diabetes_prediction.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.035103,
     "end_time": "2020-11-08T15:20:59.941840",
     "exception": false,
     "start_time": "2020-11-08T15:20:59.906737",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Diabetes Prediction with Machine Learning\n",
    "![banner](https://github.com/oguzerdo/diabetes-prediction/blob/main/images/diabetes.png?raw=true)\n",
    "\n",
    "# Business Problem\n",
    "\n",
    "Develop a machine learning model that can predict whether people have diabetes when their characteristics are specified\n",
    "\n",
    "This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases.\n",
    "\n",
    "The objective of the dataset is to diagnostically predict whether or not a patient has diabetes, based on certain diagnostic measurements included in the dataset. Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are **females at least 21 years old of Pima Indian heritage.**\n",
    "\n",
    "# Dataset Info\n",
    "\n",
    "The datasets consists of several medical predictor variables and one target variable, Outcome. Predictor variables includes the number of pregnancies the patient has had, their BMI, insulin level, age, and so on.\n",
    "\n",
    "**Number of Observation Units:** 768\n",
    "\n",
    "**Variable Number:** 9\n",
    "\n",
    "| Feature | Definition |\n",
    "| --- | --- |\n",
    "| Pregnancies | Number of times pregnant |\n",
    "| Glucose | Plasma glucose concentration a 2 hours in an oral glucose tolerance test |\n",
    "| BloodPressure | Diastolic blood pressure (mm Hg) |\n",
    "| SkinThickness | Triceps skin fold thickness (mm) |\n",
    "| Insulin | 2-Hour serum insulin (mu U/ml) |\n",
    "| BMI | Body mass index (weight in kg/(height in m)^2) |\n",
    "| DiabetesPedigreeFunction | Diabetes pedigree function |\n",
    "| Age | Age (years) |\n",
    "| Outcome | Class variable ( 0 - 1) |"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.03521,
     "end_time": "2020-11-08T15:21:00.012630",
     "exception": false,
     "start_time": "2020-11-08T15:20:59.977420",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**Details about the dataset:**\n",
    "The datasets consists of several medical predictor variables and one target variable, Outcome. Predictor variables includes the number of pregnancies the patient has had, their BMI, insulin level, age, and so on.\n",
    "\n",
    "**Pregnancies:** Number of times pregnant  \n",
    "**Glucose:** Plasma glucose concentration a 2 hours in an oral glucose tolerance test  \n",
    "**BloodPressure:** Diastolic blood pressure (mm Hg)  \n",
    "**SkinThickness:** Triceps skin fold thickness (mm)  \n",
    "**Insulin:** 2-Hour serum insulin (mu U/ml)  \n",
    "**BMI:** Body mass index (weight in kg/(height in m)^2)  \n",
    "**DiabetesPedigreeFunction:** Diabetes pedigree function  \n",
    "**Age:** Age (years)  \n",
    "**Outcome:** Class variable ( 0 - 1)\n",
    "\n",
    "-----------\n",
    "\n",
    "**Number of Observation Units:** 768  \n",
    "**Variable Number:** 9"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-08T15:21:00.255394Z",
     "iopub.status.busy": "2020-11-08T15:21:00.254600Z",
     "iopub.status.idle": "2020-11-08T15:21:03.883913Z",
     "shell.execute_reply": "2020-11-08T15:21:03.883246Z"
    },
    "papermill": {
     "duration": 3.679919,
     "end_time": "2020-11-08T15:21:03.884076",
     "exception": false,
     "start_time": "2020-11-08T15:21:00.204157",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/oe/miniconda3/envs/dsprojects/lib/python3.9/site-packages/xgboost/compat.py:36: FutureWarning: pandas.Int64Index is deprecated and will be removed from pandas in a future version. Use pandas.Index with the appropriate dtype instead.\n",
      "  from pandas import MultiIndex, Int64Index\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import pickle\n",
    "from helpers import *\n",
    "\n",
    "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score, precision_score, recall_score, f1_score,roc_auc_score\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
    "from sklearn.model_selection import GridSearchCV, cross_validate, train_test_split\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier, VotingClassifier\n",
    "from lightgbm import LGBMClassifier\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "import warnings\n",
    "warnings.simplefilter(action=\"ignore\")\n",
    "\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.width', 170)\n",
    "pd.set_option('display.max_rows', None)\n",
    "pd.set_option('display.float_format', lambda x: '%.3f' % x)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exploratory Data Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-08T15:21:04.043469Z",
