131    -116.92  \n",
       "5652     -118.29  \n",
       "12733    -121.35  \n",
       "17402    -120.44  \n",
       "\n",
       "[14448 rows x 8 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Scaling\n",
    "\n",
    "This model uses simple linear regression with no regularization, so scaling of the features is optional but not required. Scaling is useful if we are interested in comparing relative feature importance; however, we should keep the data in its original scale in this example so that the linear regression coefficient estimates are more interpretable."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# scaler = StandardScaler()\n",
    "# X_train = pd.DataFrame(scaler.fit_transform(X_train),\n",
    "#                        columns=X_train.columns,\n",
    "#                        index=X_train.index)\n",
    "# X_test = pd.DataFrame(scaler.fit_transform(X_test),\n",
    "#                       columns=X_test.columns,\n",
    "#                       index=X_test.index)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fit\n",
    "\n",
    "Let's define our model and fit it to the training data! \n",
    "\n",
    "**Note:**, we don't need to add a column of ones to our data to get an intercept. The `fit` method takes care of this for you!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LinearModel()\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predict\n",
    "\n",
    "How do our predictions look compared to the true values?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "preds = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjUAAAHHCAYAAABHp6kXAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAmGBJREFUeJztnQeY1NTXxt+lL71LL4LS7Y0iolIURBQVPkEEUWxIRwFFig1QlGKhKMVGUxAFRFxEQEAU9Y9YERAp0gSRzu6yzPe8N2Q3OzslmclkMjPn9zzZ2clkkps7yb0npyZ5PB4PBEEQBEEQYpxc0W6AIAiCIAiCHYhQIwiCIAhCXCBCjSAIgiAIcYEINYIgCIIgxAUi1AiCIAiCEBeIUCMIgiAIQlwgQo0gCIIgCHGBCDWCIAiCIMQFItQIgiAIghAXiFAjCCHSrFkztej89ddfSEpKwsyZM7Nt99lnn+GSSy5BgQIF1Of//fefo+1ke3hcti+RGDFihDrvRMTXtWh3f6xcuVLtj6+C4BZEqBEShm3btuGhhx7C+eefrwSMokWLonHjxpgwYQJOnToVkWMeOnQIHTp0QHJyMl5//XW8++67KFSoEGIZXUj67rvvfH5OQa9+/fpIZLp166b6SF94rV188cV4+eWXkZqailjijTfeyCGoC4JbyRPtBgiCEyxZsgR33XUX8ufPj3vvvVdNumlpaVizZg0ef/xx/PLLL5g6dWpYx6hataoSjvLmzZu5bsOGDTh27BieffZZNG/eHNGgS5cu+L//+z917onE0KFDMXjw4Kgdn/391ltvqf+pnZs/fz4GDhyorok5c+bETH9QqCldurQS1Iw0bdpUXe/58uWzsZWCEB4i1Ahxz/bt29WkTqFjxYoVKF++fOZnPXv2xNatW5XQEy58IqcGyMiBAwfUa/HixWEXJ06csKTtyZ07t1oSjTx58qglmse/5557Mt8/+uijuPrqqzF37ly88sorqFChQo7vsL7w6dOnlWbP7f2RK1euHNe7IEQbMT8Jcc+LL76I48ePY9q0adkEGp2aNWuiT58+me9nzJiBG264AWXLllVP23Xr1sWkSZMs+zHQDNO1a1f1/5VXXqk+Mz7tfvDBB7j88svVBMYnYU6Af//9d7Z9cvvChQsr01nr1q1RpEgRdO7cWX3G/T322GNYuHCh0jyxrfXq1VM+PMF8aj7++GO0adNGTaz8Xo0aNZQ2KSMjA5HgzJkzav88Do9XrVo1PPnkkzlMMWwnfT+84fbGvktPT8fIkSNxwQUXqIm1VKlSaNKkCVJSUgL6kJjtM0JfkSuuuELtn+2eMmVKWH4pFAJ0Hyz9t+B53XLLLVi2bJk6Fq8FHkfX7vTt2xeVK1dW7eR1OmbMGJw9ezbbfrkd+6ZYsWJKeOY158tvy1/b33vvPVx11VUoWLAgSpQooTQwn3/+eWb7qMVctWpVpilNPwd/PjVWrmuuv+2229T/ZcqUUZos72uQWi3uj9c+zXgNGjRQJmNB8IVoaoS4Z9GiRcqPplGjRqa2pwDDie7WW29VT7b8Pp+yOZlQs2OWp556CrVq1VJmrWeeeQbVq1dXk6MuaNx3331K2Bk1ahT279+vBuq1a9fif//7XzbNDgWCVq1aqUl77NixavLRoflswYIFqn0c9CdOnIg77rgDO3fuVBO9P3h8TiT9+/dXr9RgDRs2DEePHsVLL71k6vyOHDmCgwcP5lhPgcObBx54AG+//TbuvPNODBgwAN988406799++w0fffQRrMIJmt/nfjkhs9308fnhhx/QokWLgN8102f8DW666SYlBFN44kTL35ATbzhQOCXG32bz5s24++67lb9Xjx491DVz8uRJXHfddWrS5/oqVapg3bp1GDJkCPbu3Yvx48dnanbatWunzunhhx9GnTp1VH/qwnQweG7sS94bPD+akvjb8Hpo2bKlOk6vXr3UNcLrmZx33nl+92flumaf8rqm9orX9fLly5XPEe+RRx55RG1DIZV9c+ONNyqBjvCa4f6MDyKCkIlHEOKYI0eOeHiZt2vXzvR3Tp48mWNdq1atPOeff362ddddd51adLZv366ONWPGjMx1/J/rNmzYkLkuLS3NU7ZsWU/9+vU9p06dyly/ePFite2wYcMy13Xt2lWtGzx4cI42cX2+fPk8W7duzVz3448/qvWvvvpqjjawfYHO8aGHHvIULFjQc/r06YD9o+8v0FKvXr3M7Tdu3KjWPfDAA9n2M3DgQLV+xYoV2c5p+PDhOY5ZtWpV1Rc6F198sadNmzYB28n9eA9xZvusbdu2qi/+/vvvzHVbtmzx5MmTJ8c+fcG2FipUyPPPP/+ohcd74YUXPElJSZ6LLroo23lxf5999lm27z/77LPq+3/88Ue29bwOcufO7dm5c6d6v3DhQvX9F198MXObM2fOeK699toc16J3f/B8cuXK5bn99ts9GRkZ2Y5z9uzZzP/5Wxqvc50vv/xS7Y+voV7XzzzzTLZ9XnrppZ7LL788832fPn08RYsWVeckCGYQ85MQ1/AJnvCJ3CxGfwZdG8Gn5j///FO9DxdqFOhrQ02B0SeB5qDatWv79O/Rn1y9ofOxrv0hF110kVLRs61mz5GOzDzHa6+9VmkIfv/9d1PnwWguPkl7L2yDkU8//VS9UitkhBobEoo/E5/4aRbZsmWL5e8G6zNqEKg1oFnE6PdC88/NN99syfeJmh0u/C7NbQ0bNsyhmaIGjxoLbxMOfw+ag/jb6AvbzvatXr06s2+pTTReH/SfonYlGDTBUftIDR1NY0ZCMbGFcl1Tu2SE52y8dvk7sx+NZkVBCISYn4S4hpOVPnGbhart4cOH4+uvv1aTvBEKNfRdCIcdO3aoV5oZvOHgT1OCEU5alSpV8rkvmiW84UR4+PDhgG2gQMBoGJoZdMFPx6zgRrMP/UB8Hd9oluL5ctLkxG6kXLlyatLS+8MKNJXQ7HLhhRcq3xiaihjl5S1QhdJnnJgZ1ePdXuJrnT84sdN0SegTQ+HF1+/I9d5QWNu0aZNfc5fugM6+o4mM5iEjvq4tX6Yw/i70GbMDq9c1+8f7/LyvXQpI8+bNU8JkxYoVlUmMKRL4ewuCL0SoEeJeqOHT9s8//2xqew70tN9zEGaECp006WfAJ+Jx48blcNJ0Ak6I3k/SOv6imjRLi2/oRErNE/uGwgG1Fpxg6I8yaNCgiJ1jOInfvJ1H6czK34oOz3RqZeg0f5/JkycrP5tAhNJnocDjmAnj9xXpxN+AvkFPPPGEz+9QmIt1zETk0Vl/48aNypF66dKlaqEjP9My0EdLELwRoUaIexhdQmddal6o/g8En6wZkfPJJ59ke6L/8ssvbWsPQ8t1B1FGWRnhOv3zSMFoFSYFpLMshQNj6Hsk4Plwkqb2gY6sOnQipYBlPF8+qXtH7jCfEJ1jvSlZsqRySuXC6DaeC51egwk1ZiZSCnkM9ffG17pIQEGT5xRMKGLfffHFF2pbo7aG15GZY/B3+fXXX1XG63CF0Uhd13yoaNu2rVrYXmpvGCH29NNPW9KcCYmB+NQIcQ+fdpnXhZMdJ1Jv+MSvh4jqT4/Gp3aaY/h0aBc02XDipFbBGNLMp1BGdtAHIZL4OkcKDkyyFgkYik70iB0dasKI8Xw50er+IjoUSL01NRTKjHBC5wRnR7ZeXcNCn5M9e/ZkE2j4GzkBTSwUwqmh8IZCHyPi9L7l/8aUA+yrV199Negx6DNEDSC1dd7aOeO1wXvHTGmPSFzX3r8z26ubGGMtM7PgDKKpEeIeTpSzZs1Cx44dlabAmFGYYbJ0ytRzoNBmrz8ZMpSWT8BvvvmmGqx9aQtCgRmHGZ5KDQPNQAxZ1UNfmRekX79+iCQM36VGhGG/vXv3Vk/iLN9gt/lFh+UBeCwKJ7rp69tvv1XmA06s119/fea2FDzpPMoQa5pffvzxRzWxM9+JEfqBMF8K85dQY0Mn1Q8//FDloLEDanxo1mIZDTrhUlB47bXX1HVDc0ikYZZragupZeS1yfOkw+xPP/2kzpN5btgnvE7ZRmYK5jr2CzVwZvyiKAQyTJv5g+ig2759e2XqZMZjmmwZkk14bApNzz33nPoO7wVvTUykrmteD//++686Hv2R6LdDgY2aJaPWTxAyMRUjJQhxAMNje/To4alWrZoK6y1SpIincePGKpTXGMb8ySefqLDbAgUKqG3HjBnjmT59eo6w6FBDunXmzp2rQljz58/vKVmypKdz586e3bt3+wwN9gX327Nnz6Dhz75CuteuXeu55pprPMnJyZ4KFSp4nnjiCc+yZcuyhej6I9A56f1iDOkm6enpnpEjR3qqV6/uyZs3r6dy5cqeIUOG5AgfZ2jxoEGDPKVLl1Yh1QylZzi09zk999xznquuuspTvHhxdQ61a9f2PP/88yqsOFhIt5k+I1988YX6fXit1KhRw/PWW295BgwYoK6LYAT63byP6y80/dixY6qPatasqdrAPmnUqJFn7Nix2c7z0KFDni5duqjQ52LFiqn///e//wUN6dbhta1fhyVKlFC/X0pKSubn+/btU23k/cLv69e8d0i3Hde1dxs//PBDT8uWLVWoOPugSpUqKvXA3r17g/atkJgk8U+WiCMIgiD4g5qlUEPJBUGIPOJTIwiC4APvyu0UZBgFp5cJEATBfYimRhAEwQfM/0J/FpbYoC8H/UronMp0/6w5JQiC+xBHYUEQBB8wwdvs2bOxb98+5UDLdAAvvPCCCDSC4GJEUyMIgiAIQlwgPjWCIAiCIMQFItQIgiAIghAXJJRPDbNmMkMoKzaHU4dGEARBEATnoKcMCxMzMaS/WngJJ9RQoGGBQkEQBEEQYo9du3b5rHafkEINNTR6p7BCsU56erpKic4U+Uz1LUQe6fPoIP3uPNLn0UH6Pb76/OjRo0opoc/j/kgooUY3OVGg8RZqChYsqNbJxe8M0ufRQfrdeaTPo4P0e3z2eTDXEXEUFgRBEAQhLhChRhAEQRCEuECEGkEQBEEQ4gIRagRBEARBiAtEqBEEQRAEIS4QoUYQBEEQhLhAhBpBEARBEOICEWoEQRAEQYgLRKgRBEEQBCEuEKFGEARBEISwyMgA1qzR/ucr30cDEWqEhIE32cqVwOzZ2mu0bjpBEIR4YsECoGpVoE0b7T1f+Z7rnUaEGiEh4M1VrRpw/fVAp07aK99H46YTBEGIFxYsAO64A/j77+zr+Z7rnR5jRagR4h7eVHfeCezenfOm43oRbARBEKxDbfeDDwbehp87qRUXoUaIa3gz9ekDeDw5P9PX9e0rpihBEASr0Ix/6FDgbfg5t3MKEWqEuOarr3JqaLwFm127tO0EQRAE85gVVkSoEQSb2LvX3u0EQRAE9yJCjRDXlC9v73aCIAiCRrNmsHU7OxChRohrrr0WqFQJSEry/TnXV66sbScIgiCYh8JK4cKBtylSRIQan1SrVg1JSUk5lp49e0a7aYKLyZ0bmDBB+99bsNHfjx+vbScIgiDYi68gjUgSM0LNhg0bsHfv3swlJSVFrb/rrrui3TTB5bRvD3z4IVCxYvb11OBwPT8XBEEQrEEH4OPHA2/Dz510FM6DGKFMmTLZ3o8ePRo1atTAddddF7U2CbEDBZd27bQoJzoF04eGJifR0AiCIEQ++unGG+EIMSPUGElLS8N7772H/v37KxOUP1JTU9Wic/ToUfWanp6uFh39f+M6IbJEq88bN876/+xZbUkk5Fp3Hunz6CD97gzJycb/07O9Ggn3ZzD7OyZ5PE5bvMJn3rx56NSpE3bu3IkKFSr43W7EiBEYOXJkjvWzZs1CwYIFI9xKQRAEQRDs