{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "eAWwICVEM_3x"
   },
   "source": [
    "# TableMage Demonstration\n",
    "\n",
    "TableMage is a Python package for low-code/conversational data science. In this notebook, we provide a few examples of how the package can be used.\n",
    "\n",
    "## Notebook Contents\n",
    "\n",
    "1. Introduction\n",
    "2. Exploratory Data Analysis\n",
    "3. Regression Analysis\n",
    "4. Causal Inference\n",
    "5. Machine Learning\n",
    "6. Conversational Data Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_n9HUVQ1Nwye"
   },
   "source": [
    "# Section 1: Introduction\n",
    "\n",
    "## 1.1: Installation\n",
    "\n",
    "Let's first install the package.\n",
    "On a local machine, you simply need to copy-and-paste the following code into your terminal:\n",
    "```{bash}\n",
    "git clone https://github.com/ajy25/TableMage.git\n",
    "cd TableMage\n",
    "pip install .\n",
    "```\n",
    "If you want to use the conversational data analysis mode, you should replace the last line with the following line:\n",
    "```\n",
    "pip install '.[agents]'\n",
    "```\n",
    "NOTE: If you are a MacOS user, you'll need to install [libomp](https://formulae.brew.sh/formula/libomp). It's a dependency for using XGBoost, a TableMage dependency.\n",
    "\n",
    "Okay! Let's run the cell below. On Google Colab, you'll be prompted to restart the session—this is normal."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "using_google_colab = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "gtUy4h6oM9NW",
    "outputId": "0c7a1616-55c6-43e2-ad91-6de0009c11ec"
   },
   "outputs": [],
   "source": [
    "%%capture\n",
    "!pip uninstall -y tablemage\n",
    "!rm -rf TableMage\n",
    "!git clone https://github.com/ajy25/TableMage.git\n",
    "%cd TableMage\n",
    "!pip install '.[agents]'\n",
    "import tablemage as tm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ZI5H04BPPYAg"
   },
   "source": [
    "## 1.2 The Analyzer Class\n",
    "\n",
    "Now that TableMage is installed, let's try importing the package. We'll use a toy dataset from scikit-learn for now."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 290
    },
    "id": "TpU2XO20NvxC",
    "outputId": "7f2886ff-ebaa-4516-9ae0-1a7b671335d4"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>17.99</td>\n",
       "      <td>10.38</td>\n",
       "      <td>122.80</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>0.11840</td>\n",
       "      <td>0.27760</td>\n",
       "      <td>0.3001</td>\n",
       "      <td>0.14710</td>\n",
       "      <td>0.2419</td>\n",
       "      <td>0.07871</td>\n",
       "      <td>...</td>\n",
       "      <td>17.33</td>\n",
       "      <td>184.60</td>\n",
       "      <td>2019.0</td>\n",
       "      <td>0.1622</td>\n",
       "      <td>0.6656</td>\n",
       "      <td>0.7119</td>\n",
       "      <td>0.2654</td>\n",
       "      <td>0.4601</td>\n",
       "      <td>0.11890</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20.57</td>\n",
       "      <td>17.77</td>\n",
       "      <td>132.90</td>\n",
       "      <td>1326.0</td>\n",
       "      <td>0.08474</td>\n",
       "      <td>0.07864</td>\n",
       "      <td>0.0869</td>\n",
       "      <td>0.07017</td>\n",
       "      <td>0.1812</td>\n",
       "      <td>0.05667</td>\n",
       "      <td>...</td>\n",
       "      <td>23.41</td>\n",
       "      <td>158.80</td>\n",
       "      <td>1956.0</td>\n",
       "      <td>0.1238</td>\n",
       "      <td>0.1866</td>\n",
       "      <td>0.2416</td>\n",
       "      <td>0.1860</td>\n",
       "      <td>0.2750</td>\n",
       "      <td>0.08902</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19.69</td>\n",
       "      <td>21.25</td>\n",
       "      <td>130.00</td>\n",
       "      <td>1203.0</td>\n",
       "      <td>0.10960</td>\n",
       "      <td>0.15990</td>\n",
       "      <td>0.1974</td>\n",
       "      <td>0.12790</td>\n",
       "      <td>0.2069</td>\n",
       "      <td>0.05999</td>\n",
       "      <td>...</td>\n",
       "      <td>25.53</td>\n",
       "      <td>152.50</td>\n",
       "      <td>1709.0</td>\n",
       "      <td>0.1444</td>\n",
       "      <td>0.4245</td>\n",
       "      <td>0.4504</td>\n",
       "      <td>0.2430</td>\n",
       "      <td>0.3613</td>\n",
       "      <td>0.08758</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.42</td>\n",
       "      <td>20.38</td>\n",
       "      <td>77.58</td>\n",
       "      <td>386.1</td>\n",
       "      <td>0.14250</td>\n",
       "      <td>0.28390</td>\n",
       "      <td>0.2414</td>\n",
       "      <td>0.10520</td>\n",
       "      <td>0.2597</td>\n",
       "      <td>0.09744</td>\n",
       "      <td>...</td>\n",
       "      <td>26.50</td>\n",
       "      <td>98.87</td>\n",
       "      <td>567.7</td>\n",
       "      <td>0.2098</td>\n",
       "      <td>0.8663</td>\n",
       "      <td>0.6869</td>\n",
       "      <td>0.2575</td>\n",
       "      <td>0.6638</td>\n",
       "      <td>0.17300</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20.29</td>\n",
       "      <td>14.34</td>\n",
       "      <td>135.10</td>\n",
       "      <td>1297.0</td>\n",
       "      <td>0.10030</td>\n",
       "      <td>0.13280</td>\n",
       "      <td>0.1980</td>\n",
       "      <td>0.10430</td>\n",
       "      <td>0.1809</td>\n",
       "      <td>0.05883</td>\n",
       "      <td>...</td>\n",
       "      <td>16.67</td>\n",
       "      <td>152.20</td>\n",
       "      <td>1575.0</td>\n",
       "      <td>0.1374</td>\n",
       "      <td>0.2050</td>\n",
       "      <td>0.4000</td>\n",
       "      <td>0.1625</td>\n",
       "      <td>0.2364</td>\n",
       "      <td>0.07678</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 31 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\n",
       "0        17.99         10.38          122.80     1001.0          0.11840   \n",
       "1        20.57         17.77          132.90     1326.0          0.08474   \n",
       "2        19.69         21.25          130.00     1203.0          0.10960   \n",
       "3        11.42         20.38           77.58      386.1          0.14250   \n",
       "4        20.29         14.34          135.10     1297.0          0.10030   \n",
       "\n",
       "   mean compactness  mean concavity  mean concave points  mean symmetry  \\\n",
       "0           0.27760          0.3001              0.14710         0.2419   \n",
       "1           0.07864          0.0869              0.07017         0.1812   \n",
       "2           0.15990          0.1974              0.12790         0.2069   \n",
       "3           0.28390          0.2414              0.10520         0.2597   \n",
       "4           0.13280          0.1980              0.10430         0.1809   \n",
       "\n",
       "   mean fractal dimension  ...  worst texture  worst perimeter  worst area  \\\n",
       "0                 0.07871  ...          17.33           184.60      2019.0   \n",
       "1                 0.05667  ...          23.41           158.80      1956.0   \n",
       "2                 0.05999  ...          25.53           152.50      1709.0   \n",
       "3                 0.09744  ...          26.50            98.87       567.7   \n",
       "4                 0.05883  ...          16.67           152.20      1575.0   \n",
       "\n",
       "   worst smoothness  worst compactness  worst concavity  worst concave points  \\\n",
       "0            0.1622             0.6656           0.7119                0.2654   \n",
       "1            0.1238             0.1866           0.2416                0.1860   \n",
       "2            0.1444             0.4245           0.4504                0.2430   \n",
       "3            0.2098             0.8663           0.6869                0.2575   \n",
       "4            0.1374             0.2050           0.4000                0.1625   \n",
       "\n",
       "   worst symmetry  worst fractal dimension  target  \n",
       "0          0.4601                  0.11890       0  \n",
       "1          0.2750                  0.08902       0  \n",
       "2          0.3613                  0.08758       0  \n",
       "3          0.6638                  0.17300       0  \n",
       "4          0.2364                  0.07678       0  \n",
       "\n",
       "[5 rows x 31 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.datasets import load_breast_cancer\n",
    "import pandas as pd\n",
    "\n",
    "brca_dataset = load_breast_cancer()\n",
    "df = pd.DataFrame(data=brca_dataset.data, columns=brca_dataset.feature_names)\n",
    "df[\"target\"] = brca_dataset.target\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "fNY3i9A2QTu2"
   },
   "source": [
    "The Analyzer is the bridge between the data and the analysis methods. Most likely, you'll want to do some modeling of some sort, such as linear regression or some type of machine learning regression/classification. As such, the Analyzer splits the data into a train dataset and a withheld test dataset upon initialization.\n",
    "\n",
    "Be careful! The Analyzer will rename variables to make them easily formula-compatible (i.e., replace spaces and other prohibited characters with underscores). It is recommended that you remove spaces and special characters from variable names *before* you initialize an Analyzer, just to make sure you have full control over the names. A good rule-of-thumb is to avoid punctuation and spaces, with the exceptions of \"_\" and \".\", which are totally fine. We'll let Analyzer handle the renaming for now."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Jl3xiFhJM8zw",
    "outputId": "282d433e-56e5-4369-9991-de2b7cead761"
   },
   "outputs": [],
   "source": [
    "analyzer = tm.Analyzer(\n",
    "    df, test_size=0.2, split_seed=42, verbose=True, name=\"Breast Cancer\"\n",
    ")\n",
    "\n",
    "# You can also split the dataset yourself, e.g. ...\n",
    "# df_train, df_test = sklearn.train_test_split(df, random_state=42)\n",
    "# analyzer = tm.Analyzer(df_train, df_test=df_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "NctfBOyBTDGO"
   },
   "source": [
    "TableMage is designed for notebooks. Many objects are display-friendly!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "Gc49sk8xS_3f",
    "outputId": "f34d1e9a-1811-4b99-b6d3-bdc7514c1267"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mBreast Cancer\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(455, 31)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(114, 31)\u001b[0m                       \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[93mNone\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'area_error', \u001b[0m\u001b[95m'compactness_error', \u001b[0m\u001b[95m'concave_points_error', \u001b[0m\u001b[95m'concavity_error', \n",
       "  \u001b[0m\u001b[95m'fractal_dimension_error', \u001b[0m\u001b[95m'mean_area', \u001b[0m\u001b[95m'mean_compactness', \u001b[0m\u001b[95m'mean_concave_points', \n",
       "  \u001b[0m\u001b[95m'mean_concavity', \u001b[0m\u001b[95m'mean_fractal_dimension', \u001b[0m\u001b[95m'mean_perimeter', \u001b[0m\u001b[95m'mean_radius', \n",
       "  \u001b[0m\u001b[95m'mean_smoothness', \u001b[0m\u001b[95m'mean_symmetry', \u001b[0m\u001b[95m'mean_texture', \u001b[0m\u001b[95m'perimeter_error', \u001b[0m\u001b[95m'radius_error', \n",
       "  \u001b[0m\u001b[95m'smoothness_error', \u001b[0m\u001b[95m'symmetry_error', \u001b[0m\u001b[95m'target', \u001b[0m\u001b[95m'texture_error', \u001b[0m\u001b[95m'worst_area', \n",
       "  \u001b[0m\u001b[95m'worst_compactness', \u001b[0m\u001b[95m'worst_concave_points', \u001b[0m\u001b[95m'worst_concavity', \n",
       "  \u001b[0m\u001b[95m'worst_fractal_dimension', \u001b[0m\u001b[95m'worst_perimeter', \u001b[0m\u001b[95m'worst_radius', \u001b[0m\u001b[95m'worst_smoothness', \n",
       "  \u001b[0m\u001b[95m'worst_symmetry', \u001b[0m\u001b[95m'worst_texture'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UcMRobVMRPlF"
   },
   "source": [
    "Before we proceed, let's discuss why TableMage requires train-test splitting upon initialization. TableMage aims to accelerate data science on tabular data. Often, the end goal is to train a model to predict a target, such as whether or not a patient has breast cancer based on geometrical features, or a patient's billing amoung given the health insurer and disease type. In these cases, it is incredibly important to think in terms of pipelines, especially when transformations must be made to the data. Transformations—including missing data imputation and feature scaling—must be \"fit\" on the train data only. Performing data transformations based on the entire dataset is a common mistake, even for experienced data scientists.\n",
    "\n",
    "TableMage handles all of this for you. You can explore the dataset (looking at the entire dataset or only the train or test dataset—your choice), make transformations such as imputation, feature engineering, and scaling, and immediately train a model to predict a target variable, without needing to worry about all the intermediate details! Hopefully, this will be more clear in section 5, when we discuss machine learning.\n",
    "\n",
    "If you don't plan on doing any modeling, simply set test_size to 0.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wAtZltXuT2g1"
   },
   "source": [
    "## 1.3 Submodules\n",
    "\n",
    "TableMage has two submodules:\n",
    "1. ml: Machine learning models\n",
    "2. fs: Feature selection models\n",
    "\n",
    "Let's print an object from each. These will be discussed in greater detail in section 5."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 53
    },
    "id": "oZeIB5TwT1_Y",
    "outputId": "15251e55-c69d-4808-c74a-7d7ab1696441"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LinearC(l2)\n",
      "BorutaFSR\n"
     ]
    }
   ],
   "source": [
    "print(tm.ml.LinearC())\n",
    "print(tm.fs.BorutaFSR())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GntK4oMpWL_R"
   },
   "source": [
    "# Section 2: Exploratory Data Analysis\n",
    "\n",
    "Let's explore a dataset. We'll use the Kaggle House Prices dataset as an example since it contains a good amount of categorical and numeric features with varying levels of missingness."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "BB6_W0PgRPSR",
    "outputId": "1495dd27-6cfd-4e36-cd8f-c662a5327c2c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mHouse Prices\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(1168, 80)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(292, 80)\u001b[0m                      \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[95m'Alley', \u001b[0m\u001b[95m'BldgType', \u001b[0m\u001b[95m'BsmtCond', \u001b[0m\u001b[95m'BsmtExposure', \u001b[0m\u001b[95m'BsmtFinType1', \u001b[0m\u001b[95m'BsmtFinType2', \n",
       "  \u001b[0m\u001b[95m'BsmtQual', \u001b[0m\u001b[95m'CentralAir', \u001b[0m\u001b[95m'Condition1', \u001b[0m\u001b[95m'Condition2', \u001b[0m\u001b[95m'Electrical', \u001b[0m\u001b[95m'ExterCond', \n",
       "  \u001b[0m\u001b[95m'ExterQual', \u001b[0m\u001b[95m'Exterior1st', \u001b[0m\u001b[95m'Exterior2nd', \u001b[0m\u001b[95m'Fence', \u001b[0m\u001b[95m'FireplaceQu', \u001b[0m\u001b[95m'Foundation', \n",
       "  \u001b[0m\u001b[95m'Functional', \u001b[0m\u001b[95m'GarageCond', \u001b[0m\u001b[95m'GarageFinish', \u001b[0m\u001b[95m'GarageQual', \u001b[0m\u001b[95m'GarageType', \u001b[0m\u001b[95m'Heating', \n",
       "  \u001b[0m\u001b[95m'HeatingQC', \u001b[0m\u001b[95m'HouseStyle', \u001b[0m\u001b[95m'KitchenQual', \u001b[0m\u001b[95m'LandContour', \u001b[0m\u001b[95m'LandSlope', \u001b[0m\u001b[95m'LotConfig', \n",
       "  \u001b[0m\u001b[95m'LotShape', \u001b[0m\u001b[95m'MSZoning', \u001b[0m\u001b[95m'MasVnrType', \u001b[0m\u001b[95m'MiscFeature', \u001b[0m\u001b[95m'Neighborhood', \u001b[0m\u001b[95m'PavedDrive', \n",
       "  \u001b[0m\u001b[95m'PoolQC', \u001b[0m\u001b[95m'RoofMatl', \u001b[0m\u001b[95m'RoofStyle', \u001b[0m\u001b[95m'SaleCondition', \u001b[0m\u001b[95m'SaleType', \u001b[0m\u001b[95m'Street', \u001b[0m\u001b[95m'Utilities'\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'1stFlrSF', \u001b[0m\u001b[95m'2ndFlrSF', \u001b[0m\u001b[95m'3SsnPorch', \u001b[0m\u001b[95m'BedroomAbvGr', \u001b[0m\u001b[95m'BsmtFinSF1', \u001b[0m\u001b[95m'BsmtFinSF2', \n",
       "  \u001b[0m\u001b[95m'BsmtFullBath', \u001b[0m\u001b[95m'BsmtHalfBath', \u001b[0m\u001b[95m'BsmtUnfSF', \u001b[0m\u001b[95m'EnclosedPorch', \u001b[0m\u001b[95m'Fireplaces', \n",
       "  \u001b[0m\u001b[95m'FullBath', \u001b[0m\u001b[95m'GarageArea', \u001b[0m\u001b[95m'GarageCars', \u001b[0m\u001b[95m'GarageYrBlt', \u001b[0m\u001b[95m'GrLivArea', \u001b[0m\u001b[95m'HalfBath', \n",
       "  \u001b[0m\u001b[95m'KitchenAbvGr', \u001b[0m\u001b[95m'LotArea', \u001b[0m\u001b[95m'LotFrontage', \u001b[0m\u001b[95m'LowQualFinSF', \u001b[0m\u001b[95m'MSSubClass', \u001b[0m\u001b[95m'MasVnrArea', \n",
       "  \u001b[0m\u001b[95m'MiscVal', \u001b[0m\u001b[95m'MoSold', \u001b[0m\u001b[95m'OpenPorchSF', \u001b[0m\u001b[95m'OverallCond', \u001b[0m\u001b[95m'OverallQual', \u001b[0m\u001b[95m'PoolArea', \n",
       "  \u001b[0m\u001b[95m'SalePrice', \u001b[0m\u001b[95m'ScreenPorch', \u001b[0m\u001b[95m'TotRmsAbvGrd', \u001b[0m\u001b[95m'TotalBsmtSF', \u001b[0m\u001b[95m'WoodDeckSF', \u001b[0m\u001b[95m'YearBuilt', \n",
       "  \u001b[0m\u001b[95m'YearRemodAdd', \u001b[0m\u001b[95m'YrSold'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from pathlib import Path\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "plt.rcParams[\"figure.dpi\"] = 150\n",
    "\n",
    "if using_google_colab:\n",
    "    curr_dir = Path.cwd()\n",
    "else:\n",
    "    curr_dir = Path(\"__notebook__\").resolve().parent\n",
    "\n",
    "data_path = curr_dir / \"demo\" / \"regression\" / \"house_price_data\" / \"data.csv\"\n",
    "df = pd.read_csv(data_path, index_col=0)\n",
    "analyzer = tm.Analyzer(\n",
    "    df, test_size=0.2, split_seed=42, verbose=True, name=\"House Prices\"\n",
    ")\n",
    "analyzer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "9wO41RUMXKGR"
   },
   "source": [
    "## 2.1 Plots"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MJwmBmdflS2L"
   },
   "source": [
    "We can begin our analysis by using TableMage to make plots of the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 465
    },
    "id": "VXE_iNJtQQR4",
    "outputId": "263ead1f-7fdb-490e-e1a2-cc71eb4edc96"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 750x750 with 1 Axes>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().plot(\"SalePrice\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "imuGgltYXURD"
   },
   "source": [
    "By default, Analyzer considers the entire dataset (train and test) for exploratory analysis. You can change this by specifying which dataset you would like to consider in the `analyzer.eda()` method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 465
    },
    "id": "Bfgg7icFXP5_",
    "outputId": "e0da3188-f934-4a28-efad-dc6c763cbc6d"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 750x750 with 1 Axes>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda(\"train\").plot(\"SalePrice\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_BHAQYidXvuY"
   },
   "source": [
    "Let's plot the sale price versus 1st floor square footage."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 479
    },
    "id": "_CD5f8t-XIgA",
    "outputId": "b4e83082-c33f-4588-d3d8-38c5747be9d6"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 750x750 with 1 Axes>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().plot(\"SalePrice\", \"1stFlrSF\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bFcoVptrYAG1"
   },
   "source": [
    "You can plot any two variables agains each other, regardless of whether they are numeric or categorical."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 481
    },
    "id": "538MldzwX4kI",
    "outputId": "80fcb125-850e-4ccf-b2f4-66667cb4a752"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1650x750 with 2 Axes>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(ncols=2, figsize=(11, 5))\n",
    "analyzer.eda().plot(\"SalePrice\", \"Alley\", ax=axs[0])\n",
    "analyzer.eda().plot(\"Alley\", \"Heating\", ax=axs[1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bAmyeUuCYZ07"
   },
   "source": [
    "You can change colors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 481
    },
    "id": "bLn1dTDWX9wp",
    "outputId": "a7cdbf59-5438-4ab9-e69b-f2af8e3e82d2"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1650x750 with 2 Axes>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tm.options.plot_options.set_color_map(\"viridis\")\n",
    "tm.options.plot_options.set_bar_color(\"red\")\n",
    "fig, axs = plt.subplots(ncols=2, figsize=(11, 5))\n",
    "analyzer.eda().plot(\"SalePrice\", \"Alley\", ax=axs[0])\n",
    "analyzer.eda().plot(\"Alley\", \"Heating\", ax=axs[1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Jco5f1-BZ4jK"
   },
   "source": [
    "You can make pair plots, like in R. Hypothesis tests are automatically selected based on data normality and homoskedasticity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "69em5vTXYnnq",
    "outputId": "dab3c02d-1e7b-473a-932c-4316ba5325d4"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABbQAAAUGCAYAAABJoDepAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAABcSAAAXEgFnn9JSAAEAAElEQVR4nOzdd1xW9f//8SdDBBFFcw9UtAAHiAPcgzQ1M8ty5Cr3tlITTT+aablFxTQ1R6mZDXOUZZYj0dw7FffemgNEELh+f/jjfL0CFE04XPC4327cvDjnfZ3rdS643h6e533ex85isVgEAAAAAAAAAEA6Z292AQAAAAAAAAAApASBNgAAAAAAAADAJhBoAwAAAAAAAABsAoE2AAAAAAAAAMAmEGgDAAAAAAAAAGwCgTYAAAAAAAAAwCYQaAMAAAAAAAAAbAKBNgAAAAAAAADAJhBoAwAAAAAAAABsAoE2AAAAAAAAAMAmEGgDAAAAAAAAAGwCgTYAAAAAAAAAwCYQaAMAAAAAAAAAbAKBNgAAAAAAAADAJhBop6FTp06pfv36j2xz+PBhVa9eXe3atVO7du00b968NKoOAAAAAAAAANI3R7MLyCwWLVqkH374Qf/8888j2+3fv19t2rRRz54906gyAAAAAAAAALANBNppJE+ePPr6669Vo0YNSVJERISGDh2qa9euKTY2Vn379lW1atW0f/9+nTp1Sps3b1aePHk0ZMgQ5c2b1+TqAQAAAAAAAMB8dhaLxWJ2EZlJpUqVtGPHDk2YMEE5c+ZUly5ddPPmTbVs2VIrV67U8uXL5eXlJV9fXy1btkyrV6/WjBkzzC4bAAAAAAAAAEzHCG2THDlyRNeuXdOff/5pLLt8+bJeeukl5cyZU5LUoEEDTZo0yawSAQAAAAAAACBd4aaQJilZsqRatWqlBQsW6IsvvlCDBg2UP39+dejQQdu3b5ckbdq0SWXLljW5UgAAAAAAAABIH5hyJI0lTDly69Yt/e9//9M///yj27dvq0WLFmrTpo0OHDigUaNGKUuWLMqWLZs+/vhj5c+f3+yyAQAAAAAAAMB0BNoAAAAAAAAAAJvAlCMAAAAAAAAAAJtAoA0AAAAAAAAAsAmOZheQkcXHxys2NlaSZG9vLzs7O5MrApDAYrEoPj5ekuTo6Ch7e9s5v0ffAqRvttq/0LcA6Zut9i0S/QuQntG3AEgtqdm/EGinotjYWO3fv9/sMgA8Rrly5eTk5GR2GSlG3wLYDlvqX+hbANthS32LRP8C2Ar6FgCp5Vn3L7Zz6g0AAAAAAAAAkKkxQjsVPTyUvly5cnJwcDCxGgAPi4uLM87m29JldRJ9C5De2Wr/Qt8CpG+22rdI9C9AekbfAiC1pGb/QqCdih6ev8nBwYHOFUinbG2uNfoWwHbYUv9C3wLYDlvqWyT6F8BW0LcASC3Pun+xrdNvAAAAAAAAAIBMi0AbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAO52JiopSr169NHHiRFksFrPLAQAAAAAAAIB0w9HsAjKLX375JUUB9c6dOzV9+nRJUlxcnHx8fJJs16RJk2daHwAAAAAAAACkd4zQTmc8PT3l4OAgSVq1apXJ1QAAAAAAAABA+kGgnc7kypVL1apVkyT99ddfioqKMrkiAAAAAAAAAEgfCLTToTp16kiSYmJitG3bNnOLAQAAAAAAAIB0gkA7HSpfvrxcXV0lSWFhYSZXAwAAAAAAAADpA4F2OpQlSxYFBARIkvbt26e4uDiTKwIAAAAAAAAA8xFop1N+fn6SpKioKB0/ftzkagAAAAAAAADAfATa6VTZsmWNxwcOHDCxEgAAAAAAAABIHwi006l8+fIpZ86ckqSzZ8+aXA0AAAAAAAAAmI9AOx0rVKiQJOnixYsmVwIAAAAAAAAA5svQgfbvv/+uxo0bq0KFCmrWrJl27tyZqM2RI0fk4+Mjf39/42v16tUmVJtYwYIFJUkXLlwwuRIAAAAAAAAAMJ+j2QWklrNnzyo4OFgzZsxQpUqV9NNPP6lnz576448/lD17dqPd4cOHVadOHc2YMcPEapOWMEL75s2bunv3rrJly2ZyRQAAAAAAAABgngw7QvvixYtq0aKFAgICZG9vr1dffVWSdOrUKat2hw8flre3twkVPl7CCG1JunTpkomVAAAAAAAAAID5MuwI7YCAAAUEBBjf79mzR1FRUSpevLhVu/DwcMXExKhu3bqys7NTy5Yt1a1btzSuNmkJI7SlB9OOeHp6mlgNAAAAAAAAAJgrwwbaDzt9+rT69Omjd99912q6EUlyd3dXmTJl1KpVK124cEHdunVT3rx51axZM5Oq/T8Pj9DmxpAAAAAAAAAAMrsMO+VIgn379qlVq1Zq0aKFOnXqlGj9xIkT1bFjR2XLlk2lSpVSmzZttHbtWhMqTSxbtmzKmTOnJG4MCQAAAAAAAAAZOtDeuHGjOnTooH79+qlPnz6J1t+7d09jx47VnTt3jGUxMTHKmjVrWpb5SIULF5YknT9/3uRKAAAAAAAAAMBcGTbQPnXqlPr27atPP/1UzZs3T7KNs7OzwsLC9Nlnn+n+/fs6cuSIFi1aZNxAMj3w8PCQ9GDaFIvFYnI1AAAAAAAAAGCeDBtoL1myRFFRURo0aJD8/f2Nrx07dhj/SlJoaKjCw8MVGBioLl26qHv37qpdu7bJ1f+fYsWKSZKioqJ0+fJlk6sBAAAAAAAAAPNk2JtCBgcHKzg4OMl1u3fvNh4XL15c8+bNS6uynlipUqWMx3///bcKFChgYjUAAAAAAAAAYJ4MO0I7oyhVqpSyZcsmSdq1a5fJ1QAAAAAAAACAeTLsCG1b1KRJk2SXL1myRDt27FCdOnXk5uaWxpUBAAAAAAAAgPkYoW0D2rZtK+nBPNrz5883txgAAAAAAAAAMAmBtg1o2LChPD09JUljx47VvXv3TK4IAAAAAAAAANIegbYNcHR01NChQyVJ58+f18iRI02uCAAAAAAAAADSHoG2jWjXrp0qVKgg6cEo7a1bt5pcEQAAAAAAAACkLQJtG+Ho6Ki5c+fK0dFRcXFxev3113Xu3DmzywIAAAAAAACANEOgbUP8/PwUEhIiSbp48aJefvllXblyxeSqAAAAAAAAACBtEGjbmN69e6tnz56SpP3796t27dq6cOGCyVUBAAAAAAAAQOoj0LZBU6ZM0dtvvy1JOnz4sKpUqaLt27ebXBUAAAAAAAAApC4CbRuUMJ92wkjts2fPqkaNGpo9e7YsFovJ1QEAAAAAAABA6iDQtlH29vaaNm2aJk+eLAcHB8XExKhr16567bXXdPHiRbPLAwAAAAAAAIBnjkDbhtnZ2endd9/V2rVrVaBAAUnSihUrVLp0ac2bN0/x8fEmVwgAAAAAAAAAzw6BdgZQq1YtHThwQK1bt5Yk3bx5Ux07dlSVKlW0efNmk6sDAAAAAAAAgGeDQDuDeO6557Ro0SL9+OOPKliwoCRp+/btql69ulq2bKnDhw+bXCEAAAAAAAAA/DcE2hnMa6+9piNHjmjo0KFydnaWJH377bcqU6aM2rZtq/DwcJMrBAAAAAAAAICnQ6CdAWXPnl0jR47U4cOH1bp1a9nZ2Sk+Pl6LFi1S6dKl1apVK23bts3sMgEAAAAAAADgiRBoZ2DFihXTokWLdODAAbVq1coItpcsWaLAwEDVrFlTP/74o+Li4swuFQAAAAAAAAAei0A7EyhdurQWL16sAwcOqG3btnJ0dJQkhYWFqVmzZipZsqQ++eQTXbx40eRKAQAAAAAAACB5BNqZSOnSpbVgwQKdOnVKgwYNkru7uyTp9OnTGjp0qDw8PPTGG2/ot99+U3x8vLnFAgAAAAAAAMC/EGhnQoULF9bo0aN19uxZTZ8+Xb6+vpKk2NhYLV26VA0aNFCxYsUUHBys/fv3m1wtAAAAAAAAADzgaHYB+D8rV65M89csUqSIRo4cqfDwcP36668KCwtTTEyMzp07p3HjxmncuHEqUaKE6tSpo1q1aum5555LtVqaNGmSatsGAAAAAAAAYPsItCE7Ozt5e3vL29tbnTt31saNG7V+/XodOnRIknTy5EmdPHlS8+fPl6+vr2rXrq3AwEC5ubmZXDkAAAAAAACAzIRAG1ayZ8+uRo0aqVGjRrp06ZI2bNig9evX6/z587JYLNq7d6/27t0rBwcHlStXTlWrVlWVKlWUK1cus0sHAAAAAAAAkMERaCNZBQoUUMuWLdWiRQsdO3ZM69ev159//qlbt24pLi5Oe/bs0Z49e/T555/Lx8dHVatWVdWqVZUvXz6zSwcAAAAAAACQARFo47Hs7Oz0/PPP6/nnn1fHjh114MAB/fXXX9qyZYtu3Lghi8WigwcP6uDBg5ozZ45KlSqlgIAAVa5cWZ6enrKzszN7FwAAAAAAAABkAATaeCIODg7y8/OTn5+funbtqiNHjuivv/7S5s2bdfnyZUnSsWPHdOzYMX399dfKnTu3KlasqEqVKsnPz0/ZsmUzeQ8AAAAAAAAA2CoCbTw1e3t742aS77zzjk6ePKnNmzdry5YtOnPmjCTpxo0bWrNmjdasWSNHR0eVKVNGlSpVUuXKlVWoUCGT9wAAAAAAAACALSHQxjNhZ2cnT09PeXp6qm3btrp8+bJ27typHTt2aN++fYqJiVFsbKxxU8k5c+aoYMGC8vf3V/ny5VWuXDmzdwEAAAAAAABAOkegjVSRP39+vfzyy3r55ZcVHR2tffv2aceOHdqxY4euXr0qSbp48aIuXryoVatWyd7eXqGhoapfv77q16+vgIAAZcmSxeS9AAAAAAAAAJCeZOhA+/fff1dISIguXryo4sWLa8iQIapYsaJVm3v37mnIkCHasGGDXF1d9d577+n11183qeKMKWvWrKpcubIqV64si8WiM2fOaMeOHdq9e7cOHjyo2NhYxcfHa/Pmzdq8ebNGjBghNzc31a1b1wi4X3jhBW4uCQAAAAAAAGRyGTbQPnv2rIKDgzVjxgxVqlRJP/30k3r27Kk//vhD2bNnN9pNmjRJUVFR2rhxo44dO6bOnTvLx8dH3t7eJlafcdnZ2alYsWIqVqyY3njjDUVHR+vAgQPas2ePTpw4of3790uS7ty5oxUrVmjFihWSpEKFCqlOnTrGV6lSpQi4AQAAAAAAgEzG3uwCUsvFixfVokULBQQEyN7eXq+++qok6dSpU1btfvrpJ/Xo0UMuLi4qV66cXnnlFSNERerLmjWrKlasqE6dOmnfvn26cOGCvvrqK7Vr104FChQw2l24cEFff/21unbtqhdeeEFFihRRmzZtNHv2bB09elQWi8XEvQAAAAAAAACQFjLsCO2AgAAFBAQY3+/Zs0dRUVEqXry4sezWrVu6fv26PD09jWUlSpRQWFhYWpaKhxQsWFDt2rVTu3btZLFY9Pfff+uPP/7Qhg0btGHDBt24cUPS/wXcX3/9tSSpcOHCViO4S5YsyQhuAAAAAAAAIIPJsIH2w06fPq0+ffro3XfftZpuJCoqSpLk4uJiLHN2dta9e/fSvEYkZmdnp7Jly6ps2bJ69913FR8frwMHDmj9+vVav369VcB9/vx5LVq0SIsWLZL0fwF3rVq1VL16dfn4+MjePsNekAAAAAAAAABkChk+0N63b5+6deum1q1bq1OnTlbrnJ2dJT24MWS2bNkSPUb6Ym9vL19fX/n6+qpv376Kj4/X/v37rQLuf/75R1LigDtXrlyqWrWqqlevrurVq6ty5cr8nAEAAAAAAAAbk6ED7Y0bN+q9997ToEGD1Lx580Tr3d3dlTt3bp06dUqlS5eWJJ08eVIlSpRI61LxFOzt7eXn5yc/Pz9jBHdyAfc///yjVatWadWqVZIkR0dHVahQQdWrV1e1atVUvXp1FSxY0MzdAQAAAAAAAPAYGTbQPnXqlPr27asxY8aoQYMGybZr3Lixpk6dqgkTJujUqVP66aefNH/+/LQrFM9MUgH3wYMHtWnTJuPrxIkTkqTY2Fht27ZN27ZtU0hIiKQH86cnjOCuXr26ypQpwzQlAAAAAAAAQDqSYQPtJUuWKCoqSoMGDdKgQYOM5bNnz1aXLl00e/ZsVapUSf369dPIkSP14osvysXFRYMHD5aPj4+JleNZsbe3N+bg7tatmyTp0qVL2rx5sxFw79q1S/fv35f0YHT+yZMntXDhQklSzpw5VaVKFSPgDgwMlKurq2n7AwAAAAAAAGR2GTbQDg4OVnBwcJLrdu/ebTzOli2bRo8enVZlwWQFChRQs2bN1KxZM0kPbgy6fft2I+DevHmzMU3JrVu3tHr1aq1evVqS5ODgoPLlyxsBd7Vq1VSkSBHT9gUAAAAAAADIbNJVoH38+HFt2rRJV65cUbt27XT27Fl5e3sre/bsZpeGDMrFxUW1atVSrVq1JEnx8fEKDw+3mqbk6NGjkqS4uDjt3LlTO3fu1NSpUyVJHh4eVtOUlCtXTg4ODqbtDwAAAAAAAJCRpYtAOz4+XsOGDdMPP/wgi8UiOzs7NWrUSNOnT9eZM2e0cOFCFShQwOwykQnY29vLx8dHPj4+6ty5syTpypUrVtOU7Ny5UzExMZKkM2fO6MyZM1q8eLEkyc3NTVWqVDFuNFmlShW5ubmZtj8AAAAAAABARpIuAu3p06dr5cqVGjVqlOrUqaPq1atLkj744AP16tVLISEhGjt2rMlVIrWtXLnS7BKS5eDgYIzkjomJ0bFjx3To0CHj686dO5KkO3fuaM2aNVqzZo2kBwF5sWLFjJC8dOnSyps3r5m7kqQmTZqYXQIAAAAAAADwWOki0P7hhx/Ut29fvfHGG4qLizOW+/j4qG/fvpowYYKJ1QHWnJycVLp0aZUuXVqSZLFYdP78eSPcPnz4sM6dOyfpwdUHCTebXLVqlSQpT5488vb2NkLuEiVKME0JAAAAAAAAkALpItC+du2afHx8klyXP39+3b59O40rAlLOzs5ORYoUUZEiRVS/fn1J0u3bt3X48GEj5D569Kju378v6cHve1hYmMLCwiRJzs7O8vLyUunSpeXj4yMvLy+5uLiYtj8AAAAAAABAepUuAu1ixYppw4YNqlatWqJ127ZtU7FixUyoCnh6OXLkUEBAgAICAiRJ9+/f1/Hjx62mKbl165Yk6d69e9q7d6/27t0r6cE0JZ6ensYIbh8fHz333HOm7QsAAAAAAACQXqSLQPvtt9/WsGHDdP/+fdWtW1d2dnY6ffq0tm7dqrlz52rQoEFmlwj8J1myZJG3t7e8vb31+uuvy2Kx6OLFi0a4ffDgQatpSo4dO6Zjx44Z84oXKFDAah7uIkWKyN7e3sxdAgAAAAAAANJcugi0mzdvrhs3bmjGjBlavHixLBaL+vXrpyxZsqhz58566623zC4ReKbs7OxUqFAhFSpUSC+++KKkB9OUJITbhw4d0rFjxxQbGytJunTpki5duqR169ZJktzc3OTt7a3SpUurXLlyKlmyJPNwAwAAAAAAIMNLF4G2JHXr1k1t2rTR7t27dfPmTeXIkUN+fn5yd3c3uzQgTeTIkUOBgYEKDAyUJEVHR+vYsWNGwH3o0CFFRkZKku7cuaPt27dr+/btkiQXFxeVLl1aZcuWJeAGAAAAAABAhpVuAu2dO3dqy5Yt6tWrlyTp4MGDGj58uLp06aKyZcuaXB2Q9rJmzaoyZcqoTJkykh5MRXL27FljFPfBgwd15coVSVJUVJR27typnTt3SiLgBgAAAAAAQMaULgLtDRs2qFevXipXrpwRaNvZ2enUqVNq3bq15s6dq0qVKplcJWAue3t7FStWTMWKFVPDhg0lSVeuXNGBAwe0f/9+HThwQJcvX5aUdMBdpkwZlS9fXv7+/ipSpIjs7OxM2xcAAAAAAADgaaSLQDs0NFSNGzfWmDFjjGU+Pj5avny5goODNWnSJH399dcmVgikT/ny5VNQUJCCgoIkSVevXrUKuC9duiTpQcC9Y8cO7dixQ5KUJ08e+fv7y9/fX35+fqbVDwAAAAAAADyJdBFoHz9+XP37909yxOhrr71mjNoG8Gh58+ZV3bp1VbduXUn/F3Dv27dPe/fu1bVr1yRJ165d05o1a7RmzRrZ29tr6tSpatCggV566SUFBgbK0TFddA0AAAAAAACAlXSRWrm5uenkyZOqWrVqonVnz55VtmzZTKgKsH0PB9wWi0Xnzp3Trl27tHv3bh04cEAxMTGKj4/X1q1btXXrVn388cdyd3fXyy+/rKZNm6phw4bKkSOH2bsBAAAAAAAASEongXb9+vU1ZcoUFSxY0BhZKkkbN27UlClT9NJLL5lYHZAx2NnZqWjRoipatKiaNm2qmJgYHTx4ULt379bx48e1b98+SdLNmzf19ddf6+uvv5aTk5Pq1q2rpk2bqmnTpipUqJDJewEAAAAAAIDMLF0E2u+//77279+vHj16KEuWLHJ3d9fNmzcVGxsrPz8/9e/f3+wSgQzHyclJ5cuXV/ny5dWkSRNdvHhRv/32m1auXKlff/1VkZGRiomJ0erVq7V69Wr16tVLtWrVUqtWrfTmm28qT548Zu8CAAAAAAAAMpl0EWhnz55d33zzjTZs2KCdO3fq1q1bcnNzU6VKlVSnTh3Z29ubXSKQ4RUsWFBvv/223n77bd27d0/r1q3T8uXLtWLFCl28eFEWi0UbNmzQhg0b1Lt3b9WvX1+tWrXSG2+8oezZs5tdPmCTLBZLkvePQMrfm9R6D/nZAObgMw0AAIDHSTdJsb29verWrasBAwZo5MiRGjhwoIKCggizARM4OzurUaNG+vzzz3Xu3Dlt2bJF/fv3V+HChSVJcXFx+vXXX/XOO++oYMGC6tatm7Zv3y6LxWJy5UiJwYMHy8vLS2FhYUmu37hxo7y8vDRhwoQ0rWvp0qXy8vLS1q1b//O2Ro4cqZCQEOP7v//+W126dFGVKlUUGBiojh076u+//7Z6TmxsrCZPnqzatWvLz89PrVu31t69e63aHD9+XM2bN1eFChXUvXt340arCf744w81atRIcXFxj63x6NGjeuuttx7bLuF9OXfu3GPbpjdBQUEaNGiQJCkmJkYNGzbUnj17Hvu8P/74Q8HBwY9tt3PnTnXt2vW/lplISn82SN/atWundu3aJVoeERGhFi1aqGzZsvr9999Nq+NJbN269bH945tvvqlmzZolWv7rr7/Ky8tLjRo1SrRu9erV8vLy0o4dO1JUx8P7cu7cOXl5eWnp0qWSnk1fxWcaSH8iIyM1YsQIVa9eXf7+/urSpYtOnDjx2Oft3r1b7dq1k7+/v2rUqKFRo0YpIiLCqs3x48fVvXt3+fv7KyAgQH379tWpU6eS3WZsbKzefPPN/9ynAjBfavYtKdl2RESExo4dq3r16hlXrS9atEjx8fHPdD+RekxLiwcPHqyzZ88ajx/19eGHH5pVJpDp2dvbKzAwUBMmTNCZM2f0559/qmfPnsqbN6+kB/8RzJo1SwEBAfL399f06dMVGRlpctV4lMGDBytfvnwaNmyY7t69a7UuIiJCw4YNk5eXl/r27ZumdSWMnPuvI+j++usvrVmzRt27d5cknT59Wm3bttW9e/f0ySefaPTo0YqJiVHr1q2tDmzGjBmj+fPnq3PnzgoJCZGDg4PeeecdnT592mgzcOBAPffccwoNDdU///yjTz/91FgXFxeniRMnql+/fnJwcHhsnb/++qt279792HZ16tTRkiVLlC9fvid5G9IdJycnDRgwQMHBwbp3794j286fP18XL1587Da/++47HT9+/FmVaEjpzwa2JyIiQp07d9bhw4f12WefqV69emaX9MxUrVpV4eHhifr1jRs3yt3dXSdOnND58+et1m3fvl2urq4qX778f379Z9FX8ZkG0p/+/fvr119/Vf/+/TV27FhdvnxZ7du3161bt5J9zuHDh/XOO+/I1dVVoaGh6tevn3755Re9++67RpuzZ8/qrbfe0tGjRzVs2DBjIEXLli2TPTE2a9Ys7d+//9nuIABTpFbfkpJtWywWvffee1q6dKk6dOigGTNmqG7duho1apRmzJiRqvuNZ8e0QHvr1q1G6LV169bHfgEwn729vWrWrKnPPvtMFy5c0IoVK9SkSRPjSoq9e/eqV69eKlasmD766CNdvXrV5IqRlBw5cmjEiBE6f/681ShmSZo4caKuXr2qcePGycnJKU3rSjhJkj9//v+0ndGjR+udd96Ri4uLJGnBggVycXHRzJkz9eKLLyooKEizZs2Si4uLFi5cKEm6ePGiFi9erIEDB6pdu3YKCgrSnDlz5O7urtmzZ0uS7ty5owMHDqh3796qXr26OnfurM2bNxuvu3TpUmXPnl3169f/T/X/W+7cuVW+fPk0/3mkhnr16ilLlixavHix2aUgE0oIsw8dOqQZM2aodu3aZpf0TFWtWlWxsbGJriwJCwtT27Zt5eTkpI0bN1qt27FjhwICAuTo+N9nIcxIfRWAB3bv3q1169ZpzJgxatasmV566SXNnz9fkZGR+vrrr5N93pdffqmcOXNq6tSpqlGjhpo1a6b+/fsrLCzMGEzw5ZdfKioqSvPnz9frr7+uWrVqafLkySpatGii41PpQZA1c+ZM43gRgO1Kzb4lJds+ePCgNm7cqI8++kht2rRR1apV1a9fP7Vo0UJffPEFV57bCNMC7bVr18rb21uStGzZMq1duzbZrz/++MOsMgEkw9HRUU2aNNGKFSt05swZjRw5UsWKFZMkXb9+XSNGjFCxYsXUp08fXb582eRq8W9BQUFq0qSJFi5caIQfO3fu1OLFi9W3b1+jf354yogESV1WfuTIEXXr1k0VKlRQhQoV1KtXL+MqHOn/Lpf/66+/1LFjR/n5+al69eoaP368MT3H888/r2zZssnDw0OSdODAAb399tuqWLGi/P399c477zx2uor169fryJEjaty4sbHM09NTHTt2VLZs2Yxl2bJlU4ECBXTmzBlJD0Z1x8bGWoXRTk5OqlOnjjZs2CDp/0aOOzs7S5KyZMliXJIWFRWlqVOnasCAAY+sL0FoaKimTZsmSfLy8lJoaKjxeNq0aWrWrJl8fX01bdq0RO/3oEGD1KlTJy1ZskT16tWTr6+vWrVqpZMnT2rdunVq0qSJ/Pz81Lx5cx06dMh4zad9nvQg9Grbtq38/PwUEBCg4OBg3bhxw6rN4cOH1aFDB/n7+6tu3bpasWJFkvvepEkTzZs3TzExMUmub9eunbZt26Zt27Y9coqFQYMG6ccff9T58+etpj2Ijo7WuHHjVLt2bZUtW1ZNmjTRqlWrrJ77qN+t5H42sG2RkZHq0qWLwsPDNWvWLFWvXt1qfVBQkD799FO9/fbb8vX11ZAhQ5KdQuPf/eKmTZvUokUL+fv7q3LlyurRo8cjRxlv3LhRZcuW1ZAhQ4w/mLZv365OnTqpcuXKKlu2rIKCghQaGvpEl71WrFhRWbNm1a5du4xlR48e1aVLl1S3bl1VqFDBaqqpO3fuKDw83Hgv7t27p4kTJ+qll15S2bJlVaFCBXXo0CFRf5Ccf79fN27cUP/+/VW9enWVK1dOTZs21bJly5J9Pp9p4Mkl1Xcl187LyyvZr+SEhYUpW7ZsqlGjhrEsd+7cqly5snF8lJT33ntPs2bNsjrBlSVLFkky/v8/ceKESpUqpaJFixpt7O3tk9x2TEyMMeigRIkSj3hHADwLtty3pHTbLVu2VNWqVa227+npqbt37+r69evJ1oD0I13cFLJx48YaPHiwXn75ZbNLAfAUChcurKFDh2rw4MFaunSpxo4dq507dyoqKkrTpk3T/PnzNXDgQPXr10+urq5ml4v/b+jQofrrr780cuRIff311/roo49Uvnx5derU6Ym2c/LkSbVq1Uqenp4aO3asYmNjNWPGDL311ltavny5nnvuOaPtgAED1Lp1a3Xp0kXr16/XF198oaJFi6pVq1bKnz+/cUl4wkjKKlWqKDQ0VDExMZoxY4Y6deqk9evXy83NLclaVqxYofLly1uN8m7dunWidqdPn9bRo0eNg5jjx4/L1dU10aifYsWK6cqVK4qMjFT27NlVqlQpLV26VN27d9eKFStUoUIFSQ+myPDx8VFAQECK3rPmzZvr0qVL+v7777VkyRIVKFDAWPf555+rf//+KlGihAoXLpzkpbW7d+/WlStXNGjQIEVHR+ujjz5S165dZWdnp759+8rFxUXDhw/XgAED9PPPP/+n523fvl0dOnRQlSpVNHnyZN26dUtTpkxR+/bt9f3338vZ2VmXL19W27ZtVbx4cY0fP14RERGaMGFCkgeDDRs21KRJk7Rt2zarA80Ew4cP1wcffGA8LlWqVJLvYc+ePXXjxg0dPHhQ06ZNk4eHhywWi3r16qVdu3apb9++KlmypNasWaP3339fMTExeu211x77u/Wonw1s0927d9W1a1cdPHhQc+bMUaVKlZJst2jRInXo0EFdunSRq6urTp48+dhtnz17Vj179tQbb7yhfv366fbt25o0aZK6du2qNWvWJLoXzPbt29W7d281adJEo0aNkp2dnXH5bMOGDRUSEiKLxaKVK1dq2rRp8vT0tDpB9yhZs2aVv7+/VaAdFham3Llzq0yZMqpRo4Y+//xzxcbGytHRUbt27VJ8fLwRaA8cOFA7duxQv3795OHhodOnT2vKlCnq37+/fv755yeeDuqDDz4wTnBnz55dy5cvV3BwsAoUKKAqVaokas9nGng6/+67kjJt2rRkTyQ/yvHjx1WkSJFEU6l5eHho5cqVyT4vf/78xrHY3bt3tWfPHoWEhKhChQrGoIlcuXLpyJEjun//vhFISQ/61Tt37ujmzZtyd3eXJH322WeKjY1V3759n/g4FcDTsdW+JSXbLlOmjD7++ONE2//999+VO3du5c6d+4n3CWkvXQTaMTExypUrl9llAJnWo/7TeFLOzs4aNmyY9u/fr++++0579+415mWePHmyunTpYjUyrkmTJs/stfFk3N3d9dFHH6l3797q2LGjzp07p2XLlqVo/ueHTZs2TS4uLpo/f76yZ88u6cGl7/Xq1dMXX3xhdXO/5s2bq1evXkab33//XevXr1erVq2stnns2DH9888/at++vREae3p6asmSJYqMjEw20N6yZctjw5979+4pODhYTk5Oatu2raQHIxUTan9YwsFbRESEXF1dNXr0aL333nuaM2eOypYtqylTpujGjRuaO3euFixYoL1792r06NG6d++eOnbsqFdffTXJGgoUKGCEKv+eu7ZSpUrq0KGD8X1SgXZkZKQmT56skiVLSpK2bdumb775RvPnzzdC+tOnT2vs2LG6ffu2cuTI8dTPmzhxokqUKKGZM2cavxt+fn5q3LixfvjhB7Vp00bz589XXFycZs2aZRwAlihRQi1atEhUe7FixZQzZ0799ddfSQbapUqVMn4Wj5rX18PDQ7lz55aTk5PRbtOmTdq4caNCQkKMk+Q1a9ZUVFSUJkyYoFdeeeWxv1uP+tnA9iSE2Tt37jS+T06hQoWsrrJISaC9b98+3bt3T926dTP+wCpQoID++OMP3b1716pf2bdvn7p166YGDRrok08+MQLiw4cPq1q1aho/frwRgFevXl1r167V1q1bUxxoSw/61S+++ELx8fGyt7fXxo0bVa1aNdnZ2alGjRqaMGGCdu/ercqVK2v79u0qWLCgPD09FRMTo8jISA0dOtT47AQEBCgiIkJjxozRtWvXnvgy/23btqlXr17GPOUBAQFyd3dPdkoSPtPA0/l335WU0qVLP9W2H3V8lJJ75lgsFlWpUkXR0dFyd3fX//73P2Nds2bN9NNPPyk4OFjvv/++ceIrYWqkqKgoubu7a9++fZo7d64WLVrElEZAGrLVvuVpt/3ll19q27ZtGjRoUKIBCUif0kWg3b59e02ePFnOzs7y9vY25j0FYJvs7Ozk6+srX19f7d69W/Pnz9fJkyd148YNjR07VjVr1lS3bt2MkA3mqV+/vl5++WWtWrVKw4YNM6aNeRJbtmxRQECAnJ2dFRsbK0nKnj27KlWqZDXHtCT5+/tbfV+gQIEkA6bnn39euXPnVvfu3dWwYUPVrFlT1atXN0buJiXh8rAiRYok2yYiIkK9evXS/v37NWXKFBUuXFiSHjtPWsJBja+vr9auXau7d+8aU5iMGjVKderUkaenp4KCgtStWzd5eXmpa9euj73cLik+Pj6PbZMzZ04jlJakPHnySHoQNCdIGNX0cKD9pM/LkiWL9u7dq06dOslisRg/36JFi6pkyZLatGmT2rRpo507d6p8+fJWoxn8/PxUqFChJOsvVKhQsjd8SkpcXJzVz8je3j7JA82//vpLdnZ2ql27tlGr9OByyBUrVujo0aNP9bsF23XgwAG5u7tr0aJF+vDDDzVo0CAtX748yXA2JZ+9f/Pz81PWrFn15ptvqmHDhqpVq5YCAwPl6+tr1e7ChQvq0qWLLBaLhg0bZvX7+9prr+m1115TdHS0Tp48qdOnT+vQoUOKi4vT/fv3k3zdh3+/JcnBwUF2dnaqVq2aQkJCdOTIERUvXlw7duwwRiB5e3srT5482rx5sypXrqwdO3aoWrVqkh5MsTRnzhxJ0uXLl3Xy5EmdOnVK69atk6SnGn0VGBio0NBQHTx4UDVr1lTt2rWtTnCmBJ9p4PFS0nf9+//Rf0tuHv1HPSclV20kXLUXHR2tWbNmqU2bNlq8eLG8vb2Nqec+/fRT46qwatWqqUuXLgoNDZWzs7Oio6M1aNAgY9oDAGnHVvuWp9n2woULNXr0aDVq1EjvvPPOY18f6UO6CLSXL1+uCxcuJHlZuPTgl+7gwYNpXBWAZ8Hf31++vr5av3695s6dqzt37mjjxo06cOCABg8ezAjtdKBmzZpatWrVU98g7ebNm1q1alWiOU0lJbpcK2H+6QT29vZJHnS4urpq0aJFmjFjhn755RctWbJEzs7Oatq0qYYOHZrkCJ07d+5IktVc2Q+7ePGiunXrppMnTyokJMQYNSg9COCTOmMfEREhSYlGhCe8xpkzZ/TDDz9o5cqV2rlzpyIjI9WmTRtjDsg1a9Y8caCdXP0PS2rUQUqe+6TPu337tuLj4zV79mzj5pgPy5o1qyTp1q1bSZ5ISG5Ep4uLi/HepkT9+vV1/vx54/vXX39dY8aMSdTu5s2bslgsxijNf7ty5Yp8fHye+HcLtitnzpz68ssv5e3trXHjxql169YKDg7WnDlzEv1Rk5LP3r8VKVJECxcu1KxZs/T999/rq6++Uo4cOdS6dWu99957xmucO3dONWrU0NatWzVt2jSrObjv3bunkSNHavny5YqNjVWRIkXk7+8vR0fHJPvHc+fO6cUXX7RaNnr0aDVr1kxlypSRm5ubdu3apcuXLysmJsa4KsrOzk5Vq1bV1q1bde/ePR04cEDt27c3trFx40Z9+umnOnHihFxdXeXt7W28J09zc6SQkBB9/vnn+uWXX7R69WrZ29urWrVq+vjjj42TiY/DZxp4vJT0Xf/+f/TfwsPDk1yePXt2Xbt2LdHyR10t97AsWbIYfVDlypUVFBSkL7/8UqNHj5Ykvfrqq2rcuLHOnj0rFxcX5c+fX1OmTJG9vb1y5MihCRMmKD4+Xj179jROaiX0R7GxscbJPADPnq32LU+y7fj4eI0bN07z5s3TK6+8orFjx9Kn2JB0EWgnd0k2gIzBwcFBL774oipUqKDPPvtM27Zt0z///KOhQ4eqePHiat68udkl4hESbtqY4N8jqt3c3FStWjWraTISJHdWPiU8PT2Nm0bu27dPy5cv1+LFi+Xh4aHOnTsnap8wddXt27cTrQsPD1enTp0UHR2tuXPnqnLlyoleKyIiQjdu3LAK4U+fPq3ChQsnCuIThISE6M0331SRIkW0d+9eubm5GSMvc+TIoatXrz71/qcHrq6usrOz0zvvvJPktAcJV1TlypUryQPHmzdvJrnd27dvJzt6OykzZsywGiGa3DRlbm5uypYtm7766qsk1ydcgfCkv1uwXV5eXsacin5+furWrZs+++wzffHFF+rSpcsjn5vwB82/b8z475NfCTdwjYmJ0c6dO7VkyRJ9/vnn8vb2VqNGjSRJL7zwgmbOnKnJkydr7ty5aty4scqVKydJ+uSTT7R69WpNnjxZ1apVM/6A/PeNihLky5dP33//vdWyhBNKDg4OCggI0N69e3X27Fl5eXlZnViqUaOGhg4dqu3btys2NtaYy/rMmTPG9CAzZ85U0aJFZWdnp0WLFhmX/z8pNzc3ffDBB/rggw904sQJ/fHHH5o+fbpGjBihWbNmpXgbfKaB/+7f/4+mVIkSJRQWFmZMY5Tg9OnTVld8/dvatWvl5uZmdbzl5uamokWL6sqVK5IezHO7f/9+vfbaaypevLjR7uDBg/Ly8pKDg4NWr16t8+fPJ7rCT3owB27CyTwA5kiPfUtKtx0TE6P+/fvrt99+U8eOHTVw4EDCbBuTLgLt3r17m10CgDSQK1cuDRkyRL/88otmzZqlmJgYtWjRQl988QU3eEmnsmfPrkuXLlktS5iLNkFAQICOHTsmHx8fI8C2WCwaMGCAihUr9lSX8f/666/66KOPtHLlSuXNm1f+/v7y9/fXzz//rAsXLiT5HCcnJ+XNm1cXL160Wn7x4kV16NBBDg4OWrx4cZI3GUy47P7XX381rhaKiYnR+vXrVbNmzSRfb9++fdq4caN+++03SQ9Go9+6dcu4udHVq1cfOYWLLczNlj17dpUuXVonTpwwwjfpwYjSvn37qnbt2ipVqpSqVKmiOXPm6PLly8Y8wseOHdPZs2cTjay0WCy6fPlyohGmD7O3t7cKEZMb5f7v9zAgIEBz586VxWKxujT5hx9+0Jo1a/Tpp5+m6HfLFn42eDo9e/bUn3/+qSlTpiQ5NcjDEq5ouHTpkjw8PCQ9CGAePlEzf/58ffnll1q9erWcnJxUtWpVlS1bVr/88otVX+Xu7i5HR0f16tVLq1at0tChQ/XDDz/I0dFRO3fuVGBgoNVVIwcOHNCNGzcShenSg77u4c/jv1WrVk2LFi2Sq6tronnqq1evrvv37+u7775T6dKljRN4Bw4cUHR0tLp27WrsqyQjzH7SEdrnz59X69atNXjwYDVs2FCenp7y9PTUnj17dPr06WSfx2caSB1PerVYgoSbyW7cuNG4ku/GjRvasWOHunXrluzz5s+fr+vXr2vFihXG/TcuXbqk48ePq02bNpKko0ePKjg4WL6+vvL09JT04NghLCxMPXr0kJR0WDZ8+HBJ0ogRIx45zRyA1Jce+5aUbnvw4MFas2aNBg8ezDQjNsrUQPv69etaunSpLly4oGLFiqlJkyZ67rnnzCwJQCqzs7PTyy+/rIIFC2rMmDGKiopSt27dVKBAgSe68RXSRt26dTVz5kzNnDlTfn5+Wrt2rbZs2WLVpmfPnmrVqpW6deumt956S1mzZtWSJUv0+++/a+rUqU/1uhUqVFB8fLx69eqlrl27ytXVVb/88ovu3Lmjl156KdnnVa9eXbt27bJaNmrUKF2/fl0jRoxQRESE9uzZY6zLnj27SpUqpcKFC+v111/X6NGjFR0dreLFi2vevHm6fft2sqP7xo8frw4dOhiBUPny5eXi4qJJkybphRde0K5duzRw4MBka02Y1/qnn36Sn5+fihYtmtK3J03169dPXbt2Vf/+/fXqq68qLi5Oc+fO1d69e9WzZ09J0ttvv63vv/9enTp1Up8+fRQXF6eQkBBlyZIl0faOHDmiO3fuJHuiQHrw3uzevVt//fWXSpcurZw5cybb7tq1a9qwYYN8fHxUu3ZtVa5cWT179lTPnj1VsmRJ7du3T1OnTlXNmjWVO3fuFP1u2crPBk/O0dFR48eP1+uvv65+/fpp2bJlyU7FExgYKGdnZ40ZM0bvvvuuIiMjNXXqVGOeeUmqUqWKJkyYoF69eqlt27ZycHDQN998IycnJ9WtWzfRNl1cXDR8+HB17dpVc+bMUbdu3eTr66tffvlFixcvVsmSJXX48GHNmDFDdnZ2ioqKeuJ9rFq1qkaNGiUHBwf179/fal3evHn1wgsvaO3atVZX1ZQpU8Z4bzp27KiYmBgtXbpU69evl/Tom2kmpXDhwipQoIBGjRqliIgIeXh46MCBA9qwYcMj/1DlMw2kL5UrV1ZAQIBxtYW7u7tCQ0Pl5uamt956y2h37NgxxcTEGDeI69mzpzp27Kj3339fLVq00I0bNzR9+nTlyJFDHTt2lCTVrl1bHh4eGjBggN59911FRERo3LhxKlKkiBEuJRWWJdyw+1En9gCkb6nZt6Rk27///rt++uknBQUFqXz58lZ/H0oPbnbJlGXpn2nDFY4dO6aXX35ZEydO1OLFizVmzBg1atRI27dvN6skAGnI399fI0aMkLOzs+Li4tSiRQsdP37c7LLwL926dVPz5s01Z84c9ejRQ1evXtUnn3xi1cbb21uLFi2SnZ2dBg4cqL59++rq1av67LPPHhk+P0q+fPn0xRdfyM3NTUOGDFG3bt30999/KzQ01LhEPikNGjTQ4cOHdfnyZUn/N8paejCip2XLllZfI0aMMJ778ccf66233tLs2bP1/vvvKy4uTvPmzUtylPWGDRt04sQJq0AoIcz+/fffNWHCBAUHB6ts2bLJ1vrSSy+pXLlyGjRokHEztvSoRo0amjNnji5duqS+fftq4MCBcnBw0Lx581S+fHlJD66+WLx4sYoUKaJBgwbp008/VZs2bYypHh72559/Km/evMnOiStJbdq0UZYsWdSlSxf9+eefybZr1qyZChcurF69emnZsmWyt7fXrFmz1LhxY82cOVOdOnXSN998ow4dOigkJERSyn63bOVng6dTokQJDRw4UGfPnjVG+iUlR44cCg0NVVxcnHr16qUpU6aoV69eVp9rb29vff7554qIiFC/fv3Uu3dv3bx5U3PnzjVGHP5b7dq11aBBA3322Wc6deqUBg0apHr16mny5Mnq1q2bvvvuO/Xo0UMtWrTQ7t27E0379DglS5ZU3rx55eTkpIoVKyZaX6NGDd2/f9+4MkV6MHXHxIkTdfnyZfXo0UPDhg2TJC1YsEB2dnbasWPHE9UgSdOmTVPNmjU1ZcoUdezYUYsXL1bv3r3Vq1evZJ/DZxpIf6ZNm6YXX3xR48aN06BBg5Q/f37Nnz/f6mTziBEjrK66rlKliubOnatr166pb9++GjVqlMqUKaNvv/3WuCG1i4uLvvjiC+XNm1f9+/fXp59+qmrVqmnBggXJnmgEkHGkVt+Skm0nXGG7du3aRH8ftmzZ0pi+BOmbneVp7vLyDPTu3VuHDh3S2LFjVa5cOZ04cUJDhgxRbGysVqxYYUZJz1xcXJxxpufixYtPdUMdIKOLj4/Xa6+9JunBaODff/89TS4NfvjzWb58eeOSJVtgy7WnNovFoldffVUNGjRgOqt0yGKxqEGDBmrdunWGvrTPVj+jtlo3kFnY8mfUlmsHMjpb/nzacu1AZpCan1HTRmjv2LFD/fr1U6VKlZQ1a1b5+Pjoww8/1NGjR3Xjxg2zygKQxpo2baru3btLktatW6fvvvvO5Ipgy+zs7PTBBx/om2++UUREhNnl4F9+++03xcXFqVWrVmaXAgAAAACwUaYF2nfu3FGhQoWslnl7e8tisejatWvP9LXmzZunQYMGJbnuyJEj8vHxMW4g4+/vr9WrVz/T1wfwaGPHjjUuERo3bhxXM+A/qVWrll588UXNnDnT7FLwkJiYGE2aNEnjxo2Ts7Oz2eUAAAAAAGyUaTeFjIuLSzTU3MXFRZJ0//79Z/Yac+bMUUhIiJo2bZpkm8OHD6tOnTqaMWPGM3lNAE8uR44c6tOnj4YPH65du3Zp+/btCggIMLss2LCH58ZG+uDk5MQJYwAAAADAf2baCO20EBwcrJ07d6p58+bJtjl8+HCSN60CkLY6depkPF65cqWJlQAAAAAAACC9SpeBtp2d3TPZzsCBAzVz5kzlzZs32Tbh4eHasWOH6tatq6CgIC5RB0xSuHBhVahQQZL0+++/m1wN8HQiIiIUFBSkpUuXPrZtfHy85syZo/r166tcuXJq1KiRFi5cmKjdgAED5OXllejr119/faa1x8bGqkWLFgoNDU20LjIyUiNGjFD16tXl7++vLl266MSJE8/09QEkbenSpXrllVfk6+urBg0a6Kuvvnrs1FzR0dGaNGmS6tatKz8/P7Vs2VIbN260apPQB7300kvy9fXVq6+++sxvzP7TTz+pcePG8vX1VaNGjfTjjz8manP8+HF1795dFSpUUEBAgHr16qWzZ88+0zoA/J/9+/erXbt28vf3V40aNTRp0iTFxMQ89nlhYWF644035Ofnp6CgIM2ZMydRX3T69Gl1795dlSpVUmBgoIYPH57oniZPekyxdu1aeXl5PXVN69at05tvvqly5cqpVq1a+vTTTxUZGfnY/QXw35nd3xw7dkzdunVT5cqVFRgYqODgYF29etWqzXfffZfk31off/yxJCk0NDTJ9Qlf27Zt+4/vEp6WaVOOSFLLli2TXP7GG29YfW9nZ6eDBw8+8fbz5cv32Dbu7u4qU6aMWrVqpQsXLqhbt27KmzevmjVr9sSvB+C/CQwM1K5du7R//37Fx8fL3j5dnnMDknTr1i317NlT58+fT1H7MWPG6Msvv1SrVq1Uv359nTlzRlOmTNG5c+es7vtw+PBhvfLKK2rXrp3V84sXL/7Mao+OjtbAgQO1d+9e1axZM9H6/v37a+/evfrggw+UPXt2TZs2Te3bt9fPP/+snDlzPrM6AFj77rvvNHToUHXu3Fk1atTQ3r17NWbMGN29e9e4oXJShgwZonXr1qlfv34qUaKEfvzxR3Xr1k1fffWVKlWqJEmaMmWK5syZo759+6pcuXLasGGDPvjgA9nb2+uVV175z7WvXr1aAwYMUPv27VWzZk39/vvvGjRokJycnNS4cWNJ0sWLF9W6dWuVKFFCkyZNUlRUlCZPnqyOHTtq5cqVzLcPPGNnz55Vhw4dVL58eU2ePFnHjx9XSEiIbt68aYQ3SdmzZ4+6d++uRo0a6d1339XOnTs1fvx4xcXFqWvXrpKk27dv6+2331aePHk0ZswY3bhxQ+PHj9e5c+c0Z84cY1tPckyxdetW9e/f/6lrWrNmjfr06aOAgABNnjxZ9+/f1/Tp07V7924tXrxYjo6mxiFAhmZ2f3P58mW1b99eHh4eGj9+vKKiohQSEqIOHTroxx9/VJYsWSRJhw4dUokSJTRmzBirOhLu8dW8efNEfx/dv39f77//vvLmzStfX99n9p7hyZjWg/fu3dusl7YyceJE43GpUqXUpk0brV27lkAbMEGZMmUkPRi5ceHCBRUpUsTkioCU+eOPP/TJJ5+keMTPjRs3tHDhQjVv3txqvu+CBQuqZ8+eat68uUqWLKno6GidPHlSb7/9tsqXL58qte/YsUMff/yxLl++nOT63bt3a926dZo1a5Zq164tSapUqZJefPFFff311+rRo0eq1AVA+vzzz9WgQQN98MEHkqSqVavq1KlTWrhwYbKB9rlz57Ry5UoNGzZMbdq0kSRVqVJFu3bt0tdff61KlSopKipKX331ldq1a2f8cVi1alX9/fffWrBgwTMJtCdNmqSGDRvqww8/lCTVrFlTt27d0pQpU4xAOzQ0VNmzZ9e8efOMe+kUKVJEPXr00IEDB4zwHcCzMXv2bLm6umr69OlycnJS7dq15ezsrJEjR6p79+4qVKhQks8LDQ2Vj4+Pxo8fL+nBDbhjY2P1+eefq3379nJ2dtbixYt18+ZNLV26VLlz55Yk5c+fX127dtXOnTtVsWLFFB9TREREaPbs2Zo9e7bc3Nx09+7dp6opNDRUJUuW1BdffCEnJyfj9erXr6+lS5eqRYsWz/YNBmAwu7/57rvvdOfOHc2YMUO5cuWSJOXOnVvt27fXli1bjJD60KFDKleuXLJ/axUoUEAFChSwWjZ69GhFRkbqm2++4eS7iTJ1oH3v3j1NmTJFPXv2lJubmyQpJiZGWbNmNbkyIHMqWLCg8fjq1asE2ngqQUFBatKkiaKiovTjjz/K3t5etWvX1ocffih3d/ckn7N161a1b98+2W2+/vrric7aJ7h9+7Z69+6tV199VW3bttWbb7752BpPnTqluLg41a1b12p5YGCg4uPjtXHjRpUsWVJHjhxRbGysfHx8Hrm9CxcuaMKECQoLC1N0dLTKly+v4OBglS5d+rG19OjRQxUrVtSMGTMUFBSUaH1YWJiyZcumGjVqGMty586typUra8OGDQTayFTSun+ZNWtWouPSLFmyKDo6Otnt5cuXT99//73VVRz29vZydHQ0nufk5KTFixfrueeeS7TtO3fuWC37/fffNX36dB09elQ5cuRQo0aN1K9fP2XLli3ZGs6dO6dTp06pb9++VssbNGigX375RadOnVKxYsX022+/qWPHjkaYLUnlypVTWFhYstsGMpK07lPCwsJUu3ZtI9yVpIYNG2rEiBEKCwtLMuCNiYnR1q1bk/w8f/HFF9q5c6eqV6+usLAwVaxY0QiXJKlGjRpydXXVn3/+qYoVK6b4mOL777/Xt99+q2HDhunq1auaNm3aU9V04sQJtWnTxmp/8+TJI09PT61fv55AG5lKZutvWrdurdq1axthtiRjVHbC8ZDFYlF4eLjq16+f7D7+W3h4uBYsWKD+/fuTV5gsXV1jc/z4cW3atElXrlxRu3btdPbsWXl7eyt79uyp8nrOzs4KCwuTxWJR//79dfLkSS1atEijRo1KldcD8GgPX2b47z+ogSfx9ddfq1ixYho9erRu3LihiRMn6vTp0/rmm2+SvE9DmTJltGTJkmS39/DB0r85Ozvr559/lqenp86dO5ei+hIOrC5cuGC1/MyZM5JkbOfw4cOSHkw70L17d928eVO+vr4KDg6Wn5+fpAejvVu1aiUXFxf973//k4uLi7788ku1adNG33//vUqWLPnIWhYuXJjs3JTSg/+bixQpIgcHB6vlHh4e3MAVmVJa9i8Jn1+LxaJbt25pzZo1WrZsmTp27Jjsc5ycnFSuXDlJD+bJvnz5subOnaszZ85o6NChkiQHBwfjpugWi0XXr1/X0qVLtXnzZqvLgFeuXKkBAwaoSZMmeu+993T+/HmFhITo2LFjmjdvXrL3vTl+/LikxFMjFStWTJJ08uRJOTg46M6dOypUqJBGjBihn3/+WVFRUapRo4aGDx+eaDQUkFGlVZ9y7949nT9/XiVKlEjUPnv27Dp58mSSzzt79qzu37//yM9z9erVdfz4cb388stWbRwcHFSkSBFj2yk9pggKClLLli3l4uKS5L09UlqTu7t7omOt+/fv6+LFiymaxxfIaDJTf5M7d26jvujoaB06dEgff/yxPDw8jJNqZ86cUWRkpPbv368GDRro3LlzxpVir732WpI1jhs3TkWKFNHbb7+d7PuCtJEuAu34+HgNGzZMP/zwgywWi+zs7NSoUSNNnz5dZ86c0cKFC5/pQa2/v79mz56tSpUqKTQ0VCNGjFBgYKDc3NzUvXt34/InAOZ5VjeHReZkb2+vefPmGVff5M6dW7169dLGjRtVq1atRO2zZ8/+1FN6ODk5ydPT84meU6JECVWsWFGhoaEqUKCAqlSporNnz+p///ufnJycjEtrDx06JEmKiorSxIkTdfPmTc2aNUvt27fXkiVL5O3trS+//FI3b97U4sWLVbhwYUkPLs17+eWXNWXKFE2dOvWRtTwqzJYenFxK6sSyq6srN1VCppSW/UuCPXv2qFWrVpKksmXLqkOHDil63uzZszVp0iRJUosWLVStWrVEbX7++Wdjjto6dero1VdflfQg6J4wYYJq1qypCRMmGO2LFy+ud955Rxs2bFCdOnWSfN2EmzL9u+9wdXU11v/zzz+SpAkTJsjX11eTJk3S9evXNWnSJLVv317Lli175ChwIKNIqz4lYbBIcv+n//tmao973sOf54R2CcuS23ZKjyk8PDyeal/+XdMbb7yhzz//XLNmzdKbb76pe/fuafLkybpz5w79CzKlzNTfPOzVV1/VqVOn5OzsrGnTphnThCT8rZVwDyNHR0ctW7ZMwcHBiomJSTSK/PDhwwoLC9OoUaOYgz8dSBd3XJs+fbpWrlypUaNGadOmTcbdSz/44APFx8crJCTkP22/T58+VpdB7N6925iTr3jx4po3b5527dqlDRs2GHMNAkh78fHxxmMCbfwXQUFBxoFawveOjo7avn17ku0tFotiY2OT/Xr4d/NZmTp1qipVqqTevXurUqVKevvtt9WyZUu5u7sbl9+3bdtWX3zxhcaNG6fAwEA1aNDAmGv2888/lyT99ddf8vHxUf78+Y167e3tVatWLW3evFmSFBcXZ7U/cXFxKa7z33cUfxifU2RGZvQvhQoV0oIFCzR69GhdvXpVrVq1UlRU1GOfV7duXS1cuFDvv/++li1bZnXD2QS+vr5auHCh/ve//2nXrl3q3LmzLBaLTpw4oUuXLikoKMiq3sqVKyt79uzatGmTJCXaH4vF8th9sre3N0ZH5smTR9OmTVONGjXUtGlTTZkyRadPn+YKEGQaadWnPO5zmdz/6Sn5PCfU9bhtP6tjipTW1KdPH3Xp0kVTp05V1apV9dJLL8nV1VUvvvii1VRHQGaRmfqbhw0fPlxz5sxR1apV1b17d23cuFGSVLlyZX3++ef68ssvVbduXdWsWVMTJ05UtWrVNHXq1ESvs2jRIj333HNq2rTpI+tE2kgXpxR++OEH9e3bV2+88YbVH9k+Pj7q27ev1agQABnXzZs3jccP/0cLPKn8+fNbfW9vb69cuXLp1q1bSbbftm3bU88P97Ty5Mmj6dOn6/bt27py5Yo8PDxkb2+v4cOHG9PveHp6Jhr9nSNHDlWoUMGYjuTmzZs6ffq0cVPVf4uKilLXrl21bds2Y1lAQIAWLFiQojqzZ8+ua9euJVoeGRnJ5xSZkhn9S/78+ZU/f34FBASoaNGiatu2rVavXp3s5bAJXnjhBUkP/mCLjY1VaGio3n//fasbMXl4eMjDw8MIqoODg7Vjxw7jj8YRI0ZY3bw2wZUrV3Tu3Dm9+OKLVstHjx5tXOL776s4Hh65nTD6qlatWsZrSVL58uXl5uamgwcPPnLfgIwirfqUhM9cUldXRUREJPt/esLyR32eE/5NbtsJ+/isjilSWpOjo6MGDBigPn366OzZs8qXL59y5MihNm3aWE11CGQWmam/eVjCFWpVqlRR48aNNXv2bNWsWVPPPfdconsaSVLt2rW1efNmXbt2TXnz5pX0YIDQmjVr9PLLL1vNCw7zpItA+9q1a8ne8Cp//vy6fft2GlcEIK08PAJrzZo1xuN9+/YZ8wk/qSZNmvznumDbEi5lTxAXF6d//vkn2XneypQpo++//z7Z7T18M5Fn5eeff1bJkiXl7e2tHDlySJL279+v+Ph442aOq1atUo4cOaxuniQ9mAcuYV/c3NwUEBCggQMHJvk6Tk5OGjFihNVBX1KX6CWnRIkSCgsLU3x8vFXodPr06cfOzw1kRGnVv0RGRmrt2rXy9fU15o6UZPQPV65cSfJ558+f1+bNm/Xqq69a3VAy4aTXlStX5OzsrD///NP4Yy6pbSeE4QMHDlRAQECi18mZM6dxA8qHFSlSxDh2P336tNXNaU+fPi3pwdzguXLlkp2dXZLz2MbFxRmXAwMZXVr1Ka6ursqfP7/xOUxw/fp1RUZGJvt/uoeHhxwcHBI9L+E4PeF5JUqUSHTsHhcXp3Pnzumll14y2jyLY4qU1rR161bFxMSoZs2aKlWqlKQHV5UcOXJEr7/+eopfD8goMlN/s2XLFkVHR1tNKezo6CgvLy8dOXJEkrRjxw6dPXs2UX8QHR0tBwcHqxNfe/fu1T///KNGjRol/WYgzaWLKUeKFSumDRs2JLlu27ZtVgfxADKuhBEbDg4ORsAHPI0///zTKiT5448/FBsbq6pVqybZPnv27CpXrlyyX6lxB+sZM2Zo1qxZVsvmz58vNzc3BQYGSpK++eYbDR8+3GpfLl++rF27dhltAgICdPLkSZUoUcKq5uXLl+v777+Xg4ODPD09rdY9yZzfNWrUUGRkpHFpnvTgRpQ7duxQ9erV/8tbANiktOpfHB0dNXToUM2ZM8dqecJUH8nNf3/hwgUNHTrU6iRxwvOyZMmiEiVK6N69ewoODk70R+rD2/b09NRzzz2nc+fOWdWbP39+TZw4UQcPHjRuQPnwV65cuVSsWDEVKVJEq1evttr+b7/9puLFi6tIkSJydXVV5cqV9dtvv1m9n3/99Zfu3r1rTA8IZHRpecxSvXp1rV+/3ur1Vq9eLQcHB1WpUiXJ52TNmlWVKlXSmjVrrC6/X716tdzc3OTr62tse/v27bpx44bRJiwsTHfv3jWOF57VMUVKa1q9erX+97//6f79+0abH374Qbdv31a9evVS/HpARpGZ+pvly5dr4MCBVnNqR0REaPfu3cYx1JYtWzRo0CCrm1TGx8dr9erV8vf3txqJvXfvXjk6Oho1wHzpYoT222+/rWHDhun+/fuqW7eu7OzsdPr0aW3dulVz585Ncr4/ABlPwn8kRYoUsRq1ATypixcvqkePHmrfvr0uXryoSZMmqWbNmkYInNZiYmJ08OBBFShQwLjJcbt27TR8+HA9//zz8vf316pVq/TTTz/po48+Mi6369mzpzp06KCePXuqffv2unXrlqZNmyZ3d3d17NhRkvTOO+9o+fLleuedd9SxY0flypVLq1at0rfffqvBgwf/59orV66sgIAAffDBB/rggw/k7u6u0NBQubm56a233vrP2wdsTVr1L1mzZlXXrl0VGhqq3LlzKzAwUOHh4Zo2bZqqVatm3LwpIiJCx44dk4eHh3Lnzq2KFSuqWrVqGjlypCIiIuTh4aF169Zp0aJF6tOnj3LmzKmcOXPqjTfe0GeffSZHR0eVLl1aO3bsMG6cljCS8f3339ewYcPk4OCgunXr6vbt25o+fbouX76c7DRHCXr16qXBgwfL3d1dQUFB+uOPP/TLL79Y3RunX79+ateunbp06aKOHTvq+vXrmjBhgvz8/BQUFPRM308gvUrLY5bOnTvr559/VufOndWhQwedOnVKkyZNUosWLYypiJI6ZunRo4c6dOigd999V2+88YZ2796tOXPmqH///sZc1K1bt9bChQvVoUMH9e7dWzdv3tT48eNVq1YtVahQQdKzPaZISU2tWrXSt99+q0GDBunNN9/U4cOHNXHiRL388stJXnkCZHSZqb/p3Lmzfv31V/Xo0UOdOnVSTEyMZs+ercjISPXp00fSgz7im2++Uffu3fXuu+/KxcVFX3/9tY4cOaJFixZZ7c+RI0dUpEgRq6vfYC47y6NmU09DM2fO1IwZMxQdHW2cicmSJYs6d+6sd9991+Tqnk5cXJz27Nkj6UHHkU7eaiBdslgsatOmjSIiIvTiiy/+p899SqYcefjzWb58eTk4ODz166U1W649LQQFBcnf3185cuTQsmXLlC1bNr3yyit6//33U/0S9oT5ZEePHq1mzZolWt67d2/jAEqSvvzySy1cuFBXr15ViRIl1KlTJ73yyitW2/zrr78UGhqq8PBw2dvbq2bNmhowYIDVHLhnzpzRxIkT9ddffyk6OlrFixdXu3bt9Oabbz5R/V5eXolqlKRbt25pzJgx+v333xUfH68KFSpo8ODBTzTSOzOx1c+ordadltK6f7FYLPrmm2+0aNEinTlzRrlz59Yrr7yiPn36GH9Qbd26Ve3bt7fqdyIiIvTZZ59p9erVunLliooXL663335bzZs3N7YdExOjOXPmaNmyZTp//rwKFiyoFi1aqFOnTlYnlVetWqUvvvhCR48eVbZs2VShQgW99957yY4Qf9g333yjuXPn6uLFiypatKi6du2aaN7vXbt2KSQkRPv27ZOzs7Pq1aun4OBgrtRKgi1/Rm259tRkxjHLjh07NG7cOB06dEi5cuVS06ZN1bdvX2XJkkVS8scsa9as0dSpU3Xy5Enlz59fbdq0MU6uJzhy5Ig+/fRT7d69W66urqpXr54GDhxozHsrPfkxRWhoqKZNm6bw8PBE61JS06ZNmzRx4kQdP35cefLk0euvv65u3boZ+wvb/nzacu1pLTP2NwcPHtTEiRO1f/9+xcbGKiAgQP369TOmVZMeTHk0ceJE7dixQ5GRkSpXrpzee++9RFeKdenSRbdu3dK3336bGm9VhpWan9F0E2hLDw6+d+3apVu3bilHjhzy8/OTu7u72WU9NQJtIOVOnTqlvn37SpK6deumxo0bP/W2CLQzt6CgIAUEBDzzmzgCKWWrn1FbrTst0b/ATLb8GbXl2lMTfQrSA1v+fNpy7WmN/gZmSM3PaLqYciRB9uzZjcsnAWQuW7ZsMR5XrFjRxEoAAAAAAACQXpkWaAcFBcnOzi5Fbe3s7PT777+nckUAzBIXF2d8xkuUKGHMnwUAAAAAAAA8zLRAOyAgIMWBNoCMbfPmzbpy5YokqWHDhiZXA1u3du1as0sAkEHRvwB4luhTAKQV+htkNKYF2szbA0CSoqOj9eWXX0qS3NzcFBQUZHJFAAAAAAAASK/SzRza0dHRCg8PV0xMjHHzxPj4eEVFRWnHjh0aMGCAyRUCSA0LFy40Rme3adNGWbNmNbkiAAAAAAAApFfpItDeunWr3n33Xd26dSvJ9a6urgTaQAa0adMmLV++XJJUqlQpNWjQwOSKAAAAAAAAkJ6li0A7JCREuXLl0siRI7VixQrZ29urWbNm+vPPP7V48WLNnj3b7BIBPGN79+5VSEiIpAcnrT744AM5ODiYXBUAAAAAAADSs3QRaIeHh2vUqFGqX7++7ty5o2+++Ua1a9dW7dq1df/+fc2YMUOzZs0yu0wAz8ju3bv1ySefKCYmRvb29urXr58KFixodlkAAAAAAABI5+zNLkB6MFd2/vz5JUnFihXT0aNHjXUNGjTQwYMHzSoNwDNksVj0448/asSIEUaYPWDAAFWuXNns0gAAAAAAAGAD0kWg7eHhofDwcElSiRIlFBUVpRMnTkiSYmNjFRkZaWZ5AJ6B27dva+zYsZo3b57i4+OVJUsWffDBB6pRo4bZpQEAAAAAAMBGpIspR5o0aaIJEybIYrGobdu2Klu2rEaOHKl27drp888/V6lSpcwuEcBTslgsWr9+vebMmaPbt29LkvLly6dBgwbx2QYAAAAAAMATSReBdufOnfXPP/9o7969atu2rYYPH64uXbqoZ8+eyp49u2bMmGF2iQCewvHjxzV//nzt3bvXWBYQEKC+ffsqR44cJlYGAAAAAAAAW5QuAm17e3sFBwcb33t4eGjatGlycnKSp6ensmfPbmJ1AJ7UuXPntGjRIm3atMlY5u7urq5du6p69eqys7MzsToAAAAAAADYKlMD7X379mn69Olq2LChXnvtNUnSwoULNX78eMXExChr1qzq06ePOnXqZGaZAFLoyJEjWr58uTZt2qT4+HhJkoODgxo0aKC2bdtycgoAAAAAAAD/iWmB9uHDh9WuXTu5u7urWbNmkqT9+/frk08+UcmSJfXee+/pxIkTCgkJUbFixVSvXj2zSgXwCHFxcdq2bZuWL1+ugwcPGsvt7OxUu3ZttW7dWgUKFDCxQgAAAAAAAGQUpgXaM2fOlLe3t+bPny8XFxdJ0ldffSVJmjBhgry9vSVJ165d04IFCwi0gXTmwoUL+v3337V27VrduHHDWO7g4KCaNWuqWbNmKl68uHkFAgAAAAAAIMMxLdDevn27Bg0aZITZkhQWFqaiRYsaYbYk1ahRQz/++KMZJQKZRpMmTVLU7vbt21q6dKnmzp2rjRs3Wq1zd3dX9+7d1bt3bxUuXDg1ygQAAAAAAEAmZ1qgffPmTatpCI4fP65//vkn0UhsFxcXxcTEpHV5AP6/27dva+XKlfr222/166+/Jvo8Vq1aVR06dNBbb73FHNkAAAAAAABIVaYF2u7u7rp+/brx/ZYtW2RnZ6eqVatatTt+/Lhy586d1uUBmdr169f1yy+/aOnSpVq1apWio6Ot1ufPn1/t27dXhw4d5OPjY1KVAAAAAAAAyGxMC7QDAgL07bff6qWXXlJcXJx++OEHZc2aVTVr1jTaxMTEaNGiRapQoYJZZQKZgsViUXh4uFauXKmVK1dq06ZNio+Pt2qTK1cuvf7662rRooWCgoKUJUsWk6oFAAAAAABAZmVaoN2jRw+1bNlS9erVk8Vi0YULF9SrVy+5ublJkn744QctWrRIJ0+e1Lhx48wqE8iw7t69q7///lt79uzR+++/r+PHjydq4+7urtdee00tWrTQiy++KCcnJxMqBQAAAAAAAB4wLdB+/vnn9e2332ru3Lm6fv26unTporfeestYP3nyZDk6Ouqzzz5jSgPgGYiNjdXRo0e1Z88e7d27V+Hh4YqLi0vUrlSpUmrSpImaNGmiGjVqMBIbAAAAAAAA6YZpgbb0IDj79NNPk1z3/fffK2/evLK3t0/jqoCMwWKx6Ny5c9q7d6/27Nmj/fv3KyoqKlE7BwcHVatWzQixvby8ZGdnZ0LFAAAAAAAAwKOZGmg/Sv78+c0uAbAp8fHxOnfunP7++2/j6+Ebrz7Mw8NDfn5+Kl++vMqUKaOWLVumcbUAAAAAAADAk0u3gTaAR4uLi9OJEyd04MABHTx4UAcPHtSdO3eSbJs7d24jwPbz81Pu3LnTuFoAAAAAAADgv8sUgfa8efMUHh6uMWPGJFp37949DRkyRBs2bJCrq6vee+89vf766yZUCTxadHS0jh49agTYhw8f1r1795Js6+bmptKlS8vX11d+fn4qWrQo04gAAAAAAADA5mXoQDsuLk5z5sxRSEiImjZtmmSbSZMmKSoqShs3btSxY8fUuXNn+fj4yNvbO42rBf6PxWLRlStXdPjwYYWHh+vw4cM6efJkkjdxlKQ8efKoTJkyKl26tMqUKaMiRYow/zwAAAAAAAAynAwdaAcHB+vOnTtq3ry5YmJikmzz008/aebMmXJxcVG5cuX0yiuvaMWKFQTaSFPR0dE6duyYEWCHh4frn3/+SbZ94cKFrQLsfPnyMQIbAAAAAAAAGV6GDrQHDhyofPnyKTQ0VOfPn0+0/tatW7p+/bo8PT2NZSVKlFBYWFhalolMxmKx6PLly8bI6/Dw8EeOvnZ0dFSpUqXk5eUlb29vlS5dWrly5UrjqgEAAAAAAADzZehAO1++fI9cHxUVJUlycXExljk7Oyc7LzHwNBLmvk4YeX348GHdvHkz2fZ58uSRt7e3vLy85OXlpZIlSypLlixpVzAAAAAAAACQTmXoQPtxnJ2dJT24MWS2bNkSPQaelMVi0aVLl4zw+nGjr7NkyaKSJUsaAba3t7eee+65NK4aAAAAAAAAsA2ZOtB2d3dX7ty5derUKZUuXVqSdPLkSZUoUcLkymAr7t69a4y+PnLkiMLDw3Xr1q1k2+fNm9dq9LWnpyejrwEAAAAAAIAUytSBtiQ1btxYU6dO1YQJE3Tq1Cn99NNPmj9/vtllIR2Kj4/X+fPnrUZfnzlzRvHx8Um2z5Ili0qVKmUVYDP6GgAAAAAAAHh6mTLQ9vf31+zZs1WpUiX169dPI0eO1IsvvigXFxcNHjxYPj4+ZpeIdODOnTvGqOuEEdiRkZHJti9QoIARXHt5eal48eKMvgYAAAAAAACeoUwRaPfp08fq+927dxuPs2XLptGjR6d1SUhn4uLidObMGeOmjeHh4Tp//nyy7Z2dnfX8888b4fULL7ygXLlypWHFAAAAAAAAQOaTKQJt4N/u3r2r8PBwHTp0SIcOHVJ4eLju3buXbPsiRYpYjb728PCQg4NDGlYMAAAAAAAAgEAbT6xJkyZml/DEzp8/r02bNiksLExhYWHau3dvsnNfu7u7KzAwUFWrVlWVKlUUEBDA6GsAAAAAAAAgHSDQRoYTHx+vQ4cOGeF1WFiYTp06lWz70qVLq3r16qpWrZqqVKmiF154Qfb29mlXMAAAAAAAAIAUIdCGzbNYLDp8+LDWrVundevWaf369bp27VqSbZ2cnBQQEKDq1aurRo0aqlatmnLnzp3GFQMAAAAAAAB4GgTasDkWi0XHjx83Aux169bp0qVLSbbNnTu3EV5Xr15dFStWlLOzcxpXDAAAAAAAAOBZINCGTbhw4YJ+++03rV27VuvWrdO5c+eSbJcvXz7VrVtXdevWVa1ateTl5cX0IQAAAAAAAEAGQaCNdCk6OlqbNm3Sr7/+qtWrV2vfvn1JtsudO7fq1KljhNilS5eWnZ1dGlcLAAAAAAAAIC0QaCPduHDhglasWKFVq1Zp7dq1ioyMTNQmZ86cqlWrlhFg+/r6MgIbAAAAAAAAyCQItGEai8Wiv//+W8uXL9fy5cu1ffv2RG3s7OwUGBiohg0bqmHDhqpUqZIcHBxMqBYAAAAAAACA2Qi0kaYsFot27typJUuWaOnSpTpx4kSiNgUKFDAC7Hr16um5554zoVIAAAAAAAAA6Q2BNlKdxWLR/v37tWTJEi1ZskTHjx9P1KZMmTJq2rSpmjZtqkqVKjGNCAAAAAAAAIBECLSRai5duqSvvvpKX375pQ4ePGi1zs7OTjVq1NBrr72mpk2bqmTJkiZVCQAAAAAAAMBWEGjjmbp//75WrVqlOXPmaNWqVYqLi7NaHxgYqFatWql58+YqXLiwSVUCAAAAAAAAsEUE2ngmLl26pJkzZ+rzzz/XpUuXrNZ5e3vr7bffVsuWLVWiRAmTKgQAAAAAAABg6wi08Z/s2LFDU6ZM0ZIlS3T//n1juZubm1q1aqWOHTsqMDBQdnZ2JlYJAAAAAAAAICMg0MYTs1gs2rBhg0aNGqU//vjDal2FChXUp08fNW/eXK6uriZVCAAAAAAAACAjItBGilksFu3Zs0fjxo1TWFiYsdzBwUFvvvmm+vbtq6pVqzIaGwAAAAAAAECqINBGihw7dkzz58/Xvn37jGUuLi7q1q2b+vfvryJFiphYHQAAAAAAAIDMgEAbj3TlyhV99dVX+vPPP41l2bNnV8+ePdWvXz/lz5/fxOoAAAAAAAAAZCYE2kjS/fv3tWzZMi1ZskQxMTGSJEdHRzVq1Ehz585Vnjx5TK4QAAAAAAAAQGZDoI1EDhw4oOnTp+vcuXPGspo1a6pdu3YqUKAAYTYAAAAAAAAAUxBowxAdHa0FCxZo5cqVslgskiQPDw91795dZcuWNbk6AAAAAAAAAJkdgTYkSYcPH9YXX3yhI0eOSHpww8cRI0bovffeU5YsWUyuDgAAAAAAAAAItDO9uLg4LV68WN9//73i4+MlSVWqVNGXX36pF154weTqAAAAAAAAAOD/EGhnYtevX9f48eN18OBBSZKTk5NGjhyp/v37y8HBweTqAAAAAAAAAMAagXYmtXPnToWEhOj27duSHsyV/fPPPzNXNgAAAAAAAIB0i0A7k4mPj9fixYu1ZMkSY1n9+vXVtWtXwmwAAAAAAAAA6RqBdiYSGRmpSZMmafv27ZIkZ2dn9ezZU3Xq1DG3MAAAAAAAAABIAQLtTOLs2bP69NNPdf78eUlS4cKF9eGHH6po0aImVwYAAAAAAAAAKUOgnQls2bJFISEhioqKkiQFBATo/fffl6urq8mVAQAAAAAAAEDKZfhAe+/evRo+fLhOnTql0qVLa8yYMfLw8LBqExERocqVK8vZ2dlY1rdvX3Xo0CGty32m4uPj9c033+ibb74xlrVq1UqtWrWSvb29iZUBAAAAAAAAwJPL0IF2dHS0evXqpUGDBumll17SrFmz9N5772np0qVW7cLDw/X8889rxYoVJlX67EVGRiokJETbtm2TJLm4uOj9999XlSpVTK4MAAAAAAAAAJ5Ohh6mu2XLFrm7u+uVV16Rk5OTevToobNnz+rYsWNW7Q4fPixvb2+Tqnz2zp07pwEDBhhhduHChTVhwgTCbAAAAAAAAAA2LUMH2idPnpSnp6fxvYODg4oWLaoTJ05YtQsPD9epU6fUoEED1axZU2PGjFFMTExal/tMbN26Vf379zdu/li5cmVNmDCBmz8CAAAAAAAAsHkZOtC+e/eu1bzY0oOpNxJujpggW7ZsCggI0Pfff68lS5Zo+/btmjlzZlqW+p/Fx8fr66+/1ieffGLsX8uWLTVkyBBu/ggAAAAAAAAgQ8jQc2i7uLjo3r17VsuioqISBbyDBg0yHru5ualr1676/PPP1adPnzSp87+6e/euQkJCtHXrVknMlw0AAAAAAAAgY8rQI7Q9PT116tQp4/u4uDidOXNGJUqUsGo3depUnT171vg+JiZGWbNmTasy/5NLly4pODjYCLMLFSqk8ePHE2YDAAAAAAAAyHAydKAdGBio69eva9myZYqJidGMGTPk4eGhkiVLWrU7ePCgJk2apKioKJ0/f16zZs3Sq6++alLVKXfgwAENGDBAp0+fliRVqFBBEyZMkIeHh8mVAQAAAAAAAMCzl6EDbWdnZ82cOVMLFixQYGCgNm/erMmTJ0uSGjdurBUrVkiSRo0apdjYWNWuXVtvvvmm6tWrp7feesvEyh/vt99+07Bhw3T79m1JUtOmTfW///1P2bNnN7kyAAAAAAAAAEgdGXoObUkqW7asfvjhh0TLf/75Z+Nxnjx5FBoampZlPbW4uDjNnTtXK1eulCQ5OjqqZ8+eqlevnsmVAQAAAAAAAEDqyvCBdkYSGRmpcePGaffu3ZKknDlzavDgwSpdurTJlQEAAAAAAABA6iPQtiGLFi0ywuxixYpp6NChyp8/v8lVAQAAAAAAAEDaINBOI40aNZKDg8N/2saJEyf0888/64033tC8efOYLxsAAAAAAABAppKhbwqZ0bz77ru6c+eOvvvuO8JsAAAAAAAAAJkOgbaNcXV1NbsEAAAAAAAAADAFgTYAAAAAAAAAwCYQaAMAAAAAAAAAbAKBNgAAAAAAAADAJhBoAwAAAAAAAABsgqPZBWRkFovFeBwXF2diJQD+7eHP5MOfVVtA3wKkb7bav9C3AOmbrfYtEv0LkJ7RtwBILanZvxBop6L4+Hjj8f79+02sBMCjPPxZtQX0LYDtsKX+hb4FsB221LdI9C+AraBvAZBannX/wpQjAAAAAAAAAACbYGextWtKbEh8fLxiY2MlSfb29rKzszO5IgAJLBaLcYbQ0dFR9va2c36PvgVI32y1f6FvAdI3W+1bJPoXID2jbwGQWlKzfyHQBgAAAAAAAADYBNs59QYAAAAAAAAAyNQItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATHM0uICOLj49XbGysJMne3l52dnYmVwQggcViUXx8vCTJ0dFR9va2c36PvgVI32y5fwGA1MCxC5B+2fJxC30LkL6lZv9CoJ2KYmNjtX//frPLAPAY5cqVk5OTk9llpBh9C2A7bK1/AYDUwLELYBts7biFvgWwHc+6fyHQBgAAgCGzjG6KiIgwu4Q04+LiYnYJeIZsafQkAABAaiDQTkUPH2yWK1dODg4OJlYD4GFxcXHG2Xxb+8OQvgVI32y5fwGA1MCxC5B+2fJxC30LkL6lZv9CoJ2KHh7h5ODgQOcKpFO2NhqRvgWwHbbWvwBAauDYBbANtnbcQt8C2I5n3b/Y1uk3AAAAAAAAAECmRaANAAAAAAAAALAJBNoAAAAAAAAAAJtAoA0AAAAAAAAAsAkE2gAAAAAAAAAAm+BodgHIvOLi4kx9fe6ADAAAAAAAANgWAm2YIi4uTqtWrTK1hpdffplQGwAAAAAAALAhBNow1bZt256ofUxMjMaNGydJGjhwoJycnJ7qdQMCAp7qeUB6s3XrVrNLADINBwcHBQYGml0GAAAAAGRqBNownb+/v+ztUzad+71796ye5+zs/ESvFR8fr927dz/Rc4D07MaNG7JYLGaXAWQKzz33nNklAAAAAECmR6AN09nb26d46o+H2zk4ODBlCAAAAAAAAJCJpGxYLAAAAAAAAAAAJiPQBgAAAAAAAADYBAJtAAAAAAAAAIBNINAGAAAAAAAAANgEAm0AAAAAAAAAgE0g0AYAAAAAAAAA2AQCbQAAAAAAAACATSDQBgAAAAAAAADYBAJtAAAAAAAAAIBNINAGAAAAAAAAANgEAm0AAAAAAAAAgE0g0AYAAAAAAAAA2AQCbQAAAAAAAACATSDQBgAAAAAAAADYBAJtAAAAAAAAAIBNINAGAAAAAAAAANgEAu0MxmKxyGKxmF0GngI/OwAAAAAAAODRCLQzEIvFoho1aqhmzZoEozaGnx0AAAAAAADweI5mF4Bn5+7du9q8ebPx2NXV1eSKkFL87AAAAAAAAIDHY4Q2AAAAAAAAAMAmEGgDAAAAAAAAAGwCgTYAAAAAAAAAwCYQaAMAAAAAAAAAbAKBNgAAAAAAAADAJhBoAwAAAAAAAABsAoE2AAAAAAAAAMAmEGgDAAAAAAAAAGwCgTYAAAAAAAAAwCYQaAMAAAAAAAAAbAKBNgAAAAAAAADAJhBoAwAAAAAAAABsAoE2AAAAAAAAAMAmEGgDAAAAAAAAAGwCgTYAAADSnI+Pj6KiolSsWLEULc8ITpw4oSpVqujChQtml5Lq5s+fr8GDB5tdRqrLLPsJAACQnhBo26DIyEgdOnRIO3fu1KFDhxQZGWl2SUCa4HcfADIGBwcHzZs3T87OzilanhHExsbqo48+UkxMjNmlpKq4uDjNnj1b48ePN7uUVJVZ9hMAACA9cjS7ADPFx8fL3t62Mv2zZ89q7969slgsxrLjx4/Lz89PuXPnNrEyIHU96ne/aNGiJlYGAHhSgwcPVlhYmAIDA1O0PCOYN2+eypcvrwMHDphdSqoaPHiwbt++rebNmys6OtrsclJNZtlPAACA9ChTBtrjxo1TtWrVVKNGDVksFtnZ2ZldUopERkYagV7evHmVN29eXb16VVevXtXevXsVEBBg1TY9i4uL071790x7/Xv37ikyMlIODg6m1fCw9P7zMtvjfvdz584tV1dXs8sEAKSAr6+vWrZsqcqVK6t///6PXZ4RHDlyRL/99psWLFighQsXml1OqhowYIDy5cunadOm6fz582aXk2oyy34CAACkR5ku0L57967i4uL00Ucf6ZNPPlFgYKDNhNpnzpwxAr0qVapIkkqWLKktW7bo6tWrOnv2rNE2f/78ZpX5RIYOHWrK67Zo0cKU18XTedzv/pkzZ+Tj42NylQCAx8mSJYvmzZunbt26WZ3YTm55RnD//n199NFHGjJkSIacSuXf8uXLZ3YJaSKz7CcAAEB6ZFvzbfxHFotF2bJlU8+ePdW+fXt9+OGH2rJli+zs7KymMUiv7t69K0nKmzev1fKE7zPaH4BAgsf97kdFRaV5TQCAJzds2DCtX79emzdvTtHyjGDWrFmqWLGiypcvb3YpAAAAQIaQqUZoJ4zCnj59ugIDA/Xmm29qyJAh+vTTT21ipHa2bNkkSVevXlXJkiWN5VevXpUkq1E/ly9fTtdTMMTFxWn16tXat2+fKa//7bffqkGDBulqyhFbGVVvhsf97ru4uJhSFwDgybz55psqWLCgOnbsaCzbt2+fLl26pPz58yda3r17dy1evNiMUp+ZP/74Q9euXdPy5cuNZS1bttSHH36oRo0amVgZAAAAYJsyVaAtSRcuXNC5c+fk5+enHj16KDo6Wh9++KERaqfnG0V6eHjo+PHjunr1qrZs2WI1j7CdnZ3VjfFcXV3TfaBt5mW3zs7OcnV1TTeBNh7tcb/7Hh4eZpcIAEiBf08PZbFY5Ovrq9OnT6douS1aunSp1fcVKlTQkiVLVKhQIZMqAgAAAGxb+kxun6G4uDir7wsVKqQKFSpowoQJunPnjnr16qXXXntNw4YN06ZNm9JtmC09CKn9/PxkZ2enq1ev6uDBg0ag5+fnl64DbOC/4HcfAAAAAAAAUgYfoR0XFycHBwfFx8frp59+0vPPPy8fHx916tRJBw8e1A8//KB33nlH7dq107179zR+/HhVqFBBzs7O6XbqkaJFiyp37tw6c+aMoqKi5OLiIg8PD7m6uioyMtLs8oBU86jffQCAbUrueCu9Hoc9C7t27TK7hDTRu3dvs0tIE5llPwEAANKTDBtox8fHG2H2kCFDtHXrVpUpU0YuLi768MMP5e3trePHj0uS3N3d1bVrV3Xq1Mkm5uJ1dXVNdMkukBnwuw8AAAAAAJC5pd/5Nf4je3t7xcfHq3PnzipUqJCWLFmizp076+rVqxo8eLBu3LihH374QV9//bUkKWfOnMqdO7fJVQMAAAAAAAAAkpPhAu07d+7o2rVrioyM1Pz583X16lW99tpryps3r/z8/DRv3jy98sorKlCggOzs7LRz505FR0ebXTYAAAAAAAAA4DEy1JQjI0aM0OXLl3X27Fm1a9dOt2/flsVi0dy5c9WnTx9jBHbjxo0lSaVLl1bBggWVNWtWM8sGAAAAAAAAAKRAhgm0e/TooevXr+uTTz7RqVOnVL9+fd25c0eXL1+WJC1btkxvvPGGcubMqfj4eNnb26ty5comVw0AAAAAAAAASKkMEWiHhobq9u3b+vbbbyVJzz//vM6ePauuXbvq6tWrKleunOzt7fXjjz/q9ddfV86cOU2uGAAAAAAAAADwpGw+0LZYLDp37pzat29vLLtw4YJat26tV155RWXLllVISIicnZ118eJFOTk56a233pKdnZ2JVQMAAAAAAAAAnpTN3xQyOjpahw8fVkREhLFs7969ateunYKDg1W7dm25u7vLx8dHtWvXVt26dQmzAQAAAAAAAMAG2fwIbXt7e+XIkUPHjx83ljVq1Mh4bLFYlCNHDlWtWpU5swEAAAAAAADAhtn8CG0nJyd16NBBixcv1k8//ZRo/dKlS3Xt2jV5eHiYUB0AAAAAAAAA4Fmx+RHaklSjRg116NBBI0eO1JUrV1S/fn1FRERo8+bNmjlzpubPn6/8+fObXSYAAAAAAAAA4D/IEIG2k5OTunTpooIFC2ry5Mn69ttv5e7urjx58mjBggXy8vIyu0QAAAAAAAAAwH+UIQJtSXJxcVHz5s2N0dlubm7KmjWrnJ2dzS4NAAAAAAAAAPAMZJhAO4G7u7vc3d3NLgMAAAAAAAAA8IzZ/E0hAQAAAAAAAACZQ4YboZ2ZZcuWTdWrVzcew3bwswMAAAAAAAAej0A7A7Gzs9PGjRuNx7Ad/OwAAAAAAACAxyPQzmAIQ20XPzsAAAAAAADg0ZhDGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBMItAEAAAAAAAAANoFAGwAAAAAAAABgEwi0AQAAAAAAAAA2gUAbAAAAAAAAAGATCLQBAAAAAAAAADaBQBsAAAAAAAAAYBNSJdAeNmyY9u7dmxqbBgAAAAAAJrNYLGaX8Myl1j5lxPcKeJb4jCQvpe9NZuu/UiXQ3rJli1q1aqVGjRpp9uzZunLlSmq8DAAAAAAA/1m7du3k5eWlVq1aJdvm/fffl5eXlwYNGpSGlT3auHHj5OPjozt37lgtv3Hjhry9veXt7a2rV68mue6zzz6TJHl5eSk0NPSRr9OuXTu1a9fO+P67777T2LFjn9Fe/Hf/ru/fgoKCHvlzi4mJ0aeffqqVK1c+89qmT5+uOXPmPPPt4r8bPHiwvLy8FBYWluT6jRs3ysvLSxMmTEjTupYuXSovLy9t3br1P29r5MiRCgkJMb7/+++/1aVLF1WpUkWBgYHq2LGj/v77b6vnxMbGavLkyapdu7b8/PzUunXrRINWjx8/rubNm6tChQrq3r27rl27ZrX+jz/+UKNGjRQXF/fYGo8ePaq33nrrse0S3pdz5849tm1683AfFBMTo4YNG2rPnj2Pfd4ff/yh4ODgx7bbuXOnunbt+l/LTCSlPxszpEqg/dtvv2nhwoWqVKmSZs2apbp166pr16769ddfdf/+/dR4SQAAAAAAnpq9vb327NmjS5cuJVp39+5drVu3zoSqHq1q1aqKj49PFIxs3LhR2bJlk6OjY6KwbufOnbJYLKpRo0aKX2f48OEaPny48f2MGTN08+bN/1J6unLlyhV9+eWXio2NfebbnjJliqKiop75dvHfDR48WPny5dOwYcN09+5dq3UREREaNmyYvLy81Ldv3zSty87Ozurfp/XXX39pzZo16t69uyTp9OnTatu2re7du6dPPvlEo0ePVkxMjFq3bq0TJ04YzxszZozmz5+vzp07KyQkRA4ODnrnnXd0+vRpo83AgQP13HPPKTQ0VP/8848+/fRTY11cXJwmTpyofv36ycHB4bF1/vrrr9q9e/dj29WpU0dLlixRvnz5nuRtSHecnJw0YMAABQcH6969e49sO3/+fF28ePGx2/zuu+90/PjxZ1WiIaU/GzOk2hzaFStW1MiRIxUWFqaxY8fKyclJgwcPVo0aNTRq1CgdOXIktV4aAAAAAIAnUrp0aWXNmlW//vpronXr1q2Ti4uL8ufPb0JlyatUqZKyZMmiXbt2WS0PCwtThQoVVL58eW3cuNFq3fbt25UjRw6VLVs2xa9TqlQplSpV6pnUDKQXOXLk0IgRI3T+/HmrUcySNHHiRF29elXjxo2Tk5NTmtaVN29eSfrP/c3o0aP1zjvvyMXFRZK0YMECubi4aObMmXrxxRcVFBSkWbNmycXFRQsXLpQkXbx4UYsXL9bAgQPVrl07BQUFac6cOXJ3d9fs2bMlSXfu3NGBAwfUu3dvVa9eXZ07d9bmzZuN1126dKmyZ8+u+vXr/6f6/y137twqX758mv88UkO9evWUJUsWLV682OxSbFaq3xQya9asqly5sipVqqSSJUvq1q1bWrlypZo2baouXbro8uXLqV0C0rn4+HjFxcWl+CvBkzwn4Ss+Pt7EPQUAAACQXmXLlk21a9dOMtBetWqVGjRoIEdHR6vlN27c0IgRI1S3bl2VLVtWAQEB6tWrl9Ul8e3atdOQIUM0a9Ys1alTR+XKlVOrVq20b98+o01oaKjq16+v9evXq0mTJipbtqwaNGigZcuWPbJmFxcX+fv7WwXaFotFmzZtUrVq1VS1alVt2rTJ6u+gHTt2qEqVKlYjJyMiIjRkyBAFBATI399fffv2tZpC4OEpPYKCgnT+/Hn9+OOPxuX/S5cuVenSpbV37161bNlS5cqVU926dRNNtREdHa1x48apdu3aKlu2rJo0aaJVq1YZ68eOHStfX99EU6hMnz5dFStWTJWRzufOndOLL74o6cGI3aCgIGPdjh071LZtW/n5+SkgIEDBwcG6ceOGsT4+Pl4hISEKCgpS2bJlFRQUpIkTJxpXpnt5eUmSpk2bZjxG+hIUFKQmTZpo4cKFxrQaO3fu1OLFi9W3b195e3sb7f49bU1SU2AcOXJE3bp1U4UKFVShQgX16tVLZ8+eNdZv3bpVXl5e+uuvv9SxY0f5+fmpevXqGj9+vJF3PP/888qWLZs8PDwkSQcOHNDbb7+tihUryt/fX++8885jp6tYv369jhw5osaNGxvLPD091bFjR2XLls1Yli1bNhUoUEBnzpyR9GBUd2xsrFUY7eTkpDp16mjDhg2S/m/kuLOzsyQpS5YsRh8TFRWlqVOnasCAAY+sL0FoaKimTZsmyXr6Iy8vL02bNk3NmjWTr6+vpk2bluj9HjRokDp16qQlS5aoXr168vX1/X/s3Xd4FNX/9vF7syEk2RBCR0oUIiX0XkMRpatIFUFAekd6QBEEBZGOgDQpAkqRqoLwFZUmvYsSkSJVek0hIbv7/MGT/RESIJANm0ner+vycnd2Zs5nthw29545o+bNm+vUqVP67bff9MYbb6h48eJq2rSpjh496mjzWbeTntwnSFJISIjatm2rkiVL6pVXXtH3338f77G/8cYbmjdvnqKiouJ9vFWrVtq9e7d279792CloBg0apFWrVun8+fMqUKCAVq5cKenJ/a30+PfWo16b5ML9yas8m/DwcG3YsEFr1qzR7t275e3trbp16+qjjz5S8eLFdejQIfXp00fvv/++lixZklRlwACe5vSFBz/oBw4cSBG/zAGJkTFjRleXAKQaCTllEgBgbPXq1VPv3r118eJFZc+eXdL9sHfLli2aN2+etmzZ4ljXbrerc+fOunXrlvr376/MmTPr77//1qRJkzRs2LBYYe6GDRsUEBCgIUOGyG636/PPP1fPnj3166+/Ov59uXLlikaMGKGuXbsqZ86cmjNnjoKDg1W0aFEFBAQ8suYKFSroq6++UnR0tNzd3fXXX3/p2rVrCgoK0t27d/XFF1/oyJEjKlasmEJDQxUSEqJmzZrF2seCBQv0xhtvaPLkyTpx4oRGjx4tSfriiy/itDd16lR16tRJhQoVUrdu3Ryn/9tsNvXu3VvvvfeeevfureXLl2vMmDHKnz+/qlSpIrvdru7du2v//v3q1auXAgIC9PPPP6tPnz6KiorSW2+9pSZNmmju3Llav369mjZt6mhzzZo1qlevnmOkqTNlzZpVU6dOVY8ePdS1a1fVqlVL0v2R7G3btlWFChU0adIk3bp1S5MnT1br1q21fPlyeXp6avbs2Vq8eLGCg4OVO3duHTp0SBMnTlSaNGnUq1cvLV26VG+//baaNGkS63iQvAwZMkQ7duzQJ598om+//VYff/yxSpQoofbt2z/Vfk6dOqXmzZsrb968+vzzzxUdHa3p06frnXfe0Zo1a5QpUybHuv3791eLFi3UsWNHbdq0SV999ZVy586t5s2bK1u2bI6cJDQ0VB06dFCFChU0ZcoURUVFafr06Wrfvr02bdqkdOnSxVvL999/rxIlSsQa5d2iRYs4650+fVr//POPKlasKOn+3NgWi8UxSjzGiy++qMuXLyssLEw+Pj56+eWXtXLlSnXp0kXff/+9SpUqJen+FBmBgYEqV65cgp6zpk2b6uLFi1q+fLmWLl3q6HclacaMGerXr5/y5MmjnDlz6o8//oiz/YEDB3T58mUNGjRIkZGR+vjjj9WpUyeZTCb16tVLXl5eGjZsmPr376+1a9cmaruE9AmXLl3Su+++q5deekljx45VaGioxo0bp2vXrsWpvU6dOpowYYJ2794d7xRQw4YN04ABAxy3H3WWTLdu3XT9+nX99ddfmjp1qvz9/RPU3z7pvfW41yY5SJJAu3///vrll18UERGh0qVLa+TIkapTp06sf3yKFy+ut956S/Pnz0+KEmAQCe3kHvQ0c70BKV358uUJ2QAAAJykevXq8vLy0vr16/Xee+9Jkn7++WdlypRJpUuXjrXu5cuX5eXlpeDgYJUpU0bS/e9mZ86c0dKlS2OtGx0drTlz5sjHx0eSFBYWpuDgYB09etQx9UdERIRGjhzpCJZeeuklvfLKK9q8efNjA+2KFSvqiy++UEhIiIoUKaKtW7cqW7Zsyp8/v2w2m/z8/LRlyxYVK1ZM+/fvl9VqVeXKlWPto2jRohozZoxjf4cOHXKMxnxYoUKF5OHh4Tj9P4bdble3bt0cwW3p0qX1888/a9OmTapSpYq2b9+urVu3auLEiapXr54kqUqVKoqIiNC4ceP0+uuvKyAgQCVLltSaNWsc+9m/f7/+/fdfR8jubB4eHgoMDJQk+fv7q1ChQpLuTzmRJ08ezZw50/F9u3jx4qpfv75WrFihli1bavfu3SpSpIgaN24s6f7ft15eXo6QMeb5yZ49e6znCsmLn5+fPv74Y/Xo0UPt2rXTuXPntHr16qf+O2vq1Kny8vLS/PnzHZ/1ihUr6rXXXtNXX30V6+J+TZs2Vffu3R3rbNy4UZs2bYpzYdrjx4/rxo0bat26tSM0zps3r5YuXaqwsLBHBto7d+6MNTo7Pnfv3lVwcLA8PDz07rvvSro/nUhM7Q+yWCyS7gfsFotFn332mXr37q05c+aoSJEimjx5sq5fv665c+dq4cKFOnTokD777DPdvXtX7dq105tvvhlvDdmzZ3cEpQ9/RsqUKaO2bds67scXaIeFhWnSpEmOPnL37t1asmSJ5s+f7+hLT58+rc8//1y3b9+Wr6/vM2+XkD5h/vz5slqtmjVrlmPwWZ48eeL8iCjd/5Egffr02rFjR7w518svv+x4LR7Xf/j7+ytjxozy8PBwrPf7778/sb990nvrca9NcpAkgfbOnTv17rvvqnHjxnrppZceuV6FChU47SaVMpvNjg+VK2sAAAAAgBienp6qUaNGrEB77dq1qlu3bpwLtGXLlk0LFiyQ3W7XuXPndPr0aZ08eVL79++Pcwr5g8FEzLaS4kyh8WBoEBMkxFyszmq1ym63Ox53c3OTm5ubihUrJovFov3796tIkSLatm2bI7B2c3NThQoVtGPHDvXo0UP79u1T7ty5lTt37ljtPhzW58qVS7dv307Qc/agkiVLOm7HhN4x9e/YsUMmk0nVqlWLdfHFGjVq6Pvvv9c///yjwMBANW7cWB999JHOnz+vnDlzatWqVcqTJ0+sfT+Lp7nAXkREhA4dOqT27dvLbrc76s2dO7cCAgL0+++/q2XLlipfvrzGjx+vFi1aqEaNGqpevbojGISx1KxZU/Xq1dO6des0dOhQvfjii0+9j507d6pcuXLy9PR0vGd8fHxUpkyZWHNMS4rzfs6ePXucC1NK96cfyZgxo7p06aI6deqoSpUqqly5smPkbnzCw8N17do15cqV65HrhIaGqnv37vrjjz80efJk5cyZU5Ji9THxcXO7P3NxsWLF9Ouvvyo8PNwxhcmnn36q6tWrK2/evKpRo4Y6d+6sAgUKqFOnTipQoMBT538xPzQ9Tvr06WP94Jc5c2ZJ94PmGH5+fpIUK9B+2u3SpEmToD5h3759KlGiRKwzqYsXL64cOXLEW3+OHDliTVnzJI/6d+BhCelvn+W9lZwkSaC9efPmBIWFzzI6FykHgTIAAACA5KZu3brq0aOHLl68qLRp02rHjh3q3bt3vOt+//33mjBhgv777z/5+fkpMDDQMa/sgx6eKiMmgHj4Gj8PrhezTkx4UbNmTZ0/f97xeMOGDTV69Gi5u7urXLly2r9/vxo1aqSDBw/GmlogKChIw4cP1927d7V37944o7MlxZpTN6btJwVb8Xn42B/cz82bN2W32x0jAR92+fJlBQYGql69eho1apTWrFmj9u3b66efflKnTp0e2663t7du3rz5yMejoqKearqS27dvy2azafbs2Y4L4T0obdq0kqQOHTrIYrFoxYoVGjdunMaOHat8+fJpyJAhqlChQoLbQ/JQpUoVrVu3TtWqVXum7W/evKl169bFmadYijtV5OM+Kw+yWCz65ptvNH36dP30009aunSpPD091aBBAw0ZMiTeaVhj5qB/+HMd47///lPnzp116tQpTZw4Ua+99prjMR8fH4WFhcXZJjQ0VJLijAiPaePMmTNasWKFfvjhB+3bt09hYWFq2bKl3NzcVLZsWf38889PHWg/qv4HxTeaPCHbPu12Ce0Tbt26Fe8PCQ9P4RLDy8vL8dwmxKP+HXhYQvvbp31vJSdJEmibzWZdv35dc+bM0fbt23XlyhV99dVX2rhxowoWLBjrwwIAAAAAQHJRtWpVWSwWrV+/Xt7e3sqVK5djWpAH7d27V8HBwWrVqpXat2/vGHU9ZswY7du3z+l1TZ8+PdbI7wwZMjhuV6hQQV9//bX27Nkjq9XqOGVekipXrqx79+5p9+7dOnz4sNq0aeP02hIiXbp08vb21oIFC+J9PGZErMViUZ06dfTTTz8pf/78Cg8PV4MGDR6778yZM+vYsWPxPhYVFaXr1687RmAmhMVikclk0nvvvRfvtA0x4bibm5tatmypli1b6tq1a9q8ebNmzJihnj176vfff0/2gRCeTsxFG2M8PKI6Xbp0qlSpUqxpMmI8fEHZp5E3b17HRSMPHz6sNWvWaPHixfL391eHDh3irB/TN8R3lsXff/+t9u3bKzIyUnPnzlXZsmXjtBUaGqrr16/HCuFPnz6tnDlzxvuDnSRNnDhRTZo0Ua5cuXTo0CGlS5fO8aOcr6+vrly58szHnxwktE/IkCFDrAvqxnjUD263b99+5Ojt+Dzu34EHJbS/fdr3VnISd1y6E5w9e1Zvvvmmli1bpmzZsunatWuyWq06deqUevXqpU2bNiVFswAAAAAAJIqHh4dee+01bdiwQT/99NMj56E9cOCAbDabevbs6QizrVarY2qBh0dfJ1aBAgVUtGhRx38PjgKsVKmSLly4oPXr16tIkSKxQo4cOXIoT548Wr58uaxWq1NGDsd3ivuTlCtXTuHh4bLb7bGO49ixY5o2bVqs0+KbNGmiY8eO6euvv1alSpViXdjuUfu+cOGCDh48GOexjRs3PvG4Hz572MfHR4UKFdLJkydj1ZovXz5NmTJFu3btkiQ1b95cn376qSQpU6ZMatSokVq2bKnbt287Rl0+y3OF5MfHx0cXL16MtezhH67KlSun48ePKzAw0PGeKVKkiObPn6+ff/75mdpdv369KlSooCtXrshsNqtkyZL6+OOP5evrqwsXLsS7jYeHh7JkyaL//vsv1vL//vtPbdu2lclk0uLFi+OE2dL9viSm3RhRUVHatGlTvGd3SNLhw4e1detWde3aVdL90ei3bt3SvXv3JN2/4O2DF8R8mBE+IwntEypUqKADBw7o0qVLjm2PHz+us2fPxtmn3W7XpUuXHNO9xOfh5+ZR/w48vF5C+tuEvLeS82uTJJV9/vnnypQpk3755RdNnTrVcdrE+PHjVaNGDc2YMSMpmgUAAAAAINHq1aunAwcOaNeuXY8MtIsVKyZJGjFihHbu3KkNGzaobdu2CgkJkRR39GZSyp8/vzJnzqy1a9fGe3GxoKAg/frrrypatKhjDtnE8PX11V9//aXdu3fr7t27CdqmWrVqKlu2rLp166Zvv/1Wu3bt0uzZs/Xxxx/Lzc0t1mjQ0qVLK0+ePNq9e7caNWr0xH3Xq1dPhQsXVufOnTV37lzt2rVLO3bs0LRp0/Thhx/q9ddff+Sp99L/TaOwY8cOHTp0SJLUt29fbdu2Tf369dPmzZv166+/qkOHDtqxY4cKFy4sSSpbtqwWL16sGTNmaNeuXfr+++81b948lStXznE8vr6+2r9/v/bs2fNM07ggeXjllVe0Z88ezZw5Uzt37tSoUaO0c+fOWOt069ZNZ86cUefOnbVx40Zt3bpVPXv21Nq1a1WwYMFnardUqVKy2Wzq3r27Nm7cqB07dmjo0KG6c+eOatWq9cjtKleurP3798da9umnn+ratWvq3r27QkNDdfDgQcd/x48flyTlzJlTDRs21GeffaZ58+bpt99+U4cOHXT79u1HjtgdO3as2rZt63jPlyhRQl5eXpowYYJWrVql/fv3q0aNGo+sNaZP+vHHH+MNfpOLhPQJbdq0Ufr06dW+fXtt2LBB69atU9euXZUmTZo4+zt27Jju3LmjKlWqPLJNX19fnTp1Sjt27NCtW7ceu97Vq1e1efNmXb58OUH9bULeW8n5tUmSQHvHjh3q1q2bfH1941x44e2339Y///yTFM0CAAAAAJBolSpVkq+vr/LlyxfrwmEPKl++vIYOHaoDBw6oY8eOGj16tHLkyKGpU6dKijt6M6lVqFBB9+7de2Sgfe/ePcfoy8Rq166drl69qvbt2+vIkSMJ2sbNzU2zZs1S/fr1NXPmTLVv315LlixR27ZtNXHixDjrV69eXenTp0/QlKVp0qTRokWL9Pbbb+u7775T586dHSFNnz59NHbs2Mdu7+Pjo7Zt22rjxo3q2LGj43mcM2eOLl68qF69emngwIEym82aN2+e4+Kd77//vrp06aIVK1aoQ4cOGj16tIKCgvTFF1849t2lSxcdOXJEHTt2jDNiFsbRuXNnNW3aVHPmzFHXrl115coVjRw5MtY6BQsW1DfffCOTyaSBAweqV69eunLliqZNm/bY8PlxsmbNqq+++krp0qXThx9+qM6dO+vPP//UlClTHnvWQe3atRUSEuIYKRwzylqShg0bprfffjvWf8OHD3dsO2LECL3zzjuaPXu2+vTpI6vVqnnz5sV7oczNmzfr5MmTsaZZiQmzN27cqHHjxik4ODjeaZti1KpVS0WLFtWgQYM0Z86cp32KnpuE9AkZMmTQ4sWLlStXLg0aNEijRo1Sy5Yt4/1BY8uWLcqSJctjf2xr2bKl0qRJo44dO2rLli2PXK9Ro0bKmTOnunfvrtWrVyeov03Ieys5vzYmexL8RFi6dGmNGTNGr776qqxWqwoXLqwVK1aocOHC+uWXXxQcHKy9e/c6u9lkx2q1Ok55KlGiBBdBBJIRI38+jVw7kBoY/TP68GCElOppLsBjdE9zITQkf8n59N9HMXq/iOfPbrerfv36CgoK0gcffODqclI0I38+jVx7UrPb7XrzzTdVu3Zt9ejRw9Xl4CF2u121a9dWixYt9N5777m6nCSTlJ/RJPk2VKZMGc2cOTPWKVYmk0k2m02LFy9+7K8PAAAAAAAg9QkNDdXUqVPVpUsXnT17Vq1atXJ1SYAhmUwmDRgwQEuWLElVP+Ibxf/+9z9ZrVY1b97c1aUY1rNfZvUx+vXrp3feeUe1atVS+fLlZTKZNGfOHJ04cUKnT5/Wt99+mxTNAgAAAAAAg/L09NSSJUtks9k0atQo5c6d29UlAYZVtWpVvfrqq5o5c6b69evn6nLw/0VFRWnChAkaM2aMPD09XV2OYSVJoJ0/f34tX75cU6dO1a5du2Q2m7V9+3aVLVtWn3/+uQoUKJAUzQIAACCR8ubN6+oSnovUNA2HEaeoeBY2m83VJQBIJHd3d23bts3VZQApxoNzYyN58PDw0IYNG1xdhuElSaAtSXny5NH48eOTavcAAAAAAAAAgFTGaYH2nj17nmr9smXLOqtpAAAAAACQRP744w+NGTNGR44ckcViUaNGjdSjRw95eHg8druDBw9q/Pjx+uOPP+Tt7a0qVapo4MCBypQpU5x1o6Oj1aJFC1WpUkU9e/aM9djEiRM1Y8aMONsMHDhQ7du3T9zBAXCZpOxb3nnnHe3fvz/OtsuXL1fRokVVo0YNnT9/Pt7958yZU7/++mviDg5JymmBdqtWrWQymWIts9vtse6bTCbZ7XaZTCYdPXrUWU0DAAAAAIAkcPbsWbVt21YlSpTQpEmTdOLECU2cOFE3b97UiBEjHrndkSNH1Lp1a1WqVElTp07V5cuXNWHCBHXv3l1LliyJtW5kZKQGDhyoQ4cOqUqVKnH2FRISonLlysWZBzhHjhzOOUgAz11S9i12u11///232rZtqzp16sTaPiAgQJI0depURUVFxXrs4MGD+uyzz7hYowE4LdBesGCBs3YFAAAAAACSgdmzZ8tisejLL7+Uh4eHqlWrJk9PT33yySfq0qXLI0PlsWPHqlChQvryyy8dc/n7+Pho5MiROnv2rOOCj3v37tWIESN06dKlR9Zw9OhRNWrUSCVKlHD68QFwjaTsW86cOaOwsDBVq1btkf1GoUKFYt0PDQ1V3759Vb16dXXq1Mmpxwrnc1qgXa5cOWftCgAAAAAAxKNGjRp64403FBERoVWrVsnNzU3VqlXTBx98ID8/v3i32bVrl1q3bv3IfTZs2FCjR4+O97Ft27apWrVqsaYAqFOnjoYPH65t27apWbNmcba5ceOGdu/erdGjR8e6MG2tWrVUq1atWOt27dpVpUuX1vTp01WjRo04+7p+/bouXbqkwMDAR9YPIPFSUt8SMytEwYIFH3vMD/ryyy91/fp1DR06NMHbwHWcFmgPHjz4qdb/7LPPnNU0AAAAAACpxrfffqsXX3xRn332ma5fv67x48fr9OnTWrJkSZypQCWpcOHCWrp06SP3lzFjxniX3717V+fPn1eePHnirO/j46NTp07Fu93ff/8tm82mjBkzql+/fo65aGvWrKkhQ4bI19fXse6iRYtUoECBR9YWEhIiSdq0aZNGjx6ty5cvK1++fOrTp4+qVav2yO0APL2U0rccPXpU3t7eGjNmjH799VeFh4erQoUKGjx4sPLmzRtnvxcuXNCCBQvUuXNn5cyZ85HHg+TDaYH2rl27Erzuw3NrAwAAAACAhHFzc9O8efOULl06SfdDoO7du2vr1q2qWrVqnPV9fHyeabqOO3fuOLZ/mMViUWhoaLzbXb9+XZL0wQcfqGrVqvryyy/177//asKECTp79qy+/fZbRzj2uDBb+r+RlleuXNGnn36qqKgoLVq0SF26dNGsWbPinXMbwLNJKX1LSEiIwsPD5evrq2nTpun8+fOaNm2aWrZsqdWrVytbtmyx9vv111/Lw8PjsaPNkbw4LdBOyNU/L126pO+++07Lly93VrPAc2G1Wl1dgiTJbDa7ugQAAAAALlajRg1H4BRz393dXXv27Ik3dLLb7Y/9m8bNzS3W6fsxbDbbY+uIb8SmJN27d0/S/dGbI0eOlCRVrFhRvr6+6tu3r37//XcFBQU9dt8x6tatq7x586pq1aqOv4eCgoLUoEEDffHFFwTagBOllL6lT58+6tChg8qWLStJKlOmjEqVKqW6detqwYIFGjBggGOfkZGRWr58uZo0aaL06dM/ti4kH04LtB9n69atWrJkiTZv3qzo6GjHxR8AI7BarVq3bp2ry5Ak1atXj1AbAAAASOUeHl3o5uamDBky6NatW/Guv3v37mea5zZm9GRYWFicx0JDQ2MFXw+yWCySpFdeeSXW8pjw+a+//kpwoJ0jR444F4dLkyaNKleurCVLliRoHwASJqX0LfHNnZ07d24FBAQ4pjGKsW3bNoWGhuqNN9545HEg+UmyQPv69etavny5li1bpvPnz8vHx0cNGzZUgwYNVKZMmaRqFkgyu3fvdsp+oqKiNGbMGEnSwIEDY10A4XG48Cri8zTTPQHJndlsVvny5V1dBgAAyd6NGzdi3bdarbpx48Yj56stXLjwY8+UzpAhQ7zLLRaLsmXLptOnT8dafu3aNYWFhSkgICDe7V566SVJ9//2eVB0dLQkydPT85G1PGzz5s26e/euateuHWt5ZGTkI48XwLNJCX1LdHS0fvjhB7300ksqWbJkrPXu3r0b51g2bdqkXLlyqWjRoo88DiQ/Tg+0d+7cqaVLl2rjxo2yWq0qXbq0Y64aAjkYXcmSJeM9XeZp3L17N9b+nvRlzmaz6cCBA4lqEynX9evXuS4BUoxMmTK5ugQAAAxhy5YtioqKcgyO+eWXXxQdHa2KFSvGu76Pj88zhzWVK1fWpk2bNHjwYEd7GzZskNlsVoUKFeLdJiAgQDlz5tTatWv17rvvOqYP+OWXXyTpqQa5rV+/Xhs2bFD58uXl5+cnSQoPD9emTZse2T6AZ5MS+hZ3d3dNnTpVWbNm1eLFix3b/vnnnzpz5ow6duwYa58HDx5UqVKlnukY4DpOC7Tnz5+vpUuX6tSpU3rxxRfVrVs3NWzYUN7e3ipXrtwj578BjMTNzS3RU348uL3ZbGYKEQAAAABP5b///lPXrl3VunVr/ffff5owYYKqVKmSJGc6dejQQWvXrlWHDh3Utm1bxwXYmjVr5pgKJCoqSn/99ZeyZ8+u7Nmzy2QyaeDAgerdu7f69OmjZs2a6fjx45o4caJq166tQoUKPVX769evV8eOHdW5c2fZbDbNnj1bERER6tmzp9OPF0jNUkrf0rNnTwUHB2vgwIFq0KCBLly4oMmTJyswMFANGzZ01GC1WnXy5Em9/vrrTj8+JC2nBdqjR49WgQIFtGDBglgjsWOuXAoAAAAAABKvfv368vX1Ve/eveXt7a2GDRuqT58+SdJWQECA5s6dqzFjxqhXr17KkCGD3nvvPfXq1cuxzuXLl/X222+rR48ejpC5Tp06mj59uqZNm6bOnTsrffr0at68+VPXGRAQoEWLFmnChAn68MMPFRUVpbJly2rkyJFcnwtwspTSt7z11lvy8PDQV199pe7du8vLy0s1a9ZU3759Yw0qvHnzpqKjo+Xr65skx4ik47RAu379+vrll1/UuXNnVaxYUQ0bNowzSTsAAAAAAEicNGnSaNiwYRo2bNhzaa9MmTJatmzZIx/PlSuX/v777zjLX3nllafKBeLbh3R/nt45c+YkeD8Ank1K6lvq1aunevXqPXadTJkyPbLfQfLmtEB7/PjxCg0N1Q8//KCVK1eqZ8+eypAhg1577TWZTCamHAEAAAAAAAAAJErirm73EB8fH73zzjv67rvv9MMPP6hBgwb69ddfZbfb9cEHH2jy5Mk6fvy4M5sEAAAAAAAAAKQSThuh/bB8+fJp0KBB6t+/v3777TetWLFCs2fP1owZM5QvXz59//33SdU0AAAAAAAp0q+//urqEgCkQPQtMJIkC7QdDbi7q2bNmqpZs6auXr2qVatWadWqVUndLAAAAAAAAAAghXHqlCNPkjlzZnXs2FHr1q17ns0CAAAAAAAAAFKA5xpoAwAAAAAAAADwrAi0AQAAAAAAAACGQKANAAAAAAAAADAEAm0AAAAAAAAAgCEQaAMAAAAAAAAADIFAGwAAAAAAAABgCATaAAAAAAAAAABDINAGAAAAAAAAABgCgTYAAAAAAAAAwBAItPHc2e122e12V5eBx+A1AgAAAAAAQHJEoI3nym63KygoSFWqVCEwTaZ4jQAAAAAAAJBcubu6AKQu4eHh2r59u+O2xWJxcUV4GK8RAAAAAAAAkitGaAMAAAAAAAAADIFAGwAAAAAAAABgCATaAAAAAAAAAABDINAGAAAAAAAAABgCgTYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAAAAAAAAAAyBQBsAAAAAAAAAYAgE2gAAAAAAAAAAQyDQBgAAAAAAAAAYAoE2AAAAAAAAAMAQCLQBAAAAAAAAAIZAoA0AAIDnpnbt2vrf//6nw4cPa9WqVSpZsqQkqXr16vrpp5908OBBzZkzR9mzZ3dxpc43f/58DR482NVlJKlDhw7prbfeUokSJdSiRQudOXPG1SUlqdTwmgIAACQ3BNrJQFhYmI4ePap9+/bp6NGjCgsLc3VJzySlHAeSzvN4j/A+BIDkK2fOnBo7dqwGDBigYsWKadGiRZoyZYpy586tKVOmaNKkSSpTpoz27dunmTNnurpcp7FarZo9e7bGjh3r6lKSVGRkpLp3764OHTpo9+7dqlSpknr37u3qspJEanlNAQAAkiN3VxeQ2p09e1aHDh2S3W53LDtx4oSKFy+u3Llzu7Cyp5NSjgNJ53m8R3gfAkDydv78eVWoUEHh4eFKkyaNMmTIoBs3bqhq1arav3+/NmzYIEmaPn26OnfurIIFCyokJMTFVSfe4MGDdfv2bTVt2lSRkZGuLifJ7Ny5U35+fnr99dclSV27dtXXX3+t48eP6+WXX3Zxdc6VWl5TAACA5IhA24XCwsIc4VuWLFmUJUsWXblyRVeuXNGhQ4eUMWNGWSwWV5f5RM96HEYZOWu1WnX37l1Xl6G7d+8qLCxMZrM5SdtJqlHTSf1eTymfJwBI6cLDw5U/f379+OOPio6OVseOHRUQEKCIiAjHOna7XXa7Xf7+/iki0O7fv7+yZs2qqVOn6vz5864uJ8mcOnVKefPmddw3m83KnTu3Tp48meIC7dTymgIAACRHqS7Qtlqt8QaCNptNbm7PdwaWM2fOOMK3ChUqSJICAgK0c+dOXblyRWfOnFFgYOBzrelZPOtxZMuW7XmXmihDhgxxafvNmjVzafuJ8Tze6ynl8wQAqcHJkydVqFAhNWjQQNOmTVObNm3Uv39/ValSRTt27FC7du3k6emptGnTurpUp8iaNaurS3guwsPD5enpGWuZl5dXrB8rUorU8poCAAAkR6lqDu2YMNtms2nWrFlasGCBvvnmG0l67mG2dP9LvyRlyZIl1vKY+0b58p9SjgNJ53m8R3gfAoBxREdHKzo6WitWrNCFCxeUPXt2DRgwQEOGDNG2bdvk4eGh48eP686dO64uFU/By8srzlltERERnCEFAAAAp0pVI7RjwuxGjRopW7Zsyps3r/bs2aMffvhB8+bNk5eXl+x2u0wm03Opx9vbW5J05coVBQQEOJZfuXJF0v0/CozgWY/j0qVLhvgDx2q1asOGDTp8+LBL61i2bJlq1679XKYccfbo+efxXk8pnycASMkqVaqkzp07q02bNo5ladKkkdVq1b///qvatWtLknx8fNS1a9cUMd1IapI3b16tWrXKcd9qterMmTPKkyePC6sCAABASpOqAm1JWrdunbJnz64ZM2ZIkoKDg3Xs2DHdvn1bXl5ezy3MliR/f3+dOHFCV65c0c6dO2PN+WsymeTv7//cakmMZz0Oi8VimED74dNnXcHT01MWiyXJA+2k8Dze6ynl8wQAKdnRo0dVpEgRvf766/rpp5/UokULmc1mnTlzRsuWLVOjRo106dIlBQcHa+fOnbp48aKrS8ZTKF++vK5du6bVq1erXr16mjVrlvz9/WP90AwAAAAkVoqfcsRms8W6Hx0d7bjoXXBwsP7++28tWbJEEydO1KJFi55rbRaLRcWLF5fJZNKVK1f0119/OcK34sWLGyLslVLOcSDpPI/3CO9DAEj+bty4oU6dOqlTp07au3evateurfbt2+vYsWP6/PPPtWjRIm3fvl1+fn7q27evq8vFU/L09NTMmTO1cOFClS9fXtu3b9ekSZNcXRYAAABSmBQ/QjtmbuyhQ4eqSZMmKliwoCwWizp37qyLFy9qzZo1kqSLFy/qjTfeeO715c6dWxkzZtSZM2cUEREhLy8v+fv7Gy58SynHgaTzPN4jvA8BIPnbt2+f3nzzzTjLly5dqqVLl7qgouenR48eri4hyRUpUkQrVqxwdRnPTWp4TQEAAJKbFB9ox7hy5Yq+/PJLzZgxQ9myZdP69es1YcIE2Ww2LV++XMePH3fZlAQWi0WBgYEuaduZUspxIOk8j/cI70MAAAAAAICUK0UG2jabzTEyO8YHH3ygTz/9VEePHtXw4cNlt9u1ePFiffHFF4qOjtbMmTOVO3duF1UMAAAAAAAAAHiSFBlou7m5yW6368MPP1SdOnVUoUIFvfDCC0qfPr1WrFihIUOGaMSIEbpy5YqioqJksVjk5+fn6rIBAAAAAAAAAI+RogJtq9Uqs9ksSbp586bSp0+vIUOGqEaNGqpYsaL69OmjFi1a6NVXX1XFihWVJUsWF1cMAAAAAAAAAEioFBNox4TZNptN33//vfz9/RUcHKwmTZpo586dmjBhgooXL648efJo3759qlixoqtLBgAAAAAAAAA8Bbcnr5L82e12R5jdoEEDffXVVxo8eLDGjRsnHx8ftWzZUitXrlT27NkVGhqq5cuXKzIy0tVlAwAAAAAAAACeguFHaNvtdplMJtlsNvXq1UtFixbVqFGjNH36dP3yyy8ymUxq2LCh8ubNq969eysqKkq3b99W2rRpXV06AAAAAAAAAOApGHqEts1mc4y0jo6OVkREhDp27ChJunbtmrJnz64///xTa9as0dGjR+Xm5iZPT09lzZrVlWUDAAAAAAAAAJ6BYQPtTz75RN26dVP37t21atUqmc1mmc1mpU+fXkOHDlVISIimTp2ql156ScuWLdPs2bMVERHh6rIBAAAAAAAAAM/IkIF2t27d9Oeff+qNN95Q3rx5NW/ePN26dUvjx4+X2WzWuXPnNG7cOEmSr6+v6tWrpw8//FBeXl4urhwAAAAAAAAA8KwMN4d2jx49dO3aNS1dulSSlCdPHu3atUvXrl1Tvnz5dPXqVR05ckQ//PCD3NzctHLlSn399dfKlCmTiysHAAAAAAAAACSGoQLtHj166J9//tGGDRscy7y8vGS32xUdHS1Jypw5s4YMGaKvv/5a3t7e+vLLL5UnTx5XlQwAAAAAAAAAcBJDBdpNmzbVwIEDderUKeXJk0dnz55VmzZt1LJlSwUGBkqS7Ha73nzzTdWoUUNms5lpRgAAAAAAAAAghTDUHNrVqlXTmDFj9M477+i3337Te++9p2bNmqlz586SJJvNJpPJJEny8fEhzAYAAAAAAACAFMRQgbZ0P9T+/PPP1bVrV1WuXFk9evSQdD/MdnMz3OEAAAAAAAAAABLIkAlwtWrVNGfOHP388886evSoJBFmG4S3t7cqV66sypUry9vb29XlIB68RgAAAAAAAEiuDDWH9oMqV66szz77TO3atdPMmTNVrFgxV5eEBDCZTNq6davjNpIfXiMAAAAAAAAkV4Ye1ly9enWNGDFCffr0UVRUlKvLQQKZTCaC0mSO1wgAAAAAAADJkWFHaMeoWbOmKlWqJA8PD1eXAgAAAAAAAABIQoYeoR3DYrG4ugQAAAAAAAAAQBJLEYE2AAAAAAAAACDlI9AGAAAAAAAAABgCgTYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAAAAAAAAAAyBQBsAAAAAAAAAYAgE2gAAAAAAAAAAQyDQBgAAAAAAAAAYAoE2AAAAAAAAAMAQCLQBAAAAAAAAAIZAoA0AAAAAAAAAMAR3VxcAGInNZkv0PqxWa6zbD95PqjYBAAAAAACAlIBAG3gKBw4cSPQ+oqKiYu3Pw8Mj0ftE6pUxY0ZXlwA4jdlsdnUJAAAAAIBkjkAbSKBy5co5bV9BQUFO2xdSt/LlyxMCAgAAAACAVINAG3gCs9msevXquboMSYxeBAAAAAAAQOpGoA0kAEEyAAAAAAAA4Hpuri4AAAAAAAAAAICEINAGAAAAAAAAABgCgTYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBHdXF5CS2e12x22r1erCSgA87MHP5IOfVSOgbwGSNyP3LwCQFPjuAiRfRv7eQt8CJG9J2b8QaCchm83muP3HH3+4sBIAj/PgZ9UI6FsA4zBa/wIASYHvLoAxGO17C30LYBzO7l8ItAEAAOBw4sQJV5cAPBM3N2ZTBAAASA1MdqOdU2IgNptN0dHRku5/wTaZTC6uCEAMu93u+IXQ3d3dUH8E07cAyZuR+xcASAp8dwGSLyN/b6FvAZK3pOxfCLQBAAAAAAAAAIZgnJ/eAAAAAAAAAACpGoE2AAAAAAAAAMAQCLQBAAAAAAAAAIZAoA0AAAAAAAAAMAQCbQAAAAAAAACAIRBoAwAAAAAAAAAMgUAbAAAAAAAAAGAIBNoAAAAAAAAAAEMg0AYAAAAAAAAAGAKBNgAAAAAAAADAEAi0AQAAAAAAAACGQKANAAAAAAAAADAEAm0AAAAAAAAAgCEQaAMAAAAAAAAADIFAGwAAAAAAAABgCATaAAAAAAAAAABDINAGAAAAAAAAABgCgTYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAAAAAAAAAAyBQBsAAAAAAAAAYAgE2gAAAAAAAAAAQyDQBgAAAAAAAAAYAoE2AAAAAAAAAMAQCLQBAAAAAAAAAIZAoA0AAAAAAAAAMAQCbQAAAAAAAACAIRBoAwAAAAAAAAAMgUAbAAAAAAAAAGAIBNoAAAAAAAAAAEMg0AYAAAAAAAAAGAKBNgAAAAAAAADAEAi0AQAAAAAAAACG4O7qAlIym82m6OhoSZKbm5tMJpOLKwIQw263y2azSZLc3d3l5sbvewBSN763AMmbkb+70L8AyRd9C4CkkpT9C4F2EoqOjtYff/zh6jIAPEHRokXl4eHh6jIAwKX43gIYh9G+u9C/AMZA3wIgqTi7fyHQBgCDYgRCypI3b15XlwAnO3HihKtLAAAAAIAUh0A7CT04lL5o0aIym80urAbAg6xWq+PXfCOdVgcASYXvLUDyZuTvLvQvQPJF3wIgqSRl/0KgnYQeHD1pNpvpXIFkipHOAMD3FsBIjPbdhf4FMAb6FgBJxdn9i7F+fgMAAAAAAAAApFqM0EayZrVaXV1CkuIXZAAAAAAAACDhCLSRbFmtVq1bt87VZSSpevXqEWoDAAAAAAAACUSgjWRv9+7dz62tqKgojRkzRpI0cOBAeXh4JFlb5cqVS7J9AwAAAAAAACkRgTYMoWTJks/list3796N1aanp6fT27DZbDpw4IDT9wsAAAAAAACkdATaMAQ3N7fnMjXHg21wlWQAAAAAAAAgeUn6Ia8AAAAAAAAAADgBI7QBAADwRLt27ZLVanV1GU/NbDarfPnyri4DAAAAgJMQaAMAAOCJrFarrl275uoynlqmTJlcXQIAAAAAJ2LKEQAAAAAAAACAIRBoAwAAAAAAAAAMgUA7mbDb7bLb7a4uA0hyvNcBAAAAAADwrAi0kwG73a6goCBVqVKFoA8pGu91AAAAAAAAJAYXhUwGwsPDtX37dsdti8Xi4oqApMF7HQAAAAAAAInBCG0AAAAAAAAAgCEQaAMAAAAAAAAADIFAGwAAAAAAAABgCATaAAAAAAAAAABDINAGACQrgYGBioiI0Isvvpig5Ui+ateurf/97386fPiwVq1apZIlS0qSqlevrp9++kkHDx7UnDlzlD17dhdXCgAAAAAwCgJtAECyYTabNW/ePHl6eiZoOZKvnDlzauzYsRowYICKFSumRYsWacqUKcqdO7emTJmiSZMmqUyZMtq3b59mzpzp6nIBAAAAAAZBoA0ASDYGDx6sbdu2JXg5kq/z58+rQoUKOnTokNKkSaMMGTLoxo0bqlq1qvbv368NGzYoOjpa06dP10svvaSCBQu6umQAAAAAgAG4u7oAV7Db7TKZTK4uI15hYWGuLiHZsFqtunv3rqvLSDJ3795VWFiYzGazq0t5bnh/43GKFSumt99+W2XLllW/fv2euBzJX3h4uPLnz68ff/xR0dHR6tixowICAhQREeFYx263y263y9/fXyEhIS6sFgAAAABgBKky0E6uYbYkZcuWzdUlJDtDhgxxdQlJolmzZq4uAUg20qRJo3nz5qlz586xfsh61HIYx8mTJ1WoUCE1aNBA06ZNU5s2bdS/f39VqVJFO3bsULt27eTp6am0adO6ulQAAAAAgAGkqilHPv30U40cOVJnz57VrVu3JN0fGfbg/wEAz9/QoUO1adMmbd++PUHLYRzR0dGKjo7WihUrdOHCBWXPnl0DBgzQkCFDtG3bNnl4eOj48eO6c+eOq0sFAAAAABhAqhmhfenSJa1du1Y2m02hoaE6e/asunfvrrx58ypbtmyOUduuno7k0qVLslgsLms/ObFardqwYYMOHz7s6lKSxLJly1S7du1UN+UIZyEgPk2aNNELL7ygdu3aOZYdPnxYFy9eVLZs2eIs79KlixYvXuyKUpFAlSpVUufOndWmTRvHsjRp0shqterff/9V7dq1JUk+Pj7q2rUr040AAAAAABIkVQTadrtd2bJlU9++fXXhwgW98sor2rlzpyZPnqw0adKoSpUqatKkifz8/OTm5ubSUNtisRBo/39Wq1Wenp6uLiPJeHp6ymKxpKpAG3iUwMDAWPftdruKFSum06dPJ2g5kp+jR4+qSJEiev311/XTTz+pRYsWMpvNOnPmjJYtW6ZGjRrp0qVLCg4O1s6dO3Xx4kVXlwwAAAAAMIBUMeVITDidMWNGbdmyRQEBAerUqZMsFovu3LmjJUuWqE+fPmrbtq3Onj2brOfYBgDACG7cuKFOnTqpU6dO2rt3r2rXrq327dvr2LFj+vzzz7Vo0SJt375dfn5+6tu3r6vLBQAAAAAYRKoYoR3j1Vdf1dq1a/Xll1/qzp07unLlihYvXqw0adJo3bp12rhxo+7du+fqMgEg1XvUD4v84Ggs+/bt05tvvhln+dKlS7V06VIXVAQAAAAAMLoUG2hbrVbHVA4P3m7UqJGGDx+uzJkza/bs2Y7pPd566y29+eabcnNLFYPWAQAAAAAAAMBwUmR6GxNg22w2ff755+rUqZM2b94sSSpVqpQyZcqkokWLOi5OZ7fbJYkwGwAAAAAAAACSsRSZ4MaE2Y0bN9aVK1f06quvKjAwUHa7Xd7e3nr//ff1559/6p9//pHEKewAAAAAAAAAYAQpdsqRjRs3KkeOHBo3bpwkaerUqTp69Kjy58+vGjVq6ObNmzpy5Ijy5cvn4koBAAAAAAAAAAmRYgLtB+fJliQvLy+FhoZq6NChOnbsmK5evapmzZrpyy+/VKVKldSuXTsVK1bMhRUDAAAAAAAAAJ5Gigi0o6Oj5e7uLrvdrl27dsnPz09BQUHau3evoqKiFBQUpK5du8psNuv06dM6ceKEmjdv7uqyHby9vVW5cmXHbSCl4r0OAAAAAACAxDB8oG2z2eTu7i6r1arGjRvLarUqTZo0ql+/vvr06SNJCgkJ0T///KMtW7Zo/fr16tChg4urjs1kMmnr1q2O20BKxXsdAAAAAAAAiWH4QNvNzU02m03dunVTsWLF1KdPH82dO1erV6/W7du31adPH61Zs0YHDx7UvXv3tGjRIuXJk8fVZcdBuIfUgvc6AAAAAAAAnpVhA+07d+4oMjJSFotF4eHhunbtmiZOnChvb2/dvHlTgYGB2rdvn7799lsFBwdLkkJDQ+Xj4+PiygEAAAAAAAAAz8LN1QU8i+HDhys4OFjvvfeevv/+e125ckUBAQGKjIzUoEGDdOHCBQ0aNEg+Pj4aMWKEBg4cKEmyWCwurhwAAAAAAAAA8KwMN0K7a9euunbtmkaOHKkzZ86oevXqCgsLU926dWWxWHTs2DFNnz5dGTNmlL+/vz788ENVr15dElMdAAAAAAAAAICRGSrQnjJlim7fvq1ly5ZJkvLly6ezZ8/qvffe040bN9SnTx/lyZNHBw8e1OnTp7V27VotWbJEuXPndnHlAAAAAAAAAIDEMkygbbfbde7cObVu3dqx7MKFC2rRooXefPNNvfzyy5o2bZoiIiJktVoVEhKiWbNmEWYDAAAAAAAAQAphmEA7MjJSISEhKleunGPZoUOH1KpVK3Xq1El37tzR0qVLVbFiRbVv315Wq1Xp06d3YcVwJpvN9lzasVqtsW4/eN9ZntexAAAAAAAAACmNYQJtNzc3+fr66sSJE45ldevWjbWOt7e3SpcuLR8fn+ddHpLYgQMHnks7UVFRsdr08PB4Lu0CAAAAAAAAeDLDBNoeHh5q27at+vXrp0KFCun111+P9