     "iopub.status.busy": "2020-11-08T15:21:04.042750Z",
     "iopub.status.idle": "2020-11-08T15:21:04.069060Z",
     "shell.execute_reply": "2020-11-08T15:21:04.068433Z"
    },
    "papermill": {
     "duration": 0.07403,
     "end_time": "2020-11-08T15:21:04.069170",
     "exception": false,
     "start_time": "2020-11-08T15:21:03.995140",
     "status": "completed"
    },
    "tags": []
   },
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.600</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.600</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.300</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.100</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.100</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin    BMI  DiabetesPedigreeFunction  Age  Outcome\n",
       "0            6      148             72             35        0 33.600                     0.627   50        1\n",
       "1            1       85             66             29        0 26.600                     0.351   31        0\n",
       "2            8      183             64              0        0 23.300                     0.672   32        1\n",
       "3            1       89             66             23       94 28.100                     0.167   21        0\n",
       "4            0      137             40             35      168 43.100                     2.288   33        1"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Read Data\n",
    "df = pd.read_csv(\"data/diabetes.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### Shape #####################\n",
      "(768, 9)\n",
      "##################### Types #####################\n",
      "Pregnancies                   int64\n",
      "Glucose                       int64\n",
      "BloodPressure                 int64\n",
      "SkinThickness                 int64\n",
      "Insulin                       int64\n",
      "BMI                         float64\n",
      "DiabetesPedigreeFunction    float64\n",
      "Age                           int64\n",
      "Outcome                       int64\n",
      "dtype: object\n",
      "##################### Head #####################\n",
      "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin    BMI  DiabetesPedigreeFunction  Age  Outcome\n",
      "0            6      148             72             35        0 33.600                     0.627   50        1\n",
      "1            1       85             66             29        0 26.600                     0.351   31        0\n",
      "2            8      183             64              0        0 23.300                     0.672   32        1\n",
      "3            1       89             66             23       94 28.100                     0.167   21        0\n",
      "4            0      137             40             35      168 43.100                     2.288   33        1\n",
      "##################### Tail #####################\n",
      "     Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin    BMI  DiabetesPedigreeFunction  Age  Outcome\n",
      "763           10      101             76             48      180 32.900                     0.171   63        0\n",
      "764            2      122             70             27        0 36.800                     0.340   27        0\n",
      "765            5      121             72             23      112 26.200                     0.245   30        0\n",
      "766            1      126             60              0        0 30.100                     0.349   47        1\n",
      "767            1       93             70             31        0 30.400                     0.315   23        0\n",
      "##################### NA #####################\n",
      "Pregnancies                 0\n",
      "Glucose                     0\n",
      "BloodPressure               0\n",
      "SkinThickness               0\n",
      "Insulin                     0\n",
      "BMI                         0\n",
      "DiabetesPedigreeFunction    0\n",
      "Age                         0\n",
      "Outcome                     0\n",
      "dtype: int64\n",
      "##################### Quantiles #####################\n",
      "                          0.000  0.050   0.500   0.950   0.990   1.000\n",
      "Pregnancies               0.000  0.000   3.000  10.000  13.000  17.000\n",
      "Glucose                   0.000 79.000 117.000 181.000 196.000 199.000\n",
      "BloodPressure             0.000 38.700  72.000  90.000 106.000 122.000\n",
      "SkinThickness             0.000  0.000  23.000  44.000  51.330  99.000\n",
      "Insulin                   0.000  0.000  30.500 293.000 519.900 846.000\n",