4OTJk2reP3LkCIoWLRpfQk2rVq2QL18+LFq0KOB2vjQ1lStXxsGDB7N1CiVA+ui0aNECefPmjWjbBQ3p8+gg/e480ufRQfo98syaBTzySNZ7amimT09B9+4tcOpUVp9PmqTV3AsHzt+lS5cOKtTEnPlpx44dWL58ORaYKNiTP39+tXjDC9zXRe5vvRA5pM+jg/S780ifRwfp98ixfj1w6lTO9RRojEINt+vaNbxjmf0NYyb6SWfGjBkoW7Ys2ug1zgVBEARBcBzvytzhbmcHMSXUnD17Vgk1Xbt2RZ48MadkEgRBEIS44W8RasKDZic6B3fv3j3aTREEQRCEhCZfPnu3s4OYUne0bNkSMejXLAiCIAhxHc5tx3YJp6kRBEEQBEHwhwg1giAIgiBYJi3N3u3sQIQaQRAEQRAsU7WqvdvZgQg1giAIgiBYxmzumXBz1FhBhBpBEARBECzDIpWFCwfehp87VcySiFAjCIIgCIJlcucG3n478Db8nNs5hQg1giAIgiCERPv2wOOPA0lJ2dfzPdfzcycRoUYQBEEQhJBgGcaxYwFfKeS43kSZRlsRoUYQBEEQBMtkZAB9+vgWaPR1fftq2zmFCDWCIAiCIFjmq6+A3bv9f07BZtcubTunEKFGEARBEATL7N1r73Z2IEKNIAiCIAiWKV/e3u3sQIQaQRAEQRAsc+21QKVKOSOfdLi+cmVtO6cQoUYQBEEQBMsw/8yECdr/vkK6yfjxkqdGEARBEIQYoH174MMPgYoVs6+nBofrnc5Tk8fZwwmCIAiCEE+0bw+0awesXg0cPQosWQI0beqshkZHNDWCIAiCIIQFBZgmTbT/+RoNgYaIUCMIgiAIQlgwwd6aNdr/fHUy4Z4REWoEQRAEQQgZlkKoWhVo00Z7z1e+d7pEAhGhRhAEQRCEkKDgcscdwN9/Z1/P91wvtZ8EQRAEQXA9GRlA166Bt+nWTWo/CYIgCILgclasAI4fD7zNsWPadk4hQo0gCIIgCJZ5+217t7MDEWoEQRAEQbDMX3/Zu50diFAjCIIgCIJlGOFk53Z2IEKNIAiCIAiWCeYkbHU7OxChRhAEQRAEy9x4I1CgQOBt+Dm3cwoRagRBEARBCIlChcL73G5EqBEEQRAEwTJffQUcOhR4G37O7ZxChBpBEARBECyzd6+92yWcUPP333/jnnvuQalSpZCcnIwGDRrgu+++i3azBEGIQ5gFdeVKYPZs7TVaBfoEwa2UL2/vdnaQBzHC4cOH0bhxY1x//fVYunQpypQpgy1btqBEiRLRbpogCHEG69X06QPs3p21rlIlYMIEoH37aLZMENxDo0ZArlzA2bP+t+Hn3M4pYkaoGTNmDCpXrowZM2ZkrqtevXpU2yQIQnwKNHfeCXg8OQv0cf2HH4pgIwiEvjKBBBrCz7mdUxFQMSPUfPLJJ2jVqhXuuusurFq1ChUrVsSjjz6KHj16+P1OamqqWnSOHj2qXtPT09Wio/9vXCdEFunz6CD9HhiamAYN8h+mmpQEDB4MtG4N5M5tbp/S59FB+j3y0CybnJz1Pjk5PdurcbumTcM7ltnfMcnj8X4ecScFzo0y/fv3V4LNhg0b0KdPH0yePBld/WT2GTFiBEaOHJlj/axZs1CwYMGIt1kQBEEQhPA5efIkOnXqhCNHjqBo0aKxL9Tky5cPV1xxBdatW5e5rnfv3kq4+frrr01ramjCOnjwYLZOoQSYkpKCFi1aIG/evBE+E4FIn0cH6ffA0LR0//3Bt5s2TTNFmUH6PDpIv0ceGkrmzct6Tw3N9Okp6N69BU6dyurzDh2AN98M71icv0uXLh1UqIkZ81P58uVRt27dbOvq1KmD+fPn+/1O/vz51eINL3BfF7m/9ULkkD6PDtLv/qM0Tp0yt53V7pM+jw7S75GjYkXf9wsFGqNQw+3C/QnM/oYxE9LNyKfNmzdnW/fHH3+gqpOVsgRBiGuuvVaLcqLvjC+4vnJlbTtBSHRuuMHe7ewgZoSafv36Yf369XjhhRewdetW5RczdepU9OzZM9pNEwQhTqDzL8O2ibdgo78fP968k7AgxDONTIZqOxnSHTNCzZVXXomPPvoIs2fPRv369fHss89i/Pjx6Ny5c7SbJghCHMFwbfrWUGVuhBocCecWhCymTIGt29lBzPjUkFtuuUUtgiAIkYSCS7t2Wn4NpninDw1NTqKhEYQstm2DrdslnFAjCILgFBRgmjWLdisEwb1Uq2bvdgllfhIEQRAEwT00aGDvdnYgQo0gCIIgCJb55x97t7MDEWoEQRAEQbCMCDWCIAiCIMQFZcrYu50diKOwEBNFBiUKRRAEwV2UK2fvdnYgQo3gahYsAPr0AXbvzp4vhAnSJF+IIAhC9Dh71t7t7EDMT4KrBRoWDTQKNOTvv7X1/FwQBEGIDitX2rudHYhQI7jW5EQNja8a8vq6vn217QRBEATn2bnT3u3sQIQawZXQh8ZbQ+Mt2OzapW0nCIIgOA9dAezczg5EqBFcCZ2C7dxOEARBsJfSpe3dzg5EqBFcCaOc7NxOEARBsJeyZe3dzg5EqBFcCcO2qbJMSvL9OddXrqxtJwiCIDjPvn32bmcHItQIroR5aBi2TbwFG/39+PGSr0YQBCFabNxo73Z2IEKN4FqYh+bDD4GKFbOvpwaH6yVPjSAIQvQ4ftze7exAku8JroaCS7t2klFYEAT3k2jZzz0ee7ezAxFqBNfDQaFZs2i3QhAEwT+JmP38rGQUFgRBEIT4IlGzn2/ZYu92diBCjSAIgiCESCJnPy9UyN7t7ECEGkEQBCHmoJDAmkKzZ2uv0RIaEjn7eYEC9m5nB+JTIwiCIMQUbvJfSeTs5yVL2rudHYimRhAEQYgZ3Oa/ksjZz0+dsnc7OxChRhAEQYgJ3Oi/ksjZz//9197t7ECEGkEQBCEmcKP/SjxlP8+w6Kd04oS5/Zrdzg5EqBEEQRBiArf6r8RD9vMFC4Bq1YDrrwc6ddJe+T6QOY8aKDOY3c4ORKgRBEEQYgI3+69QcPnrL+DLL4FZs7TX7dtjR6C5MwQ/pVatzO3f7HZ2INFPgiAIQkyg+69wsvXlV0NzDz/ndk5msY3l7OcZQfyU2Kf0U2K5Gm8TmhuFTNHUCIIgCDFBPPmvxIOf0qFD5o5hdjs7EKFGEARBiBniwX8lXvyUSpUy912z29mBmJ8EQRCEmIKCC80hiVQRO1KUD8OEJJqaMBgxYgSSkpKyLbVr1452swRBEAREz3/l7ru1VxFoQiOcPDslSpg7htntEkqoIfXq1cPevXszlzVr1kS7SYIgCIKQkH5K69ebO4bZ7RLO/JQnTx6UK1cu2s0QBEEQhJCjjdxmNmt/zk/JVz0tCjT+/JT27DG3f7PbJZxQs2XLFlSoUAEFChRAw4YNMWrUKFSpUiXazRIEQRCEmCrEaYef0vHj2d9fcHazqe0iScwINVdffTVmzpyJWrVqKdPTyJEjce211+Lnn39GkSJFfH4nNTVVLTpHjx5Vr+np6WrR0f83rhMii/R5dJB+dx7pc+c0IF9/DezbB1Chf+WV7ur3RYuALl20EOnk5Ox1kbietG2LqNO4cdb/zPUTKN8PhZVCBTJwy9lFeOzMRDRJXYMvt49DcnJ6ju3C/RnM/o5JHo+vlDvu57///kPVqlXxyiuv4P777/frXEzhx5tZs2ahYMGCDrRSEARBEOKPPKdOocry5Th/8WIU2r9frTubOzc2PfQQdrRsafvxTp48iU6dOuHIkSMoWrRo/Ak15Morr0Tz5s2VGcqspqZy5co4ePBgtk6hBJiSkoIWLVogb968jrQ90ZE+jw7S784jfe6cBsRIwYLpmDYtBRkZLdC2bV6f3xs0SMtOrMPcN2PG2K8xYUxLmzbBt1uyBGjSBFFnUZC+yTV5MnINHYqkc9aPQyiJaXl64O3CPfDCzJ/RvXsLnDqV1edlygBbt4bXJs7fpUuXDirUxIz5yZvjx49j27Zt6KLr7XyQP39+tXjDgcXX4OJvvRA5pM+jg/S780ifRy7F/8mT/rcZPDgv2rXLm803RK915C0Ibdumrbc7iR9NYqdOmdsu2pfIAj99s31rBu68M7fWN6VLU8rAH7lq4eWz/fAuuuDUmYJITqWJ6Gcl0BiFGso+4Z6X2XsnZkK6Bw4ciFWrVuGvv/7CunXrcPvttyN37ty4m0kKBEEQhIQjWIp/ws+NKf6D1ToirHXE7ezCjTWSfOHdN7lxBndhHtahIfpiXFbf3H4nsHQprkj+FVPxEE4hsDvHmTNwjJgRanbv3q0EGDoKd+jQAaVKlcL69etRhnotQRAEIeEIJcV/OLWOopHgzkm+Otc3xfAfBmAstqEG5qEjGmI9HsRU0FtF9c36vMBNNyHDY06EcLK4aMyYn+bMmRPtJgiCIAguIhQNSDi1jsJNcEezDgUYo5bITYU4j23chvGYiO6YjiLQ4rAPoAzewKOYhEfY2mx9w3ibQKY/HSfjcmJGUyMIgiAIVjQghJ8bNSDRMgXFQiHOqxYNRR9MVALNT6iP7piGKtiJkRiBAzgvR9+4saClCDWCIAhC3Kb4Hz06uwYkmqYgCi5//QV8+SVTi2iv27dHSaBJSwPef59ZbTNXlX6+P1YUuBktkIKLsAkz0B2pKOC3b8qWNXcos9vZgQg1giAIQsziTwOiv/cOzw6n1lFcFOL891+AaVCqVwfuuQd4+eWstl1zJf57/1N8kdRcFY0O1je//WbukGa3swMRagRBEISYxpcGZNOm2DYF2c7mzcAjj2gn+eSTWkEm2pEuvDDkvjlxwrxSyClixlFYEARBEIJpQHSCZdUPpdZRzNKtG/D221nvL70U6NcP6NgRyJcvpL5h+LeZ3DtOI0KNIAiCEHfoeWaoXfAnsHgLQnFDaqqW7S7XOWMMHWFoP6ItjsLMddcF9q420TdWQt6dDOkW85MgCIIQVzArboMG2v8sDXj99UC1atr6uObAAeCZZ4AqVYDPPstaz4x6f/wBfPyxJqkEEWjsDnm34XCmEaFGEARBiBv0NP/GukWE77k+3gQbaqQ2zPgZ265/AGcrVQGGD9eEG0Y26bCsQc2ath7XSsi75KkRBEEQBItEowRC1PB4sPbpz7C2UEtc2b0Baqychlzpqfhf3qvwTf85wMyZET08zXl5TDqwMNDKKUSoEQRBEFwHBY+VK4HZs7VXM4JINEogRAtqnAo/NwhNU1OQgVz4AHeiEdbi8vT1aDiuIxYsimxlTCv+SLop0AlEqBEEQRBcN2HTB4a+MJ06mfeJiUYJBMdgo0eMAI4f1zRSfZPwAp7EK+iHGtiGDvgAX6MRPOdKGTihkbr8cnPblSwJx5DoJ0EQBMF1PjHeJiTdJyZQHplYqYZtiY0bgXHjNJUV49RLlcJXDXopjRSLTXIJpJFqFsHorp077d3ODkRTIwiCIMSFT0ysVMM2FQP9ySeaioo5Zd55RxNomjQBatd2jUbqwAF7t7MDEWoEQRAEVxCuT0y0SyDYwunTQL16Wva7lStxNnce/NXobnw/6VtkrPwKaNHCNRqpEyfs3c4ORKgRBEEQXIEdGgg9zX+FCjFUAoH1mHQKFADq1EFaoeJ4vcggVMnYjurrZuGKR67M9Ctyi0bq4EF7t7MDEWoEQRAEV2CXBoKCy08/af9PmxblatiB+PZbrbIlT+jPPzNXL715Ikqd2IXHjo3G36iUw6+IOfTcoJE6ZbJMgpPlFESoEQRBEFyBnRoIfUKnEBCVatj+OHNGUxk1bgxcfTUwZ45W8XHJEvUx/YUefKYSjqOwT/MbF/od0ToV7aKcRYvau50dSPSTIMQIHOwSoviekLDoPjEURCjAGB2GzWogjPcJM9nyPcsgRZ2TJ4EpU4CJE7WS4oQNY8w6vZ8vucSUXxHh588/DwwbZq7w5FcRGjd8OXSHs50diKZGEOI4b4cgxBq6T0woGgjjfcKaT3rit1Duk1CS/wXd4ciRmkBTqhQwdCiwY4eW+fecQGPFr4jVEHheehI8WrGaeWmkIj1uiPlJEISQ83Z4P73Fay0bQaDgwrmfvjCzZpnzifF3n+zZY/0+CVsYoGpi7VpgwIAsNUWRIlqxyalTtRCuZ5/16RxkJWIpUHj7AgfGjXz57N3ODsT8JAgxnLeDKnkObFRBiylKiCespOE3m9/GzH0STvI/lUtm/nzglVeADRu0da1bAzfeqP3fu7dpv6JgJijiL8Fehon+ePhhTYNCjZhZk5S3KYvLli3uSnYomhpBcDGJVMtGEKJ9n4Sc/O/wYeDFF4Hzz9fsQBRo8ucHHngAqFrV0rkYc+2YwZe56isTfjn//APcc495LZQv7ZXZcYfHcgoRagTBxbglc6gQHWz364hT7LpPQhKOfvtNC8kaNEj78nnnaWYmbvjmm0DNmrAKNUF0vzGDLy3IXovjQTCTlD9TllkH4GPH4BhifhIEF+OWzKGC83AiodbAOJHQLMGneNflW7GRUKJ17LpPzAkDHhz5aRfQrIr2tlYtTaih40i/fpqmhlqaMKlTB8iVS6uY4Auannk9+ApvL29xPAhkyg6kvTKLk0KNaGoEwcW4JXOo4CyJ6hweqoOuXfdJIGEgL9LQBe/gB1yG1kMvywrpoeRBT2YWnuzWzRaBhufbsaN/gUbHX3j7tUH6w4qJzowpy0xqHqcQoUYQXEygWjb6QHTHHdrAE8umCTGz2FfUMd4FOV/XSig1n3ztx5cwUAoH8SSexw5UxTvoikuxEXnOnAK+/z5ro3LlrEkQATCjGeF5zJvnX2OXO8i4YUVbZYdpu3DOPIIRQ4QaQYjRvB36AM3BOpbz1kgOnuwkonN4MEGOCwW5Dz7wf634u0/43jtiyd81Zyw/UAU7MRkPYRcq43kMRXnsw25UxM+dRyGJPwArZkdAkDejGeG2pUsH3qa9n/4Ixv792dtkh2n7wgvhGCLUCEKM5e3g4E68n9Rj0TSRqGaWQCSic7iZiZxyRIcOga8V433Cmk9k06acAk2ga45QGKh+3kk8hKlIxmlswBXoVfJ9bJi7HfXfGwyULBmWABNIOLPz92/fHti2DRg3Dnj0UaBYscCaGz4o0S3I2CZGLlk1ZXnDXEFOIY7CghAjcMCherxLF9+fx1reGsnBE7/O4VadfSlQhIqva4V5W5gy5tNPzTm95sdpdPa8j/OxHX37PqcS/bVrVxt/PvQ8tlVsirzNGmN8U21Wp1BixYnZl8O3L3ShasQI+37/BSaPrePrQYm+PQMHAmPH5ixdYZZDh+AYoqkRhBginkwT8XQudhLrzuG+TDt0OaF2IlJ5TMxeK97XXFnsxwgMx05UwTQ8gEEYDc+uXWo7Civnv/UkWoxsgmbXJynTlFUzqT+tkL9zIIwCp8ko3N9/gYVj+xPM9Dax5iZ9eKyasnRscjcyhQg1ghBDxJNpIp7OxU5CcXp1C/4m0oMHNdPRE0/4NsewFJIdBLtW9M/r4ydMQ3clzAzHMyiLf7ADVTAIY3AExXLsJxQzaSih0NyWx3jwwfB+/wyLxw7kdK4LjPTh8S5dYdZXhql7nCJmhZrRo0cjKSkJfXUHA0FIAOLBNBGP5+Kmoo7RwsxE+tJLmjmjbNnsGg+WSLKDYNcKP++IOfgJF6E7ZiA/0rAODXEX5qEGtuEVDMAxFM3cT1oa8PLLwL33Wo9GCycUmqYz9qW3sGf29//KhjBsbyjoGYtnUlOUnGzuu9TUOUVM+tRs2LABU6ZMwUUXXRTtpghCVEwTfEL0NcgGSsjlNuLpXCIBJy76iOi+KRQEyIEDmnbDbL0epzA7kdKM4Q01OcHguQYLY/dpxjpxQvvgggtUn/WscBMO7ymOZWiFceiHb3G1z2uOWiWWcAp2TKPpy1iDKRwN43PPZf3POpgtWwKPPJKzCrc/Pv4YtmMUGK366jCVj1PEnKbm+PHj6Ny5M958802UKFEi2s0RBEeJZdNEPJ+LXXibZQgnMuZzY1635s3N+XNEI+9POJN4MDMJrwdG5QSDGp/Mc/37b9R5913kYT2mzp3VQXgtPftqcVTFTnRKmpNDoNGvuSFDNK2SlX7zPn+7NIzMxssamdRwmRFWFizQzsFOqDHSHy6s+Oro6HkKnSDmNDU9e/ZEmzZt0Lx5czxnFGd9kJqaqhado0ePqtf09HS16Oj/G9cJkUX6PHTattVU0Cw1Y4wa4RPm6NHa5/661W39Hs65xApm+3zRopz9QPMTJ5CJE7WJ36ju//ffrEg49lOw/YwZk327UOFE//XXwL59mlmhYUNN8OT/Zs0RwSZQY7SMfi3wGfb11wN/lxqfH976AZevmoA8H3yAC8+lsvUcOoQzjCsuW1b1wcz5BTBoULrPa65VK6BrV+vnwvM3/sTXXKOVfeJhwykxoHPypO/f2/u3GTTInt/BSIEC2rlx4f753hfJyenZXo3tCvc+NjtmJXk8dnS3M8yZMwfPP/+8Mj8VKFAAzZo1wyWXXILxfsTSESNGYKSPqmCzZs1CwYIFHWixIAiC4ASlfvkFtd9/H6V//TVz3cF69bCtbVvsu/LKxFL5xSEnT55Ep06dcOTIERQtWtReTc2uXbuUk24lirYAvv32WyUo1K1bFw/qbts2w2P26dMHKSkpSqAxw5AhQ9C/f/9smprKlSujZcuW2TqFEiD326JFC+TNmzci7ReyI30eHaTf3dfnfIpt0CC8XC1Llmgak0D7oXmFGhsmowsWOcOcJJMmAYcPZ61nvjlqhyINz8VXst41a4A2bfx/79aMNMxJ+xUZufLgnxs6oOiwR7H234Oq3y+zcK2z7Mjy5dba/N57/rUnvjRnkeqjDz8E7r8fEUFPZhho/9TQTJ+egu7dW+DUqaw+p8bKWFUiFHRLSzBCEmooLVF46dKlC/bt26cumnr16uH9999X74cNGwa7+f7773HgwAFcdtllmesyMjKwevVqvPbaa8rMlNvrTs2fP79avOHA4mtw8bdeiBzS59FB+t09fb52LbB1a3j7pilo/frg+9myRdvO6NBqhP4SfC71lSzNzknZH8y/0rSpb6GLDtL0JmCRxyrYgV54FbtRCROgRcB+gPaojhfwztl7sWd5RdT8Kx1jx35q6VpntNMXX1jzAdEjlPwdwujwTZ8YCkBGx2ie8wMPAMOHW/u9fR2vfPnI+a/oPkJm9k+BxijUXHWV//4xi9nfMCRH4Z9//hlXsZXKk30e6tevj3Xr1imhZubMmYgEN954I3766Sds3Lgxc7niiiuU0zD/9xZoBEEQYgE78vBwwgk374/uAOpk9ldvTZI/x3BGIv3f/wFXnf0ac9EB21ADA/GyyiuTD5rf5FnkxmgMwR5UzJaan5qSQOhO1XREZoQZfVesQO1VsJIeeig0yxVQIDHmemH24qee0nx6zOLPCflaE4kbWVzSajSSnuwvlOrfpEoVOEauUNWpugZk+fLluPXWW9X/tWvXxt4IZcoqUqSIEp6MS6FChVCqVCn1vyDoSMVnIZYIJ0rGmF02nLw/oSSKM8vQoVrkTiDoUcDyANRoeDN/7hnseGkuvsY1+BqN0AEfIA8ykILmuB/TkA7fT/D6uQwe7H8MMGY/pkB15Ijl07NcOd2Y60UP0TZGAgbCTDbhHj38p0jg+uPHNW2XFShQerfTimAzfTrcLdTQ1DR58mR89dVXylZ80003qfV79uxRQoYgRAup+CzEGqE+/XqHvTMVS6An8EAT4vPP25+sTYcTaEpK4G1On9bML973KoWEf+57HHPxf7gG3yAV+TAd9+Ei/IiWSMFStIYnyDTG8/JVPiGU0ORQyjT4e8iiqYt5cG6/XUvux3w0zOHjbwoNluZAH/uG+zFj0Z8q1OmZPlb676InhgxWJdzbdOgYnhD48ssvPcWLF/fkypXLc99992WuHzJkiOf222/3uJUjR45QflWvRtLS0jwLFy5Ur4IzRKLP58/3eJKSOLxkX7iOCz9PdORad2ef69eu9/Wrr3v8cY+nUqXsn1WunHVN89X7uvd1H/i6B8x816mFbayBrZ6lk7artn35pcfTAD969qOMZziGe8pin+l9JSdr/c7XWbOyn/OZMx5PqVL2t9/7OOxb79+N79u183hy5cr5/cKFPZ4PPvB4Ro70eEqW9P97e8PvBGrXyJEez/Ll4f0uPH5qqvab8DyffDJwnxvXFy3qidj87U1IjsIMpT548KDyRjYmwKPzsIRKC9FAKj4LsVSV2hv96dc7Sys1OHwy5+ejRvk+Bo8dLOiUGpy5c3Om19fvm+jjwbX4Cv0849AOH2P+gHuR0WOmOleWNKiE3UhHvpD37m1yo2YqEr5D3ll3qQnyHpP4+/rTDtE0dNddWrI9ajfMXFMsFEpTViDefBOoUQNha6J4PYZSfNRJA07IyffomOud0bcadV+C4PKKz/4iPwQhFHyljOfgT98DKzWavMsieE9kui+GNzRpBJugaQLylYA9EjWCrJAXaeiAeeiHcbgcP2Suz3PyCL5a7UH58prNJRyBxrvUBgU5M/4roUzc3LduXgrHR4nf5bUQbKzitcdCocHYvVuL6gqXUKupn8uB6F6hZv/+/Rg4cCC++OILFWbtnb+PodaC4CRS8VmIhkaGgzydYL0nL716M7UvVrL4+hNcAqGXUzCz3Y03uud+eBBTMAzPoCK0MKVTKIC30RUT0Ae/ow5m7dMmbAoloQheug8KswTrGi3+dpzcI5Fvh4Ily1iwvXTWDUdY1P2AKIz5E3KtatlmzND8dlh2wWlcXyahW7du2LlzJ55++mmUL19eJeIThGgiFZ+FaGhkOMEEM3m2bg3XEs37oTQOKoFmD8rjdfTEFDyEQyidrW16tI0vM45ZkweFSqsFGMOBAq2VnDP+YE4blkUwtrlMGa2MFbU4FGqsns+xKAg0xIpTcVSEmjVr1qjIJ5YoEAQ3IBWfhUjizz8ikFJaN3myTlIkoWYnSBk8xZ9/Ai+/rNUoYiSMMe+Iv/vGHjy4ASuUiektPICPcZtaSyFmJ6pgLjrmMC8Zo7R0fyPWY6LPiVnog0QWLjRnorELu/rRV/Ufaga5noud9ZwrV9bCthnlROy+FqghcrVQw1IDMVQySkgAjE90ej6GRK/4LNhDuDlcmGwtkvETnPxZ9SVYFnkme+Pi7fej3zdW4D3FsgnML+Mv03B+nMbdmI2+GI+LsUmtK4JjmUINtTLv4VyFRj95UXSomeCxrAg1550HnDgBdO8OW9BNWE5g5ljGEhbhUKaMlok6Xz6tCGckNFoUqF2dp4YFJAcPHoy//vrL/hYJQojoT3R8CjXCwZvrrThtColDsGSN4TrTUjMSSQ0So1pMlsXJBs9JF2YGDjT/Pf0hYepUYMcOrU4SBRydMjiAYRiJHaiKGeiuBJrjKIRX8RgewFumjjFnTvbfgb+BsbSAGfSIILsEEe6HGYEpGDKhoFlC8c5w0i31n3+Adeu0/zlGclpnpmOWc6DAYwdWszQ7LtR07NgRK1euRI0aNVSm35IlS2ZbBCFaGG9KYxpyEWgiRyxncDaTrDFUZ1o92R0LTUYCO5LHUfv00EPA+++b/w6HeP0hgRoFOh8zZJjny+VD3ImRGIHzcAC7UAlPYAwqYxd641VsxQWmjuGdyC6U34BaGruh9ofCkrfDtT9Gjsz5kMVrgponX8IO10XDB2vv3pzO6mx3qNFO3thpKouI+YmaGkFwK6FEkAjRDWd2k5+MMXKJ5xCKM22kTZ52ljWwqgHJFj7OBixbhvY3XIMPPyyu2vTG7keRH6kYh36Yjztwxk8ZAysTrVsc/FkQlDRqpDm/+us73YePNZ24UNjXo9Q4NjH6io7A3rA7P/3UervCjWoq76N/7YyMc9LsH5JQ05UeWwISPWGYkNjXiFmhINaTNZpxpvX2gTAmzUtPt7/90c4v07vHKdy6712kvjgehXb8hi09XkSxjo+r8OnlKR1xzdss9hReVOz+/Zr2j9cdhYhQQ7vthBqpunW14peBBBpeJ6y8zbIHFIRoqtN9j+jUbfc426sX0KKFdp/yeGynmb4KFEBhpyAZSk0tx5PvMRfNwoUL8dtvv2XWg2JhS6mWHRvE8hO2EP1rhJN9LGdwtpqsMZAzLc+VPiB8cnfqASFa+WXKYS964nU8/O9k5Ol5SE0gR1EE097MwJg39a3sSfFBwcFo8mIOGAoJ0YTXDDP+BkL3wAgU1m23ifaGG7Jrp596KuthhEIO22I1gMJMRKlZTaHVApqOCzVbt25F69at8ffff6NWrVpq3ahRo1RU1JIlS5SvjeBeYvkJW3DHNcKKym7K4GxV6+hL9R9IeOD9QGdaFiA0TkgsP0AfCAo0Tmo6nTfHeFQ4dhe8i3zQVE/bUU0lypuO7jiGohE9Os010RZozMAoNLbVyeBg5uPxvsdye5ng69cPXIIj1IjSChVYyDp4G+lH5GpH4d69eyvBZdeuXfjhhx/UwmR81atXV58J7iWY2p3wCTuWnD0F568Rs2nm/WkU7HQu9uXsy0mfwrmvY9IpltlVrQgP3NdLL+VsJ59AFy92phq8sc9o0op8PR3jBZCEZJxSAs0aNMYd+BA1sRUT0DfiAk0swSg0p7Od0LQVTJhuH2IARbCI0iZNzLWxQQM4RyjVMgsWLOjZtGlTjvUbN270FCpUyONWpEq3VmHVTFVWbhdJEqnP3YSZfjd7jYR6HfmrXBxKFXV/ldn1hdWt/R0z2FKsmFaVeM4c3xWVfVUy9lUJ245rPZT2h7oUwjHPo3jN8zsu9NTGr5nrL8TvnivwrSNtsGPxVzE6XpbSpbVrU6+azSrcy5dr/3MdK5HbBfelH8e475tuMtfn3M7VVbrz58+PYz5crY8fP458zOAjuJZYqpEkjszR6W9WCDYDfQeYAIzDllkHRDtNn2YigKhdoTaFZqNA2/lzbqQ2xGzCN6u+RGavb399ZjeVsAuP4TU8iKkogf/UukcwCX0wUf3/BzRXA8F59GSHfNUdlPnKkgn+tJyVbPSR9BdR+u235r5vdruomZ9uueUWPPjgg/jmm29UZmEu69evx8MPP6ychQX3Eis1kszkDxEi09+vvWbuO3oxPe98G/4cEO02fZqNAGLCtFAFAisZbAmP451jxYrJjM6xRnOcnaHb/rgS32IW7sZ2VMcgvKgEmi2oiZ54DU/ihcgdWDCF7s/CUHrviKtA98rf5x4UIjlm/vefvdtFTaiZOHGi8qlp2LAhChQooJbGjRujZs2amBCJmu6Cbege7f6yXOoJw6JZI8lfUjEnbtJExGoSN/0aYYSFlQzOViKO7NQmOhl5ocNhkNWgjZPOmjWaP8wzzwB33JGzL/S6PkYBPtKh2/mQiiVog7sxB3mQgRW4Hm3xCWphM95AT5xA4cgdPA4pHEJ3sYTGk09qmZk/+EC7f4zw/grFf8rjgI+k2XvL9dFPxYsXx8cff4wtW7bg999/V+vq1KmjhBrB3bi9RpKV/CHxYoqKppktVE2Afo1QcOFvYab9dps+naz8axUWUeTCyahHD62mTps2wKlT5r5PQYaCDxc7KYKj6IB5KmLJg1xIQ34VwXQBtqhkeT9CihSHAgURZhqmuTOUEgIvvAC88442NtOh15isr3hxa2UsnIxCZD2u06fNbef6PDXkggsuUIsQW+ge7VZD/NyYPyTWiXa+oFA0ARxgjW2jAENBRhds+MpkaawnYxR07DR9st8efBCuhyYD/pYUakLBrH9TMKphO3pjIu7HNBTFMexBBSyFlo//eVgoZCTkgL/tqlVaDa5w0DXRvL+o0bNTQ7d3b+RC2M0INcWKwX1CTf/+/fHss8+iUKFC6v9AvEKvPMHVWHnCdpJYcmQOl3CdZu3Q8FjtRz3R3KhR2nsenzlfWPzOaO/3lWGXlZeDYcb0abfjrJkK17GJB42wDv0wDrfjI+SGZgP4FXWi3bC4Yv16rX5WuEKIfj2Hou0xW94hEFbHE96HZmtDmdVQOirU/O9//0P6uXzf/F+IfdxYIylWHJmjbWazS8NjtR91TdnzzwdOxe5tw+d2Y8cG3//LLwceSCPhOEvn3GnTApdBiDVK4SA+RWtchQ2Z65ahpTIxLUMr27L+ChozZ8LVvPmm5gPn797yN57Qyd5XpmyrDxaurP30JbP1+PhfEOzETGpuf7VKYolwzGx2hkWbqWvki0Ap4MOBYav0JfD3tBgJx1kmRacwaLf/itPkQXpm8chDKKWKSp5GfryLLhiPvvgV9aLdRCFK7N4NrFgB5M1rXkDxVRKCYwUNMTTWWBkvypSBu6Ofunfv7jNPzYkTJ9RnghCuI7OVUGE3YTZTbqhmNrvDogP1dzTo0MF3GL/er3b5mBjZvBn4+efQIlfcQE1swat4TIVkF4Ieg56ErngbVbATD+JNEWgEtGqV895itJUVzScffniPWn2wOHEC7hZq3n77bZzyYSTjunfowi0IYRAsNbdb61JZya0TqpnNzrBoXVBITdVqObGOS7Rh3RzvQZQalPPOs5ZDxwojR2qaJ6s5aaKLB83wJT7GrdiMWngMr6MS/sYdyJL6GMn0D8pGtZVCTqL18ODxhC+ghGqedVKosRT9dPTo0cxke9TUMD+NsWr3p59+irJl5SYS4teR2R8UXHyZL/TQXGoYjMJYqGY2sxoeOu8G8pdatMi3DZ0TPLMEUxvmK+TfaZ8T/XiMIhK0vDL/hznoi/G4FBsz1y9GG+UvswI3RLV9Qk6875tw7yEK4PQBM9673o75ZnDyXnYy/UIeq/lpkpKS1HLhhRfm+JzrR3JUFIQ4dWT2BQeTYOHF/Nzo9BtqviCzGh5+l/CYvoTBLl20/BhGOEhSY0NtGL/jS+h54IHI+dPEK3bm6KiIv1WOGUYynUQyZqKbyjMTiyUMmMMnEYRVu4UH+oAxl43xgY+Rh9S6eFzq6H7bbS4VauggTC3NDTfcgPnz56MkvfrOwZpPVatWRQU36LAFwUFowgk2OPNzbnfjjVnrqLlhTgo63hmfsnLl0hzxfJnZdA2PGZUxBRsuxqgo/Tj+Bj+upwC2f3+WpozapH37NNMQTVV86uL5uHUAdRtpaaF/tzZ+QzOsxGQ8ot5vx/mYjIexG5UwFQ/iX0S8VHfEoGBdogTw4ovOmiecgvdxJDLpUojx9cDHh5EePXKacN0Af2dXCjXXXXedet2+fTuqVKmiNDOCkOjomT/NbGcUamiyYpizt3BAwYPrmdTLW7DhYGY1cykFID0qyszgQoGFIdvDhmkDJDU2ifBEHSmsT2wetECKyi9zMz7DWSThc7TEn9Cyu9F/JpbRTSW6NjFeiVRpAH+5YThWFCsGNG+OiKKbxvkwRt/Bc5leAsKxh6UgXOsovGLFCnzIVnrxwQcfKCdiQRACO+e+/76WsCuQtsNXFBPfM7LKKjwO97dnj7ntKTTRFEV/IBFonKEATuF+vIWf0ACfo1WmQPMx2iEPziBeiFQdIjdx002R2/fDD+esK6bTrFng2n7+6rjNnWvNX5ECKR+UzGpgzI47URNqRo0ahdI+PH/oJPwCi1gIQoxgNgQ7EGb9fjho6NFR99yTs+KumSimcPK0cH+BjmmEkUDiHuccrJS9E1XwFnqgPn7BMRTGBPRWNZna46OY9JmJJ5h1mg8FTEZnNnzaCi1bmt+W2lNqY3xFVua2kKLB6LvH+B4zYx/zzRgjUM1oacI1wToi1OzcuRPVq1fPsZ4+NfwsEkyaNAkXXXQRihYtqhZWCF+6dGlEjiUkBlZCsIMJNcGq6DIHCoUEqwIJo5jsLA9hcIMTokxWThmWLqirtDE7UAUDMBaVsQt9MSHT5CREF44JFGh69QqsCdE1H48+ai3ih6UWrKJHVjIjtvGBrL2flBjemhhjigyz4wr7wGgSp9+QGcxuZwchHYoamU2bNuVY/+OPP6JUKDXSTVCpUiWMHj0a33//Pb777jvlrNyuXTv88ssvETmeEN/oWTS9hQw9K68VwYaDRZMmgbehg20o8CnK2JZwy0O40YkwkUjCWbTGEqSgOdaisfKfISdQGE2xGjWwDa9gAI6geLSbKhi0E7o21mxy0Hz5NG2sWcKpPcbjeT+QtW+vRUgx+f+sWdorox2N77dvzxJQzI4r3oKS2cg+J6t0M5rJMk888YSnatWqnhUrVnjOnDmjli+++EKtGzBggMcpSpQo4XnrrbdMb3/kyBGOIOrVSFpammfhwoXqVXAGs31+5ozH8+WXHs+sWdor34cL91GpEg08vpekJI+ncmXzx0pN9Xhy5/a/v3AXtlVvi952tjGUfb33ntbvFSumRay9smRfkpPTPIvmzPH0zvuq5zfUyvwgHbk99bEp6u2LtyVfvqx+57XO13D2N29eznt+/vycYwjHDK7X4Xjl5HlzTEhKyt4Gq2Oiv3HF35jYunX27fz1ObcLF3/ztzeWop90WK37r7/+wo033og8ebRdnD17Fvfee68jPjVM9EenZJZloBnKH6mpqWoxJg8kLMypF+fU3xtfhchjps+ZIG7QIE17YnxSGDMGaNs29GOvWaM5vyYn+9+GvierVwfXwJBJk7Qns0jBthrbwidFhsMSDhlWWLMmXTkxTpyYbulJUgiN8p496OV5FS0fmIJb0jVz038ohhl57sek3I9id64qSIaMO3ZCjQk1KsnJWr/qr6HAyD/mWPEepjj+tG4NfP21lu6gXDmAUxGPq2975ZWaKcqsH5td5z54sNY2q4lK/Y0reh4tpnqYNy/7udarp2l9dPz1ObcLd3o1Oz8nUbIJ9SB//PGHMjklJyejQYMGyqcmkvz0009KiDl9+jQKFy6MWbNmoTV/PT+MGDHCZzJAfq9gwYIRbasgCELZ779Hw2efVf+fOO88/Nm2LXbeeCPOBJKoBUHIwcmTJ9GpUyccOXJE+dVGRKhxmrS0NOWIzJNiSPlbb72FVatWoW7duqY1NZUrV8bBgwezdQolwJSUFLRo0QJ5WcZUiDiB+pwObw0aZNfQGOGTAzU2dOsKpWwCNT1mFIpLlgTX1FCbRKfAcGziZvjkE+1c+VS4bRvrr/nvn0DwCWr69BR0794CffrkBUu1ORluGc/k8mSgzdnFKOY5gvfy3KvWJXnOYtrZ7qjevwpumfIkTpx20rkgsTFe66dOhT6um9EOc8zStTa8P0M1WND3hGHS4QYEvPmmVsvNW4tkBu9zGTUqp0ZY9x+iL45x/PDX58yC/O234Z0T529GXQcTakybn/r376/MToUKFVL/B+IVZuWJAMxaXLNmTfX/5Zdfjg0bNmDChAmYMmWKz+3z58+vFm84ifoSXvytFyKHrz5fuxbYujXw97Zs0SIGrJZR4A3Ly8VHPdYckQFNmwYeCHRn40g/FhQpAnTrFpoQ4w8OOMOHy7VuB4VxDPdhBvpgAmrgTxxEKbyb3gmnoWljuifPxOxrPsWJCQXCmlyF0GCfh9PvHIsYZcSK1rzffY0D3iVFQoXjEvfFPLfeJRCI2bGmX7/sSfoY9cj9PvVUzjGNY6J3jT06HnM9nY+9y6kYodBjps/ptBzu1Gp2bjYt1Pzvf//LtGnxf384mWWYfjxGTYwQH5h9SgnlacZsnhemGw8k0PCG5yDhhJ7z2DFtEdxFFexAL7yKB/AWiuOIWncIJVX5gnxIyxRqhPjg//5Py2d1112RfbCZOBEYMgRYty5L0GByPOoSzApO//yTM+qRNdu47969gQsuyBKYKAB513ijfw0FITsENXL6NBwjj5W6T77+d4ohQ4bg5ptvVuUZWCGcfjErV67EsmXLHG+LEFnMhheGEt5sVhDiTR+IcJLgCbEPM/+yBlMeaMlBfkctjEdfvIN7cQrirxeP8EGGGpP587PqqEXiwYYCCE1eRgdjChoUqmh29lcmwWzQwfAgBWn1tBY8N7twMk9NSNFP0eDAgQMqumrv3r0oVqyYSsRHgYY+GUJ8oRdt5M3la8DQa49wu2gJTOHavIXYIjfOoBiOZBaQ/ArXIhfOYjluxDj0w1LcDE9oab+EGIOZhfVir5F6sPGOmOJxWA8uWD6df8IQeHQ45nKMZSkXu6hSBe4Tatr7KhnshwVWU7KaYNq0abbvU3AneoIrPi3o4YS+ElyF4iTcqFHgm9+swBRuEjwhNiiG/5R5iWamdWiETtAKb7FsARPl/YWcmdWF+EYvX+KmBxuOaS+/DNyr+aeHDcdcjpHMikztTrjaKCeFGtOPFtSO6As9j7/44guV2VeHmX65jp8LQrj4S/VtTO1tFcraNWoEFmh489IpkINWoFooujZJCtXHJ+djm6q9tBuVMBaPoyp24jqsQjKyvCZFoElcdF8Xt8AxLRKFZ+85l8sq3HHut9/gPk3NjBkzMv8fNGgQOnTogMmTJyP3ucdlJsR79NFHA4ZaCYIVKLjoal6jZ74VDY3u2c8aStTuBLP7cntux4VPKW+8obWBr/T0p1DEEG4m2/OnTbIKv08NEqO+hOhyFb7BYIxGO3yMXOdKGPyMesrE9D46IxUSku0UnEoinSohVDgW8Z7lGOFkcr1g2ppKlew1iXHs45gbbnSXHWaxiPrUTJ8+HWvWrMkUaAj/Z6h3o0aN8NJLL9nZRiGB4SVmNWw71FBLb82MMZTSyIABWsZOvjLDpnf0gFUoEIlA4w6uxVe4HQvV/0txE15BfyxHc1W1SXAWCjR80Dh7NtotyZligbEyzL7rFoGGUKs9YYKmaQ4XoxmeY7D+cEk/R+9wcTNEMuO6LULNmTNn8Pvvv6MWM+oY4DqGWQuC3fjKpRCtHDK8xBcv1hbe+B07alEJbhrghOCUwL94CFPwC+phEW5V697CA6iO7XgNj+F31Il2ExMeN04nTK/wzDPOOO1aFUA+/hhgTelwTFG+/BaND5c//ghY1VtceincLdTcd999uP/++7Ft2zZcddVVat0333yjqmjzM0EIVRgxq3HRcyn48q1xMocM20QHPSF2uBCb0Rfj0RVvoyBOYQOuwCIwXWySqo79GF6PdhOFGIYCzY4dwIUX+o/gtAujAEKB5k4bHuQ4tnJ//sZW5uqxSsuWcLdQM3bsWJQrVw4vv/yyCrEm5cuXx+OPP44B1MkLcUko2hJ/wojZgpT+NC56LgVfTsOSQ0bIiQc3YAX6YRxuwZLMtf/DJXgVvZAEDzxiYnIVbvapCQQ1NN98Y5/PnRkBhOYhZv/1eAL3Z+HC2csasOAmH8ooiJkZ10MdWwPk63WHUJMrVy488cQTatErX4uDcHxjVVtiRhgJprEJpHHRcynoOSOM+7KznIAQH7yJHngAWlqIs0hSmhk6/67CdeIv41I4tURSIIgkFBDuvlsb5+wqoeALmoE4/q5cGfwYR49q4zLHylA156GGsVMYcoqQs0XRr2b58uWYPXt2ZmmEPXv24Pjx43a2T3ABuoDifdPoAop3WqJgwggZPDj4cYM9FXBfes4IY1sp6AiJTRkcUDlmdBbjFpxAQbyGnqiFzbgNH2MV6CQgAo2biUWBhpQtq71S4GDdIz00OhiMqLJC585aTSqzwsaBA5pvDAUuvlp1BQg1jN3JMgkhCTU7duxAgwYN0K5dO/Ts2RP/nPOIGjNmDAYOHGh3G4UoYkZAoRBhjBwyI4yYeXKxWgNKF77EYTdxqYef8SYewE5UUQnzdKiZqYTd6IXXsBVBamAIQpjQmZa+J9SgEJqGzFC9emilG1jg1wzlw8ytE2p+rlASpToq1PTp0wdXXHEFDh8+jOTkrKJtt99+u0rAJ8QPoWhL7Mq0aaWkgZPOwYK7SMJZ3ISlWIaW+BkNlJmpAFJxJTZkbnMWufEfSkS1nULiQNfSTp20atcUaMxO6lWrhna8N9/UQrqT/AgbXE//mVBKy/jK9q7v0yznamG7V6j56quvMHToUOTzCj6vVq0a/haHBiR6xWy7Mm2aeSqggxtVtuIcnJh0xUz8jPpYitZoiRRkIBc+wJ1ohLUqgZ4gRBtOiSNHak66gWAodt68oR2DY9+DD2r/+xov+bD3wAOh7ZsPjNQ46Zon+jD6yvYeiDNn4G6hhrlomEHYm927d6MIMxMJcUMoBSCDCSN6XgU7ngpo+WSWX4YzColHU6xGXfyGoyiCV9APNbEVHfABvgadE8RfJt7xjk9x0sxhFl17HKxSdWqqJvyEygUXBBY2WJ2bWiPdB9JbWPFVFobb8jvUOBk1T4S+QmaFMCc16CEJNS1btsR4Q855OgrTQXj48OFozVSrQtxgRkDxVmsGEkb096NHZ60LdHP5qwHl/SQUrASCEPtcgv/hbdyLi/Bj5rqXMQB9MU75ywzAK1KPKcFg+RJm9501S3udMweuhdFHeli1L8KNseGDZftzjsn+hCM9uOOJJ3wLK8agj2ABInyQNCvUBBPobMUTAjt37vTUrVvXU6dOHU+ePHk811xzjadUqVKeWrVqefbv3+9xK0eOHKG8qF6NpKWleRYuXKhehZzMn+/xJCVpiyZza4u+jp/7+16lStm/U7mytl7v8/nz03Jsw/fGfZ454/EsW+bxFCmSfTvvtuTO7f9zWbQlOVnrd75Guy1mliRkeNriY88KNMtcOQNdo96ueO7zWFq+/DLnuNO3b+L1e6lS2jhJ+Oo9pppZjON5sH1wO47lefNmX++vz/Pl80Rs/vYmpDw1lStXxo8//oi5c+eqV2ppmGG4c+fO2RyHhfhA15b4ylPjL/NksIKUuuMY66eczCp8nCOXDendO3juGd46gapqC7FFIRxHN8xEH0zABdiq1p1BbnyAu/A6eka7eYILoD+dL8dXjjmJprllWQRqTtq3D92/0Jj7q1gxcwEiZms6OWkWtCzUpKeno3bt2li8eLESYrgI8U+oFbP9FaTUBRDeHP5uLjq+Wa1hYhSGhFjFg/W4BvXxi3p3GMUxFQ+qeky7UTnajRNcwuuv+x5/dJP5v/8ioejaVRujw4k+1YUVPRQ9GAUKAGlpwbdz0tXWsqUrb968OO1kJh3BNegCSqiJm4y+M1OmBL+5QinK9vDD5pyQBXdxOb5DLuiqtiTMxt3YgproiddQGbswGGNEoBEyefxx4K67fH9m9OkLB/rx0bmWD0qxAH1yOne2L/rUDGbz79RxsDZsSO47TLjHRHvMKiwIZvD2oh8yxP5jMCSSwta4cfbvW7Cf3DiDO/Ah1qAxvsOV2UKw6QDMzL9voCdOIEgsrJAw0NGWGXRffDFwoAE1y+++m/P7VnKr8Nm9Xj1g/XrEDB98AFx9dWgJ8oxwHDUTIGJWWKlQAY4Rkk/Nhg0bVJK9zz//XGUWLlSoULbPF3jnzRcSGn91oCJlVy4hOdZcTREcxf2Yht6YiOr4S61LQ15ciD8yt0lFgSi2UHCzUHP77YFr0pUurUVF3XYb8OmnwJIlwL59wP79QL9+1sYTZuuNJc6e1bRYr7wCdOyYs3aWmVpa+sOhv4Kcxsrg335rrl1VqsDdQk3x4sVxxx132N8awfWVt61+1+lMvz16ADfd5MyxBGvkRRrGYJASaIrimFp3EKUwGQ8r5999cFBvLsQkFF445nDS9fewxDIpFEZYX+6aa4AmTbTQY2pyEsXXaPZsrQ/WrMkeZEGT2n//mQsfNxMgsny5uTY5WW09j9Wkey+99BL++OMPpKWl4YYbbsCIESMk4ilBKm+H8t1QPPHDqcxL50DmrBDcRzryohHWKYHmV9TBePTFe7gHp1Aw2k0TYgg+RJl5WOJYRKGGE3vTps76mkSbf/8F5s7VtC7MWcPEfHo5mebNg2uodMExWIDIn3/CdVjyqXn++efx5JNPonDhwqhYsSImTpyo/GuE2CNQYiUq4Z55xn+mSStVu0PxxC9ZUnPQ884WKsQOeZCO/8NsrMD1KI7D59YmYRDGqDpN9VXhyQdFoBEsw4nVysNSmzaaPx81OOH6moQKx7Qnn3T+uIcOASNGAPnza0IKq3SbYf78rLHfX4AIx/lly8ztj9mSHcNK8puaNWt6Jk+enPk+JSXFky9fPk9GRoYnFpDke6ElZzImwzPz3TJlPJ7UVG375ct9b+OdpKlgQY+ncOHs23i/lyX8JdIJyYrjX88TGO3ZiayLZCBejPp5x3Ofx8PCMeWDD7RX7ySf3gnfOAbNmmWt3/XEco8/7juRqJkl1O/oCe2YKDBa/Vv5XL9ZbYN3ItRgc4i/a/3SS51LvmdJU7Nz585sZRCaN2+uSiTs2bMnEvKWECGsmoSMGhgz32U9JtpumYqbuRPMwAR83nbecNOGC85RE1vwqsojUwljMBiVsRv7URbDMBJvw+RFICQkjFZkan+OMcHKq9CXg5oCq6YkfXqdPh0YNsx8MUY9yodRRVYKOOpQM0S/FJpxzBTojRS7dmljt9U2+NK+hzKH0I/HKSwJNQzhLsBsO155a5iQT4gdrJqEOBgQZpo0W4Sdqt6XXjK/vRC7lMC/qlL2Y3gdhXASP+IidMMMVMFOPIth+Adlo91EwaVQYOjVK8uk4a/Wm1E4IJycQzFP0xxDHxOOaXzlmOZvP0ZBihM7BS/Wlxo61Lywtn17VpvNFOiN9Lif22IbjGO/0Q3B6hxSvz7c6Sjs8XjQrVs35KeB7hxMxPfwww9nC+uWkG53RzKF4jDHi5vSPrUwQmLDKKZmWIkUtFTvD6Mk5qEDSuAwxqEfVuAGqZAtmEJP628cq3TnVPp06Jlt6cthzEzO1A3hRNTwYYt+e5ysdQ30q69mz0LsXQZG9y1hW2fMCPzAxhIOjz6ac/z1F1HkBOXLh9YGfezXnYeN+zKLk8EbljQ1Xbt2RdmyZVGsWLHM5Z577kGFChWyrROcx1+JeF/yZThqUD55OFnHQ3APpXAQT+E57EBVfI5WqI3fMj+7DzPQFouxAjeKQCOYhloDX2MVhZZu3YDnntMWRuzo2+iRT3ZAoYX7njZNy3JurPht1LIYYduCJdXnw1+NGr7HX72StlNJQpPOmdCMdbL0NvA8H3vM3H543qHMIawP5a8yeUTwJBDx6iisV9EO5KTm7zuhOL/ZsYjzZOz0e2386pmMBz0nUSBz5W5U8LTC0qifTywscq0HX4xjVbDxrGNH+/s90FhpZqwNZZ9mnJ3NLKxKzirdoZ7XlyadhxkAolcC1/vCbJ//95/HnY7CgvsIlK/Bnz00kO3aH5TIRUOTWFTEbnyKm/Eb6uIhTEUyTuM7XI7OeA/VsR3LIFkOBXvQxyqOZb17+x/PuDD/SqSO72usDDWRaLB92pU3h6Y6Zkumj1DJkoF9kXxBrQvNZcGg9okmKB3u88ILzbXREF8UcUSoiXGCeaEb7aHe6CpI3gzB4H783exCfHIIpXAFvsNZJOEj3IZrsRpXYgNmoTPSkS/azROiCE0KdsMxhmNZtIILjGOlr3pSoSQSDTT+hhsNZTQr8YGTUV0HDpgzoRnhd1kI0wzeDsKH9RRUQdiyBY4RM0LNqFGjcOWVV6JIkSLKr+e2227D5s2bkeiY9UL3tZ1+4waraMuL3i4btuBOymI/RmA4VqEpknBWrTuNZHTF27gAW9AeH2ENaJQXfxkBSEuDq6GwsHBhaN+l74gv/0SjT4lVfI2/4UZDUWDSQ9yN+2zmI1GeGW2PGby1S4aYoYCY3S6hhJpVq1ap7MXr169HSkqKCiNv2bIlTpw4gUTGrApT304XZFjYjevoJGf0+PcFv2O2xLwQWzTAJkzHfdiJKhiOZ9AUX6ElPs/8fCla40/UiGobBSFUB2RdYLAiNFBQ8JUtnevtHqetugEYoYY9mBbGLLrWyIqzMWHRTDOY3S6hhJrPPvtMhZPXq1cPF198MWbOnKmSAX7//fdwG75Ul5EimArTeDEaI6R4g1oJz6bNNdBFL8QQZ8/i5owlWI4bsQkX4z7MRH6k4Wtcgw6Yi+UIUhxGECIAxyqOMZzg7czj8u675oUGf5oNs340ZoUBIxRMtm0z59dihPWc7CL3Oa2RLwHQO/GhkZtvNrd/s9sllFDjzZEjR9RrSW/PqBgKrbaDQCpM48VI1amvek1mKVfOWWlbiBwlf/8d89Nux41YgTPIjbnogGvwNRrha3yADsiwlr5KiFFYuTpa+BurOJZNnBh4GzP7Njrntm2bFb7M9YH2becDaCBhwJt166znALO7QGd7k4kPjdDExaKZgeDnxhxDkSYmRy9WC+/bty8aN26M+gFSFaampqpF5+i5bE00XRmzIOv/h5IZmTfB118D+/Zp0vaoUZpUbyxcTvNOly5ZN5jdcJ+86AYNyu5kx4tx9GjN87xBA8ArGbQlaKNl2QK7CrInJ6dnexUiRwXP36h/9id8nvsm1d//1qmDNXmuxXe4ApNyP4pduaqq7ZIhv0UkcPO1nicKM4D+HOqd6I5jlT4++hvPWGw3mA+gntF83bqscZ0CXOPG2kKtia9933or8MYbNp2k1zkFm1roc2N2bKWwRMGDFcjtTubftq02X+hzGh9mGzbUhDJ/x5o6FbjnHv/XOj8/e1ZbwsHs/JzEuG7EGI888giWLl2KNWvWoFIAm8iIESMw0kdoz6xZs1CwoFQHFuKbYlu3osaiRai4Zg0y8ufH59Om4Yw+cvK2j0audkEQhBA4efIkOnXqpKw0RQPUyIg5oeaxxx7Dxx9/jNWrV6N69eoBt/WlqalcuTIOHjyYrVMoAdL5uEWLFqqWlRkWLdK0L1Z7b8kSoEkTOAqfeu6/H66Ckvz06Sno3r0FTp2Koh48zsjlyUCbs4vR68wENDm7JnP9mlxN8HDeqdhbqKr0u8Mk2rVOLQLHRmbo9Rfyq2sbNm2ynv9qzRqgTZvg2y1enI5jx1JQpEgL7N+fN5vWwZ/WnRpt1mcOdVYMdXxnNBnbF8z8VaEC8OKLkdH4h4J3u31d6+xvan3CTQPA+bt06dJBhZqYMT9R9urVqxc++ugjrFy5MqhAQ1ijylinSoeCiy/hxd96f0mYWFnaKrxh1q71X5/JbP0mf+3y9V3+f+oUXAkv/EQY6J2AeWRm4D7UwJ/qfTryYC46qnpMP5y9HEgFknNpKlzpd+cx0+f0e+PEyrpEsYo+1nCsC5a7ZP166/4WTZtqfho0H/kSPnSHYxav5ER6yy1Z/c71NF/58g/h0D9mjPYbEKuCDcdamrdC8VXinEDzfjAoKN7ISiQu4fXXfbfb+1p/880sf6ZQMatwiBlHYYZzv/fee8p0xFw1+/btU8upKMzWoSRh0uEP68+JOBwnY25TtWr27/I910ez5L0QWfScMmQXKqMa/sK/KIEXMET93wXv4QdcHtU2CubgPTpnjpZE7fHHEbNQmDErlFmt9mw2OOL//k+rHeUNBSEKLf7GVN1ZNpT4Ez5U0uE3FMz2A5PruYlt2+zdzg5iRqiZNGmSUjs1a9YM5cuXz1zmRiJndgRuRKMDm6+b7IknfEcn8T2d4555RlP1+QoV/+ADbRvvTJx8z/WMfIpmyXvBfq7GesxBR6WJ0fkL1XELFqMyduEpvIA9CCH5heA4ehgt71FO2LyveY/HKlY0HGXL2h+pM2+e1n9WS8cYoZbHybnBar4xt1Cjhr3b2YIngbCroKXZAmDGomLBtsmdO/g2uXJlf1+pksczcGDO9d4Li52xEBkLkPE7xs9Kl/Z4Che2p7CalUWK/FlfciPdcxfmetbhmsyVZ5DLUx5/S7+7ePHucxYGNH5eubJ2b/Ie5dgydKgz7YpWMVvjUrFi8CKSgdD7jMUh+aq/99Xv3gu387U/7zHSyuJrn2bPw19RSu9x3E2kpmafu3z1OT/ndk4VtIwZnxo3oZtz/Nl0vSldOngOAjP5EbxD4qjFGTs2+Pf41PHFF9rTDdNh6343fErauBEYODD4PoToURRH8ADeQm9MRFXsVOtSkQ+z0Anj0Rd7USHaTRRMQs3Cn39qZgqj75uemj9Us7ZVqBWmP4sTx6MWyt84SVMV2xKs6KI/9LIAdpWOCdW1QPfjCZRkLx7Jlw/o3x946SX/2/DzSNQK84cINQjdpsub0fuG1d8zkpwZHzloUfjR4/ijBds6c2ZWjY9vvwXef996wifBeTrjfbwMTfI8gDKYhEfUsh/lot00wSJ0AVy8OPsETv8O3p9mHpDsQjfd6OMUH3Dog2L2Qc0s3GdKiv8ilTyWniyPY5PVSCi7TTmhmI+sJNnzB4WpYCYvfs7tnExkZwZGY5GXX86+nn1BgUb/3ClixqfGbQSz6dJDX4chb9Hm2DHNv+a880IrkyA4hUdFMV2PFZlr3kZXrEFj3I+3UAU7MQIjRaBxCLvTWTHhHO9D3VFVj6S0KkhwwgjXP45akhEjtGKDjKgJ5neXK5f1rOJ8kDJk1fBJoErWkS4dY4fPSqCMu2YJR7vkFjxe13C4yfZCRTQ1YeBtzuENQUdgFos0qjAp+BQpogkWgQYpXgSRfloL1QFOiCx5kYYOmId+GIfL8QM2oQEuxo8qvukkCuFaZOWcEZwjlLQNZnjwwayxw4q5Q5+o+QRM07M/TbEZvLUk+oMahSxjmwoXBu66C5g8WRunGH5sRaPjHRwR6Qlb16TrWdytaFWCuRbo+XUorDESyWrajXhzFCYMcvFlfmL/6eud1NaIpiZMjKXe+RTWoYPvCq/+BBo98oGDlJB4lMC/GIxR2I7qeA9dlEBzCgXwNRoiGS5NLiTY8nDBCEarE7muFeAk4U9TPH++tpgpQOutJaFgo9dJeu89YNw4TZi5915trAsUTh0udk7YPA8WsrSqVTGen7/+4lhPzRZfOfbbYTILR7sUTdLSgFdeCbwNP+d2TiFCjU2EqkYONkgJ8cvDmKRyy4zCk6iIPdiLchiKZ1VI9sOYglOQUh7RgpOI1arJVqFQY3YiHzpUEzS2b8+akI0CyKxZ2T/XP+P3zGAUrjhJ8wGN9ZGodaY/oDHvlT/Te6hEasLWs+4yy693/wSCnwcKnqCGzO4CxWYLE9shQNkJa2UFC3Lh53bW1AqGCDU2EYrXPAfNrVuzD1I7dmjOe0I84kE+pvU9B7UzhXAS/8MluBdvq2R5z2MoDqF0VFuZ6OiTCLOlRjpppdkndPq++NIKGDXF3p/zf7PZZ43CFSfsQHmvdMGGCdXCFfycmLBZtsCKVsVMnqBgeW6cqpIdbbZJ8r34JRR7MB11vTNQ8qZjRlGz6mPau81sJ0QPCjLdMAMbcQmexrOZ6z9HSzTGGlyGH/Au7kUacpb0EJxHn0ToRxLJpJX6JBvJJ3SrZg1O1PT3CQQ/17PnWg02YHoLfxM29+kruajbHlDtdmw2Ekj75kZquDD5njgKR9kebBSGvGs3Ubpl6Xp/Kcc5IL39dpbDIXNdTJsW2CFZcI4yOICHMRk98TrOg5bfvDj+w3CMxFnkhge5sA6No91MAZp2lAMvJ2lqH5gmn/ejP+dZ1h6iX4w/R91gDruMJNIFCX/H4IRPgSacCS1Y+glvoYnChJnQYm5nJWW/nseFmmnvHD08NrU/vs7fX50mO/Eed/2FnzsVieQr945befRRzVQXSADl+XA7x/AkEHZlFPaFnonSapZOPQOlr2y/fM/1vj7Ts5Dq8P9Axy5SJPrZQxMls21d/Ox5E/d7TiF/5spdqOh5HGM8xfGv9HuEF6vXOu8bZmtldltf95+/zLX+7suRI831uXf2WV/HsAszYwh58klzfcbtrGRWZx/7yxzsb+ziukDfC4aZcd1Xv3hnfLY7e3C88fjjga91fm4HklHYYQI9EQXLQOkv+ZZeF4r2dGps9KdI2lyNYYRmnJRZqZ1anPvuA06csOGEBb88htfwAKap/7/FlapK9oe4E2cgVbGdoFgx4KOPgH37tHuGT+GBHDt53/jSTuj3n24e8X569pXSgfcl81SF8qQfySd0f231NmvRrGIGbmc2s3ogjUugsSsSifmM+Bt3g4Wgx3L24AwvrZQd4ehuS74nQo2N+FMje2NU+5JANzUxmp/0AcJ4IZpxUubA89tvmoAUyxWA3UYBnEIXvIsNuBIbcalax9IFZfCPEmbWoZHKNSM4B+8F3h+dO2uD+NNPh7YfM5OqL0HErTlHzAhN9K8xA7cz8yBHs95TT/mfOK34r9gp8AUTpvzh5kikYCyIoInvmmu065lRc8aks1zvNOIoHGFHL97UgbzZrUZN6U+PxidPs7ZdCkdO1ZaJd8phL57FUBWSPRUPYRDGZH72B2rhLnx4zl9GBBoO/kw+6ST6PfH888Dx46HvxzipxnvOEXLDDda28xexw/NjsAODHgJN/tHKpGt23A3k2BxLLDinlfKVQ817Pgl1396+SHpdL7vD34MhmhoHnoj4pOJP5Wf1ZtWfHh9+WKsjw8GEdVvM4mS+gHjkYmxUWX/vxmzkQ7patx3VsFYcfgM+FTvtvL5/v1bbzEzBVzNYuU+9NRix9KTPcUt3gvYHPzeOb2ZNW76IllbL7O/J34ljrJ3mGqfJiKCJL5rmQ3+IUBNltW8oNysvFvoK6EUy+fTA0G4zT6Tp2jwshMBMdEVXvJP5fi0a4RX0x8dohwy5lSJOsMnWeL8xaZydWL1PjaZoY5vtiGiKJOy7qVO1fDT+4Of+8uVYxUxZgkj4r5j9PSnQOB2JZLffy1cRNPFFy3wYCDE/RZlgqmoz8KIKR8Uu+KYQjiPPOW0M2YSLcAa5MRv/h6vwDZpgLRbgDhFoIgjT9Ov5Oqh9oUmDwk0grOY3CXTvhWMq0k3RzGhL+OrmnCM6bB/72dukxPdcb2f7o5VJ160mQppqqlXTMjh36qS98n04Jpy9ETTxubEQpwg1USaStVSE0KiEXRiNQcpf5i58kLl+Kh5EdWxHJ8zGBlwV1TYmCqwqb8wGywmVwg191ZhLxkioEx/rtek12OyeVPk9ZrQlfI0l04W35iRYRGcsZdJ1Y1mCSPm9lI+gic+NTvEi1LgAu2upCKFxJb7FLNytyhcMwosogf9wOz7K/Pw4imA3TIaHCLbgazDUs24z+ZvukE+NTigZaKn1oe9NrKWnjyR6mQQ6ehrhe71MQjxk0nVTWQIz0Vihlma4NoJaqUaNggt+/JzbOYXozV2Ct7Pdli1atJKZnDdCOHjQHguU8y/NSTpfopkKyV6MW6LaukTFjC+F0Y8jWK2eYP4h4Ti7RhO7/S/MlkmIhONnNDLpuuV3j6RvSm6LWaWtwOzQZgpacjunflsRalyE901dv37wnDdCuCShNyYqgSYNeTEbd6s8M3rOGcF5Qhloraq3+WTq7bDrpvT0ZoSVSOQdsVImwWyxTLfjht890r4p7SNUikN8aoSQVLJDh0a7JfFDVfyFsRiA0siqxDcKQ/AcnlJVsrvhbRFoooxV9T8FAC7ePjb+oD+Omx12zTiLRsr/gsKKndsJ7vFNaR8BE5/41AhB8a5US+LliSh6eNAIa/EB7sQ21MAAvKIKTeosw014Gs9hLypEtZWCJsCbGWj1+4Sh2xwwmzfPns00kBborbfgWswIK5H0vxCiAzVxwaL6+Hm40Vi5z2