fjKlSt19epV5cuXz0UVIqk8OCr/eQgKCnqu7QEAAAAAAABIGMME2tL9oLFt27b65JNPdPnyZdWsWVOhoaHavn27Zs6cqfnz5ytbtmyuLhNOYjabVa9ePVeXkaTMZrOrSwAAAAAAAAAMw1CBtoeHhzp27KgXXnhBkyZN0rJly+Tn56fMmTNr4cKFKlCggKtLhJMR+AIAAAAAAACIYahAW5K8vLzUtGlTx+jsdOnSKW3atPL09HR1aQAAAAAAAACAJGS4QDuGn5+f/Pz8XF0GAAAAAAAAAOA5MWygDQCpXWhoqKtLgBN5eXm5ugQAAAAAAJI9N1cXAAAAAAAAAABAQhBoAwAAAAAAAAAMgSlHkOxZrVZXl4BkyGw2u7oEAAAAAAAAPGcE2kjWrFar1q1b5+oykAzVq1ePUBsAAAAAACCVIdCGIezevTvR+4iKitKYMWMkSQMHDpSHh0ei9wnXKFeunKtLAAAAAAAAgAsQaMMwSpYsKTe3Z5/2/e7du7H25enp6Yyy8BzZbDYdOHDA1WUAAAAAAADARQi0YRhubm6JmmLiwW3NZjPTVQAAAAAAAAAG8+zDXQEAAAAAAAAAeI4ItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAAAAAAAAAAyBQBvPxG63y263u7oMIF68PwEAAAAAAFImAm08NbvdrqCgIFWpUoXQEMkO708AAAAAAICUy93VBcB4wsPDtX37dsdti8Xi4oqA/8P7EwAAAAAAIOVihDYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAJK1kydPqkKFCrpw4YKrS4ETzJ8/X4MHD3Z1GQAAAAAAgyLQBgAkW9HR0fr4448VFRXl6lKQSFarVbNnz9bYsWNdXQoAAAAAwMBSZaC9evVqnTt3ztVlAACeYN68eSpRooSry4ATDB48WPv27VPTpk1dXQoAAAAAwMDcXV3A83b69Gl99tlnGjx4sHLlyiW73S6TyeTqsgwrLCwsSfdvtVp19+7dJG0DxnP37l2FhYXJbDbHeSyp35N4fo4dO6b//e9/WrhwoRYtWuTqcpBI/fv3V9asWTV16lSdP3/e1eUAAAAAAAwq1QXaL774ooKDgzVhwgQVKlRI+fPnd3VJhpYtW7bn0s6QIUOeSzswhmbNmrm6BCSxe/fu6eOPP9aHH34oT09PV5cDJ8iaNaurSwAAAAAApACpZsqRkydPOm6//vrrqlWrltauXavw8HAXVgUAiM+sWbNUunRpphsBAAAAAACxOG2E9p49ex75mMlkksViUe7cueXj4+OsJhNswIAB2rhxo7p06aJWrVrJ29tbVapU0aJFi3Tz5k15e3vLarXGO30BHu/SpUuyWCxJtn+r1aoNGzbo8OHDSdYGjGfZsmWqXbv2I6cceV5nDiDp/PLLL7p69arWrFnjWPb222/rgw8+UN26dV1YGQAAAAAAcCWnBdqtWrWKNRd1fHNTu7m56a233tKIESOea3icL18+/f333/r22291/PhxlShRQs2bN9fvv/+u4OBgLVy4kDD7GVksliQPtJluAA/z9PSUxWLhc5uCrVy5Mtb9UqVKaenSpcqRI4eLKgIAAAAAAMmB06YcmT59ujw8PNSsWTMtWLBA69at08KFC/Xuu+/K3d1dgwcP1gcffKCff/5Zs2bNclazCRIUFKRq1app5MiRKlWqlHbt2qUWLVqocePG8vb2jhOcAAAAAAAAAACSH6eN0J49e7ZatGih4OBgx7K8efOqTJky8vb21s8//6yFCxdKkhYsWKCuXbs6q+l4bd26Vblz59ZLL72kQoUK6bvvvtOSJUs0depUvfPOO/r00081YsQI2Ww2/e9//1P9+vWVNm3aJK0JAPBs9u/f7+oS4CQ9evRwdQkAAAAAAANz2gjtP//8U1WqVIn3sfLly+vQoUOSpAIFCui///5zVrPx2rNnjz766CNNmTJFq1evliQNGzZMt27d0pQpUyRJQ4YMUc+ePVW6dGkdOnRIoaGhSVoTAAAAAAAAACBxnBZoZ8mSRbt27Yr3sV27dilz5sySpBs3bsjX19dZzcarbNmymjx5sgoVKqTx48dr+PDhunr1qtq2bauwsDAdP35cklShQgX1799fP//8szJlypSkNQEAAAAAAAAAEsdpU4688847Gj9+vCIiIlS7dm1lypRJV69e1caNG7Vo0SL17NlTFy9e1PTp01W+fHlnNRuL1Wp1XCSuePHiKl68uKpXr65hw4Zp2rRpSps2rU6cOKFjx47p5Zdfdmzn4+OTJPUAAAAAAAAAAJzHaYF2+/btFRERoa+++soxV7bdble6dOnUs2dPde7cWatXr1ZUVJT69u3rrGYdYsJsm82msWPH6tixY2rZsqVq1KihadOmaePGjTp16pR27typPXv2yN/fX0WKFHF6HQAAAAAAAACApOG0QFu6f6Gn9u3b68CBA7px44ayZcumwMBAWSwWSdIbb7yht956y5lNOsSE2Y0bN1ZAQIBeffVVFSlSRHa7XenTp1fjxo0dAfumTZuYYgQAAAAAgFTAbrfLZDIZZr8AjIG+xXWcNod2DC8vL1WqVEn169dXmTJlHGG2JMd0IEll48aNypEjh8aNG6cWLVpo2bJl6tGjhyZOnKhr167JZDKpc+fOmj17tl544YUkrSUl8/b2VuXKlVW5cmV5e3u7uhwgFt6fAAAASCqtWrVSq1at4iwPDQ1Vs2bNVKRIEW3cuNFldTyNXbt2qUCBAo+8FpYkNWnSRI0aNYqzfP369SpQoIDq1q0b57ENGzaoQIEC2rt3b4LqePBYzp07pwIFCmjlypWSpJUrV6pAgQI6d+5cgvYVn3379qlTp07PvP2j/PPPP3rnnXecvl+kTvQt99G30LcklNNGaF+/fl0jR47Upk2bFBERIbvdHutxk8mkv/76y1nNSYo9Z7Z0P0wPDQ3V0KFDdezYMV29elXNmjXTl19+qcKFC6tWrVqSmDM7sUwmk7Zu3eq4DSQnvD8BAADwPIWGhqpDhw4KCQnRtGnTVK1aNVeX5DQVK1bU3LlzFR4eHmuwyNatW+Xn56eTJ0/q/Pnzypkzp+OxPXv2yGKxqESJEoluv3r16lq6dKmyZs36zPv47rvvdOLEiUTX8rD169frwIEDTt8vEIO+hb4Fj+a0QHvEiBH67bffVL9+fWXPnl1ubk4f/B1LdHS03N3dZbfbtWvXLvn5+SkoKEh79+5VVFSUgoKC1LVrV5nNZp09e1bXr19P0npSG4JCJGe8PwEAAPA8xAROR48e1fTp01W5cmVXl+RUFStW1KxZs3To0CFVrFjRsXzbtm169913NWvWLG3dulXNmzd3PLZ3716VK1dO7u6JjxsyZsyojBkzJno/gNHQt9C34PGcljpv2bJFH3zwgUaNGqVevXqpR48ecf5zFpvNJnd3d1mtVjVs2FAjR47UBx98oLlz56pPnz4KDg7Wa6+9pn/++UezZs3SunXrVL58eae1DwAAAABI3cLCwtSxY0f9/fffmjVrVpzAqUaNGho1apTatGmjYsWK6cMPP3zkae41atTQoEGDHPd///13NWvWTCVLllTZsmXVtWvXx44E3Lp1q4oUKaIPP/zQcbb0nj171L59e5UtW1ZFihRRjRo1NGXKFNlstgQfY+nSpZU2bVrt37/fseyff/7RxYsX9corr6hUqVLatm2b47E7d+7o77//djwXd+/e1fjx41WrVi0VKVJEpUqVUtu2bXX06NEEtf/w83X9+nX169dPlStXVtGiRdWgQQOtXr36kdsPGjRIq1at0vnz52NNNxAZGakxY8aoWrVqKlKkiN544w2tW7cu1rZHjhxRmzZtVLp0aZUsWVLvvfeeDh48KEmaMmWKpk6dKkkqUKCApkyZkqDjARKCvoW+RaJveRKnjdBOkyaNcufO7azdPZabm5tsNpu6deumYsWKqU+fPpo7d65Wr16t27dvq0+fPlqzZo0OHjyoe/fuadGiRcqTJ89zqQ0AAAAAkLKFh4erU6dO+uuvvzRnzhyVKVMm3vW++eYbtW3bVh07dpTFYtGpU6eeuO+zZ8+qW7duaty4sfr27avbt29rwoQJ6tSpk37++ec4Z0Pv2bNHPXr00BtvvKFPP/1UJpNJISEheu+991SnTh1NnDhRdrtdP/zwg6ZOnaq8efOqfv36CTrOtGnTqmTJkrFCp23btiljxowqXLiwgoKCNGPGDMcZ1Pv375fNZnOETgMHDtTevXvVt29f+fv76/Tp05o8ebL69euntWvXPvWZlQMGDNC1a9c0fPhw+fj4aM2aNQoODlb27NlVoUKFOOt369ZN169f119//aWpU6fK399fdrtd3bt31/79+9WrVy8FBATo559/Vp8+fRQVFaW33nrLMTq2QoUKmjJliqKiojR9+nS1b99emzZtUtOmTXXx4kUtX75cS5cuVfbs2Z/qOIBHoW+hb6FvSRinBdo1a9bUjz/+qEqVKjlrl3HcuXNHkZGRslgsCg8P17Vr1zRx4kR5e3vr5s2bCgwM1L59+/Ttt98qODhY0v3TNJgzGwAAAADgDDGB0759+xz3HyVHjhzq37+/435CQqfDhw/r7t276ty5s7JlyyZJyp49u3755ReFh4fH+vv28OHD6ty5s2rXrq2RI0c6QpyQkBBVqlRJY8eOdYRUlStX1q+//qpdu3YlOHSS7k8N8NVXX8lms8nNzU1bt25VpUqVZDKZFBQUpHHjxunAgQMqW7as9uzZoxdeeEF58+ZVVFSUwsLCNGTIENWrV0+SVK5cOYWGhmr06NG6evWqsmTJkuA6JGn37t3q3r27XnvtNcf+/Pz85OHhEe/6/v7+ypgxozw8PBzz7v7+++/aunWrJk6c6KirSpUqioiI0Lhx4/T666/r+PHjunHjhlq3bq1SpUpJkvLmzaulS5cqLCxM2bNndwRNzpjPF5DoW+hb6FuehtMC7UKFCmnSpEk6e/asihcvLk9Pz1iPm0wmde/e/Zn3P3z4cF26dElnzpxRq1atVLx4cQUEBCgyMlIjRozQlStXNHbsWH3wwQcaMWKEDh48qDFjxshisST20AAAAAAAkHT/dHE/Pz998803+uCDDzRo0CCtWbMm3gAlMDDwqfdfvHhxpU2bVk2aNFGdOnVUtWpVlS9fXsWKFYu13oULF9SxY0fZ7XYNHTo01ujKt956S2+99ZYiIyN16tQpnT59WkePHpXVatW9e/fibTc6OjrWfbPZLJPJpEqVKmnixIk6duyYXnrpJe3du1cjRoyQJBUsWFCZM2fW9u3bVbZsWe3du9cxyM3Dw0Nz5syRJF26dEmnTp3Sv//+q99++02SFBUV9dTPTfny5TVlyhT99ddfqlKliqpVq+YYzJZQO3bskMlkUrVq1WIdc40aNfT999/rn3/+Ub58+ZQxY0Z16dJFderUUZUqVVS5cmUNGDDgqWsGEoq+hb4FCefUi0JK909J2LNnT5zHExNod+3aVdeuXdPIkSN15swZVa9eXWFhYapbt64sFouOHTum6dOnK2PGjPL399eHH36o6tWrO9oFAAAAAMAZ0qdPr6+//loFCxbUmDFj1KJFCwUHB2vOnDlx/v709vZ+6v3nypVLixYt0qxZs7R8+XItWLBAvr6+atGihXr37u1o49y5cwoKCtKuXbs0derUWPPk3r17V5988onWrFmj6Oho5cqVSyVLlpS7u7tjHtwHnTt3Tq+++mqsZZ999pkaNWqkwoULK126dNq/f78uXbqkqKgox2n/JpNJFStW1K5du3T37l0dOXJErVu3duxj69atGjVqlE6ePCmLxaKCBQs6npP46niSiRMnasaMGfrpp5+0YcMGubm5qVKlShoxYoRy5syZoH3cvHlTdrvdMTryYZcvX1ZgYKC++eYbTZ8+XT/99JOWLl0qT09PNWjQQEOGDHnkqE0gMehb6FvoWxLOaYF2SEiIs3YVy5QpU3T79m0tW7ZMkpQvXz6dPXtW7733nm7cuKE+ffooT548OnjwoE6fPq21a9dqyZIlz20+bzw/T3OBgfhYrdZYtx+8D2NI7HsAAAAASKwCBQqoYMGCku6PeOzcubOmTZumr776Sh07dnzstjGB0cPfa8PCwmLdL1asmKZOnaqoqCjt27dPS5cu1YwZM1SwYEHVrVtXkpQ/f37NnDlTkyZN0ty5c1W/fn0VLVpUkjRy5Eht2LBBkyZNUqVKlRxBT8WKFeOtK2vWrFq+fHmsZbly5ZJ0fzRluXLldOjQIZ09e1YFChSINWI0KChIQ4YM0Z49exQdHe2Yb/bMmTOOU/hnzpyp3Llzy2Qy6ZtvvtHWrVsf+zw9Srp06TRgwAANGDBAJ0+e1C+//KIvv/xSw4cP16xZsxK8D29vby1YsCDex1988UVJ96cBGDt2rKxWqw4fPqw1a9Zo8eLF8vf3V4cOHZ6pfuBx6FvoW+hbEs5pgXZSsNvtOnfuXKxfYS5cuKAWLVrozTff1Msvv6xp06YpIiJCVqtVISEhmjVrFmF2CnXgwIFEbf/gaScHDhzgly8AAAAAidatWzdt2bJFkydPjvf0/QfFzFF78eJF+fv7S5JOnDihmzdvOtaZP3++vv76a23YsEEeHh6qWLGiihQpop9++kkXLlxwrOfn5yd3d3d1795d69at05AhQ7RixQq5u7tr3759Kl++vGM+WOn+dAbXr1+Pd5CIh4eHI7CKT6VKlfTNN9/IYrEoKCgo1mOVK1fWvXv39N1336lQoULKmDGjo73IyEh16tTJcaySHIHT046iPH/+vFq0aKHBgwerTp06yps3r/LmzesY3PYoD1/orly5cpo7d67sdnus12rFihX6+eefNWrUKK1fv14ff/yxfvjhB2XJkkUlS5ZUyZIltXbtWsdr8PB+AWejb6FvwaMlKtBu3bq1hg0bpoCAgFihc3xMJpO+/vrrp9p/ZGSkQkJCVK5cOceyQ4cOqVWrVurUqZPu3LmjpUuXqmLFimrfvr2sVqvSp0//TMeC5O3B90BiPNxBAgAAAEBiuLu7a+zYsWrYsKH69u2r1atXx7q42oPKly8vT09PjR49Wu+//77CwsL0xRdfyM/Pz7FOhQoVNG7cOHXv3l3vvvuuzGazlixZIg8PD73yyitx9unl5aVhw4apU6dOmjNnjjp37qxixYrpp59+0uLFixUQEKCQkBBNnz5dJpNJERERT32MFStW1Keffiqz2ax+/frFeixLlizKnz+/fv31V7Vt29axvHDhwo7npl27doqKitLKlSu1adMmSY+/4F18cubMqezZs+vTTz9VaGio/P39deTIEW3evFmdO3d+5Ha+vr66evWqNm/erMDAQFWrVk1ly5ZVt27d1K1bNwUEBOjw4cP64osvVKVKFWXMmFGlSpWSzWZT9+7d1alTJ1ksFv3000+6c+eOatWq5divJP34448qXrw4A+vgdPQt9C30LY+WqED7wV89nvQLyLPMYePm5iZfX1+dOHHCsSzmFIgY3t7eKl269CM/1DA2s9nsuDos8CCz2ezqEgAAAABJUp48eTRw4EANHz5cw4YN0/jx4+Ndz9fXV1OmTNH48ePVvXt35cyZUz169NDq1asd6xQsWFAzZszQtGnT1LdvX1mtVhUpUkRz585V3rx5491vtWrVVLt2bU2bNk21a9fWoEGDdO/ePU2aNElRUVHKlSuXunbtquPHj+vXX3996ukXAwIClCVLFoWGhqp06dJxHg8KCtKxY8ccF22T7p9eP378eE2dOlVdu3ZV+vTpVaJECS1cuFCtWrXS3r17VaBAgaeqY+rUqZowYYImT56sGzdu6IUXXlCPHj3UqVOnR27TqFEjbd68Wd27d1evXr3UqVMnzZo1S5MnT9bMmTN17do1ZcuWTW3btnVc9ytr1qz66quvNHnyZH344YeKiIhQvnz5NGXKFMe0B7Vq1dKaNWs0aNAgNWnSRB9//PFTHQuQEPQt9C30LfEz2Z8laX6Ofv31V/Xr10+ffPKJXn/99ViPff3111qxYoVmz56tbNmyuajCR7NarTp48KAkqUSJEgRwQDKSEj6fD8+HBmPz8vJydQlwMqOdLvikfnH79u26du2aCypLnEyZMsX6IwgwKiN/dzFy7UBKZ+TPp5FrB1KDpPyMOu0vrdatW8caSf2gkJAQvfHGG8+036CgILVt21affPKJ5s6dq7Nnz+ro0aOaM2eOpk2bptGjRyfLMBsAAAAAAAAA4FyJmnJk7969jqlEdu/erT179uj69etx1vvtt9909uzZZ2rDw8NDHTt21AsvvKBJkyZp2bJl8vPzU+bMmbVw4cKnPo0AAAAAAAAAAGBMiQq0v/vuO61Zs0Ymk0kmk0nDhw+Ps05M4P3wdCFPw8vLS02bNlXNmjUVGhqqdOnSKW3atPL09HzmfQKA0TFFRcpitOkpAAAAAABwhUQF2kOGDFHjxo1lt9vVpk0bDR06VC+//HKsdWIu7JgvX75EFSpJfn5+sa7QCgAAAAAAAABIPRIVaKdLl07lypWTJC1YsECFChWSj4+PUwoDAAAAAABJ648//tCYMWN05MgRWSwWNWrUSD169JCHh8djt9u2bZsmTpyo48ePK1OmTGrZsqXatWsnk8nkWOf06dP67LPPtHfvXpnNZtWpU0cDBgyIlRucP39eY8aM0e7du2Wz2VS6dGkNGjRI/v7+jnVu3bqlCRMm6JdfflFYWJiKFSumfv36qVixYvHWFh0drebNm8vLy0sLFy5M5DME4Fm4sm9p1aqVdu/e/cg2/v777zjLfv31V3Xt2jXOYzabTfPmzdPSpUt18eJFvfTSS+rQoYPefPPNp3k64GSJCrQfVK5cOV26dElbtmxRVFSUY7nNZlNERIT27t2riRMnOqs5AAAAAACQCGfPnlXbtm1VokQJTZo0SSdOnNDEiRN18+ZNjRgx4pHbHTx4UF26dFHdunX1/vvva9++fRo7dqysVqs6deokSbp9+7batGmjzJkza/To0bp+/brGjh2rc+fOac6cOZKku3fvql27doqOjtZHH32ktGnT6osvvlCrVq30ww8/yNfXVzabTd26ddOZM2fUv39/ZcqUSfPnz1ebNm20atUqvfTSS3HqmzVrlv744w/HADwAz5er+5Zhw4YpNDQ01r7PnDmj4OBgNWvWLE67u3btUr9+/eKtafLkyZozZ4569eqlokWLavPmzRowYIDc3NwSNb0yEsdpgfb69evVv39/RUdHO341sdvtjtt58+Z1VlMAAAAAACCRZs+eLYvFoi+//FIeHh6qVq2aPD099cknn6hLly7KkSNHvNtNmTJFgYGBGjt2rCSpatWqio6O1owZM9S6dWt5enpq8eLFunnzplauXKmMGTNKkrJly6ZOnTpp3759Kl26tPbu3at///1X8+fPV8WKFSVJefLkUd26dfXLL7+oYcOG2rt3r/bu3auZM2eqevXqkqQyZcqoQoUKWrFiRZwQKiQkRDNnzlSWLFmS6FkD8CSu7lseng7ZarXq008/VcGCBfXhhx86loeGhmr27NmaPXu20qVLp/Dw8FjbRUREaMGCBWrVqpUjUK9YsaL+/PNPLVy4kEDbhZx2BaoZM2aocOHCWrlypRo1aqQGDRpo7dq1GjBggMxmsz744ANnNZXq3b5923Ehztu3b7u6HAAAAACAE9SoUUMTJ07UqFGjVLZsWZUvX14DBw7UzZs3H7nNrl27VKBAgUf+N2jQoEduu23bNlWrVi3WFAB16tSRzWbTtm3b4t0mKipKu3btUs2aNWMtr127tsLCwrRv3z7HvkuXLu0InCQpKChIFotFW7ZskSRFRkZKkiwWi2OdmOtmxRxzkSJFtGTJElWuXNmxTpo0aWQymRzbP1jbwIED1apVK+XJk+eRxw2kNqmtb3nYkiVL9Oeff2r48OGxalq+fLmWLVumoUOH6t13342znYeHhxYvXqx27drFWp4mTZo4/Q+eL6eN0D516pTGjx+vQoUKqXz58po7d64CAgIUEBCgq1evasaMGbH+AQIAAAAAALF9++23evHFF/XZZ5/p+vXrGj9+vE6fPq0lS5bEmkM2RuHChbV06dJH7u/B0OdBd+/e1fnz5+MEvxkzZpSPj49OnToV73Znz57VvXv34kz18eKLL0q6nw1UrlxZJ06cUL169WKtYzablStXLse+g4KCFBAQoLFjx2rUqFHy9PTUqFGj5O3trddee02S5O3trZIlS0q6Pzf2uXPnNGXKFNntdjVq1CjW/qdNm6bo6Gj16tVL7du3f+RzAqRGqalveVBYWJi++OILNWjQIM68+zVq1NDbb78tLy8vTZkyJc62ZrNZBQsWlHR/Fopr165p5cqV2r59+2OnTkHSc1qg7ebmpvTp00u6/2Y7efKkbDab3NzcVLVqVa1atcpZTQEAAAAAkCK5ublp3rx5SpcunaT7IVD37t21detWVa1aNc76Pj4+KlGixFO3c+fOHcf2D7NYLHHmn33SdjGjrGO2u3PnTqyR1/HtO23atBo5cqS6dOniCLA9PDw0Y8YM5c6dO862I0aMcARsvXr1cgRNknT48GHNnTtX33zzzRMvOgekRqmpb3nQihUrdPv2bXXu3DnOYw9efPZJ1q5d65jiqHr16lwU0sWcNuVI3rx5tX//fsftqKgohYSESLo/RcaDF4oEAAAAAABx1ahRwxE4xdx3d3fXnj174l3fbrcrOjr6kf/ZbLZ4t3vU8hjxjdhMyHZubm6Oup607927d6t169YqWLCgZs6cqdmzZ6tq1arq0aOH9u7dG2e7Jk2aaMGCBWrfvr2mTJmiSZMmSbo/dcmgQYPUpk2bOCMwAdyXmvqWB33zzTeqUaNGoqchKlasmBYtWqSPPvpI+/fvV4cOHR5bC5KW00ZoN2/eXMOGDVN4eLj69OmjChUqaPDgwWrSpIkWLVqkwoULO6spAAAAAABSpGzZssW67+bmpgwZMujWrVvxrh8TCj9Kw4YNNXr06DjLY0ZBhoWFxXksNDQ0VvD1oJjlD28XMzIyZr8+Pj6P3HfMMc6YMUPZsmXT7NmzHaOqg4KC1Lx5c40aNUorV66MtW1MWF2+fHnduHFDc+bMUffu3TVp0iTZbDZ169ZN0dHRkv4v9IqOjpbZbH5kiAakFqmpb4kREhKif//9V3369HnkcSSUv7+//P39VbZsWfn4+Cg4OFh79+5V2bJlE71vPD2nBdpNmzZVVFSUzp07J+n+qUCdOnXSyJEjlTNnzlhXEQUAAAAAAHHduHEj1n2r1aobN248cr7awoULa/ny5Y/cX4YMGeJdbrFYlC1bNp0+fTrW8mvXriksLEwBAQHxbufv7y+z2RxnuzNnzkiSY7s8efI4lj14LOfOnVOtWrUkSefPn1eRIkViTRHi5uam0qVL65tvvpEkHT9+XIcOHVLjxo3jHPfKlSt18+ZNbdiwQefPn3fMtf3wep999lmc+baB1CY19S0xNm3aJC8vL1WvXv2Rx/E4169f15YtW1SlShVlypTJsbxQoUKSpMuXLz/TfpF4Tgu0Jally5aO2/7+/vrpp58e++EAAAAAAAD/Z8uWLYqKinKEvL/88ouio6NVsWLFeNf38fFR0aJFn6mtypUra9OmTRo8eLCjvQ0bNshsNqtChQrxbpM2bVqVKVNGP//8s9q3b+8Y+bxhwwalS5fOMYq6cuXKmjNnjq5fv+7IBLZt26bw8HBVrlxZ0v3pSg8fPhzreO12uw4cOOCYQ/vIkSP64IMPlDdv3liB9bZt25QlSxZlypRJ06dPjzPN6bBhwyRJw4cPV65cuZ7p+QFSktTUt8Q4ePCgChUqJE9Pz2c6jrt37yo4OFh9+/aNNQf377//LkkqUKDAM+0XiefUQFuSTpw4od9//12XL19Wq1atdPbsWXl4eMQ7GTwAAAAAAPg///33n7p27arWrVvrv//+04QJE1SlShWVL1/e6W116NBBa9euVYcOHdS2bVv9+++/mjBhgpo1a6YcOXJIkqKiovTXX38pe/bsyp49uySpa9euatu2rd5//301btxYBw4c0Jw5c9SvXz95eXlJklq0aKFFixapbdu26tGjh27evKmxY8eqatWqKlWqlCSpW7duatGihTp06KA2bdrI3d1dK1as0MGDB/XFF19IkmrXru3Y9/vvv6+MGTPqhx9+0G+//abPP/9cbm5u8YZKMReNe9ZADkhpUlPfEuPYsWMKCgp65uPIkSOHGjdurGnTpsnd3V2FChXS3r17NWvWLDVp0kQvv/zyM+8bieO0QNtms2no0KFasWKF7Ha7TCaT6tatqy+//FKnT5/WN99843iDAgAAAACAuOrXry9fX1/17t1b3t7eatiwoVPmf41PQECA5s6dqzFjxqhXr17KkCGD3nvvPfXq1cuxzuXLl/X222+rR48e6tmzpySpYsWKmjJlir744gt1795d2bJl08CBA9WuXTvHdhkzZtSCBQs0atQo9e/fXxaLRXXq1NHAgQMd6xQtWlSLFi3S5MmT1b9/f6VJk0YFChTQggULVK5cOUmSl5eX5s2bp4kTJ2rcuHG6efOmChQooC+//FKvvvpqkjwvQEqUmvqWGNeuXZOvr2+ijuXjjz9W7ty5tWzZMp0/f14vvPCCevXqpfbt2ydqv0gck91Jl+ScOnWqZs+eraFDh6p69eqqXLmyVqxYITc3N3Xv3l1ly5bV559/7oymDMNqtergwYOSpBIlSshsNjtlvzdv3nTMVXTjxg35+fk5Zb9AapJUn8/n6UlXgYaxxFy1G3CVJ/WL27dv17Vr11xQWeJkypRJlSpVcnUZQKIZ+buLkWt/3mrUqKFy5crFe6E1ICkY+fNp5NqfN/oWuEJSfkad9tfzihUr1KtXLzVu3DhWwBoYGKhevXo55pdB4j34x6QR/7AEAAAAAAAAgGfhtED76tWrCgwMjPexbNmy6fbt285qCgAAAAAAAACQCjltDu0XX3xRmzdvjveUzt27d+vFF190VlMAAAAAAKQ4v/76q6tLAJAC0bcgpXFaoN2mTRsNHTpU9+7d0yuvvCKTyaTTp09r165dmjt3rgYNGuSspgAAAAAAAAAAqZDTAu2mTZvq+vXrmj59ur799ltJUt++fZUmTRp16NBB77zzjrOaAgAAAAAAAACkQk4LtCWpc+fOatmypQ4cOKCbN2/K19dXxYsXj3WRSAAAnsb8+fP1999/67PPPnN1KUikQ4cOadiwYfr3339VqFAhjR49Wv7+/q4uCwAAAABgIIkKtAcPHvzEddavXy9JMplMGjVqVGKaAwCkIlarVXPnztWkSZP05ptvurocJFJkZKS6d++uQYMGqVatWpo1a5Z69+6tlStXuro0AAAAAICBJCrQ3rVrV5xl//33nzJnzqw0adLEWm4ymRLTFAAglRk8eLBu376tpk2bKjIy0tXlIJF27twpPz8/vf7665Kkrl276uuvv9bx48f18ssvu7g6AAAAAIBRJCrQfvgqqdHR0SpSpIhmzJihwoULJ6qwpGSz2eTm5ubqMgAAj9G/f39lzZpVU6dO1fnz511dDhLp1KlTyps3r+O+2WxW7ty5dfLkSQJtAAAAAECCOTXVNcoo7Jgwe/To0QoJCXFxNQCA+GTNmtXVJcCJwsPD5enpGWuZl5eXIiIiXFQRAAAAAMCIUu0w5TNnzujEiRO6dOmSpPtztQIAgKTh5eWlu3fvxloWEREhi8XioooAAAAAAEaUagLthwNrf39/BQYGauzYsbJarTKbzS6qDACAlC9v3rz6999/HfetVqvOnDmjPHnyuK4oAAAAAIDhpJpA22w2y2azad26dTp16pQkqW/fvvL399d3333n4uoAAEjZypcvr2vXrmn16tWKiorS9OnT5e/vr4CAAFeXBgAAAAAwkCQJtJPTXNoPjsw+ePCgxo4dq3HjxmnkyJEKDw9XoUKFdPLkSRdWCABAyufp6amZM2dq4cKFKl++vLZv365Jkya5uiwAAAAAgMG4J2bjGjVqxBted+nSRWnSpIm1zGQyaePGjYlp7qlFR0fL3d1ddrtdR48eVb58+bRhwwbt27dPY8aM0UcffaQMGTJo6dKlKlGihOrVq/dc6wMAPFmPHj1cXQKcpEiRIlqxYoWrywAAAAAAGFiiAu1y5colq9HYD7LZbHJ3d5fNZlPTpk1lMpl0584d9ezZU6+//rpWrVqlZcuW6fr167p3755+//13vfbaa/Lw8HB16QAAAAAAAACAeCQq0B49erSz6nA6Nzc32e12tWvXTvnz51enTp20cOFCjR49WpGRkWrcuLGaNWsmScqXL5/y589PmA0AAAAAAAAAyViiAu3kyGq1ymw2S5JOnTql27dva/78+Y7Hy5Ytq6lTp8rLy8sxxcirr77qilIBAAAAAAAAAE8hSS4K6So2m01ms1k2m02LFi1SVFSUsmbNqtDQUA0cOFDnzp3Thx9+qFy5cqlv376aM2eOq0sGAAAAAAAAACRQihqhHTPNSKdOnZQrVy699dZbGjFihE6fPq2//vpLq1atUpo0aZQ/f35VrlxZ1atXd3XJAAAAAAAAAIAEShGB9p07dxQZGSkvLy8tXbpUly9f1scffywfHx/5+Pjo1q1byp49u3bt2qVTp05pw4YNWrlypbJmzerq0gEAAAAAAAAACWT4QHv48OG6dOmSzp49q1atWun27duy2WyaM2eOevbsqYwZMypdunRyd3fX119/rRMnTmjmzJmGDrMzZcoU720AAAAAAAAASMkMHWh37dpV165d08iRI/Xvv/+qZs2aunPnji5duiRJWr16tRo2bKjs2bNr5MiRjgtGGj0EdnNzi/c2AAAAAAAAAKRkhg20p0yZotu3b2vZsmWSpHz58uns2bPq1KmTrly5oqJFi8rNzU2rV69WgwYNDB9iAwAAAAAAAEBqZ8hA226369y5c2rdurVj2YULF9SiRQu9/vrrKlKkiCZOnChPT0/9999/Sps2rd555x2ZTCYXVg0AAAAAAAAASAxDzlcRGRmpkJAQhYaGOpYdOnRIrVq1UnBwsKpVqyY/Pz8FBgaqWrVqeuWVVwizAQAAAAAAAMDgDDlC283NTb6+vjpx4oRjWd26dR237Xa7fH19VbFiRZUtW9YVJQIAAAAAAAAAnMyQI7Q9PDzUtm1bLV68WD/++GOcx1euXKmrV6/K39/fBdUBAAAAAAAAAJKCIUdoS1JQUJDatm2rTz75RJcvX1bNmjUVGhqq7du3a+bMmZo/f76yZcvm6jIBAAAAAAAAAE5i2EDbw8NDHTt21AsvvKBJkyZp2bJl8vPzU+bMmbVw4UIVKFDA1SUCAAAAAAAAAJzIsIG2JHl5ealp06aO0dnp0qVT2rRp5enp6erSAAAAAAAAAABOZuhAO4afn5/8/PxcXcZz4+vrK7vd7uoyAAAAAAAAAOC5MuRFIQEAAAAAAAAAqQ+BNgAAAAAAAADAEAi0AQAAAAAAAACGQKANAAAAAAAAADCEFHFRSAAAjM5ms7m6BDiZmxvjBgAAAADA2fhLCwAAAAAAAABgCATaAAAAAAAAAABDYMoRGJ7Vao2zzGw2u6ASAAAAAAAAAEmJQBuGZrVatW7dujjL69WrR6gNAAAAAAAApDBMOYIUYdu2bXrzzTf15ptv6u7du64uBwAAAAAAAEASINAGAAAAAAAAABgCgTYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAAAAAAAAAAyBQBsAAAAAAAAAYAgE2jAsu90uu93+1I8BAAAAAAAAMCYCbRiS3W5XUFCQqlWrFie4ttvtqlq1qqpUqUKoDQAAAAAAAKQg7q4uAHgW4eHh2r59uyQpMjIy1mORkZHasWOHYz2LxfLc6wMAAAAAAADgfIzQBgAAAAAAAAAYAoE2AAAAAAAAAMAQCLQBAAAAAAAAAIZAoA0AAAAAAAAAMAQCbQBAsjZ//nwNHjzY1WXASXg9AQAAAACJQaANAEiWrFarZs+erbFjx7q6FDgBrycAAAAAwBncXV2AK0yePFnFixdX9erVXV0KAOARBg8erNu3b6tp06aKjIx0dTlIJF5PAAAAAIAzpLoR2jdv3tTFixe1b98+RUREuLocOMHdu3dj3ScoAVKG/v37a8aMGcqcObOrS4ET8HoCAAAAAJwh1QXafn5+qlq1qjZv3qzTp09Lkmw2m4urQmK0bt061v2OHTu6qBIAzpQ1a1ZXlwAn4vUEAAAAADhDqgm0//jjD8ftunXrqkyZMgoODlZ4eLjc3FLN0wAAAAAAAAAAhpUqktwvvvhCTZs21axZs7R27VpJ0kcffaQCBQpo+fLljNA2uAULFsS6P3v2bBdVAgAAAAAAACAppYpAO+Y058uXL2vjxo3q3bu3bt68qaJFi+rcuXOOubQJto3J09Mz1v20adO6qBIAAAAAAAAASSlVBNrNmzfXO++8o6ioKPXs2VM3b97URx99pPDwcG3cuFFLly6VJKYeAQAAAAAAAIBkzN3VBSSVBQsWqEiRIipVqpQkqWbNmlq3bp18fHw0f/58LVy4UHfu3JHZbNb06dNVokQJx7oAgOSjR48eri4BTsTrCQAAAABIjBQ5JPnEiRPav3+/OnbsqCVLlujmzZsqU6aMQkNDNXPmTElSq1at9O6776p79+568cUXlTNnThdXDQAAAAAAAAB4nBQ5QjsgIEDjx4/X+vXrNX36dP3111+qUaOGRowYoZYtW2rt2rWqX7++fH199dZbb6lWrVry9vZ2ddkAAAAAAAAAgMdIUYG21WqV2WyWJJlMJtWvX18FCxbUli1bNGPGDOXPn1/NmjXTkSNH9Morr8jT01Nubm7y8vJyceUAAAAAAAAAgCdJMVOOxMyHbbfb1a9fP3Xu3Fnff/+9cubMqbZt22rq1Kn677//tGLFCs2bN09Hjx51XATSZDK5uHoAAAAAAAAAwJOkiBHa48aN0+3bt/X+++9rwIABSpcunV5++WXNnTtX169fV926dZUtWzbNnj1bGzZs0Nq1a+Xn5+fqsgEAAAAAAAAAT8HQgbbNZpObm5uqV6+uDz/8UGPHjlWWLFn0+eefS5JWrVqlZcuWSZLq1Kmj7Nmzq3bt2nr11Vfl7m7oQ0/1vL29VblyZdntdqVNmzbWY2nTplWlSpVkMpmYGx0AAAAAAABIQQw75ci9e/c0atQoXbp0SWXKlNG8efN05MgRbd68WSEhIZKkhg0bqkmTJvrll1+0evVqXb58WZIIs1MAk8mkrVu3avPmzXGmjDGZTNq8ebO2bt3KdDIAAAAAAABACmLYQNtut0uS2rZtq8qVKys0NFRjx45V+vTptXbtWl25ckWS1LhxY9WtW1f79u2Th4eHK0uGk5lMpkcG1o97DAAAAAAAAIAxGTbQlu6H2bdu3VJ4eLgyZsyowMBAjR07Vv/73/80d+5cXbt2TZLUokULTZgwgXmzAQAAAAAAAMDADDf3xtSpU3Xp0iUdPHhQOXLkULp06dSoUSO1bdtW48aNU7FixTR27FgNGjRIYWFhev/995UpUyb5+Pi4unQAAAAkc7t27ZLVanV1GU/NbDarfPnyri4DAAAASHKGCrS7dOmi27dvq02bNsqXL59u376tLVu26M6dOypevLj69OmjyZMnq1ixYhozZoyGDx/umJqE6ScAAADwJFar1XGWn5FkypTJ1SUAAAAAz4VhAu2JEyfq6tWrWr58eazlgYGB6t69u3r27Kn69eurR48eCgoKUuHChfXtt98qTZo0LqoYAAAAAAAAAOBMhphD22az6fz58+rUqZMkKSoqyrH81VdfVd++ffXjjz+qTp06qlu3rvbv3698+fIRZgMAAAAAAABACmKIQDsyMlLHjx93zGfo7n5/YLmb2/3yS5curcjISPn4+Kh3795avHixihYt6rJ6AQAAAAAAAADOZ4hA283NTV5eXvrnn38c9202myPg9vHxUdasWZU2bVpJkqenp8tqBQAAAAAAAAAkDUPMoZ02bVq99957GjRokPLmzavXX3/dMTpbkjZv3iwfHx95eHi4sEq4UlBQkIKCglxdBgAAAAAAAIAkZIhAW5JeeeUVtWnTRsOHD9fFixf12muvKTo6Wr/99ptmz56thQsXytvb29Vl4jkzm82qV69evMsBAACAXbt2Oc7sNAqz2azy5cu7ugwAAIBkyTCBtoeHhzp16qQcOXJo8uTJ+u6775Q+fXr5+Pho4cKFKliwoKtLhIsQXgMAAOBRrFarrl275uoynkqmTJlcXQIAAECyZZhAW5K8vb3VrFkz1apVS6GhofLy8pKnp6csFourS4uX3W533DbaqBAgpXvwM/ngZxUAUquEfG8xmUzPqxynetrvYanhOPfu3WvI76dms1llypR56u2M+Jo+/PoY+bsLfxcByRd9C4CkkpT9i8lutB7LQKKiovTHH3+4ugwAT1C0aFFDzsFvs9lcXQKAx3jweh9GwPcWwDiM9t2F/gUwBvoWAEnF2f2LoUZoAwD+j9HCMgAAAAAAgMRihHYSstlsio6OlnQ/eDLiqY5ASmW32x0jnN3d3QmHAaR6fG8Bkjcjf3ehfwGSL/oWAEklKfsXAm0AAAAAAAAAgCEY56c3AAAAAAAAAECqRqANAAAAAAAAADAEAm0AAAAAAAAAgCEQaAMAAAAAAAAADIFAGwAAAAAAAABgCATaAAAAAAAAAABDINAGAAAAAAAAABgCgTYAAAAAAAAAwBAItAEAAAAAAAAAhkCgDQAAAAAAAAAwBAJtAAAAAAAAAIAhEGgDAAAAAAAAAAyBQBsAAAAAAAAAYAgE2gAAAAAAAAAAQyDQBgAAAAAAAAAYAoE2AAAAAAAAAMAQCLQBAAAAAAAAAIZAoA0AAAAAAAAAMAQCbQAAAAAAAACAIRBoAwAAAAAAAAAMgUAbAAAAAAAAAGAIBNoAAAAAAAAAAEMg0AYAAAAAAAAAGAKBNgAAAAAAAADAEAi0AQAAAAAAAACGQKD9HP3777+qWbPmY9c5ffq03n33XbVo0ULdunVTaGjoc6oOAAAAAAAAAJI3Au3n5JtvvlHfvn1148aNx643btw4dezYUd9++60KFiyob7/99jlVCAAAAAAAAADJm7urC0gtMmfOrG+//VZBQUGSpNDQUA0ZMkRXr15VdHS0evXqpUqVKmny5MkymUyy2Wz677//VLRoURdXDgAAAAAAAADJA4H2c1K7du1Y92fMmKHChQurY8eOunnzpt5++2398MMP8vDw0M2bN9W8eXOFhYWpc+fOLqoYAAAAAAAAAJIXAm0XOXbsmK5evaotW7Y4ll26dEm5c+eWn5+f1q9frz179uj999/XmjVrXFgpAAAAAAAAACQPzKHtIgEBAWrevLkWLlyor776SrVr11a2bNnUpUsXhYSESJIsFovc3HiJAAAAAAAAAEBihLbLdOnSRR999JF++OEH3b59W82aNZOHh4e6dOmijz/+WGnSpJHJZNJnn33m6lIBAAAAAAAAIFkw2e12u6uLAAAAAAAAAADgSZjPAgAAAAAAAABgCATaAAAAAAAAAABDINAGAAAAAAAAABgCF4VMQjabTdHR0ZIkNzc3mUwmF1cEIIbdbpfNZpMkubu7y83NOL/v0bcAyZtR+xf6FiB5M2rfItG/AMkZfQuApJKU/QuBdhKKjo7WH3/84eoyADxB0aJF5eHh4eoyEoy+BTAOI/Uv9C2AcRipb5HoXwCjoG8BkFSc3b8Y56c3AAAAAAAAAECqxgjtJPTgUPqiRYvKbDa7sBoAD7JarY5f8410Wp1E3wIkd0btX+hbgOTNqH2LRP8CJGf0LQCSSlL2LwTaSejB+ZvMZjOdK5BMGW2uNfoWwDiM1L/QtwDGYaS+RaJ/AYyCvgVAUnF2/2Ksn98AAAAAAAAAAKkWgTZSlVu3bunSpUuy2+2uLgUAAAAAAADAU2LKEaQKJ06c0JgxY5QhQwZZLBb9+++/atSokerXr+/q0gA8QlhYmM6cOaPw8HB5e3vL399fFovF1WUBAAAAAAAXItBGinfjxg0NHz5c06dPd4Rhdrtdn376qby9vfXKK6+4uEIADzt79qwOHToU62yKEydOqHjx4sqdO7cLKwMAAAAAAK5EoI0Ub/78+Ro4cGCskZ0mk0kffPCBunTpQqANJDNhYWGOMDtLlizKkiWLrly5oitXrujQoUPKmDEjI7UBJAt2u13h4eFJtn9vb2/DXaALAAAASGoE2kjxTp06pSJFisRZbjab5eXl5YKKADzOmTNnHGF2hQoVJEkBAQHauXOnrly5ojNnzigwMNDFVQJI7ex2u4KCgrR9+/Yka6Ny5craunUroTYAAADwAAJtpHhp06bV7du35evrG+exyMhIF1QE4HFiRjtmyZIl1vKYkdoRERGuKAsA4iBoBozvhx9+eC7tvPHGG8+lHSllHhMAAA8i0EaK984772j69OkKDg6OtfzAgQPKkyePi6oC8Cje3t6SpCtXriggIMCx/MqVK5LEmRUAkgWTyaStW7cmeMqRsLAwZcuWTZJ06dKlBE2dxJQjAAAAQFwE2kjxSpUqpd9//11DhgxRu3bt5OvrqzVr1mj37t2aMmWKq8sD8BB/f3+dOHFCV65c0c6dO2PNoW0ymeTv7+/qEgFA0v1Q+1nm9LdYLFwLAAAAAHhGBNpIFXr27KnTp09r2bJlCgsLU+3atdWuXTtGPQHJkMViUfHixXXo0CFHkC3dD46KFy9OCAQAAAAAQCpGoI1U48UXX9SAAQNcXQaABMidO7cyZsyoM2fOKCIiQl5eXvL39yfMBgAAAAAglSPQBgAkSxaLRYGBga4uAwAAwGXCwsJ0+fJl3bx5U5JkNpuVPXt2Zc6cWW5ubq4tDgAAF0kVgfa8efP0999/a/To0XEes1qtGj9+vFauXCm73a4333xTgwcP5ssBAAAAAOC5sNvtOnbsmLZu3aqDBw/qzz//1JEjR3T16tV410+bNq1KlSqloKAgvfHGGwoKCmI6RQBAqpGiA22r1ao5c+Zo4sSJatCgQbzrzJ07V3v27NG6deskSW3atNHq1avVqFGj51kqAAAAACAVuXr1qtauXau1a9dq8+bNunz5coK3jYyM1I4dO7Rjxw6NHTtW+fLlU7du3dS1a9ckrBgAgOQhRQfawcHBunPnjpo2baqoqKh41/nuu+80cuRIZcyYUZI0c+ZMmc3m51kmgAQ6ceKEjh8/rpdfflkBAQGuLgcAAAB4KmfOnNHSpUv1/fffa/v27bLZbHHWsVgsKlSokAoXLqz8+fMre/bs8vPzk5ubm6KiovTff//p+PHj2r59uw4cOCCbzaZ//vlHffr00aRJk9SsWTNGbAMAUrQUHWgPHDhQWbNm1ZQpU3T+/Pk4j4eFhen06dP6999/NWTIEEVERKhJkybq2bOn02s5evQoXyhSOLvdzmucRG7duqVJkyYpR44cyp8/v9avX6/z58+rd+/eSp8+/TPt0263O7lKOFtYWJjOnDmj8PBweXt7c1FIAABgSHfv3tXXX3+tr7/+Wr/99lucxzNkyKDXXntN1apVU5UqVVSkSJEET4F5+fJlffPNN5o+fbr++ecfnT59WmPHjtXu3bvVtWtXeXt7O/twAABwuRQdaGfNmvWxj9+5c0eS9PPPP2vp0qUKDQ1V+/btlStXLqYcQYJcv35dc+bMUUREhNzd3RUZGakmTZro/7F333E19///wB/ntIcWshKFi6wKl0S2LiN7bxJJZZOVUBRZGaFSxkfWZV72vLhy4cpKRlbKVshoj9P5/eHnfK9zVYTq3anH/XZzu9XrvR6HOs55ntf7+WrQoIHQ0UoUPz8/ODk5oUKFCgCA1q1b482bN1ixYgUWLFggcDoqDM+ePcM///yD+Ph4pKenQ01NDYaGhrCyskLVqlWFjkdEBYQfXBFRSZaQkIAjR47g2LFjSEpKkttWuXJlNG3aFE2bNoWZmZnsLuEnT57gyZMn33WdmjVrwtfXF6dOnUJoaCg+fvyI8+fP4/79+/Dw8ICRkVGBPSYiIqLioEQXtL9FRUUFAODo6Ag9PT3o6elh4MCB+PPPPwu8oP3vFylUMiQnJ8Pb2xsrVqyQFVqzsrLg5uaGmjVrokmTJgInLBkePHiAJk2aoF27djm2Xbt2DWKxGGZmZt99XolEgoiIiAJISAUtOTkZp0+fRkxMDMqUKQNdXV18/PgRkZGRSExMRP/+/VnwIioBnj17hps3b8rdMRMdHQ1zc3PBPriSSCRFcm6JRFJo1+LrTSLhvXv3Djt27MDZs2eRlZUlG9fV1UWbNm3Qtm1bmJqaFug1lZSU0KlTJ1hZWWHVqlW4fv06Xr9+jRkzZsDDwwO1a9cu0OsREREJqVQXtA0MDKCjoyObqQ18foPBVgSUl9jYWDx8+BCmpqY4e/YsJkyYICtmA4CysjIWL16MCRMmsKBdQO7fvw8LC4tct1lYWODBgwc/VNCm4uvevXuyYnbLli1Rvnx5vHnzBmFhYYiJicG9e/fQuHFjoWMS0U9ITk6WFbPLly8v+z1/8+YNbt68CQMDgyL/4EoikcgWCS8MaWlpsq9PnDgBdXX1QrlOly5dWNQmEkh6ejr27NmD/fv3y63hVKdOHfTs2RNNmzaFsnLhvgXX19eHh4cHdu/eje3btyMxMRHu7u6YP38+6tWrV6jXJiIiKiqluqAtEonQvXt3hISEoFGjRkhKSsLOnTsxYcIEoaNRMfPp0yfMmjULlSpVgrm5Ofbs2YP//e9/OHfuXI59VVVVZbP/6efVqFEDJ06cwG+//ZZj2+3bt3OduU2KLSYmBlKpFCYmJmjWrBmAzz8Hz58/x82bNxEbG8uCNpGCe/r0KaRSKbS1taGrq4sPHz5AV1cXqampSEpKwtOnTwX7sDI8PLzQzu3u7g4AiIyMLJTzN23atFDOS0TfdufOHaxdu1Zu7aZff/0Vffv2LfLnM7FYjIEDB0JPTw/r169Heno6Fi5ciMWLF6NatWpFmoWIiKgwlMqCtqWlJYKCgtCkSRPMmDEDvr6+sLOzQ1ZWFoYMGYLu3bsLHZGKmZkzZ2LmzJkwNjYGAHTr1g3R0dGYNm0aNm/enGP/zMzMIk5YctWtWxcrVqzA27dvUa5cOdn4u3fvcPPmTUycOFHAdERE9CNSUlLw5s0bvH79Wq6v7OvXr6GkpIQqVaoImO7za8X8LshWHGRnZ+PGjRtCxyAqlSQSCXbt2oVdu3bJ7vStUaMGHBwcUL9+fUGzderUCSoqKli1ahWSk5Mxf/58+Pr6onz58oLmIiIi+lmloqA9fvx4ue///YJfVVUV7u7ushkzRP8VExODKlWqyIrZXwwbNgxr1qxBZGQkGjZsKBt//PixXOGVfp63tzfc3NzQqFEjmJubIzIyElevXsXixYuFjkaFwMTEBJGRkYiJicHly5dlrQhiYmIgEolQvXp1oSOWaFKpFCkpKULH+GGampoQiURCx6B8iI2NRZkyZdCgQQPZ7/m9e/eQmJgIc3NzQbOJxWK27SCib0pKSsLSpUtl7y9VVVVlE6SKy3NI+/bt8eHDB2zZsgXv3r3DkiVL4OPjwztKiYhIoZWKgjbRz3jw4EGub6xtbGwQEhICPz8/rF69Gpqamjh58iRCQ0Oxbt06AZKWXIaGhggJCUFERAQePnyIFi1awMXFRehYVEjq1KkjK2iHhYXJFoVMTEyEiYkJ6tSpI3TEEksqlcLGxgYXL14UOsoPa9GiBcLCwljUJiKiQvXu3TvMnz8fT548AQAYGRnJ3dFZnPTu3Rvx8fE4duwYHjx4gJCQEIwdO1boWERERD+MBW2ibzA1NcX+/fvRtWtXuXGRSAQrKytoaGhgwYIFSE9PlxW5OeOhcFhYWOS5QCSVHFpaWujQoQP++ecfxMfHIyUlBVpaWjAxMYGVlVWRLxRX2rAQTEWlevXqkEgkssUgAUBPTw9ly5blzyERFWuvX7+Gu7s74uPjAQDW1taYOHEiNDU1BU6WO5FIhNGjRyM6OhoPHjzAkSNHULduXbRs2VLoaERERD+EBW2ib6hVqxYePXqE+Ph4GBoaysY/fPiAy5cvY9OmTXzjTVTAqlatCgMDAzx9+hSpqanQ0NCAsbExi9mFTCQSISwsrNBajiQnJ6NChQoAgLi4uEL592TLEcWgqamJ8uXLQ1tbGxUrVpT9nmtrayMpKQkaGhpCRyQiylVCQgLmzp0rK2Z36tQJY8eOLTYtRvKioqICNzc3TJ48GYmJiVi/fj3q1asHAwMDoaMRERF9Nxa0ifLB29sbM2bMgKWlJSwtLXH79m1cunQJixYtYuGEqJBoaWnBzMxM6BiljkgkKpIPDrS0tPgBRSlmbGyM6OhoJCUl4ePHj7Ie2klJSRCJRMXyln0ioqSkJMyfPx9xcXEAPrfyGDFihMK8HzA0NISrqyt8fHyQlJSEdevWYc6cOQqTn4iI6AvFWb6dSEDlypVDcHAwbGxs8Pz5czRu3BibNm1ClSpVhI5GRESkcLS0tGBubg6RSIQ3b97g7t27ePPmDUQiEczNzflhBxEVOxKJBL6+voiNjQUAdOzYUaGK2V9YW1ujVatWAIDw8HCcO3dO2EBEREQ/gDO0ib4DezgTEREVDLYWIiJFsmPHDkRERAAAmjVrBicnJ4UrZn/h6OiIyMhIfPjwAcHBwfj111+hra0tdCwiIqJ84wxtIiIiIhLEl9ZCjRo1gpmZGYvZRFQshYeHY/fu3QA+fxg3efLkYt8z+2t0dHTg6OgIAPj06RNCQ0MFTkRERPR9WNAmIiIiIiIiysX79++xatUqAICGhgZmzZpVIhaubdGiBRo2bAgAOHbsGGJiYgRORERElH8saBMRERERERH9h1Qqxfr165GYmAgAcHV1hZGRkcCpCoZIJIKjoyOUlJSQnZ2NgIAASKVSoWMRERHlCwvaRERERERERP/x119/4fLlywA+z2hu2bKlwIkKlrGxMbp27QoAuHv3Lq5cuSJwIiIiovxhQZuIiIiIiIjoX5KSkhAYGAgA0NXVhZOTk8CJCseAAQNk6xds2bIFEolE4ERERETfxoI2ERERERER0b9s375d1mpk7Nix0NXVFThR4dDW1ka/fv0AAM+ePcPZs2cFTkRERPRtLGgTERERERER/X9PnjzB0aNHAQANGjRAixYtBE5UuOzs7FCuXDkAnwv5GRkZAiciIiL6Oha0iYiIiIiIiPB5IciNGzciOzsbYrEYY8aMgUgkEjpWoVJTU8OgQYMAAO/evcPp06cFTkRERPR1LGgTUQ5c4ZyIiIiISqOIiAjcvHkTANCpUydUr15d2EBFpG3btqhQoQIAYM+ePcjMzBQ4ERERUd6UhQ5ARIVDKpXi/v37yMzMRN26daGkpPTNY/bu3YujR49CS0sLaWlpMDY2hpubG1RVVYsgMRERERGRcKRSKbZt2wYA0NDQkM1aLg2UlZXRt29f+Pv74+3btzh79iw6duwodCwiIqJccYY2UQl04cIFjBo1CidOnMDff/8NJycn7N2796vHbNmyBW/fvsXGjRuxevVqBAYGomvXrpg0aVLRhCYiIiIiEtCVZlTQyAABAABJREFUK1fw8OFDAEC3bt1K7EKQeWnXrp2sl/aePXuQlZUlcCIiIqLccYY2UQkTHR2NXbt2ITg4GGLx/31m5e3tjbCwMLRs2TLHMVlZWbh48SICAgLkxi0sLGBmZoYbN27A0tKy0LMTEVHJIJVKkZKSUmjn19TULPE9bYmoaGVnZyM0NBQAoKWlhZ49ewobSAAqKiro27cvNmzYgLi4OJw/fx7t27cXOhYREVEOnKFNPyU9PR2nTp3C0aNHkZiYKHQcAhAcHIy5c+fKFbMBYPr06di+fXuux0RHR6N+/fq5brOzs8Off/5Z4DmJiKhkkkqlsLGxgba2dqH9admyJdd7IKICdfXqVcTExAAAevToAW1tbYETCaNDhw4wMDAAAPz++++QSCQCJyIiIsqJBW36Yfv27YOrqysSExMhlUoxZ84c+Pv7Cx2r1EtOToahoWGOcRUVlTx7YZcpUwbv37/PdVtCQgJ0dHQKNCMREZVsnD1NRIpm3759AD7fAdKtWzeB0whHVVUVvXr1AgC8fPkSly5dEjgRERFRTmw5Qj8kMjIS169fR1BQkGzMzs4OQUFBOHz4MLp27SpgutJNJBIhNTUVGhoacuNSqRRpaWm5HlO5cmU8e/YMKSkp0NTUlNu2efNmeHp6FlpeUnyF3VqgMLFtAVHBE4lECAsLy9fzQnJyMipUqAAAiIuLg5aWVr6uwd9dIipI9+7dw927dwEAnTp1yvdzUUnVqVMn7N69G4mJiThw4ABatGjB51wiIipWWNCmH7J161bMnTs3x7iDgwOcnZ1Z0BbQgAEDsG7dOkydOlVu/MCBA2jVqlWex7m5ucHJyQmTJk1Co0aN8OrVK/j5+cHGxkZ22yHRf31pLXDx4kWho/yQFi1aICwsjG/SiAqYSCT67oKQlpZWqS8iEZEw9u/fDwBQVlYu1bOzv1BTU0Pnzp2xe/duPHjwAFFRUahbt67QsYiIiGRKRcuRTZs2YebMmV/dRyqVYtiwYVizZk0RpVJsmZmZua76LRaLoaamJkAi+sLa2hpaWlqYMmUKwsPDcfPmTcybNw8REREYPHhwnsfVqlULa9euxaVLlzBhwgRs2LABjo6OGDhwYBGmJ0XEYjAREREpqpcvX+Ly5csAgNatW6Ns2bICJyoe7OzsoKz8ef7bgQMHhA1DRET0HyV6hrZEIkFwcDBWrlyJHj16fHXfLVu24OrVq2jatGkRpVNsKioq+PjxY46itkQiybOtBRWu7OxshIWFIS4uDra2tujTpw8OHz6MzMxMODg4wNjY+Jvn0NHRgYuLSxGkpZLie1oLfK8fbUXwPdi2gIiIqHQ7cuSIbJHZL72jCdDX10ebNm1w+vRp/PPPP3j58iUqV64sdCwiIiIAJbygPWPGDCQmJqJfv37IyMjIc7+YmBjs3r0btra2RZhOsY0YMQK+vr5YtGiR3HhwcDC6d+8uUKrS69atW/D19UWnTp1QrVo17Nq1C69fv4avry/U1dWFjkcl3I+0FvhebEVAREREBS05ORlnz54FAJibm+drAkhp0rNnT5w+fRpSqRR//PEHnJychI5EREQEoIQXtN3c3GBoaIg1a9bgxYsXue4jkUgwa9YszJ07FwcPHiy0LFFRUSVqFqBYLIahoSH69u0LGxsbqKio4OLFizA1NUWLFi1w584doSOWGunp6Zg3bx68vLygoqICAOjRoweio6Ph6uqKyZMnC5ywePoyE4eIiIiISqcdO3YgOTkZANClSxeB0xQ/xsbGaNSoEa5fv47Tp09j8ODB0NHREToWERFRye6hbWho+M19goOD8csvv8Da2roIEpUsHTp0gLu7O7S1taGkpIRJkyax37IAzpw5g169esmK2V/UqFED6enphdIKgoiIiIhIkUmlUvj7+wMAypUrx9aTeejZsycAICMjAydOnBA2DBER0f9Xomdof8vDhw+xd+9e7N27t9CvZWZmBiUlpUK/jhAsLCyEjlCqHThwAHZ2drJew//WqFEjlC9fHtWrVy/6YMWcRCJBRESE0DGIiIiISAD//POP7LVgx44dS+x7tZ9lbm6OatWq4cmTJzh27Bh69+7NvysiIhJciZ6h/S2nT59GfHw82rRpgyZNmuDw4cMIDAzE2LFjhY5GlG916tTBjRs3ct0WExOTa6GbiIiIiKg0CwwMBAAoKSnht99+EzhN8SUSiWBnZwcAePv2Lf755x+BExEREZXygva4ceNw48YNXL16FVevXkXXrl3h6OiIgIAAoaMR5Vv37t2xbdu2HK1Frl69CgMDA2hoaOR5bHp6OuLj45GVlVXYMYmIiIiIioWkpCTs3r0bANC0aVPo6+sLnKh4a9OmjWxx7iNHjgichoiIqJS2HLG0tERQUBCaNGkidBSin6aiooL58+fD2dkZTZo0gbGxMS5dugSpVAovL69cj0lNTYWXlxcSExNRoUIFPHv2DGZmZpg4cWKJWryUiIiIiOi/fv/9d9likB06dBA4TfGnrq6ODh064ODBg7h16xaePn0KY2NjoWMREVEpVioK2uPHj5f7Pq/2DIsXLy6KOEQFrmbNmti8eTNu3bqF169fY9KkSV9tNTJlyhRMmjQJtWvXlo2dOHECvr6+mDFjRlFEJiIiIiISREhICACgYsWKaNSokcBpFEPnzp3xxx9/QCqV4vDhw3B2dhY6EhERlWKluuUIUUnToEED2NrafrWYHRkZidq1a8sVs4HPi+G8ePFCNluFiIiIiKikefDgAS5cuAAAGD58OBc4zKfKlSujcePGAIA///wTSUlJAiciIqLSjAVtolLm8uXLaN++fa7bmjRpgrt37xZxIiIiIiKiorFlyxbZ1/b29gImUTxfFodMT0/H2bNnBU5DRESlGQvaRKVMuXLl8PLly1y3vXz5EuXLly/iREREREREhU8qlWL79u0AACsrK9SpU0fgRIrF0tISlSpVAvB5ccjs7GyBExERUWnFgjZRKdOlSxfs2LEjxwvQpKQkPHr0CNWrVxcmWAGIiIjAuHHjMH78eDg7O2PWrFl4//690LGIiIiIqBi4fPkyYmNjAQCDBw8WNowCEovF6NKlCwDg1atXOHnypMCJiIiotGJBm6iUUVdXx6hRo+Do6Ijr168jMTERp0+fhpOTE9zd3YWO98MiIiIQHBwMPz8/rFmzBuvWrYOLiwvGjx+P1NRUoeMRERERkcB27NgB4HNhtn///gKnUUzt27eHuro6AGDt2rUCpyEiotJKWegARFT0WrVqBXNzc+zYsQN79+5FgwYNEBwcDDU1NaGj/bCAgAD4+fnJPQYjIyM4Ojpi165dGDlypHDhiIhIYWRkZCAtLU2hFoqTSCTIyMgQOgZRsZaVlYXdu3cDANq1a4eKFSsKnEgxaWtro02bNjh+/DiOHj2Kx48fw9TUVOhYRERUyrCgTaQgTpw4gX379kFNTQ1paWmwsrLCqFGjIBKJfuh8urq6cHJyKuCUwlFWVs61IN+yZUv8/vvvLGgTEVG++Pr6Ch3hh9nY2AgdgajYOnfuHOLi4gAAgwYNEjiNYuvSpQuOHz8OqVSK9evXY+nSpUJHIiKiUoYtR4gUwLZt2xAVFYV169Zh9erVCAwMRKVKlTB37lyhoxUbWVlZuY6np6cr1Cw7IiIiIip4XxaDVFVVRe/evQVOo9iqV6+OevXqAQBCQkLY3o+IiIocZ2gTFXOZmZn466+/EBgYKDfepUsXXLlyBU+ePEG1atUESld86Ovr49mzZ6hatarc+LZt29CjRw+BUhERkaJxc3ODpaWlQn0YKpFIcOPGDaFjEBVb6enp2LdvH4DPr6H19PSEDVQC2NnZ4c6dO0hISMDOnTthb28vdCQiIipFWNAmKuZu374NKyurXLd1794dp06dwujRo4s4VfHj5uYGV1dXODo6omXLlkhPT8e2bdsQHR0NBwcHoeMREZGCUFVVhbq6usIVtFVVVYWOQVRsHTt2DB8/fgTAdiMFpVmzZqhUqRJevXoFf39/jBw58odbIRIREX0vthwhKubU1dWRnJyc67aUlBTZKuOlnZ6eHjZu3IiYmBhMmDABs2bNQs2aNeHt7c0X10RERESl2I4dOwB8XtCwa9euAqcpGZSVleHo6AgAuHbtGsLDwwVOREREpQkL2kQCe/z4MQ4dOoSbN2/mur1OnTq4ceMGJBJJjm07d+7ki/J/UVdXx4gRI7BmzRqsXLkSbdq0YTGbiIiIqBRLTU3FkSNHAHy+u1FTU1PgRCWHo6MjlJU/3/Tt7+8vcBoiIipNWNAmEkhycjJcXV2xY8cOqKur4++//8bIkSPx9OlT2T4SiQQHDx5EUlISLCwssGHDBmRlZeHjx4/w8vJCkyZN2AOQiIiIiCgPJ0+elN3t2LdvX4HTlCyVK1eWLbC5a9cuxMfHC5yIiIhKCxa0iQTi7u6OyZMnY86cObC1tYWzszPWrFmDOXPmIDs7G1lZWXB2doZUKsXOnTtx+PBh/PXXX2jYsCHmz5+Pbt26YcSIEUI/DCIiIiKiYuvLYpCampro2LGjwGlKHhcXFwBARkYGgoODBU5DRESlBQvaRAJ48+YNNDQ0UKNGDbnxMmXKoHPnzjh//jy2bt2K/v37o1evXlBSUkK1atWwfft2bN68GaamprCwsMhxXqlUisjISPz555/48OFD0TwYIiIiIqJiKDMzE3/88QcAoHPnzmw3UghatmyJ+vXrAwA2bNiQa5tEIiKigsaCNpEAYmNjUbdu3Vy3mZub4+HDh7hy5QratWuXY3vTpk1x9+7dHON3796Fvb09wsLC8P79e8ybNw8jRozAqVOnkJaWVuCPgYiIiIioOPv3JI8vrTGoYIlEItks7adPn+Lw4cMCJyIiotKABW0iAVSrVg1RUVG5bouMjETNmjWhpKSU54KGSkpKct8nJyfDx8cHAQEBcHFxwadPn5CZmYkaNWogNDQUEydOxM6dOwv8cRARERERFVdf2o2oqKjAzs5O4DQl19ChQ6GjowOAi0MSEVHRELSg3ahRI9y+fVtu7N27d8jOzhYoEVHRMDQ0RHJyMh4/fiw3npiYiKNHj6JNmzYoX748YmJichwbFxcne8H4xa5duzBu3Dioqanh3LlzSEhIwLp16+Dh4QE1NTWsW7cODx8+RHh4eKE+LiIiIiKi4kAikeDAgQMAAFtbW+jq6gobqATT1taWre1z6tQpPHjwQOBERERU0gla0E5JSZErXkskEtjY2OQ5c5VIEaSnpyMuLg5ZWVlf3W/hwoVYvnw5vL29cebMGaxfvx6urq5YuHAhxGIxxo0bBw8PDyQkJODDhw94//49Pn36hBkzZsDZ2VnuXFFRUWjcuDEA4Pfff4erq6tsW4UKFZCYmIipU6ciNDS04B8wERU5iUSisH8U/TEQEZFiuHjxIuLi4gCw3UhR+Pf7k3Xr1gmYhIiISgNloQP8l1QqFToC0Q9JS0vDwoUL8eHDB1SsWBHPnz9HrVq1MHnyZIjFOT870tbWhr+/P6Kjo3Hnzh00a9YMTk5OsjYjhoaGGDp0KFq1agU1NTW5axgZGcmdy8TEBFFRUbCwsICysjJUVVVl296+fQttbW0oKxe7X3ci+gESiQRHjx4VOsYP+Xc//xMnTkBdXV3AND+mS5cuOdo+ERFR8fOl3YhYLEb37t0FTlPy1alTBx06dMDp06exadMmLFy4ENra2kLHIiKiEooVLqICMm3aNDg7O8st9njmzBn4+Phgzpw5eR5Xo0YN1KhRI8d4TEwM9u3bhxs3bkBFRQXA50LWpEmTUKdOHZiZmcn2HTx4MKZMmYKNGzciMzMTmZmZUFFRwY0bN1CxYkUoKysjNTWVHxgRlSCK2kLI3d0dwOf1AhRN06ZNhY5ARET5IJVKZQXtVq1aoXz58gInKh1cXFxw+vRpfPr0CaGhoRg7dqzQkYiIqIRiQZuoAERFRaF69epyxWwAaN++PQ4dOoRPnz7l6Hv9LQEBAfDy8pIVs4HPi0EuXLgQ8+fPx8qVK2Xjenp6GDNmDOzt7WFiYgI3NzeULVsW7969g6+vLwDAz88PgwcP/olHSUTFjaWlZa53gFDBys7Oxo0bN4SOQURE+XTr1i08ffoUANCrVy+B05QeXbt2RdWqVfHs2TP4+/vD0dExz0XuiYiIfgbfBRMVgMuXL6Ndu3a5brOyssqx+Gl+pKSkwNDQMMe4rq5urn1cra2tERwcDGtrayQlJeHBgwewtbXF8ePHMW7cOBgZGaFZs2bfnYOIii+xWAwlJSX+KeQ//NCAiEixHD58WPZ1165dBUxSuigrK8PJyQnA5w8VLly4IHAiIiIqqQSfob1nzx789ddfAD7fGiYSibBr164chTyRSAQXF5cfusamTZtw//59LF68OMe2169fY/78+bh+/TrU1dUxYMCAH74OlV7ly5fHy5cv0ahRoxzbXrx4gSZNmnz3ObOysiCRSHL0apVKpcjIyMj1GGVlZXTs2BEdO3ZEUlISzp8/D2VlZSxfvhyamprfnYGIiIiISNF8KWjXrVsXpqamAqcpXUaPHo0FCxYgIyMD/v7+aNmypdCRiIioBBK8oL179+58jf1IQVsikSA4OBgrV65Ejx49ct1n9uzZMDU1xerVqxEfHw97e3sYGxujW7du33UtKt1+++03jBkzBl26dJGbyZecnIw7d+5g2rRp333ODh064Pfff8fAgQPlxo8ePYrmzZt/83htbW3Y2dl993WJiIiIiBTVmzdvcPnyZQCcnS0EQ0ND9O/fH9u2bcPevXvx6tUrVKpUSehYRERUwgha0L53716hnn/GjBlITExEv379cp3Rmp2dDVVVVTg5OUFVVRVGRkZo3749IiIiCrygHRUVxf5hJZytrS369OmDgQMHwsTEBLdv38a+ffvg4uKCO3fufPf5fvnlF6xevRpXr15Ft27dIBaLcfToUbx69QpTp079oXPS/+ECmUREREQlz7Fjx2Sv81jQFoaLiwu2bduGrKwsBAUFwcPDQ+hIRERUwgg+Q7swubm5wdDQEGvWrMGLFy9ybBeLxdiwYYPs+8zMTPz9998YOnRoUcakEsLS0hK1atXC0aNHcebMGdSsWRNeXl5QVVX9ofOJRCJMnDgRDx48wJ49eyCRSNC2bdscC08SEREREdFnX9qN6Ovrw9raWuA0pZOVlRUaNWqE69evY8OGDZg1a5bcQvdEREQ/q1gUtG/fvg0dHR0YGxsDAN6/f4+goCBER0ejdu3aGDlyJAwMDL77vLktqJcXiUSCmTNnQkVFpVBWwjYzM8vRC5lKJisrqwI9X7169bg6eyGQSCSIiIgQOgYRERERFZCMjAwcP34cANC5c2coKxeLt7ulzpd2oQ4ODnj16hX27NmDQYMGCR2LiIhKEPG3dyk8mZmZcHV1Rb9+/WQvPNLT0zFkyBBs2rQJcXFx2LNnD/r164eEhIRCy5GSkoJx48YhJiYGGzdu/OEZtURERERERCSMsLAwJCYmAmC7EaENGjQI5cqVAwAsW7aM7f6I6KsuXLiAPn36wNzcHO3atUNwcHC+njcOHz4MOzs7NGzYEJ07d8b+/ftz7LNv3z507doVDRs2RMeOHbF161a5c9euXTvPP8OGDSvQx0kFR9CC9rZt2xAWFoZZs2ahb9++AIDQ0FA8fvwYEyZMwIEDB3Dq1Cloa2vLtQYpSB8/fsTQoUMhFouxbdu2H5oJTkRERERERML60m5ESUkJHTt2FDhN6aahoQFXV1cAwPXr13H+/HmBExFRcRUREQEnJyeYmppizZo16NatG5YuXYqgoKCvHnfixAlMmzYNLVq0gL+/P5o2bYqZM2fiyJEjsn1+//13zJo1C61bt0ZAQAB69eqFxYsXIyAgQLbPrl27cvxxcHAAAN5dUowJeg/WoUOHMGrUKAwfPlw2duzYMWhoaGDUqFEAAC0tLQwbNgwbNmzA7NmzCzzD5MmTUblyZaxatYotQShPUVFR2LVrF1JTU9GxY0e0bduWi3wSERERERUTUqkUhw4dAgC0aNGCE5WKAWdnZyxevBhpaWlYvnw52rRpI3QkIiqG1qxZAzMzMyxduhQA0KpVK2RlZWHDhg0YPnw41NXVcz1uxYoV6NSpk6xW2LJlS3z8+BGrVq2CnZ0dAGDDhg3o2LEjpk+fDgCwtrZGbGwstm3bBicnJwCAhYWF3HlfvXqF33//HUOGDEGXLl0K4yFTARB0hnZsbCyaNGki+z4pKQl37tyBpaUl1NTUZOPVq1dHXFxcgV3X0tISV69exYMHD/D333/jr7/+QpMmTWBpaQlLS0uuwkxylixZgn379sHJyQlz587Fy5cvMWbMGKSnpwsdjYiIiIiIADx48ADR0dEA2G6kuChfvjxGjhwJ4PPs+aioKGEDEdFXtWvXDt7e3hgxYgQaNmyIOXPm5Lnf19p0fI+MjAz8888/sLW1lRvv2LEjkpOTce3atVyPe/78OWJjY3M97smTJ4iNjQUABAYGws3NTW4fFRWVr9ZzFi9eDDU1NUyZMuW7HgsVLUFnaEulUojF/1dTv3HjBrKzs3MsqpeYmAgNDY0fvs748ePlvr9x44bs6/v37//wean4evHiBbKysmBsbPxTM6n//vtvaGpqyv0MDR06FA0aNMDKlSsxc+bMgohLREREREQ/4Uu7EYAF7eJk8uTJCAgIgFQqxYoVK77ZQoCIhBUaGgp7e3uMGTMGWlpaue6zdu1aZGRkFMj1nj17hszMTFSvXl1uvFq1agCAmJgYtGjRIsdxXz7A/Npx1atXR40aNQB8rj9+/PgRp06dwoEDB2RdIf4rIiICx48fh4+PD7S1tX/moVEhE7SgbWJigtu3b8Pa2hoA8Oeff0IkEsHGxkZuv/Pnz+f4IaXS6fnz59i9ezeSk5PRvn17WFtbyxWsr169ivXr18PU1BQqKiq4f/8+Bg4cmONTu/zau3cvFi5cmGPc3Nwc69ev/+HHkR+vXr2Cr68v0tPTIRaLIZFI4OLigvr16xfqdYmIiIiIhPSldcj32LJlCwCgYsWKePjwIR49elTQsegH/PLLL+jRowcOHDiArVu3wsvLCxUrVhQ6FhHloXLlypg2bdpX96lbt26BXe/LQr7/LR5/KaYnJSXletyX8fweFxERgYEDBwIA6tevD3t7+1zPu3HjRlSpUgXdu3f/nodBAhC0oN29e3f4+/tDX18f2dnZ2LdvH8zMzFCvXj3ZPseOHcPevXsxefJkAZNScRAQEIDHjx9j9OjR0NXVxR9//IHNmzdjzZo1UFNTQ2xsLDZu3IiAgAAoK3/+0ZZKpZgzZw709fXl2tvkl0QigaamZq7bVFVVf+rxfM2HDx8wffp0rFq1CmXLlgUApKenY+LEiZg0aRLq1KlTaNcmIiIiIlIkX1pXAsCvv/7KtW6KmWnTpuHAgQPIyMiAv78/vLy8hI5ERHkwMzP75j4SiQRSqTTP7V/qMf+VlZUl971YLEZ2dvZXr/Xvrg7/9r3HVa5cGf/73//w/Plz+Pn5YeDAgdi/f79cN4jXr1/jzJkzmDlzZp6PgYoPQf+Fhg0bhvv372Pu3LmQSqWoVKkSfH19Zds7d+4s67M9bNgwAZOS0CIjIxEfH48lS5bIxkaPHo2mTZti2bJlmDNnDgIDAzF//ny5Jx6RSIS5c+di2rRpP1TQrlatGu7cuSP3IQsAZGZmFmoP7ZCQEMyaNUtWzAYANTU1LF26FHPmzMHq1asL7dpEREREpZFUKkVKSkqhXkNTU5PF1kLwpXUl8LmgTcVL8+bN0axZM1y+fBnr1q3DzJkz82xlQETCymtC37/Z2trixYsXeW7Pq7Xvf+sqrq6u6NSpEwAgOTlZblteM7C/KFOmzHcdV6FCBVSoUAFNmzZF1apVMXToUJw4cQI9e/aU7XPy5EmIRCLZgpJUvAla0FZSUoKPjw8mTJiAt2/fok6dOlBRUZFtb9OmDUxNTdGzZ0+5cSp9QkNDc+1X3bBhQ/j7+wP4/MSV2+1rGhoaUFJS+qHr2tvbY+LEifD395c9YUqlUsybNy/PW1QKQkxMTI4ne+Dzk/bXPgklIiIiou8nlUphY2ODixcvFup1WrRogbCwMBa1C9iVK1cAfH7dn9traBKWSCTC1KlT0a9fPyQkJCAkJCTHOldEpDjWr1//Qz209+zZI/e9oaEh9PT0oKSkhCdPnshte/r0KQDIemD/l4mJCQDgyZMnci1QvpynRo0aSE5OxtmzZ9GwYUNZb23g/1qmxMfHy53z3LlzaNKkCcqVK/fdj42KXrGYQ1+pUiXs378fmpqacj+sM2bMEDAVFSepqanQ19fPdZuamhqAz7ecZGRk5GgFIpVK5WZTZ2RkYNmyZXj69ClUVVWRkpKC3r17o0uXLjnOra+vD09PT7i5uUFdXR3q6uqIj4/H0KFD0axZswJ8hPKkUimysrJyvc0lMzOz0K5LREREVFqxyKyYJBIJrl27BgCwtLTkRKhiqlevXqhRowaio6Ph6+sLR0dH2fs4IlIstWvX/qHjGjRokOt4kyZNcOrUKTg4OMj+Lz5x4gTKlCmDhg0b5npMtWrVYGRkhBMnTqBz586y8ZMnT6J69eowMjJCeno63N3d0aNHD3h6esr2+fvvv3M8DqlUisjISAwdOvSHHhsVvWJR0AY+90euV69enp++UOlWs2ZNREREwMLCQm48OzsbqampAIDevXsjJCQETk5OcvscOXIEzZs3l30/YcIEODk5yc4llUrh5+eHpKQk9O/fP8e1q1evjvXr1yM1NRWZmZnQ0dH54ceRlpYGAFBXV//qfr/99hv27t2LAQMGyI3fvn0bxsbGP3x9IiIiIspJJBIhLCws3y1HkpOTUaFCBQBAXFxcvtsnsOVIwbt//75sUTG2Gym+lJSUMGvWLIwePRrPnz/Hli1b4OjoKHQsIioGxo0bJ7s7vk+fPrhx4waCg4MxdepUWY/rpKQkPHr0CMbGxjAwMAAAuLi4YNasWdDT00O7du1w5swZHDt2DCtXrgTwefKjo6Mj1qxZAwMDA1hZWeH+/ftYu3YtmjdvjlatWskyvHz5EomJiahZs2bR/wXQDyk2Be2aNWsiJiYGrVu3FjoKfUVmZibWrVuHqKgoqKqqQiKRYPTo0bC0tCzU644YMQKurq5Yv369XC+kpUuXol+/fgCAdu3a4dq1a/Dw8MCQIUOgoqKCPXv2ICEhAT4+PgA+345obm4uVxgXiUSYPHkyRo8ejb59++a56ICGhobcggHfIyIiAuvWrZO1DElKSsKkSZPyXB24W7dumDZtGlJSUjBo0CCoqKjg+PHj2L17NzZs2PBDGYiIiIgobyKR6If6+mppabEfsIC+tBsRiURo1KiRwGnoa4YNGwZPT088ffoUPj4+sLe354x6IoK1tTXWrFmD1atXw8XFBRUqVICbmxtGjRol2+fOnTsYPnw4fHx80Lt3bwCfJzVmZGQgJCQEe/fuRdWqVbFkyRK5u++dnZ1hYGCA0NBQhISEwMDAAAMHDsT48ePlPmB+9+4dAPzUBEYqWsWmoN22bVusWLECYWFhqF27do5G9CKRCC4uLgKlI+DzTObx48djxIgRmDhxIoDPrUDc3d2RkpKCFi1aFNq1dXV1sWDBAkydOhUGBgYoU6YMbty4gdTUVDx79gwHDhyAnp4epk6diuTkZBw4cACZmZno3r076tSpIzvPmTNn8lxgtHbt2nj27Jlcb6WC8OjRI2zYsAH+/v6yF2zp6elwcXGBh4dHrjOuRSIRli1bhnPnzmH27NnIyspCmzZtEBwczNV2iYiIiIj+v6tXrwIAatWqlWeLQioeVFVVMWvWLIwbNw6xsbHYtm1boa5LRETf5+zZs4Jd29bWFra2tnlu/zK7+r8GDhyIgQMH5nmcSCTCoEGDMGjQoK9ev2HDhnkuZknFU7GpjK1duxbA5142X/rZ/BsL2sK7cOECrKysYG1tLRvT0NDA0qVL4ejoWKgFbQAwNTVFQEAA3r9/j6ioKERHRyMkJES2WOPz588xYcIEBAQEYMKECbmeQ1tbGx8+fECVKlVybPv06VO+VvT9Xhs2bICPj4/c7AM1NTUsXLgQq1evhre3d67HiUQitG3bFm3bti3wTERERJS37OxsoSN8F0XLS1RQ4uLiZAuAsd2IYrC3t8fChQvx4sULeHt7Y9iwYZywQ0RE363Y/M9x7949oSPQNxw9ehSzZ8/OMS4Wi1GuXDkkJibKisuFSV9fH7t378bKlSvlrmdkZISpU6diy5YteX740a9fP/j6+mL58uVy48nJyYiLi0P58uULPG9GRkaus0UqVqwo6/dHRERExceNGzeEjkBE+fBldjbAgraiUFNTg5ubGyZOnIhHjx5h586dXISNiIi+W7EpaFPxp6qqirS0tFyL1pmZmUX6ybpEIsm1t1GjRo2wadOmPI+rUKEC6tWrh/nz52P8+PEoW7Ysbt68ieXLl8PDw6NQsmZkZEAqleZYACg7OxtZWVmFck0iIiL6MU2bNi2U86alpckWn969e/c3F4imgiGRSAr9vBKJpNCuo6SkVCjnLSm+9M8uW7YsTExMBE5D+TVmzBh4e3sjLi4Onp6eGDBgAHtpExHRdxG0oD18+PB87ysSibBly5ZCTEPf0q9fP2zevBnTp0+XG09JSUFycvIPL5j4I/J60yCRSCCVSr967KhRoxAVFYXly5cjOTkZNWrUwOrVq6Gnp1cIST/3ejp9+nSOflAHDx5EmzZtcuz/4cMHhIeHQ0dHB02bNs1zkUoiIiIqOEpKSnKLCBW05ORk2dcdO3YstEUEWQD9PxKJBEePHi2Uc6elpcm+PnHiRKF9QNGlSxf+m+YhNTUVkZGRAD7Pzv7v5BEqvjQ0NDB79mxMnDgRDx8+xKZNm+Do6Ch0LCIiUiCCFrS/VXj80X2pcNSvXx979+7Fxo0bMXz4cKiqqiI6OhpeXl5wd3cv0iwVKlTAo0ePULNmTbnxP/74A+3atfvm8WZmZnn2ri5ow4cPx+TJkxEbG4tBgwYhOzsb27Ztw+PHj7F06VLZflKpFEuWLEF8fDzatGmDly9fYv369Rg3bhyaNWtWoJlSU1Px9OlTlC9fHgYGBgV6biIiIkVVmIXDf59bSUmJRcoiFB4eXijn/fL690tRtaAV1t0CJcXNmzdldzuy3YjiGTt2LFasWIEnT55gwYIFGDp0aKGsZ0RERCWToAXt//3vf0Jenn7AvHnzcPr0aUydOhUikQgVKlSAr68vDA0Nv3pcfHw8nj9/DlNT0wKZCT158mS4uLjA0dERNjY2kEgk2L9/P86fP4/Vq1cjPT0du3btQnh4OEQiETp06IBu3brJzXaOi4vDuXPnoK6uDltb20J7AaWkpIRVq1bh0qVL8PLygkgkQu/eveHs7Cy3X1BQEOrVq4eZM2fKxoYNGwYnJyeYmpp+8+84P7Kzs7F48WK8evUKZmZmePbsGZKTk7FgwQKuCk9EREQllqWlpcLc9Zadnc0+7vnwpX+2qqoqGjZsKHAa+l5qamrw9PTEiBEj8PLlS6xduxZubm5CxyKiInbr1i34+vri9u3b0NLSQu/eveHq6gpVVdVc9//nn3++2u1h/PjxcHV1BQBcunQJ/v7+uH//PlRVVdGoUSNMnz4dxsbGsv1fvHgBX19fhIeHIzs7G40bN8bMmTPl9qHiSdCC9qZNm9CtWzeUK1dOyBj0nTp06IAOHTrka9+PHz/C3d0durq6qFGjBrZv3w5lZWUsWLAAampqP5xBR0cHgYGB2LlzJ3bt2gWRSARbW1usXr0aqampGDduHOzt7TFs2DBIJBIcPHgQrq6uWLNmDcRiMby9vZGYmAg7OzskJydj8uTJsLW1Rd++fX8409eIRCI0b94czZs3z3OfK1euICgoSG5MSUkJ06dPx+bNmwvkBZ6Pjw9atmyJVq1aycZevnyJKVOmICQkhLdqEhFRrhS9DzHAVhylnVgs5s9ACZKdnS3rn92wYcOfel9BwhkyZAh8fX1x584d+Pj4YMyYMZxkQ1SKPHv2DPb29rCwsICfnx+io6OxcuVKfPjwAZ6enrkeU69ePezatSvHuJ+fH27dugU7OzsAwLVr1+Dg4ID27dtj2bJlSElJwbp16zBo0CAcOnQIBgYGSEtLw6hRo5CVlYW5c+dCTU0Nq1evxrBhw3Do0KFc122j4kPQgravry8aN24sK2hLpVIsWLAATk5OqFixopDRKJ9evHiBO3fuwNjYGHXq1Mmxfdq0aZg3bx6MjIxkY5GRkfDw8MCSJUt+6toaGhqwt7eHvb293PiqVaswa9YsmJmZAQCUlZXRp08fqKmpYc+ePUhPT4eZmRl69+4tO6ZTp06YPXs26tWrJzuuKEml0jx7kP/yyy94/vz5T18jOTkZ8fHxcsVsAKhcuTJatWqFixcvokWLFj99HSIiKllKQh9igL2IiUqS6OhovH//HgDbjSgyJSUleHt7o0ePHvjw4QN8fX3h4+MjdCwiKiJBQUHQ0tLCunXroKqqitatW0NdXR1eXl5wcnJC5cqVcxyjra0NCwsLubEzZ87g0qVLWLVqlWyB4KCgINSoUQOrVq2S3aHVqFEjtGnTBvv374eDgwOuXr2K2NhYbN68GdbW1gAAExMTdO7cGWfOnEGvXr0K9y+Afkqx6qGdnZ2NXbt2oV+/fixoF3OpqamYPXs2dHR00KRJExw7dgxLly6Fp6cnqlSpAgCIiIiAubm5XDEb+DyLYseOHXjz5g3Kly//1eskJibi1atXqFy5MrS1tfOV7fnz57kWpbt06YLx48cjMzMTAQEBObZPmzYNvr6+WLx4cb6uU5BEIhFSU1Nz3fb48eMC+X2Ijo5GgwYNct1mY2OD48ePs6BdghXmrMfCUpQzNwsTC2hUUihqH2KAvYiJSpovs7MBoEmTJgImoZ/VrVs3WFtb49KlS/Dz84OTkxOqVasmdCyiUqldu3bo1q0bUlNTsX//fojFYrRu3RqzZ8/Os3Xst1qA9OrVK88ay4ULF9C6dWu59iKdOnXCggULcOHCBfTv3/+bmdPS0rBw4UK0adMGnTp1ko2bm5ujQ4cOcu3GKlSogDJlyuDp06cAgPT0dACQW6j7y+P88OHDN69NwhK0oJ0bLv6oGDw8PDB27Fi5WdkfPnzA+PHjsXXrVohEIkRGRso+5fqvRo0a4f79+3kWtFNTU7FgwQJkZGTA1NQUjx49gra2Njw8PHLtpRQVFYWgoCBkZWXhr7/+wv/+9z8MGTJE7slLLBZDLBZDXV0919YaBgYGSElJ+d6/igLToEEDnDlzBu3bt5eNSaVSLF26FHPnzv3p81eoUEH2xP1fMTExqFSp0k9fg4qnwpxdWZiKcuZmYeKsUCpJFKkPMcBexPRZRkYG0tLSFOa5WCKRICMjQ+gYxdqX/tkmJibfnCBDxZtIJMKyZcvQokULpKWlYdq0afj999+FjkVUam3fvh3VqlWDj48PEhISsHz5cjx58gQ7d+7MtY6SVwuQLwwMDHIdT0tLw4sXL2Qzqv+9v7a2NmJiYvKVd+vWrYiLi8PmzZvlxseNG5dj3/DwcHz8+BG1atUC8HliX40aNbB06VJ4e3tDXV0d3t7e0NTUzHebXRJOsStoU/H37t07KCkp5Wgxoqenh44dO+L8+fNo06YNqlSpgkePHqFx48Y5zvHo0aOvzqaYMWMGnJ2d5a4RGRmJ2bNnY9myZXL7/vPPPwgNDcXChQuho6ODKVOmQFVVFW5ubnL73r59