      "BMI                       0.000 21.800  32.000  44.395  50.759  67.100\n",
      "DiabetesPedigreeFunction  0.078  0.140   0.372   1.133   1.698   2.420\n",
      "Age                      21.000 21.000  29.000  58.000  67.000  81.000\n",
      "Outcome                   0.000  0.000   0.000   1.000   1.000   1.000\n"
     ]
    }
   ],
   "source": [
    "check_df(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.04339,
     "end_time": "2020-11-08T15:21:05.428979",
     "exception": false,
     "start_time": "2020-11-08T15:21:05.385589",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Get numeric and categorical variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-08T15:21:05.546881Z",
     "iopub.status.busy": "2020-11-08T15:21:05.545441Z",
     "iopub.status.idle": "2020-11-08T15:21:05.551675Z",
     "shell.execute_reply": "2020-11-08T15:21:05.552406Z"
    },
    "papermill": {
     "duration": 0.06919,
     "end_time": "2020-11-08T15:21:05.552604",
     "exception": false,
     "start_time": "2020-11-08T15:21:05.483414",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Observations: 768\n",
      "Variables: 9\n",
      "cat_cols: 1\n",
      "num_cols: 8\n",
      "cat_but_car: 0\n",
      "num_but_cat: 1\n",
      "Categorical Columns: ['Outcome']\n",
      "\n",
      "Numerical Columns: ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age']\n",
      "\n",
      "High Cardinality Columns: []\n"
     ]
    }
   ],
   "source": [
    "cat_cols, num_cols, cat_but_car = grab_col_names(df)\n",
    "\n",
    "print('Categorical Columns:',cat_cols, end='\\n\\n')\n",
    "print('Numerical Columns:',num_cols, end='\\n\\n')\n",
    "print('High Cardinality Columns:',cat_but_car, end='\\n')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Analze Categorical Features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Outcome  Ratio\n",
      "0      500 65.104\n",
      "1      268 34.896\n",
      "##########################################\n"
     ]
    }
   ],
   "source": [
    "for col in cat_cols:\n",
    "    cat_summary(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Analyze Numerical Columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean      3.845\n",
      "std       3.370\n",
      "min       0.000\n",
      "5%        0.000\n",
      "10%       0.000\n",
      "20%       1.000\n",
      "30%       1.000\n",
      "40%       2.000\n",
      "50%       3.000\n",
      "60%       4.000\n",
      "70%       5.000\n",
      "80%       7.000\n",
      "90%       9.000\n",
      "95%      10.000\n",
      "99%      13.000\n",
      "max      17.000\n",
      "Name: Pregnancies, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean    120.895\n",
      "std      31.973\n",
      "min       0.000\n",
      "5%       79.000\n",
      "10%      85.000\n",
      "20%      95.000\n",
      "30%     102.000\n",
      "40%     109.000\n",
      "50%     117.000\n",
      "60%     125.000\n",
      "70%     134.000\n",
      "80%     147.000\n",
      "90%     167.000\n",
      "95%     181.000\n",
      "99%     196.000\n",
      "max     199.000\n",
      "Name: Glucose, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean     69.105\n",
      "std      19.356\n",
      "min       0.000\n",
      "5%       38.700\n",
      "10%      54.000\n",
      "20%      60.000\n",
      "30%      64.000\n",
      "40%      68.000\n",
      "50%      72.000\n",
      "60%      74.000\n",
      "70%      78.000\n",
      "80%      82.000\n",
      "90%      88.000\n",
      "95%      90.000\n",
      "99%     106.000\n",
      "max     122.000\n",
      "Name: BloodPressure, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean     20.536\n",
      "std      15.952\n",
      "min       0.000\n",
      "5%        0.000\n",
      "10%       0.000\n",
      "20%       0.000\n",
      "30%       8.200\n",
      "40%      18.000\n",
      "50%      23.000\n",
      "60%      27.000\n",
      "70%      31.000\n",
      "80%      35.000\n",
      "90%      40.000\n",
      "95%      44.000\n",
      "99%      51.330\n",
      "max      99.000\n",
      "Name: SkinThickness, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean     79.799\n",
      "std     115.244\n",
      "min       0.000\n",
      "5%        0.000\n",
      "10%       0.000\n",
      "20%       0.000\n",
      "30%       0.000\n",
      "40%       0.000\n",
      "50%      30.500\n",
      "60%      72.200\n",
      "70%     106.000\n",
      "80%     150.000\n",
      "90%     210.000\n",
      "95%     293.000\n",
      "99%     519.900\n",
      "max     846.000\n",