mljM738RZFJkJNDDyhMScNLxzBGgzH7og5+AZXYy2a4E7MR26cxedogTU4F5ISpzBvUSxCAT7YQGu8T6g65/0RyQzB4UDBYs0a7X++BhI0zAorX3xh3v/CKmbNMNE21wjuILcLo8hEqImBJ7SOHbVFsCbQ/Iq6mIO7cRU24DTy4y3cj/r4Ca3wOVbiesQzdH5kRFCsYPaJzt99YhUnbPy68NWmjfaer6yH80FWloCQnEV5/pE6RworwQRilrwQocZe+Nub8WVyShiP1SgyIkKNCwj2hMblnaxEtoIfKiJrRmBF7K9wLfajLIZhJKpgJ3rgLfyC+kgEqlYFevUKrtJ2A2af6MxUozdLpG38/oQvVoBmXpwnnghdCDFbciLUc8yfP/Dn+fKFtl8hthxuYzXRpAg1LsBMcTUrKvbEwoPrsBIL0Q47UUXVZtJ5Ai+iKnbgWQzDP7BQICsOMFuY0A2YfaKzWvw1WjZ+M8LXSy9p5xwJQSucc4xljUEs40aH21hNNClCjQtwq/TtZvIiDV3wDn7AZcqU1A6fIBc8uAErMrc5hNJIRQEkGkWLauYBMxOUG9q6dau5Jzq77pNI2/jNCl+PPprdx8aOkinhnmOsawxiFTc63MYqItS4ADdL324jGSfxJJ7HDlTFO+iKS7ERJ5GMSXgYtfEbxqE/Ep3u3bUJLRYmnqNHtcRcTtwnDPl2wsZvtt+pfTVqPOwomRLuOcaDxiAWcaPDbawiQo0LoPRdunS0WxEbnEEe9MTrKI99+BsVMAQvoDJ24VFMwmbUjnbzXOMkHEsTj1khIFxNxrx5ztj4rfS797n7c7osU8aZcxSNQfRwm8NtrCJCjQug9M0QbsEbD5ojBdNxH3LjjFqTjnwYjNHojPdUccnRGIJ/EQPesA5hLC1gpznDuH8mr9PrLTkpBISqydAnYqcidqw8pPg6d19J0mjOMiNshHuOojGILtGogRVviFDjEqpXj3YL3EN+nEZ3TMMmXIQUtMR9mIl2+Djz83dxL2ahsxJw4glOGuFGK/XokTXhBJuguDz+uPlMvEyMxwGXxSSZvIs+IeEITKE89ft7mqVvjr9jOD0R8zhvvBF8u0Dn7p0kjRFHTgkbojGILnYnyEs0YkqoWb16Ndq2bYsKFSogKSkJCxcuRLxgVr0cz5TFfozAcBXFNA0PoAF+xnEUwkT0Ug7BiQALLM6fH7pwc8EF5iYovuf6F1/UTBahJMajL0yo4dXhTMS+nmaZTZj95p2kMloT8V13aQJjoPO3eu5OChuiMRBilZgqaHnixAlcfPHF6N69O9rH2d3lPVAlGtXxJ35DHeRHmnq/A1XwKnrhLTyAIyiOeCdXLmDuXG3S0EOCQ8GfOcNYiZhs2gQUOBcYxqdBToxM9OhLSPFXMdusLwyTuRUvbm8hPV9FCN1ScVmHAuNVVwH9+wcvpmkWJ8/RDYUeBSGuhZqbb75ZLfGI7v+QKBW5kzxnUYTpUc+xHefjf7gUHiRhHPphAdojI7Yuz7A4ezbLDyPUfCxmzBnp6cCnn2afBHUzFZPFUYAxCja+NCp6BemffzbXrgEDgKefTsyJmH16yy3AsmXAtGn2nLvbzlFwvkK74J+4njVSU1PVonOU8aN0Nk1PV4uO/r9xXTTgxNKliz0ZU91KsuckOme8h15pE1F94A6US74d+84lxrvNsxhHk4qp//OBnRDd38NpOIidPq2p+pOTrX+fggeFIy7+8Hett22rmTAGDdI0NjoUtEeP1j7nVxYtyr6NmXYyERfb1Lhx1rpg7Ywnzp7V+rpdu3TkzZtY5x5N3DKuW8H7/tK1+GPGaPdgIvd5usl9Jnk8sTmF0qfmo48+wm233eZ3mxEjRmAkQzW8mDVrFgoWLBjhFgpGChw6hOqffopqn3+OfOfyvKcXLIhvhwzBwQYNot08QRAEwcWcPHkSnTp1wpEjR1DUX2RAvAs1vjQ1lStXxsGDB7N1CiXAlJQUtGjRAnn5KOWQivHrr4F9+7Qidw0bZqkYV60Cbr0VcUHlszsw4sww3JnxAfKeC8venlQdU5MfRZNplXBvz1tx6pQzfR7PPPmk9oQXjFCvdV6vlD2NT5BmYR0YPX16IhKN8UWIrX4Pdn/RDEyNDX3h3GyKSo9gn3P+Ll26dFChJq7NT/nz51eLN+xsXx3ub30kit3REdTbcZLmJzoCNm0KpKVlT6EeqxxHMu6EJtCsxrXKX+YTz63I7zmLa5I/VQKNCDXhM2UKMGSI+QHP6rW+dq1WzsAKuoMxr2c3D8RO4dT4IsRev5u5v7ZsAdavd68/VUYG8M032v/ffJMXTZvmtfW+N/sbxlRIdzzgr3ovJXSu5+cMlY1FgaYwjqEXJqqSBTp7UBG9MRGX4ztch9VYiNtxFjLD2Q2vp0gWGbRackEStQlC4tTcWrAAqFYNaNNGe89Xvud6p4kpoeb48ePYuHGjWsj27dvV/zt37kQsEKh6r76ub1/AEBQUE1TGTryIx7ELlTERffAwpqg6TDqT8Qh+wOVRbWMiwDwtK1dGRiC2WnJBErUJQmLU3Fpg4kHdSWJKqPnuu+9w6aWXqoX0799f/T+MKU5jgGChuhRsKNCYLfAXba7GesxBR/yJ8/E4xqI4jmAzLsQjeEMl0BOc5bXXgOuv9/+ERGFnzRrtf75aEX7MlFxgAsn33ou9RG3sBwqDs2dHTiiM5fYIkSdWa25lmHxQd/IajimhplmzZqBfs/cyc+ZMxAJmVYfffw/Xcxs+wno0REfMQx5k4AvcgFuwCHXwm9LMnEShaDcxYfH1hBSuethMyYXJk4HOnWMrtbveLxQGWX8tkFCYiO0RnCFWa259ZfJBPZKm8ZgWamIds6rDDRvgOoriCC7Cj5nvP8NN2IVKmIFuuBgb0RxfYAlugUcuqajj/YRkl3o43moCuU1t7rb2CM4Si/fXXhf6AsV19JPboOqQF2woYbHR4nxsU46+3TEde1BBaWIouJxGMmpiK9KQM7pMiD76ExLNF4HUw3wKpPDD1PtmngLdVoogUmpzq/0Sb+0RokOs3V/lXegLJEKNg3z8sZYx1hfe6emjiwdNsAb98Yqqjp1LZfcFziAPKmAP/oZWNVAEmsijF7Y8dChrXbFiWl6jzz4L/n0KNWbVw2ZDReMhTb8VtbkT5+q29gjRI5bur2uvDa1uXCQRocZh1bI/waVIESYXQtRpilV4GQNwBbIce5biJpVfJgUteJlGtX3xjC7YMgk2q22X1apHqASN//yjOeJS08cBgpObGaHGLG4NFU0Utbnb2iMIZvCuG+cGXyBxgEB0Vcs6eVwiXubCWSXQnEIBTEUP1MUvaI2lSEFLEWgiTMmSWlg2g/mYM7JbN6B5c+Cee4B+/YDBg4F//9UGCLPREmaf+NwYKppIanO3tUcQYtUXSIQaBzBTdZmTldNciM14HY9iJLJC4leimQrJroKdeAhT8RvqOt+wBOXwYa1ExjPPAHfckfOa4Xuup4DDa2rcOG19oCckCjWxGCqaaCG0bmuPIFiBgstff2klUQhfo5XWQYQaBzCrMuaTeqA8IPbgwQ34AotwCzajNh7FJPTBBBTC8XOfJ6mQ7IMoE+mGCF6wcvPEicDw4YG3o7DCUF8KNwMHBn5CitVQ0Ujjtn5xW3sEwSq8NvUab3yN1rUqQo0DmFUZ00QVKfIhFV0xExtxCb5Ac9yCJTiLJHyCtsoZ+ITklYk56Jw3dizwyitawrtZs3wnvnNCPRyLCePcpjZ3W3sEIRZxiSdHfGPWQ/ypp4A6dYC777Z/UhiGZ/AUXlD/n0BBzMB9mIA+2IoL7D2Q4Bh6qO+AAZogE+jJSA8VXb1ac0inetiuQpPBCrS6GbeF0LqtPYIQa4hQEwUPcaNg461aZoSLHQINHXw9SMr0iXkTPdAZ72MSHlH/H0bJ8A8iBKVQIeDEicjt30yoL68nfZIsV85e9bC/qD49YVwsaBjcFkLrtvYIQiwh5ieXqZbDC9n0oBU+w2dohV9QHy/gycxPdqAazsefeBGDRKBxkEgKNEb8XTfeaff1MgmLFsVn3RdBEBIb0dS4TLUcSshmAZxCF7yLvhiPuueqY2cgF9KQD7mQgbPQDiAlDJyFv6tTE7qv6yZQbqQuXbTXcLQokjBOEAS3IbNclFTL9JvxVfjPTDVkI3pF7Kl4SAk0R1EE49BXlTBgsUldoIkVChfWJuJwGDo0p0bMV6ZevRBjpHBCoPEX6msmN1K4WhRJGCcIgtsQocZlBArtzCJrpkqCB2VwENtRDf3wCiphN/pjHP5CdcQSTCy3fDnw339Agwbh7Ss11X85CqOmYsQIoEKF0I4RSBjib9i7d2j7DaUNvkJ9naieKwnjBEFwGyLUxIj/TRLO4hYswgpcj/swI3P92+iKO/EBLsAWjEc/HENRxBoFCmilATgxz5mj5WoJh5deyl4ryUiuXFmCAPPBUDCwqhlq3DiwYMNzuP122ILeXl8ECvV1QotC7ZBem8of/FwSxgmC4BTiU+Ny/5u1n59A8tyZqLpwAsoe2aI+K4YjmIHu6v8TKIz5CNNeE2WoVaHGxJ8gYneCO+8oHQoGVujZE+jfP2cYM81AFJb429GsEyiM3yy9egG33aYJH3otqAMHgof6mtWObNEuKUEQhLhAhBq3sns3cr/6Kq55fSrynfhPrfoPxTAFD+E1PIZ4wwmBxhehCBy6QMFq2Uw0R+gfZfSRMobxhwMFmlCcbIPlRtKhtqp+/dAchmm6Cva78XNxFBYEwSlEqHErDz4ILF2KfHyaRk2VKG8muinNjBAd9CSJrJjNMGmjlmbmzJzJ5nQzordGxyzh1PoxK1TxnOgwTK2g1bw14igsCILbEJ8aN0BbBcszG0b/jJ69sTbPdbgVH6M2fsfreEwEmiii+8/83/8BHTvmFFL0ZHMMo/ZV6I0+Q1aOxcWOWj+MJgtEOA7D4igsCILbEKEmmjBfPWeumjW1GfG11zI/ev77m9DkzEoswq0Bw7Lz53eorQkONTTz5mm1jawmm6NgMmyYJrdyP96OtN7OtnbU+tFz1Bw7FjltilSWFgTBbYhQEw346E5PU84ILLXM9yzRTSeNc4obPaw7GMnJSBjYRcE0D5GAeW9YW6l06fDCpHWtjbH45P792hKoIKVVzOSosUObIpWlBUFwG+JT4zTdugHvvpsVhlO7tvZ4z8QpBQuqVZwU//3X3O6Y1yVRMNsndnPjjdrEbIcPib+6PnY60gbLUePLTyhUbYo/vyHuU48EEwRBcAoRaiLNmTNAHkM3U3ChQNOihaaladUqRzIS+meYgVqL48dtbq/gd8KPFR8Sq6akcLUpUllaEAS3IOanSHH4MPDii0D16sD69dlT527aBHz+OXDzzTkEGvpCUHFjhnDDhYXA0HxjnPDNlLBglfVGjRBVzApVbKtdVbSDlf8QBEFwAhFq7GbrVi1jGj0kBw3SdPJvvZX1eZUqfusA6M6dBw8GPwydS6dMyel4KtgHhUvjhG+mhAXDvWvUyBkF5SRmhC/dP0jMQ4IgxBMi1Nj1SM8sbNTBX3ihFsV04oQmvEyfni2qyQ7nTk5WU6cC+fIBPXrYcwrxAGs5+YouIqEUruTPaaaEhTf+wrudwqwDL68fQRCEeEKEGjugREIH4E8+0aSS1q2BlBTgxx+B++7TihvZ5NzpbTK44ALYCiNwxo7VJvRYiqxiZFSTJsC2bTmjixhK7S2EBDKPBAtFZt/zOPwtfGEM705L0+RdhoLz1YnK3YGEL/1927bOtEMQBMFJxFHYDugI/MQTwE8/aeoWRjRFyLlz3LjsJgO9HpBd0GLGkOIBAzRNwx13IGYio5o31zQ11FLQtyOQIytNfB06aJ8btWNmQ5HXrdNMTcHCu/UMxDp6+5ww+/g672uuAZYti/yxBUEQooEINXbx6KOOOHcGMnvYgZ5nhc6enBSp5WDFhmjVZrKKbvrxdoD1FUodTiiyWSHUW/Dx175I4X3e6emRP6YgCEK0EPOTSwg1OysrNtsNBRndVMKJlyYcWtFigUCZfc0kwzOb+C7UsG0r7RMEQRDiXKh5/fXXUa1aNRQoUABXX301vv32W8QDoWZnjUROFPo1X3+9VrSRJigek2l1nIQCHMsSLF+u+ctYwUo9o1BDkc1EGNnRPkEQBCFOhZq5c+eif//+GD58OH744QdcfPHFaNWqFQ5EQl0RBfw5dwaqBRTO5BoMmmX0KJ4tW+BIOQJqTCjIzJih5S2kkDF5claRRytEsjq0mfDuYEj1akEQhAQWal555RX06NED9913H+rWrYvJkyejYMGCmM6w6TjBqknEjsk1mFaBficMIXeiHAELdDKQjE6/nTppGiOWyRo40Lo/UaQz+/oTQv1FRbkt87AgCEK8ETOOwmlpafj+++8xZMiQzHW5cuVC8+bN8fXXX/v8Tmpqqlp0jrIqtnKWTFeLjv6/cV20adw4639WVdBLRfmC4bmcXBm5ZCyxQIHHDr8N3UnYzhDv5OT0zFcKYxQMGJHUtasmSBmPxcim118H3n5byzuzZw/Ay4Dt8pXXR98fI30i/ZOy7xnBz0tw3z6gXDngqquASy7R2hnt9nnjxms93pE+jw7S7/HV52b3meTxWKnlGz327NmDihUrYt26dWjYsGHm+ieeeAKrVq3CN998k+M7I0aMwMiRI3OsnzVrltLwCIIgCILgfk6ePIlOnTrhyJEjKFq0aOxrakKBWh364Bg1NZUrV0bLli2zdQolwJSUFLRo0QJ58+ZFLEKNDLUFuhbDTKkFuxk1StOqvPRS8G2poZk+PQVDh7bAyJF5UaIE0KZN8O8tWaIl2SOLFuXUTtG/aPRodySXc2P74uFajzWkz6OD9Ht89bluaQlGzAg1pUuXRu7cubGf8cUG+L4cdf4+yJ8/v1q8YWf76nB/690OHXm9863YSZEiQLFi2uTsz5zCyfqxx7SIpVOngu/zllu01w0b8qJAgbwq466Z79HEo/9Ebq8O7eb2xeq1HsvEcp9nZGTEnBmHbc6TJ496pauC4O4+573BOT7Q53El1OTLlw+XX345vvjiC9x2221q3dmzZ9X7xzibJih6EcxIGhFZI4iZjJmBlwJMoAy8Zp1fFy8GOncGPv1Um/zNfs97O19J9dyE29snCIGgd8K+ffvw33//IRbbzgfeXbt2ISkSURSC7X1evHhx9f1wfq+YEWoITUldu3bFFVdcgauuugrjx4/HiRMnVDRUImKlCKY/aIULptWjQy6rOpvJwKuHmPvT6njTpYv2So1GoO/p2iB/9ZgEQbAfXaApW7as8kOMJeGAD73Hjx9H4cKFRVPj8j6nMESfGT09S/kwQkNjSqjp