GyYmJoiKikJ2dnaON+QvX76Erq7ud/1dFCRXV1fMnz8fp0+fxm+//YaEhAQcOnQII0aMyPVWm+9VoUIFvHnzBm/fvpXrWy+RSBAaGorAwMCfvgYVb4U1u7IwFcXMzcLEWaFU0rAPMSkiX19foSP8EBsbG6EjFEvv3r3Do0ePALDdSEnRvHlzDB48GNu3b8eePXvw559/om3btkLHIiqVxGIxNm3ahDJlygD4XGB2cXFBWFhYjvalQO4tQPIjMTFRdvx/aWlpISkp6ZvnyMjIwNatW9GlS5dv3tmRkJCAuXPnwtDQED179gTweXHaRYsWwcnJSVbAVlVVxYYNG1C1atXvfERU1FjQpu8WExODunXr5rqtUaNGCAsLQ5s2bdC2bVuMGDECPXv2lFuoJSEhATExMTk+ifviS4uN/xbMGzZsCHV1dbx8+VKuwBsYGIjAwEDZG+zx48fDy8sLtWvXRkREBCwsLPD69WssXrwY/v7+OHfuHIKDgzFmzBjZObKzs7F48WJMnjz5h/9efpZYLIanpydev36Nv//+Gzo6OggKCoKKikqBXWPBggWYPHkyunTpghYtWiA6OhqbN2+Gs7MzF9MpJRRtdqWi4qxQIiKiwnHt2jXZ12w3UnIsWbIEBw4cQEpKCiZNmoRr165BWZnlCqKi1q5dO1kx+8v3ysrKuHLlSq4FbalU+tXWkF/ulP+v7Ozsr+bIbTb4f504cQJv3rzB6NGjv7pffHw8HBwcEB8fj82bN8uK6OHh4XBwcECjRo1gb28PsViMXbt2wdXVFUFBQfw/ppgrlv9D5OcHl4RjbGyMAwcO5Lrtzp07skK1WCzGnDlz4ODggL59+6JOnTq4cuUKTp48iaVLl+Z5/uvXr+fZy7l58+aIjIyUFbTfv3+PSpUqyc0WMzExwezZs7FkyRLs3bsXTZo0gY6ODlasWAFdXV306NEDAQEBcHFxQevWrZGcnIy//voLw4cPz7PIXpQqVqyIPn36FMq5DQ0NsWXLFpw9exa///47qlSpgg0bNuS5ICWVPJxdSUREpY2bmxssLS0V5v8/iUTCD0W/4kv/bF1dXdlt4ySMQ4cOFej5evfujW3btiEyMhLjx49Hly5dAHzus01ERaNChQpy34vFYujr6+Pjx4+57h8eHv5DPbS/FJWTk5NzbEtKSpIrquflxIkTqFWrVo7JkP92//59ODk5ITk5GRs3boS5ubls24YNG1ChQgUEBQXJWtva2Nhg4MCB8Pb2xr59+76ZgYQjeEF7wIABOcZyK+aJRCLcvXu3KCLRNxgaGuLTp0948uSJ3G0dKSkpOHjwILZu3Sobq1OnDjZv3oyTJ0/i7NmzqFevnqzHdl4qV66Mhw8fonXr1jm2xcTEyN1+KRKJcv1kr2bNmvD09MTGjRtz7T89duxYpKam4sqVK9DQ0MCIESNKzaxVsViMDh06sCcUERERlQqqqqpQV1dXqIJ2bmvG0OfbyyMiIgAAjRs3Vph/U8qfHj164OTJk4iPj0doaChatGghaEtIotLo/fv3ct9LJBK8f/8+z17Y9erVw549e/I8n76+fq7jWlpaqFChAp48eSI3/u7dOyQnJ6NGjRpfzZmZmYkLFy58dXb25cuX4eLigjJlyiA0NDTHh6AvXrxA/fr15f7PFYvFaNy4MUJDQ796fRKeoAVtV1fXIrnOpk2bcP/+/Vw/FUpLS8OcOXNw/vx5aGlpYdKkSejVq1eR5FJkCxcuxPTp01GrVi00a9YMDx8+xNmzZ7FgwYIchWFlZWXZp+v5YW1tjfXr12PgwIFybTCSk5MRHh4OZ2dn2Zienh7i4+ORmZmZozVHaGjoV/8tNTQ0cr1lhoiIiIiIip9bt24hPT0dAPtnl0RqampwcHCAj48PEhMTERwcjClTpggdi6hU+euvv5CRkSEr8p45cwZZWVmwtrbOdX9tbW00aNDgh67VokULnDt3DrNmzZJd78SJE1BSUkKzZs2+euyDBw+Qmpqa65ptAHD37l04OTnByMgIwcHBOWaeA4CpqSkiIyPlHq9UKsWNGzfYQ1sBlOiCtkQiQXBwMFauXIkePXrkus+KFSuQmpqKsLAwPHr0CKNHj4aZmdlXb1kgQEdHBwEBAYiKisKtW7dQu3ZtjBw5skDaxYhEIsyePRsODg4YOnQo6tevj8uXL2P79u1YvHhxjmu4urrC1dUVXl5eMDQ0hEQiwZ49e/D+/XvUr18/39e9f/8+QkJCkJqaCiUlJQwePJgvlImIiIiIiokv7UaUlJRgaWkpcBoqDM2aNUPTpk0RHh6Oc+fOoU2bNmw5QlSEXr16hXHjxmH48OF49eoVVqxYgZYtW8LKyqrArzV69GgcOXIEo0ePhr29PWJjY7FixQr0799f1mY2IyMDd+/eRcWKFVGxYkXZsQ8ePACAPGdyz5kzB1lZWRg/fjxevXqFV69eybYZGBjA2NgYzs7OGDx4MEaPHo0RI0ZAWVkZe/fuRUREBFavXl3gj5cKluAtR74YPnw45s2bl+sP47179zB9+vTv7tE1Y8YMJCYmol+/fsjIyMh1n8OHDyMgIAAaGhpo0KABunbtij/++KPAC9pRUVEltjd4vXr1AKDAW8JMmzYNx44dg7u7O7S0tNCwYUO4u7vjl19+wcCBA2V/nyoqKujduzdmz56NtLQ02aeHgwYNwp07d/J1rUuXLiEsLAyOjo7Q09NDSkoKtm3bhpMnT8pWwC0ImZmZCA0NxZMnT6CiooKMjAx06dIFTZs2LbBrUP5IpVKhIxARERFRPkmlUoSHhwMA6tevD01NTYETUWEQiURwcnLCrVu3kJqainXr1mHatGnQ0tISOhpRqWBnZwcdHR1MmjQJmpqa6NWrFyZPnlwo16pRowZCQkLg6+uLCRMmQF9fHyNHjsSECRNk+8THx2PAgAFwdXXF+PHjZeNv374FgFzbEj179kxWn/r3ub740te7QYMG2LZtG1atWoVp06ZBRUUFtWvXxtatW1mjUQCCFrSvXr0qKyqFh4fjypUrSEhIyLHfn3/+iWfPnn33+d3c3GBoaIg1a9bgxYsXObZ//PgR7969g6mpqWzMxMQEFy5c+O5rUcFTVlZGeHg4fHx8ZJ/OAcDZs2cRGhqKoUOHysaMjIx++Ek2OzsbR44cgZeXl6xIrqmpCUdHR3h7e6NDhw6yBQt+1pIlS9C9e3eMHDkSwP/dRZCcnIy2bdsWyDWKq7dv32L//v14+/YttLS00KNHD7ke7ERERESFJbc1V4orRcpalGJjY2UFDBYaSrZy5cphxIgR2LBhA+Lj4+Hh4YHly5cLHYuoVFBRUcG8efMwb968IrlekyZNsHv37jy3GxkZ4f79+znGx4wZgzFjxuR6TNWqVXM9Jjfm5uYICQnJX1gqVgQtaP/+++84ePAgRCIRRCIRFixYkGOfLwXvrl27fvf5DQ0Nv7o9NTUVwOdeyl+oq6sjLS3tu6/1LWZmZoIsWhIbG4udO3fi06dPaNu2Ldq3b68wix9euHAB3bt3h62trdx4vXr14OTkhJo1a8r12P5R169fh52dXa7tScaMGYMnT56gf//+P32dq1evwsbGBoMGDZIb9/Pzw+jRo+Hi4lJiZ/Ffu3YN27Ztw8yZM1GjRg3Ex8djxYoVaNKkCfr27StIJolEIltUiIiIiEq2GzduCB2BftKX2dkA+2eXBp06dcK5c+dw7949+Pn5oV+/ft/sqUtERKWHoAVtd3d39OnTB1KpFCNGjICHhwdq1qwpt49YLIaOjk6O1UgLgrq6OoDPC0N+uWXt318ruoCAADx58gSOjo4wMDDA0aNHMWrUKPj7+yvELVv//POPXLEzOTkZhw8fxocPH1CuXDnExsaidu3aePjwIV6+fAkzM7NvfoiRm8zMzDwL42pqasjMzMz3uWJiYrBmzRpkZGQgOzsbFStWxKRJk6Cjo4NTp05h+PDhOY4RiUT45Zdf8Pz58xK58IBUKsWaNWuwceNGKCt/fsoxNDTE4sWLMXbsWHTq1KnAZsATlSYZGRlIS0sT5MPS0kYikeTZuoyIir/CmM2blpYmm/Cwe/du2fsKKjxfCtrGxsZyfVSpZBKLxXB1dcWkSZOQlZWFoUOHIiIigu8biIgIgMAF7TJlysheYG7duhX16tUr0kKrnp4eDAwMEBsbi7p16wL4XJA0MTEpsgyF5e7du3j9+jW8vb1lYwMHDkTjxo3h4+ODhQsXCpguf8qXL48XL16gWrVqOHbsGPbu3YshQ4agXr16mDx5MqKjo6GhoQEzMzOYmppi5cqVkEgkWLhwoWyF2vywtLTEpk2bMGzYsBzb/vjjj1xbmWRkZMDPzw+PHz+GqqoqMjIy0L59exw9ehQrVqyAvr4+AODhw4dwdnZGUFAQNDU1kZSUlGuG5ORkuTsFSpKoqCg0atRIVsz+t4EDB+LIkSMYMGCAAMmIFJuvr6/QEUodGxsboSMQ0XdQUlJCly5dCuXcycnJsq87duxYaO9h+KHlZwkJCXj48CEAthspTYyNjTFs2DBs2rQJ0dHRmDJlCgIDA4WORVRinT17VugIRPlWbBaF/LKSsaqqKiwsLPDy5Ut4enrixYsX6NSpE1xcXArlunZ2dli9ejWWLVuG2NhYHD58GJs3by6UaxWl0NBQTJkyJcd4rVq1ZL3nhHbx4kXs2LEDYrEYWVlZ6N+/P1q3bi3b/mXxgerVq+PIkSMICgqCSCRCQkICatSogefPn8PExATTp08HAPTp0wc3b97EggULsGjRonznUFVVhY2NDZYvX46JEydCWVkZUqkUO3fuhK6ubo5Z31KpFK6urnByckKjRo0AfJ7lbWNjg9mzZ8uK2cDnv29nZ2eEhoaiT58+8Pf3h4+Pj9z50tLS8OrVK5QrV+67/w4VQXJycq4LNQCfF3CIiYkp4kRERERUWhRWQfjf51VSUmLhuZBdvXpV9jUL2qVLjx49EBMTg3PnziEoKAhdu3ZF9+7dhY5FREQCKzYF7QMHDmDWrFkYNWoULCws4OHhgWvXrqFFixbYsGEDVFRU4OjoWCDXsrS0RFBQEJo0aYIpU6bAy8sL7du3h4aGBmbNmgUzM7MCuY6QEhMTYWBgkOs2VVVVSKVSQfs1b9++HU+ePMHSpUuhrq6OjIwMrF27Fo8ePYKDgwOAzzP4BwwYgJ49e2Lu3Ln49OkTwsLCsGPHDtmLmLNnz8o9FnNzc2zduhWfPn2Cjo5OvvMMHToUZ8+ehaurK1RVVZGeno4OHTpg5syZOfYNCwuDtbW1rJgNfF44oUmTJjh06BB69Oght7+1tTW2b9+O0aNHw8jICIsXL4azszN0dHRw7949LF68ONfrlBQNGzbEpk2bMGLEiBzbDh8+nGsbFiL6Njc3N1haWrKIUgQkEgn77xIRCehLuxFdXd1CaUVJxZdYLMaWLVvQsGFDfPz4EaNHj8atW7dQoUIFoaMREZGAik1Be/PmzejVqxemT5+ON2/e4OLFi5g6dSocHBwQEhKCXbt2/XBBe/z48XLf//tNqaamZo4ZsyWBubk5Ll26hObNm8uNS6VSpKSkFEoxOzY2FmfOnIG6ujq6du2a56zctLQ0/PXXX9iwYYNsTFVVFVOmTMH48eORnJwsu23T1tYWe/bswdOnT7Fs2TI0atQIQUFBsp+FO3fuYN26dRg1apSsZUedOnXw5MkTNGjQQO667969w5EjRyCRSNCxY0dkZmbi9OnTUFdXh52dHdq1a4d27dp983GeOHFCNiv836RSKSpVqoT379/LzdL+90r1Li4uuHbtGjw9PZGRkQEjIyMsW7asxM7OBj73IbewsEBwcDBGjRol+9n7888/kZycjOrVqwsbkEhBqaqqQl1dnQXtIiCRSL6rlRURERWc9PR02ULeTZo04f97pZCxsTH8/f0xdOhQvHnzBkOGDMGJEyf4s0BEVIoVm4L248ePMXv2bADA+fPnIZVK0b59ewBAgwYN4OfnJ2A6xTNo0CA4OjrCzMxMVlyVSqVYunSp3EKLBUEqlcLd3R2qqqro3r07kpKSMGfOHFhbW2PIkCE59r948SJsbW1zPVeXLl1w9uxZdOvWTTbWqFEjWFpaomnTpkhPT8e4ceNQp04dmJub48CBA7C0tMTYsWOxfv16aGlp4fHjx+jdu7fcedevX4+HDx+if//+UFJSQr9+/aCuro6lS5ciJSUFc+fORdOmTXPto/1fGhoaSEpKgp6enty4gYEB4uPjoaKiIjd++PBhuUJ548aN0bhx429epyRxdHTE3r174ejoCE1NTaSlpaFBgwYl8sMkIiIiIio4kZGRsoV52W6k9Bo8eDCOHTuG0NBQnDlzBp6enliwYIHQsYiISCDFpqCto6MjWzAvLCwMlStXls3cfPr0qdyMV/o2TU1N+Pr6wt3dHWpqaihTpgxevHiB7t27o1OnTgV6raCgILRq1QodO3aUjbVs2RLz5s3D7du3Ub9+/e86339njw8ZMgTjxo1DYGAgtm3bhlGjRqFZs2Zo27Ythg4diubNm0NHRwf+/v4YMGAAUlNTUbZsWdnxFy5cQFpaGlasWAEA2LhxI9zd3fH+/Xs8fvwYffv2hY2NDRYsWIDIyEg0bNjwq/n69++PkJAQeHh4yI2PHTsW7dq1w8OHD2FpaYns7GwcOXIEx48fx9q1a7/r76Ak6tOnD/r06SN0DCIiIqJcfbmTMT/+vSjkv7/+Fk1NTUHb/imif/75BwCgrKwMCwsLYcOQYEQiETZs2IDr168jKioKXl5eaN68udx7UCIiKj3EQgf4wsrKCmvXrkVgYCDOnDkjW5H8xIkTWLVqFVq0aCFwQsVTuXJl+Pv7Y+HChZgwYQKCgoIKZQGNa9eu5fpCYtKkSfjf//6XY7x58+Y4depUruc6cuQI2rZtKzemra0Nd3d3uLi4ICQkBA8ePMCECRPQqlUrWU/tlJQUHDx4EN7e3vDy8pI7fvfu3Rg3bpzs+/DwcHTu3BkDBw6UyzFx4kRs27btm4+3Ro0a+PjxI2bPni17A3P37l3MmTMH+/btw8WLF+Hq6orx48cjNTUVa9asQXR0NCIjI5GVlfXN8xMRERFR0ZJKpbCxsYG2tna+/vy7f2+FChXyfVzLli0hlUoFfKSKJTs7W7YgpLm5uazFIJVO2tra2LNnDzQ1NSGVSjFkyBA8e/ZM6FhERCSAYjNDe86cOZg+fTrWrl0La2trjB07FgDg4+ODypUrY+rUqQInVFyamprQ1NQstPOrqanlOq6vr4+0tLQc4+rq6mjVqhV8fHwwefJkqKurIz09Hf7+/rC0tJT1z/632rVrIyQkBMOHD4eFhQUGDx4MdXV1ZGdn4/z583jw4AGqVq2KgICAXLOoq6vn+FosFstl19PTyzXvv+3duxfHjh1DkyZNcP/+fTRt2hRmZmZo1qwZ/Pz8YGBgINe7Ozw8HGPGjIG5uTk0NTWxdu1atG3bFoMGDfrqdYiIiIioaHHmdPETHR2NhIQEAMCvv/4qcBoqDurWrYvAwEAMHToU7969Q+/evfHXX3/xww4iolKm2BS0DQwMEBwcnGN8+/btqFy5sgCJKL/S0tKQnZ0NsVh+wv/Tp0/lWn/82+DBg3Hp0iVMnz4dIpEI2dnZ6N+/P1q1avXVa9WvXx+amppyRem2bdvixYsXuHfvXq7HqKury14IL1++HKdPn4aLiwuUlJRk4wDw/PlzGBgY5HntsLAw3Lt3Dxs3bpSNZWdnY+LEiejVq1eOY589e4bg4GBs3LhRtmCJo6Mjli9fjlOnTuXZR5yIiIiIipZIJEJYWFi+W478KLYc+T7h4eGyr9k/m74YMmQI/v77b6xfvx5Xr16Fg4MDQkND+btFRFSKFJuCdl5YzC7+evTogXXr1sHV1VU2JpFI4O3tjblz5+Z5nLW1Naytrb/rWo6OjnBxccHixYtRtWpVAEBcXBxmzpyJpUuX5nrMqFGj4OHhgQ8fPsDHxwctW7bEgwcPEB8fj+joaMTGxqJq1apYtGiRbGHS3OzYsQOrVq2SGxOLxZg7dy78/Pzg7e0tty04OBhz587Nsfr2pEmT4OzszII2FbmMjAykpaVxRfgiIJFIZAtYEZUUivgcwt9F+h4ikSjXOwVJOF8K2qampihXrpzAaag48fPzw927d3H+/Hns2LEDDRo0wKxZs4SORURERUTQgvaVK1e+a3/eZlY82dnZYcuWLRg7diysrKyQlJSEGzduwMnJCVWqVCnQa+np6WHVqlVYtWqVbHZ1mTJl4Ovri4oVK+Z6TJ06dQAAnz59wqFDh6CiooJ9+/ZBVVUV3bp1g4ODA4yNjTF27FhZkTw3KioqUFFRyTFuaGiY62JACQkJMDIyyjGupKSUZ5sWosLk6+srdIRSx8bGRugIRAVGkZ9D+LtIpHhev36NmJgYAJydTTmpqqpiz549aNq0KWJiYjBnzhzUrVsXPXr0EDoaEREVAUEL2s7OzkhKSgLweSGWvG4R+rItKiqqKOPRdxgxYgQGDx6MW7duQUNDA+PHjy+0W77KlSuXY+HH/Dh48CBu374NiUSCUaNGITs7G7du3cKlS5cQEhLyzbxpaWm5/pympKTkeqyqqio+ffoEHR2dXM9FRERERES5u3z5suzr772rk0qHcuXK4Y8//oC1tTWSkpIwePBg/Pnnn/wAhIioFBC0oH3o0CGMGjUKCQkJWLJkCRdyUHAqKipo1KiR0DFyJZVKIZVK5RZsVFJSQqNGjaCnp5ev4nurVq2wf/9+9O7dW258/fr16N+/f479hwwZgtWrV8Pd3V1u/Pjx47zbgATh5uYGS0tLhWoXoKgkEglu3LghdAyiAqWIzyH8XSRSXF8K2hUrVkT16tWFDUOCOnTo0Fe3T548GYsWLUJKSgpsbW3h6+v7w61Lu3Xr9kPHERFR0RK0oF2xYkUEBwejV69euHz5MmbMmCFkHCrBWrZsiWPHjsHOzk5u/OHDh6hUqVK+ztGpUyf0798fixcvRvXq1WFqaorU1FTUqVMHzZs3z7G/paUlIiIiMHHiRAwaNAiampo4ePAgUlNTsWjRogJ5XETfQ1VVFerq6gpVjFJUEokEqqqqQscgKlCK+BzC30UixfT+/XvZ3bnW1tZc7I++6tdff4WTkxPWrVuHT58+Yd68efD19YW+vr7Q0YiIqJCIhQ5QqVIluLm5ITQ0FHFxcULHoRKqX79+OHz4MA4ePAiJRAKpVIq///4bnp6emDRp0jePj4+Px8SJExEQEIC9e/eiffv2EIvFePPmDUaPHp3ncfb29pg3bx7u37+PS5cuYejQofD29uaLciIiIiKiPPzzzz+QSqUAgGbNmgmchhRBp06dMGDAAABAXFwcPD09kZKSInAqIiIqLILO0P6iV69eqFu3LluO/ITz589j586dUFFRQXp6On777Tf06dNHtv306dPYu3cvVFRUkJGRATs7O8Fup0pNTYVUKoWmpmaRXVNJSQlr167FwYMHMXHiRACfZ1AHBgbm6+duxYoVWLp0qWw299ixYwF8/nvdvXs3hgwZkuexBgYGGDFiRAE8CiIiIiKiku/SpUsAAH19fdSuXVvgNKQoBg8ejHfv3uH06dOIjo7GkiVL4O7uDhUVFaGjERFRASsWBW2RSIQ6deoIHUNh7dy5E0+fPsXq1auhoqKC7Oxs7NixA0uWLMGMGTOwadMmfPr0CWvWrIGysjKys7OxadMmrFq1SlbcLQp3796Fn58fypQpA7FYjA8fPmDcuHFF1ndbSUkJvXv3ztEDOz8+ffqUa2uS9u3bw9XV9asFbSIiIiIiyp8PHz4gMjISwOfZ2WKx4DcVk4IQiURwdnbGhw8fcPXqVdy4cQNLly6Fm5sblJWLRemDiIgKCF8dKLjMzEycPXsWbm5usk+exWIxhgwZgvfv3+PJkycIDw/HxIkTZf+Ji8ViODg4IDY2Fh8+fCiSnM+ePcPy5cuxatUq9O3bF23btoWnpyc2btyI+/fvF0mGn/G1FiESiQR//vknTpw4gaSkpCJMRURERERUshw+fBgSiQQA243Q91NWVoabm5tswtzly5fh5+cn+5kiIqKSgQVtBXfjxg20aNEi1209evRAYGAg2rVrl+t2Ozs7nD17tjDjyQQEBKBfv34YO3Ys7t+/D5FIhFWrVkFbWxvr16//qXPHx8dj3759OHHiBDIyMgoosTxNTU3Ex8fnGF+8eDHu3r2LN2/eICMjA7Nnz4a/v3+hZCAiIiIiKun2798PANDS0kKDBg0ETkOKSF1dHfPmzUPNmjUBAH/99RfWrl2L7OxsgZMREVFBYUFbwSkrKyMzMzPXbZmZmVBRUfnm9qLw5s0b7Ny5EyEhIRg5ciQ6d+6MxYsXo2vXrrh69eoPnVMqlcLT0xMrVqyAvr4+UlNT4eTkhBMnThRwemDy5MmYOnUqnj9/Lhvbu3cvQkNDcfLkSfTv3x/dunXD6tWroaamhj/++KPAMxARERERlWRSqVT2Wr5p06ZsE0E/TEtLC/Pnz0e1atUAAGfOnEFgYKBssVEiIlJsfIWg4CwsLLB27Vo4ODjkaIuxd+9eeHh4YMaMGRg0aFCO7YcOHcKyZcuKJGdUVBRWrlyZ40Vpy5YtkZCQgOzs7O/ujxcUFITGjRvDzs5ONtajRw9MmjQJderUkb14KQiVK1fGsmXL4O/vj4SEBEgkEty/fx/Hjx+Huro6jh07hv3790NdXR0pKSmIjY1Ft27dvtqq5N9u3ryJrVu3IjMzE2pqarC3t0fdunULLD8RERERUXEnEolgZmaGiIgIdOnSReg4pOB0dHTg6emJ2bNn48WLFzh69CgAwNHRkb3ZiYgUHJ/FFZxYLMagQYMwffp0vH//HgCQkpICX19fNGjQAGXLlkX37t0xZ84cfPz4EQCQlJSEhQsXokWLFtDU1CySnDo6Onj06FGO8TNnzsDExAQpKSnffc4rV67IFbOBzy+C3dzcsGnTph/OmpcKFSrA09MTa9euxfr169GgQQMYGRkhJCQEjx49wvr167F69WoEBQVBWVkZS5Ysydd5d+/ejb1792LevHlYvXo1Zs2ahc2bN8tecBERERERlRZhYWHYtm0bateuLXQUKgH09fWxcOFCVKxYEQBw9OhRrFu3ju1HiIgUHGdolwC2trYwMjKCj48P0tPTAQCDBg2SLaLSvXt3mJiYwMvLC5mZmbJFI5s0aVJkGTt27Ijjx48jLi4Ow4YNg5KSEnbt2oXIyEhUrlw518J6Wloa9u/fj+joaPzyyy/o2bMnVFVVZds1NDRyvVaVKlWQkJBQaI/lCzU1Nbx69QpXrlyR6wMulUpRrVo1vH//Hm/fvkW5cuXyPEdKSgrOnDmDgIAA2ZiBgQGWLFmC0aNH47fffuOtlkRERERUaqirqxfZpBsqHcqWLQtvb2/MnTsXL168wMmTJ5GZmYkJEyZASUlJ6HhERPQDWCkrIczMzODr65vn9gYNGhRZe5HcDBs2DNevX0ezZs2wbNkySCQS9OzZE7Vr18b+/ftx9+5d1K1bV3br1+3bt7FkyRLY29ujffv2iIiIgL29PebNm4dffvkFAJCamprrtWJjY2FoaFjoj2nEiBFwc3PLcTvk1q1b0alTJ5QrVw5nzpzBgAED8jzH2bNn0b179xzjIpEI7du3x+XLl2FjY1Pg2YmIiIiIiEqLcuXKyYraT58+xZ9//onMzExMmTKFE4iIiBQQW45QkdDT08O4ceOwZs0a1K1bFx06dMCKFSswfvx41KpVC2FhYRg9ejROnDiB7OxsLFmyBMHBwWjXrh0MDQ3x22+/YePGjVi0aJFsIY+WLVvi999/l7vOl2Pt7e0L/THVq1cPDRo0wPr167F//34cP34ckyZNwsePH9GrVy+kpqbKzSjPzZee2blRU1NDRkZGYUQnIiIiIiIqVfT19eHt7Q0TExMAwIULF7BkyRJkZmYKnIyIiL4XC9pUZJo2bYotW7agatWquHnzJipVqoSIiAg4Oztj3LhxCA4Oxp9//omtW7fit99+y1EM1tDQQLNmzRAREQHg86zvp0+fYtKkSTh48CC2bt2KUaNGYfDgwahSpUqRPKapU6eievXq0NTURFZWFhYsWICJEycCAA4cOIDffvvtq8e3adMGx44dy3Xbn3/+CWtr6wLPTEREREREVBrp6Ohg4cKFqFWrFgDgn3/+gZeX1w+t6URERMIp8QXtmzdvomfPnrCwsMDgwYPx9OnTHPtkZmZi7ty5aNasGaytreHj48NFIn5SZmYmTp8+jYMHD+Ldu3eycbFYjFatWuHJkyfw8fGBSCSSbROJRJgzZw727NkDY2PjXM9rbGyMuLg42f5Tp06Fp6cntLS08MsvvyAkJAQtW7Ys3Af3L0pKShg+fDiOHz8OKysr6Orq4uPHj5g/fz5sbGygpaX11eP19fVhZGSELVu2yH7mJBIJ1q1bB3Nz8zz7hBMREREREdH3K1OmDDw9PVGnTh0AQEREBObMmYP3798LnIyIiPKrRBe009PT4eLigtGjRyM8PBzNmzfHpEmTcuy3fft2vHz5EmfPnsWRI0dw4cIFHDx4sOgDlxCnTp2Co6MjPnz4AE1NTSxZskSuVQjwuRid22IvZcqUQfny5REWFpbruf/++2+Ym5vLjeno6KBDhw5o1qyZrAd3UerQoQOcnZ2xYsUKTJgwAV5eXujVqxcGDx6cr+MnT54MHR0djBs3DhMmTICzszNMTEwwZsyYQk5ORERERERU+mhpacHT0xNNmjQBAERHR2PGjBl49OiRwMmIiCg/SvTqB5cvX4aenh66du0KABg3bhy2bNmCR48eoWbNmrL9njx5AolEIpshKxaL8+xr/KOioqLkZiOXVK9evcLmzZsxa9Ys2eMdMWIEzp07By8vL/Tp0wcA8Pr1a0RGRuZYVTozMxNpaWm4f/8+Dhw4ILsVDADu3r2L169fIyEhAQkJCUX3oPJp6NChct/fuXMn38f+8ssvssUuf+R4+n7//oCFiIiIiIhKF3V1dcyePRv+/v44c+YMXr9+jRYtWuDo0aNo3Lix0PGIiOgrSvQM7ZiYGJiamsq+V1JSQtWqVfH48WO5/fr164f79+/j119/hbW1NUxNTdGlS5eijlsi7N+/H6NGjcpRvG/Tpg1u3bol+75Vq1b4448/cj2+bdu2mDJlCo4dOwYfHx9s3rwZ3t7e+PPPPzFhwoRCfwxERERERERU8ikrK2PChAno378/ACA+Ph6tW7fGyZMnBU5GRERfU6JnaKekpEBdXV1uTENDA6mpqXJjGRkZ6NatG1xcXJCYmAgnJyeEhoZiyJAhBZbFzMwsx2zkkkhZWRnt27fPdVvlypVRr149AEC9evWwdOlSbNu2DX369IFUKsWePXtQsWJFODo6AgACAgKQkpKCN2/ewNDQ8Lv7SaekpGD//v149uwZGjZsiI4dO5aKfwPKH4lEIltglIiIiIiISieRSIShQ4dCX18fgYGBSE5ORpcuXbB27Vo4OTkJHY+IiHJRogvaGhoaSEtLkxtLTU3NsVDfrFmzsHjxYujq6kJXVxdOTk4IDg4u0IJ2cZSeno7AwEBERUVBSUkJ2tracHFxgZGR0Q+fs1y5cnj69Gmuizr+d+Xo6dOn4/Xr1zh69KhsgUdDQ0O5fTQ1NVGtWrXvzhEeHg5/f3+MGjUKbdu2xeXLlzFixAj4+vqicuXK332+gnbv3j0EBgZCIpEgPT0d1tbWGDZsmCA9wImIiIiIiEo7Ozs7dOjQAUOHDkV6ejrGjRuHu3fvYsWKFVBWLtGlEyIihVOin5VNTU2xf/9+2fcSiQRPnz6FiYmJ3H6vX79GZmam7HtlZeUS/x9WVlYWxo0bh7Fjx2L8+PEAgLi4OMyYMQMeHh5yrVq+h729PXx8fLBmzRq54uy+ffvQokWLHPtXrFgRo0aN+rEHkYeMjAysXbsWmzZtks3ItrCwwPXr19G5c2d4e3ujU6dOgs3WDg8Px9atW7Fo0SLo6upCKpXi2LFjcHV1hYmJCZ49ewbg8wuq3377rVT0XiciIiIiIhJa3759UbVqVfTo0QNxcXFYs2YN7t+/j127dkFPT0/oeERE9P+V6OmgVlZWePfuHQ4cOICMjAysX78exsbGqFGjhtx+LVu2xKpVq5CYmIg3b94gKCgIHTt2FCh10Th48CB69+4NKysr2ViFChWwZs0a+Pn5/fB5jYyM0K9fP4waNQrbt2/HkSNHMGXKFDx69AgjRowogOTfdvToUQwcOFBWsN6wYQOCg4MxduxYdO/eHc+fP4e9vT0SExOLJM9/BQYGYtWqVdDV1QXw+Ra3+vXr4+rVqzAxMcHq1auxbNkyvHr1Ch4eHoJkpJIrOzsbEomEfwr5z5dFhomIiIhIsVhZWeHKlSswNzcHAJw8eRLW1ta4d++ewMmIiOiLEj0NWV1dHQEBAZg3bx4WLFgAMzMzWbHWzs5OVuBcsGABFi5cCFtbWygrK6NXr14YOXKkoNkL2/nz57Fy5coc42XKlIFEIvmpc7dp0wYtW7bEpUuXkJSUBA8PjyL7NPvp06c4ceIE2rZtC6lUivv37+P169dYtGgRAKBmzZqoX78+OnbsiEWLFmHx4sVFkuuLjx8/onz58rh27Rri4uJgaWkJIyMj+Pr6YufOndi8eTP69u0LVVVVjBw5EqtXr8aVK1fw66+/FmlOKrlu3LghdAQiIiIiomKtatWquHDhAoYOHYqDBw/i3r17+PXXX7F582b06dNH6HhERKVeiS5oA0D9+vWxd+/eHONHjhyRfa2np4dly5YVZaxiQSqVFtq5lZSUYGNjU2jn/6+0tDTMmjULenp6qF+/Pg4ePIgjR45AS0sLnp6esv2uX7+O3r17o0yZMvjw4QOkUmmRtvR48OABDh06hJo1a8LY2BhBQUFITEyERCKBlpZWjjYo9vb2WLhwIQvaVCCaNm0qdITvkpaWJltxfvfu3TkW+SUiIiIiKiza2trYt28f5s2bh4ULFyIpKQl9+/bFtGnT4OPjU+LblBIRFWd8Bi6lOnTogD/++AO9e/eWG3///j1UVVUFSvXjFixYgNGjR6NevXoAPheu3dzc0KNHD9ms/PPnz6NcuXIoU6YMgM8z+LOzs4usl3Z6ejpWrVqFX3/9FcOHD4eKigpsbW1x9uxZjB8/Hv7+/ujbt6/cMerq6sjIyCiSfFRyKSkpoUuXLkLH+G7Jycmyrzt27JhjQV9FIVS/fiIiIiL6OWKxGF5eXrCyssKwYcPw4cMHLFu2DFeuXMH27dtRuXJloSMSEZVKLGiXUnZ2dnB2doauri7atWsHkUiE2NhYeHh4yNpzKIrExESkp6fLitkA4OfnBw8PD2hpaaFXr16oXr06jIyMMGfOHACfZ6cnJiYWaaHpwIEDGDlyJMqXLw9XV1fMnTsXa9euRVZWFl6/fo3Tp08jPj4eXl5eKF++PIDPvc5/++23IstIJZciFlX/nVlJSUkhHwNRSaNo/eEVLS8RERVPXbt2xbVr19C7d2/cvHkT58+fR8OGDRESEoLu3bsLHY+IqNRhQbuUUlJSgr+/P/73v//BxcUFSkpKKF++PJYtWwZDQ8Miz/Pq1SusX78e79+/R1ZWFlq2bImBAwdCLP72uqUvX75EzZo15cbKlCmDlStX4saNGxg6dCgCAwNRpUoVAJ+L2UuXLs0xG7qwPXz4EO3atUP58uUxa9Ys9OvXD9WrV4e+vj6sra1Rrlw5zJo1C9OnT8emTZsQGRmJY8eOISgoqEhzEhER5YV9+ImIqLQyNTXFpUuX4OrqipCQELx79w49evSAs7Mzli1bBg0NDaEjEhGVGixol2LKysqwt7eHvb29oDmio6Ph5eUFLy8vVK1aFVKpFEeOHMGkSZOwatWqb/a4rly5Mh49epTrtpcvX2L69OlYsmQJRCIRtLW18fr1a/Ts2ROdO3cujIeTp1q1auHmzZvo0KEDdHV1YWNjg6VLlwIAJk6ciMGDB2Pp0qV4/vw5evfujWbNmsHf3z9fRX0iIqLCVhh9+Nkrn4iIFImGhgaCg4Nha2sLJycnfPz4EevWrcO5c+cQGhoKCwsLoSMSEZUKLGiT4FasWAF/f39Zf1yRSISuXbvi7du3+Ouvv9C6deuvHl+mTBmoqqri7t27qFu3rmw8NTUVO3bsQEhICIyMjHDgwAG8ffsW9evXR6tWrfI8X3Z2NpKTk6GlpVWgxeSePXvCwcEBLVu2xKNHj9CwYUMAwM2bN6GjowMrKytYWVnh9u3buHjxIhwdHQvs2kRERD+qMPvwF2WvfLYtIiKigjJw4EBYW1tjyJAh+Pvvv3H37l38+uuvmDVrFtzd3RVyXSoiIkXCgjYJSiqVQiQS5foGduDAgZgzZ843C9oAMH/+fMycORP6+vpo0aIFYmJiEBYWhnnz5sHLywumpqZYsWIFVFVVERkZCVdXVyxZskRuEY/s7GwsX74cjx49Qrly5fD27VuYmppi2rRpBfImWE1NDXPmzMHo0aNhYWGBiIgIPHr0CElJSfDx8ZHt9+DBAxgbG//09YiIiApKYRWD2SufiIgUVbVq1XDu3Dl4e3vD09MTWVlZ8PLywoEDB7Bp0yY0btxY6IhERCUWexkooOjoaKxZswbr1q3DixcvhI7z3aRSKS5duoRRo0ahadOmOHz4MAIDA5GSkiK3n1gszvdiTurq6vDz88PIkSORkpICCwsLbNmyBe/fv0eFChVgb28v+5S8YcOGWL16NZYsWSJ3Dg8PDzRr1gwBAQFYtGgRAgICYGNjg7lz5xbMAwdgZmaGrVu3wsbGBm/fvkX37t2xfPlyWbb09HTs378ftra2BXZNIiIiIiIiKnjKysrw8PDAlStXYG5uDgC4desWrKysMHPmTLk7kYiIqOBwhrYCkUqlmDdvHlRVVdG3b19kZWVh3bp1MDAwwNSpU4WOly9SqRTu7u6IjY1F1apVcejQIYwcORJ79+7F2bNnsXTpUhgZGUEkEmHv3r3o1KkTwsPD8fTpUzRo0AC1a9f+6vmrVauGatWqyb7fs2cPPDw8cuynr6+PrKws2Qzx+Ph4SCQStGzZUm6/Fi1a4MiRI3j9+jUqVqxYIH8HIpEIVlZW2LZtG6ZNmwZra2s0a9YMDx48wIEDBzB79mzOUCOifMnvh370c/j3TEREVDocOnToh4/18PDAnj17sHv3bkgkEixZsgQhISEYM2YMrKysvrk2VGHp1q2bINclIipMLGgrkJ07d8LCwgK9e/eWjS1atAgbNmzAmTNn0L59ewHT5c+ZM2dgYGCArKwsLF68GMDnHtpjxoxBZGQkLC0tUblyZWhqaiI+Ph6qqqqoVKkSdHR0ULt2bXz69Am+vr7Q0dHJ1/UyMjLyXGBKSUlJVtC+cuVKnq1N2rZti/DwcHTv3v3HHnQeypYti5CQEFy5cgXh4eEwNjbGli1bWMwmony7ceOG0BGISEF9+vQp3/tmZ2fj3bt3hZalbNmy37VuSX5fBxIRFSUVFRUMGjQIzZo1w9q1a/Hw4UO8efMG3t7e+PXXXzFmzJgCmyRFRFTasaCtQM6fP4/169fnGB81ahSmTp2qEAXtQ4cOoWLFinILHkZFReHt27coU6YMtLS0ULNmTfzzzz/4+PEjHj9+jLJlyyI1NRWurq5wcHCAu7s7Vq9ena/rtWvXDkeOHEGPHj3kxrOyspCeni5786Svr4+HDx/meo64uDi5Wd8FSSQSoWnTpmjatGmhnJ+ISi5FfN5IS0tD//79AQC7d+/O8wNHIkUhlUpztEzLy79vO8/vLeiampqFNqNPV1e3UM5bFKRSqdARiIjyZGJiAl9fX5w6dQpbt25FUlISrly5gps3b6Jv377o3bs3F40kIvpJLGgrEDU1tVzf1Kiqqn7XrBYhZWdnIyUlBQYGBrKxefPm4e+//8aCBQtQvnx5fPjwAf3790dgYCDWr18Pd3d3aGhoYPHixVi+fDn09PTw6tUrVKpU6ZvXs7Ozg4ODA2rVqoW6desC+FxQmTlzJkaPHi3b70vv7CFDhkBZ+f9+LbKysnDy5Els3ry54P4SiIh+gpKSErp06SJ0jB/y7yJex44dc10QuLjjXTT0hVQqhY2NDS5evPjdx1aoUCFf+7Vo0QJhYWGC3aZOREQ/RklJCZ06dYK1tTU2b96MM2fOICMjA9u3b8fZs2fh4OCApk2b8vmdiOgHsaCtQCQSCVJTU6GhoSE3/vbtW4WZ5VarVi2oq6vj2LFjGDx4MCQSCcRiMbS0tJCdnY2nT59CXV0dHz9+xPz58zFhwgS4u7sDAMqXL4/k5GQ0bNgQT548yVdBW0lJCevXr8eKFSuwZs0aqKioQCKRYMyYMbCwsJDtJxaLMWHCBIwePRoTJkyAubk5IiMjsXr1akyYMEFhPjAgotJBUYuq/86tpKSksI+D6AtFLkR8/Pgx3/sWt5YjRESKQldXFxMnToStrS3Wr1+PJ0+e4PXr11i0aBEaNWqE0aNHw8jISOiYREQKhwVtBTJy5EgsXLgQCxculL2BkkgkWLBgASZOnChwuvwZOXIkxo0bB6lUil9//RWmpqbIzs6Gm5sb1NXV0aFDB5w8eRK//PILbty4IfdGUSqVIisrC3fu3EGHDh3yfU0NDQ3MmTPnm/s1btwYq1atwvbt27Ft2zbUrFkTfn5+Cn1LLhERERUOkUiEsLCwfLcc+RGF2XLke/tQ6+npFUoOIqLSoG7duvDz88OxY8cQGhqK5ORkXL9+HRMmTEC3bt0wYMAAaGpqCh2TiEhhsKBdDKSlpeHYsWNISEhA8+bNYWZmlut+TZo0wdu3b+Hg4IAGDRogMzMT9+7dg4ODA2rWrFnEqX+Mjo4Oli1bhoULF2LgwIFIT0/Ho0ePULlyZUycOBF2dnZITExEcnKybLHIL86dOwcjIyO8ffsWhoaGhZJPV1cX48aNK5RzExERUckiEokUsnUOEREVPSUlJXTt2hUtW7bEtm3bcPLkSWRlZWH//v04d+4cRo4cidatW/OOFSKifGBBW2Bnz57F//73PwwcOBCmpqY4cuQI/P39sXz5cqipqeXYv1OnTujYsSOio6OhpKSE6tWrK9ztrpUqVYK/v79sQZ9Tp05h4sSJEIlEkEqlsLOzQ4cOHZCZmYmoqCgsW7YM8fHxOHfuHJo2bYolS5YI/AiIiIiIiIiIvp+uri5cXFzQsWNHBAYG4t69e3j//j1WrlyJY8eOwdHRUWEmrBERCYUFbQG9ffsWO3fuREhIiKwobW5ujlu3bsHb2xsLFizI9TiRSFQi/oP78ph/++03bN68Ge7u7pg9ezbEYjGsra3RtWtXnDp1CpGRkahTpw527doFExMTgVMTERERERER/ZyaNWtiyZIlOHfuHDZv3oz379/j3r17mDp1KmxtbTFs2DC2vyQiygML2gLatm2bbGbyvzVo0ADr1q2DRCIpNQtmWVlZ4dSpUznGu3TpIkAaIiIiIiIiosIlEonQtm1bWFlZYdeuXTh06BCysrJw8uRJ/P333xgyZAg6d+5cauoCRET5xYK2gJ4+fYpffvkl121ly5ZFcnLydy/YU5xIpVJcvnwZd+/eRfXq1dG2bdsS2w/s6tWriIyMRJUqVdChQwfcuHEDBw4cgFQqRffu3dG0aVOIRCJkZWXhyJEj+Pvvv6Gvr4/BgwejWrVqQscnIiIiIiIigWhqasLe3h62trYICgrCjRs3kJycjMDAQJw4cQKOjo5o0KCB0DGJiIqNklldVBANGjTAP//8k+u2uLg4aGtrF3GighMfHw97e3vcvXtXtpjliBEj8OjRI6GjFaj379/DwcEBV65cQePGjZGYmIiGDRti//79mDp1KqZPn44bN25gypQpePfuHezt7SESieDp6YnBgwdj/fr12LRpk9APg4iIiIiIiARmZGSE+fPnY86cOahYsSIA4MmTJ5gzZw58fX3x5s0bgRMSERUPnKEtoAEDBsDR0RGNGzeGhoaGbPzw4cOwsLBQ6NnM7u7uWLZsGcqVKwfgc2/wbt26wdHREVu3blXox/Zvc+fOhaenJ6pUqQIAuHfvHjw8PLB582YEBgZCV1cXffr0wdWrVzFkyBAEBwejSpUqyMjIwJUrV6Cvr49Dhw6hZcuWJaIvOpVOUqkUKSkpBX7e5OTkXL8uSJqamgq3sC4RERERlVwikQhWVlawtLTEgQMH8PvvvyM9PR0XLlxAeHg4+vXrh169ekFVVVXoqEREgmFBW0CampqYN28eXFxcYGZmhooVKyI8PBzGxsaYNm2a0PF+WExMDExMTGTF7C80NTXRqVMnhIWFoXXr1gKlKzjx8fHQ09OTFbMB4MyZM1BSUoKxsTHKlSuHxo0bY9GiRWjYsCGeP3+OKlWqICoqCosWLcLQoUMxZMgQVKhQAX369MH+/fthamoq4CMi+n5SqRQ2Nja4ePFioV6nQoUKhXLeFi1aICwsjEVtIiIiIipWVFVV0b9/f7Rt2xabN29GWFgYMjIyEBoaitOnT8PV1RXm5uZCxyQiEgQL2gKrVasWQkJC8OjRIyQkJKB3797Q0tISOtZPefr0KWrVqpXrttq1a+PevXtFnOjnPH78GDt37sSnT5/Qtm1b2NraQiwW48WLFzkK0Ldu3YK/vz+0tLRw+vRpWFhYwM/PDzNmzIBUKoVUKoW3tzeCg4OhpqYGABg6dCiuXbsGT09PbN68WYBHSPRzWAwmIiIiIioc5cuXx/Tp09G5c2cEBATgyZMniIuLw9y5c9GpUyeMHDkSmpqaQsckIipSJbqgffPmTcybNw+xsbGoW7cuFi9eDGNj4xz7BQcHY9OmTUhPT0erVq2waNEiqKurF2nWktRuonbt2jh58iT69u2bY1t4eDisra0FSPVj1q9fj5cvX8LR0REGBgY4cuQIRo0aBX9/f5iammLbtm1y+6empsLIyAgnTpxAvXr1ZOMODg7YtGkTLly4AFtbW1kxGwBOnTqF1q1b4/Xr14iMjETDhg2L7PER/SyRSISwsLBCaTlSFNhyhIiIiIgUQf369eHn54ejR49i69atSE9Px/Hjx3Ht2jWMHz8eFhYWQkckIioyJaORcS7S09Ph4uKC0aNHIzw8HM2bN8ekSZNy7Hf06FHs2LEDO3bswLlz5/D+/XsEBQUVfeASpGLFikhLS0NUVJTc+KtXr3D9+nU0atRIoGTf5/bt23j79i28vLxQtWpVaGlpoX///nB3d4ePjw90dXWhrq6O69evy46xsLDA1KlTceLECVlblczMTKxcuRJ169bFpk2bUL16ddn+cXFx2LZtG3r06AETExO8evWqqB8m0U8TiUTQ0tJSyD8sZhMRERGRolBSUkK3bt2wZs0aNGjQAADw5s0beHh4YO3atQo7yYSI6HuV2Bnaly9fhp6eHrp27QoAGDduHLZs2YJHjx7JzYb+/fff4erqiqpVqwIAfH19kZaWVuB5oqKiSlXhZPDgwViyZAmUlZVRu3ZtxMbG4t27d5gwYQLu3LkjdLx88fPzg729fa55Hzx4gDt37qBfv37w9/dHVlYW6tatiytXrqBy5crQ0NDAqFGjIBKJkJiYCCsrK+jp6UEsFmPcuHGwsbFBUlISxGIxnJ2d8eDBA/zxxx8YNGiQwvz9KDqpVCp0BCIiIiIiou9WsWJFeHl54fjx49i8eTPS0tJw8uRJREREYPLkyXJ3CxMRlUQltqAdExMj199YSUkJVatWxePHj+UK2lFRUWjXrh26deuGhIQEdOzYETNnzhQicomirq6O6dOnIyEhAU+fPkXjxo0LbVG3wpKamgpdXd1ct6moqEAqlUJFRQWTJk3Cx48fERsbi4EDByI1NRVDhgxBamoqpFIpxGIxFixYgFmzZkFHRwcxMTFo164dateuDRUVFQDAvXv3kJGRgfLlyxflQyQiIiIiIiIFJBaL0aVLFzRq1Ahr165FZGQk4uPjMXv2bPTu3RuDBw+Wvd8kIippSmxBOyUlJUcfbA0NDaSmpsqNffr0CQcOHEBQUBBUVVXh7OyMgIAAjB8/vkDzmJmZQUlJqUDPSYWrXbt2+PTpE5o3by43np2dDQ0NDdSvX19u/Mt+O3bswMqVK1G/fn18+PABz58/x7Jly/DLL78A+NyzfcGCBbh8+TJMTU3x6NEj6OjoICAgAKqqqkXz4AgSiQQRERFCxyAiIiIiIvphFStWhKenJ44ePYrNmzcjIyMDe/fuxfXr1zF16lSh4xERFYoSW9DW0NDI0TokNTUVWlpacmMqKioYNmwYKlasCAAYNWoUNmzYUOAFbVI8gwYNwpgxY2BmZgZ9fX0An9tULFmyBP379//qcf3790dsbCy0tLRkP1tfaGhoYPHixUhMTMTr169RuXLlHD+XRERERERERPkhFovRtWtXNGzYECtWrMDjx48RExODyZMnQ1tbGyNGjBA6IhFRgSqxBW1TU1Ps379f9r1EIsHTp09hYmIit1/16tWRlJQktx976xIAaGpqYtmyZZg7dy5UVFSgra2Nly9fonfv3vjtt9++eqySkhJq1Kjx1X3KlCmDMmXKFGRkIiIiIiIiKqWMjY2xdOlS7Nq1C3v27EFmZiamTJmC4cOHl6o1vYio5CuxBW0rKyu8e/cOBw4cQJcuXRAYGAhjY+McRcYePXpg+/btsLW1hYqKCkJCQr5ZrKTSo1KlSli7di3S0tKQlpYGXV1dvhAgIiIiIiKiYklFRQVDhw5Fo0aNsGfPHvTt25fvYYmoxBELHaCwqKurIyAgAP/73/9gZWWFixcvws/PDwBgZ2eHP/74AwAwcuRIdO3aFQMHDkTHjh1Rv359ODg4CJiciiN1dXXo6enxhQAREREREREVe3Xr1oWHhwdmzJghdBQiogJXYmdoA0D9+vWxd+/eHONHjhyRfS0Wi+Hs7AxnZ+eijEZERERERERERERE36nEztAmIiIiIiIiIiIiopKFBW0iIiIiIiIiIiIiUggluuUIUX69e/cOGzduxIsXL5Ceno7s7Gyoq6tDKpXCwMAACQkJEIvFMDY2hoODA/T19YWOTEREREREREREVOpwhjaVek+ePMHkyZPRs2dPzJw5E4mJiTA1NYWOjg7U1NTw/v17qKqqYtWqVejSpQvGjx+PFy9eCB2biIiIiIiIiIio1OEMbSr1li5dirVr10JHRweTJk3CmjVrULZsWUyYMAFlypTB8uXLsXHjRvz1119o3bo1Vq9eDU9PT/j5+QkdnYiowEmlUqSkpBTKuZOTk3P9uiBpampCJBIVyrkp//L7c/SjPxP8dyYiIiIiKr1Y0KZSTSKRQCQSQUdHBwCQnp6OsmXLAgCys7ORmpoKABgyZAjmzJmD1q1bw8DAABkZGYJlJiIqLFKpFDY2Nrh48WKhX6tChQqFct4WLVogLCyMxU4B/ejP0ff8TPDfmYiIiIio9GLLESrVsrOzoaz8f5/rKCkpyW2XSCQAAFVVVWRlZcnGxWIxpFJp0YQkIipCLBBSQeDPERERERERFRbO0KZSTUVFBUlJScjKyoKysjKysrKQnp4ONTU1qKmpoUyZMgCAo0ePom3btgCAjIwMZGVl8c06EZU4IpEIYWFhhdZypCiwFYXwiuLniP/ORERERESlFwvaVOo5Ojpi6tSp8PHxgbOzMyZNmoQhQ4YgISEBb9++xb59+/DHH39g48aNSE5OxvTp0zFu3DihYxMRFQqRSAQtLS2hY5CC488REREREREVFha0qdT79ddfoaamBjc3N4jFYrx//x4zZ86Eubk5MjIyEBgYiKpVq2LKlCkAAFdXV9StW1fg1ERERERERERERKUPC9pEABo2bIi1a9cKHYOIiIiIiIiIiIi+gotCEhEREREREREREZFCYEGbiIiIiIiIiIiIiBQCW44UIqlUKvtaIpEImISI/uvfv5P//l1VBHxuISreFPX5hc8tRMWboj63AN///CISiQozDlGp8q3fudL03EJERaswn19Y0C5E2dnZsq9v3bolYBIi+pp//64qAj63ECkORXp+4XMLkeJQpOcW4PufXypVqlSYcYhKlYiIiHzvW9KfW4hIOAX9/MKWI0RERERERERERESkEERSRbunRIFkZ2cjKysLACAWi3nrHFExIpVKZZ8QKisrQyxWnM/3+NxCVLwp6vMLn1uIijdFfW4B+PxCVJzxuYWICkthPr+woE1ERERERERERERECkFxPnojIiIiIiIiIiIiolKNBW0iIiIiIiIiIiIiUggsaBMRERERERERERGRQmBBm4iIiIiIiIiIiIgUAgvaRERERERERERERKQQWNAmIiIiIiIiIiIiIoXAgjYRERERERERERERKQQWtImIiIiIiIiIiIhIIbCgTUREREREREREREQKgQVtIiIiIiIiIiIiIlIILGgTERERERERERERkUJgQZuIiIiIiIiIiIiIFAIL2kRERERERERERESkEFjQJiIiIiIiIiIiIiKFwII2ERERERERERERESkEFrSJiIiIiIiIiIiISCGwoE1ERERERERERERECoEFbSIiIiIiIiIiIiJSCCxoExEREREREREREZFCYEGbiIiIiIiIiIiIiBQCC9pEREREREREREREpBBY0CYiIiIiIiIiIiIihcCCNhEREREREREREREpBBa0iYiIiIiIiIiIiEghsKBNRERERERERERERAqBBe0iFBsbC1tb26/u8+TJEwwdOhSDBw+Gs7MzkpKSiigdERERERERERERUfHGgnYRCQ0NxZQpU/D+/fuv7rds2TKMGTMG27dvR506dbB9+/YiSkhERERERERERERUvCkLHaC0KFeuHLZv3w4bGxsAQFJSEtzd3fH27VtkZWVhwoQJaN68OVatWgWRSITs7Gy8evUKDRo0EDg5ERERERERERERUfHAgnYR6dixo9z3GzZsQL169TBmzBh8+PABAwYMwKFDh6CqqooPH/4fe3cdFlX+/n/8OUNIKKBY2C3YLQrqGmt3rx1goCjYimKLXVgo2LG6dq26u8a6omJ3LAY2gk3DML8//Dnf5QMqygwDeD+uy+uS9zlzzmsQDzP3vM/9fkvnzp0JDw+nf//+ekoshBBCCCGEEEIIIYQQaYsUtPXk7t27hIaG8vfff2vGgoODyZ8/P1ZWVhw6dIhz584xdOhQ9uzZo8ekQgghhBBCCCGEEEIIkTZID209KVq0KJ07d2bDhg34+vrSqFEjcuXKxYABA7h9+zYA5ubmKJXyTySEEEIIIYQQQgghhBAgM7T1ZsCAAUyYMIF9+/bx/v17OnbsiLGxMQMGDGDSpEkYGRmhUCjw8vLSd1QhhBBCCCGEEEIIIYRIExRqtVqt7xBCCCGEEEIIIYQQQgghxNdIPwshhBBCCCGEEEIIIYQQ6YIUtIUQQgghhBBCCCGEEEKkC1LQFkIIIYQQQgghhBBCCJEuyKKQOhQfH09cXBwASqUShUKh50RCiE/UajXx8fEAGBoaolSmn8/35NoiRNqWXq8vcm0RIm1Lr9cWkOuLEGmZXFuEELqiy+uLFLR1KC4ujmvXruk7hhDiK8qWLYuxsbG+YySbXFuESD/S0/VFri1CpB/p6doCcn0RIr2Qa4sQQle0fX1JPx+9CSGEEEIIIYQQQgghhPihyQxtHfrvVPqyZctiYGCQ4mPeunULADs7uxQfKzWl19wg2fVF19lVKpXm0/z0dFsd6ObaIoTQnvR6fZFrixBpW3q9tsCXry/yejX1Se7UldZzZ9RrixBC/3R5fZGCtg79t3+TgYGBVi6un46Z3i7U6TU3SHZ9Sc3s6a3Xmi6uLUII3UhP1xe5tgiRfqSnawt8+foir1dTn+ROXekpd0a6tggh0hZtX1/S18dvQgghhBBCCCGEEEIIIX5YUtAWIgOLi4sjNjZW3zGEEEIIIYQQIsNQq9VERUWhVqv1HUUIIX5I0nJEiAzo/v37zJ07l3fv3mFgYICJiQn9+/encuXK+o4mhPiBhYeH8+jRIyIiIjAzM6NAgQKYm5vrO5YQQgghRLJERkYyY8YMQkJCsLCw4PXr1/z0009069ZN39GEEOKHIgVtITKYly9fMnnyZJYuXUpQUBAAJUuWxN3dHRMTE0qXLq3nhEKIH9Hjx4+5cuVKgplM9+7do3z58uTPn1+PyYQQQgghkmfo0KEMGzYMW1tbzdj69evx9fXFyclJj8mEEOLHIi1HhMhgVq1axcSJE8mcObNmzNDQEC8vL3x8fPSYTAjxowoPD9cUs3PkyEGpUqXIkSMHarWaK1euEB4eru+IQsvUajXh4eE6+yO3eAshhEhtAQEBVKpUKUExG6BHjx4EBARIq0chhEhFMkNbiAwmODiYIkWKJBr/b4FbCCFS06NHjzTFbHt7ewCKFi3KmTNnCAkJ4dGjR9jZ2ek5pdAWtVqNo6Mj/v7+OjuHg4MDJ0+e1Ppq6UIIIcTnnDx5knbt2iW5rWzZsjx48IASJUqkciohhPgxSUFbiAwmPj6euLg4DA0T//eWWQNCCH2IiIgAIEeOHAnGc+TIQUhICJGRkfqIJXRICs1CCCEyGisrK16+fEmhQoUSbQsNDcXS0jL1QwmRivbt25cq52nRokWqnEekbz9Ey5E1a9YwZsyYL+6jVqvp3r073t7eqZRKCN1o1KgR27ZtSzR+9uxZSpYsqYdEQogfnZmZGQAhISEJxj99bWpqmuqZhO4oFApOnjxJWFjYV/8EBwdrHhccHJysx4SFhcnsbCGEEKmubdu2rF27NtH4hw8feP78Obly5Ur9UEII8YPK0AVtlUrFypUrmT179lf3XbduHefPn0+FVELoVvPmzbl27RpLliwhPDycmJgYNm/ejJ+fH4MGDdJ3PCHED6hAgQIoFApCQkI4c+YM9+7d07QbUSgUFChQQN8RhZYpFArMzc2T9eeT5O5vbm4uxWwhhBCpLmvWrDRo0AB3d3eCgoJQq9WcOnUKFxcXxo0bp+94QgjxQ8nQLUdGjx7Nhw8f6NChAzExMZ/d78GDB2zbto2ff/45FdMJoRsKhQIvLy/OnTvHihUriIuLo0ePHvj4+EgBQAihF+bm5pQvX54rV64QEhKimZmtUCgoX758gqKmEEIIIURa1bZtW6pVq8b69esJDg6mQoUK+Pj4aO5GE0IIkToydEF71KhR5MyZE29vb54+fZrkPiqVirFjxzJhwgT27Nmjsyy3bt3SSjExOjoagBs3bqT4WKkpveaG9JvdzMxMMyM7U6ZM3Lx5U8+Jvo2uv+9qtVonxxVCJC1//vxky5aNR48eERkZiampKQUKFJBithBCCCHSlXz58smMbCGE0LMMXdDOmTPnV/fx8/OjRIkS1KhRQ6cFbSGEEOJHZ25ujp2dnb5jCCGEEEIIIYRIxzJ0Qftr/v33X3bs2MGOHTt0fi47OzsMDAxSfJxPs1VLly6d4mOlpvSaGyS7vug6u0ql4vLlyzo5thBCCCGEEEIIIYTQjR+6oP3nn3/y8uVLfvrpJwCioqJQKBRcv34dHx8f/YYTQgghhBBCCCGEEEIIkcAPXdAeOHAgAwcO1Hw9ZswY8ubNi6urqx5TCSGEEEIIIYQQQgghhEiKUt8B9KFixYqcP39e3zGEEEIIIYQQQgghhBBCfIMfYob2/864vnTpUpL7zZw5MzXiCCGEEEIIIYQQQgghhPgOP0RBWwjxY3j9+jUrV67k6dOnxMfH4+joSMeOHbWyIKsQQgghhBAifVCpVGzbto1//vkHpVJJ3rx56devH9myZdN3NCGEEFrwQ7YcEUJkPM+fP2fo0KG0bdsWb29vlixZgqWlJUOGDCE+Pl7f8YQQQgghhBCpID4+niFDhmBhYcGSJUvw9vambdu2DB06lGfPnuk7nhBCCC2QGdpCiAxh7ty5LFiwgOzZswOgUCho2rQpHz584NChQzRt2lTPCYVIH9RqNREREfqO8d3MzMxQKBT6jiF+ELr+/yI/z0II8e0OHTpE7dq1adasmWasRIkSLFiwAC8vL+bNm6fHdEIIIbRBCtpCiAwhMjJSU8z+r7Zt2zJ8+HApaAuRDGq1GkdHR/z9/fUd5bs5ODhw8uRJKQIKnUuN/y/y8yyEEN/u0KFDSRats2fPTmRkpB4SCSGE0DZpOSKEyBA+92bfwMAAtVqdymmESL+kcCZE8sn/FyGESHvUavVn19CR67YQQmQMMkNbCJEhKJVKwsLCyJw5c4Lxw4cPU6tWLT2lEiJ9USgUnDx5UmctFMLDw8mVKxcAwcHBmJuba/0c0qJBpJZv/f/yPT//8vMshBDfrlatWhw+fJgmTZokGA8PD0eplDl9QgiREUhBWwiRIQwZMoQhQ4Ywd+5czerlly9fZuvWraxatUrP6YRIPxQKhU4Kzf/L3Nw8Vc4jhC597/8X+fkXQgjdadOmDc7OztjY2FChQgUAXr9+zciRIxkzZox+wwkhhNAKKWgLITKE4sWLM2HCBLy8vIiKikKlUlGkSBGWL1+OkZGRvuMJIYQQQgghUoGRkRHLly9n6dKlrFy5EgMDA0xMTBg/fjyFCxfWdzwhhBBaIAVtIUSGUbhwYebMmaPvGEIIIYQQQgg9MjU1ZcSIEfqOIYQQQkekgZQQQgghhBBCCCGEEEKIdEEK2kIIIYQQQgghhBBCCCHSBSloCyGEEEIIIYQQQgghhEgXpKAthBBCCCGEEEIIIYQQIl2QRSFFuvTmzRsOHTpEfHw8DRs2JEeOHPqOJIQQQgghhBCpSq1Wc+rUKf7991+KFy+Og4MDCoVC37GEEEIInZIZ2iLd8fHxYfLkyeTNm5fChQsze/Zs5s2bp+9YQseio6PZunUrU6dO5ddffyU6OlrfkYQQQgghhNCbJ0+e0LNnTwIDA6lQoQKBgYH07NmTp0+f6jua0JLbt28ze/Zs5syZw927d/UdRwgh0gyZoS3SlZMnTxIeHs7ChQs1YzVr1mT16tXs27ePFi1a6C+c0Jnbt28zbdo0evbsyYABA7h69Sp9+/Zl3LhxlCpVSt/xhBBCCJEBqNVqIiIidHoOMzMzmT0rtGbChAl4e3tjaWkJQMWKFWndujXu7u6sWbNGz+lESqjVasaPH4+FhQWdO3cmPj6ezZs3Exsby8SJE+U6IoT44f0QBe01a9Zw584dZs6cmWjbixcvmDRpEhcvXsTExIROnToxaNAgPaQUybFt2zbmzJmTaLxnz54MGjRICtoZkFqtZsaMGfj6+mJiYgJA/fr1cXR0xMnJifXr18sLOj1LjQKArkhhQQjxXyqVKlWOrVKpdHYuAwMDnRw3o1Or1Tg6OuLv76/T8zg4OHDy5En53SNS7MqVK1SpUkVTzP7EysqKSpUqcfXqVcqVK6endCKltm3bRqVKlWjXrp1mzMPDg02bNrF3715atWqlx3RCCKF/GbqgrVKp8PPzY8GCBZ+94I8bN44iRYqwePFiXr58Se/evSlQoIAURtMohUKhKWr+l4GBAcbGxnpIJHTt/Pnz1K5dO9G/e6ZMmahbty5nz57F3t5eT+lEahUAdEUKC0KIT1QqFQcPHtTZ8aOiojR/P3z4cJKvZ7ShadOmUtT+TvK7QKQnDx8+pGTJkklus7W1JSgoSAra6djx48dZtmxZovHOnTvj6uoqBW0hxA8vQxe0R48ezYcPH+jQoQMxMTGJtsfHx2NsbMyAAQMwNjYmX7581K9fn8uXL2u9oH3r1i2tvEj+1Df4xo0bKT5WatJW7nfv3nH27FkyZ86cYDwmJoaQkBCdfF/S6/ccMkb2gIAAjIyMknwO8fHxnDt3jixZsnzz8dVqdYozio+kACCEyEgCAgJ0duzx48cDcPXqVZ0cv1q1ajo57o9AoVBw8uTJZN9xFB4eTq5cuQAIDg7G3Nw8WY+TO4OEtpQqVYodO3bQoEGDRNvOnz9Phw4d9JBKaIuRkVGS1woDAwOMjIz0kEgIIdKWDF3QHjVqFDlz5sTb2zvJhTGUSiUrVqzQfB0bG8upU6fo1q1basYU36B169asWrUKNze3BL/g16xZQ7NmzfSYTOiKnZ0dv/32Gw4ODom2XbhwIcFteCL1fWsB4Ft8b7HgW0hhQQiRlIoVK6JUpp+10+Pj47l06ZK+Y6R7CoXiu37XmJub6+R3lBBfUrx4cYKCgggKCqJgwYKa8YcPH/L48WOKFSumx3QipQwMDHj//j0WFhYJxl+9eiV3JgshBBm8oJ0zZ85k76tSqRgzZgxGRka0adNG61ns7Oy0cvvnp1mqpUuXTvGxUpO2cpcuXRoTExMWLFhAzZo1MTAw4NSpUzRs2FBnsxDS6/ccMkb2evXqcfDgQWJjY6lQoYJm+5UrVzA1NU1yVkpyqFQqLl++rIWk4nsLAN9CigVCiNSkVCqlbYcQIs2bPXs2Hh4eZM2alVKlSnHjxg3evn3LrFmz9B1NpJCTkxMTJ05k3rx5mg9YVSoVEydOZOjQoXpOJ4QQ+pehC9rJFRERgZubG6Ghofj6+sonnmlckyZNaNiwIZcvX0alUtGtWzcMDeVHOSObMWMG06ZNw8/Pj0KFChEUFISlpWWSC70KIYQQQgjxI8iSJQuLFy/m2bNnPHjwgFq1apEnTx59xxJaULp0adq1a4eTkxOFCxdGrVYTFBSEs7MzxYsX13c8IYTQux++Cvju3Tt69+5Nzpw52bhxI2ZmZvqOJJLBwMCAypUr6zuGSCXGxsZMmTKFyMhIXr58Sc6cOTE1NdV3LCGEEEIIIfQuT548UsjOgBwdHXF0dOT58+coFApy586t70hCCJFm/PAFbXd3d/LkycOiRYvk1lIh0jhTU9MEPQKFEEIIIYQQIiOzsbHRdwQhhEhzfsiCdsWKFVm1ahUWFhacOnWKTJkyUaVKFc32Fi1aMGXKFD0mFEIIIYQQQgghhBBCCPG/foiCtqura4Kv/7sK/J07d1I7jhBCCCGEECIVqFQqnR9XpVLp7DxyB6kQQgghRGI/REFbCCGEEEII8WNRqVQcPHhQJ8eOiorS/P3w4cOYmJjo5DxNmzaVorYQQgghxP+QgrYQQgghhBAiwwoICNDJccePHw/A1atXdXL8atWq6eS4QgghhBDpnRS0hRBCCCGEEBlaxYoVUSqV+o6RLPHx8QlaJAohhBBCiISkoC2EEEIIIYTI0JRKpbTuEEIIIYTIINLHNAUhhBBCCCGEEEIIIYQQPzwpaAshhBBCCCGEEEIIIYRIF6SgLYQQQgghhBBCCCGEECJdkIK2EEIIIYQQQgghhBBCiHRBFoUUQgghhBBCZFgxMTFERUWlm0UhVSoVMTEx+o4hhBBCCJFmSUFbCCGEEEIIkWHNnj1b3xG+i6Ojo74jCCGEEEKkSdJyRAghhBBCCCGEEEIIIUS6IDO0hRBCCCGEEBnWqFGjqFixYrpqOXLp0iV9xxBCCCGESLOkoC1+KNeuXWP79u3ExMTQrFkzHBwcUCgU+o4lhBBCCCF0xNjYGBMTk3RV0DY2NtZ3DJHGqNVqTp8+zf79+zEwMKB9+/aUL19e37GEEEIIvZCCtvghqNVqJk+ejLm5OYMHDyZTpkzs2LGDTZs2sXjxYoyMjPQdUQghhBBCCCESUalUDB06lPLlyzN69Gji4uJYt24dv/32G1OnTpUJOkIk0759+1LtXC1atEi1cwnxI5Ie2iJDUKvVX9z+xx9/UKBAAUaOHEmOHDmwsLCgd+/edO/eneXLl6dSSiGEEEIIIYT4Nr6+vrRv3x5nZ2csLS2xtrZm2LBh2NnZsX///iQf87X3R0IIIUR69kPM0F6zZg137txh5syZibZFRUXh4eHBiRMnMDc3x83NjTZt2ughpfhWsbGxzJkzh6CgIExMTAgPD6dBgwZ07tw50b779u1j3rx5icZr1qzJ+vXrUyOuEEIIIYQQQnyzy5cv079//0TjnTp1ws3NTTMTVK1Ws3btWvz9/TEzMyMyMpKSJUvi5uaWblruCCGEEMmRoQvaKpUKPz8/FixYQKtWrZLcZ/78+URGRnLy5EkCAwNxcnLCzs4OW1vbVE4rvtWwYcPo3bs3lSpVAv7vBZyvry9OTk4J9lUoFJ/tRSg9CoUQQgghhBBp1eferxgaGqJU/t9N14sWLSJv3rysWrVKM3bq1CnGjRvHrFmzdJ5TCCGESC0ZuuXI6NGjuXDhAh06dPjsPvv372fgwIGYmppStmxZmjdvzt69e1Mxpfge169fp0iRIppiNnwsWvfu3Zvz588TGxubYP8cOXJw//79RMeJiIggPj4+xXkCAwO5cuVKovMKIYQQQgj9i4+PR6VSpYs/2nhtKjKesLCwRGNPnjwha9asAISHh3Pv3r1E730dHBwwNzcnKCgoVXIK7Xn16hUXL14kNDRU31GESBG1Ws2zZ8+4cOEC586d49GjR9IWSaRYhp6hPWrUKHLmzIm3tzdPnz5NtP3du3e8evWKIkWKaMYKFy7MP//8o/Ust27d0spiHdHR0QDcuHEjxcdKTdrOvWXLFmrUqJHk8XLlysWBAwcoXry4Zqx27doMGzaM8ePHY2pqCnx8YzN37lxatmz5xVxfyn779m02btxI8eLFMTc3Z/r06ZQvX57WrVun8BlqR1r6ebl+/brmwyKVSsVPP/1ErVq1Pru/rrPLL1AhhBDix3Hp0iV9RxDiu/Xr149x48axYMECTeuQqKgoJk6cyJQpU4CPbUkcHBw0j1Gr1ezatYs//viD169f069fP+bNm0eZMmX08hxE8kVERDBhwgSMjIyws7Pjt99+Izo6mqlTp2Jubq7veEIkW0xMDAcOHODgwYMEBwcn2JY9e3YaN25MixYtNDUaIb5Fhi5o58yZ84vbIyMjARL85zExMSEqKkqnuUTKmZub8+7duyS3vX37lsyZMycYy549O87OzsyePRtTU1OMjIx48+YNbdq0+e72MqGhoWzatImJEydiZGQEQPv27fn11185evQo9erV+67jZkTHjh3j+vXruLu7Y2pqSlxcHLt372bdunX07NlT3/GEEEIIkYFVq1ZN68eMioqiY8eOAGzbtg0TExOtn0OIT0qXLk3Xrl3p378/1tbWqFQqPnz4wIgRI8ibNy8AFhYWvH79WvOYKVOmULJkSZYuXcrhw4d59+4da9asoUWLFuTIkUNfT0Ukw+jRoxkyZEiCCVqBgYGMHj2aJUuW6DGZEMn377//MnfuXJ4/f57k9tDQUDZu3Mjhw4cZOnQo5cqVS+WEIr3L0AXtr/n0wjMqKgozM7NEf9cmOzs7rSzE8Wm2aunSpVN8rNSk7dz58uVj7NixdO3aNcF4VFQUYWFhNGjQINFjSpcuTbNmzYiMjCQuLo4sWbIk61yfyz5z5kxmz55NsWLFEoxPmTIFZ2dnXF1dv+Up6URa+HlRqVTMnz8fX1/fBHcplC9fnlGjRpEjR44kP3zSdXaVSsXly5d1cmwhhBBC6J+BgQFNmzbVybHDw8M1f2/UqJHOZk3KQn7ik+rVq1O9enXCwsJQKpWJ3rOWKVOGuXPn4uzszKNHj1AqlXTu3Bm1Ws327dtZunQpHTt2xMnJiWHDhmnl7mGhfQ8ePCBnzpwJitkAxYoVI0+ePNy/fz/BHeZCpEX//PMP8+fPJy4uDvhYv2nUqBElSpRAoVAQGBjIkSNHePjwISEhIXh6ejJgwAAaN26s5+QiPfmhC9pWVlZky5aNhw8fUqpUKeDjL5DChQvrOZn4GktLS+rVq8eIESNwd3cnb968XLp0iQULFuDh4fHFx2rrdpZnz54lKmbDx17euvhQJL26evUq9vb2Sb5obtu2LYcOHaJHjx56SCaEEEKIjE5XBeH/HtfAwEAKzyLV/O+dqJ8oFArc3Nzo168fuXLlok+fPjx8+JB58+bRoUMHzWSukiVL8vz5c/LkyZOasUUy3bhxg+rVqye5rXr16ly7dk0K2iJNO3XqFHPmzEGtVmNgYED37t1p1apVgt+Ttra2NG3alEOHDuHn50dsbCzLli0jLi6O5s2b6zG9SE8y9KKQydGsWTMWL15MWFgY169fZ//+/fIfKJ1o3749gwYNwtfXlyFDhnDq1Cm8vb0pWbJkqpw/c+bMn12gQ9rW/J8vzf5Qq9UyO0QIIYQQQggtqFixInPnzuXOnTtMnTqVjRs3Mnr06ASzHuX1d9qWN29eAgMDk9z277//ki9fvlROJETy3bp1i/nz56NWqzExMWHSpEm0bds2yQ99lUolTZs2xcvLS3P3/KpVqwgICEjt2CKd+iEL2hUrVuT8+fMADBs2jKxZs1K/fn0GDx7M2LFjsbOz03NCkVyFCxdm4sSJLF68mMGDB2NpaZlq5+7RowcLFixINH7ixIl01xJGl8qVK8eZM2eSXIRxx44dNGnSRA+phBBCCCGEyHisra2ZP38+xYoVY/z48QkKoPHx8fz777/kzp1bjwnFl1SoUIGzZ8/y4cOHBONhYWGcPn2aSpUq6SmZEF/24sULpk+fTmxsLEqlkrFjx1K+fPmvPq5EiRJMmTIFExMT1Go18+bN4/r166mQWKR3ems5MmDAAMaMGUOhQoV0fq7/7WX831XOzczM8PLy0nkGkXoiIyM5fvw4cXFx1KlTBwsLC52cx9bWljJlyjB48GB++eUXLC0t2bt3L2/evGHWrFk6OWd6pFQqadeuHePGjcPDw4PMmTMTGxvLqlWryJ8/P9mzZ9d3RCGEEEIIITKMwoULo1QqWb9+PV27dsXAwIC3b98yadIkevXqpfMZ2s+ePePs2bNky5YNR0dHacnzDRQKBVOmTGHgwIG0aNGC8uXLc/XqVfbu3cu0adNkdr1Ikz6tm/X+/XsAXFxcqFixYrIfX7RoUYYNG4aXlxeRkZG0atWKK1eufLbFkhCgxxnax48f1/yww8dPi5s2bcq9e/f0FUl8B7Vazb1797h9+zbx8fH6jsPWrVtxd3cnNjYWIyMjJkyYwNKlS3V2vl9++YXp06fz4MEDTp06RceOHZkzZw5K5Q9588NnNW3alE6dOjF+/HiGDBmCm5sbJUqUYOjQofqOJoQQQgghRIYzfvx4rKyscHV1ZejQoUydOpX+/ftTq1YtnZ1TpVIxduxYli1bhqWlJU+fPqV3796cO3dOZ+dMLWq1msDAQO7evZvknafaVLBgQdavX4+1tTXHjh0ja9asrF+/PlUmAwrxPXbv3s3t27eBj219GzZs+M3HsLe3p2vXrgDcv3+fUaNGaTWjyHjSzKKQarWa+/fvS+/hdOT06dOsXLmS0qVLkylTJubOnUuLFi1o1aqVXvJcunSJW7dusWLFCs1Y48aN8fHx4eDBg1pZ5V6tVnPmzBkOHDiAkZER7dq1o0yZMnTr1i3Fx87oKlSowMKFC/UdQwghhBAiSWq1moiIiGTtGx4enuTfv8bMzExmWIoUefv2LZs3byYoKIjSpUvToUOHJBe9VygUtGzZkpYtW6Zatjlz5tCyZUtq1KihGevUqRNOTk4sXLgwVdtDatPx48dZv349ZcuWRalUMmvWLDp27EijRo10dk6lUkmDBg1o0KCBzs4hhDY8ePCATZs2AR97wPfq1eu7j9W+fXsuXbrEjRs3WL58Oe3bt6devXpaSioymjRT0Bbpy4MHD9iwYQO+vr6aW8jUajXTpk0je/bsODg4pHqm9evXM2XKlETjTk5OuLi4pLigHRcXx9ChQ6lQoQIjRowgOjqa9evX89tvvzFp0iR5cyKEEEIIkU6p1WocHR3x9/f/5sfmypUr2fs6ODhw8uRJed0ovss///zDmjVrGDx4sGbms7OzMxMnTqR48eJ6zRYfH8+DBw8YM2ZMgnEDAwOGDBnCpk2bcHFx0VO673fz5k327NmDr6+v5i5ctVrNuHHjyJkz5ze1VRAio1Gr1Sxfvpy4uDiUSiXu7u5kypTpu4+nVCoZOnQo7u7uhIeH06dPH27cuIG5ubkWU4uMQvoiiO/i6+vLxIkTE/RDUygUjB49WvPpXGpTqVSa1XH/y8DAIEUX1U98fHzo1KkTzs7OWFlZkStXLkaOHEnhwoU5fPhwio8vhBBCCCH0R4rMIi2LiYlh1apVrFq1iooVK2Jqakrt2rVZtWoV06dP13c8wsLCyJEjR5LbypYtS2BgYCon0g4/Pz8mTpyYoKWkQqFg/PjxrFmzRo/JhNC/v//+W9NqpFWrVpQoUSLFx8ydO7dmTbKgoCDmzp2b4mOKjEkK2uK7hIWFJTkbxdjYGCMjIz0kAkNDwwR92T+Ji4sjJiYmxce/du0atWvXTjTetWtXDhw4kOLjCyGEEEII/VAoFJw8eZKwsDCd/pHZ2eJ7HTlyhPbt2ydaq8fU1JRy5cpx584dPSX7KHPmzISEhCS57fLly1opdOlDbGwsVlZWicZlxqj40UVFRbF27VoArKys6NSpk9aOPXDgQM3dD7NmzeLJkydaO7bIOPTacuTmzZtER0cDH2fXKhQKbt68mWTvuqpVq6Z2PPEVkZGRifq1qdVqvfVB79WrF7Nnz2batGkJxlesWEGbNm1SfHxjY+Mkx42MjGQRSCGEEEKIdE6hUEiRSqRZoaGhlC1bNsltefLkITQ0lJIlS6Zyqv+jVCopVqwYf//9d4JJQLGxsSxZsoTFixfrLVtKxMXFERsbm2jSVnx8PLGxsXpKJYT+7dy5k1evXgHQo0cPzMzMtHZspVLJwoULqVOnDpGRkYwZM4aNGzdq7fgiY9BrQXvy5MkJvlar1UyYMCHBrAW1Wo1CoeDWrVupHU98QYcOHfDx8cHNzS3B+P79+/XSPxugXLly3Lt3D2dnZxo2bIiRkRF//vkn5cuX18qCHZ8WCvrfC3VQUBDZsmVL8fGFEEIIIYQQIik1atRgz549VK5cOdG206dPp3i9IG0YPnw4kyZN4sCBA9SpU4cXL15w/Phx3N3dsbCw0He879KyZUvWrl2Ls7NzgvFff/2Vhg0b6imVEPr1/v17du/eDUCxYsV0snBj7dq1ad++Pdu3b2fTpk24ublRpUoVrZ9HpF96K2ivX79eX6cWWuDo6Mjly5cZNWoUv/zyCyYmJuzYsYPIyMhEM6RTU5s2bWjWrBmnTp0iNjaW2bNnawrQb968Ye/evYSHh9OgQYNvvu3NycmJ8ePHM3fuXM2M7KioKCZPnpwm+tYJIYQQQgghMqaSJUvy+PFjrl+/TpkyZTTjf/zxBzlz5kwTBWOlUsmUKVMICQnh/PnzlC5dmt69e6frNjuNGzdmzpw5eHh40KlTJ5RKJdu3b8fQ0BAPDw99x/uia9eu8ffff2NlZUXLli2TXG9KiO+xc+dOzZ353bt319kd67Nnz2bPnj3ExsYyceJEafUqEtBbQbtatWr6OrXQksGDB/PixQv27t1LbGwsXbp0oUiRIvqOhbGxMXXr1k0wtnHjRgICAujSpQsWFhbs3LmT0NBQZs2alWBhyy8pX7487du3p3///uTIkYPY2Fjev3/PqFGjsLGx0cVTEUIIIYQQQggA5s6dy/Tp01m2bBk5c+bk+fPn2NraMm7cOH1HSyBHjhw0adJE3zG0ZuTIkTx9+pR9+/ahVqvp06cPBQoU0Hesz4qJicHd3Z3ixYvTuHFjQkJCGDFiBM2aNaNly5b6jifSubdv32oKy3Z2dlSoUEFn5ypcuDBOTk4sX76cgwcPcubMGezt7XV2PpG+6LXlCHxs4xATE0OmTJk0YydOnCAwMJCSJUvi6Oiox3Tia3Lnzk2/fv30HeOLbt68yZ07dxL0bStVqhR///03S5cuZciQIck+Vs2aNalZsybv37/HwMBA+iwKIYQQGUxMTAxRUVHJ/sA7LVCpVFpZAFsIkbZlypSJKVOmEBsby4cPH7C0tExX16r0LG/evAwYMEDfMZJl5syZ9O/fn3LlygFga2uLo6Mjbm5uVK5cmbx58+o5oUjPdu7cqVkLr0uXLjq/A2PcuHH4+fkRExPDxIkTOXz4sE7PJ9IPvRa0169fj7e3Ny4uLvTu3RsANzc3Dh8+rOmdXadOHZYsWYKhod5r7yKd2rBhAyNGjEg0Xrt27e9eWCAt3NInhBBCCO2bPXu2viN8N5kIIsSPwcjISNbwEUlSq9U8ffpUU8z+RKFQ4O7uzrp169LcjH6Rfnz48IHff/8dgNKlSyf6OdOFfPny0a9fP5YsWcKRI0fw9/enZs2aOj+vSPt00+gmGf78809mzJhB9erVqVq1KgCHDh3i0KFD/Pzzz5w7d45ff/2Vq1evsmHDBn3FFBlAeHg41tbWSW4zMTHRyjlu377N6NGjGTJkCMOGDePixYtaOa4QQgghhBAi44iNjWXjxo24uLgwePBglixZQlhYmL5jiQwiLi7us72yCxYsSHBwcConEhnJ77//rpmd3bFjx1Trjz927FhNV4f0PPFAaJfepj1v3LiRFi1aMGfOHM3Y9u3bMTAwYMKECWTJkoXy5cvTu3dv9uzZo5nBLcS3ypMnD4GBgRQrVizBeHx8PBERESk+/pEjRzh8+DDjxo3D2tqaDx8+sGDBAm7dukWbNm1YtmwZ9+/fR6lUYmFhgaurq/TcFkIIIdKoUaNGUbFixXR1G79KpeLSpUv6jiGE+IrY2FhcXFzo0KEDS5cuRaFQcOHCBQYMGMCSJUuwsrL66jH27dvHgQMHMDY2Ji4ujq5du+Lg4KD78CJdMDIy4u3bt0luO3fuHKVLl07dQCLDiIqKYt++fcDH3ta67J39v/LkyUP37t3x9fVl79693Llzh5IlS6ba+UXapLcZ2rdu3UqwUERcXBznz5/Hzs6OHDlyaMbLlStHUFCQPiKKDKJ37954eXkRGxubYHzZsmW0bt06RcdWqVRs2bKFuXPnamaBZ8mSBU9PT/7++2+cnZ35+eefWbZsGUuWLMHV1ZXRo0fz5MmTFJ1XCCGEELphbGyMiYlJuvtjbGys72+dEOIrtm3bRocOHWjYsKFmZmPlypWZPHkyixYt+urj582bR0hICEuXLmXx4sUsWLCA48eP89tvv+k6ukhHatWqxZYtWxKMRUZG4u3tTZcuXfSUSqR369ev5927dwC0adMm1WZnfzJs2DDgY1ud+fPnp+q5RdqktxnaERERCW6FuXHjBlFRUVSrVi3BfvHx8akdTWQwuXLlwtXVlX79+lGqVCksLCy4ePEijo6ONG/ePEXHPn/+PHXq1EnyYm5hYUG+fPkoX768ZszGxoYFCxbg5eXF3LlzNeOBgYGsXbuW9+/fkzVrVvr06UPBggVTlE0IIYQQQgiRdvj7+zNnzhzWrFnDhQsXUCqVNG7cmMaNG3+1FURISAjBwcEMHz5cM5YpUyY8PDxwcnKidevWGBkZ6fopiHSgZ8+eLFu2jIEDB1KpUiVCQ0MJDAzE09OTzJkz6zueSIfi4+OZN28eADly5NDLmh12dnY0b96c/fv3s27dOqZOnUrOnDlTPYdIO/RW0M6dOzdBQUGa/tknT55EoVAkul3q0qVL0p5BpFiFChVYs2YN9+/fJzw8nL59+2plodHY2FhNL6f/FRgYSKdOnRKNW1tbExkZqfl6//79HD9+nFGjRpEzZ06ePn3KzJkzadu2LXXr1k1xRiGEEEIIIYT+xcbG0q9fP/r370+vXr2Ii4tjx44duLu7f/WxR44c+ezdpY6Ojly6dCnR5DDx43JxcSE6Opo7d+5gaWkpk6VEivzxxx/cvXsXgJYtW2qllvI9Ro4cyf79+4mOjmbp0qVMnjxZLzlE2qC3liP16tXD19eXx48f8/DhQ7Zt24a1tTX29vaafR4/fsz69etT9OnPlStXaN26NRUqVKBLly48evQo0T6xsbFMmDABe3t7atSogZeXl8wMz6CKFClC2bJltXYBrlKlCn///XeS24KCgqhXr94XHx8dHc3u3buZM2eO5tPFvHnzsmjRItavX49KpdJKzv86ceIEAwYMYOjQofTv35/Vq1ejVqu1fh4hhBBCCCHE/3ny5AkdOnSgVq1aKBQKjIyM6Ny5M2XLluXFixdffKyBgQFxcXFJblOpVFrt+3/16lUGDx7MkCFDGDhwIPPmzSMmJkZrxxepI1OmTJQrV06K2SLFlixZAnz8mapfv77ectSqVUszKXbp0qVaWRNNpF96K2gPHDgQpVJJw4YNadKkCa9fv2bSpEmaX8Tjxo2jVatWGBsb079//+86R3R0NIMGDcLJyYmAgABq1qyJm5tbov02b97Ms2fPOHr0KAcOHOCff/5hz549KXl64gdhYmJCtWrVWLRokab4rFar2bRpE7a2tly8eDHRY54/f46FhQUAR48epWXLlolaliiVSurWrcvZs2e1mnfHjh34+/uzZMkSFi1axIoVK8idOzfjx4/X6nmEEEIIIYQQCeXJk4fffvuNe/fuacZCQ0M5ceIElpaWX3xs48aN2bVrV6JxtVqNv7+/1hZoCwgIYPXq1cyePZvFixezfPly6tSpw6BBg2TSlxA/oAcPHnDgwAEA6tatq9e2NQqFghEjRgDw6tUr1q5dq7csQv/01nLEysqKXbt28fvvv/Pq1Stq1apFiRIlNNvv379PvXr1cHd31yy2963OnDmDlZWVpk/ywIEDWbduHYGBgRQrVkyzX1BQECqVSvMLWqlUfraNxPe6deuWVprmR0dHAx97jqcn+s79/Plz1q5di0qlQqFQEB8fT9euXSlSpMhXH/u17NWqVePUqVP88ssvGBkZERsbS40aNRg9ejRTpkzh+fPnVK1aFYVCwcOHD1m+fDmjRo3ixo0b3LlzBwsLiySP/ebNG27evPnVF7fJzf5pAcvJkydz584dzT4FCxbk0KFDHDp0iPz583/3ubRN1z8zMitdCCGEEEKkJhMTE+bOncvixYt58eIFSqUSc3NzvLy8mDlz5hcfa2Vlha2tLfPnz8fFxQUTExPu3btH586dyZkzJ25ubsTExDBgwAAqVqz43RlXrVrFihUrEsz4rlKlCnfv3uXo0aM0aNDgu48thEh/li9frnnv3LRpUz2ngbZt21KoUCEePnzIkiVLGDhwYKovUCnSBr0VtOHj7QqtW7fm9OnTFChQIMG2X3/9NcXHf/DgQYKCpYGBAfnz5+f+/fsJCtodOnSgT58+VK1alfj4eBo3bpwm/qMK7Xj9+jWLFi1i3LhxmpnRkZGReHl54ezsrJUiroODQ6L+7wATJkxg7969HD58GKVSSa5cuRg3bpymSF25cmXWrFlD9erVEz323LlzDB06NMXZPnn48CF2dnZJbqtfvz6nTp2ic+fOWjufEEIIIYQQ4v8olUoMDQ3x9PRMMH7u3DnKlCnz1cf379+fkydPMnLkSOLi4jh+/DjLly/np59+AiAmJobhw4fj5OSUYGH65IqOjiZLlixJti9p164d48aNk4K2ED+QyMhI/Pz8gI/tPgoVKqTfQIChoSEDBw5k9OjR3Lp1i+PHj8vaYz8ovRa0P3F1dcXT05OWLVtq9bgRERGYmJgkGDM1NU2wIB98/MXfokULBg0axIcPHxgwYACbNm2ia9euWstiZ2enlb5mn2arli5dOsXHSk36zD19+nQWLlxI0aJFE4yvWrWKGTNmMHfu3C8+PqXZv3b7399//83du3dp3bo1ly5dYuXKldy7d4+IiAj27dvHqFGjvvu2nv9mNzExITAwMMnnERUVRWhoaJr6udL1z4xKpeLy5cs6ObYQQgghhBD/a9CgQbi7u7Nw4ULMzc2Bj321Fy5ciI+PT7KOUatWLWrVqsXy5cs1k7I+MTY2Zs6cOQwbNoxly5Z9cz6lUqnp0x0cHMzcuXMJDw9HoVB8tn+3ECLj2rp1K69fvwZg8ODBek7zf/r06YOnp6dmcUgpaP+Y0kRB28LCIlHhWRtMTU2JiopKMBYZGal58fDJ2LFjmTlzJpaWllhaWjJgwAD8/Py0WtAW+vPixYtExWyAbNmyadpapJa4uDi8vb25ffs2mTJlIjo6ml9++YWgoCDatGlDUFAQFStWxMnJiU6dOhEYGIiLiwt+fn4YGRml6NxFihTh+vXrSS4as2XLFkaPHp2i4wshhBBCCCE+r2TJkgwfPpwxY8agVqtRqVRYWVnh7e39zRNYbt68ycCBAxONm5iYJHitf/XqVXx8fDTF6ty5c9O0aVPMzMwSPdbIyAiVSsXjx48ZO3Ys8+fP1yxcP2vWLE6dOsWDBw8oXLjwNz5zIUR6o1arNYtB2tjY0KZNGw4dOqTnVB9lz56dzp07s27dOnbv3s2TJ0/Ily+fvmOJVJYmCtr9+/dn2rRpPHjwAFtb2yR/uf73k+fkKlKkSIKFM1QqFY8ePUr0C/jFixfExsZqvjY0NMTQME18a8Q3io6O5vHjx1hbW3P37l0OHjxIQEAAN2/epFSpUon2/++/e2pwd3fnl19+wd3dHfhY4Pby8qJixYrkzJmT6dOnc/r0aQwMDIiMjKRYsWL88ssv7N69mw4dOqTo3AqFgn79+jF48GAmTJhAnjx5CA8PZ9myZRQrVowcOXJo4ykKIYQQQgiRoYWGhvL+/XtCQkLw9/fn/PnzNG7cmFy5cn31sba2tnh7e6c4g1KpJDo6Osm1nz69x7l06RJ+fn7MnTsXU1NTAO7evcuIESOYMmVKkscdMWIETZs2pWrVqixevJiaNWsSHBzMhw8fWLt2bbLucBVCpH/nz5/nwoULAPTr1y/FE+y0bdCgQaxbtw6VSsXKlSs/e00TGVeaqNpOnDgRgAULFgAkaOiuVqtRKBTcunXrm49bvXp1Xr16xe7du2natCkrV66kQIECiWbr1qpVi0WLFrF06VKioqJYtWoVTZo0ScEzEqlNrVYzf/587t27R/Hixdm4cSMWFhasXLmSXLly4eXlRcmSJRk/frzmMefOnaNkyZKplvHChQuULFmSmjVrasYMDQ0ZP348ffr04cKFCxQrVoxGjRoREhLC4MGD6dChA40aNcLNzS3FBW0Ae3t7bGxsWL58Oe/fv0epVNK5c+cke3gLIYQQQggh/s+TJ0+YNm0a2bNn5+bNm9y4cYPatWvToEEDFixYQPbs2RkxYkSqZGnRogWbN2+md+/eCcYDAwM1s6pXrFiBt7c3xsbGmu0lSpSgWbNmHD16NMnWiMeOHUOhUGBtbU1ISAiLFi1CpVKxa9cusmTJkugOaCFExrR69Wrg44dnzs7Oek6TWNWqValatSrnzp1j5cqVjB8/PsG1TmR8aaKgvX79ep0c18TEBB8fHyZOnMjkyZOxs7Nj4cKFADRr1oz+/fvTsmVLJk+ezLRp0/j5558xNDSkTZs29OrVSyeZhG7MnTuXcuXKMXz4cJYtW8b8+fMpUaIEY8aMYfXq1dy6dYuHDx9y8OBBGjVqxP79+9m7d+939Zb7Xn/88Qfdu3fn3bt3bNu2jeDgYCpVqkR0dDQnT57E3NycQYMGaVri1K9fH1dXV4oVK6bVC3PBggWZOnWq1o4nhBBCCCFERqZWq/nnn39wdXWlZcuWPHv2jNjYWMaOHcuzZ8+4ffs2M2fOZM2aNezfv5/mzZvrPFP9+vUZN24cPj4+dO/eHRMTE/788082bNjA8uXLgY8tRJJ6H1GzZk1mzpyZaDwwMJD79+/j6OjIrFmzUCqVANy/f58ZM2bg5eVFfHy8bp+YEELvIiIi2Lx5MwCNGzcmb968ek6UtEGDBtGrVy+Cg4PZuXMnnTt31nckkYrSREG7WrVqOjt2mTJl2LFjR6LxAwcOaP5uZWUlt03pyLVr17h58ybx8fGULVtWJ+eIiori4cOHjBw5EvjYJ87FxQWAn3/+mb///pvFixdz6NAhxo4dy6FDh2jQoAErV67UykKdyWViYsLvv/9OQEAA/fr1w9DQkMGDB2NoaIixsTGFCxemb9++uLm5YW9vj0KhYNiwYbi5uTFu3LhUyykyJpVKpe8I3+y/mVUqVbp8DkCqXmeEEEII8ZFarebs2bMEBQVRpkyZ715oPCYmhiFDhhATE0O9evW4d+8eFy5coFevXjx//pxz585x69YtunfvTo8ePRg8eHCqFLQVCgUzZszg1KlTjB8/nri4OBwcHPDz89MUsT/32ik6OjrJFpsbNmzA1dWVo0ePcvDgQc3zKFKkCG/evOHq1asULFhQd09KCJEm7Ny5k/fv3wPQt29fPaf5vE6dOjF8+HBevXrFsmXLpKD9g9FbQftTc/nkUCgUDBo0SIdphLa9efOGkSNHUqZMGapUqcJff/3Fli1bWLJkCQUKFNDquYKCghL0x/7vLITatWuzbds2KlSowPPnz8mSJQu9e/emYsWKWs2QHA0bNqRr165cvHgRhUKBs7MzBw4cICQkBHt7e44fP87QoUOZOnUqu3btIj4+niNHjhAcHIy9vX2q5xUZh0ql4uDBg/qO8c3+e0vr4cOHdbJ4cGpo2rSp1ova6bW4nxE+pJAPKIQQIu17+PAhEyZM4KeffqJkyZIcPnyYRYsWMWfOHCwtLb/pWPPmzWPAgAEsXboUlUrFpk2bGDp0KDExMVhYWJArVy6OHDnCo0ePKFiwYKr2mVUoFDg6OuLo6JjkdlNTU16+fKlpQfLJ/v37adCgQaL937x5Q86cOenYsSOurq5ERUXRunVrDAwMCAkJYc6cOfj4+OjkuQgh0o5P7UZy5MiRKh/QfS8TExP69OnDnDlzOHnyJLdv38bW1lbfsUQqkYK20Ilx48YxZcoU8uTJA0DWrFlp3LgxHh4erF+/PkGf9JTKnj07T58+1XwdHx9PZGQkpqamBAUFERQUxPjx42nUqBGVKlXi1KlTrFy5koULFya5iIqu+Pv78/PPPzN37lyaN29O4cKFCQ4OxsvLC2tra0xMTFi1ahVjxoyhTZs2lChRAltbW3r27JlqGUXGFhAQoO8I3+xT3/urV6/qOcn30cUdSOn1AwrIGB9S6OIDCiGEENoTHx/P+PHjWbFiBZkzZwbA0dGRJ0+e4OHh8U3vQ+Hj5JkKFSrw5MkTRo8erRm/f/8+t2/fZuLEifzxxx/Mnj2bypUro1artfp8UmLMmDG4u7szfPhwKlWqRExMDJs3b+bJkye0b98+0f5VqlTh77//pk6dOixZsoQDBw4wbNgw4uPjefXqFVu2bJEetUJkcPfu3ePYsWMAdO/ePc3/n3dycmLOnDkArFq1innz5uk5kUgteito3759W1+nFjr26NEj8uTJoylmf5I5c2bq16+Pv78/Dg4OWjuftbU1796908w+6Nu3LxMmTGDWrFksXryYPHnyMHfuXFxcXJg6dSp58uTh2rVrzJo1C09PT63l+Jrg4GBGjBjBw4cPmTZtGiEhISgUCmbNmsXgwYPZvHkzAwYMYMCAAfj7+9OjRw/69++vlVXQhfikYsWKmn6IQnfi4+O5dOmSTs+RHj+ggPT9IYUuW6QJIYTQjhMnTtCkSRNNMfuTfPnyYW1tzbNnzxK9T/mST8WcfPnysWPHDn766SeUSiVqtZpixYoBkDNnTmbOnEnTpk0ZOnSo9p5MCuXMmZMVK1awfv161qxZg0KhoHnz5ri5uSU5wahjx4707duXsmXLki1bNlq0aEGLFi1YuHAhDRs2TPOFLSFEyq1du1bz9/9ddDYtKlGiBD/99BPHjx9n3bp1zJgxI1UnLgr90VtB+8aNGxQtWjRdzs4SX/bgwQPs7OyS3Fa6dGlu376t1YI2wOTJkxk2bBhNmzaldu3aFC5cGDs7O0xNTcmZMydDhgxh+PDhmhevZcuWTXJ2hlqt5uTJk9y9e5dixYpRp06db8px79491q1bx9u3b8mTJw+9e/cmV65cwMcZD8ePH6djx46sWLGCCRMmMHbsWODjDPbw8HAGDx7Mu3fvyJEjBwMHDmTMmDGEh4fz5s0bChQooNWZ7Z9z8eJFLl68SJ48eWjYsGGS/fVE+qVUKmV2aQYiH1CkjtT4gEIIIYR23L9/n8qVKye5zdbWlqCgoK8WtF+9esXvv/9OfHw8r1+/Jj4+nrp16/Lvv//i4uLCixcvqFy5MsuXL+fGjRuYmJjg5uaGs7Mzly5dSnL2s75kyZIl0d3ON27cSHJfExMT5s6di6enJ5kyZcLS0pKgoCCaNm1Ky5Ytk33OyMhInj17Rs6cOcmSJcs35Y2KimLr1q2cP38eIyMj2rRpg6OjY6q8D/oW0dHRHDp0iNDQUOzt7b+7R7sQaYlKpdIUtKtVq0aZMmX0GyiZnJ2dOX78OK9evWLXrl3SS/sHobdKVfv27dm6dSvlypXTjB08eJBatWp98y89kfrevXvH+/fvyZMnT6LiWPHixTl69GiSL+QuXryYrP7VkZGRrF27luvXr6NQKLC1taV3796Ym5snuX/27NlZu3Ytf/31Fxs2bMDGxoZLly4xbNgwvLy8CA8PZ9u2bWzfvp06depQu3ZtzMzMUKlUmvyPHz9m3LhxNGzYkOrVq3P16lW6d+9Or169sLGx+Wrm3bt3c+rUKYYPH07u3LkJDAxk/Pjx9O/fnypVqvDzzz/Ts2dP6tSpQ65cubC2tubEiRO8efOGsmXLMnjwYG7evImHhweenp5EREQwd+5cChYsiImJCXfv3qVt27Y0bdr0q1m+x/v37xk2bBiVKlXC0dGRBw8e0Lt3b4YNG6aXnuNCiK+TDyhEatFVv/PU7Ksu/1eE+DHY2tpy6dIlKlSokGjb9evXqV+/fqLxK1eusG7dOlQqFdeuXcPGxgZ7e3uuXbvGjRs3aNiwIQcOHKBPnz5Mnz6dnj17snPnTjw8PLh+/Tp58+Zl9OjRGBgYMGTIkFR4lrpjY2PDkiVLCA8PJyIiguzZsydZTI6KiuLly5fkyJEDU1NTAOLi4vDy8uLly5cUK1aMR48eoVQqmTRp0mffx/3XmzdvcHV1xdnZmR49ehAVFcX69es5fPgwU6dO1fpz/V5///03q1evplOnTlSpUoXDhw+zdOlS5s+fLxP2RLr2xx9/8OTJEyBtLwb5v9q2bUu2bNl4/fo1q1atkoL2D0JvBe3/7S2mUqkYPnw427dvl08307AXL14wdepUMmfOTPbs2fn333+xt7enT58+mn3y5MnD27dvuX//PkWKFNGMv3nzhtOnT9OvX78vniMiIoIBAwYwaNAgBg4cCMD58+cZMGAAy5cvT3T74CdKpZKff/6Zn3/+WTNWsWJF5s2bR3h4OE5OTlhbW/P777/Tt29f4uPjE7y59fT0ZMmSJZqFYsqWLUuLFi3o3r0706dP/2ze+Ph4AgICWLduHVu3btXcilesWDGWL19O3759Wbt2LUqlkoULFzJ58mTev39PYGAgS5cuRaFQULNmTQIDAzE0NGTDhg28e/eO2bNns2LFCs3CMmq1mkmTJmFlZUXNmjW/+D38Hp6ennh6emoW7SxXrhzNmjWjd+/e+Pr6ym07Qgjxg9Jl3/bU7Ksu/c+F+DHUrFkTHx8fWrVqRbZs2TTj//77L5GRkYkWSNy5cyeXLl1i8uTJXLx4kRw5crBjxw6srKyYMWMGL1++pEuXLlSpUoVWrVrRrl07Hj58iLOzM3/99Zfmwzh3d3dCQkK+qZ0JfLwOXrlyBXNzc0qXLp1mZiKbm5snWYT+VLQODg6mUKFCPH78mMyZMzNhwgSmTZtGixYtqF69umb/wMBARowYwfLly796ztmzZ+Pl5UX+/PmBj4ta9u/fHx8fH06ePIm1tbX2nuB3evv2LevWrWP16tWau+TKly/PrVu3mDZtGtOmTdNzQiG+36fFIE1NTenUqZOe0ySfiYkJPXr0YOHChRw9epTAwEBNSyiRcaWpXgJpaQGN1KJWq/nrr7/Yu3cv8PETcScnJ3LkyKHnZInFxsYyfPhwvL29E7w4XL9+PevXr6dHjx6asenTpzNu3Disra2pVKkSx48fJygoiGXLln31RZqvry9Dhw5NcKtglSpVGDVqFMuXL2fkyJFJPu7hw4ecO3eO7NmzU7t2bQwMDChSpIhmxdtPLy579OjB06dPE/SfvXr1KpUrV0606rmFhQXlypXj9u3bSd5uc/z4cdauXUumTJkoXrw4rq6uODo60r17dwAMDQ2pVq0aN27coEyZMlhbW9OpUyc2b97MqlWrKFasGPHx8ezcuZMTJ06wYsUK4ONq6p6englWSVcoFHh4eDBkyBCtF7TfvHlDpkyZNMXsTwwNDenevTt79+6lQ4cOWj2nEEKI9EVXfdtTo6+69D8X4sehUCiYPXs2o0aNwtbWlpIlS3LhwgVCQ0OpWLGipv1GhQoV6NixIwcPHsTX1xeA7du3Y2Jiwo4dO5g9ezbm5uaUKlWKCxcuUKlSJZo1a4a7uzuHDx/m3r17mJmZ4ejoiJOTE5cuXcLT0xNra2uOHj1KvXr1vprVx8eHK1euUKNGDd6/f8/cuXMZNGgQVatW1en36H89ffqU06dPY2VlxU8//fTFloOenp60bt06wXX1xo0bDBkyBCsrqwTFbPg4yad48eLcuHHjqxPX3r59qylm/1ePHj0YN24cTk5O3/jMtG/z5s0MHjw4Ucs3Ozs73r59S0xMjPQaF+lSaGgou3fvBqBDhw6JaiNpnbOzMwsXLgQ+1pRmzpyp30BC59JUQftHNGXKFPLly8fcuXMxNjbWfILt6elJ0aJF9R0vgd27d9OjR48ExWz4+ALDycmJ7t27a4rVmTNnZvHixTx69Ig7d+5Qv359ChYsmGhGRFJu376d5K16ZcuW1RR84eMii0uXLiUkJAR/f39sbGwYNmwYwcHBdO7cGbVaTWhoKF27dqVx48ZYWlrSvn17bty4QfXq1cmVKxdqtRqFQkFQUBAlSpRIMk+hQoV4/vx5ovF79+6xc+dOVq9ezYYNGyhVqhRVq1ZlwYIF/PHHH5qZ4paWloSFhWket2bNGlauXJngRdAvv/zCu3fvCAgIoFq1arx69SrJF3PGxsY6eYH04sULChYsmOS2kiVLsn37dq2fUwghRPqT3vq2f2//8/j4eB2k0Z30llcIXcudOze+vr7cuXOHR48e0aNHD6ZPn06BAgU0d5aePn2a9u3bJ5iUo1AoCAsLo0iRIjRr1ozjx4/TpEkTDAwMqFy5Mn/++Sc1atSgS5cueHl5ceXKFVQqFStWrMDU1JRGjRrx6NEjpk2bRt26db84kWf79u0YGRmxbNkyzVhcXBwuLi7kz5+f3Llz6+4b9P+pVCrGjx+PoaEhDRo0ICQkhL59++Ls7Iyjo2Oi/V++fMm///7LmjVr2LhxI/Hx8XTr1g17e3vUanWS718AateuzYULF75a0P5cId3ExIS4uLhvf4I68OjRI3r27Jnktpw5c/L+/XuyZ8+eyqmESLlNmzYRGxsLkOAO/PSiVKlSODg4cOrUKdasWcOUKVPkw6UMTgraenTt2jXMzc0T9CYqVqwYy5YtS/ZtWakpICDgs7dQ5cmTh3fv3mFlZZVgvECBAhQoUOCzC48k5Usv/D5te/78OaNGjcLLywtfX1/Wrl2LQqFg/vz5rFy5kgMHDhAdHY2dnR2TJ09mypQpHD58mJ07d7Js2TIMDQ25fv26pu1I6dKl2bJlCw0bNkx0zmvXrtGoUaNE435+fowfPx6lUslPP/3E2rVrqVq1KkOGDMHFxUVT0Pb399f0E3/79i25cuVKshjQoUMHFi5cSLVq1VAqlURGRmr60f1XdHR08r6R36BAgQLcvn07yW1nz55NN4tBCCGE0K0fpW+7LAIqRMZQsmRJSpYsiZ+fHz169Eiw4HvNmjXp1KkTR44c0dxdqVAoNHdIGhkZaYo7UVFRmJqaEhoamuD4Q4cOZc+ePezZsydBMbdBgwbs2bOH1q1bfzbb4cOHWblyZYIxQ0NDxowZw+rVqxk3blyKnntyzJ8/n+bNm+Pg4KAZa9u2Lf3798fOzi5Ri4+JEyeSK1cuFi1ahIGBAVFRUcyePZunT59Sr149Dhw4gKura6LzBAUFJatAHxsbm+QM57///psqVap857PUrjJlynD27NkkZ+A/ffqUrFmz6iGVECmjVqvx8/MDoGjRotSuXVvPib5Pv379OHXqFC9fvmTfvn20a9dO35GEDqW5gnZa6RmWGrZt28bQoUMTjZubm2NiYkJUVFSaWlQiV65cPHr0iOLFiyfa9ubNm2Qt9JEc+fPn586dO5QsWTLB+P3798mVKxcACxcuZN68eVhZWRESEqJZtNDJyYmpU6dSt25d7OzsWLlyJadPn6ZmzZo0atSII0eOEBYWhqWlJe/fv9e8KS9SpAjPnj1L1Pf74cOHPH/+PFErDoDw8HDNjPOCBQsSFRWlub0wU6ZMqNVq1q1bR9myZTX/jgYGBp+dXRATE6N5Ad2hQwdWrlyZ6Ofjr7/+0skCjebm5lhbW3PmzBns7e0142/evGHv3r2sX79e6+cUQggh0iJdtSeJioqiY8eOwMfXgGnpNZ4QGd2FCxeSnHHYpUsXzS3q8PG9RNeuXVGr1fz++++ayTyzZ8+mVKlSWFhYaPY1NDTk999/Z9SoUYlmJtvb23+1oG1mZpbke98iRYrw4sWLb3yG306tVvPvv/8maueoVCpxd3dn/fr1uLu7a8ZDQ0OJjIykSpUqmvdQJiYmeHp64uzsTO3atXn9+jUfPnwgS5YsmsfFxcWxZ88e1qxZ89VM/fr1Y+TIkcyZM0dT1H78+DGrVq3C19eXe/fuaeOpp0j79u3p27cv1atXT/D+98iRI9jZ2f0QH/qKjOfChQtcu3YN+Dg7O73W5dq3b8+QIUN49+4dq1atkoJ2BqfXgvakSZM0C/x96p89YcKERIVRhULBunXrUj2frkVHRyc5Axc+zghQqVSpnOjLunbtysyZM1m0aFGC8UePHpEpU6YE/Z5TYsCAAQwePJhp06ZRqFAhzTk8PT015/5UTA4ODk6w8EqtWrXw9PSka9eu5M+fnxw5crBs2TJKly6NpaUl5cqV4969e5w+fZoWLVokOO+sWbMYP348mTNnxs7Ojtu3b/P+/XuGDx+eZE5DQ8MEL9imT5/O0qVL2bx5M2fOnMHZ2Zmff/6ZXr16aR6TJUsWXr9+TXR0dKJFFjds2KC54Do4OHDu3Dk8PDzo3r07pqam7NixgydPnjB37twUfX8/x8PDgylTpvDbb79RqVIlgoKCePjwIXPmzElXt5cLIYQQ38PAwICmTZvq7Pjh4eGavzdq1EhrEwH+lxRThEhMqVQmWaAxMzMjZ86ceHt7M3DgQMqWLUuzZs0oVqwY1apVY9u2bZw5c4ZatWpx+PBhzQxG+DiTecOGDYnuUI2NjeXFixcJirpJiYyMTHL85cuXCQrnuhITE/PZHrl2dnYJWj3CxxnlTk5O+Pr6EhERgZmZmWZb9erV2bJlC0uXLmXAgAF06tSJqlWrcvv2bVavXs2wYcOSdW2qVKkSAEOGDMHQ0BCVSoWlpSXe3t5p5kNAExMTpk6dypAhQ7C1tcXGxoZz585hY2PD6NGj9R1PiO/yaTFIpVKZoA1TemNmZkb37t1ZsmQJR44c4eHDh5qaksh49FbQ/rTQxX8XgkxqLKmvM4qmTZuyY8eORBeM+Ph4rc541hYbGxtq167N4MGDcXZ2xsbGhj/++IM//vgDb29vrZ3HysqKxYsX4+3tzcuXLwHInj07Cxcu1Nz29uln4vXr12zdupUXL14QFxdHgQIFMDU15d9//yUkJISyZcvi6urKmDFjsLCw4Pz58+TKlYtWrVolmjGROXNmFi5cSHBwMA8fPqR+/frkzp37s+1SunbtyqJFixg0aBDr1q3j/v37ZM2alUqVKlG7dm1sbW1Rq9XExsYmKPY7OzvTtm1bhg0bRr169VCpVGzatImIiIgEfeXc3Nx4/Pgxu3btIjo6mqZNm36171xKGBoaMmXKFN6+fcudO3dwdHT8bF9tIYQQIiPSZTH4v8c2MDCQwrMQOhYUFMTs2bO5ceMG0dHRnD59mho1aiTY5/nz59SoUQNbW1tcXV0xMjIiJiaGtm3bcu/ePS5fvoyVlRVnzpxhzpw5CYqqRYsWxcDAgC1btuDp6YmxsTHPnz9n0qRJDBw4MFE7kf9lbW1Nq1atKFiwIDExMZQuXZqBAwcyf/78BC0pdcXY2Jg3b94kue3KlSuJ1hdSKpWo1Wo8PDzo168fPXr0oGLFity8eZPVq1czePBgChcuzLp16zh48CBr166lUKFCrFq16puK0ZUqVUpUTE9rihQpgp+fH/fu3SM0NJTWrVtrJuoJkd5ERkayefNm4OMH7vny5dNzopRxdnZmyZIlmjYqU6dO1XckoSN6K2hv2LBBX6dOM+rUqcOAAQMoWbKkZjXoyMhIPDw86N27t57TJa1du3bUqVOHbdu28fr1a2rWrMmaNWu0fktKtmzZmDhxIgAPHjxg3bp1TJkyBTs7O7p164aFhQV///03GzZsoE2bNjRq1IiaNWuyatUqPnz4wJYtW1Aqlfj5+WFqasry5cu5e/cuL168YM2aNV+ccXzv3j3Wrl1LpkyZNH3cklpRu1KlShw6dIgaNWowevRounXrxqZNm9i2bRs2Njb06NEDpVKJr68vjRo1ol27dsyaNYsXL17QvHlz5syZw+DBg6lYsSLdu3dP8pPQ/PnzJ7lApi4ltTq5EEIIIYQQuvTmzRtmzpzJu3fvMDIyIjo6ml69elGzZs1vPtbWrVsZOnQoefLk4aeffsLf3586deqwePFiBgwYAEBISAijRo1i9uzZ2NjYaNa/+SQ+Pp7nz5+TJUuWz86YHjZsGPv27WP48OEoFAosLS3x8PDA39+fBg0afDbf6dOniYyMpESJEpibm9O8eXNOnTpFuXLlmDJlSpItHr+XWq3m6NGj7N+/H4BmzZqRO3duFAoF5cqV48iRIwnWEYqNjWXRokUsWLAgwXEaNWrE1KlTWbBgAatXr2bPnj2sWLGCQoUKUbx4cTp16gR8nCTTsmVLWrZsqbXnkFYVLVqUokWL6juGECmyc+dO3r17B5AqH6bpWrly5ahWrRoBAQGsXr2aiRMnfnbBWZG+yb+qHikUCpYsWcKSJUtYs2YNxsbGqFQqnJ2dqVChgr7jfVb27NlxcXFJlXNt27aNc+fO4e7uTp48eTh37hwuLi64urrSrVs3duzYQalSpfD09GTp0qUEBwdTrlw5AgICyJMnD4cPH6Z48eKcOXOGf/75h/nz53+xmO3v78/u3btZvny5ZubU0aNHmTFjBjt27EjUJiQwMJCTJ0/y119/cfv2bZo1a4a5uTnnz58nICAAS0tLXF1d2bNnDyNGjKBBgwaMGTOGkJAQIiIiuH//PgEBAZQpUybd9qkSQgghhBAiJWJiYnB1dWXWrFnkzZsX+Nh72cPDA+Cbitpbt26lW7du5MuXj7p16zJ16lTMzMzw9/fnp59+4sqVKyiVSszNzZk5cyY2NjZJHkepVGqyfE6lSpX4999/CQ8Pp0OHDhgZGbFy5UpMTU2/uKijn58fPj4+GBgY8OjRI44ePUrevHlxdXVN1uKJyaVSqRgyZAj29vbMnDkTgO3bt+Pr68u4ceNwdXVl+vTpHD58mDp16vDy5UtOnjzJ0KFDE7VSyZYtGyVKlGDRokUMHDiQDh068OHDB7y8vOjQoYPcdSJEOvWp3Uj27NkTtWVNr/r160dAQADPnj3j4MGDP8QHbD8ivRW0x44d+037e3l56SiJfhkZGSVYbONHExsbS2RkJFmyZElU0H39+jV///03S5Ys0YxVrVqVFStW4ObmRu3atdm3bx8+Pj7Ex8dToUIF7OzssLGxwcDAgAULFnDkyBHNbIevLW6gVqtZuXJlgmI2fFwMs3Hjxvj6+jJw4EBNQfzBgweULFmSHDly0LlzZwBcXFx4+/Yt9evXx8bGhubNm7Ny5UqUSiWHDh1i3rx5/PPPP6xbt45hw4Zha2vLli1b6Ny5M4sXL6Zy5cra/PYKITKwmJgYoqKi5A1kKlCpVMTExOg7hhBCZFhHjhyhb9++5M2bl/fv3xMWFkaePHmYMWMGLi4uyS5ot2jRgjt37pAvXz7u3LnDzJkzKVOmDMeOHaNmzZpUqVKFrFmzMmPGjM8eIy4ujvDwcCwsLJI14aRTp07kzp2bgwcPEhsbi4uLS4I1fv7Xhw8fyJ49u+b3d4ECBTRr7nz48IEZM2bg6OiYrOf7NRs2bKBVq1YJZmB37dqVyMhI9uzZQ7ly5Rg/fjxv3rzh/PnzVKhQgb59+372eQ8cOJDjx49remIrlUp69epF+fLltZJXCJG67t+/z9GjRwHo3r27ZjHW9K5Tp064ubkRFhbGypUrpaCdQemtoH327NkEX798+ZK4uDjy5MlDjhw5ePv2LY8fP8bY2BhbW9vvOseVK1eYOHEiDx8+pFSpUsycOZMCBQok2s/Pz481a9YQHR1N7dq1mT59eppZdCKjevfuHVOnTiUqKgpLS0tevHjBzz//rCkMw8dbX/67oOIn5ubm5MuXj/v37yc58yEmJgalUomhoWGyF3fau3cvu3fv5vr164wePRqFQsGECRN49uwZHTp0AOD9+/csWrSIHj16MH78eN6/f0+2bNkSHCcgIIBt27YRFRXF8ePHyZYtG2PGjGHGjBnEx8cTFxfHqlWrErQ96dSpE2fPnmXRokWsW7dOZmoLIZJl9uzZ+o7ww9FWgUEIIURCV69epWHDhpQrVw6FQoGZmRmvXr2iR48eySqwXLp0iZEjRxIYGEjmzJmJiYnh7t27eHp60qhRIzp06EBAQAD29vacP38+yWNERkYybdo03rx5Q7Zs2Xjx4gX29vZfLPB+Ym1tTffu3ZP1XA0MDIiLi0tyW1RUVIK1d1Lq7NmzLFu2LNG4vb19gr6yWbNmTdRy5XN++uknfvrpJ21FFELo0dq1azV/79Onj/6CaFnmzJnp2rUrPj4+/P777zx+/Jj8+fPrO5bQss/3XtCxo0ePav64u7tjbW3Ntm3bOHr0KFu3buXw4cPs3buXnDlz0qRJk28+fnR0NIMGDcLJyYmAgABq1qyJm5tbov0OHjzIli1b2LJlC8ePH+fNmzesWrVKC89QfE58fDyurq4MHTqUJUuWMH36dPz8/Hj//r1mMQL4WED+tAjk/8qWLRsGBgaEhoYm2vbbb7/RrFmzZOfZv38/d+/exc/PjypVqrB48WI8PDzo378/LVq0YMGCBWzYsIFu3bpx+/Ztjh8/zuzZs7Gzs+PChQsJjhUZGUm+fPnYv38/devW1Yz369ePkJAQTpw4QfPmzRO0Pblz5w6FCxemTp06nDt3Ltm5hRBCCCGEyAji4+Np3bo1u3bt4sqVK5w+fZrbt29z7NixzxagP/n3339ZuXIlYWFhHDt2jDlz5hAfH8+iRYsICgqievXqhIeHA3Ds2DHs7e2TPM7QoUPp2bMny5YtY9q0afj6+mJlZZVkQTglzMzMCAsLIzIyMtG2devWaSbTaIOhoWGSxXiFQiE9ZYX4walUKtasWQN8vBO+TJkyek6kXf369QM+/n7x9fXVcxqhC2nit9iCBQsYNmwY5cqVSzBerFgx3Nzc8PLyomfPnt90zDNnzmBlZUXz5s2Bj7dHrVu3jsDAQIoVK6bZ77fffmPw4MGaT2tmz55NVFRUCp+R+JLDhw/TokWLRJ+Q9evXj759+9K5c2eUSiU//fQTv//+e5L9uq9fv86UKVNwc3PDw8MDOzs7VCoVe/fu1cx2Tq5du3bh6+uLQqEgS5YsPH36lLx58/Lhwwfq169PwYIF2bBhAx07dtS0DildujSNGjUiKCiIBg0a0LZtW7p3707JkiUZM2YMKpUKOzs7zTm2b99O9uzZuXjxIlWrVtWMx8fHs3DhQry8vPD39+ft27ff/g0VQvyQRo0aRcWKFaXlSCpQqVRcunRJ3zH0Lj22uZF2MUKkD8+ePaN69eoJFthTKpWsXr2aihUrfvGxK1asYMaMGfz0008ULFiQwoULExkZia2tLT4+PsyYMQMjIyOWLVvGo0ePGD9+fKJjnD9/nooVK1KiRIkE4+3bt2fAgAFER0cnWksnJYYNG4aLiwuenp4ULlyY2NhYNm7cyIcPHyhbtmyKjn327Fl+++03YmJiePDgAQ8ePKBw4cIJ9gkNDcXU1DRF5xFCpG9//vknT548ATLGYpD/q1KlSlSpUoXz58/j6+vLhAkT5IO8DCZN/Gu+efPmsytHGxoaEhER8c3HfPDgAUWKFNF8bWBgQP78+bl//36CgvatW7eoV68eLVq04PXr1zRq1IgxY8Z8+5P4ilu3bmmllUR0dDQAN27cSPGxUtN/c+/Zs4devXol+RzMzMz4559/sLa2JlOmTJw4cQIbGxvNi0u1Ws2OHTsoUKAA7969w8XFBT8/P549e4ZaraZ69eo4Oztz8+bNZOWKiYlBpVJp9m/Tpg39+/enbdu2BAUFYWVlxZo1a4iMjMTMzEyT+e3bt/j5+TFx4kT++ecftm/fzpw5c1CpVLx9+xYbGxvWrl2LQqHg2LFjqFQqOnfuzNmzZ9m2bRvDhw/n1atX/PHHH7Ru3ZoXL16wY8cO+vXrp9V/2/T68wK6z65Wq3VyXCFSi7GxMSYmJumquJheqVSqDNNTMCXSc5sbaRcjRNr24sULGjRowMKFC+nbty+ZM2fm2LFjrF69+ov9qOHjmjxZs2bFwcGBhQsXMmzYMM6ePYu9vT1RUVEEBARw8+ZNJk6cyMaNG5O8np86dUozEep/VahQgXv37lGqVCmtPFeAEiVK4OXlxapVqwgJCSE+Pp7mzZsn2W7xW0yfPp0sWbIwefJkzMzM2LVrFw0aNODYsWOa1psREREsWrQoyUlDQogfh5+fHwCmpqYJWr+mBfv27dPKcT61mXr27BkTJ05M8g6djLIQ5o8oTRS0K1SowPLly6lUqRKWlpaa8ZcvX+Lt7U316tW/+ZgRERGJ+mCbmpomurXr/fv37N69m1WrVmFsbIyLiws+Pj64urp+35MRX2VpaUloaChZsmTRjKnVaq5evYq/vz9mZmY0b96cbNmy4ebmhqenJy9evCB79uxYWVnh6OhI48aNNcfq3bv3d2cxNDRMMCPf0tKSKVOmcOTIEUJCQrh27RotWrSgdOnSmn0eP35MTEwM/fv3B6BJkyY0adKEDx8+MH78eIoUKULPnj05ffo0arWa9u3bs2LFCpo3b06HDh2YMmUKx44do1y5ckyaNAkjIyNOnTpFlixZEvz8CyGEEEII8SMwMTGhR48evHz5kilTphAVFUX16tXx8/OjUqVKX3xsTEwMarWamTNnUr58eRo0aEC5cuU0a/TcvHmTxo0bs3Pnzs/OzsuWLRsnT55k586dmJiY0LZtW/LmzQt8XDTtzZs37Nu3j3r16iW42zIlcufOzYQJE7RyLIALFy5gamrKkCFDNGNt27Yld+7ctGzZEgcHBxQKBfHx8fTp0wcbGxutnVsIkb6Ehoaye/duANq1a5dh6xC1atXCz8+PyMhIDh8+/NmWUyJ9ShMF7dGjR9O9e3fq1q1LxYoVsbKy4tWrV1y6dAlLS0uWL1/+zcc0NTVN1DokMjISc3PzBGNGRkZ0796d3LlzAx8b4a9YsULrBW07OzutzKL7NFv1vwXW9OC/ud3c3Jg9ezYLFiwAPi5+MmTIEEqWLEn58uXp0qULq1evJkeOHNy9e5fx48dTokQJTp8+zY4dO+jUqRP58uXTWrb8+fNjYWGRoAVKpUqVOH/+PM+fP9e8iP70PV+4cCFFixZN8t/g04votWvXkjlzZqKjo3n69CmrV68mZ86cAGzevJmFCxdy5coVHjx4wLt37yhfvjyLFy/W+oKQ6fXnBXSfXaVScfnyZZ0cWwghMqL02OZG2sUIkT707NkTZ2dnjhw5kqBgfPToUbJmzfrFx9rb23PkyBEaNWrEoUOH6NKlC9HR0URGRhIZGYm7uzsjR4787ONVKhWnT5/m0qVLbNmyhcjISLy9vcmfPz8GBgb8/vvvbN68GSsrK/bv34+fnx+LFy9Oc3fubN26Ncl2KjVr1qRGjRp4e3ujUChQKBTp8u5NIYT2bNiwgdjYWACcnJz0nEZ3TE1NNa1sL168SHBwMLly5dJ3LKElaaKgbWtry/79+1m7di0XL17kyZMnZM2alT59+tCzZ0+srKy++ZhFihRh165dmq9VKhWPHj1K1D+sUKFChIWFJdhPWhHolo2NDdWqVWP48OEMHjwYPz8/KleuzN69e6lZsyaXL19mwoQJ1KlTh127dmnajbRt25b69eszfPhwrTb1Hz9+PIMHD6Zdu3Y0adKEly9fsnz5cho1asSRI0fo2bMno0ePJm/evEydOpXt27cTEBCQ5LHMzc2pXr06TZo0ITY2FgMDgwQLQMLH9jfDhw9HrVYTGxuLkZGR1gvZQiQlPfa/Ta+kb6/IiNJjmxtdt4tRq9XJbo33aVG6//37l5iZmclrBPFDaNSoEf7+/tSpU4cFCxZQpEgRpk6dyu7duzl9+vQXH9ujRw/c3d15+PAhv/zyC3/++Sfr1q3jwYMHLFy48Kv/h5YuXUrz5s0xNjame/fujBkzhqlTp9KtWzfOnz/P0aNHKViwIPBxXaYrV64wZ84cPDw8tPb8tSEqKorMmTMnue3T+w25nggh1Gq1pt1IsWLFqF27tp4T6Vbjxo35/fffUavVHDlyhO7du+s7ktCSNFHQBsiVKxejR4/W2vGqV6/Oq1ev2L17N02bNmXlypUUKFAgwUIjAK1atWLz5s38/PPPGBkZsXr1aho2bKi1HCJpv/zyC7Vq1WLjxo3s2bOHvHnz0rBhQ1q0aEFoaCg9e/akbt26bN68mUmTJmkeZ2lpSdGiRXn48CGFChXSShZLS0vWrl3LgQMH8PDwwMrKCmdnZwoXLoyzszN+fn7MnTuXWbNmUatWLbp3786cOXOYOXMm2bJl0xxHrVbz9OlTzSwSIyOjL55XoVCkuZkdImNLz/1v0yvp2ytExqVWq3F0dMTf3/+bH5vc2UEODg6cPHlSilDih7B9+3b++usvRowYwfv372nZsiV37tz56iJeSqWShQsXcvbsWby8vFAoFLRt2xY3N7dknXf37t2ULVuWbt260bFjR2bMmIGnpye5cuXSLBD/X+XLl/+uO4i/RXBwMAcOHEClUtG0aVNN+5MvcXBw4MiRI5rWjJ+oVCoiIyPlOiKEAD4uHPvpLg0nJ6cMf20oXLgwJUuW5M6dO/z555/88ssvsjhkBpFm/hU/fPjAmTNniIiISHKGdOvWrb/peCYmJvj4+DBx4kQmT56MnZ0dCxcuBKBZs2b079+fli1b0qtXL6KioujcuTNhYWE0b948Q67wmhbly5ePUaNGsWfPHmbNmkX58uUBKF68OG3btuX48eNJzmAqWLAgL1680FpBGz7Omm7ZsiUtW7ZMtM3e3p7q1avz66+/YmxsTKtWrRg/fjzu7u7Url2bvn37Eh8fj5eXF+3atcvwvxCEEEII8ZH8zhdCu+rXr0/9+vW/+XEKhQJ7e/tv7o968+ZNwsLCWLRokWZs//79nDp1irFjx2Jqaprk4zJlyvTNGZNr0aJFPHv2jA4dOmBgYMDy5csxMzNj3LhxX3xc27Zt6dOnD3Z2dpoifFxcHB4eHilac0gIkbF8mp1tYGBAz5499ZwmdTRu3Jg7d+7w5s0bAgICqFmzpr4jCS1IEwXtkydPMmTIkEQLNn6iUCi+uaANUKZMGXbs2JFo/MCBA5q/K5VKXFxcZJVnPVEqlbx584Zy5colGK9cuTIBAQE8f/480WPOnz9Ps2bNUisiADt37qRGjRqa827bto3Zs2fj4+PDH3/8QZYsWejcufN3vQAXIrWkx/636ZX07RUi41MoFJw8eTLZLUe+h7QcEUK3NmzYgJ2dHXFxcQlm7Dk4OBAeHk58fHyix6jV6mS3DfpWR48excjIiFmzZmnGKlasyMaNG9m1axdt2rT57GONjIxYunQpM2fO5M2bNxgZGREdHU3v3r1lITQhBPBxIumWLVsAaN68uWYtuYzO0dERX19fwsPDOXTokBS0M4g0UdCeN28eRYoUYezYseTKlStRz2GRsYSFheHt7U1QUBBPnz7l+fPnODo6MmnSJOrXr49SqaRYsWIcPXqU6tWrJ3jsqVOnsLCw0MkqvLGxsezbt48bN25QqFAh2rVrh5mZGQDXrl1LsAq5qakpEydOZNiwYUyaNIl58+ZpPY8Q2pYe+9+mV7ru2yuESBsUCkWiBceFEOlHeHg4ffr0YdasWYwdO5ZNmzbxzz//YGhoyP3797GwsCAiIkLzngDA29ubVq1aJfscMTEx7Nixg9OnT2NiYkKnTp2oXLlykvvu3LmT+fPnJxrv0qULLi4uXyxoA1hYWDBjxoxE42q1muPHj+Pv70+2bNkoV67cd61TJYRI37Zt26b5QO5H6kyQKVMm6taty/79+7l8+TLPnz/HxsZG37FECqWJgva9e/dYtmwZVapU0XcUoWNRUVG4uLgwcuRIli5dSteuXcmSJQt37tyhR48ewMdFI01NTZk0aRJr1qxh+PDhFChQgH///RcbG5sEheXvpVKpOHjwIH/99RfGxsY4ODiwbds2unTpQv/+/bl9+zYDBgxg6NChmJiYYGxsnOQMqSxZsmhWBxZCCCGEEEKkH/ny5cPGxgaVSkXOnDnJkSMHZmZmZM+endq1a1OwYEFat26Nvb09VlZW3Lp1i3r16tGiRYtkHf/t27cMHjyYXr16sWjRIsLCwvD19eXw4cNJthBRKpVJfiD+ufHk+PDhA66urtSvXx8nJydevHjBrFmzqFatGqVLl060f1xcHHv37uXEiROYmJjQuXNnKlas+F3nFkKkLZ/ajdjY2NCkSRM9p0ldjRs3Zv/+/QAcPnyYXr166TeQSLE0UdDOkycPYWFh+o4hUsGvv/6Kk5MTp0+f5pdffqFOnTo8evSIR48e0apVK2rUqMH79+8pW7Yszs7OnD9/HoVCQUhICHnz5sXExCTFGSIjI3FxcaFVq1bMnTuXqKgofv75Z2rXrk3Tpk1RKBTkzJmTmjVr0qdPH4YPH05MTAwqlSrRzNb/LgIphBBCCCGESD969+5NmzZtqFWrFq6urvTs2RMjIyPc3d2xtrZm0aJFODk54eLiQmRkJG5ubt90N7GXlxdeXl7kz58f+DgZxt3dnQULFnDu3DmqVq2aYH9jY2Pevn2baPZ0ZGRkku1PkmPq1KlMmjRJs/5Qrly58PDwYObMmYlmKYaFheHi4kLHjh2ZP3++pgB/8OBBPDw8vuv8Qoi04ebNm5w+fRr4eO370RZGLFCgAKVKleLmzZv89ddfdO3aFSMjI33HEimQJnp79O/fn6VLl/LkyRN9RxE6dv78eWrVqsWlS5eoXbs2APfv36dLly6aPpQbN25k48aNuLi4cObMGSwsLChatKhWitkA8+fPZ8SIEbRu3RpDQ0OeP39Ou3btKFGiBEePHtXsZ2hoSJs2bThz5gyNGzdOdPufSqVi2rRpP9StOkIIIYQQQmQU5ubm5M2bl+PHj/Pu3TsOHjzIpEmTaNmyJcbGxoSFhVG+fHnevXtH4cKFv7k15rt37zTF7P9ycnJi27Zticb79OnD1KlTUavVmjG1Ws2MGTO+a/G22NhYIiIiNMXs/+rSpQsbN25MMDZr1iwmTZpE8+bNMTAwwNLSkuHDh5MlSxbOnDnzzecXQqQdn2Znw8drzY+oUaNGwMdr86fivki/0sRHMvv27SM4OJiff/6ZbNmyJVm4/Ouvv/SQTOhCfHw8RkZGKBQKzd9dXFy4evUqtWvXJiAgAF9fX2JjYxk1apTmoqMtjx8/TnB73cuXLylQoACtWrVi1KhRCRZ2LFCgALdu3aJVq1Zcv34dZ2dnqlSpQkREBFeuXGHAgAEUKFBAq/mEEEIIIYQQuufv70/nzp017wcKFixIv379MDQ0JHv27Bw/fpyYmJjvnsX3ucdlzpyZqKioROOlSpWiWbNm9OnTh0qVKmFgYMCFCxdo06ZNotncyREZGfnZu0ltbGwSvccODQ2lSJEiifbt27cvEydOlMUlhUinoqKiWL9+PQB169alaNGiek6kHw4ODvj6+vLhwwcOHDigmWQp0qc0UdDOnTv3D7O66o+ubt26HDhwAHNzc16+fEmOHDlQq9U8e/aMrFmzkjVrVvLlywd87N+miwVC//eFZalSpdi1axcdO3ZMdCvfiRMnNMXvTp060a5dO27evImJiQlubm5J9tUWQgghhBBCpH0GBgbExcXRqlUrFixYwKxZszTbYmNjUSgU3Lx5k+HDh3/X8aOiopJsW3jixAmqVauW5GPq1atH3bp1uX37NiqVigEDBnz3e6IsWbLw/PnzJLcFBAQkKpJ/rgBvZmZGTEzMd2UQQujf9u3bCQ0NBcDZ2VnPafTH2NiYhg0bsmPHDm7dukVgYKC+I4kU0HtB+8aNG9SuXZvixYtTrFixRNtfv37N33//rYdkQhdat27NoEGDqFGjBmPGjGHJkiW8evUKd3d3Zs2axbhx45g+fToAW7ZsoXXr1lrPoFKpiIqK0twJkDVrVszNzVm3bl2CTyr//fdfAgMDNTPEQ0NDiYqKomzZslLIFkIIIYQQIp1zcHBg0KBBdOjQgbx587Jo0SL69++PiYkJ27dvx8TEBGdn5+9+7d+7d2/GjRvHjBkzNEXt58+f4+vri6+v72cfp1AosLOz+65z/u9x6tSpw/r16+nRo4dm/N27d+zdu5edO3cm2D86Opq4uLhEvXXPnj1L2bJlvytDVFQUwcHBmgU3hdCnV69eERERQdasWcmcObO+46SaZcuWAZAzZ07atm2r5zT61bRpU3bt2kV8fDz79u3D3d1d35HEd9JbQTssLIyhQ4fi7++PWq1GoVBQr149ZsyYgaWlpWa/x48fM3bsWJ0UNkXqMzAwYMmSJWzdupWoqCjs7e0xNjbm3bt3eHp6MnHiRGxsbNi1axfXrl2jd+/eWs/Qr18/Ro8ezbx58zQv1lxdXWnQoAFVqlRh3rx5PH78mEyZMjF37lz++usv1q1bh62tLebm5gQGBtKmTRuaN2+u9WxCCCGEEEKI1GFsbEyTJk3w9PRk5MiRXL58GXd3dy5dukSuXLlYsGBBki04kqtmzZqo1WoGDhyIiYkJsbGxZM6cmcWLF2ttfaCv6d69O2vWrMHJyYmSJUsSGhpKUFAQI0aMwNjYOMG+nwrwXl5emgJ8SEgIS5YswcfH55vOGxsby4wZMwgJCaFQoUI8evQICwsLJkyYQKZMmbT2/IRIrtmzZzN69GjN13nz5sXBwYEmTZpgbW2tx2S6denSJU2/aCcnpx/+/1+OHDmoUaMGp06d4uTJkwQHB5MrVy59xxLfQW8FbW9vb65fv868efMoUqQIf/75J6tWraJbt26sWbOG7Nmz6yua0DFDQ0O6du1K165dgY8LnQQHB7Ny5UoWLlyISqWibt26zJs3TyczoStUqEC3bt1wcXHBxMREMwvhwIEDZM+enRcvXpA9e3bMzc0JCQnBz88PT09PKlWqpMk7ffp0smTJQp06dbSeTwghhBBCCJE62rZtS5EiRfD09ESlUpEpUyaWLFlClSpVtHJ8BwcHHBwcNJO49KF379706NGDp0+fYmFhwdOnT5Pcz97enri4OAYMGKBpM5IpUybmz5+Pubn5N51zwoQJtG/fPsH38fr164wePZqFCxem5OkI8V3u37+f4OunT5+ybds2du/eTfv27enQoUOi9kAZwfLlywFQKpX069dPz2nShhYtWnDq1Cni4uLw8fHB09NT35HEd9BbQfuvv/7Czc2Npk2bAmBra0utWrVwdnbG2dmZDRs2/FC3gPzIFAoFuXPnTtWLSNWqValatSoqlQqlUpngxWXBggU1f1+9ejXOzs4JPsVUKBSMGTOGQYMGSUFbCCGEEEKIdK5ChQpUqFBBp+fQd8tCAwMDzWL2nytoAzg6OuLo6Jjk+6TkevHiBUqlMtGHAmXKlMHa2poHDx5QuHDhbz6uECmxYMECsmfPTlRUFC9evODcuXPcvXuXmJgYNm/ezJUrVxgxYkSGmq399u1bNm3aBEDz5s0T1Dp+ZHZ2dhQtWpR79+6xfPlyxowZk+iOFZH2aX/FvWR69eoVhQoVSjBWvnx5li9fzv3793F1dSUuLk4/4cQPw8DA4Isv0p49e5bo5xQ+zjJPrdsEhRBCCCGEECI1fe190pdcuXIFBweHJLfVrl2bCxcupCSaEN/F1NSU6tWrU6dOHTp16sTcuXPx8vLSfNBz48YN3NzcePjwoX6DatH69euJiIgAwMXFRc9p0g6FQqFpIfvixQt+++03PScS30NvBe38+fNz5syZROOVK1fGy8uLM2fOMHr0aClqC70yMjLS/AL4X9HR0amcRgghhBBCCCHStly5cvHo0aMktz169Ej61Yo0o3Tp0sybN4+ff/4Z+LhgqoeHR6L2JOmRWq3WLAZZtGhRzXMUH9WuXVuzft/ixYv1nEZ8D70VtH/55Rd8fX2ZNm0aly5dSrCtadOmjBgxggMHDiRo2i9EauvUqRO//vprovGzZ89SokQJPSQSQgghhBBCiLSrfPnynDlzhsjIyATjMTExHDly5LOzt4XQh0yZMuHq6krv3r0B+PDhA+PHj//shzLpxZEjR7hz5w4AAwYMQKnUW/kvTTIyMqJx48YABAQEJDnhVqRtevuJ7ty5M0OHDmXv3r0cPHgw0fa+ffsyadIkQkJC9JBOiI+qVq1KpkyZWLBgAXfu3OHZs2csXbqU9evXM2TIEH3HE0IIIYQQQog0RaFQ4OHhgbOzM0eOHCEkJIRjx47Rt29fRo0aJYU1kSa1adMGJycnAMLCwpgyZQpv377Vb6gUmDdvHgDm5ub07dtXz2nSpiZNmmBo+HFpQVmsNv3R228ShUJBv379OHv27GcLg507d+avv/5i2rRpqZxOpAVqtZqzZ8+yefNmLly4QExMDIcOHeLXX39N1U9Lu3btSufOnTl48CBr167F3t6epUuXai58QgghhBBCCPElKpWKP//8ky1bthAYGKjTcz18+JAtW7Zw+PBhYmNjdXquzylRogSrV6/m7du3rFixgufPn7Nq1SrKli2rlzxCJEfLli3p1q0bAC9fvmT69OnExMToOdW3u3r1Kn/88QfwcbJo1qxZ9ZwobcqWLRudO3cG4LfffuPevXt6TiS+hd4/GlUoFGTJkuWz27Nnz067du1SMZFIC54+fUqvXr24evUqhQsXZtOmTZQqVYoXL16QP39+Vq9ezahRo1CpVKmSx8bGBnd3d8aNG0flypVT5ZxCCCGEEEKI9O/ixYv06tWL169fU7BgQX777TeGDBmi9TV54uLiGDFiBOvXr6dgwYKEh4fTt29f/P39tXqe5DI2NqZjx45MmDCBLl26YGJiopccQnyLDh06ULduXQDu3LnDypUr9Zzo232ana1UKnFzc9NvmDRu5MiRAMTHx2u+byJ90HtBW5euXLlC69atqVChAl26dPnqrN6RI0cyZsyYVEonPketVuPh4cGiRYtwdnamWLFihIWF4e/vzz///IODgwOTJk2iTZs2zJ07V99xhRBCCCGEECJJ4eHhLFy4kDVr1tCxY0dq1qzJ2LFj6d+/P1OmTNHquWbOnEnnzp3x9PSkZs2atG3blrVr1+Ln58ebN2+0ei4hMiqFQsHgwYOxs7MDPvaiPnbsmJ5TJd+zZ8/YsmULAG3btqVw4cJ6TpS2lStXjqZNmwKwevVqgoOD9ZxIJFeG7ZkQHR3NoEGDGDNmDA0bNmTlypW4ubmxc+fOJPf/888/2b9/P61atUrlpOJ/Xbp0ierVq2NlZQXA+vXrGTZsGDlz5sTW1pbbt29ja2tLjRo1WLNmDWq1GoVCod/QQgghhBBCCPE/fvvtN/r165eoXWHp0qV5//49UVFRWpm5rFKpePLkCVWqVEkwrlQqGTp0KBs3bsTV1TXF5xHiR2BkZMSoUaMYOnQo79+/Z9myZRQrVoz8+fPrO1oi+/btS/D1unXrNK2GqlWrlmi7SGz06NEcPHiQ6OhoFi9ezPTp0/UdSSRDhi1onzlzBisrK5o3bw7AwIEDWbduHYGBgRQrVizBvq9fv2bOnDm0bdtWZy0sbt26pZWi66fb0m7cuJHiY6Wmb8l94sQJsmbNqtn34sWLNGrUiBs3bmBubs6JEyc0/06xsbFcvnwZY2PjNJE9rZHsn6dWq3VyXCGEEEIIIT558OABLVu2THJbvnz5ePXqFXnz5k3xecLDw7G2tk5yW6lSpVi7dm2KzyHEj8Ta2prhw4czadIkoqOjmTdvHnPmzMHIyEjf0T4rMjKSQ4cOAWBra4utra2eE6UPtWrVokaNGpw+fZqlS5cyevRoLCws9B1LfEWGLWg/ePCAIkWKaL42MDAgf/783L9/P1FBe/LkyTg5OfHixQuePn2a2lHTrTNnznD48GGMjIyIiYmhQoUKtGrVKsWF+yJFiuDv70/VqlUBKFSoEHfu3MHW1pZbt27RrFkzzb7v379P079QPomIiGDHjh08evQItVpN0aJFad26NaampvqOJoQQQgghhNAROzs7Ll68SIMGDRJte/ToETly5NDKeTJnzkxISEiS2y5cuPDFwpZarebXX3/l2LFjmJiYEBUVRdu2bWncuHGS+z969AgfHx/CwsKIi4ujYcOGtGzZUu6aFRlOxYoVadu2LTt27OD+/fts3bpVs2hkWnTkyBHCw8MBaN26tX7DpCMKhYLRo0fTunVr3r17h4+Pj6a3tki7MmxBOyIiItGtW6ampkRGRiYYO3jwIOHh4XTo0AFvb2+d5bGzs8PAwCDFx/k0W7V06dIpPlZK/Prrr7x+/ZrNmzdjaGiIWq1m3759bNu2LclecN+Su3Tp0uzfv59s2bJhY2OjudWnfPnyxMXF0ahRIwB+//136tWrR5kyZbT75FKQPSkfPnxg4MCBjBgxggoVKgBw7tw5Fi9ezIoVKzAzM9NW1ETSys/L99B1dpVKxeXLl3VybCGEEEIIIQDatGlDnz59cHBwSDCZxd/fn7x582rtTlOlUkmpUqX4888/ExTPY2JiWLp0KcuWLfvsY728vChWrBg+Pj4oFApUKhXLli3j+fPn9O7dO8G+V69exdvbm6lTp5I7d25UKhVbt27F09OTqVOnauW5CJGWdOnShYsXL/LgwQO2b99OlSpV0uTM5+joaE2L3bx581K9enU9J0pfWrRogZ2dHbdu3WL+/PkMHjxYJiCmcRl2UUhTU1OioqISjEVGRmJubq75OjQ0lPnz58sv3m8UFxfH0aNHGTlypKYXnEKhoGXLliiVyq8uvpkcs2fPZsqUKUyfPp1jx45hZmZG8+bNKV68ODt37sTd3Z3Lly/j4uKS4nPp2rJly/Dw8NAUswGqVq3KkCFD8PPz018wIYQQQgghhE5lypSJSZMm4eLigre3N7t27WLUqFH8/vvvjB49WqvnGjJkCGfOnGH48OHs3LmTZcuW4ezszKhRo8icOXOSjwkODub9+/d07NhRM8PawMAAV1dXAgICNG0AP/H29mbp0qXkzp1bs2+XLl2wtLTk+vXrWn0+QqQFRkZGDBs2DENDQ+Lj41mwYEGiWlNa8Mcff2gWf+3YsaNWJlT+SJRKJWPHjgXgxYsXrFixQs+JxNdk2BnaRYoUYdeuXZqvVSoVjx49SrDC66lTpwgNDaVFixbAx0+01Go1N27ckMb5X3D9+nVNO5D/1bp1a3bt2sXz5895//49BgYGxMTE0KBBA0qVKpXsc2TNmpXly5fz4MEDHjx4wJgxY1i6dClXrlzhzZs3TJo0CUtLS209JZ0KCgrSrJD8X1WqVGH16tV6SCSEEEIIIYTQBbVajZ+fHwEBAZiamhIREUGNGjVYvXo1N27c4OXLl4wePfqz/a5TQqlUMn78eN6+fculS5coWrQoAwcO/GIrkL/++kvzfvh/1apVi/Pnz+Pg4AB8bPdobW2d5Kzybt26sXLlSp3fPSuEPhQsWJDu3buzZs0anj9/zurVq9PU5LqYmBi2b98OgI2NDbVr19ZzovTpl19+Ydq0ady9e5eZM2fSr1+/BJNiRdqSYQva1atX59WrV+zevZumTZuycuVKChQoQNGiRTX7tGrVilatWmm+9vb25unTp8ycOVMfkdONTJkyffYTybdv37Jt2za2bt1Kvnz5gI8X1z59+gDf3j6icOHCCT6E+O8s5/TiSy8gpc+cEEIIIYQQGYeXlxdlypRh5cqVmrFdu3Yxa9YsxowZkyoZrKysqFu3brL2zZQpU6K2nJ9ERkaSKVMmzdfx8fGfnfVpaGiISqX69rBCpBMtW7YkICCAGzducOjQIapXr07lypX1HQv42Dv79evXgMzOTglDQ0MmTpxI165defnyJcuXL2fEiBH6jiU+I8O2HDExMcHHx4cNGzZQvXp1/P39WbhwIQDNmjVj7969+g2Yjtna2nLx4kXi4+MTbZsxYwYeHh6aYjaAsbExI0aM0Hxi+KPJlSsXDx48SDR+48YNChUqlPqBhBBCCCGEEFr36tUr3rx5Q8uWLROMt2nThpCQEN6+faufYF/QqFGjBHc2f6JWq/nnn3+oVKmSZszKyorg4OAkC9dbt25N9LyFyEgMDAxwc3PT9FX29vbm/fv3ek71cf24rVu3ApA7d27q1Kmj50TpW6dOnTR32M+aNYuwsDA9JxKfk2EL2gBlypRhx44dXLp0ic2bN1OgQAEADhw4kOQvW1dXV5mdnQwKhQInJydcXV15/vw5AGFhYXh5eaFSqWjSpEmixxgZGWFoaEhsbCwnT57k+PHjifqxZVSDBg1iwoQJBAUFacbu3buHl5cX/fv312MyIYQQQgghhLb4+/snWJDxv+rXr4+/v/9nHxseHs7Ro0fx9/dP1ZnOmTNnxsHBgUmTJvHu3TsAXr58ibu7O927d0epTFgycHJyYtiwYXz48AH4WPg+cuQIgYGBaWa2qhC6kitXLpydnQF4/fo1K1asQK1W6zXT7t27Nf93u3fvrlnnTHwfAwMDJk2aBHxcd2/p0qX6DSQ+S37SxXdxcHAgb968LFu2jHfv3mFoaEiXLl0ICQkhKioqydVgg4KCcHFxoV69ehgaGuLm5kbNmjXp3r27Hp5B6rG2tmbRokUsWbKEly9fAh/7Wi1ZsgQLCws9pxNCCCGEEEJog7m5OaGhoUlue/fuHXnz5k1y29KlS7l9+zZ169YlPDycVatW0a1bN+rXr6/LuBpdunThypUrTJ06lZiYGDJnzszgwYMpVqxYon3t7e3JkiULEyZMID4+npiYGKpVq8a8efNSJasQ+la/fn3Onj3L2bNn+eeff6hevbreZkUHBweze/duAIoVK6bpdy9Spn379pQpU4br168ze/ZsBgwYkG7WcPuRSEFbfLdChQoxderUBGMRERFs2LCBfv36JRg/efKk5sXZJx06dGDOnDmcOHEiw98WY21tzcSJE/UdQwghhBBCCKEjtWvXxtnZmQ4dOiRYKyc+Pp4jR47g6+ub6DE7d+7EzMwMb29vzVi3bt1wc3OjcOHCFClSJFWyly9fnvLlyydr39KlS2vaeQrxo1EoFAwaNIjbt2/z7t07VqxYQenSpcmePXuqZ/H09NSsb9azZ89Ed1SI76NUKpk8eTLt2rXj9evXeHl5STeHNEh+2oVW1apVi0ePHuHj40NkZCRqtZoTJ04wa9Ys5syZk2j/oUOHavo9CSGE+Dbx8fGoVCr5o+M/Sa0ZIYQQQvwvQ0NDunXrhqurK48ePQI+3qXq6upKjx49klyo7dChQ/Tq1SvBmEKhYMyYMaxZsyY1YgshvpGVlRWDBg0CPrYLWrRoUaq/XgwICNBMGKxUqVKyP5ASydOmTRtq1KgBwMKFCxO0kBVpg8zQFlqlUCiYOnUq//zzDx4eHsTGxlK1alWqV6+OjY1Nov2NjY2lx5MQQnynS5cu6TuCEEIIIf6jfv36lChRgjVr1hAaGkqOHDkYO3Ys+fLlS3J/ExOTBLO5P7GxsdH0xRVCpD329vbUr1+fv/76iytXrnDw4EGaN2+eKudWqVS4uLigVqsxNDRMdIe8SDmFQsG8efOoWbMm0dHRjBs3jk2bNuk7lvgPqSQKrVMoFNSqVYtatWppxg4fPqy5Fea/4uLiiImJSc14QgiRIVSrVk3fEb5ZVFQUHTt2BGDbtm2YmJjoOZEQQgihffnz58fT0zNZ+366q/V/i9qhoaGYm5vrIp4QQkucnZ25du0aL1++ZO3atZQpU4ZChQrp/Lw+Pj5cuHABgLZt25InTx6dn/NHVKNGjf/X3n1HRXG+fx9/00FAsJvYsdfYYjf2EkVj7yVExR7F3lssUYwVe4uxxN41atRYol+JGnvvPRYsiICU3ecPH/YnQQ0quCx+Xud4jky9ZpYd5r7mnuumUaNGrFixgqVLl9K9e3e+/PJLc4cl/58S2vJR1KxZk8WLF8cY+XrOnDnUrVvXTFGJiFgeGxsbatSoYe4w3svz589N/69WrZpFNtRf97q4iIjI+ypXrhyrV6+mQYMGpmlGoxFfX1+8vLzMGJmI/JckSZLQvXt3Bg0aRFhYGGPHjuWnn34iSZIk8bbPK1eu0KdPHwAyZcpEw4YN421fAmPGjGHdunWEhYXRs2dP9uzZ89q3auTjUw1t+Si++OILUqVKRefOndm6dSu///473bt3x2AwUK1aNXOHJyJiUWxsbCz2n6Ufg4iISFxq3rw5Fy9epE+fPvzxxx9s2rQJb29vSpYsSa5cucwdnoj8h3z58tGkSRMAbt++zYwZMzAajfGyr8jISFq3bm3qJDJ79mwcHBziZV/ykoeHB127dgVg3759rFixwswRSRQltOWj+eabbxg7dixhYWEEBQUxfPhw00AKIiIiIiIinxorKyv69+9Pnz59ePToEVZWVkydOpU6deqYOzQRiaWGDRtSsGBBAPbs2cP69evjZT/jx4/nzz//BKBz585UrVo1XvYj0Q0cOJCUKVMC4OPjo/ENEggltOWjcnFxoXbt2tStWxc3NzdzhyMiIiIiImJ2KVOmpH79+tSsWVNjTIhYGBsbG3r06GFKei5YsIBNmzbF6T527NjBwIEDAciePTtjx46N0+3LmyVLloyffvoJgLt37zJ48GAzRySghLaIiIiIiIiIiMh7c3d3Z9CgQTg4OGA0GmnatCmHDx+Ok21fvnyZRo0aERkZiaOjI7/++qtFjkVjyVq2bEm5cuUAmDZtWpx9tvL+NCikiIiIiIiIiIjIB/Dw8KBnz56MHj2aoKAgqlatyq5du0zlSN7HvXv38PT05PHjxwDMnTuXIkWKxFHEsnHjxlgv26hRI/bv309ERARNmzbF19c31mPs1KpV631DlDdQD20REREREREREZEPVKJECTp06ADA48ePqVKlynv35r137x4VK1bk3LlzAPTq1YvmzZvHWazybjJkyEC9evUAuHTp0jslwyXuKaEtIiIiIiIiIiISB2rUqMGkSZMAePjwIWXLlmX58uXvtI3Tp0/z1VdfcebMGQC+++471c1OABo2bEjatGkBWLRoETdu3DBzRJ8uJbRFRERERERERETiSLdu3fDz88Pa2prQ0FCaNHRCFxYAAFtNSURBVGlCu3btCAgIeOt6RqORn3/+mWLFinHhwgXgZTJ7zpw5WFsrhWduDg4OdO/eHWtra8LDw5kwYQLh4eHmDuuTpG+DiIiIiIiIiIhIHOrcuTO//fYbbm5uwMv61zlz5uTHH3/k9u3b0ZYNDQ1l7dq1lClTBi8vL4KDg7GysmLIkCFKZicwefLkoW7dugBcuXLlnXvfS9xI9N+I48ePU6dOHQoWLEizZs1e+zrAs2fP6N27NyVKlKB06dKMHDmSsLAwM0QrIiIiIiIiIiKJQdWqVfn777+pVq0aAAEBAfTv35/06dPj4eFB6dKlKViwIO7u7tSrV48DBw4AkDp1arZt28bw4cOVzE6AmjVrRpYsWQBYtWqVqc65fDyJ+lvx4sULOnfuTNu2bfnrr78oVaoU3bt3j7HcuHHjePHiBTt37mTjxo2cPHmS+fPnf/yARUREREREREQk0fDw8OC3335j1apV5MuXzzT96tWrHDhwgOPHj/PixQsAkiZNSt++fTl//jxVqlQxV8jyH+zs7OjRowe2trYYDAZ8fX0JDAw0d1ifFFtzBxCfDh48iLu7O56engB07NiRhQsXcunSJbJly2Zazmg00qlTJ5ydnXF2dsbT05P9+/ebK2wREREREREREUkkrKysqF+/PvXq1ePw4cNs3bqVkydPEhAQgJOTE1mzZqVs2bJUr14dFxcXc4crsZApUya8vLyYM2cODx48wNfXl2HDhmFjY2Pu0D4JiTqhffXqVTw8PEw/29jYkCFDBq5cuRItoT1y5Mho6+3Zs4c8efLEaSxnz57Fysrqg7cT9dTu9OnTH7ytj8lS4wbFbi7xHbvRaIyX7YqIiIiIiIi8jpWVFV9++SVffvmluUOROODp6cm5c+fYt28fx48fZ+nSpbRs2dLcYX0SEnXJkeDgYBwdHaNNc3JyIiQk5I3r+Pr6cuXKFby8vOI7PBEREREREREREbFAVlZWdOnShYwZMwKwcuVKDh48aOaoPg2Juoe2k5MToaGh0aaFhITg7OwcY9mIiAiGDh2Kv78/P//8M8mSJYvTWHLnzh0nrx1E9VbNmzfvB2/rY7LUuEGxm0t8xx4ZGcmxY8fiZdsiIiIiIiIikvg5OTnRv39/evToQUhICBMmTGDUqFFkz57d3KElaom6h7aHhwfXrl0z/RwZGcmNGzdMI5FGCQsLo2PHjly4cIHly5ebnqyIiIiIiIiIiIiIvEm6dOno0aMHVlZWhIaGMmLECO7evWvusBK1RJ3QLl68OAEBAaxbt46wsDBmzJhBxowZyZo1a7TlfvjhBwIDA/nll19IkSKFmaIVERERERERERERS1O8eHG8vb0BePr0KcOGDePp06dmjirxStQJbUdHR2bNmsWiRYsoXrw4Bw4cYNKkSQDUrFmTDRs28OzZM1atWsWZM2coVaoUhQoVolChQrRt29a8wYuIiIiIiIiIiIhFqFmzJg0aNADg7t27DB8+nKCgIDNHlTgl6hraAPny5WP16tUxpm/evNn0/7Nnz37MkERERERERERERCSRadmyJQEBAfzxxx9cunSJwYMHU61aNZInT27u0BKVRN1DW0RERERERERERORjsLKyomvXrpQqVQqAy5cvU6FCBR48eGDmyBIXJbRFRERERERERERE4oCtrS29e/emXLlyAJw4cYLy5ctz/fp1M0eWeCihLSIiIiIiIiIiIhJHbGxs6N69OxUrVgTgzJkzFCtWjP/9739mjixxUEJbREREREREREREJA7Z2Njw/fff0717dwDu379P+fLlWbx4sXkDSwSU0BYRERERERERERGJY9bW1kycOJFZs2Zha2tLWFgYLVu2pFOnTgQHB5s7PIulhLaIiIiIiIiIiIhIPPH29mbbtm0kS5YMgBkzZlC0aFGOHTtm3sAslK25AxARkY/HYDCYO4RPgs6ziIiIiIiIvKpixYr8/ffftGjRgv3793P27FmKFy/OgAED6NOnD05OTuYO0WIooS0i8gk5evSouUMQERERERER+SRlzpyZ3bt3M2bMGIYPH05YWBjDhg3jl19+YcqUKdSsWdPcIVoEJbRFRD4RxYoVM3cI7yQ0NJRGjRoBsGLFChwdHc0ckYiIiIiIiMiHsbW1ZfDgwVStWpX27dtz/Phxrly5gqenJ1WrVmX48OGUKFHC3GEmaEpoi4gkcjY2NtSoUcPcYbyz58+fm/5frVo1nJ2dzRjN+7OxsTF3CCIiIiIiIpLAFC9enMOHDzNjxgwGDRpEYGAg27dvZ/v27VSvXp1BgwZRqlQprKyszB1qgqNBIUVEPgE2NjYW+c/S41cyW0RERERERN7E1taWrl27cuHCBTp37oy9vT0AW7dupUyZMhQpUoT58+cTEhJi5kgTFiW0RURERERERERERMwkTZo0+Pn5cenSJTp27IidnR3wchysNm3a8Nlnn9GmTRt27dpFZGSkmaM1PyW0RURERERERERERMwsQ4YMTJ8+nRs3bjBixAg+//xzAJ4+fcr8+fOpVKkSGTJkwNvbm40bNxIcHGzmiM1DCW0RERERERERERGRBCJt2rQMHjyYa9eusXLlSmrXrm3qtX337l3mzJlD7dq1SZEiBTVr1mTChAn8/fffn0zvbQ0KKSIiIiIiIiIiIpLA2NnZ0aBBAxo0aEBAQACrVq1i/fr17Nq1ixcvXhAaGsqWLVvYsmULAG5ubnz11VeUK1eOMmXKUKhQIVNd7sRECW0LExERwR9//MHMmTOxtramWrVqVK9enQcPHrBgwQLu3LmDu7s7rVu3JmvWrBw4cIDVq1fz+PFjnjx5Qpo0aUiTJg1eXl5kzJiRffv2sXbtWiIiIvjyyy9p1KgRjo6O7xzXixcvWLVqFQcPHsTGxoZvvvmG8uXLY2VlxZUrV/Dz8yMwMBB3d3eMRiM2NjakS5eO58+f8/TpU1KkSGGKKcqNGzdYsGABAQEBpE6dmm+//ZarV6+ydu1awsPDKVq0KI0bN36veI8ePcrQoUO5fv067u7u9OjRg9q1a7915Ng7d+4wf/587t+/T4oUKfj222/JlClTtGXCwsJYvXo1Bw4cwMbGhlq1alGxYsU3bvf+/fssWLCA27dv4+bmRqtWrciePbtpfkREBCNGjGDDhg2Eh4eTKlUq8uTJQ/LkyWndunW0ZU+dOsX48eM5ceIEzs7OeHh4EBISgp2dHU2bNqVGjRpYW//fSxmXLl1i4cKFPH36lHTp0uHl5UXq1Knf+VyKiIiIiCQG+/fvZ/Xq1YSHh1O4cGGaNGmCk5PTW9e5cOECixYtIjg4mKxZs9K6dWvc3d1jtb/Q0FBWrFjBoUOHCAsL48aNG9y+fRs7Ozu8vb1p3779W9c3GAxMmjSJRYsWERERQZo0aciaNStBQUHcvHmTp0+f4ubmRtu2bWnWrBm2tjGb/0ajkb1797Ju3ToiIiLInTs3QUFB3Lp1C2dnZ1q0aEHevHlfu//w8HDWr1/Pnj17sLa2pmrVqkRERLBz504AKlWqhKen5zsNkh0aGsry5cs5fPgwdnZ2lC1blkOHDrFv3z6ePn1KhgwZsLOz4/r16zg5OdG4cWO8vb1xcnIiICCAn3/+mevXr+Pi4kLLli3JnTt3jOP9/fff2bx5MwaDgbJly1K3bl1Tr8djx46xdOlSQkNDyZEjB61atSJp0qSxjv9DnD17lkWLFhEUFESmTJn49ttvSZEixUfZt4hYhhQpUtC+fXvat2/P8+fP2blzJ5s2bWLr1q3cvHkTeFmaZOPGjWzcuBEABwcHihQpQsmSJU3/osqYWLJEndA+fvw4Q4cO5dq1a+TJk4cff/wxWsIUXt4EjBkzhg0bNmBtbY2Xlxfe3t5mivjtQkNDGTZsGJUrV2bSpEkYDAbWrFlD48aNSZo0Kf379ydbtmz8888//PTTT9y+fZtSpUrx9ddfs3LlSpo3b87atWvp1KkTP/30E/fv36dSpUqMHj0aR0dH9u7dS9u2bfHz84v1TRjAs2fP6NSpE15eXkyZMoWwsDCWLl1Knz59KFOmDHv37qVJkyZs3LgROzs77ty5Q6lSpdi+fTsGg4Fp06ZhMBgYN24cnp6eVK1ale3bt7Np0yb69OlD+vTpuXr1Kt988w0VKlRg1KhRODo6sm/fPtq2bcvUqVNJlixZrOP18/Njzpw5DBs2jDp16vD333/z/fffs2HDBubOnfva5PPff//NgQMH6Nu3L5kzZ+b27duMGzeOGjVqUK1aNQCCgoLo1KkTrVq1Mp2HZcuW0atXL8aPHx9ju0ePHsXPz4++ffuSI0cO7t27x4QJE/jyyy9p0KABoaGhFC5cmK+//pqZM2cyY8YMkiRJwo4dO9i6dSuzZ8+mSJEiNGzYkLlz57J69WpKlCjB+PHjadeuHadOncLV1ZUBAwYQGBhIp06d8PPzw9bWllWrVnHo0CF69uxJ6tSpuXDhAv3796dLly4UKlQo1udSRERERCQxGDZsGKlTp2bkyJE4OTlx4MAB2rVrx+TJk9+YVFy5ciUBAQGMGDGCZMmSceLECb7//nuGDh1K1qxZ37q/J0+e0KVLF9q1a0exYsWoVq0aZcuWpWDBgvTo0YPOnTuzfPlydu3a9dr1DQYDJUuWJE+ePGzatIl+/frh5OTEqlWrSJ8+PV9++SXOzs60atWK3r17s2HDBhYvXhytM5DRaGTgwIFkyZKFMWPGcO3aNbp164adnR2LFy8mMjKSKVOmkDlzZry8vKLtPzQ0lI4dO9KwYUMmT55MaGgonp6eODg4sG7dOmxtbdm4cSMdOnRg+vTppoTx2zx+/JiuXbvSrl07WrVqxe7du+nduzfPnz9n5cqVrF69milTppAxY0Y6depE+fLl8fHxYevWrQwZMoRZs2bRp08f8uTJw8OHD5k8eTI5cuSgZcuWpnPWvXt3SpQoga+vL7a2tmzfvp127doxY8YM5s+fT2BgIAMHDsTNzY2jR4/SuXNnfvjhBzJnzvyf8X+IRYsWceHCBXr27EmKFCk4c+YMPXv2NB2PWJ6oZKIIxN/vg5WVFbVq1cLT05N79+5x6tQpTp48yalTp3jw4AHwsgPqgQMHOHDggGm9lClTkitXLnLmzEmuXLnw8PCI1XX6VbVq1YrTY3lXVkaj0WjWCOLJixcvqFSpEv369aNq1arMnj2bXbt2sWbNmmjLLVy4kM2bNzN79myePn2Kl5cXgwYNomLFih8cQ2RkJMeOHQOgYMGC7/Rk+nUmTpxIunTpyJs3r+kpudFopEqVKrRq1YpWrVqZlv3rr7/o3r0727dvp0uXLsyfPx9ra2vu3buHr68vnp6eDBw4kD/++CPaqwc3btxg5syZjB49OtZxDR06lFatWsW4aYtKsm7ZsoWNGzeyY8cOU6I3T548nD9/nsDAQIYMGcLUqVMxGo20adMGPz8/unTpwrx580xJ4H379nHy5En8/f2ZP3++6VzeunULPz8/fvzxx1jF+s8//1CvXj0WLlwYrXdzcHAwnp6e9O7dm6+//jraOidPnmTw4MGsWbMmWg/nqHhnzpyJvb09I0aMoEmTJuTIkSPa+kuXLsXd3Z0aNWpEW/e7775j9uzZMS4aHTt2ZNy4cfj4+JAtWzb69u0bbdm5c+eybds2Vq5cSceOHenRowdjx44lQ4YMDB06FD8/P4oWLUqBAgVo1qwZTk5O/Prrr+zYsYNbt25Rv359+vTpw4wZM6LtNzw8HG9vb+bPn//Wnuofy+nTpwHe2CPkQ8X19/NjSmixG43GeBmI4vnz56RJkwaAe/fu4ezsHOf7SJIkSYL4fU9I4uvzhE/nM01o39HYelPckZGRbNmyhb/++otChQpF+1v4JkajkRcvXsRbrA4ODrH6nA0GA0ePHqVYsWLUqFHDYj6LjyEwMDDWyxoMBgICAuItlhQpUsTq9yrKx+otmdBY6rUF3h57fN/zxcbBgwc5dOgQXbt2jTb97t27TJgwAV9f3xjr3L59m8GDB9OzZ89osT9//pwePXowa9ast+5zwIABdOjQgYwZM1K0aFHmz59PgQIFmDt3LtmyZaN8+fLUq1ePb775htatW8dY/8cff+Ty5cvMmTOHkSNH0rBhQ5ydnWnUqBGBgYGcOnWK5cuXkyRJEipWrEirVq0oU6YMPj4+pnN+//59rly5Qps2bQBo164dU6dO5d69e8yePZtRo0YB4OPjQ//+/aO9zTl+/HiqVKnCF198AcC8efPw8PAgKCiI4OBgGjduDMCff/7JyZMn6dix439+Dv3796dTp05kyJABg8HAd999h42NDYUKFSJHjhz8+OOPlCpVijt37uDi4sLgwYNJliwZTZs25fz58xw6dAgHB4do24x6wJAiRQpWr16NtbU1devWjbbMyZMnWbJkCTY2NqZjjvLs2bPXtp3exX/9jgcEBDB8+HCmTJkSbfqLFy/o3Lkzc+fOfe99x0Zivba8jpLM8im5d+8e586d4/z585w7d46rV6++sb62nZ0dWbNmNSW4c+fOTfLkyd+6/dgktOPz+pJoe2gfPHgQd3d3PD09gZdJwoULF3Lp0iWyZctmWm7Tpk20adMGd3d33N3dadGiBevXr4+ThParzp49+8EN7IMHD9K3b19evHhh+qN44cIFSpQowZYtWyhSpIhp2RkzZtCsWTMGDx5M9uzZOXv2rGnezZs3mT9/PvXr12fBggWUKVMm2n6uXLli2n5snD9/ntDQ0BjrPH36lLCwMM6cOcPGjRtp0qQJp0+f5u+//yZfvnysX7+enDlz8ujRI44dO4adnR0FChRg4MCBFChQgDNnzpi2NXfuXL7//nuePn3Kr7/+Gq0X8dWrV2Md79KlS0maNClhYWEx1smaNStz586N0Yv/yJEjFCpUKNo5jFKwYEF+/vlnSpcuzenTpwkPD4+x3Tx58uDr6xutPMnVq1dJkyYNFy5ciLHN4sWLM3PmTHbv3k23bt3YvHmzqRc1QMmSJfnxxx85ffo0JUqUoHfv3jg7O/PVV19x+vRp/vzzTypUqMDVq1dJmTIljx8/5u+//yZt2rTMnTuXBw8eULx48deeszRp0rB582ayZMkSq/MZn6ISIe/yu/guEumzvI/OaDRSpkyZaE9740NUEjSulS5dmn379pk9AZpQfKzPE/SZWqqjR4/+5zJGo5GFCxdy69ateIsjffr0tG7dWp/zB3BzczN3CO9Nf8Mlrq1atYrhw4fHmP7ZZ58RFBT02nVWrlwZIzEK4OzsTMqUKXn06NFbkwGPHz82tTtCQkIoUKAAAC1atKB///6UL18ePz+/Nya0ly1bxp9//gm8LI2YM2dOJk6cSJYsWUzX6vr16+Pj40OtWrXIkSMHp06diraNDRs2mDoG/fPPP6RPnx5HR0cyZcrE48ePTct9++23rFmzhg4dOpimXblyxZTMBjh8+DDfffcdRqORrl27mhLaZcqUYcmSJW88D6968uQJGTJkAF62wfLnz09wcDBt2rShYcOG2NjYUKdOHe7evcu1a9dYu3Yt3t7eFCxYkHPnzsVIZgO0atWKdevW0aZNG3bt2sXUqVNjLJM/f352797Nr7/+GmOeq6srLi4uPHv2DFdX11gdx7tau3ZttM5pURwcHMiSJQu3bt0iffr08bJvEUm8okoOlytXDniZY7l8+TLnzp0zJbqjrvXh4eGm6evXrzetnzt3bnLnzk2ePHnIkCHDO3VAiG+JNqF99epVPDw8TD/b2NiQIUMGrly5Ei2hfeXKlWjLZcmShbVr137UWGPrdTXPQkJCcHV1jfGUIywsjOTJk3P06NEYr0fZ2toSERFBsmTJePLkSYxtvusTkzctHx4eboo5JCQEFxcX0/+TJUtm6gHo4OBAREQEdnZ2uLq6EhgYGONmISIiAgcHB1xdXWP0HHzdeXmT4ODgN9bBS5o0qemVjFe9Gvu/ubq68vTp07fG8brXNv5rm9evX8fGxgZra+vXLht1zl1cXAgKCsLR0dG0zKufR9TNV3h4OA4ODtjY2BAcHPzGmzEXF5d465kpiZcSSomLPk95k2LFisVqOaPRGOONuLjm6upKsWLF9PsqInEiLCyMJEmSvHbem+7xnz9//sZ76qg2y9sS2lHbNRgM0e7fo9pGAKlTpyYsLOy16xsMBtP9f9S2goKCcHJyMv1sa2truk66urpy//79aNuIjIw0va37/PnzaG8/vHrcbm5uMRL7/24DRu3LysoqRsIjtu21V5cLCgrCwcEBW1tbHB0defHiBdbW1jg6OuLm5oaVlZUpJnt7+zfuw93d3bSctbX1G5MxBoPhjQ/6XFxcCA0NjbeE9vPnz9+479edexGR9+Hg4ECePHlMZYyMRiP3799/Yy/ue/fuce/ePXbv3g28fGAb1Xs7d+7cVK5c+T/HmYhPiTahHRwcHGOwQCcnJ0JCQqJNCwkJifYBODo6EhoaGufx5M6d+4O71qdLl46QkBDc3d1Nryt5eHjQrl27aGVIAGrXrs2mTZvo378/s2fPNs2LiIjA2dmZkiVLsnPnTn766adoveTCwsJImjTpO73ylyxZMjw8PGL8Il+9epU///yTvHnzUrp0aQ4cOICPjw/p06dn+vTpTJ8+HUdHR6ytrSlatCgAv/zyC7179+bnn382vfoGULVqVQICArh8+TLDhg0z/cF/13ibN29Or169yJw5c4xX3S9fvkzlypVjbCsoKAg/Pz969uwZY3uLFy/Gx8eH1KlTkzx58tdu9++//6ZkyZLRtpstWza6d+/+2rjXr19PixYt2L17N0+ePKF27drs2rXLtOzp06dJnjw5efPmZf369XTu3Jndu3dz+fJlmjRpQsaMGUmVKhWpU6fm5s2bGI1GihcvzvXr18mZMyfNmzdn2bJl1K9fP8a+/fz86NOnT4IYAfdjlhyR92dlZcW+ffss9kFIQihPkZBY+ucJ+kzjg42NTbSyWbFRo0aNeP09ep/P2ZJeof4Yoh7Ix0ZCKzkiEtdKlCjBzp07qVy5crTpERERb0woV6pUia1bt9KwYcMY8y5dukS6dOneus+IiAhevHiBg4MD4eHhhIaG4ujoyP79+ylcuDAAY8eOpXz58q9dP3/+/CxYsMBU2zooKIjKlSszcuRIU3v2+PHjps5cZ86c4bPPPou2jS+++IL//e9/lCpViixZspjekH3x4oUpqQ4vyzT8+9zY29vz+PFj01hGyZMn59atWwQHB0frTXz37t1YlwkKDw8nLCwMe3t7vvzyS9asWUNoaCh79+6levXqbNmyhUOHDnHx4kWSJEliet390qVLMdr5UTZs2EDVqlUByJgxI2fPno0xUOTTp0/JlCkTGzdujNEb3mg0cvPmTVKmTBmrY3gfFStWZOPGjfTo0SPGvBMnTsSqXIuIyLuysrJ6bS/uS5cucfbsWc6cOcO5c+dMD9WeP3/OkSNHOHLkCPCyMsTBgwf/8+9dfEm0CW0nJ6cYiemQkJAYycZ/J7BDQ0Pf+HTe3Dp16oSPjw8DBgwwTQsJCeHixYuUKFECo9Foaty5u7tz9OhRnJycyJgxI8uXL6du3boMGDCA7777jrt373LixAnCw8NN2woLC6NXr17vPChmx44d6dmzJxMmTDA9RLh79y6//voruXPnZufOnZQuXZohQ4bw9ddf89dff5ElSxY2bNjAqVOnaNasGfCy/IuLiwu5cuXC2dmZTZs2mUrGNGrUiKpVq/LVV19FS2b37t2bdu3axTrWokWLkjZtWlq3bm0aFMVgMDB8+HACAgL49ttvY6zj4uJC2rRpWbFiBQ0bNjSd4y1btuDk5GSqJdepUyd69uzJpEmTTOchaoDOmTNnRtumg4MDhQsXZu7cubRp08a0zb179/LkyROyZs2Kn5+fKZldpEgR5s6dy9dff80333zDkiVL2Lt3L48fP6Zu3bps27aNpUuX8sUXX9CpUyf69OljGuG8fv36PH78mMGDBzN+/HhSp07N06dP2bt3L1999RXw8kZt3rx5FC5cOEEks8WyWFlZxUstZDEPfZ7yOu+TDP5U6xxbinf9fN5lwHARS9OgQQPatGlD9uzZTWUCw8PD6du3b7RONq8qXrw4EyZM4Ny5c6YOGAaDgfHjx1OzZs3/fOjWvn17evfuzfjx4+nZsydlypRh6dKlzJw5kzlz5vDnn38yb948Tpw48dr1J06cSPHixU33/7169WLYsGHs37+frFmzcu7cOXx9ffHz82P48OHcvXuXkSNHRttG06ZN8fb2JmPGjKRPn57KlSszfvx4rl27ZmoTHj58mHPnzsWoL965c2d69+7N5MmTcXZ2pmPHjnTr1g3AVG86MDCQfv36xXp8Jm9vb3r37o2vry8uLi5kzZqV48eP06NHD/78809OnTrFuHHj+OKLL0iVKhUFChRg3rx5XLx4kebNm+Pn50fnzp1N597f359r166RL18+ANq2bUvXrl2ZNGmSKUEdHBxMz549GT16NGPHjqVw4cLkz58feNkB5scff6Ru3brx+rA8f/78zJkzB39/f4oXLw68bJ9NmzaNcuXK6YGsiHw0Dg4O0TrMGgwGbt26xZkzZzh79ixnz57ln3/+AV6OaXf//n2zJbQT7aCQe/bs4aeffmLDhg3Ayz9GxYsXZ/ny5dEGL2zQoAHt27enSpUqAMyfP58TJ04wadKkD44hPoqfb9myhcWLF5MsWTKMRiMODg707NmT/fv38/vvv5MkSRJTDbaWLVvi6+vLw4cPuXLlCrdu3SJ//vy4ublRtGhRGjZsyLhx43j69Ck2NjZERETg7e1t6hHwLk6cOMGMGTOwsbEhMjISFxcX+vbtS/LkyZk+fTp79uzB2tqaixcvkjx5cnLlysXJkydJmjQpWbJkISQkhGLFitG2bVusrKwwGo3MnTuXv/76CycnJ4KDgylcuDDXr18nMDAQW1tbwsPDadeuXbTa4bERFhZGnz59+P3337GxsSE8PJy8efMyY8YMUqVKFWP506dPYzQa+fvvv9m3b5+pp/+XX35Ju3btot3cnDp1iunTp2NtbU1kZCTOzs707dv3tduFl/X6tm7dSpIkSQgNDSVPnjx07drV9Lvi7+9Phw4dCA8PJzAwkKCgIMqXL0/KlCmjLRsWFsaPP/7Ihg0bePHiBaGhoYSFhZE1a1ZSp05NmjRp6Nmzp6lOX2RkJH5+fpw+fRpHR0eCg4OpXr06DRo0eKdzGZ80KOSbWXLsIp8CS/2OWmrcIp8KS/6OJvRBIeFlL92xY8fy6NEj7OzsCAsLo23btnz55ZdvXOfYsWMsWLCA0NBQHBwcCA4OpmHDhlSrVi1W+zx69CizZs3C1taW06dPc+LECdKmTYvRaMTd3Z0VK1a8tXby+fPnadmyJc+fPyc8PJyHDx9StGhRHjx4wK1bt0iZMiVWVlZkz56d8ePHkz17diD6OX/06BFjx44lMDAQGxsbLl++jIODAxkzZiQ0NJSsWbPSo0eP15ZRPH/+PFOnTsVoNGI0GgkLCzO1Ua2srLCxscHHx+edxuf5+++/mT17Nra2tkRGRnLr1i2CgoK4f/8+L168ICQkBIPBQIoUKTAajXz22WeMHTuWIkWKsHHjRtavX29qW2XPnh0fH59o5Uju3r3L+PHjCQkJMbXjunbtSq5cuQgNDcXX15dbt26ZPs+mTZtSqVKlWMf/OrH5HY+IiGDixIlcvHjR1D775ptvYjXo2odKrNeW19GgkCIf7vHjx5w7d45q1aqZena/SXxeXxJtQjs0NJRKlSrRu3dvatSowezZs9m1a1eMmo4LFixgy5YtzJw5k+fPn/Ptt98ycODAD/6jBfHzwSWUG753Zalxg2I3FyW038ySYxf5FFjqd9RS4xb5VFjyd9QSEtrvw1JjV9wfV0KPO7FeW15HCW2RuBObB27xeX1JtMXqHB0dmTVrFosWLaJ48eIcOHDA1Ou6Zs2app7bLVu2pGjRotSuXZsmTZrEyRNYEREREREREREREYl7ibaGNkC+fPlYvXp1jOmbN282/d/W1pa+ffvSt2/fjxmaiIiIiIiIiIiIiLyjRJ3QNrdXq7lERkbG6Tbjansfi6XGDYrdXOI79le3a2mVl+Lj2iIiccdSry+6togkbJZ6bYG3X190v/rxKe6PK6HHnVivLa8Tn4N7inxqYvOdi8/rS6KtoZ0QhIWFcfLkSXOHISL/IX/+/Njb25s7jFjTtUXEcljS9UXXFhHLYUnXFtD1RcRS6NoiIvElrq8vibaGtoiIiIiIiIiIiIgkLuqhHY8MBgMREREAWFtb6/UWkQTEaDRiMBiAl7X0ra0t5/meri0iCZulXl90bRFJ2Cz12gK6vogkZLq2iEh8ic/rixLaIiIiIiIiIiIiImIRLOfRm4iIiIiIiIiIiIh80pTQFhERERERERERERGLoIS2iIiIiIiIiIiIiFgEJbRFRERERERERERExCIooS0iIiIiIiIiIiIiFkEJbRERERERERERERGxCEpoi4iIiIiIiIiIiIhFUEJbRERERERERERERCyCEtoiIiIiIiIiIiIiYhGU0BYRERERERERERERi6CEtoiIiIiIiIiIiIhYBCW0RURERERERERERMQiKKEtIiIiIiIiIiIiIhZBCW0RERERERERERERsQhKaIuIiIiIiIiIiIiIRVBCW0REREREREREREQsghLaCdDx48epU6cOBQsWpFmzZty4cSPGMkFBQeTOnZtChQqZ/i1YsMAM0b7eggUL6Nev32vnhYaG0rNnT4oWLUq5cuVYu3btR47u7d4W+4ULF2Kc923btn3kCGPasWMHNWvWpHDhwtSrV48jR47EWCahnvfYxJ5Qz7vEDYPBYO4QREQ+2Lp167h165a5wxBJUD60XWOu+9fYxF2zZs1oMefLl49q1ar95zF9DO/bFjN3e+Ftcf/zzz906NCBYsWK8dVXXzFt2jTTvD/++IO8efNGO98nTpz4WGED79+GfPToEe3ataNQoUJUrVqVvXv3fsywE6XYfH8NBgOjRo2iePHilCxZktmzZ5shUvNKDHmnj8WS81sf00fPpRklQQkNDTWWLl3auHHjRuOLFy+MU6dONdatWzfGcocPHzbWqlXLDBG+XUREhHHWrFnGXLlyGfv27fvaZUaNGmXs2LGjMTg42HjixAljsWLFjGfPnv3IkcYUm9jXr19v7NChw0eO7O1u3LhhLFy4sNHf398YGRlpXL9+vbFYsWLGZ8+eRVsuIZ732MaeEM+7fLixY8ca9+3bZzQajUaDwWDmaEQkPnwq3+1r164ZixUrZly7dq3RaEy8xx0ZGWnuED6aSZMmGf/44w9zh2HR4qJdY47719jG/arAwEBjpUqVjLt27TIajeZrq31oW8xc7YXYxO3l5WX84YcfjC9evDDevHnTWLlyZeOGDRuMRqPROH36dOMPP/wQ73G+zoe2ITt16mQcPny48cWLF8Y9e/YYixYtanzw4EF8hpyoxfb7+/PPPxsbNmxofPz4sfHatWvGChUqGHfu3GmGiM3D0vNOH4sl57c+JnPl0tRDO4E5ePAg7u7ueHp6Ym9vT8eOHbl58yaXLl2Ktty5c+fIlSuXmaJ8s759+3LkyBEaNmz4xmU2bdpEx44dcXJyIn/+/Hh6erJhw4aPGOXrxSb2hHje7969S6NGjShWrBjW1tbUrl0bgGvXrkVbLiGe99jGnhDPu3yY4OBgIiMjGTZsGP7+/lhZWWE0Gs0dlrynyMjI105X73uxsrIydwgfRaZMmejbty8TJkzgwoULifa4ra1fNh1+/PFHzp07Z+Zo4s+TJ0/4559/OHLkCCEhIeYOx2LFRbvGHPevsY37Vb6+vpQoUYIKFSoA5rt3/dC2mLnaC/8Vt8FgwN7eng4dOmBvb0/69OmpVKkSx44dA8zbVviQNuTz58/5448/6NKlC/b29nz11VcUKVJEb6J+gNh+fzdt2sR3332Hu7s7mTJlokWLFqxfv95MUX98lp53+lgsOb/1MZkrl6aEdgJz9epVPDw8TD/b2NiQIUMGrly5Em258+fPc+3aNapVq0bZsmX58ccfCQsL+9jhxtCnTx9mzZpFqlSpXjv/6dOnBAQERDvGLFmyxDg+c/iv2OHleT98+DAVKlSgYsWKzJo16yNG+HrFihWjb9++pp+PHTtGSEgImTNnNk1LqOc9NrFDwjzv8v6MRiNJkiShU6dOtGrVigEDBnDw4EEltS1UZGQkNjY2GAwGZs+ezS+//MKSJUuA/0t+yadn5MiRjBo1ips3b/L06VMA0/c7MX3PX/076unpSdWqVdm8eTPBwcFmjCp+3bhxg8uXL3Pv3j3gzQ+0LJm7uztfffUVe/bs4fr164Ae0L2PD23XmOv+NbZxR7l8+TKbN2+mR48epmnmaqt9SFvMnO2F/4rb2tqamTNnkjJlSgDCw8PZv38/OXLkAF4mSn777TfKlClDtWrVWL16dbzHHNvY4c1tmevXr+Pq6kry5MlNy2bJkoWrV6/Ge9yJVWy/v1euXElwbeOPydLzTh+LJee3PiZz5dLU0kxggoODcXR0jDbNyckpRu+QJEmSUKxYMVatWsXy5cs5dOhQgkjypU6d+q3zo47DycnJNM3R0ZHQ0NB4jSs2/it2eNnAqVChAps3b2b27NmsWLGCNWvWfIToYuf69et07dqVbt264eLiYpqekM97lDfFDgn/vMu7ieq5OH36dNKnT0+DBg0YOHCgempbqKhkdlQN/Lt377J27VqaNGliuvboM/203Lt3j82bN7NhwwamT59O586d+d///sf9+/eB/7sGWPrvRe/evalfvz6zZs0iODgYe3t7ypYty5kzZ3jy5AmQOJK9/z6GjBkzkjt3bnx9fU0PtBKLkydPmv7/9ddfU7RoUfr27UtwcLAe0L2HD23XmOv+NbZxR/n5559p0KBBtKSkudpqH9IWM2d7ITbtsCiRkZH069cPOzs76tati8FgIG3atNSqVYtdu3bx448/MnbsWPz9/eMx4v/zIW3I4ODgaOcbXp5zvRny/mL7/Q0JCUnQbeP4Zul5p4/FkvNbH5O5cmm6M0tgnJycYvzyh4SE4OzsHG1av3796NWrF66urnz++ed4e3uza9eujxnqe4m6aL56jKGhoSRJksRcIb2Tn376ie+++44kSZKQLVs2mjdvnmDO+4kTJ2jSpAmNGjWiTZs20eYl9PP+ttghYZ93eT937tzh1q1bhIaG0rFjR2rVqsWAAQNMSW31hLMsW7ZsIW3atMyaNYu+ffuSNWtWXrx4QWBgIPDplJ2Ql0nqNGnS0KNHD5o1a0bTpk356quvmDx5Mr169WL27Nk8evQIg8Fg8Q+wsmfPToYMGVi6dClDhw5lyZIllClThixZspjePkoMyd6oh1Zbtmwx9Rrs0aMHGTNmZOXKlWaOLu5MmTKFhg0bMnv2bDZv3gzA4MGDyZkzJ6tWrdLfpffwoe0ac92/xjZugLCwMLZs2UKDBg2iTU+obbW3ndOE3l6Al0m4jh07cvXqVebOnYu9vT3W1tYsXLiQOnXqYG9vT6FChUzJ7YTiTW2Z1/2uJbRzbmli+/39d9LxUzvviT3v9LFYwnUzoYiPnI4S2gmMh4dHtPrBkZGR3LhxgyxZskRbbsqUKdy8edP0c1hYGA4ODh8rzPfm7u5O8uTJox3j1atXYxxfQhQaGsrYsWN59uyZaVpCOe/79u3Dy8uLHj160LVr1xjzE/J5/6/YE/J5l9j7dw+/zz//nMKFCzN+/HiePXtG586dqVOnDkOGDGH//v3qCZfA/TuxExERwfPnz4GXNdTOnz/PsmXLmDhxIosXLzZHiGImUQ8vkidPzt69e8maNSve3t44Ozvz7Nkzli1bho+PD15eXty8edOiH3aUKVOGcuXKMWrUKAoXLoy/vz/NmjWjfv36JEmSxOLfJHr1un3s2DF8fX0ZP348o0aNIjg4mDx58iSqV2qjehfdv3+fHTt20L17d548eUL+/Pm5deuWqReWEtux96HtGnPdv8Y2boC///6blClTkj179mjTE2pb7W3nNCG3F+Dlq/0tWrTA2tqaxYsXm3rE379/n/Hjx0d7QJpQzje8vS2TKVMmnj17ZnqrBxLWObdEsf3+/nu5T+28J/a808eS0K+bCUV85XSUMUhgihcvTkBAAOvWrSMsLIwZM2aQMWNGsmbNGm25M2fOMGHCBEJCQrh9+zazZ882DaiX0NWsWZMpU6YQFBTEqVOn2LRpE56enuYO6z85Ojry559/Mm3aNMLDw7lw4QJLliwx+3m/du0a33//PaNHj35rEf6EeN5jE3tCPe8Se6/WWN6wYQNnz54FoE2bNhQqVIjVq1djZ2dHy5YtqVy5Mr6+voSEhFh0z83ELuqBw5AhQzhx4gS5cuXC2dmZ9u3bc+7cOdatW4eDgwP//POPbug+UZUqVSJTpkxMnz6dIUOG8ODBA5YsWcLWrVupW7curq6uhIeHmzvMd7Zv3z5ToyVPnjwEBQWxbNkymjZtypQpU8ifPz8jRowgMDCQ7du38+LFC/MG/J4iIiKwsbHBaDRy5swZsmfPzrZt22jRogWHDx9m8ODBPHnyhF9//ZUtW7aYO9w40aRJE5o2bUpYWBhdu3blyZMnDB48mODgYHbs2MHy5csBjQ3wLuKiXWOO+9fYxg0v3zIsWLBgjOkJua32tnOaENsLUXx8fPj888+ZNm1atN6Pbm5urFmzhoULF2IwGDh8+DBbtmxJMHG/rS3j4uJC2bJlmThxIi9evGDfvn0cPnyYKlWqmDtsixXb72/NmjWZPXs2AQEB3Lhxg8WLF1OrVi0zRf3xfQp5p48lIV83E4r4yunojiyBcXR0ZNasWSxatIjixYtz4MABJk2aBLz8okSNljpy5EgiIiIoV64cDRo0oHLlyjRt2tSMkb9doUKFOHz4MPDyNdVkyZJRqVIlunTpQv/+/cmdO7eZI3yzV2OfOnUq58+fp3jx4rRr144OHTpQrlw5s8a3fPlyQkJC6NevH4UKFTL9O3z4cII/77GNPSGed4kdg8FgSmYPHDiQSZMmMX36dPr06cOTJ0/IlSsXly9fBl4+4fb29mb+/Pk4OTlZdM/NT8WDBw+YPn06uXLlIk2aNBw7dow+ffpgMBhYsWIFly5dImPGjOYOU+LZqz15X/1/vXr12L59OxcvXmTOnDk4Oztjb29PnTp1mDJlSrQBdCzBoUOHGDx4MFOnTmXdunUADB06lKdPnzJ16lQABg0aRNeuXSlSpAjHjx8nKCjIjBG/H4PBgK2tLQaDgQYNGjBkyBAaNGjA9u3bKVmyJGvXrqV48eKkTJnSNDCbpQ4Q9csvv/D333+bfq5SpQoGgwEXFxd+/vlnihcvbnooO2PGjGjLyn+Li3aNOe5fYxs3vCyh9rpBsBJaWy22bYKE1l6IivvChQvs37+fvXv3UrRoUVObYciQITg4ODBz5ky2bNlCkSJFGDBgAKNGjTINGGnu2OHtbZlRo0bx4MEDSpcuzciRI5kwYcJbB1aTt4vt97dly5YULVqU2rVrmx5oVqpUyYyRf1yJNe/0sST0PEtCEd85HSujusCJiEg8MhgMtG3blkKFCtGkSRPu3LnDpEmTcHR0JHPmzCxcuJBBgwbRrFkzc4cqb2EwGGL0TLx58yYjR46ke/fu5M6dmyFDhvDo0SMePHhAREQEI0aMIG/evGaKWD6GV9/A8PX15cKFC7Rq1Ypy5coRHBzMd999R4ECBRgwYADwssa2JT+sOn78OIcPH+bnn3+mcuXKdO7cmRMnTvDXX3/RoEEDsmXLZlo2KCgoxiDHlsJoNOLl5cVnn32Gt7c3ixYtYvv27fj4+FC/fn3Tcjt37iRHjhxkyJDBjNG+n8uXLzN16lT27dtH7969qV69OkmSJKFPnz6kSJGCwYMHAxAYGMiuXbtYvHgx06ZNI02aNGaOXERERESU0BYRkTj37NkzXrx4gZOTE8uXL2ft2rVMnz49WtJj8+bNPHz4kHHjxlG9enVGjx6tmmwJnNFoZODAgVSvXp0SJUpgbW3NgAEDSJo0KYMGDQJe9toOCwvD2dkZd3d38wYsH4XBYKB+/fpkzZqVwoULU7lyZVKlSoWVlRX/+9//8PPzY9iwYTFqzFqKqKT9qy5fvszQoUPJnj07Dg4OXL58mbp161KjRg0zRfnhXj3OK1eu0KtXL1Md8BEjRvD48WOOHTtG7969Lfo4XxUZGcnWrVuZMWMGhQsXpmLFihQuXJjmzZvToUMHatasaVo2ODhYgzyJiIiIJBC25g5AREQSl+HDh3Pv3j1u3rxJy5YtCQwMxGg0Mn/+fLp27WoaxCcqUZAnTx4+++wzJbMTqFeTXE+ePMHNzY1BgwZRsWJFSpYsiY+PD82aNaNSpUqULFlSr8l+gnbs2MHnn3/O+PHjAfDz8+Ps2bPkyJGDihUr8uTJE06dOmWRCe3X9UBv3rw5FStWZNq0aezYsYOrV69y8OBBDh06RMaMGcmXL5+5w35nr5aHWrp0KUWLFiV16tQEBQUxYsQInjx5wujRo/Hx8aFHjx7cvXuXNm3amDvs9/LqNc3KyoqaNWuSK1cu9u7dy8yZM8mRIweNGjXi1KlTVKhQAUdHR6ytrXFycjJz5CIiIiISRQltERGJMx07diQgIIBRo0Zx7do1qlSpwrNnz7h37x4A69ato379+ri5uZlKWHz55Zdmjlre5N8DembMmJG+ffvSoEEDDh48yIQJE/jiiy/IkiULR44coWTJkuYOWT6Cf/dYdnJyIigoiCFDhnDhwgUePnxIo0aNmD59OqVKlTKVHbFEUb//UT3QK1WqRL58+TAajbi5uVG/fn2MRiOurq7s3r2bFClSmDvk92JtbY3RaMTb25v06dNTp04dRowYwfXr1zlz5gxr167Fzs6OHDlyULp0acqXL2/ukN/Ls2fPcHV1xWg00qtXLwIDA6lVqxZVq1bFy8uLWrVq0b9/f06cOMG5c+eoXLkyRYoUAbDoUjkiIiIiiY0S2iIiEiemTp1KYGAgK1asACB79uzcvHkTb29vHjx4QP78+bG2tmbt2rXUrVsXNzc3M0csb2M0Gk3JvG+++Qaj0Uh4eDhVqlShZcuWNG/enDp16jBr1iyuXbvGqlWraNeunXraJ3IRERHY2tpiNBrx9/fH3d2dMmXKcPjwYcLCwihTpgwdO3bExsaG69evc/nyZZo0aWLusD/Im3qgZ8uWjVatWpEiRQrat29P8+bNLa5m9r/LQ92/f59hw4bh4uKCi4sLT58+JW3atPj7+3P16lW2bdvGmjVrSJ06tblDf2fjx48nMDCQbt260bt3b1xdXcmWLRvz58/n0aNHfP3116RJk4Y5c+awbds2Nm/erLJJIiIiIgmUEtoiIvLBjEYjt27dolWrVqZpd+7coVmzZnh6epIvXz4mTpyIo6Mjd+/exd7enqZNm6rHWwIVNXCfwWDg+++/J3/+/IwePZoZM2awc+dOrKysqFu3Lh4eHnTv3p2wsDACAwOVzE7kDAYDtra2REZGUr9+fSIjI7Gzs6NmzZr4+PgAcO7cOS5evMjevXvZunUrbdu2NXPU7+5deqDnzZuXqlWrAlhcMvt15aEMBgPz5s0zlYdydXXF1taWhQsXcvnyZWbNmmVxyeyot4HKly/PwIED8fX1JVWqVIwdOxaAtWvXmh7EVq9enbRp01KtWjUqVaqEra2aSiIiIiIJke7SRETkg7148YJz585RrFgx07Tjx4/TsmVLvL29CQoKYsGCBeTOnZs0adLw1VdfKZmdQBkMBsLCwnB0dCQiIoKQkBB69uwJQEBAAGnTpuX06dNYW1tTvXp1cufOjaOjI46OjmaOXOKbtbU1BoOBTp06UaBAAXx8fJg/fz7r1q0jMDAQHx8f1q9fz7FjxwgPD2fx4sVkyZLF3GG/k3fpgX7z5k0ePXpk7pDfS2zKQ9WtW5e0adMyatQoU5Lf0kqqhIeHM3bsWNq1a0fRokVZsGAB3t7ePHz4kHPnzpErVy7q1q2LwWBg3bp1hIaGUq9ePVKnTq1ktoiIiEgCpjs1ERH5YNbW1iRNmpTLly+bpn399dem/xuNRpImTUrJkiVVMzsB++GHH7h9+zbh4eF4enpSu3ZtbGxscHNzY8iQIVy5coXFixczYsQIVqxYwc2bNxk1apQGS0vkospSODs7ExwcTEBAABMnTiRJkiQ8efKE3Llzc+TIEZYuXUrfvn0BCAoKsrgey+/aA33Lli189913Zo763cW2PNS6dev45ptvLC6J/Sqj0QiAl5cXT58+ZcGCBfj6+tK9e3c2b95MihQpSJUqFfXr1+fFixf88ccfFl8iR0RERORTYG3uAERExPLZ29vj5eXFr7/+yqZNm2LMX7NmDQ8fPiRjxoxmiE5io1OnTpw+fZpatWrh4eHBggULePr0KT/99BM2NjbcunXLVEM4adKk1KhRg4EDByqZncgNHz6cvn378u2337JhwwYePHhA1qxZefHiBf369ePOnTv069cPFxcXRowYQZ8+fQBwdnY2c+Tv7t890H/55RdKly7NunXrmDhxIgDr169n+PDhbN++3SJ7oL+tPFT58uUZPnw4N2/e5M6dOxw6dIitW7eaksKWKiqZHRwcTPLkycmdOze+vr5s376d+fPnExAQAECzZs2YMGGC6maLiIiIWAD10BYRi3ft2jXatWvH77///sZlzp07R5s2bfDw8ACgYsWKeHl5fawQPwllypTBy8uLH374gfv371OlShWCgoI4cOAAs2bN4ueffyZNmjTmDlNeo0uXLgQEBLB8+XIAsmTJgr+/PwEBAWTPnp2HDx9y6tQpNm7ciLW1NWvWrGHhwoUW3XNT/turZSlu3LhB+fLlef78OV9//TXOzs5cuHCBGTNmkDx5cjJmzMjAgQMpX748gEWVFPpUeqDDp1Meys/Pj3v37nHs2DE+//xzXF1dqVevHl5eXowfP54CBQrg6+tLv379eP78Od26dSNFihQW+ZmKiLwqNu2i69evM3DgQAwGA+7u7owbN07XPxF5q4R4bVFCW0Qs2pIlS1i9ejWPHz9+63InT56kefPmdOrU6SNF9umxt7enXbt2fPbZZ0yaNIkVK1bg7u5OypQpWbRoETlz5jR3iPIaXbp04eLFi2zbts00zcnJCaPRSEREBAApU6Zk0KBBLFy4kCRJkjB9+nSL65kq7+ZNZSm+/fZbHj9+jI+PD1myZOHYsWNcv36dzZs3s2zZMjJkyGDmyN9N1MCIN27coGXLlnzxxRemHugjRozgwYMH+Pr6MmDAAEaMGMGxY8cYN26cRfZAh0+jPFSHDh0IDAykdevWZM+encDAQPbu3cuzZ8/44osv8PHxYfLkyRQoUIBx48YxfPhwUy90S0zei8SlqEGhxTLFtl00fvx42rVrR7ly5ZgyZQpLly7F29v7I0UpIpYmoV5blNAWixLVG+yvv/7i6dOnuLu7U7RoUTp06ECuXLlivZ1+/frx119/sWvXrlivM3XqVPz8/KJNs7GxwdXVlaJFi9K9e3eyZ8/+1m1UrFiRYsWK8eOPP8Z6v/J2KVOmZOnSpZQpUwZ42Wtu0KBBPHz4kIiICL7//ntKlSrFyZMnuXbtGgcOHCBlypQMHDiQVKlSmTn6xMfJyYmGDRuaeme7urri4OCgAQMTsIYNG9KnTx+uXr1KlixZuHnzJq1bt6Z58+bkzp0beNnArV27NhUrVsTGxkZlRhK5t5WlqF27NtmyZWPatGmEhIQQGRnJuXPnmD17tsUlsz+VHuiviioP1bNnT/LkyYOnp2e0+ZZeHmrixIk8fPiQVatWRZueO3duOnfuTNeuXalZsyZdunShTJky5M2bl6VLl2JnZ2emiEXi3j///IOnpyfTpk2jePHisVonMDCQkSNH0rBhQ9PDrNe1fV7Vp08f2rRpQ8uWLQFYtGjRW/cRERHB4sWLWb9+PVevXsXKyorMmTNTq1YtWrRogb29vWnZt3WCSJIkCUePHo3VcX1qYtsumjx5MlZWVhgMBu7evUv+/PnNHLkkNAaDgeXLl7N06VJu3bpF8uTJqVSpEt9///0H97j9d06kZcuW/PXXX29cftWqVeTPn5+cOXPSpUsXunbt+tbtP378mJkzZ7Jz507++ecfkiRJQu7cuWnRogVVqlQxLefv7x/tXvffypcvz6xZs97x6BKnhHptUUJbLMbFixdp3LgxBQsWZNCgQaRIkYJ//vmHxYsX06hRI3755RcKFiwY73FEvZIPEBkZyZ07d5g4cSLNmzdn8+bNb02S+vn56XWuOFatWrVoP8+cOZO8efPSrl07njx5QuPGjdm4cSP58+enQYMGFChQgHXr1jFkyBBmzJhhpqgTP3d3d9UhtRDlypVj3LhxNG3alDFjxjBy5EgaNWpE+/btgZc3tNbWL4fc0PXr0/BfZSmePXvG8uXLKVmyJG3atCEyMhI3NzczRvzuPpUe6K+TWMtDGQwGbt++beoJFBYWhr29PQaDgUqVKtGjRw/Wrl2Ln58f4eHh7Nmzhzp16iiZLYnK3bt3adOmDc+ePXun9c6ePcv69eupX79+jHmvtn1e9fnnn7/TPgYPHsz27dvx9vYmX758GAwGDh8+zKRJkzhy5AjTpk2LtnyDBg1o2LBhjO1E3ZNITLFtF9nb2/PkyROaNGnC8+fPTfd8IlHmzp3LpEmTaNOmDSVLluTq1atMmTKFixcvMn/+/Dh/sJ8nTx6GDh362nlZs2aN9XZCQ0Np3rw5kZGReHt7kylTJp49e8Zvv/1Gly5dGDBgAK1bt462zpAhQ8ibN2+MbSVNmvTdDiIRS6jXFiW0xWIsWLCAZMmSMWfOHGxt/+9Xt3LlylSvXp3p06cze/bseI/j30nzIkWK8Nlnn9G8eXPWrl371lcq8uTJE8/RyYULF3j48CF79+41Tbt37x5Vq1Y1JVyqVavGhAkTzBWiSIJTrlw5xo4dS/v27WnUqBFdunQBoiez5dPxX2Up4GUPuSJFiljkQ45PpQf6myTW8lAvXrzg0qVLVKpUCcB0rxh1DStSpAjLli3DxcWF7t2706FDB709JImGwWBg3bp1jB07Ns63HRcdhu7cucPatWsZMWIEjRo1Mk0vW7YsyZMnZ/To0Zw4cYICBQqY5qVNm/ajdFZKzN7ULsqQIQPu7u5s3bqVQ4cO0a1bN9avX2/GSCUhMRgMzJkzh8aNG9OzZ08ASpUqRbJkyfDx8eHUqVNx3vPWxcUlTr7vW7du5fLly2zbto3MmTObpleuXJnQ0FCmTJlCixYtsLGxMc3Lli2brjXvKKFcW9RKFYvx8OFDjEYjBoMh2vQkSZIwYMAAU2M7MjKS2bNn4+npSYECBShYsCBNmjTh4MGDb93+ypUrqVmzJvny5aN8+fJMnTqVyMjIWMWWL18+AG7fvg287PlVpUoV/Pz8KFasGGXKlOHp06dUrFiRfv36mdYLCgrihx9+oGzZshQsWJD69euze/fuOIvrU5Q1a1aaNGnCokWLmDt3LtWqVSNNmjR4eXlx6NAhAPbv32/6zETkpXLlyjFv3jx+//13zp49C6gX1KcqqizFr7/+yqZNm2LMjypL8V9lthKqqB7oQUFBpmlRPdB79+5N5cqVSZkyJY0aNWLkyJEsX778tT13LFlUeajNmzczd+5cZs2axfjx4y02mQ0vr1dOTk5cvHjR9LPBYDDdM7m4uJA6dWocHBwAlMyWROX8+fMMHTqUOnXqMG7cuBjzHz16RM+ePSldujT58+fnm2++Yd26dUD01+5btWplKiHyvnLmzImfnx/16tWjQIEC+Pn5vbEdB1CrVi169Oih3pDx4E3tog4dOnDu3DkAnJ2ddb8n0QQFBfHNN9/EKEvm4eEBwM2bN+nXrx/ffvstq1evplq1auTLl49vvvkmWoIT4Ny5c3h5eVGoUCEqVKjAhg0b4iRGf39/cubMybJly6hQoQKFCxdm//79PHz4EOC115r27dvTqVMnwsLC4iSGT1lCubaoh7ZYjPLly7Nnzx6aNGlC/fr1KVGiBB4eHlhZWVG9enXTcuPHj+fXX3+lZ8+e5MyZk3v37jFt2jS6devG7t27X1v7ddasWUycOJEWLVrQv39/zp49y9SpU7l79y6jR4/+z9iuXr0KEK3m5J07d9izZw8TJ07kyZMnMV7HjoyM5LvvvuPatWt8//33eHh4sHbtWjp37szChQspWrToB8f1KerQoQODBw9m48aNBAYG0qhRI+zt7RkxYgQjR47Ezs6OJEmSMGLECHOHKpLglC5dmjFjxvDdd98xa9asaD2l5NOSWMtSQOLvgf4uElN5KAcHB7799lv69euHh4cHnp6e0RpSe/bswcXFJVqdXpHE4rPPPuP3338nbdq0+Pv7x5jfu3dvAgICGD58OC4uLqxfv56+ffuSNm1a8uXLx5AhQxgxYgRDhgyJUXc7aoDoV1lbW781UTFz5kx69uxJlixZSJcuHZkyZeKzzz5jzJgxnD9/3pSAcnFxIXny5K99Ld1gMLx236++qStv96Z2UYcOHRg2bBh2dnZYWVkxZswYc4cqCUjSpEkZNGhQjOk7duwAXvZo3rt3L6dOneL+/fumutqTJ0+ma9eu7N27Fzc3N+7du0eLFi3InDkzvr6+BAUFMX78eAICAmJs+9XB6F9lY2Pz1vImfn5+DBo0iNDQUAoVKkTKlCmZOHEirVu3pnHjxqbxMuzs7ChQoMBr2zavu9ZYWVlF68Ut0SWUa4v+GojFaNasGQ8ePGDevHmmZGSyZMkoU6YMrVq1Ml2c7t+/j4+PT7TeBQ4ODnTt2pXz58/HeJ3k2bNnTJ8+ncaNG5su3GXKlMHd3Z1Bgwbh5eUVrRfaqxe70NBQzp07x+jRo3F1daV27drRluvbty9FixZ97fHs3buX48ePM23aNCpXrgxAiRIluHnzJgcPHiRnzpzvFNen7vDhwwC4ubkxZcqUGPPz5cvHsmXLPnZYIhanfPnyjBgxAh8fH3777Tclfz5RibUsBcR+YET9jbU8FSpUoHXr1gwfPpx//vmHypUrExERwR9//MGcOXNYtGgRSZIkMXeYInHuvx5M/fXXX3Tu3NnU5ihWrBju7u7Y29vj4uJCtmzZgJeJqqj/R3ndGyqNGzd+a+eQokWL4uXlFW3a7Nmz6dOnD0uXLmXp0qVYW1uTN29evv76a5o3bx7jrYnp06czffr0GNv+888/NbD7f/ivdlHBggXVLpJ3cvz4cWbPnk2FChXIkSMH8DKPsmbNGlOnviRJktCiRQsOHjxItWrV+Pnnn01vzydPnhyALFmyRCs7FOXQoUOvvdZMmDCBmjVrvjGuZs2aRevcmDNnTiZOnMjw4cOZOnUqU6dOxdHRkaJFi9KgQYMYHRgAvv322xjTsmTJwtatW99+Uj5BCe3aooS2WJRu3brx7bffsm/fPv73v//h7+/Pxo0b2bRpEwMGDKBVq1b89NNPwMtX665cucL169f5448/AF77esnRo0cJDQ2lYsWK0ZLVFStWBF6Wp3i1Ufu6C2327Nnx8/OLcXOVO3fuNx7LkSNHsLOzM+0HXvZ2iLoA7N27953iEhGJK1WqVKFUqVJKZn/iospSRPXOdnV1xcHBIVGUakjMPdA/Zfb29nh7e/P5558zefJkVq5ciZubGy4uLixatIhcuXKZO0QRsyhevDhTp07lzJkzlC1blnLlytG3b99Yrbtq1aoY01KkSPHWdV7XBsqRIwfr1q3j5MmT/Pnnn/j7+3P06FFOnjzJqlWrWLJkiSnpBdCoUaPXJr6SJUsWq7hFJG4cOXKEDh06kD59+mg9bpMnTx7tDfW0adMCEBISYlqvYMGC0b7XX3zxxWsHlM2bNy/Dhw+PMf3V7b/O6641VatWpUKFChw8eJADBw7g7+/PgQMH+PPPP/ntt9+YPHlytF7fw4cPj5HjSQz3up8CJbTF4ri5ueHp6WnqUXXmzBl69+6Nr68vtWrV4tatWwwfPpyTJ0/i5OREtmzZTBdNo9EYY3tPnjwBeONgjvfv34/286s3dXZ2dqRKleqNN3XOzs5vPI4nT57g7u7+xtf13jUuEZG49Lbrl3xaElNZiiiJuQf6py5JkiQ0atSIqlWrEhQUhJOTE46OjrqmySdt4sSJzJw5k99++41t27ZhbW1NqVKlGDFiBOnSpXvruu8z+Nvb3oTInz8/+fPnp2PHjoSEhDB//nymTJnCnDlzoiXZU6dOHecDz4nIu9myZQv9+vUjc+bMzJ07N9oDpX+Xco1KEkfVr3769Cnp06ePsc3XvWHh7Owcp9caOzs7ypYtS9myZYGXAxaOHDmSbdu2sXv3bipUqGBaNkuWLLrWWCgltMUi3Lt3j/r169OtWzcaNmwYbV6ePHnw8fGhc+fOXLp0iS5dupAzZ042b96Mh4cH1tbW7Nmzh23btr1221EDkIwfPz7aSLhRUqZMGe3nuLrYubq68uTJE4xGY7QnhGfOnMFoNL5zXCIiIhJ7ibkHuiTOBzEi78vV1ZXevXvTu3dvrly5ws6dO5k+fTrDhw9n9uzZ8b7/sWPH8scff8R4hd/JyYnOnTuzfft2Ll26FO9xiEjszZs3D19fX4oVK8a0adNwdXV9p/WTJUtmGqTxVVEd9+JDkyZNyJIlS4zazWnSpGHUqFGma82rCW2xXBrOVixCypQpsbW1ZenSpbx48SLG/CtXruDg4IC9vT1PnjyhVatWZMuWzdT7OWq03deNdvvFF19gZ2fHvXv3TD0G8ufPj62tLRMmTODWrVvxckxFixYlPDw82kjARqOR/v37M2vWLLPFJSIi8ilxd3cnffr0uLm5KZktIonO7du3KVeunCmZ7OHhQbt27ShVqhR37twBiPfBz7JkycLVq1fZsmVLjHnPnz/n/v37prq8ImJ+y5YtY9y4cXz99dfMnTv3nZPZ8HJ8sKNHj3Lv3j3TtEuXLnHz5s24DDWadOnSsXXr1tfu4+rVqwC61iQi6qEtFsHGxoZhw4bRuXNn6tevT/PmzcmaNSshISHs37+fJUuW0K1bNzw8PHBxcWHmzJnY2tpia2vLtm3bTGVCouo5vSpZsmS0bduWyZMnExQURPHixbl3756ptlJ81VssX748hQoVol+/fnTv3p0MGTKwfv16Ll++zA8//GC2uEREREREJHFIly4dadOmZeTIkQQFBZExY0ZOnTrFnj17aN++PYApWbV7927c3NzivJ1Rp04dNm7cSJ8+ffD396dcuXIkTZqUa9eu8csvv+Do6Mh3330Xp/sUkffz4MEDxowZQ7p06WjevDlnzpyJNv+/6lpHad26NatWraJNmzZ07dqVyMhIJk6ciJ2dXXyEDYCPjw/+/v40aNCAVq1aUahQIaytrTl58iTz58/nq6++4quvvoq3/cvHpYS2WIzy5cuzYsUK5s2bx8yZM3n06BH29vbkyZOHiRMnUrVqVeDliNjjxo2jW7duODs7kzt3bhYvXky7du04fPhwtEEYo3Tv3p1UqVKxdOlS5s6di5ubGyVLlqRHjx7v9TQyNmxsbJgzZw7jx49n8uTJhISEkDNnTubPn0+BAgXMFpeIiIiIiCQefn5+TJgwgcmTJ/P48WM+++wzunTpYhqrJ3v27Hh6erJkyRL27dvHpk2b4nT/9vb2zJs3j19++YWtW7eyefNmQkNDSZ06NRUrVqRjx47/OdCkiHwce/bsITQ0lNu3b9O8efMY8/9dzuNNkiVLxq+//sqoUaPo168fzs7OtG3b9rVvasSV9OnTs3btWmbNmsXGjRuZM2cORqORTJky0aZNG1q1ahWt3KtYNivj60bJExERERERERERERFJYFRDW0REREREREREREQsghLaIiIiIiIiIiIiImIRlNAWEREREREREREREYughLaIiIiIiIiIiIiIWAQltEVEROJYz549yZkzJ/Pnz48xr2LFivTr1w8Af39/cubMib+//8cOUURERERERMQiKaEtIiISh549e8aOHTvIkSMHy5cvx2g0mjskERERERERkURDCW0REZE4tGnTJgAGDhzItWvXOHjwoJkjEhEREREREUk8lNAWERGJQ6tXr6ZkyZKUKFGCTJkysWzZsnda/8KFC7Rv357ChQtTuHBhOnfuzM2bNwGIiIigTJky9OzZM8Z6VatWZdCgQXFyDCKSeOmtERERERGxdEpoi4iIxJGLFy9y8uRJ6tSpA0CdOnXYuXMnDx8+jNX6V69epUmTJgQEBDB27FhGjRrFzZs3adq0KQEBAdja2lKnTh127NhBUFCQab0jR45w/fp16tWrFx+HJSJxrF+/flSsWPGN81+ttR9XAgMD6dOnD4cPHzZNa9myJS1btozT/YiIiIiIxDcltEVEROLI6tWrcXd3NyWq6tatS2RkJKtWrYrV+n5+fjg5OfHzzz9TpUoVvv76a3755RdCQ0OZO3cuAPXr1yc0NJRt27aZ1lu3bh2ZM2emcOHCcX9QIpIonD17lvXr12MwGEzThg4dytChQ80YlYiIiIjIu1NCW0REJA6Eh4ezYcMGKleuTGhoKIGBgTg7O1OkSBFWrFgRLYn0JgcPHqRYsWI4OjoSERFBREQELi4uFC1alAMHDgCQJUsWihQpwvr16wEIDQ3lt99+U+9sEXln2bJlI1u2bOYOQ0RERETknSihLSIiEgd2795NQEAAq1at4ssvvzT9O3ToELdv32bfvn3/uY0nT56wZcsW8ubNG+3fH3/8wf37903LNWjQgL/++ou7d++yY8cOnj9/bipzIiKJz8qVK6lZsyb58uWjfPnyTJ06lcjIyBjL1KtXj4IFC1KgQAG++eYbfvvtNwD8/f1p1aoVAK1atTKVGfl3yZGcOXOyZMkSBg4cSLFixShUqBDdunWLUTZp3rx5VKpUiQIFCtCkSRN27dpFzpw58ff3j8/TICIiIiICgK25AxAREUkMVq9eTYYMGRg1alS06UajkS5durBs2TLKlSv31m24urpSqlQpvLy8Ysyztf2/P9nVq1dn5MiRbN26lcOHD1O6dGnSpEkTNwciIh9NRETEfy4za9YsJk6cSIsWLejfvz9nz55l6tSp3L17l9GjRwOwZMkSRo4cSdeuXSlSpAhPnz5lzpw59OrVi0KFCpE3b16GDBnCiBEjGDJkCMWLF3/j/iZOnEiVKlWYMGECN2/eZMyYMdjY2DBhwgTgZWmkadOm0aZNG0qUKMG+ffvo3r17nJwPEREREZHYUEJbRETkAz148IB9+/bRtm3b1yaKqlevzpo1a7h3795bt1OsWDEuXbpE7ty5TQlso9FIr169yJQpE7lz5wYgSZIk1KhRg02bNnH58mVTUktELMft27fJmzfvW5d59uwZ06dPp3HjxgwaNAiAMmXK4O7uzqBBg/Dy8iJ79uzcvHmTNm3a0KlTJ9O66dKlo169ehw5coSaNWuaSov8V5mRHDlyMGbMGNPPJ06cYOvWrQAEBwczZ84cmjdvTq9evUzxhISEsHz58vc7ESIiIiIi70gJbRERkQ+0bt06IiIiqFmz5mvn16lTh5UrV7JixYq3bqdTp040adKE9u3b07RpUxwcHFi+fDk7duxgypQp0ZZt0KABjRs3xs3NjcqVK8fZsYjIx5EqVSpmzJjx2nkdO3YE4OjRo4SGhlKxYsVovbmjBp7dv38/2bNnp1+/fgAEBgZy5coVrl+/bir/ERYW9k5xFSxYMNrPadOmJSQkBIBjx44RGhpK9erVoy3j6emphLaIiIiIfDRKaIuIiHygNWvWkD17dnLkyPHa+UWKFCF9+vSsXLkSKyurN24nV65cLFmyhIkTJ9KnTx+MRiM5cuRg2rRpVKpUKdqyBQsWxN3dnRo1amBvbx+nxyMi8c/e3p78+fO/cR68rKsP4O3t/drlomrr37hxgyFDhvC///0POzs7PDw8yJUrF/DyLY934eTkFO1na2tr0zYePXoEQPLkyaMtkyJFinfah4iIiIjIh1BCW0RE5ANFDbz2JlZWVuzcuTPG9OLFi3P+/Plo0/LmzcvcuXP/c5/Hjx/nyZMnNG7c+N2CFRGLkTRpUgDGjx9P5syZY8xPmTIlBoMBb29v7OzsWLVqlalk0aVLl1i/fn2cxpM2bVoAAgIC8PDwME2PSnSLiIiIiHwM1uYOQERERGLP39+fKVOm4OPjQ5kyZUy9MEUk8fniiy+ws7Pj3r175M+f3/TP1taWCRMmcOvWLR4/fszVq1dp0KCBaR7A3r17ATAYDADY2Nh8cDy5cuXC1dWV33//Pdr07du3f/C2RURERERiSz20RURELMjjx49ZsGAB2bNnZ+TIkeYOR0TiUbJkyWjbti2TJ08mKCiI4sWLc+/ePSZPnoyVlZUpwZwuXTqWLFlC2rRpSZo0Kfv27eOXX34BMNW/dnV1BWD37t24ubm918MwFxcX2rZty5QpU3BycqJYsWL89ddf/Prrr8DL8iQiIiIiIvFNCW0RERELUr169RgDsolI4tW9e3dSpUrF0qVLmTt3Lm5ubpQsWZIePXqYktTTp09n1KhR9OvXD3t7e7Jly8aMGTMYPXo0hw8fpmXLlmTPnh1PT0+WLFnCvn372LRp03vF0759e4xGI8uXL2fevHl88cUX9OrVizFjxpAkSZK4PHQRERERkdeyMr7rSDEiIiIiIvLJiYiIYNOmTRQvXpzPPvvMNH3JkiWMHDkSf39/U91vEREREZH4ooS2iIiIiIjESs2aNbG3t6djx44kS5aMCxcuMGnSJCpXrsyYMWPMHZ6IiIiIfAKU0BYRERERkVi5efMmEyZMwN/fn8DAQD7//HNq165N+/btsbOzM3d4IiIiIvIJUEJbRERERERERERERCyChiIXEREREREREREREYughLaIiIiIiIiIiIiIWAQltEVERERERERERETEIiihLSIiIiIiIiIiIiIWQQltEREREREREREREbEISmiLiIiIiIiIiIiIiEVQQltERERERERERERELIIS2iIiIiIiIiIiIiJiEZTQFhERERERERERERGLoIS2iIiIiIiIiIiIiFgEJbRFRERERERERERExCIooS0iIiIiIiIiIiIiFkEJbRERERERERERERGxCP8P6ggMB8hmqmQAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1500x1500 with 25 Axes>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tm.options.plot_options.set_to_defaults()\n",
    "tm.options.plot_options.set_font_sizes(\n",
    "    axis_title=8, major_ticklabel=6, minor_ticklabel=5\n",
    ")\n",
    "analyzer.eda().plot_pairs(\n",
    "    [\"SalePrice\", \"Alley\", \"Heating\", \"1stFlrSF\", \"2ndFlrSF\"],\n",
    "    htest=True,\n",
    "    figsize=(10, 10),\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aW9NF4obbWfL"
   },
   "source": [
    "## 2.2 Tables"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "j4AeBOtNlS2M"
   },
   "source": [
    "We can display all the basic statistics of each numerical variable."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "UchAMgzVZFnK",
    "outputId": "02a7dcb0-1962-46b4-a5b5-9f0e96ed6d6a"
   },
   "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>Statistic</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>variance</th>\n",
       "      <th>skew</th>\n",
       "      <th>kurtosis</th>\n",
       "      <th>q1</th>\n",
       "      <th>median</th>\n",
       "      <th>q3</th>\n",
       "      <th>n_missing</th>\n",
       "      <th>missing_rate</th>\n",
       "      <th>n</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Variable</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1stFlrSF</th>\n",
       "      <td>334.0</td>\n",
       "      <td>4692.0</td>\n",
       "      <td>1162.627</td>\n",
       "      <td>386.588</td>\n",
       "      <td>1.494501e+05</td>\n",
       "      <td>1.375</td>\n",
       "      <td>5.722</td>\n",
       "      <td>882.00</td>\n",
       "      <td>1087.0</td>\n",
       "      <td>1391.25</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2ndFlrSF</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2065.0</td>\n",
       "      <td>346.992</td>\n",
       "      <td>436.528</td>\n",
       "      <td>1.905571e+05</td>\n",
       "      <td>0.812</td>\n",
       "      <td>-0.556</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>728.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3SsnPorch</th>\n",
       "      <td>0.0</td>\n",
       "      <td>508.0</td>\n",
       "      <td>3.410</td>\n",
       "      <td>29.317</td>\n",
       "      <td>8.595060e+02</td>\n",
       "      <td>10.294</td>\n",
       "      <td>123.235</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BedroomAbvGr</th>\n",
       "      <td>0.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.866</td>\n",
       "      <td>0.816</td>\n",
       "      <td>6.650000e-01</td>\n",
       "      <td>0.212</td>\n",
       "      <td>2.219</td>\n",
       "      <td>2.00</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtFinSF1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>5644.0</td>\n",
       "      <td>443.640</td>\n",
       "      <td>456.098</td>\n",
       "      <td>2.080255e+05</td>\n",
       "      <td>1.684</td>\n",
       "      <td>11.076</td>\n",
       "      <td>0.00</td>\n",
       "      <td>383.5</td>\n",
       "      <td>712.25</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtFinSF2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1474.0</td>\n",
       "      <td>46.549</td>\n",
       "      <td>161.319</td>\n",
       "      <td>2.602391e+04</td>\n",
       "      <td>4.251</td>\n",
       "      <td>20.040</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtFullBath</th>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.425</td>\n",
       "      <td>0.519</td>\n",
       "      <td>2.690000e-01</td>\n",
       "      <td>0.595</td>\n",
       "      <td>-0.840</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtHalfBath</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.058</td>\n",
       "      <td>0.239</td>\n",
       "      <td>5.700000e-02</td>\n",
       "      <td>4.099</td>\n",
       "      <td>16.336</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtUnfSF</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2336.0</td>\n",
       "      <td>567.240</td>\n",
       "      <td>441.867</td>\n",
       "      <td>1.952464e+05</td>\n",
       "      <td>0.919</td>\n",
       "      <td>0.469</td>\n",
       "      <td>223.00</td>\n",
       "      <td>477.5</td>\n",
       "      <td>808.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>EnclosedPorch</th>\n",
       "      <td>0.0</td>\n",
       "      <td>552.0</td>\n",
       "      <td>21.954</td>\n",
       "      <td>61.119</td>\n",
       "      <td>3.735550e+03</td>\n",
       "      <td>3.087</td>\n",
       "      <td>10.391</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fireplaces</th>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.613</td>\n",
       "      <td>0.645</td>\n",
       "      <td>4.160000e-01</td>\n",
       "      <td>0.649</td>\n",
       "      <td>-0.221</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FullBath</th>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.565</td>\n",
       "      <td>0.551</td>\n",
       "      <td>3.040000e-01</td>\n",
       "      <td>0.037</td>\n",
       "      <td>-0.858</td>\n",
       "      <td>1.00</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageArea</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1418.0</td>\n",
       "      <td>472.980</td>\n",
       "      <td>213.805</td>\n",
       "      <td>4.571251e+04</td>\n",
       "      <td>0.180</td>\n",
       "      <td>0.910</td>\n",
       "      <td>334.50</td>\n",
       "      <td>480.0</td>\n",
       "      <td>576.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageCars</th>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.767</td>\n",
       "      <td>0.747</td>\n",
       "      <td>5.580000e-01</td>\n",
       "      <td>-0.342</td>\n",
       "      <td>0.216</td>\n",
       "      <td>1.00</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageYrBlt</th>\n",
       "      <td>1900.0</td>\n",
       "      <td>2010.0</td>\n",
       "      <td>1978.506</td>\n",
       "      <td>24.690</td>\n",
       "      <td>6.095830e+02</td>\n",
       "      <td>-0.649</td>\n",
       "      <td>-0.421</td>\n",
       "      <td>1961.00</td>\n",
       "      <td>1980.0</td>\n",
       "      <td>2002.00</td>\n",
       "      <td>81</td>\n",
       "      <td>0.055</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GrLivArea</th>\n",
       "      <td>334.0</td>\n",
       "      <td>5642.0</td>\n",
       "      <td>1515.464</td>\n",
       "      <td>525.480</td>\n",
       "      <td>2.761296e+05</td>\n",
       "      <td>1.365</td>\n",
       "      <td>4.874</td>\n",
       "      <td>1129.50</td>\n",
       "      <td>1464.0</td>\n",
       "      <td>1776.75</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HalfBath</th>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.383</td>\n",
       "      <td>0.503</td>\n",
       "      <td>2.530000e-01</td>\n",
       "      <td>0.675</td>\n",
       "      <td>-1.077</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>KitchenAbvGr</th>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.047</td>\n",
       "      <td>0.220</td>\n",
       "      <td>4.900000e-02</td>\n",
       "      <td>4.484</td>\n",
       "      <td>21.455</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LotArea</th>\n",
       "      <td>1300.0</td>\n",
       "      <td>215245.0</td>\n",
       "      <td>10516.828</td>\n",
       "      <td>9981.265</td>\n",
       "      <td>9.962565e+07</td>\n",
       "      <td>12.195</td>\n",
       "      <td>202.544</td>\n",
       "      <td>7553.50</td>\n",
       "      <td>9478.5</td>\n",
       "      <td>11601.50</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LotFrontage</th>\n",
       "      <td>21.0</td>\n",
       "      <td>313.0</td>\n",
       "      <td>70.050</td>\n",
       "      <td>24.285</td>\n",
       "      <td>5.897490e+02</td>\n",
       "      <td>2.161</td>\n",
       "      <td>17.375</td>\n",
       "      <td>59.00</td>\n",
       "      <td>69.0</td>\n",
       "      <td>80.00</td>\n",
       "      <td>259</td>\n",
       "      <td>0.177</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LowQualFinSF</th>\n",
       "      <td>0.0</td>\n",
       "      <td>572.0</td>\n",
       "      <td>5.845</td>\n",
       "      <td>48.623</td>\n",
       "      <td>2.364204e+03</td>\n",
       "      <td>9.002</td>\n",
       "      <td>82.946</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MSSubClass</th>\n",
       "      <td>20.0</td>\n",
       "      <td>190.0</td>\n",
       "      <td>56.897</td>\n",
       "      <td>42.301</td>\n",
       "      <td>1.789338e+03</td>\n",
       "      <td>1.406</td>\n",
       "      <td>1.571</td>\n",
       "      <td>20.00</td>\n",
       "      <td>50.0</td>\n",
       "      <td>70.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MasVnrArea</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1600.0</td>\n",
       "      <td>103.685</td>\n",
       "      <td>181.066</td>\n",
       "      <td>3.278497e+04</td>\n",
       "      <td>2.666</td>\n",
       "      <td>10.044</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>166.00</td>\n",
       "      <td>8</td>\n",
       "      <td>0.005</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MiscVal</th>\n",
       "      <td>0.0</td>\n",
       "      <td>15500.0</td>\n",
       "      <td>43.489</td>\n",
       "      <td>496.123</td>\n",
       "      <td>2.461381e+05</td>\n",
       "      <td>24.452</td>\n",
       "      <td>698.601</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MoSold</th>\n",
       "      <td>1.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>6.322</td>\n",
       "      <td>2.704</td>\n",
       "      <td>7.310000e+00</td>\n",
       "      <td>0.212</td>\n",
       "      <td>-0.407</td>\n",
       "      <td>5.00</td>\n",
       "      <td>6.0</td>\n",
       "      <td>8.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OpenPorchSF</th>\n",
       "      <td>0.0</td>\n",
       "      <td>547.0</td>\n",
       "      <td>46.660</td>\n",
       "      <td>66.256</td>\n",
       "      <td>4.389861e+03</td>\n",
       "      <td>2.362</td>\n",
       "      <td>8.457</td>\n",
       "      <td>0.00</td>\n",
       "      <td>25.0</td>\n",
       "      <td>68.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OverallCond</th>\n",
       "      <td>1.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>5.575</td>\n",
       "      <td>1.113</td>\n",
       "      <td>1.238000e+00</td>\n",
       "      <td>0.692</td>\n",
       "      <td>1.099</td>\n",
       "      <td>5.00</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OverallQual</th>\n",
       "      <td>1.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>6.099</td>\n",
       "      <td>1.383</td>\n",
       "      <td>1.913000e+00</td>\n",
       "      <td>0.217</td>\n",
       "      <td>0.092</td>\n",
       "      <td>5.00</td>\n",
       "      <td>6.0</td>\n",
       "      <td>7.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PoolArea</th>\n",
       "      <td>0.0</td>\n",
       "      <td>738.0</td>\n",
       "      <td>2.759</td>\n",
       "      <td>40.177</td>\n",
       "      <td>1.614216e+03</td>\n",
       "      <td>14.813</td>\n",
       "      <td>222.501</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SalePrice</th>\n",
       "      <td>34900.0</td>\n",
       "      <td>755000.0</td>\n",
       "      <td>180921.196</td>\n",
       "      <td>79442.503</td>\n",
       "      <td>6.311111e+09</td>\n",
       "      <td>1.881</td>\n",
       "      <td>6.510</td>\n",
       "      <td>129975.00</td>\n",
       "      <td>163000.0</td>\n",
       "      <td>214000.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ScreenPorch</th>\n",
       "      <td>0.0</td>\n",
       "      <td>480.0</td>\n",
       "      <td>15.061</td>\n",
       "      <td>55.757</td>\n",
       "      <td>3.108889e+03</td>\n",
       "      <td>4.118</td>\n",
       "      <td>18.372</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TotRmsAbvGrd</th>\n",
       "      <td>2.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>6.518</td>\n",
       "      <td>1.625</td>\n",
       "      <td>2.642000e+00</td>\n",
       "      <td>0.676</td>\n",
       "      <td>0.874</td>\n",
       "      <td>5.00</td>\n",
       "      <td>6.0</td>\n",
       "      <td>7.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TotalBsmtSF</th>\n",
       "      <td>0.0</td>\n",
       "      <td>6110.0</td>\n",
       "      <td>1057.429</td>\n",
       "      <td>438.705</td>\n",
       "      <td>1.924624e+05</td>\n",
       "      <td>1.523</td>\n",
       "      <td>13.201</td>\n",
       "      <td>795.75</td>\n",
       "      <td>991.5</td>\n",
       "      <td>1298.25</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>WoodDeckSF</th>\n",
       "      <td>0.0</td>\n",
       "      <td>857.0</td>\n",
       "      <td>94.245</td>\n",
       "      <td>125.339</td>\n",
       "      <td>1.570981e+04</td>\n",
       "      <td>1.540</td>\n",
       "      <td>2.979</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>168.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YearBuilt</th>\n",
       "      <td>1872.0</td>\n",
       "      <td>2010.0</td>\n",
       "      <td>1971.268</td>\n",
       "      <td>30.203</td>\n",
       "      <td>9.122150e+02</td>\n",
       "      <td>-0.613</td>\n",
       "      <td>-0.442</td>\n",
       "      <td>1954.00</td>\n",
       "      <td>1973.0</td>\n",
       "      <td>2000.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YearRemodAdd</th>\n",
       "      <td>1950.0</td>\n",
       "      <td>2010.0</td>\n",
       "      <td>1984.866</td>\n",
       "      <td>20.645</td>\n",
       "      <td>4.262330e+02</td>\n",
       "      <td>-0.503</td>\n",
       "      <td>-1.272</td>\n",
       "      <td>1967.00</td>\n",
       "      <td>1994.0</td>\n",
       "      <td>2004.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YrSold</th>\n",
       "      <td>2006.0</td>\n",
       "      <td>2010.0</td>\n",
       "      <td>2007.816</td>\n",
       "      <td>1.328</td>\n",
       "      <td>1.764000e+00</td>\n",
       "      <td>0.096</td>\n",
       "      <td>-1.191</td>\n",
       "      <td>2007.00</td>\n",
       "      <td>2008.0</td>\n",
       "      <td>2009.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Statistic          min       max        mean        std      variance    skew  \\\n",
       "Variable                                                                        \n",
       "1stFlrSF         334.0    4692.0    1162.627    386.588  1.494501e+05   1.375   \n",
       "2ndFlrSF           0.0    2065.0     346.992    436.528  1.905571e+05   0.812   \n",
       "3SsnPorch          0.0     508.0       3.410     29.317  8.595060e+02  10.294   \n",
       "BedroomAbvGr       0.0       8.0       2.866      0.816  6.650000e-01   0.212   \n",
       "BsmtFinSF1         0.0    5644.0     443.640    456.098  2.080255e+05   1.684   \n",
       "BsmtFinSF2         0.0    1474.0      46.549    161.319  2.602391e+04   4.251   \n",
       "BsmtFullBath       0.0       3.0       0.425      0.519  2.690000e-01   0.595   \n",
       "BsmtHalfBath       0.0       2.0       0.058      0.239  5.700000e-02   4.099   \n",
       "BsmtUnfSF          0.0    2336.0     567.240    441.867  1.952464e+05   0.919   \n",
       "EnclosedPorch      0.0     552.0      21.954     61.119  3.735550e+03   3.087   \n",
       "Fireplaces         0.0       3.0       0.613      0.645  4.160000e-01   0.649   \n",
       "FullBath           0.0       3.0       1.565      0.551  3.040000e-01   0.037   \n",
       "GarageArea         0.0    1418.0     472.980    213.805  4.571251e+04   0.180   \n",
       "GarageCars         0.0       4.0       1.767      0.747  5.580000e-01  -0.342   \n",
       "GarageYrBlt     1900.0    2010.0    1978.506     24.690  6.095830e+02  -0.649   \n",
       "GrLivArea        334.0    5642.0    1515.464    525.480  2.761296e+05   1.365   \n",
       "HalfBath           0.0       2.0       0.383      0.503  2.530000e-01   0.675   \n",
       "KitchenAbvGr       0.0       3.0       1.047      0.220  4.900000e-02   4.484   \n",
       "LotArea         1300.0  215245.0   10516.828   9981.265  9.962565e+07  12.195   \n",
       "LotFrontage       21.0     313.0      70.050     24.285  5.897490e+02   2.161   \n",
       "LowQualFinSF       0.0     572.0       5.845     48.623  2.364204e+03   9.002   \n",
       "MSSubClass        20.0     190.0      56.897     42.301  1.789338e+03   1.406   \n",
       "MasVnrArea         0.0    1600.0     103.685    181.066  3.278497e+04   2.666   \n",
       "MiscVal            0.0   15500.0      43.489    496.123  2.461381e+05  24.452   \n",
       "MoSold             1.0      12.0       6.322      2.704  7.310000e+00   0.212   \n",
       "OpenPorchSF        0.0     547.0      46.660     66.256  4.389861e+03   2.362   \n",
       "OverallCond        1.0       9.0       5.575      1.113  1.238000e+00   0.692   \n",
       "OverallQual        1.0      10.0       6.099      1.383  1.913000e+00   0.217   \n",
       "PoolArea           0.0     738.0       2.759     40.177  1.614216e+03  14.813   \n",
       "SalePrice      34900.0  755000.0  180921.196  79442.503  6.311111e+09   1.881   \n",
       "ScreenPorch        0.0     480.0      15.061     55.757  3.108889e+03   4.118   \n",
       "TotRmsAbvGrd       2.0      14.0       6.518      1.625  2.642000e+00   0.676   \n",
       "TotalBsmtSF        0.0    6110.0    1057.429    438.705  1.924624e+05   1.523   \n",
       "WoodDeckSF         0.0     857.0      94.245    125.339  1.570981e+04   1.540   \n",
       "YearBuilt       1872.0    2010.0    1971.268     30.203  9.122150e+02  -0.613   \n",
       "YearRemodAdd    1950.0    2010.0    1984.866     20.645  4.262330e+02  -0.503   \n",
       "YrSold          2006.0    2010.0    2007.816      1.328  1.764000e+00   0.096   \n",
       "\n",
       "Statistic      kurtosis         q1    median         q3  n_missing  \\\n",
       "Variable                                                             \n",
       "1stFlrSF          5.722     882.00    1087.0    1391.25          0   \n",
       "2ndFlrSF         -0.556       0.00       0.0     728.00          0   \n",
       "3SsnPorch       123.235       0.00       0.0       0.00          0   \n",
       "BedroomAbvGr      2.219       2.00       3.0       3.00          0   \n",
       "BsmtFinSF1       11.076       0.00     383.5     712.25          0   \n",
       "BsmtFinSF2       20.040       0.00       0.0       0.00          0   \n",
       "BsmtFullBath     -0.840       0.00       0.0       1.00          0   \n",
       "BsmtHalfBath     16.336       0.00       0.0       0.00          0   \n",
       "BsmtUnfSF         0.469     223.00     477.5     808.00          0   \n",
       "EnclosedPorch    10.391       0.00       0.0       0.00          0   \n",
       "Fireplaces       -0.221       0.00       1.0       1.00          0   \n",
       "FullBath         -0.858       1.00       2.0       2.00          0   \n",
       "GarageArea        0.910     334.50     480.0     576.00          0   \n",
       "GarageCars        0.216       1.00       2.0       2.00          0   \n",
       "GarageYrBlt      -0.421    1961.00    1980.0    2002.00         81   \n",
       "GrLivArea         4.874    1129.50    1464.0    1776.75          0   \n",
       "HalfBath         -1.077       0.00       0.0       1.00          0   \n",
       "KitchenAbvGr     21.455       1.00       1.0       1.00          0   \n",
       "LotArea         202.544    7553.50    9478.5   11601.50          0   \n",
       "LotFrontage      17.375      59.00      69.0      80.00        259   \n",
       "LowQualFinSF     82.946       0.00       0.0       0.00          0   \n",
       "MSSubClass        1.571      20.00      50.0      70.00          0   \n",
       "MasVnrArea       10.044       0.00       0.0     166.00          8   \n",
       "MiscVal         698.601       0.00       0.0       0.00          0   \n",
       "MoSold           -0.407       5.00       6.0       8.00          0   \n",
       "OpenPorchSF       8.457       0.00      25.0      68.00          0   \n",
       "OverallCond       1.099       5.00       5.0       6.00          0   \n",
       "OverallQual       0.092       5.00       6.0       7.00          0   \n",
       "PoolArea        222.501       0.00       0.0       0.00          0   \n",
       "SalePrice         6.510  129975.00  163000.0  214000.00          0   \n",
       "ScreenPorch      18.372       0.00       0.0       0.00          0   \n",
       "TotRmsAbvGrd      0.874       5.00       6.0       7.00          0   \n",
       "TotalBsmtSF      13.201     795.75     991.5    1298.25          0   \n",
       "WoodDeckSF        2.979       0.00       0.0     168.00          0   \n",
       "YearBuilt        -0.442    1954.00    1973.0    2000.00          0   \n",
       "YearRemodAdd     -1.272    1967.00    1994.0    2004.00          0   \n",
       "YrSold           -1.191    2007.00    2008.0    2009.00          0   \n",
       "\n",
       "Statistic      missing_rate     n  \n",
       "Variable                           \n",