      "Name: Insulin, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAigAAAHFCAYAAADYPwJEAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAysklEQVR4nO3df1jU5Z7/8dcI4/BDQIFg4IhEHdt+oG2L5Y/axBDMUiu7ss3qZMfT1jEtUtdStz1jJ8XjtaUnPNmPdaV0ufDblv3YzBjrqLmcTkqXG9hux65F04K4KgQRGkb4fP/oy3wbQXN0kPsjz8d1zXX1uT/33J/7njdcvro/M4zDsixLAAAABunX2xMAAAA4HgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQVASEpKSuRwOLR79+5enUdubq5yc3OD2hwOhzweT6/MB0B4Rfb2BAAgXP70pz9p8ODBvT0NAGFAQAFwzhg1alRvTwFAmHCLB8AZmTFjhgYMGKDPP/9cN9xwgwYMGKCMjAzNmzdPPp8vqO+aNWt0+eWXa8CAAYqLi9PFF1+sRYsWBc57PB45HI4u1+i8rbR///6TzuX4Wzydz/vjH/+oX//610pOTlZSUpKmTp2qr7766ozWDaBnEVAAnDG/368pU6YoLy9Pb7zxhn75y19q5cqV+t3vfhfoU1ZWplmzZmns2LHatGmTXn/9dT3yyCM6evRoj8/vV7/6lZxOp0pLS7VixQpt27ZNd911V49fF8Dp4xYPgDPW1tamJUuW6LbbbpMk5eXlaffu3SotLdU//dM/SZL+8z//UwMHDtQzzzwTeF5eXt5Zmd/1118fdN3vvvtOCxYsUF1dndxu91mZA4DQsIMC4Iw5HA5Nnjw5qG348OE6cOBA4Piqq67S4cOHdccdd+iNN97QN998c9bmN2XKlC5zkxQ0PwBmIaAAOGMxMTGKiooKanO5XPr+++8Dx3fffbf+9V//VQcOHNCtt96qlJQUjRw5Ul6vt8fnl5SU1GVuktTa2trj1wZweggoAM6ae++9VxUVFWpsbNTbb78ty7I0adKkwE5GZ8g5/s21Z3O3BYAZCCgAzrrY2FhNnDhRixcvVltbm/bu3StJOv/88yVJn3zySVD/t95662xPEUAv402yAM6K++67T9HR0br66quVlpamuro6FRUVKSEhQVdeeaUk6YYbblBiYqJmzpypJ554QpGRkSopKdHBgwd7efYAzjZ2UACcFX/7t3+r6upqPfzww8rPz9cjjzyiiy66SB988IHOO+88SVJ8fLy2bNmiuLg43XXXXXrggQeUnZ2txYsX9/LsAZxtDsuyrN6eBAAAwI+xgwIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBxb/qG2jo4OffXVV4qLi5PD4ejt6QAAgFNgWZaOHDmi9PR09et38j0SWwaUr776ShkZGb09DQAAcBoOHjyowYMHn7SPLQNKXFycpB8WGB8fH9ax/X6/ysvLVVBQIKfTGdaxET7UyT6olX1QK3uwc52ampqUkZER+Hf8ZGwZUDpv68THx/dIQImJiVF8fLztCt+XUCf7oFb2Qa3s4Vyo06m8PYM3yQIAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGOeMAkpRUZEcDocKCwsDbZZlyePxKD09XdHR0crNzdXevXuDnufz+TRnzhwlJycrNjZWU6ZM0aFDh85kKgAA4Bxy2gFl165deuGFFzR8+PCg9hUrVujpp5/W6tWrtWvXLrndbuXn5+vIkSOBPoWFhdq0aZPKysq0c+dONTc3a9KkSWpvbz/9lQAAgHPGaQWU5uZm3XnnnXrxxRc1aNCgQLtlWVq1apUWL16sqVOnKjs7Wy+99JJaWlpUWloqSWpsbNTatWv11FNPafz48briiiu0YcMGVVVVaevWreFZFQAAsLXT+kuyDz74oG688UaNHz9eTz75ZKC9pqZGdXV1KigoCLS5XC6NHTtWFRUVuv/++1VZWSm/3x/UJz09XdnZ2aqoqNCECRO6XM/n88nn8wWOm5qaJP3w1/T8fv/pLOGEOscL97gIL+pkH9TKPqiVPdi5TqHMOeSAUlZWpo8//li7du3qcq6urk6SlJqaGtSempqqAwcOBPr0798/aOels0/n849XVFSkJUuWdGkvLy9XTExMqEs4JV6vt0fGRXhRJ/ugVvZBrezBjnVqaWk55b4hBZSDBw/q4YcfVnl5uaKiok7Y7/i/sW9Z1k/+3f2T9Vm4cKHmzp0bOO78sqGCgoIe+S4er9er/Px8237HQV9AneyDWtkHtbIHO9ep8w7IqQgpoFRWVqq+vl45OTmBtvb2du3YsUOrV6/WZ599JumHXZK0tLRAn/r6+sCuitvtVltbmxoaGoJ2Uerr6zVmzJhur+tyueRyubq0O53OHitOT46N8KFO9kGt7INa2YMd6xTKfEN6k2xeXp6qqqq0Z8+ewGPEiBG68847tWfPHl1wwQVyu91B205tbW3avn17IHzk5OTI6XQG9amtrVV1dfUJAwoAAOhbQtpBiYuLU3Z2dlBbbGyskpKSAu2FhYVatmyZhg4dqqFDh2rZsmWKiYnR9OnTJUkJCQmaOXOm5s2bp6SkJCUmJmr+/PkaNmyYxo8fH6ZlAQAAOzutT/GczIIFC9Ta2qpZs2apoaFBI0eOVHl5ueLi4gJ9Vq5cqcjISE2bNk2tra3Ky8tTSUmJIiIiwj2d05bteVe+9pO/byZU+5ffGNbxAAA4V51xQNm2bVvQscPhkMfjkcfjOeFzoqKiVFxcrOLi4jO9PAAAOAfxXTwAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYJyQAsqaNWs0fPhwxcfHKz4+XqNHj9Y777wTOD9jxgw5HI6gx6hRo4LG8Pl8mjNnjpKTkxUbG6spU6bo0KFD4VkNAAA4J4QUUAYPHqzly5dr9+7d2r17t6677jrddNNN2rt3b6DP9ddfr9ra2sBj8+bNQWMUFhZq06ZNKisr086dO9Xc3KxJkyapvb09PCsCAAC2FxlK58mTJwcdL126VGvWrNGHH36oyy67TJLkcrnkdru7fX5jY6PWrl2r9evXa/z48ZKkDRs2KCMjQ1u3btWECRNOZw0AAOAcE1JA+bH29na98sorOnr0qEaPHh1o37Ztm1JSUjRw4ECNHTtWS5cuVUpKiiSpsrJSfr9fBQUFgf7p6enKzs5WRUXFCQOKz+eTz+cLHDc1NUmS/H6//H7/6S6hW53jufpZYR33x2PjzHW+lrym5qNW9kGt7MHOdQplzg7LskL6l7iqqkqjR4/W999/rwEDBqi0tFQ33HCDJGnjxo0aMGCAMjMzVVNTo8cff1zHjh1TZWWlXC6XSktLde+99waFDUkqKChQVlaWnn/++W6v6fF4tGTJki7tpaWliomJCWX6AACgl7S0tGj69OlqbGxUfHz8SfuGHFDa2tr0xRdf6PDhw3r11Vf1L//yL9q+fbsuvfTSLn1ra2uVmZmpsrIyTZ069YQBJT8/XxdeeKGee+65bq/Z3Q5KRkaGvvnmm59cYKj8fr+8Xq8e391Pvg5HWMeu9nALK1w665Sfny+n09nb08FJUCv7oFb2YOc6NTU1KTk5+ZQCSsi3ePr376+f//znkqQRI0Zo165d+v3vf9/t7kdaWpoyMzO1b98+SZLb7VZbW5saGho0aNCgQL/6+nqNGTPmhNd0uVxyuVxd2p1OZ48Vx9fhkK89vAHFbj9IdtCTPwMIL2plH9TKHuxYp1Dme8Z/B8WyrC47Ip2+/fZbHTx4UGlpaZKknJwcOZ1Oeb3eQJ/a2lpVV1efNKAAAIC+JaQdlEWLFmnixInKyMjQkSNHVFZWpm3btmnLli1qbm6Wx+PRrbfeqrS0NO3fv1+LFi1ScnKybrnlFklSQkKCZs6cqXnz5ikpKUmJiYmaP3++hg0bFvhUDwAAQEgB5euvv9bdd9+t2tpaJSQkaPjw4dqyZYvy8/PV2tqqqqoqvfzyyzp8+LDS0tI0btw4bdy4UXFxcYExVq5cqcjISE2bNk2tra3Ky8tTSUmJIiIiwr44AABgTyEFlLVr157wXHR0tN59992fHCMqKkrFxcUqLi4O5dIAAKAP4bt4AACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxQgooa9as0fDhwxUfH6/4+HiNHj1a77zzTuC8ZVnyeDxKT09XdHS0cnNztXfv3qAxfD6f5syZo+TkZMXGxmrKlCk6dOhQeFYDAADOCSEFlMGDB2v58uXavXu3du/ereuuu0433XRTIISsWLFCTz/9tFavXq1du3bJ7XYrPz9fR44cCYxRWFioTZs2qaysTDt37lRzc7MmTZqk9vb28K4MAADYVkgBZfLkybrhhht00UUX6aKLLtLSpUs1YMAAffjhh7IsS6tWrdLixYs1depUZWdn66WXXlJLS4tKS0slSY2NjVq7dq2eeuopjR8/XldccYU2bNigqqoqbd26tUcWCAAA7CfydJ/Y3t6uV155RUePHtXo0aNVU1Ojuro6FRQUBPq4XC6NHTtWFRUVuv/++1VZWSm/3x/UJz09XdnZ2aqoqNCECRO6vZbP55PP5wscNzU1SZL8fr/8fv/pLqFbneO5+llhHffHY+PMdb6WvKbmo1b2Qa3swc51CmXOIQeUqqoqjR49Wt9//70GDBigTZs26dJLL1VFRYUkKTU1Nah/amqqDhw4IEmqq6tT//79NWjQoC596urqTnjNoqIiLVmypEt7eXm5YmJiQl3CKfntiI6wj7l58+awj9nXeb3e3p4CThG1sg9qZQ92rFNLS8sp9w05oPzVX/2V9uzZo8OHD+vVV1/VPffco+3btwfOOxyOoP6WZXVpO95P9Vm4cKHmzp0bOG5qalJGRoYKCgoUHx8f6hJOyu/3y+v16vHd/eTrOPm8Q1Xt6X6HCKHrrFN+fr6cTmdvTwcnQa3sg1rZg53r1HkH5FSEHFD69++vn//855KkESNGaNeuXfr973+vRx99VNIPuyRpaWmB/vX19YFdFbfbrba2NjU0NATtotTX12vMmDEnvKbL5ZLL5erS7nQ6e6w4vg6HfO3hDSh2+0Gyg578GUB4USv7oFb2YMc6hTLfM/47KJZlyefzKSsrS263O2jLqa2tTdu3bw+Ej5ycHDmdzqA+tbW1qq6uPmlAAQAAfUtIOyiLFi3SxIkTlZGRoSNHjqisrEzbtm3Tli1b5HA4VFhYqGXLlmno0KEaOnSoli1bppiYGE2fPl2SlJCQoJkzZ2revHlKSkpSYmKi5s+fr2HDhmn8+PE9skAAAGA/IQWUr7/+Wnfffbdqa2uVkJCg4cOHa8uWLcrPz5ckLViwQK2trZo1a5YaGho0cuRIlZeXKy4uLjDGypUrFRkZqWnTpqm1tVV5eXkqKSlRREREeFcGAABsK6SAsnbt2pOedzgc8ng88ng8J+wTFRWl4uJiFRcXh3JpAADQh/BdPAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgnJACSlFRka688krFxcUpJSVFN998sz777LOgPjNmzJDD4Qh6jBo1KqiPz+fTnDlzlJycrNjYWE2ZMkWHDh0689UAAIBzQkgBZfv27XrwwQf14Ycfyuv16tixYyooKNDRo0eD+l1//fWqra0NPDZv3hx0vrCwUJs2bVJZWZl27typ5uZmTZo0Se3t7We+IgAAYHuRoXTesmVL0PG6deuUkpKiyspKXXvttYF2l8slt9vd7RiNjY1au3at1q9fr/Hjx0uSNmzYoIyMDG3dulUTJkwIdQ0AAOAcE1JAOV5jY6MkKTExMah927ZtSklJ0cCBAzV27FgtXbpUKSkpkqTKykr5/X4VFBQE+qenpys7O1sVFRXdBhSfzyefzxc4bmpqkiT5/X75/f4zWUIXneO5+llhHffHY+PMdb6WvKbmo1b2Qa3swc51CmXODsuyTutfYsuydNNNN6mhoUEffPBBoH3jxo0aMGCAMjMzVVNTo8cff1zHjh1TZWWlXC6XSktLde+99wYFDkkqKChQVlaWnn/++S7X8ng8WrJkSZf20tJSxcTEnM70AQDAWdbS0qLp06ersbFR8fHxJ+172jsos2fP1ieffKKdO3cGtd9+++2B/87OztaIESOUmZmpt99+W1OnTj3heJZlyeFwdHtu4cKFmjt3buC4qalJGRkZKigo+MkFhsrv98vr9erx3f3k6+h+Pqer2sPtq3DprFN+fr6cTmdvTwcnQa3sg1rZg53r1HkH5FScVkCZM2eO3nzzTe3YsUODBw8+ad+0tDRlZmZq3759kiS32622tjY1NDRo0KBBgX719fUaM2ZMt2O4XC65XK4u7U6ns8eK4+twyNce3oBitx8kO+jJnwGEF7WyD2plD3asUyjzDelTPJZlafbs2Xrttdf0/vvvKysr6yef8+233+rgwYNKS0uTJOXk5MjpdMrr9Qb61NbWqrq6+oQBBQAA9C0h7aA8+OCDKi0t1RtvvKG4uDjV1dVJkhISEhQdHa3m5mZ5PB7deuutSktL0/79+7Vo0SIlJyfrlltuCfSdOXOm5s2bp6SkJCUmJmr+/PkaNmxY4FM9AACgbwspoKxZs0aSlJubG9S+bt06zZgxQxEREaqqqtLLL7+sw4cPKy0tTePGjdPGjRsVFxcX6L9y5UpFRkZq2rRpam1tVV5enkpKShQREXHmKwIAALYXUkD5qQ/8REdH69133/3JcaKiolRcXKzi4uJQLg8AAPoIvosHAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABgnpIBSVFSkK6+8UnFxcUpJSdHNN9+szz77LKiPZVnyeDxKT09XdHS0cnNztXfv3qA+Pp9Pc+bMUXJysmJjYzVlyhQdOnTozFcDAADOCSEFlO3bt+vBBx/Uhx9+KK/Xq2PHjqmgoEBHjx4N9FmxYoWefvpprV69Wrt27ZLb7VZ+fr6OHDkS6FNYWKhNmzaprKxMO3fuVHNzsyZNmqT29vbwrQwAANhWZCidt2zZEnS8bt06paSkqLKyUtdee60sy9KqVau0ePFiTZ06VZL00ksvKTU1VaWlpbr//vvV2NiotWvXav369Ro/frwkacOGDcrIyNDWrVs1YcKEMC0NAADYVUgB5XiNjY2SpMTERElSTU2N6urqVFBQEOjjcrk0duxYVVRU6P7771dlZaX8fn9Qn/T0dGVnZ6uioqLbgOLz+eTz+QLHTU1NkiS/3y+/338mS+iiczxXPyus4/54bJy5zteS19R81Mo+qJU92LlOocz5tAOKZVmaO3eurrnmGmVnZ0uS6urqJEmpqalBfVNTU3XgwIFAn/79+2vQoEFd+nQ+/3hFRUVasmRJl/by8nLFxMSc7hJO6rcjOsI+5ubNm8M+Zl/n9Xp7ewo4RdTKPqiVPdixTi0tLafc97QDyuzZs/XJJ59o586dXc45HI6gY8uyurQd72R9Fi5cqLlz5waOm5qalJGRoYKCAsXHx5/G7E/M7/fL6/Xq8d395Os4+ZxDVe3h9lW4dNYpPz9fTqezt6eDk6BW9kGt7MHOdeq8A3IqTiugzJkzR2+++aZ27NihwYMHB9rdbrekH3ZJ0tLSAu319fWBXRW32622tjY1NDQE7aLU19drzJgx3V7P5XLJ5XJ1aXc6nT1WHF+HQ7728AYUu/0g2UFP/gwgvKiVfVAre7BjnUKZb0if4rEsS7Nnz9Zrr72m999/X1lZWUHns7Ky5Ha7g7ad2tratH379kD4yMnJkdPpDOpTW1ur6urqEwYUAADQt4S0g/Lggw+qtLRUb7zxhuLi4gLvGUlISFB0dLQcDocKCwu1bNkyDR06VEOHDtWyZcsUExOj6dOnB/rOnDlT8+bNU1JSkhITEzV//nwNGzYs8KkeAADQt4UUUNasWSNJys3NDWpft26dZsyYIUlasGCBWltbNWvWLDU0NGjkyJEqLy9XXFxcoP/KlSsVGRmpadOmqbW1VXl5eSopKVFERMSZrQYAAJwTQgoolvXTH711OBzyeDzyeDwn7BMVFaXi4mIVFxeHcnkAANBH8F08AADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGCckAPKjh07NHnyZKWnp8vhcOj1118POj9jxgw5HI6gx6hRo4L6+Hw+zZkzR8nJyYqNjdWUKVN06NChM1oIAAA4d4QcUI4eParLL79cq1evPmGf66+/XrW1tYHH5s2bg84XFhZq06ZNKisr086dO9Xc3KxJkyapvb099BUAAIBzTmSoT5g4caImTpx40j4ul0tut7vbc42NjVq7dq3Wr1+v8ePHS5I2bNigjIwMbd26VRMmTAh1SgAA4BwTckA5Fdu2bVNKSooGDhyosWPHaunSpUpJSZEkVVZWyu/3q6CgINA/PT1d2dnZqqio6Dag+Hw++Xy+wHFTU5Mkye/3y+/3h3XuneO5+llhHffHY+PMdb6WvKbmo1b2Qa3swc51CmXOYQ8oEydO1G233abMzEzV1NTo8ccf13XXXafKykq5XC7V1dWpf//+GjRoUNDzUlNTVVdX1+2YRUVFWrJkSZf28vJyxcTEhHsJkqTfjugI+5jH3+rCmfN6vb09BZwiamUf1Moe7FinlpaWU+4b9oBy++23B/47OztbI0aMUGZmpt5++21NnTr1hM+zLEsOh6PbcwsXLtTcuXMDx01NTcrIyFBBQYHi4+PDN3n9kO68Xq8e391Pvo7u53O6qj3cvgqXzjrl5+fL6XT29nRwEtTKPqiVPdi5Tp13QE5Fj9zi+bG0tDRlZmZq3759kiS32622tjY1NDQE7aLU19drzJgx3Y7hcrnkcrm6tDudzh4rjq/DIV97eAOK3X6Q7KAnfwYQXtTKPqiVPdixTqHMt8f/Dsq3336rgwcPKi0tTZKUk5Mjp9MZtDVVW1ur6urqEwYUAADQt4S8g9Lc3KzPP/88cFxTU6M9e/YoMTFRiYmJ8ng8uvXWW5WWlqb9+/dr0aJFSk5O1i233CJJSkhI0MyZMzVv3jwlJSUpMTFR8+fP17BhwwKf6gEAAH1byAFl9+7dGjduXOC4870h99xzj9asWaOqqiq9/PLLOnz4sNLS0jRu3Dht3LhRcXFxgeesXLlSkZGRmjZtmlpbW5WXl6eSkhJFRESEYUkAAMDuQg4oubm5sqwTfwT33Xff/ckxoqKiVFxcrOLi4lAvDwAA+gC+iwcAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGCfkgLJjxw5NnjxZ6enpcjgcev3114POW5Ylj8ej9PR0RUdHKzc3V3v37g3q4/P5NGfOHCUnJys2NlZTpkzRoUOHzmghAADg3BFyQDl69Kguv/xyrV69utvzK1as0NNPP63Vq1dr165dcrvdys/P15EjRwJ9CgsLtWnTJpWVlWnnzp1qbm7WpEmT1N7efvorAQAA54zIUJ8wceJETZw4sdtzlmVp1apVWrx4saZOnSpJeumll5SamqrS0lLdf//9amxs1Nq1a7V+/XqNHz9ekrRhwwZlZGRo69atmjBhwhksBwAAnAvC+h6Umpoa1dXVqaCgINDmcrk0duxYVVRUSJIqKyvl9/uD+qSnpys7OzvQBwAA9G0h76CcTF1dnSQpNTU1qD01NVUHDhwI9Onfv78GDRrUpU/n84/n8/nk8/kCx01NTZIkv98vv98ftvl3jilJrn5WWMf98dg4c52vJa+p+aiVfVAre7BznUKZc1gDSieHwxF0bFlWl7bjnaxPUVGRlixZ0qW9vLxcMTExpz/Rk/jtiI6wj7l58+awj9nXeb3e3p4CThG1sg9qZQ92rFNLS8sp9w1rQHG73ZJ+2CVJS0sLtNfX1wd2Vdxut9ra2tTQ0BC0i1JfX68xY8Z0O+7ChQs1d+7cwHFTU5MyMjJUUFCg+Pj4cC5Bfr9fXq9Xj+/uJ1/HyUNVqKo9vL8mXDrrlJ+fL6fT2dvTwUlQK/ugVvZg5zp13gE5FWENKFlZWXK73fJ6vbriiiskSW1tbdq+fbt+97vfSZJycnLkdDrl9Xo1bdo0SVJtba2qq6u1YsWKbsd1uVxyuVxd2p1OZ48Vx9fhkK89vAHFbj9IdtCTPwMIL2plH9TKHuxYp1DmG3JAaW5u1ueffx44rqmp0Z49e5SYmKghQ4aosLBQy5Yt09ChQzV06FAtW7ZMMTExmj59uiQpISFBM2fO1Lx585SUlKTExETNnz9fw4YNC3yqBwAA9G0hB5Tdu3dr3LhxgePOWy/33HOPSkpKtGDBArW2tmrWrFlqaGjQyJEjVV5erri4uMBzVq5cqcjISE2bNk2tra3Ky8tTSUmJIiIiwrAkAABgdyEHlNzcXFnWiT/h4nA45PF45PF4TtgnKipKxcXFKi4uDvXyAACgD+C7eAAAgHF65GPG6N75j73dY2PvX35jj40NAMDZxg4KAAAwDgEFAAAYh1s85whuHwEAziXsoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxInt7AjDf+Y+93SPj7l9+Y4+MCwCwP3ZQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4YQ8oHo9HDocj6OF2uwPnLcuSx+NRenq6oqOjlZubq71794Z7GgAAwMZ6ZAflsssuU21tbeBRVVUVOLdixQo9/fTTWr16tXbt2iW32638/HwdOXKkJ6YCAABsqEcCSmRkpNxud+Bx3nnnSfph92TVqlVavHixpk6dquzsbL300ktqaWlRaWlpT0wFAADYUI98m/G+ffuUnp4ul8ulkSNHatmyZbrgggtUU1Ojuro6FRQUBPq6XC6NHTtWFRUVuv/++7sdz+fzyefzBY6bmpokSX6/X36/P6xz7xzP1c8K67jo6q8W/8dpP9fVz9JvR0g5T2yRr8PR5Xy1Z8KZTA1h1Pk7Fe7fVYQftbIHO9cplDk7LMsK67/E77zzjlpaWnTRRRfp66+/1pNPPqn/+Z//0d69e/XZZ5/p6quv1pdffqn09PTAc/7+7/9eBw4c0LvvvtvtmB6PR0uWLOnSXlpaqpiYmHBOHwAA9JCWlhZNnz5djY2Nio+PP2nfsAeU4x09elQXXnihFixYoFGjRunqq6/WV199pbS0tECf++67TwcPHtSWLVu6HaO7HZSMjAx98803P7nAUPn9fnm9Xj2+u1+3/2cOM/ywg9Jxwjqxg2KOzt+p/Px8OZ3O3p4OToJa2YOd69TU1KTk5ORTCig9covnx2JjYzVs2DDt27dPN998sySprq4uKKDU19crNTX1hGO4XC65XK4u7U6ns8eK4+twyNdOQDHdiepkt1/avqAnf18RXtTKHuxYp1Dm2+N/B8Xn8+m///u/lZaWpqysLLndbnm93sD5trY2bd++XWPGjOnpqQAAAJsI+w7K/PnzNXnyZA0ZMkT19fV68skn1dTUpHvuuUcOh0OFhYVatmyZhg4dqqFDh2rZsmWKiYnR9OnTwz0VAABgU2EPKIcOHdIdd9yhb775Ruedd55GjRqlDz/8UJmZmZKkBQsWqLW1VbNmzVJDQ4NGjhyp8vJyxcXFhXsqAADApsIeUMrKyk563uFwyOPxyOPxhPvSAADgHMF38QAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMA4BBQAAGIeAAgAAjENAAQAAxiGgAAAA4xBQAACAcQgoAADAOAQUAABgHAIKAAAwDgEFAAAYh4ACAACMQ0ABAADGIaAAAADjEFAAAIBxCCgAAMA4BBQAAGAcAgoAADBOZG9PAOgJ5z/2do+Mu3/5jT0yLgAgGAEFCEFPBR+J8AMAP8YtHgAAYBwCCgAAMA4BBQAAGIeAAgAAjMObZAFD8MkjAPj/2EEBAADGIaAAAADjEFAAAIBxeA8KgD6F9/oA9sAOCgAAME6vBpRnn31WWVlZioqKUk5Ojj744IPenA4AADBEr93i2bhxowoLC/Xss8/q6quv1vPPP6+JEyfq008/1ZAhQ3prWsA5pye/P+hUuCIsrbhKyva8K1+745SeY8fbJXxPExBevbaD8vTTT2vmzJn61a9+pUsuuUSrVq1SRkaG1qxZ01tTAgAAhuiVHZS2tjZVVlbqscceC2ovKChQRUVFb0wJgEF6e9cHQO/rlYDyzTffqL29XampqUHtqampqqur69Lf5/PJ5/MFjhsbGyVJ3333nfx+f1jn5vf71dLSokh/P7V3nNp2NM6+yA5LLS0d1MkGqNWZ+/n8/3NWruPqZ+kfr+jQXy9+Tb4zrNWfF+aFaVZdjSx6r8fG7inhfD06/5369ttvdc0/7wjbuMfriRoeOXJEkmRZ1k/27dWPGTscwb8AlmV1aZOkoqIiLVmypEt7VlZWj80N5pve2xPAKaNW9hGuWiU/FaaBzhF2fD16cs5HjhxRQkLCSfv0SkBJTk5WREREl92S+vr6LrsqkrRw4ULNnTs3cNzR0aHvvvtOSUlJ3QaaM9HU1KSMjAwdPHhQ8fHxYR0b4UOd7INa2Qe1sgc718myLB05ckTp6ek/2bdXAkr//v2Vk5Mjr9erW265JdDu9Xp10003denvcrnkcrmC2gYOHNijc4yPj7dd4fsi6mQf1Mo+qJU92LVOP7Vz0qnXbvHMnTtXd999t0aMGKHRo0frhRde0BdffKEHHnigt6YEAAAM0WsB5fbbb9e3336rJ554QrW1tcrOztbmzZuVmZnZW1MCAACG6NU3yc6aNUuzZs3qzSl04XK59Jvf/KbLLSWYhTrZB7WyD2plD32lTg7rVD7rAwAAcBbxZYEAAMA4BBQAAGAcAgoAADAOAQUAABiHgPIjzz77rLKyshQVFaWcnBx98MEHvT2lPqWoqEhXXnml4uLilJKSoptvvlmfffZZUB/LsuTxeJSenq7o6Gjl5uZq7969QX18Pp/mzJmj5ORkxcbGasqUKTp06NDZXEqfUlRUJIfDocLCwkAbdTLHl19+qbvuuktJSUmKiYnRX//1X6uysjJwnlqZ4dixY/rHf/xHZWVlKTo6WhdccIGeeOIJdXR0BPr0uVpZsCzLssrKyiyn02m9+OKL1qeffmo9/PDDVmxsrHXgwIHenlqfMWHCBGvdunVWdXW1tWfPHuvGG2+0hgwZYjU3Nwf6LF++3IqLi7NeffVVq6qqyrr99tuttLQ0q6mpKdDngQcesH72s59ZXq/X+vjjj61x48ZZl19+uXXs2LHeWNY57aOPPrLOP/98a/jw4dbDDz8caKdOZvjuu++szMxMa8aMGdaf//xnq6amxtq6dav1+eefB/pQKzM8+eSTVlJSkvUf//EfVk1NjfXKK69YAwYMsFatWhXo09dqRUD5f6666irrgQceCGq7+OKLrccee6yXZoT6+npLkrV9+3bLsiyro6PDcrvd1vLlywN9vv/+eyshIcF67rnnLMuyrMOHD1tOp9MqKysL9Pnyyy+tfv36WVu2bDm7CzjHHTlyxBo6dKjl9XqtsWPHBgIKdTLHo48+al1zzTUnPE+tzHHjjTdav/zlL4Papk6dat11112WZfXNWnGLR1JbW5sqKytVUFAQ1F5QUKCKiopemhUaGxslSYmJiZKkmpoa1dXVBdXJ5XJp7NixgTpVVlbK7/cH9UlPT1d2dja1DLMHH3xQN954o8aPHx/UTp3M8eabb2rEiBG67bbblJKSoiuuuEIvvvhi4Dy1Msc111yj9957T3/5y18kSf/1X/+lnTt36oYbbpDUN2vVq39J1hTffPON2tvbu3yTcmpqapdvXMbZYVmW5s6dq2uuuUbZ2dmSFKhFd3U6cOBAoE///v01aNCgLn2oZfiUlZXp448/1q5du7qco07m+N///V+tWbNGc+fO1aJFi/TRRx/poYceksvl0i9+8QtqZZBHH31UjY2NuvjiixUREaH29nYtXbpUd9xxh6S++XtFQPkRh8MRdGxZVpc2nB2zZ8/WJ598op07d3Y5dzp1opbhc/DgQT388MMqLy9XVFTUCftRp97X0dGhESNGaNmyZZKkK664Qnv37tWaNWv0i1/8ItCPWvW+jRs3asOGDSotLdVll12mPXv2qLCwUOnp