2LEj/vnnHwwbNkzdbJdccgk+++wznHfeeUhEzBbB9IbXWq9eABVeFCLuuSf4d2g+YYK6YOYUPcSc2iNvrY4/mF2X+/X3PbP1mARBsA+aEHSBppRe7j7GJlhGzTJRqwg17u/z5HMhrxRseM0FMkUFIuZ+aZqaduzYoUK1GfHErMKJitEB1QoMD584UXPqNZv7RReczWTgpdaGeWXMXNPG7LqhJB8UBCEy6D40EikqOIV+rYXjvxVTmhohuy9Nv37h7YMakq1b7Tf7sG1jx1ozi+nZdd3sXCsIiUgsmZyE2MaOay3mNDWCprW4446cFaCtoGtI1q0LreaU3X4+RhNqqPWYBEEQnKRbt26ZgSukWbNm6MunxTCwYx+JjAg1McYHH9C3yL79URtip9nHqp+Pv+rjgiAI4Qgb9MkoUaKE8u+oWbMmnnnmGZxhQbkIsmDBAjz77LOmtl25cqXSTHhHllnZh5ATMT/FEDTrMKzaTnQNiV1mn1CKNIoDsCAIdsNixxMmTFDpQBhQ0rNnT5XrxFhqh9CxldvYQcmSJV2xj0RGNDUxAs06Dz5o3/58aUjsMPtYjcR7911xABaERBi/Vq6ESrLJVztq0gWDiVcZGVu1alU88sgjqk7gJ598kmkyev7551GhQgXUqlVLbc/cKh06dFC5UihYtGvXDn+xunDmOWSotCL8nNFgLNHjXWXI23TEgJZBgwapTPZsDzVG06ZNU/u9ntV6AaVNosaG7fK1j8OHD+Pee+9V29GR9uabb8aWLVsyP585c6Zq07Jly1CnTh0VTn3TTTdhr+EJk1ohpkEpVKiQ2rZx48Yq4CYeEaEmRuBAoBeWtAt/GpJwBiA9T00gfy9Gh37yifa/G8oZCIIQWQ1ztWoA5/BOnbRXvud6J2HIMLUyhElbN2/erFL6L168WEXbULNTpEgRfPXVV1i7dm2mcKB/5+WXX1YCxPTp07FmzRr8+++/+OijjwIek8LI7NmzMXHiRPz222+YMmWK2i+FnPnz56tt2A4KINQq+YLCznfffacEMhZvpiDVunXrbBFCzPEyduxYvPvuu1i9ejV27tyJgQxBBZTJjULcddddh02bNql9PPjgg/HrAO5JII4cOUKxWr0aSUtL8yxcuFC9upEzZzyee+7hI4E9S6VKHs/8+b6PxfX83Oz2/vaRlKQtxv3o6/i52/s8XpF+d55Y7fNTp055fv31V/UaKvpY4D0GGceCSNC1a1fPrbfe6jl8+LDnzJkznpSUFE/+/Pk9AwcOVJ+dd955ntTU1Mzt3333XU+tWrU8Z8+ezVzHz5OTkz3Lli1T78uXL+958cUXMz9PT0/3VKpUydOuXbvMddddd52nT58+6v/Nmzer+YbH9sWXX36pPmcbjRj38ccff6ht1q5dm/n5wYMHVbvmzZun3s+YMUNts3Xr1sxtXn/9dXWO5NChQ+rzlStXeiJNRkaGOh++2n3N+Zu/vRFNTYw85bz3nj37Y9FyalR9mXz0kgvejr4M9+Z6s09Wkm9GEIRAkZD6OlpZImWKWrJkCSpVqpRpsmHy1hEjRqjPGjRokM2P5scff8TWrVuVpoaaFC40QZ0+fRrbtm1TlaGpTTHmRWONI2a398fGjRuVszI1JKFC7Q6PYzwuTV80mfEzHZ5jjRo1Mt8zI6+enZfnQW0PNVFt27ZVGiGjaSreEEdhF0MhgqHbVnj6ad5sWpg2k+vp0H/GWM7A6gBETaWe+deMr43kmxGExCZYJKQx8WYk6qPRN+XFF19UkzqFGwoHOvQtMcLU/qwt+P777+fYT5kyZUI6vp4h1wm8iz0mJSVl8/eZMWMGevfurRym586di6FDhyrT2zXXXIN4Q4SaOHIMptP88OGa4PDUU9YEikgMQFLMURASF7PKgEgpDSi4nH/++ShatGjQlP2XXXaZmuyZnp/b+4LaD2axb9q0aaavyvfff6++6wtqg1g2YNWqVcpJ2RtdU0QHZH/Q8ZfH4XEbNWqk1h06dEj54dStWxdWuPTSS9XC6K+GDRti1qxZcSnUiPkpjhyD33wzS3CxGskU7QFIEIT4wmwkZBi1C22jc+fOKF26tIp4oqPw9u3bVcQQtRu7zz3t9enTB6NHj8bChQvx+++/49FHHw1YvbxatWqqAHP37t3Vd/R9zps3T33OqCxqVOiozJqG1BZ5c8EFF6g29ejRQzkn00x2zz33oGLFimq9GbZv364EGToIM+Lp888/V9FTFJjiERFqXCzUmIW+KnSkD8dXJZYGIEEQ3E+wSEg3Jd6kTwqjhqpUqYL27durCf/+++9XPjW65mbAgAHo0qWLElSo6aD/ze233x5wv5MmTcKdd96pBKDatWsr4eTEiRPqMwomI0eOxODBg1XoOesa+oKmI5rGbrnlFnVcmpU+/fTTHCanQOf2+++/44477sCFF16oIp+Ys+ehhx5CPJJEb2EkCEePHkWxYsWU05dRxcjQOF4kDJMze6FEGvrGPPdc8O1YYXvmzPB9VagBpUNysBpQ27fb4xfjxj5PBKTfnSdW+5wTOp/yq1evrrLyhoIefECM44ou6EQycICmH475ZsxPgjv6PNA152/+9kZ+aZdi1heF+ZrsEDK4DztrQAmCIEgkpOA0ItS4WKhhkrpA8HM7HXFlABIEwW44bjCNxJdfArNmaa/U+Mp4IkQCiX5yKdSITJ0aOKSbn9utOZFQbEEQ7EYiIQWnEKHGxVDAoANw796ar4tRc0JTkV1POvSn8RZiZAASBEEQYg0RalxOpDUndORj0j1jjhq7hSZBEARBcAIRahJYdatHJnhHO+llEcSPRhAEQYglxFE4QYl2XRZBEARBsBsRahIUK2URBEEQBCEWEKEmQZGyCIIgCEK8IUJNgiJlEQRBgyZWliWZPVt7FZNrYsAq3n1pY3fJPkeMGIFLLrkkpO+yyCWLcf7FhEAuhRXCeX7MOhxJRKhJUGKpLosgRAo6y7M8yPXXA506aa98z/VC7NKtW7egdZmiwcyZM1URS+/lrbfewsCBA/HFF19kO4fbbrvN1H6ff/55VeCyGi9el3LTTTepMiHvv/9+RI8jQk2CImURhERHj/7z9i3To/9EsBEiAesW7d27N9vCKuGFCxdGqWBp5H1w8uRJTJs2TRXgdDsU1CZOnBjRY4hQk8BIWQQhUZHov8SClbHvvfdeJTiUL18eL7/8co5tUlNTlbaE1bMLFSqEq6++GitpjzSYeO6++271OStfN2jQALNps7QINTPlypXLtiQnJ2czP/H/t99+Gx9//HGmNsfYFiMslpo/f35cc8016j1rVNesWRNjx47Ntt3GjRvVfrZu3Qq7YSHKevXqZav8vW3bNlXJfPr06Znr2rZti++++059FilEqElwpC6LkIhI9F+YnDjhfzl92vy2p04F39YGHn/8caxatUoJCZ9//rkSEH744Yds2zz22GP4+uuvMWfOHGzatAl33XWXMpls2bIlc+K+/PLLsWTJEvz888948MEH0aVLF3z77bewGwpXHTp0UMfXtTmNGjXyue1XX32l2qWTlJSE7t27Y8aMGdm24/umTZsqgccXNAtR6Au08Fi+YEVtfv+dd95RQlZGRgbuuecetGjRQrVFp0qVKjjvvPP87scOJPleAuNdHqFDBzE3CYmBRP+FSeHC/j9r3RpYsiTrfdmytJH43va66zTvbB36hBw8mH0bX+o0Cxw/flyZZ9577z3ceOONah21IJWokj7Hzp071aTP1woVKmQKFnRu5foXXnhBaWi4TqdXr15YtmwZ5s2bh6uuusp0e44cOaIEBB3+v2/fvmzbcB21N9QeUZMTiB07dmS22WjmGTZsmBK42Lb09HTMmjUrh/bGyK233qq0U4FgH/iDWqZnn30WvXv3xrp161S7Fi9enGM7tpWfRQoRahIUKY8gJDIS/Zc40NSRlpaWbcIuWbIkatWqlfn+p59+UtqFCy+8MNt3KVTofi78nMINhZi///5b7ZOf0xRlBZpkjFqiXLnCM5icOnVKaUq8BYc2bdoo0w+FmkWLFqm2UvsUqF1cwqF///6YP38+Xn/9dSxdutSnjxCFNfoBRQoRahIQKY8gJDp69B+veV+KADrL83OJ/vPD8eP+P/NW9x444H9b7wk9SiHJ1Obkzp0b33//vXo1omtVXnrpJUyYMAHjx49X/jT0u2H4NoUbK1CI8WcCCoXSpUvj8OHDOdY/8MADyjw2btw4pW3q2LFjQAGM5iOjT4wvKKhcG+CmOHDggBIi2Yc029F85s2///6LMmXKAIku1DBkjbZMOjvly5cP//33X7SbFJcOkhzM6SDJIppiihLiPfqPQjyveeP9INF/JihUKPrbmqRGjRoqlPibb75RPh2EQsAff/yB62j+AnDppZcqTQwnZX+T9tq1a1XYNH1FCPOtcB9169ZFJOA8xzYFg22nac2b1q1bK8Fr0qRJyoy2evXqgPsJ1/xEGIHF/ujRo4cSkJo3b446depkfk6/JAo9bDMS3VGY0jBVZ4888ki0mxLTiIOkIGhI9F9iQE0LJ1s6C69YsUI5+dLnxGj2odmJYdWMkFqwYAG2b9+u/FFGjRqlHqbJBRdcgJSUFOUv8ttvv6lJe//+/RFrN3PO0GF58+bNOHjwoPKL8UWrVq3wyy+/5NDW5M6dW53nkCFDVNsbNmwY8Hg0PVGDFGih6cgfNDmtX78eb7zxhupL5tjhq1GTxc8ZqRWsLQkh1IwcORL9+vVTaj8hdMRBUhCykOi/xICmI2pgGFJM7UGTJk2yRQwRmmgo1AwYMED523BS3rBhQ6Z2Z+jQobjsssuUEMHMwXTgNZscLxSo7WA7rrjiCmWuoabIF5wT2S76+nhDYY5CxX333YdI8vvvvyuh8bXXXst0wKZwQ2Hs6aefztyOIfAUdKz6IVnCE2PMmDHDU6xYsZC+e+TIESqZ1auRtLQ0z8KFC9VrvPPll9TFBF+4XSRJpD53E9LvzhOrfX7q1CnPr7/+ql5jkYyMDM/hw4fVa7yzePFiT506dXKc6+rVqz158+b17Nu3L+p9/s8//3hKlizp+fPPP0O65vzN397EjE9NKNDbm4vO0aNH1SvVeEZVnv6/P/VePMH8TPRR27PHv4Mk1fHcLpLdkUh97iak350nVvuc7WUiN/qORLpeTyRg2/XXWGy/FW6++Wbl37Nr1y5UrlxZzXv//POPSuJ35513Kk2PE30QqM///PNPpcmpWrWq37ZwPb/La8/bYdvs/ZNEyQZRYvDgwRgzZkzAbWi7rF27drbaGfQ4N+MozB+UZitvGK8fUfWXIAhCjJMnTx5lYuEkSadVIXaYNWuWyqND0xT/985j41ZoKqNgxrw9Z86cyfYZw8A7deqk8vyw1IQrhRpKkkw9HYjzzz8/2w1lRajxpanhDUo7n7FTKAHSAYzZD+klnwgsWgQMGqSFtOrQFDp6NFNZR/74idjnbkD63Xlitc8ZqcIJhg6r3nlQYgFObceOHVMOsMyyK7i/z3nNsdI452nva47zN8PXgwk1UTU/USUWyXh1ellz8YYDi6/Bxd/6eISOkAzbNmYUZiSj0yGsidTnbkL63Xlirc8ZTsyJiVFC4SaIiwa6iUM/B8H9fc7v8Lu+7hWz907M+NQwfTWT9vCVNxvz1RCGmRlTTgvmoQDTrFm0WyEIgiAI9hAzQg3rWLBeh46evOfLL79U4XWCIAiC/UTRQ0FIMDw2XGsxo5OjLw1P2HsRgUYQBMF+dHV/JOv0CIIR/VoLx0wbM5oaQRAEwTkYUlu8eHFVOoAwYjSWHG7p38FoGjqfik+Nu/ucCgoKNLzWeM15h3NbQYQaQRAEwScM6Sa6YBNLcKJkBWum9o8lYSyW8YTZ5xRo9GsuVESoEQRBEHzCial8+fIoW7ZsTCYPZBHHpk2bxlTUWSyTHkafc/twNDQ6ItQIgiAIAeFkY8eE4yRsLxO4Md+JCDWJ0+diaBQEQRAEIS4QoUYQBEEQhLhAhBpBEARBEOKCPImY2Eev1m10bmI4GdeL7dUZpM+jg/S780ifRwfp9/jqc33eDpagL6GEGhbaIiyWJQiCIAhC7M3jxYoVc2eV7mgkBtqzZ0+OCqJ69W5WpA1U/VOwD+nz6CD97jzS59FB+j2++lyvAF6hQoWAif0SSlPDjqhUqZLfz/kjyMXvLNLn0UH63Xmkz6OD9Hv89HkgDY2OOAoLgiAIghAXiFAjCIIgCEJcIEINgPz582P48OHqVXAG6fPoIP3uPNLn0UH6PTH7PKEchQVBEARBiF9EUyMIgiAIQlwgQo0gCIIgCHGBCDWCIAiCIMQFItQIgiAIghAXJLxQ8/rrr6NatWooUKAArr76anz77bfRblLcs3r1arRt21ZlhmRm54ULF0a7SXHNqFGjcOWVV6pM2mXLlsVtt92GzZs3R7tZcc+kSZNw0UUXZSYia9iwIZYuXRrtZiUUo0ePVmNM3759o92UuGbEiBGqn41L7dq1o9KWhBZq5s6di/79+6sQtB9++AEXX3wxWrVqhQMHDkS7aXHNiRMnVF9ToBQiz6pVq9CzZ0+sX78eKSkpquhcy5Yt1e8gRA5mL+ek+v333+O7777DDTfcgHbt2uGXX36JdtMSgg0bNmDKlClKsBQiT7169bB3797MZc2aNYgGCR3STc0Mn2Bfe+21zNpQrFvRq1cvDB48ONrNSwgo0X/00UdKeyA4wz///KM0NhR2mjZtGu3mJBQlS5bESy+9hPvvvz/aTYlrjh8/jssuuwxvvPEGnnvuOVxyySUYP358tJsV15qahQsXYuPGjdFuSuJqatLS0tQTVPPmzbPVhuL7r7/+OqptE4RIcuTIkcwJVnCGjIwMzJkzR2nHaIYSIgs1k23atMk2vguRZcuWLcql4Pzzz0fnzp2xc+dORIOEKmhp5ODBg2qgOe+887Kt5/vff/89au0ShEhCbST9Cxo3boz69etHuzlxz08//aSEmNOnT6Nw4cJKK1m3bt1oNyuuofBIdwKanwTnrB4zZ85ErVq1lOlp5MiRuPbaa/Hzzz8rXz4nSVihRhAS9QmWA0207N2JBgd5quSpHfvwww/RtWtXZfYTwSYy7Nq1C3369FG+Ywz+EJzh5ptvzvyfPkwUcqpWrYp58+Y5bmpNWKGmdOnSyJ07N/bv359tPd+XK1cuau0ShEjx2GOPYfHixSr6jE6sQuTJly8fatasqf6//PLLlfZgwoQJyoFVsB+6FDDQg/40OtTI85qn72Rqaqoa94XIUrx4cVx44YXYunUrnCZXIg82HGS++OKLbKp5vhebtxBPMBaAAg1NHytWrED16tWj3aSEhWMMJ1YhMtx4443K5EftmL5