       "1stFlrSF              0.000  1460  \n",
       "2ndFlrSF              0.000  1460  \n",
       "3SsnPorch             0.000  1460  \n",
       "BedroomAbvGr          0.000  1460  \n",
       "BsmtFinSF1            0.000  1460  \n",
       "BsmtFinSF2            0.000  1460  \n",
       "BsmtFullBath          0.000  1460  \n",
       "BsmtHalfBath          0.000  1460  \n",
       "BsmtUnfSF             0.000  1460  \n",
       "EnclosedPorch         0.000  1460  \n",
       "Fireplaces            0.000  1460  \n",
       "FullBath              0.000  1460  \n",
       "GarageArea            0.000  1460  \n",
       "GarageCars            0.000  1460  \n",
       "GarageYrBlt           0.055  1460  \n",
       "GrLivArea             0.000  1460  \n",
       "HalfBath              0.000  1460  \n",
       "KitchenAbvGr          0.000  1460  \n",
       "LotArea               0.000  1460  \n",
       "LotFrontage           0.177  1460  \n",
       "LowQualFinSF          0.000  1460  \n",
       "MSSubClass            0.000  1460  \n",
       "MasVnrArea            0.005  1460  \n",
       "MiscVal               0.000  1460  \n",
       "MoSold                0.000  1460  \n",
       "OpenPorchSF           0.000  1460  \n",
       "OverallCond           0.000  1460  \n",
       "OverallQual           0.000  1460  \n",
       "PoolArea              0.000  1460  \n",
       "SalePrice             0.000  1460  \n",
       "ScreenPorch           0.000  1460  \n",
       "TotRmsAbvGrd          0.000  1460  \n",
       "TotalBsmtSF           0.000  1460  \n",
       "WoodDeckSF            0.000  1460  \n",
       "YearBuilt             0.000  1460  \n",
       "YearRemodAdd          0.000  1460  \n",
       "YrSold                0.000  1460  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().numeric_stats()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_oSEujaKlS2M"
   },
   "source": [
    "We can also list out all the statistics for categorical variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "id": "WpAGrDfmactN",
    "outputId": "2efbdbb1-bcf1-4963-b058-96946dbf1db9"
   },
   "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>Statistic</th>\n",
       "      <th>n_unique</th>\n",
       "      <th>most_common</th>\n",
       "      <th>least_common</th>\n",
       "      <th>n_missing</th>\n",
       "      <th>missing_rate</th>\n",
       "      <th>n</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Variable</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Alley</th>\n",
       "      <td>2</td>\n",
       "      <td>Grvl</td>\n",
       "      <td>Pave</td>\n",
       "      <td>1369</td>\n",
       "      <td>0.937671</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BldgType</th>\n",
       "      <td>5</td>\n",
       "      <td>1Fam</td>\n",
       "      <td>2fmCon</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtCond</th>\n",
       "      <td>4</td>\n",
       "      <td>TA</td>\n",
       "      <td>Po</td>\n",
       "      <td>37</td>\n",
       "      <td>0.025342</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtExposure</th>\n",
       "      <td>4</td>\n",
       "      <td>No</td>\n",
       "      <td>Mn</td>\n",
       "      <td>38</td>\n",
       "      <td>0.026027</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtFinType1</th>\n",
       "      <td>6</td>\n",
       "      <td>Unf</td>\n",
       "      <td>LwQ</td>\n",
       "      <td>37</td>\n",
       "      <td>0.025342</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtFinType2</th>\n",
       "      <td>6</td>\n",
       "      <td>Unf</td>\n",
       "      <td>GLQ</td>\n",
       "      <td>38</td>\n",
       "      <td>0.026027</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BsmtQual</th>\n",
       "      <td>4</td>\n",
       "      <td>TA</td>\n",
       "      <td>Fa</td>\n",
       "      <td>37</td>\n",
       "      <td>0.025342</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CentralAir</th>\n",
       "      <td>2</td>\n",
       "      <td>Y</td>\n",
       "      <td>N</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Condition1</th>\n",
       "      <td>9</td>\n",
       "      <td>Norm</td>\n",
       "      <td>RRNe</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Condition2</th>\n",
       "      <td>8</td>\n",
       "      <td>Norm</td>\n",
       "      <td>PosA</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Electrical</th>\n",
       "      <td>5</td>\n",
       "      <td>SBrkr</td>\n",
       "      <td>Mix</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000685</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ExterCond</th>\n",
       "      <td>5</td>\n",
       "      <td>TA</td>\n",
       "      <td>Po</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ExterQual</th>\n",
       "      <td>4</td>\n",
       "      <td>TA</td>\n",
       "      <td>Fa</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exterior1st</th>\n",
       "      <td>15</td>\n",
       "      <td>VinylSd</td>\n",
       "      <td>ImStucc</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Exterior2nd</th>\n",
       "      <td>16</td>\n",
       "      <td>VinylSd</td>\n",
       "      <td>Other</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Fence</th>\n",
       "      <td>4</td>\n",
       "      <td>MnPrv</td>\n",
       "      <td>MnWw</td>\n",
       "      <td>1179</td>\n",
       "      <td>0.807534</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FireplaceQu</th>\n",
       "      <td>5</td>\n",
       "      <td>Gd</td>\n",
       "      <td>Po</td>\n",
       "      <td>690</td>\n",
       "      <td>0.472603</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Foundation</th>\n",
       "      <td>6</td>\n",
       "      <td>PConc</td>\n",
       "      <td>Wood</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Functional</th>\n",
       "      <td>7</td>\n",
       "      <td>Typ</td>\n",
       "      <td>Sev</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageCond</th>\n",
       "      <td>5</td>\n",
       "      <td>TA</td>\n",
       "      <td>Ex</td>\n",
       "      <td>81</td>\n",
       "      <td>0.055479</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageFinish</th>\n",
       "      <td>3</td>\n",
       "      <td>Unf</td>\n",
       "      <td>Fin</td>\n",
       "      <td>81</td>\n",
       "      <td>0.055479</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageQual</th>\n",
       "      <td>5</td>\n",
       "      <td>TA</td>\n",
       "      <td>Po</td>\n",
       "      <td>81</td>\n",
       "      <td>0.055479</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GarageType</th>\n",
       "      <td>6</td>\n",
       "      <td>Attchd</td>\n",
       "      <td>2Types</td>\n",
       "      <td>81</td>\n",
       "      <td>0.055479</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Heating</th>\n",
       "      <td>6</td>\n",
       "      <td>GasA</td>\n",
       "      <td>Floor</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HeatingQC</th>\n",
       "      <td>5</td>\n",
       "      <td>Ex</td>\n",
       "      <td>Po</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HouseStyle</th>\n",
       "      <td>8</td>\n",
       "      <td>1Story</td>\n",
       "      <td>2.5Fin</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>KitchenQual</th>\n",
       "      <td>4</td>\n",
       "      <td>TA</td>\n",
       "      <td>Fa</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LandContour</th>\n",
       "      <td>4</td>\n",
       "      <td>Lvl</td>\n",
       "      <td>Low</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LandSlope</th>\n",
       "      <td>3</td>\n",
       "      <td>Gtl</td>\n",
       "      <td>Sev</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LotConfig</th>\n",
       "      <td>5</td>\n",
       "      <td>Inside</td>\n",
       "      <td>FR3</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LotShape</th>\n",
       "      <td>4</td>\n",
       "      <td>Reg</td>\n",
       "      <td>IR3</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MSZoning</th>\n",
       "      <td>5</td>\n",
       "      <td>RL</td>\n",
       "      <td>C (all)</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MasVnrType</th>\n",
       "      <td>3</td>\n",
       "      <td>BrkFace</td>\n",
       "      <td>BrkCmn</td>\n",
       "      <td>872</td>\n",
       "      <td>0.59726</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MiscFeature</th>\n",
       "      <td>4</td>\n",
       "      <td>Shed</td>\n",
       "      <td>TenC</td>\n",
       "      <td>1406</td>\n",
       "      <td>0.963014</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Neighborhood</th>\n",
       "      <td>25</td>\n",
       "      <td>NAmes</td>\n",
       "      <td>Blueste</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PavedDrive</th>\n",
       "      <td>3</td>\n",
       "      <td>Y</td>\n",
       "      <td>P</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PoolQC</th>\n",
       "      <td>3</td>\n",
       "      <td>Gd</td>\n",
       "      <td>Fa</td>\n",
       "      <td>1453</td>\n",
       "      <td>0.995205</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RoofMatl</th>\n",
       "      <td>8</td>\n",
       "      <td>CompShg</td>\n",
       "      <td>Metal</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RoofStyle</th>\n",
       "      <td>6</td>\n",
       "      <td>Gable</td>\n",
       "      <td>Shed</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SaleCondition</th>\n",
       "      <td>6</td>\n",
       "      <td>Normal</td>\n",
       "      <td>AdjLand</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SaleType</th>\n",
       "      <td>9</td>\n",
       "      <td>WD</td>\n",
       "      <td>Con</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Street</th>\n",
       "      <td>2</td>\n",
       "      <td>Pave</td>\n",
       "      <td>Grvl</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Utilities</th>\n",
       "      <td>2</td>\n",
       "      <td>AllPub</td>\n",
       "      <td>NoSeWa</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1460</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Statistic     n_unique most_common least_common  n_missing missing_rate     n\n",
       "Variable                                                                     \n",
       "Alley                2        Grvl         Pave       1369     0.937671  1460\n",
       "BldgType             5        1Fam       2fmCon          0          0.0  1460\n",
       "BsmtCond             4          TA           Po         37     0.025342  1460\n",
       "BsmtExposure         4          No           Mn         38     0.026027  1460\n",
       "BsmtFinType1         6         Unf          LwQ         37     0.025342  1460\n",
       "BsmtFinType2         6         Unf          GLQ         38     0.026027  1460\n",
       "BsmtQual             4          TA           Fa         37     0.025342  1460\n",
       "CentralAir           2           Y            N          0          0.0  1460\n",
       "Condition1           9        Norm         RRNe          0          0.0  1460\n",
       "Condition2           8        Norm         PosA          0          0.0  1460\n",
       "Electrical           5       SBrkr          Mix          1     0.000685  1460\n",
       "ExterCond            5          TA           Po          0          0.0  1460\n",
       "ExterQual            4          TA           Fa          0          0.0  1460\n",
       "Exterior1st         15     VinylSd      ImStucc          0          0.0  1460\n",
       "Exterior2nd         16     VinylSd        Other          0          0.0  1460\n",
       "Fence                4       MnPrv         MnWw       1179     0.807534  1460\n",
       "FireplaceQu          5          Gd           Po        690     0.472603  1460\n",
       "Foundation           6       PConc         Wood          0          0.0  1460\n",
       "Functional           7         Typ          Sev          0          0.0  1460\n",
       "GarageCond           5          TA           Ex         81     0.055479  1460\n",
       "GarageFinish         3         Unf          Fin         81     0.055479  1460\n",
       "GarageQual           5          TA           Po         81     0.055479  1460\n",
       "GarageType           6      Attchd       2Types         81     0.055479  1460\n",
       "Heating              6        GasA        Floor          0          0.0  1460\n",
       "HeatingQC            5          Ex           Po          0          0.0  1460\n",
       "HouseStyle           8      1Story       2.5Fin          0          0.0  1460\n",
       "KitchenQual          4          TA           Fa          0          0.0  1460\n",
       "LandContour          4         Lvl          Low          0          0.0  1460\n",
       "LandSlope            3         Gtl          Sev          0          0.0  1460\n",
       "LotConfig            5      Inside          FR3          0          0.0  1460\n",
       "LotShape             4         Reg          IR3          0          0.0  1460\n",
       "MSZoning             5          RL      C (all)          0          0.0  1460\n",
       "MasVnrType           3     BrkFace       BrkCmn        872      0.59726  1460\n",
       "MiscFeature          4        Shed         TenC       1406     0.963014  1460\n",
       "Neighborhood        25       NAmes      Blueste          0          0.0  1460\n",
       "PavedDrive           3           Y            P          0          0.0  1460\n",
       "PoolQC               3          Gd           Fa       1453     0.995205  1460\n",
       "RoofMatl             8     CompShg        Metal          0          0.0  1460\n",
       "RoofStyle            6       Gable         Shed          0          0.0  1460\n",
       "SaleCondition        6      Normal      AdjLand          0          0.0  1460\n",
       "SaleType             9          WD          Con          0          0.0  1460\n",
       "Street               2        Pave         Grvl          0          0.0  1460\n",
       "Utilities            2      AllPub       NoSeWa          0          0.0  1460"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().categorical_stats()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ihEmQQN1lS2N"
   },
   "source": [
    "We can compute the correlation matrix for a set of numeric variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 175
    },
    "id": "l4M6LpZUafVT",
    "outputId": "016eaa52-971a-44be-ca48-9241ef7534d5"
   },
   "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>SalePrice</th>\n",
       "      <th>1stFlrSF</th>\n",
       "      <th>2ndFlrSF</th>\n",
       "      <th>YrSold</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>SalePrice</th>\n",
       "      <td>1.000 (1.000)</td>\n",
       "      <td>0.606 (0.000)</td>\n",
       "      <td>0.319 (0.000)</td>\n",
       "      <td>-0.029 (0.269)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1stFlrSF</th>\n",
       "      <td>0.606 (0.000)</td>\n",
       "      <td>1.000 (1.000)</td>\n",
       "      <td>-0.203 (0.000)</td>\n",
       "      <td>-0.014 (0.603)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2ndFlrSF</th>\n",
       "      <td>0.319 (0.000)</td>\n",
       "      <td>-0.203 (0.000)</td>\n",
       "      <td>1.000 (1.000)</td>\n",
       "      <td>-0.029 (0.273)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YrSold</th>\n",
       "      <td>-0.029 (0.269)</td>\n",
       "      <td>-0.014 (0.603)</td>\n",
       "      <td>-0.029 (0.273)</td>\n",
       "      <td>1.000 (1.000)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                SalePrice        1stFlrSF        2ndFlrSF          YrSold\n",
       "SalePrice   1.000 (1.000)   0.606 (0.000)   0.319 (0.000)  -0.029 (0.269)\n",
       "1stFlrSF    0.606 (0.000)   1.000 (1.000)  -0.203 (0.000)  -0.014 (0.603)\n",
       "2ndFlrSF    0.319 (0.000)  -0.203 (0.000)   1.000 (1.000)  -0.029 (0.273)\n",
       "YrSold     -0.029 (0.269)  -0.014 (0.603)  -0.029 (0.273)   1.000 (1.000)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().tabulate_correlation_matrix(\n",
    "    [\"SalePrice\", \"1stFlrSF\", \"2ndFlrSF\", \"YrSold\"], htest=True\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "m0ldajawlS2N"
   },
   "source": [
    "Here's the same thing as a figure."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 603
    },
    "id": "QMtH4r8Zaomi",
    "outputId": "9ad11f0b-498c-4562-fe42-f5848f12bd8d"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 750x900 with 2 Axes>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().plot_correlation_heatmap(\n",
    "    [\"SalePrice\", \"1stFlrSF\", \"2ndFlrSF\", \"YrSold\"], htest=True, figsize=(5, 6)\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qz-6Gv-alS2N"
   },
   "source": [
    "Correlations can be compared between a set of numeric variables and a specific numeric variable of interest. Here, we are interested in how square footage and year sold correlate with sale price."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 143
    },
    "id": "mVIWmF7kawjm",
    "outputId": "d1c1360e-373b-4994-f76d-0d841502e59b"
   },
   "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>Corr. w SalePrice</th>\n",
       "      <th>p-value (Bonferroni corrected)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1stFlrSF</th>\n",
       "      <td>0.606</td>\n",
       "      <td>1.618e-146</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2ndFlrSF</th>\n",
       "      <td>0.319</td>\n",
       "      <td>1.729e-35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YrSold</th>\n",
       "      <td>-0.029</td>\n",
       "      <td>8.082e-01</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         Corr. w SalePrice p-value (Bonferroni corrected)\n",
       "1stFlrSF             0.606                     1.618e-146\n",
       "2ndFlrSF             0.319                      1.729e-35\n",
       "YrSold              -0.029                      8.082e-01"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().tabulate_correlation_comparison(\n",
    "    numeric_vars=[\"1stFlrSF\", \"2ndFlrSF\", \"YrSold\"],\n",
    "    target=\"SalePrice\",\n",
    "    bonferroni_correction=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "uKWcv6rhlS2T"
   },
   "source": [
    "We leverage the Python `tableone` package to make descriptive exploratory tables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 537
    },
    "id": "7e2o6vIkbN6y",
    "outputId": "8d74f765-f31e-4b76-cd9a-36a0a0d91825"
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th colspan=\"7\" halign=\"left\">Grouped by GarageFinish</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>Missing</th>\n",
       "      <th>Overall</th>\n",
       "      <th>Fin</th>\n",
       "      <th>RFn</th>\n",
       "      <th>Unf</th>\n",
       "      <th>P-Value</th>\n",
       "      <th>Test</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>n</th>\n",
       "      <th></th>\n",
       "      <td></td>\n",
       "      <td>1460</td>\n",
       "      <td>352</td>\n",
       "      <td>422</td>\n",
       "      <td>605</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SalePrice, mean (SD)</th>\n",
       "      <th></th>\n",
       "      <td>0</td>\n",
       "      <td>180921.2 (79442.5)</td>\n",
       "      <td>240052.7 (96960.6)</td>\n",
       "      <td>202068.9 (63536.2)</td>\n",
       "      <td>142156.4 (46498.5)</td>\n",
       "      <td>&lt;0.001</td>\n",
       "      <td>One-way ANOVA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1stFlrSF, mean (SD)</th>\n",
       "      <th></th>\n",
       "      <td>0</td>\n",
       "      <td>1162.6 (386.6)</td>\n",
       "      <td>1326.5 (479.3)</td>\n",
       "      <td>1240.6 (351.5)</td>\n",
       "      <td>1046.0 (298.4)</td>\n",
       "      <td>&lt;0.001</td>\n",
       "      <td>One-way ANOVA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2ndFlrSF, mean (SD)</th>\n",
       "      <th></th>\n",
       "      <td>0</td>\n",
       "      <td>347.0 (436.5)</td>\n",
       "      <td>452.3 (503.3)</td>\n",
       "      <td>341.1 (448.2)</td>\n",
       "      <td>304.5 (381.3)</td>\n",
       "      <td>&lt;0.001</td>\n",
       "      <td>One-way ANOVA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">YrSold, n (%)</th>\n",
       "      <th>2006</th>\n",
       "      <td></td>\n",
       "      <td>314 (21.5)</td>\n",
       "      <td>74 (21.0)</td>\n",
       "      <td>92 (21.8)</td>\n",
       "      <td>133 (22.0)</td>\n",
       "      <td>0.997</td>\n",
       "      <td>Chi-squared</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2007</th>\n",
       "      <td></td>\n",
       "      <td>329 (22.5)</td>\n",
       "      <td>79 (22.4)</td>\n",
       "      <td>93 (22.0)</td>\n",
       "      <td>140 (23.1)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2008</th>\n",
       "      <td></td>\n",
       "      <td>304 (20.8)</td>\n",
       "      <td>74 (21.0)</td>\n",
       "      <td>89 (21.1)</td>\n",
       "      <td>118 (19.5)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2009</th>\n",
       "      <td></td>\n",
       "      <td>338 (23.2)</td>\n",
       "      <td>85 (24.1)</td>\n",
       "      <td>95 (22.5)</td>\n",
       "      <td>143 (23.6)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010</th>\n",
       "      <td></td>\n",
       "      <td>175 (12.0)</td>\n",
       "      <td>40 (11.4)</td>\n",
       "      <td>53 (12.6)</td>\n",
       "      <td>71 (11.7)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">BldgType, n (%)</th>\n",
       "      <th>1Fam</th>\n",
       "      <td></td>\n",
       "      <td>1220 (83.6)</td>\n",
       "      <td>296 (84.1)</td>\n",
       "      <td>365 (86.5)</td>\n",
       "      <td>505 (83.5)</td>\n",
       "      <td>&lt;0.001</td>\n",
       "      <td>Chi-squared</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2fmCon</th>\n",
       "      <td></td>\n",
       "      <td>31 (2.1)</td>\n",
       "      <td>3 (0.9)</td>\n",
       "      <td>2 (0.5)</td>\n",
       "      <td>17 (2.8)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Duplex</th>\n",
       "      <td></td>\n",
       "      <td>52 (3.6)</td>\n",
       "      <td>2 (0.6)</td>\n",
       "      <td>1 (0.2)</td>\n",
       "      <td>37 (6.1)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Twnhs</th>\n",
       "      <td></td>\n",
       "      <td>43 (2.9)</td>\n",
       "      <td>2 (0.6)</td>\n",
       "      <td>8 (1.9)</td>\n",
       "      <td>28 (4.6)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TwnhsE</th>\n",
       "      <td></td>\n",
       "      <td>114 (7.8)</td>\n",
       "      <td>49 (13.9)</td>\n",
       "      <td>46 (10.9)</td>\n",
       "      <td>18 (3.0)</td>\n",
       "      <td></td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><br />"
      ],
      "text/plain": [
       "                            Grouped by GarageFinish                                                                                                       \n",
       "                                            Missing             Overall                 Fin                 RFn                 Unf P-Value           Test\n",
       "n                                                                  1460                 352                 422                 605                       \n",
       "SalePrice, mean (SD)                              0  180921.2 (79442.5)  240052.7 (96960.6)  202068.9 (63536.2)  142156.4 (46498.5)  <0.001  One-way ANOVA\n",
       "1stFlrSF, mean (SD)                               0      1162.6 (386.6)      1326.5 (479.3)      1240.6 (351.5)      1046.0 (298.4)  <0.001  One-way ANOVA\n",
       "2ndFlrSF, mean (SD)                               0       347.0 (436.5)       452.3 (503.3)       341.1 (448.2)       304.5 (381.3)  <0.001  One-way ANOVA\n",
       "YrSold, n (%)        2006                                    314 (21.5)           74 (21.0)           92 (21.8)          133 (22.0)   0.997    Chi-squared\n",
       "                     2007                                    329 (22.5)           79 (22.4)           93 (22.0)          140 (23.1)                       \n",
       "                     2008                                    304 (20.8)           74 (21.0)           89 (21.1)          118 (19.5)                       \n",
       "                     2009                                    338 (23.2)           85 (24.1)           95 (22.5)          143 (23.6)                       \n",
       "                     2010                                    175 (12.0)           40 (11.4)           53 (12.6)           71 (11.7)                       \n",
       "BldgType, n (%)      1Fam                                   1220 (83.6)          296 (84.1)          365 (86.5)          505 (83.5)  <0.001    Chi-squared\n",
       "                     2fmCon                                    31 (2.1)             3 (0.9)             2 (0.5)            17 (2.8)                       \n",
       "                     Duplex                                    52 (3.6)             2 (0.6)             1 (0.2)            37 (6.1)                       \n",
       "                     Twnhs                                     43 (2.9)             2 (0.6)             8 (1.9)            28 (4.6)                       \n",
       "                     TwnhsE                                   114 (7.8)           49 (13.9)           46 (10.9)            18 (3.0)                       "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.eda().tabulate_tableone(\n",
    "    vars=[\"SalePrice\", \"1stFlrSF\", \"2ndFlrSF\", \"YrSold\", \"BldgType\"],\n",
    "    stratify_by=\"GarageFinish\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UPF56yb7lS2T"
   },
   "source": [
    "# Section 3: Regression Analysis\n",
    "\n",
    "TableMage accelerates regression analyses. Let's start with a basic example on the house prices dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "qZdhXxCPlS2T"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mHouse Prices\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(1168, 80)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(292, 80)\u001b[0m                      \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[95m'Alley', \u001b[0m\u001b[95m'BldgType', \u001b[0m\u001b[95m'BsmtCond', \u001b[0m\u001b[95m'BsmtExposure', \u001b[0m\u001b[95m'BsmtFinType1', \u001b[0m\u001b[95m'BsmtFinType2', \n",
       "  \u001b[0m\u001b[95m'BsmtQual', \u001b[0m\u001b[95m'CentralAir', \u001b[0m\u001b[95m'Condition1', \u001b[0m\u001b[95m'Condition2', \u001b[0m\u001b[95m'Electrical', \u001b[0m\u001b[95m'ExterCond', \n",
       "  \u001b[0m\u001b[95m'ExterQual', \u001b[0m\u001b[95m'Exterior1st', \u001b[0m\u001b[95m'Exterior2nd', \u001b[0m\u001b[95m'Fence', \u001b[0m\u001b[95m'FireplaceQu', \u001b[0m\u001b[95m'Foundation', \n",
       "  \u001b[0m\u001b[95m'Functional', \u001b[0m\u001b[95m'GarageCond', \u001b[0m\u001b[95m'GarageFinish', \u001b[0m\u001b[95m'GarageQual', \u001b[0m\u001b[95m'GarageType', \u001b[0m\u001b[95m'Heating', \n",
       "  \u001b[0m\u001b[95m'HeatingQC', \u001b[0m\u001b[95m'HouseStyle', \u001b[0m\u001b[95m'KitchenQual', \u001b[0m\u001b[95m'LandContour', \u001b[0m\u001b[95m'LandSlope', \u001b[0m\u001b[95m'LotConfig', \n",
       "  \u001b[0m\u001b[95m'LotShape', \u001b[0m\u001b[95m'MSZoning', \u001b[0m\u001b[95m'MasVnrType', \u001b[0m\u001b[95m'MiscFeature', \u001b[0m\u001b[95m'Neighborhood', \u001b[0m\u001b[95m'PavedDrive', \n",
       "  \u001b[0m\u001b[95m'PoolQC', \u001b[0m\u001b[95m'RoofMatl', \u001b[0m\u001b[95m'RoofStyle', \u001b[0m\u001b[95m'SaleCondition', \u001b[0m\u001b[95m'SaleType', \u001b[0m\u001b[95m'Street', \u001b[0m\u001b[95m'Utilities'\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'1stFlrSF', \u001b[0m\u001b[95m'2ndFlrSF', \u001b[0m\u001b[95m'3SsnPorch', \u001b[0m\u001b[95m'BedroomAbvGr', \u001b[0m\u001b[95m'BsmtFinSF1', \u001b[0m\u001b[95m'BsmtFinSF2', \n",
       "  \u001b[0m\u001b[95m'BsmtFullBath', \u001b[0m\u001b[95m'BsmtHalfBath', \u001b[0m\u001b[95m'BsmtUnfSF', \u001b[0m\u001b[95m'EnclosedPorch', \u001b[0m\u001b[95m'Fireplaces', \n",
       "  \u001b[0m\u001b[95m'FullBath', \u001b[0m\u001b[95m'GarageArea', \u001b[0m\u001b[95m'GarageCars', \u001b[0m\u001b[95m'GarageYrBlt', \u001b[0m\u001b[95m'GrLivArea', \u001b[0m\u001b[95m'HalfBath', \n",
       "  \u001b[0m\u001b[95m'KitchenAbvGr', \u001b[0m\u001b[95m'LotArea', \u001b[0m\u001b[95m'LotFrontage', \u001b[0m\u001b[95m'LowQualFinSF', \u001b[0m\u001b[95m'MSSubClass', \u001b[0m\u001b[95m'MasVnrArea', \n",
       "  \u001b[0m\u001b[95m'MiscVal', \u001b[0m\u001b[95m'MoSold', \u001b[0m\u001b[95m'OpenPorchSF', \u001b[0m\u001b[95m'OverallCond', \u001b[0m\u001b[95m'OverallQual', \u001b[0m\u001b[95m'PoolArea', \n",
       "  \u001b[0m\u001b[95m'SalePrice', \u001b[0m\u001b[95m'ScreenPorch', \u001b[0m\u001b[95m'TotRmsAbvGrd', \u001b[0m\u001b[95m'TotalBsmtSF', \u001b[0m\u001b[95m'WoodDeckSF', \u001b[0m\u001b[95m'YearBuilt', \n",
       "  \u001b[0m\u001b[95m'YearRemodAdd', \u001b[0m\u001b[95m'YrSold'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_path = curr_dir / \"demo\" / \"regression\" / \"house_price_data\" / \"data.csv\"\n",
    "df = pd.read_csv(data_path, index_col=0)\n",
    "analyzer = tm.Analyzer(\n",
    "    df, test_size=0.2, split_seed=42, verbose=True, name=\"House Prices\"\n",
    ")\n",
    "analyzer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_tQ_dc3TlS2T"
   },
   "source": [
    "Let's first preprocess the data some."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "id": "v-jZIu1qlS2T",
    "outputId": "5f6159fd-ae23-4f7c-e3d1-a3d5fd0965bf"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mHouse Prices\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(1168, 80)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(292, 80)\u001b[0m                      \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[95m'Alley', \u001b[0m\u001b[95m'BldgType', \u001b[0m\u001b[95m'BsmtCond', \u001b[0m\u001b[95m'BsmtExposure', \u001b[0m\u001b[95m'BsmtFinType1', \u001b[0m\u001b[95m'BsmtFinType2', \n",
       "  \u001b[0m\u001b[95m'BsmtQual', \u001b[0m\u001b[95m'CentralAir', \u001b[0m\u001b[95m'Condition1', \u001b[0m\u001b[95m'Condition2', \u001b[0m\u001b[95m'Electrical', \u001b[0m\u001b[95m'ExterCond', \n",
       "  \u001b[0m\u001b[95m'ExterQual', \u001b[0m\u001b[95m'Exterior1st', \u001b[0m\u001b[95m'Exterior2nd', \u001b[0m\u001b[95m'Fence', \u001b[0m\u001b[95m'FireplaceQu', \u001b[0m\u001b[95m'Foundation', \n",
       "  \u001b[0m\u001b[95m'Functional', \u001b[0m\u001b[95m'GarageCond', \u001b[0m\u001b[95m'GarageFinish', \u001b[0m\u001b[95m'GarageQual', \u001b[0m\u001b[95m'GarageType', \u001b[0m\u001b[95m'Heating', \n",
       "  \u001b[0m\u001b[95m'HeatingQC', \u001b[0m\u001b[95m'HouseStyle', \u001b[0m\u001b[95m'KitchenQual', \u001b[0m\u001b[95m'LandContour', \u001b[0m\u001b[95m'LandSlope', \u001b[0m\u001b[95m'LotConfig', \n",
       "  \u001b[0m\u001b[95m'LotShape', \u001b[0m\u001b[95m'MSZoning', \u001b[0m\u001b[95m'MasVnrType', \u001b[0m\u001b[95m'MiscFeature', \u001b[0m\u001b[95m'Neighborhood', \u001b[0m\u001b[95m'PavedDrive', \n",
       "  \u001b[0m\u001b[95m'PoolQC', \u001b[0m\u001b[95m'RoofMatl', \u001b[0m\u001b[95m'RoofStyle', \u001b[0m\u001b[95m'SaleCondition', \u001b[0m\u001b[95m'SaleType', \u001b[0m\u001b[95m'Street', \u001b[0m\u001b[95m'Utilities'\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'1stFlrSF', \u001b[0m\u001b[95m'2ndFlrSF', \u001b[0m\u001b[95m'3SsnPorch', \u001b[0m\u001b[95m'BedroomAbvGr', \u001b[0m\u001b[95m'BsmtFinSF1', \u001b[0m\u001b[95m'BsmtFinSF2', \n",
       "  \u001b[0m\u001b[95m'BsmtFullBath', \u001b[0m\u001b[95m'BsmtHalfBath', \u001b[0m\u001b[95m'BsmtUnfSF', \u001b[0m\u001b[95m'EnclosedPorch', \u001b[0m\u001b[95m'Fireplaces', \n",
       "  \u001b[0m\u001b[95m'FullBath', \u001b[0m\u001b[95m'GarageArea', \u001b[0m\u001b[95m'GarageCars', \u001b[0m\u001b[95m'GarageYrBlt', \u001b[0m\u001b[95m'GrLivArea', \u001b[0m\u001b[95m'HalfBath', \n",
       "  \u001b[0m\u001b[95m'KitchenAbvGr', \u001b[0m\u001b[95m'LotArea', \u001b[0m\u001b[95m'LotFrontage', \u001b[0m\u001b[95m'LowQualFinSF', \u001b[0m\u001b[95m'MSSubClass', \u001b[0m\u001b[95m'MasVnrArea', \n",
       "  \u001b[0m\u001b[95m'MiscVal', \u001b[0m\u001b[95m'MoSold', \u001b[0m\u001b[95m'OpenPorchSF', \u001b[0m\u001b[95m'OverallCond', \u001b[0m\u001b[95m'OverallQual', \u001b[0m\u001b[95m'PoolArea', \n",
       "  \u001b[0m\u001b[95m'SalePrice', \u001b[0m\u001b[95m'ScreenPorch', \u001b[0m\u001b[95m'TotRmsAbvGrd', \u001b[0m\u001b[95m'TotalBsmtSF', \u001b[0m\u001b[95m'WoodDeckSF', \u001b[0m\u001b[95m'YearBuilt', \n",
       "  \u001b[0m\u001b[95m'YearRemodAdd', \u001b[0m\u001b[95m'YrSold'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.dropna(include_vars=[\"SalePrice\"]).impute(\n",
    "    include_vars=[\"1stFlrSF\", \"2ndFlrSF\", \"YrSold\"]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "dO_5KCs1lS2T"
   },
   "source": [
    "It's really easy to fit an OLS model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "jqWZF1L3lS2T",
    "outputId": "10d4226c-e9a8-4ff8-ed09-44c516463647"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mOrdinary Least Squares Regression Report\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTarget variable:\u001b[0m\n",
       "  \u001b[95m'SalePrice'\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mPredictor variables (3):\u001b[0m\n",
       "  \u001b[95m'1stFlrSF', \u001b[0m\u001b[95m'2ndFlrSF', \u001b[0m\u001b[95m'YrSold'\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mMetrics:\u001b[0m\n",
       "  \u001b[1mTrain (1168)\u001b[0m                               \u001b[1mTest (292)\u001b[0m \n",
       "    R2:       \u001b[93m0.548\u001b[0m                            R2:       \u001b[93m0.636\u001b[0m \n",
       "    Adj. R2:  \u001b[93m0.547\u001b[0m                            Adj. R2:  \u001b[93m0.633\u001b[0m \n",
       "    RMSE:     \u001b[93m51925.911\u001b[0m                        RMSE:     \u001b[93m52810.739\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCoefficients:\u001b[0m\n",
       "\u001b[1m                            Estimate         Std. Error            p-value \u001b[0m\n",
       "\u001b[1m  Predictor                                                                \u001b[0m\n",
       "  const                  -876198.651        2181846.129              0.688 \n",
       "  1stFlrSF                   137.096             15.182              0.000 \n",
       "  2ndFlrSF                    80.969              6.990              0.000 \n",
       "  YrSold                     432.707           1086.173              0.690 \n",
       "========================================================================================"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report = analyzer.ols(target=\"SalePrice\", predictors=[\"1stFlrSF\", \"2ndFlrSF\", \"YrSold\"])\n",
    "report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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></th>\n",
       "      <th>OLS Linear Model</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dataset</th>\n",
       "      <th>Statistic</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">train</th>\n",
       "      <th>rmse</th>\n",
       "      <td>51925.911</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mae</th>\n",
       "      <td>34482.403</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mape</th>\n",
       "      <td>0.205</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pearsonr</th>\n",
       "      <td>0.740</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>spearmanr</th>\n",
       "      <td>0.771</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>r2</th>\n",
       "      <td>0.548</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>adjr2</th>\n",
       "      <td>0.547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>n_obs</th>\n",
       "      <td>1168.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">test</th>\n",
       "      <th>rmse</th>\n",
       "      <td>52810.739</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mae</th>\n",
       "      <td>35310.444</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mape</th>\n",
       "      <td>0.212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pearsonr</th>\n",
       "      <td>0.813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>spearmanr</th>\n",
       "      <td>0.806</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>r2</th>\n",
       "      <td>0.636</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>adjr2</th>\n",
       "      <td>0.633</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>n_obs</th>\n",
       "      <td>292.000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   OLS Linear Model\n",
       "Dataset Statistic                  \n",
       "train   rmse              51925.911\n",
       "        mae               34482.403\n",
       "        mape                  0.205\n",
       "        pearsonr              0.740\n",
       "        spearmanr             0.771\n",
       "        r2                    0.548\n",
       "        adjr2                 0.547\n",
       "        n_obs              1168.000\n",
       "test    rmse              52810.739\n",
       "        mae               35310.444\n",
       "        mape                  0.212\n",
       "        pearsonr              0.813\n",
       "        spearmanr             0.806\n",
       "        r2                    0.636\n",
       "        adjr2                 0.633\n",
       "        n_obs               292.000"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report.metrics(dataset=\"both\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>Estimate (Std. Error)</th>\n",
       "      <th>p-value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>const</th>\n",
       "      <td>-876198.651 (2181846.129)</td>\n",
       "      <td>0.688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1stFlrSF</th>\n",
       "      <td>137.096 (15.182)</td>\n",
       "      <td>0.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2ndFlrSF</th>\n",
       "      <td>80.969 (6.99)</td>\n",
       "      <td>0.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YrSold</th>\n",
       "      <td>432.707 (1086.173)</td>\n",
       "      <td>0.690</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Estimate (Std. Error)  p-value\n",
       "const     -876198.651 (2181846.129)    0.688\n",
       "1stFlrSF           137.096 (15.182)    0.000\n",
       "2ndFlrSF              80.969 (6.99)    0.000\n",
       "YrSold           432.707 (1086.173)    0.690"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report.coefs(format=\"coef(se)|pval\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1050x1050 with 4 Axes>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report.plot_diagnostics(\"train\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6xmgQsGtlS2U"
   },
   "source": [
    "# Section 4: Causal Inference\n",
    "\n",
    "\n",
    "\n",
    "In this section, we use the TableMage package to estimate the causal effect of education on wage using a labor market dataset.\n",
    "\n",
    "First, we load the datsaset, as shown below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "id": "gAztqx2hlS2U",
    "outputId": "047ef3c3-b0be-42dc-c5b5-b7cfe4115162"
   },
   "outputs": [],
   "source": [
    "data_path = curr_dir / \"demo\" / \"causal\" / \"data\" / \"card.csv\"\n",
    "df_causal = pd.read_csv(data_path, index_col=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ad-wI6GIlS2U"
   },
   "source": [
    "Next, we initialize an Analyzer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "Q4T3bygQlS2U",
    "outputId": "76659ba5-8ef8-4cce-b75c-e14bbe6860fd"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mLabor Market Behavior\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(2408, 34)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(602, 34)\u001b[0m                      \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[93mNone\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'IQ', \u001b[0m\u001b[95m'KWW', \u001b[0m\u001b[95m'age', \u001b[0m\u001b[95m'black', \u001b[0m\u001b[95m'educ', \u001b[0m\u001b[95m'educ_binary', \u001b[0m\u001b[95m'enroll', \u001b[0m\u001b[95m'exper', \u001b[0m\u001b[95m'expersq', \n",
       "  \u001b[0m\u001b[95m'fatheduc', \u001b[0m\u001b[95m'libcrd14', \u001b[0m\u001b[95m'lwage', \u001b[0m\u001b[95m'married', \u001b[0m\u001b[95m'momdad14', \u001b[0m\u001b[95m'motheduc', \u001b[0m\u001b[95m'nearc2', \n",
       "  \u001b[0m\u001b[95m'nearc4', \u001b[0m\u001b[95m'reg661', \u001b[0m\u001b[95m'reg662', \u001b[0m\u001b[95m'reg663', \u001b[0m\u001b[95m'reg664', \u001b[0m\u001b[95m'reg665', \u001b[0m\u001b[95m'reg666', \u001b[0m\u001b[95m'reg667', \n",