6brnnnsC/fpSrbjFIyk5OVkRERFdEmZ9fX2XtIqeN2fOHL355pv64x//qMGDBwfa3W63JJ20Tm63W21tbWpoaDhhH5yZyspK1dfXKycnR5GRkYqMjNT27dv1zDPPKDIyMvA6U6fel5aWpksvvTSo7ZJLLtEXX3whid8pk/zDP/yDHnvsMf3d3/2dhg0bprvvvluPPPKIioqKJPXNWhFQJPXv3185OTnyer1B7V6vV2PGjOmlWfU9lmVp9uzZeu211/T+++8rKysr6HxWVpbcbndQndra2rR9+/ZAnXJycuR0OoP61NbWqrq6mlqGSV5enqqqqrRnz57AY8SIEbrzzju1Z88eXXDBBdTJEFdffXWXj+r/5S9/CXxrPL9T5mhpaVG/fsH/JEdERAQ+Ztwna9VLb841TufHjNeuXWt9+umnVmFhoRUbG2vt37+/t6fWZ/z617+2EhISrG3btlm1tbWBR0tLS6DP8uXLrYSEBOu1116zqqqqrDvuuKPbj9kNHjzY2rp1q/Xxxx9b1113nW0/ZmcXP/4Uj2VRJ1N89NFHVmRkpLV06VJr37591r/9279ZMTEx1oYNGwJ9qJUZ7rnnHutnP/tZ4GPGr732mpWcnGwtWLAg0Kev1YqA8iN/+MMfrMzMTKt///7W3/zN3wQ+3oqzQ1K3j3Xr1gX6dHR0WL/5zW8st9ttuVwu69prr7WqqqqCxmltbbVmz55tJSYmWtHR0dakSZOsL7744iyvpm85PqBQJ3O89dZbVnZ2tuVyuayLL77YeuGFF4LOUyszNDU1WQ8//LA1ZMgQKyoqyrrgggusxYsXWz6fL9Cnr9XKYVmW1Zs7OAAAAMfjPSgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUADYxv79++VwOLRnzx5J0rZt2+RwOHT48OFenReA8COgADgjM2bM0M0339wr1x4zZoxqa2uVkJDQK9cH0HMie3sCAHC6+vfvH/iWVwDnFnZQAIRNbm6uHnroIS1YsECJiYlyu93yeDxBfTwej4YMGSKXy6X09HQ99NBDgXMOh0Ovv/56UP+BAweqpKSk2+sdf4unpKREAwcO1LvvvqtLLrlEAwYM0PXXX6/a2towrhLA2UBAARBWL730kmJjY/XnP/9ZK1as0BNPPBH4+vd///d/18qVK/X8889r3759ev311zVs2LCwXr+lpUX//M//rPXr12vHjh364osvNH/+/LBeA0DP4xYPgLAaPny4fvOb30iShg4dqtWrV+u9995Tfn6+vvjiC7ndbo0fP15Op1NDhgzRVVddFdbr+/1+Pffcc7rwwgslSbNnz9YTTzwR1msA6HnsoAAIq+HDhwcdp6Wlqb6+XpJ02223qbW1VRdccIHuu+8+bdq0SceOHQvr9WNiYgLh5PjrA7APAgqAsHI6nUHHDodDHR0dkqSMjAx99tln+sMf/qDo6GjNmjVL1157rfx+f6CvZVlBz+88dybXP35MAOYjoAA4q6KjozVlyhQ988wz2rZtm/70pz+pqqpKknTeeecFvaF13759amlp6a2pAuhFvAcFwFlTUlKi9vZ2jRw5UjExMVq/fr2io6OVmZkpSbruuuu0evVqjRo1Sh0dHXr00Ue77IgA6BvYQQFw1gwcOFAvvviirr76ag0fPlzvvfee3nrrLSUlJUmSnnrqKWVkZOjaa6/V9OnTNX/+fMXExPTyrAH0BofFzVkAAGAYdlAAAIBxCCgAAMA4BBQAAGAcAgoAADAOAQUAABiHgAIAAIxDQAEAAMYhoAAAAOMQUAAAgHEIKAAAwDgEFAAAYBwCCgAAMM7/BRp0aFbtCmQxAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean     31.993\n",
      "std       7.884\n",
      "min       0.000\n",
      "5%       21.800\n",
      "10%      23.600\n",
      "20%      25.900\n",
      "30%      28.200\n",
      "40%      30.100\n",
      "50%      32.000\n",
      "60%      33.700\n",
      "70%      35.490\n",
      "80%      37.800\n",
      "90%      41.500\n",
      "95%      44.395\n",
      "99%      50.759\n",
      "max      67.100\n",
      "Name: BMI, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean      0.472\n",
      "std       0.331\n",
      "min       0.078\n",
      "5%        0.140\n",
      "10%       0.165\n",
      "20%       0.219\n",
      "30%       0.259\n",
      "40%       0.303\n",
      "50%       0.372\n",
      "60%       0.454\n",
      "70%       0.564\n",
      "80%       0.687\n",
      "90%       0.879\n",
      "95%       1.133\n",
      "99%       1.698\n",
      "max       2.420\n",
      "Name: DiabetesPedigreeFunction, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   768.000\n",
      "mean     33.241\n",
      "std      11.760\n",
      "min      21.000\n",
      "5%       21.000\n",
      "10%      22.000\n",
      "20%      23.000\n",
      "30%      25.000\n",
      "40%      27.000\n",
      "50%      29.000\n",
      "60%      33.000\n",
      "70%      38.000\n",
      "80%      42.600\n",
      "90%      51.000\n",
      "95%      58.000\n",
      "99%      67.000\n",
      "max      81.000\n",
      "Name: Age, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for col in num_cols:\n",
    "    num_summary(df, col, plot=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Numerical Features vs Target Feature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         Pregnancies\n",
      "Outcome             \n",
      "0              3.298\n",
      "1              4.866\n",
      "\n",
      "\n",
      "         Glucose\n",
      "Outcome         \n",
      "0        109.980\n",
      "1        141.257\n",
      "\n",
      "\n",
      "         BloodPressure\n",
      "Outcome               \n",
      "0               68.184\n",
      "1               70.825\n",
      "\n",
      "\n",
      "         SkinThickness\n",
      "Outcome               \n",
      "0               19.664\n",
      "1               22.164\n",
      "\n",
      "\n",
      "         Insulin\n",
      "Outcome         \n",
      "0         68.792\n",
      "1        100.336\n",
      "\n",
      "\n",
      "           BMI\n",
      "Outcome       \n",
      "0       30.304\n",
      "1       35.143\n",
      "\n",
      "\n",
      "         DiabetesPedigreeFunction\n",
      "Outcome                          \n",
      "0                           0.430\n",
      "1                           0.550\n",
      "\n",
      "\n",
      "           Age\n",
      "Outcome       \n",