cccUVyseD/4tA45yj9rZt21C+fHk4TcJqagjDuakO5kV/1VVXKe94OvLdd9990W5a3F/wRgl++/btasCh42qVKlWi2rZ4NTnNmjULH3/8sbJv79u3T60vVqwYkpOTo928uGXIkCFKLc9r+tixY+o3WLlyJZYtWxbtpsUtvL69fcUKFSqEUqVKiQ9ZBBk4cKDKPUaT0549e1SaFAqQd999N5wmoYWajh07qvDWYcOGqYGeYX+fffZZDudhwV6Ys+P666/PJlwSCph0NhPsTwJHmjVrlm39jBkz0K1btyi1Kv6hGeTee+9VjpMUIOlrQIGmRYsW0W6aINjK7t27lQBz6NAhlClTBk2aNFF5sfi/0yR0nhpBEARBEOKHhPWpEQRBEAQhvhChRhAEQRCEuECEGkEQBEEQ4gIRagRBEARBiAtEqBEEQRAEIS4QoUYQBEEQhLhAhBpBEARBEOICEWoEQUhYkpKSsHDhwmg3QxAEmxChRhAES0JAoGXEiBHRbqIgCAlMQpdJEATBGkz5rzN37lxVYmTz5s2Z6woXLpz5P5OVs0JynjwyzAiC4AyiqREEwTTlypXLXFjPiNoZ/f3vv/+uCgouXboUl19+OfLnz481a9ao+lK33XZbtv307ds3Wy0qVq8eNWqUqiDOIpsXX3wxPvzwQ7/tePLJJ3H11VfnWM/vPfPMM+r/DRs2qDpLpUuXVm297rrr8MMPP/jdJ4tN8nz++++/zHUstMp1f/31V+Y6ntO1116r2lm5cmX07t1bFcLVeeONN3DBBRegQIECqo7cnXfeaapvBUEIHxFqBEGwlcGDB2P06NH47bffVBFHM1CgeeeddzB58mT88ssv6NevH+655x6sWrXK5/adO3fGt99+i23btmWu4/c2bdqETp06qfesjM0iqRRCWFyPgkbr1q3V+lDh8W666Sbccccd6ljUVnH/jz32WGaxVgo5FKyowWKB3KZNm4Z8PEEQrCF6YUEQbIUTupVK1KmpqXjhhRewfPlyNGzYUK07//zzlbAwZcoUpWHxpl69ekorM2vWLDz99NNq3fvvv6+0NzVr1lTvb7jhhmzfmTp1KooXL64EpVtuuSWkc6PwRYGKmiZCQWnixImqjayGvnPnThQqVEjtn1qrqlWr4tJLLw3pWIIgWEc0NYIg2MoVV1xhafutW7fi5MmTShCiT46+UHNj1MR4Q+GCQo3uvzN79my1Tmf//v3o0aOHEjxofipatCiOHz+uBI9Q+fHHHzFz5sxs7WzVqpUyn23fvl2dAwUZCmVdunRRghbPTRAEZxBNjSAItkJNhZFcuXIpocNIenp65v8UNMiSJUtQsWLFbNvRL8cfd999NwYNGqT8ZE6dOoVdu3ahY8eOmZ/T9HTo0CFMmDBBCRrcFzVBaWlpPvfHdhJjW43t1Nv60EMPKROTN1WqVEG+fPlUe+if8/nnnytHakaE0b+HWiJBECKLCDWCIESUMmXK4Oeff862jg64efPmVf/XrVtXCRzUoPgyNfmjUqVKantqQyjUUEtStmzZzM/Xrl2rnHbpR0Mo9Bw8eDBgO/UIrxIlSmS208hll12GX3/9NdPE5QtGezVv3lwtw4cPV8LMihUr0L59e9PnJghCaIhQIwhCRKFvy0svvaTMSdSUvPfee0rI0X1N6HsycOBA5RxMM06TJk1w5MgRJZTQZESNiz9obqLgQO3LuHHjsn1Gs9O7776rzGFHjx7F448/riKW/EFBhdFM1Kw8//zz+OOPP/Dyyy9n24aaoWuuuUY5Bj/wwANKK0UhJyUlBa+99hoWL16MP//8UzkHUzD69NNP1TnVqlUr7H4UBCE44lMjCEJEoc8JnXmfeOIJXHnllSr66N577822zbPPPqu2oSNunTp1VIQRzVEM8Q4Ew6VpYqLfinfY+LRp03D48GGlXaF/C01GRk2ON9Qc0S+HoemM2hozZgyee+65bNtwPR2NKfAwrJuCGU1MFSpUUJ9TK7NgwQIlyPE8GM3FfdKxWRCEyJPk8TZ2C4IgCIIgxCCiqREEQRAEIS4QoUYQBEEQhLhAhBpBEARBEOICEWoEQRAEQYgLRKgRBEEQBCEuEKFGEARBEIS4QIQaQRAEQRDiAhFqBEEQBEGIC0SoEQRBEAQhLhChRhAEQRCEuECEGkEQBEEQ4gIRagRBEARBQDzw/4RD9OqPvf1bAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Create a scatter plot\n",
    "plt.scatter(y_test, preds, color='blue', label='Predictions')  # Scatter plot\n",
    "\n",
    "# Add a reference line (y = x)\n",
    "plt.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], \n",
    "         color='red', linestyle='--', label='Ideal Fit (y = x)')\n",
    "\n",
    "# Add labels and title\n",
    "plt.xlabel('True values')\n",
    "plt.ylabel('Predictions')\n",
    "plt.title('California Housing Predictions')\n",
    "plt.legend()\n",
    "\n",
    "# Display the plot\n",
    "plt.grid(True)  # Optional: Add a grid for better readability\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our model is capturing the general trend of the data!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Summary Statistics\n",
    "\n",
    "This is the great part of `tidylinreg`! Calling `summary()` will calculate important statistical values for the linear model coefficient estimates, including standard error, test statistic, confidence interval, and p-values. The output of `summary()` is generated by calling the following internal class methods:\n",
    "- `get_std_error()`\n",
    "- `get_test_statistic()`\n",
    "- `get_ci()`\n",
    "- `get_pvalues()`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Parameter</th>\n",
       "      <th>Estimate</th>\n",
       "      <th>Std. Error</th>\n",
       "      <th>T-Statistic</th>\n",
       "      <th>P-Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>(Intercept)</td>\n",
       "      <td>-37.004147</td>\n",
       "      <td>0.790393</td>\n",
       "      <td>-46.817373</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>MedInc</td>\n",
       "      <td>0.438382</td>\n",
       "      <td>0.005039</td>\n",
       "      <td>86.989990</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>HouseAge</td>\n",
       "      <td>0.009267</td>\n",
       "      <td>0.000535</td>\n",
       "      <td>17.314654</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>AveRooms</td>\n",
       "      <td>-0.107089</td>\n",
       "      <td>0.006973</td>\n",
       "      <td>-15.358336</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>AveBedrms</td>\n",
       "      <td>0.635964</td>\n",
       "      <td>0.033466</td>\n",
       "      <td>19.003273</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Population</td>\n",
       "      <td>-0.000007</td>\n",
       "      <td>0.000006</td>\n",
       "      <td>-1.160798</td>\n",
       "      <td>2.457431e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>AveOccup</td>\n",
       "      <td>-0.003739</td>\n",
       "      <td>0.000536</td>\n",
       "      <td>-6.981016</td>\n",
       "      <td>3.058442e-12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Latitude</td>\n",
       "      <td>-0.422767</td>\n",
       "      <td>0.008629</td>\n",
       "      <td>-48.992423</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Longitude</td>\n",
       "      <td>-0.435591</td>\n",
       "      <td>0.009039</td>\n",
       "      <td>-48.191074</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Parameter   Estimate  Std. Error  T-Statistic       P-Value\n",
       "0  (Intercept) -37.004147    0.790393   -46.817373  0.000000e+00\n",
       "1       MedInc   0.438382    0.005039    86.989990  0.000000e+00\n",
       "2     HouseAge   0.009267    0.000535    17.314654  0.000000e+00\n",
       "3     AveRooms  -0.107089    0.006973   -15.358336  0.000000e+00\n",
       "4    AveBedrms   0.635964    0.033466    19.003273  0.000000e+00\n",
       "5   Population  -0.000007    0.000006    -1.160798  2.457431e-01\n",
       "6     AveOccup  -0.003739    0.000536    -6.981016  3.058442e-12\n",
       "7     Latitude  -0.422767    0.008629   -48.992423  0.000000e+00\n",
       "8    Longitude  -0.435591    0.009039   -48.191074  0.000000e+00"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As stated before, the intercept estimate was included without any need for modifying the dataframe."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Interpretations\n",
    "\n",
    "Wow, it looks like all of our coefficient estimates are statistically significant, except for `Population` (with a significance level alpha = 0.05). We can also make interpretations on these statistically significant coefficients; for example, we can say that a unit increase in median income in the block group (`MedInc`) is associated with an increase of \\$43,838.20 in the median house value for the housing district (holding all other factors constant).\n",
    "\n",
    "Lets look at another less intuitive example: We can see the `AveOccup` parameter has a statistically significant estimate of -0.003739. We can say that increasing the average occupancy by one person is associated to a **decrease** of \\$373.90 in the median house value for the housing district, while holding other factors constant."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "524",
   "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": "3.13.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}