       "  \u001b[0m\u001b[95m'reg668', \u001b[0m\u001b[95m'reg669', \u001b[0m\u001b[95m'sinmom14', \u001b[0m\u001b[95m'smsa', \u001b[0m\u001b[95m'smsa66', \u001b[0m\u001b[95m'south', \u001b[0m\u001b[95m'south66', \u001b[0m\u001b[95m'step14', \n",
       "  \u001b[0m\u001b[95m'wage', \u001b[0m\u001b[95m'weight'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer = tm.Analyzer(\n",
    "    df_causal, test_size=0.2, split_seed=42, verbose=True, name=\"Labor Market Behavior\"\n",
    ")\n",
    "analyzer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "fDtEtSHylS2U"
   },
   "source": [
    "We can now make a basic causal inference model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "id": "KcIl0HxrlS2U"
   },
   "outputs": [],
   "source": [
    "causal_model = analyzer.causal(\n",
    "    treatment=\"educ_binary\",\n",
    "    outcome=\"lwage\",\n",
    "    confounders=[\n",
    "        \"exper\",\n",
    "        \"expersq\",\n",
    "        \"black\",\n",
    "        \"smsa\",\n",
    "        \"south\",\n",
    "        \"smsa66\",\n",
    "        \"reg662\",\n",
    "        \"reg663\",\n",
    "        \"reg664\",\n",
    "        \"reg665\",\n",
    "        \"reg666\",\n",
    "        \"reg667\",\n",
    "        \"reg668\",\n",
    "        \"reg669\",\n",
    "    ],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bYUJ_S6slS2U"
   },
   "source": [
    "We can compute the difference in means naively."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "id": "rxqMG7gelS2U"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mCausal Effect Estimation Report\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mEstimate:\u001b[0m \u001b[93m0.194\u001b[0m                             \u001b[1mStd Err:\u001b[0m \u001b[93m0.016\u001b[0m\n",
       "\u001b[1mEstimand:\u001b[0m \u001b[94mAvg Trmt Effect (ATE)\u001b[0m             \u001b[1mp-value:\u001b[0m \u001b[92m0.000e+00\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTreatment variable:\n",
       "\u001b[0m\u001b[95m  'educ_binary'\u001b[0m\n",
       "                                                                                        \n",
       "\u001b[1mOutcome variable:\n",
       "\u001b[0m\u001b[95m  'lwage'\u001b[0m\n",
       "                                                                                        \n",
       "\u001b[1mConfounders:\n",
       "\u001b[0m  \u001b[95m'exper', \u001b[0m\u001b[95m'expersq', \u001b[0m\u001b[95m'black', \u001b[0m\u001b[95m'smsa', \u001b[0m\u001b[95m'south', \u001b[0m\u001b[95m'smsa66', \u001b[0m\u001b[95m'reg662', \u001b[0m\u001b[95m'reg663', \u001b[0m\u001b[95m'reg664', \n",
       "  \u001b[0m\u001b[95m'reg665', \u001b[0m\u001b[95m'reg666', \u001b[0m\u001b[95m'reg667', \u001b[0m\u001b[95m'reg668', \u001b[0m\u001b[95m'reg669'\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mMethod:\n",
       "\u001b[0m  \u001b[94mNaive Estimator (Difference in Means)\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report = causal_model.estimate_ate(method=\"naive\")\n",
    "report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jg131ggklS2U"
   },
   "source": [
    "With the introduction of these cofounders, we should estimate the ATE with a method that takes confounding into account. Let's use outcome regression."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "id": "LLH5JH5ylS2U",
    "outputId": "a91ef67e-c545-4f40-e6f0-424c88b2bdb9"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mCausal Effect Estimation Report\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mEstimate:\u001b[0m \u001b[93m0.238\u001b[0m                             \u001b[1mStd Err:\u001b[0m \u001b[93m0.017\u001b[0m\n",
       "\u001b[1mEstimand:\u001b[0m \u001b[94mAvg Trmt Effect (ATE)\u001b[0m             \u001b[1mp-value:\u001b[0m \u001b[92m5.107e-42\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTreatment variable:\n",
       "\u001b[0m\u001b[95m  'educ_binary'\u001b[0m\n",
       "                                                                                        \n",
       "\u001b[1mOutcome variable:\n",
       "\u001b[0m\u001b[95m  'lwage'\u001b[0m\n",
       "                                                                                        \n",
       "\u001b[1mConfounders:\n",
       "\u001b[0m  \u001b[95m'exper', \u001b[0m\u001b[95m'expersq', \u001b[0m\u001b[95m'black', \u001b[0m\u001b[95m'smsa', \u001b[0m\u001b[95m'south', \u001b[0m\u001b[95m'smsa66', \u001b[0m\u001b[95m'reg662', \u001b[0m\u001b[95m'reg663', \u001b[0m\u001b[95m'reg664', \n",
       "  \u001b[0m\u001b[95m'reg665', \u001b[0m\u001b[95m'reg666', \u001b[0m\u001b[95m'reg667', \u001b[0m\u001b[95m'reg668', \u001b[0m\u001b[95m'reg669'\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mMethod:\n",
       "\u001b[0m  \u001b[94mOutcome Regression\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report = causal_model.estimate_ate(method=\"outcome_regression\", robust_se=\"nonrobust\")\n",
    "report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "lzQKYflilS2U"
   },
   "source": [
    "Here's another example where we apply the IPW (inverse probability weighting) estimator to estimate the ATT (average treatment effect on the treated)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "id": "u3ndjd1ulS2V"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mCausal Effect Estimation Report\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mEstimate:\u001b[0m \u001b[93m0.232\u001b[0m                             \u001b[1mStd Err:\u001b[0m \u001b[93m0.020\u001b[0m\n",
       "\u001b[1mEstimand:\u001b[0m \u001b[94mAvg Trmt Effect on Trtd (ATT)\u001b[0m     \u001b[1mp-value:\u001b[0m \u001b[92m2.192e-31\u001b[0m\n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTreatment variable:\n",
       "\u001b[0m\u001b[95m  'educ_binary'\u001b[0m\n",
       "                                                                                        \n",
       "\u001b[1mOutcome variable:\n",
       "\u001b[0m\u001b[95m  'lwage'\u001b[0m\n",
       "                                                                                        \n",
       "\u001b[1mConfounders:\n",
       "\u001b[0m  \u001b[95m'exper', \u001b[0m\u001b[95m'expersq', \u001b[0m\u001b[95m'black', \u001b[0m\u001b[95m'smsa', \u001b[0m\u001b[95m'south', \u001b[0m\u001b[95m'smsa66', \u001b[0m\u001b[95m'reg662', \u001b[0m\u001b[95m'reg663', \u001b[0m\u001b[95m'reg664', \n",
       "  \u001b[0m\u001b[95m'reg665', \u001b[0m\u001b[95m'reg666', \u001b[0m\u001b[95m'reg667', \u001b[0m\u001b[95m'reg668', \u001b[0m\u001b[95m'reg669'\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mMethod:\n",
       "\u001b[0m  \u001b[94mInverse Probability Weighting (IPW) Weighted Regression\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "report = causal_model.estimate_att(method=\"ipw_weighted_regression\", robust_se=\"HC0\")\n",
    "report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jK0OtjQilS2V"
   },
   "source": [
    "# Section 5: Machine Learning\n",
    "\n",
    "Now, let's work through how to do machine learning model benchmarking using TableMage.\n",
    "\n",
    "To begin, let's use the house price data once again."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "id": "HeVRZfpjlS2V",
    "outputId": "6f07e2d8-bbe5-4f28-f71a-1d29bc068ac7"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mHouse Prices\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(1168, 80)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(292, 80)\u001b[0m                      \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[95m'Alley', \u001b[0m\u001b[95m'BldgType', \u001b[0m\u001b[95m'BsmtCond', \u001b[0m\u001b[95m'BsmtExposure', \u001b[0m\u001b[95m'BsmtFinType1', \u001b[0m\u001b[95m'BsmtFinType2', \n",
       "  \u001b[0m\u001b[95m'BsmtQual', \u001b[0m\u001b[95m'CentralAir', \u001b[0m\u001b[95m'Condition1', \u001b[0m\u001b[95m'Condition2', \u001b[0m\u001b[95m'Electrical', \u001b[0m\u001b[95m'ExterCond', \n",
       "  \u001b[0m\u001b[95m'ExterQual', \u001b[0m\u001b[95m'Exterior1st', \u001b[0m\u001b[95m'Exterior2nd', \u001b[0m\u001b[95m'Fence', \u001b[0m\u001b[95m'FireplaceQu', \u001b[0m\u001b[95m'Foundation', \n",
       "  \u001b[0m\u001b[95m'Functional', \u001b[0m\u001b[95m'GarageCond', \u001b[0m\u001b[95m'GarageFinish', \u001b[0m\u001b[95m'GarageQual', \u001b[0m\u001b[95m'GarageType', \u001b[0m\u001b[95m'Heating', \n",
       "  \u001b[0m\u001b[95m'HeatingQC', \u001b[0m\u001b[95m'HouseStyle', \u001b[0m\u001b[95m'KitchenQual', \u001b[0m\u001b[95m'LandContour', \u001b[0m\u001b[95m'LandSlope', \u001b[0m\u001b[95m'LotConfig', \n",
       "  \u001b[0m\u001b[95m'LotShape', \u001b[0m\u001b[95m'MSZoning', \u001b[0m\u001b[95m'MasVnrType', \u001b[0m\u001b[95m'MiscFeature', \u001b[0m\u001b[95m'Neighborhood', \u001b[0m\u001b[95m'PavedDrive', \n",
       "  \u001b[0m\u001b[95m'PoolQC', \u001b[0m\u001b[95m'RoofMatl', \u001b[0m\u001b[95m'RoofStyle', \u001b[0m\u001b[95m'SaleCondition', \u001b[0m\u001b[95m'SaleType', \u001b[0m\u001b[95m'Street', \u001b[0m\u001b[95m'Utilities'\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'1stFlrSF', \u001b[0m\u001b[95m'2ndFlrSF', \u001b[0m\u001b[95m'3SsnPorch', \u001b[0m\u001b[95m'BedroomAbvGr', \u001b[0m\u001b[95m'BsmtFinSF1', \u001b[0m\u001b[95m'BsmtFinSF2', \n",
       "  \u001b[0m\u001b[95m'BsmtFullBath', \u001b[0m\u001b[95m'BsmtHalfBath', \u001b[0m\u001b[95m'BsmtUnfSF', \u001b[0m\u001b[95m'EnclosedPorch', \u001b[0m\u001b[95m'Fireplaces', \n",
       "  \u001b[0m\u001b[95m'FullBath', \u001b[0m\u001b[95m'GarageArea', \u001b[0m\u001b[95m'GarageCars', \u001b[0m\u001b[95m'GarageYrBlt', \u001b[0m\u001b[95m'GrLivArea', \u001b[0m\u001b[95m'HalfBath', \n",
       "  \u001b[0m\u001b[95m'KitchenAbvGr', \u001b[0m\u001b[95m'LotArea', \u001b[0m\u001b[95m'LotFrontage', \u001b[0m\u001b[95m'LowQualFinSF', \u001b[0m\u001b[95m'MSSubClass', \u001b[0m\u001b[95m'MasVnrArea', \n",
       "  \u001b[0m\u001b[95m'MiscVal', \u001b[0m\u001b[95m'MoSold', \u001b[0m\u001b[95m'OpenPorchSF', \u001b[0m\u001b[95m'OverallCond', \u001b[0m\u001b[95m'OverallQual', \u001b[0m\u001b[95m'PoolArea', \n",
       "  \u001b[0m\u001b[95m'SalePrice', \u001b[0m\u001b[95m'ScreenPorch', \u001b[0m\u001b[95m'TotRmsAbvGrd', \u001b[0m\u001b[95m'TotalBsmtSF', \u001b[0m\u001b[95m'WoodDeckSF', \u001b[0m\u001b[95m'YearBuilt', \n",
       "  \u001b[0m\u001b[95m'YearRemodAdd', \u001b[0m\u001b[95m'YrSold'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib\n",
    "import numpy as np\n",
    "\n",
    "data_path = curr_dir / \"demo\" / \"regression\" / \"house_price_data\" / \"data.csv\"\n",
    "df = pd.read_csv(data_path, index_col=0)\n",
    "analyzer = tm.Analyzer(\n",
    "    df, test_size=0.2, split_seed=42, verbose=True, name=\"House Prices\"\n",
    ")\n",
    "analyzer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "an36oYmWTNRv"
   },
   "source": [
    "Feel free to perform any preprocessing steps."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "id": "3iezDVKJTMxq"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "========================================================================================\n",
       "\u001b[1mHouse Prices\u001b[0m \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mTrain shape: \u001b[0m\u001b[93m(1168, 74)\u001b[0m                      \u001b[1mTest shape: \u001b[0m\u001b[93m(292, 74)\u001b[0m                      \n",
       "----------------------------------------------------------------------------------------\n",
       "\u001b[1mCategorical variables:\u001b[0m\n",
       "  \u001b[95m'BldgType', \u001b[0m\u001b[95m'BsmtCond', \u001b[0m\u001b[95m'BsmtExposure', \u001b[0m\u001b[95m'BsmtFinType1', \u001b[0m\u001b[95m'BsmtFinType2', \u001b[0m\u001b[95m'BsmtQual', \n",
       "  \u001b[0m\u001b[95m'CentralAir', \u001b[0m\u001b[95m'Condition1', \u001b[0m\u001b[95m'Condition2', \u001b[0m\u001b[95m'Electrical', \u001b[0m\u001b[95m'ExterCond', \u001b[0m\u001b[95m'ExterQual', \n",
       "  \u001b[0m\u001b[95m'Exterior1st', \u001b[0m\u001b[95m'Exterior2nd', \u001b[0m\u001b[95m'Foundation', \u001b[0m\u001b[95m'Functional', \u001b[0m\u001b[95m'GarageCond', \n",
       "  \u001b[0m\u001b[95m'GarageFinish', \u001b[0m\u001b[95m'GarageQual', \u001b[0m\u001b[95m'GarageType', \u001b[0m\u001b[95m'Heating', \u001b[0m\u001b[95m'HeatingQC', \u001b[0m\u001b[95m'HouseStyle', \n",
       "  \u001b[0m\u001b[95m'KitchenQual', \u001b[0m\u001b[95m'LandContour', \u001b[0m\u001b[95m'LandSlope', \u001b[0m\u001b[95m'LotConfig', \u001b[0m\u001b[95m'LotShape', \u001b[0m\u001b[95m'MSZoning', \n",
       "  \u001b[0m\u001b[95m'Neighborhood', \u001b[0m\u001b[95m'PavedDrive', \u001b[0m\u001b[95m'RoofMatl', \u001b[0m\u001b[95m'RoofStyle', \u001b[0m\u001b[95m'SaleCondition', \u001b[0m\u001b[95m'SaleType', \n",
       "  \u001b[0m\u001b[95m'Street', \u001b[0m\u001b[95m'Utilities'\u001b[0m \n",
       "                                                                                        \n",
       "\u001b[1mNumeric variables:\u001b[0m\n",
       "  \u001b[95m'1stFlrSF', \u001b[0m\u001b[95m'2ndFlrSF', \u001b[0m\u001b[95m'3SsnPorch', \u001b[0m\u001b[95m'BedroomAbvGr', \u001b[0m\u001b[95m'BsmtFinSF1', \u001b[0m\u001b[95m'BsmtFinSF2', \n",
       "  \u001b[0m\u001b[95m'BsmtFullBath', \u001b[0m\u001b[95m'BsmtHalfBath', \u001b[0m\u001b[95m'BsmtUnfSF', \u001b[0m\u001b[95m'EnclosedPorch', \u001b[0m\u001b[95m'Fireplaces', \n",
       "  \u001b[0m\u001b[95m'FullBath', \u001b[0m\u001b[95m'GarageArea', \u001b[0m\u001b[95m'GarageCars', \u001b[0m\u001b[95m'GarageYrBlt', \u001b[0m\u001b[95m'GrLivArea', \u001b[0m\u001b[95m'HalfBath', \n",
       "  \u001b[0m\u001b[95m'KitchenAbvGr', \u001b[0m\u001b[95m'LotArea', \u001b[0m\u001b[95m'LotFrontage', \u001b[0m\u001b[95m'LowQualFinSF', \u001b[0m\u001b[95m'MSSubClass', \u001b[0m\u001b[95m'MasVnrArea', \n",
       "  \u001b[0m\u001b[95m'MiscVal', \u001b[0m\u001b[95m'MoSold', \u001b[0m\u001b[95m'OpenPorchSF', \u001b[0m\u001b[95m'OverallCond', \u001b[0m\u001b[95m'OverallQual', \u001b[0m\u001b[95m'PoolArea', \n",
       "  \u001b[0m\u001b[95m'SalePrice', \u001b[0m\u001b[95m'ScreenPorch', \u001b[0m\u001b[95m'TotRmsAbvGrd', \u001b[0m\u001b[95m'TotalBsmtSF', \u001b[0m\u001b[95m'WoodDeckSF', \u001b[0m\u001b[95m'YearBuilt', \n",
       "  \u001b[0m\u001b[95m'YearRemodAdd', \u001b[0m\u001b[95m'YrSold'\u001b[0m \n",
       "========================================================================================"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "analyzer.dropna(\n",
    "    include_vars=[\"SalePrice\"]\n",
    ").drop_highly_missing_vars(  # drop variables with more than 30% missing values\n",
    "    exclude_vars=[\"SalePrice\"], threshold=0.3\n",
    ").impute(  # impute missing values\n",
    "    exclude_vars=[\"SalePrice\"],\n",
    "    numeric_strategy=\"5nn\",\n",
    "    categorical_strategy=\"most_frequent\",\n",
    ").scale(  # scale numeric variables\n",
    "    exclude_vars=[\"SalePrice\"], strategy=\"standardize\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "n_AcKvbplS2V"
   },
   "source": [
    "We can use the `regress` function in our analyzer to properly benchmark certain models. In this case, we compare the Random Forest, XGBoost, and linear regression models."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "id": "niKBNAW0lS2V",
    "outputId": "b527dd60-f289-4ffc-a812-089fd5ac87d0"
   },
   "outputs": [],
   "source": [
    "reg_report = analyzer.regress(\n",
    "    models=[\n",
    "        tm.ml.LinearR(\"l2\"),\n",
    "        # tm.ml.TreesR(\"random_forest\"),\n",
    "        # tm.ml.TreesR(\"xgboost\"),\n",
    "    ],\n",
    "    target=\"SalePrice\",\n",
    "    predictors=[\"1stFlrSF\", \"2ndFlrSF\", \"YrSold\", \"BldgType\", \"MSZoning\", \"LotShape\"],\n",
    "    feature_selectors=[tm.fs.BorutaFSR()],  # select features\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2OZlShEClS2V"
   },
   "source": [
    "Lastly, we can compare model metrics and save models for future use."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "id": "TnzEy1mClS2V",
    "outputId": "4cd88292-7368-4918-e15f-34543136e1bb"
   },
   "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>LinearR(l2)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Statistic</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>rmse</th>\n",
       "      <td>50294.432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mae</th>\n",
       "      <td>32321.420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mape</th>\n",
       "      <td>0.194</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pearsonr</th>\n",
       "      <td>0.832</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>spearmanr</th>\n",
       "      <td>0.861</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>r2</th>\n",
       "      <td>0.670</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>adjr2</th>\n",
       "      <td>0.666</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>n_obs</th>\n",
       "      <td>292.000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           LinearR(l2)\n",
       "Statistic             \n",
       "rmse         50294.432\n",
       "mae          32321.420\n",
       "mape             0.194\n",
       "pearsonr         0.832\n",
       "spearmanr        0.861\n",
       "r2               0.670\n",
       "adjr2            0.666\n",
       "n_obs          292.000"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Compare model performance\n",
    "display(reg_report.metrics(\"test\"))\n",
    "\n",
    "# Predict on new data\n",
    "new_df = df.sample(frac=0.3)\n",
    "new_df = new_df.drop(columns=[\"SalePrice\"])\n",
    "\n",
    "y_pred = reg_report.model(\"LinearR(l2)\").sklearn_pipeline().predict(new_df)\n",
    "\n",
    "# Save model as sklearn pipeline\n",
    "joblib.dump(reg_report.model(\"LinearR(l2)\").sklearn_pipeline(), \"l2_pipeline.joblib\")\n",
    "\n",
    "# Load model and predict on new data\n",
    "y_pred_from_save = joblib.load(\"l2_pipeline.joblib\").predict(new_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7xTHOfk7lS2V"
   },
   "source": [
    "# Section 6: Conversational Data Analysis\n",
    "\n",
    "In this section, we demonstrate how to use TableMage's conversational data analysis capabilities. This is particularly useful for no-code use of the package, helping those that may not have the background necessary to do thorough data analysis on their datasets.\n",
    "\n",
    "First, we enable the use of agents in TableMage with the `tm.use_agents()` function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 263,
     "referenced_widgets": [
      "e66230f62beb48cfb2b466b8e997300e",
      "ed06698a39994da9af5219799b27785f",
      "7c066cf6a712437d833f9a4e9eac9c37",
      "b60a317241f74b0f8c8040de43f95a1f",
      "0d6823b395414ac881c05366a39bd351",
      "10e706d109aa45199b507c340948aca1",
      "957d44252f414106b9e78bdb70c1fbdb",
      "314b159bca8e44b19ba2701c1af9e87c",
      "2efb543dd0204b2aad1911a0a93b082c",
      "8a7691bc95fb47d89649a96dce84096f",
      "c7458797bdbd4e30bcec09c477c71dbb",
      "eff1ff66339f4b7c8380aa3100065996",
      "d4734156237b4cf1902853f901b74e54",
      "efdf8762d98943649e51b827f99ad246",
      "02e3e5c0a229489b9f697968e695523e",
      "9654374652e04c68b0190c7a60807dfd",
      "198fbe5e8abc4a019432ce59e1646978",
      "c6a7b90e0bc44f8ab47d09b0512d14de",
      "9cc500f2e27349ae8283b8c0d18a0446",
      "ee3e28d278b34c94977fc67111ea36e5",
      "3e650def3fd34e6aa439320b4cd09f10",
      "38edf962871a438ba9341109762ecf62",
      "c708335cdc8543358c0aae325bd4c46c",
      "d82f1cfa367142df980a08f60615b59e",
      "0ad17781c1364b45aadb8241ec604528",
      "f1b57346757c4ea2b32e63946c54d31c",
      "58af708d95414fe1a3234fc7a18d3671",
      "ee4a7345a82c4b5bac0d547fdf8a5ed8",
      "c4b8025bf90942c2bb447413d7561b6e",
      "a2ef94d2e93240c9bb437a9b7852d6a3",
      "e537bd95406142239aecc70178e49112",
      "70453b4a1bd2451ba9295be547d99698",
      "1202bfcd96a14896961ab146c430e3ac",
      "38de73dd234242dd8062cf52865d11a7",
      "a912a92e15c04db78e5f377611dc265a",
      "8350caebf7ff45688f239c66bcc5a6ab",
      "8f72245c358a4a45a47cccd272d727ea",
      "61ef9335d07d4be0b13c70027fd4f9bd",
      "28e99b0975b448d5b553705da3dcb9a7",
      "25a341bf51c042eaa8b83a55ea4e61ad",
      "9b86579e0c7d4110b4e8a373c889cd3c",
      "106e0ab7ce4e46b6a988f155118fa201",
      "e95f3e58be02494d96b266127c5c3987",
      "4dc05bdc59a942e692eacc213d911d0b",
      "687c4e737b9e45daba999bfb26984bde",
      "e07395f67cf0481f92c295c97354b2a7",
      "657f7bda6f1b4c43a62a6ff8ceed3d68",
      "a05232b82dfc4fe4978009f028d34100",
      "b7d43008e63d48078c9f1dc99a573954",
      "6251d20fa7404172be0213fec01b8b67",
      "b8b67759081e4f3294014b5c0b3bf37b",
      "798c62676b0940fc894d78bdd8ec73f6",
      "cf942bda6acf4173a2aca2fcdced213e",
      "9a8818e75ff64de6bd77c69687fe3220",
      "25f2f9987f3d4768b485ddc28885fb30",
      "2d5efc35eb284862ad4b7e7922d7a2d6",
      "1ed163cdf53140678c865d5415a9402b",
      "b29a4a47803542cda19647989c34e65d",
      "5128ffca9d5e45c68ea057003a89e5f3",
      "8fcc33c6bf37406cb2122f84fe5ecdf7",
      "84daa44a6c1c416dadc0095205b99b92",
      "db522b814ff1410397bbb42d57eee7d7",
      "501f51b68698401aa39fc26ede6f5702",
      "45d9572c96984f1da19a71be779383ea",
      "0dd52bdb0e1249f0bbe304be03c07280",
      "6ad210af487c42febd1fe562159aadaf"
     ]
    },
    "id": "HFB9L1ywb38w",
    "outputId": "715e5225-7d39-4ed9-cdb8-08000ef0b919"
   },
   "outputs": [],
   "source": [
    "from IPython.display import Markdown\n",
    "\n",
    "tm.use_agents()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6eSh5msDlS2V"
   },
   "source": [
    "\n",
    "\n",
    "We then set the API key for the OpenAI agent using the `tm.agents.set_key` method. We also configure the agent to use the GPT-4o model with the `tm.agents.options.set_llm` method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "id": "ue9IBfKPb_x2"
   },
   "outputs": [],
   "source": [
    "tm.agents.set_key(\n",
    "    \"openai\",\n",
    "    \"your-api-key-here\",\n",
    ")\n",
    "tm.agents.options.set_llm(llm_type=\"openai\", model_name=\"gpt-4o\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6aTMKH17lS2V"
   },
   "source": [
    "We initialize a `ChatDA` agent with the training dataset `df` and a test size of 20%."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "id": "ERBs1CIT_JXT"
   },
   "outputs": [],
   "source": [
    "agent = tm.agents.ChatDA(df=df, test_size=0.2, verbose=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "87HT-V2-lS2W"
   },
   "source": [
    "We interact with the agent through the `chat` method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 180
    },
    "id": "ufhH6Oaj_TNo",
    "outputId": "11bd335c-c9b9-48b9-91f9-216ba2cffa91"
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "Your dataset consists of 80 variables, with 43 being categorical and 37 being numeric. The training set contains 1,168 rows, while the test set has 292 rows. \n",
       "\n",
       "### Numeric Variables\n",
       "Some of the numeric variables include:\n",
       "- **1stFlrSF, 2ndFlrSF, 3SsnPorch**: These likely represent square footage measurements for different parts of a property.\n",
       "- **BedroomAbvGr, FullBath, HalfBath**: These could indicate the number of bedrooms and bathrooms above ground.\n",
       "- **GarageArea, GarageCars**: These might represent the area of the garage and the number of cars it can accommodate.\n",
       "- **LotArea, LotFrontage**: These could be measurements related to the property's lot size.\n",
       "- **SalePrice**: This is likely the target variable, representing the sale price of the property.\n",
       "\n",
       "### Categorical Variables\n",
       "Some of the categorical variables include:\n",
       "- **Alley, BldgType, BsmtCond**: These might describe features related to the alley access, building type, and basement condition.\n",
       "- **CentralAir, Electrical, Heating**: These could indicate the presence of central air conditioning, electrical system type, and heating quality.\n",
       "- **Neighborhood, MSZoning**: These might describe the neighborhood and zoning classification.\n",
       "- **SaleCondition, SaleType**: These could relate to the conditions and types of sales.\n",
       "\n",
       "This dataset seems to be related to real estate, possibly for predicting house prices based on various features of the properties. If you need more detailed insights, such as summary statistics or handling missing values, feel free to ask!"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response = agent.chat(\"Tell me about the dataset.\")\n",
    "Markdown(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "id": "hN7Uxj-6AI78",
    "outputId": "e789c8e1-3d2b-4568-d8c0-74115381fdd6"
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "### Summary Statistics\n",
       "\n",
       "#### Numeric Variables\n",
       "- **1stFlrSF**: Mean = 1162.63, Std = 386.59, Min = 334, Max = 4692\n",
       "- **2ndFlrSF**: Mean = 346.99, Std = 436.53, Min = 0, Max = 2065\n",
       "- **GrLivArea**: Mean = 1515.46, Std = 525.48, Min = 334, Max = 5642\n",
       "- **SalePrice**: Mean = 180,921.20, Std = 79,442.50, Min = 34,900, Max = 755,000\n",
       "\n",
       "#### Categorical Variables\n",
       "- **Alley**: Most common = Grvl, Missing rate = 93.77%\n",
       "- **BldgType**: Most common = 1Fam, No missing values\n",
       "- **CentralAir**: Most common = Y, No missing values\n",
       "- **Neighborhood**: Most common = NAmes, No missing values\n",
       "\n",
       "### Correlation with SalePrice\n",
       "The following variables have a high correlation with SalePrice:\n",
       "- **OverallQual**: Correlation = 0.791\n",
       "- **GrLivArea**: Correlation = 0.709\n",
       "- **GarageCars**: Correlation = 0.640\n",
       "- **GarageArea**: Correlation = 0.623\n",
       "- **TotalBsmtSF**: Correlation = 0.614\n",
       "- **1stFlrSF**: Correlation = 0.606\n",
       "- **FullBath**: Correlation = 0.561\n",
       "- **YearBuilt**: Correlation = 0.523\n",
       "\n",
       "These variables are likely to be significant predictors of SalePrice. If you're planning to build a predictive model, these features could be a good starting point. Let me know if you need further analysis or assistance!"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response = agent.chat(\n",
    "    \"\"\"Provide the summary statistics. \n",
    "    Also help me figure out which variables are highly correlated with SalePrice.\n",
    "    \"\"\"\n",
    ")\n",
    "Markdown(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "id": "S9qhD4n_lS2W",
    "outputId": "2a468cd7-74e9-4c37-e788-93baed6127b8"
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "The linear regression model using the selected predictors (OverallQual, GrLivArea, GarageCars, GarageArea, TotalBsmtSF) has been fitted to predict SalePrice. Here are the key results:\n",
       "\n",
       "### Coefficients:\n",
       "- **OverallQual**: Significant positive impact on SalePrice (\\$23,835 increase per unit increase in quality).\n",
       "- **GrLivArea**: Significant positive impact (\\$42.43 increase per square foot).\n",
       "- **GarageCars**: Positive impact, but not statistically significant.\n",
       "- **GarageArea**: Positive impact, but not statistically significant.\n",
       "- **TotalBsmtSF**: Significant positive impact (\\$27.5 increase per square foot).\n",
       "\n",
       "### Model Performance:\n",
       "- **Training Set**:\n",
       "  - RMSE: \\$38,625\n",
       "  - R²: 0.75\n",
       "- **Test Set**:\n",
       "  - RMSE: \\$39,979\n",
       "  - R²: 0.792\n",
       "\n",
       "The model explains about 75% of the variance in the training set and 79.2% in the test set, indicating a good fit.\n",
       "\n",
       "I've also generated diagnostic plots for further analysis. If you have any specific questions or need further analysis, feel free to ask!"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response = agent.chat(\n",
    "    \"\"\"Help me predict the SalePrice with linear regression. \n",
    "    Choose the predictors you think are most relevant.\n",
    "    \"\"\"\n",
    ")\n",
    "Markdown(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "id": "vrwUFgkTlS2W",
    "outputId": "a972dd7b-92d5-4dfb-e281-dcdeb1e9e51f"
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "I fitted several machine learning models to predict SalePrice, and here's how they performed:\n",
       "\n",
       "### Model Performance:\n",
       "- **XGBoost**:\n",
       "  - **Training Set**: RMSE: \\$21,697, R²: 0.921\n",
       "  - **Test Set**: RMSE: \\$31,235, R²: 0.873\n",
       "  - **Training Details**: Used Optuna for hyperparameter tuning with 100 trials and 5-fold cross-validation. Best parameters included a learning rate of 0.039, 100 estimators, and a max depth of 5.\n",
       "\n",
       "- **Random Forest (RF)**:\n",
       "  - **Training Set**: RMSE: \\$26,615, R²: 0.881\n",
       "  - **Test Set**: RMSE: \\$33,444, R²: 0.854\n",
       "  - **Training Details**: Optuna tuning with 100 trials. Best parameters included 400 estimators, max depth of 13, and log2 for max features.\n",
       "\n",
       "- **Ridge Regression**:\n",
       "  - **Training Set**: RMSE: \\$38,627, R²: 0.75\n",
       "  - **Test Set**: RMSE: \\$39,955, R²: 0.792\n",
       "\n",
       "- **Lasso Regression**:\n",
       "  - **Training Set**: RMSE: \\$38,625, R²: 0.75\n",
       "  - **Test Set**: RMSE: \\$39,979, R²: 0.792\n",
       "\n",
       "### Best Model:\n",
       "The **XGBoost** model performed the best with the lowest RMSE and highest R² on both the training and test sets. It was trained using a comprehensive hyperparameter search strategy, optimizing parameters like learning rate, number of estimators, and tree depth.\n",
       "\n",
       "If you have further questions or need additional insights, feel free to ask!"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response = agent.chat(\n",
    "    \"\"\"Fit some machine learning models to try to obtain better predictive performance.\n",
    "    Let me know which model is best and how it performs.\n",
    "    Tell me also how you trained that model.\n",
    "    \"\"\"\n",
    ")\n",
    "Markdown(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "k8Z2lazHlS2W"
   },
   "source": [
    "We hope you enjoy TableMage."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "kernelspec": {
   "display_name": "tmtest",
   "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": "3.12.8"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "02e3e5c0a229489b9f697968e695523e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_3e650def3fd34e6aa439320b4cd09f10",
      "placeholder": "​",
      "style": "IPY_MODEL_38edf962871a438ba9341109762ecf62",
      "value": " 740/740 [00:00&lt;00:00, 12.0kB/s]"
     }
    },
    "0ad17781c1364b45aadb8241ec604528": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_a2ef94d2e93240c9bb437a9b7852d6a3",
      "max": 695,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_e537bd95406142239aecc70178e49112",
      "value": 695
     }
    },
    "0d6823b395414ac881c05366a39bd351": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "0dd52bdb0e1249f0bbe304be03c07280": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "106e0ab7ce4e46b6a988f155118fa201": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "10e706d109aa45199b507c340948aca1": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "1202bfcd96a14896961ab146c430e3ac": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "198fbe5e8abc4a019432ce59e1646978": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "1ed163cdf53140678c865d5415a9402b": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_84daa44a6c1c416dadc0095205b99b92",
      "placeholder": "​",
      "style": "IPY_MODEL_db522b814ff1410397bbb42d57eee7d7",
      "value": "tokenizer_config.json: 100%"
     }
    },
    "25a341bf51c042eaa8b83a55ea4e61ad": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "25f2f9987f3d4768b485ddc28885fb30": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "28e99b0975b448d5b553705da3dcb9a7": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "2d5efc35eb284862ad4b7e7922d7a2d6": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_1ed163cdf53140678c865d5415a9402b",
       "IPY_MODEL_b29a4a47803542cda19647989c34e65d",
       "IPY_MODEL_5128ffca9d5e45c68ea057003a89e5f3"
      ],
      "layout": "IPY_MODEL_8fcc33c6bf37406cb2122f84fe5ecdf7"
     }
    },
    "2efb543dd0204b2aad1911a0a93b082c": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "314b159bca8e44b19ba2701c1af9e87c": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "38de73dd234242dd8062cf52865d11a7": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_a912a92e15c04db78e5f377611dc265a",
       "IPY_MODEL_8350caebf7ff45688f239c66bcc5a6ab",
       "IPY_MODEL_8f72245c358a4a45a47cccd272d727ea"
      ],
      "layout": "IPY_MODEL_61ef9335d07d4be0b13c70027fd4f9bd"
     }
    },
    "38edf962871a438ba9341109762ecf62": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "3e650def3fd34e6aa439320b4cd09f10": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "45d9572c96984f1da19a71be779383ea": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "4dc05bdc59a942e692eacc213d911d0b": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "501f51b68698401aa39fc26ede6f5702": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "5128ffca9d5e45c68ea057003a89e5f3": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_0dd52bdb0e1249f0bbe304be03c07280",
      "placeholder": "​",
      "style": "IPY_MODEL_6ad210af487c42febd1fe562159aadaf",
      "value": " 1.24k/1.24k [00:00&lt;00:00, 11.1kB/s]"
     }
    },
    "58af708d95414fe1a3234fc7a18d3671": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "61ef9335d07d4be0b13c70027fd4f9bd": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "6251d20fa7404172be0213fec01b8b67": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "657f7bda6f1b4c43a62a6ff8ceed3d68": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_798c62676b0940fc894d78bdd8ec73f6",
      "max": 217824172,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_cf942bda6acf4173a2aca2fcdced213e",
      "value": 217824172
     }
    },
    "687c4e737b9e45daba999bfb26984bde": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_e07395f67cf0481f92c295c97354b2a7",
       "IPY_MODEL_657f7bda6f1b4c43a62a6ff8ceed3d68",
       "IPY_MODEL_a05232b82dfc4fe4978009f028d34100"
      ],
      "layout": "IPY_MODEL_b7d43008e63d48078c9f1dc99a573954"
     }
    },
    "6ad210af487c42febd1fe562159aadaf": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "70453b4a1bd2451ba9295be547d99698": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "798c62676b0940fc894d78bdd8ec73f6": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "7c066cf6a712437d833f9a4e9eac9c37": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_314b159bca8e44b19ba2701c1af9e87c",
      "max": 5,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_2efb543dd0204b2aad1911a0a93b082c",
      "value": 5
     }
    },
    "8350caebf7ff45688f239c66bcc5a6ab": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_9b86579e0c7d4110b4e8a373c889cd3c",
      "max": 711396,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_106e0ab7ce4e46b6a988f155118fa201",
      "value": 711396
     }
    },
    "84daa44a6c1c416dadc0095205b99b92": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "8a7691bc95fb47d89649a96dce84096f": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "8f72245c358a4a45a47cccd272d727ea": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_e95f3e58be02494d96b266127c5c3987",
      "placeholder": "​",
      "style": "IPY_MODEL_4dc05bdc59a942e692eacc213d911d0b",
      "value": " 711k/711k [00:00&lt;00:00, 2.78MB/s]"
     }
    },
    "8fcc33c6bf37406cb2122f84fe5ecdf7": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "957d44252f414106b9e78bdb70c1fbdb": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "9654374652e04c68b0190c7a60807dfd": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "9a8818e75ff64de6bd77c69687fe3220": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "9b86579e0c7d4110b4e8a373c889cd3c": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "9cc500f2e27349ae8283b8c0d18a0446": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "a05232b82dfc4fe4978009f028d34100": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_9a8818e75ff64de6bd77c69687fe3220",
      "placeholder": "​",
      "style": "IPY_MODEL_25f2f9987f3d4768b485ddc28885fb30",
      "value": " 218M/218M [00:05&lt;00:00, 42.1MB/s]"
     }
    },
    "a2ef94d2e93240c9bb437a9b7852d6a3": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "a912a92e15c04db78e5f377611dc265a": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_28e99b0975b448d5b553705da3dcb9a7",
      "placeholder": "​",
      "style": "IPY_MODEL_25a341bf51c042eaa8b83a55ea4e61ad",
      "value": "tokenizer.json: 100%"
     }
    },
    "b29a4a47803542cda19647989c34e65d": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_501f51b68698401aa39fc26ede6f5702",
      "max": 1242,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_45d9572c96984f1da19a71be779383ea",
      "value": 1242
     }
    },
    "b60a317241f74b0f8c8040de43f95a1f": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_8a7691bc95fb47d89649a96dce84096f",
      "placeholder": "​",
      "style": "IPY_MODEL_c7458797bdbd4e30bcec09c477c71dbb",
      "value": " 5/5 [00:05&lt;00:00,  3.39s/it]"
     }
    },
    "b7d43008e63d48078c9f1dc99a573954": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "b8b67759081e4f3294014b5c0b3bf37b": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "c4b8025bf90942c2bb447413d7561b6e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "c6a7b90e0bc44f8ab47d09b0512d14de": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "c708335cdc8543358c0aae325bd4c46c": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_d82f1cfa367142df980a08f60615b59e",
       "IPY_MODEL_0ad17781c1364b45aadb8241ec604528",
       "IPY_MODEL_f1b57346757c4ea2b32e63946c54d31c"
      ],
      "layout": "IPY_MODEL_58af708d95414fe1a3234fc7a18d3671"
     }
    },
    "c7458797bdbd4e30bcec09c477c71dbb": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "cf942bda6acf4173a2aca2fcdced213e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "d4734156237b4cf1902853f901b74e54": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_198fbe5e8abc4a019432ce59e1646978",
      "placeholder": "​",
      "style": "IPY_MODEL_c6a7b90e0bc44f8ab47d09b0512d14de",
      "value": "config.json: 100%"
     }
    },
    "d82f1cfa367142df980a08f60615b59e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ee4a7345a82c4b5bac0d547fdf8a5ed8",
      "placeholder": "​",
      "style": "IPY_MODEL_c4b8025bf90942c2bb447413d7561b6e",
      "value": "special_tokens_map.json: 100%"
     }
    },
    "db522b814ff1410397bbb42d57eee7d7": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "e07395f67cf0481f92c295c97354b2a7": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_6251d20fa7404172be0213fec01b8b67",
      "placeholder": "​",
      "style": "IPY_MODEL_b8b67759081e4f3294014b5c0b3bf37b",
      "value": "model_optimized.onnx: 100%"
     }
    },
    "e537bd95406142239aecc70178e49112": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "e66230f62beb48cfb2b466b8e997300e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_ed06698a39994da9af5219799b27785f",
       "IPY_MODEL_7c066cf6a712437d833f9a4e9eac9c37",
       "IPY_MODEL_b60a317241f74b0f8c8040de43f95a1f"
      ],
      "layout": "IPY_MODEL_0d6823b395414ac881c05366a39bd351"
     }
    },
    "e95f3e58be02494d96b266127c5c3987": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "ed06698a39994da9af5219799b27785f": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_10e706d109aa45199b507c340948aca1",
      "placeholder": "​",
      "style": "IPY_MODEL_957d44252f414106b9e78bdb70c1fbdb",
      "value": "Fetching 5 files: 100%"
     }
    },
    "ee3e28d278b34c94977fc67111ea36e5": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "ee4a7345a82c4b5bac0d547fdf8a5ed8": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "efdf8762d98943649e51b827f99ad246": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_9cc500f2e27349ae8283b8c0d18a0446",
      "max": 740,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_ee3e28d278b34c94977fc67111ea36e5",
      "value": 740
     }
    },
    "eff1ff66339f4b7c8380aa3100065996": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_d4734156237b4cf1902853f901b74e54",
       "IPY_MODEL_efdf8762d98943649e51b827f99ad246",
       "IPY_MODEL_02e3e5c0a229489b9f697968e695523e"
      ],
      "layout": "IPY_MODEL_9654374652e04c68b0190c7a60807dfd"
     }
    },
    "f1b57346757c4ea2b32e63946c54d31c": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_70453b4a1bd2451ba9295be547d99698",
      "placeholder": "​",
      "style": "IPY_MODEL_1202bfcd96a14896961ab146c430e3ac",
      "value": " 695/695 [00:00&lt;00:00, 8.16kB/s]"
     }
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}