      "0       31.190\n",
      "1       37.067\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for col in num_cols:\n",
    "    target_summary_with_num(df, \"Outcome\", col)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Correlation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABJsAAARPCAYAAAC4WOAkAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd3hT1QPG8TcddDC6yx5llb3KRjaUqaBMkaWAIAg/QFArIqAoDhSUKQqi4kBEEKEKyJIplL1kQxktpYNNC23z+6OSGpqyTFtu/X6eJw/05Nybc09vmuTNOeeazGazWQAAAAAAAIAdOGR1AwAAAAAAAJB9EDYBAAAAAADAbgibAAAAAAAAYDeETQAAAAAAALAbwiYAAAAAAADYDWETAAAAAAAA7IawCQAAAAAAAHZD2AQAAAAAAAC7IWwCAAAAAACA3TxU2LRnzx49++yzCggIkKurq3LlyqVq1arp/fffV2xsrL3b+K+sXbtWJpNJa9eufeBtDxw4oLFjx+rkyZNp7uvdu7eKFSv2r9v3MEwmk9UtZ86cKlu2rMaNG6dr16491D43bdqksWPH6uLFi/Zt7COkWLFiafru9u3q1asZ8pjTp0/X3LlzM2TfAAAAAAA8ipwedIPPPvtMAwcOVGBgoEaOHKly5crp1q1bCgsL08yZM7V582YtWrQoI9qa6Q4cOKBx48apUaNGaYKl0aNH63//+1/WNExSx44d9dJLL0mSrl69qnXr1unNN9/Unj17tHDhwgfe36ZNmzRu3Dj17t1bnp6edm7to6NevXqaOHFimnJ3d/cMebzp06fL19dXvXv3zpD9AwAAAADwqHmgsGnz5s164YUX1Lx5cy1evFguLi6W+5o3b66XXnpJv/32m10adv36dZsBQFJSkhITE60eOyuUKFEiSx8/b968ql27tuXnZs2a6dSpU/rmm28UHx8vV1fXLGzdo8vT09Oq34wqvecHAAAAAABZ7YGm0b3zzjsymUyaNWuWzbAnR44ceuKJJyw/Jycn6/3331eZMmXk4uIif39/9ezZU2fOnLHarlGjRqpQoYL++OMP1a1bV+7u7nruued08uRJmUwmvf/++xo/frwCAgLk4uKiNWvWSJLCwsL0xBNPyNvbW66urqpatap++OGHex5HWFiYunbtqmLFisnNzU3FihXT008/rVOnTlnqzJ07V506dZIkNW7c2DLd6vaUKFvT6OLj4xUSEqKAgADlyJFDBQsW1KBBg9JMTStWrJjatm2r3377TdWqVZObm5vKlCmjOXPm3LPtd+Ph4SGTySRHR0er8t9//11NmzZVnjx55O7urnr16mnVqlWW+8eOHauRI0dKkgICAizHunbtWo0cOVIeHh5KSkqy1B88eLBMJpM++OADS1lMTIwcHBw0ZcoUS9nly5c1YsQIq/4YOnRomql+ZrNZ06dPV5UqVeTm5iYvLy917NhRx48ft6p3+zzZtm2b6tevL3d3dxUvXlzvvvuukpOT/1Xf3RYZGan+/furUKFCypEjhwICAjRu3DglJiZa1Rs3bpxq1aolb29v5cmTR9WqVdPs2bNlNpstdYoVK6b9+/dr3bp1lj69fc7MnTtXJpMpzRRNW9M+03t+SPffxwsWLFCtWrXk4eFh6bfb+wAAAAAAwJ7ue2RTUlKSVq9eraCgIBUuXPi+tnnhhRc0a9Ysvfjii2rbtq1Onjyp0aNHa+3atdqxY4d8fX0tdSMiItS9e3e9/PLLeuedd+TgkJqDffLJJypdurQmTpyoPHnyqFSpUlqzZo1atmypWrVqaebMmfLw8ND333+vLl266Pr163edtnTy5EkFBgaqa9eu8vb2VkREhGbMmKEaNWrowIED8vX1VZs2bfTOO+/otdde07Rp01StWjVJ6Y9oMpvNat++vVatWqWQkBDVr19fe/bs0ZgxY7R582Zt3rzZKqDbvXu3XnrpJb366qvKmzevPv/8c/Xp00clS5ZUgwYN7tm3ZrPZEoDcnkb35ZdfqmvXrnJ2drbUmzdvnnr27Kl27drpyy+/lLOzsz799FO1aNFCy5cvV9OmTdW3b1/FxsZqypQp+umnn5Q/f35JUrly5ZSQkKCJEydq69atqlOnjqSU8MrNzU0rV660hFSrVq2S2WxWs2bNJKWMvGnYsKHOnDmj1157TZUqVdL+/fv1xhtvaO/evfr9999lMpkkSf3799fcuXM1ZMgQvffee4qNjdWbb76punXravfu3cqbN6/leCIjI/XMM8/opZde0pgxY7Ro0SKFhISoQIEC6tmz5wP1220ODg5ycHBQZGSkatasKQcHB73xxhsqUaKENm/erPHjx+vkyZP64osvLNucPHlS/fv3V5EiRSRJW7Zs0eDBg3X27Fm98cYbkqRFixapY8eO8vDw0PTp0yXpoUfk2Xp+3G8fb968WV26dFGXLl00duxYubq66tSpU1q9evVDtQUAAAAAgLsy36fIyEizJHPXrl3vq/7BgwfNkswDBw60Kv/zzz/Nksyvvfaapaxhw4ZmSeZVq1ZZ1T1x4oRZkrlEiRLmmzdvWt1XpkwZc9WqVc23bt2yKm/btq05f/785qSkJLPZbDavWbPGLMm8Zs2adNuamJhovnr1qjlnzpzmjz/+2FK+YMGCdLft1auXuWjRopaff/vtN7Mk8/vvv29Vb/78+WZJ5lmzZlnKihYtanZ1dTWfOnXKUnbjxg2zt7e3uX///um28zZJNm+tWrUyX7161VLv2rVrZm9vb/Pjjz9utX1SUpK5cuXK5po1a1rKPvjgA7Mk84kTJ6zqXrt2zZwjRw7zm2++aTabzeYzZ86YJZlfeeUVs5ubmzk+Pt5sNpvN/fr1MxcoUMCy3YQJE8wODg7mbdu2We3vxx9/NEsyh4aGms1ms3nz5s1mSeYPP/zQqt7p06fNbm5u5pdfftlSdvs8+fPPP63qlitXztyiRYt79lvRokVt9tuoUaPMZrPZ3L9/f3OuXLmsfi9ms9k8ceJEsyTz/v37be43KSnJfOvWLfObb75p9vHxMScnJ1vuK1++vLlhw4Zptvniiy9s9ret8zW958f99vHt9l+8ePGu/QMAAAAAgD081NXo7sftqW53jjCqWbOmypYtazWNS5K8vLzUpEkTm/t64oknrEbrHD16VH/99ZeeeeYZSVJiYqLl1rp1a0VEROjQoUPptu3q1at65ZVXVLJkSTk5OcnJyUm5cuXStWvXdPDgwYc5XMsokTuPt1OnTsqZM2ea461SpYplVIwkubq6qnTp0lZT+e6mc+fO2rZtm7Zt26Y//vhDn3zyicLCwtSyZUslJCRISln0OzY2Vr169bLqo+TkZLVs2VLbtm2759Xr3N3dVadOHf3++++SpJUrV8rT01MjR47UzZs3tWHDBkkpo51uj2qSpKVLl6pChQqqUqWK1WO3aNHCaprY0qVLZTKZ1L17d6t6+fLlU+XKldNcRTBfvnyqWbOmVVmlSpXuu98ee+wxS7/dvg0cONDSlsaNG6tAgQJWbWnVqpUkad26dZb9rF69Ws2aNZOHh4ccHR3l7OysN954QzExMYqKirqvtjwIW8+P++3jGjVqSEo5Z3744QedPXvW7u0DAAAAAOC2+55G5+vrK3d3d504ceK+6sfExEiSZUrWPxUoUCBNOGCrXnr3nT9/XpI0YsQIjRgxwuY20dHR6e6vW7duWrVqlUaPHq0aNWooT548MplMat26tW7cuJHudncTExMjJycn+fn5WZWbTCbly5fP0h+3+fj4pNmHi4vLfT++n5+fqlevbvm5fv368vPz09NPP625c+eqf//+ln7q2LFjuvuJjY1Vzpw57/pYzZo101tvvaVr167p999/V5MmTeTj46OgoCD9/vvvKl68uE6cOKFx48ZZtjl//ryOHj1qFRL+0+3fz/nz52U2m62myv1T8eLFrX7+t/3m4eFh1W//dP78ef3yyy/3bPPWrVsVHBysRo0a6bPPPrOs77R48WK9/fbbD30O3Y2t58f99nGDBg20ePFiffLJJ+rZs6cSEhJUvnx5jRo1Sk8//bTd2woAAAAA+G+777DJ0dFRTZs21a+//qozZ86oUKFCd61/OxSIiIhIU/fcuXNW6zVJsqzfY8ud993eNiQkRE899ZTNbQIDA22WX7p0SUuXLtWYMWP06quvWsoTEhIUGxubbhvuxcfHR4mJibpw4YJV4GQ2mxUZGWkZXZKRKlWqJCllPSgptZ+mTJmS7hXY0gt5/qlp06YaPXq0/vjjD61atUpjxoyxlK9YsUIBAQGWn2/z9fWVm5tbuoue326br6+vTCaT1q9fb3M9o8y86qCvr68qVaqkt99+2+b9BQoUkCR9//33cnZ21tKlS62u+rd48eL7fqzb290ehXZbeiGprefH/faxJLVr107t2rVTQkKCtmzZogkTJqhbt24qVqyYZS0uAAAAAADs4b7DJikl3AkNDVW/fv30888/K0eOHFb337p1S7/99psef/xxy5SfefPmWQUt27Zt08GDBzVq1KiHbnRgYKBKlSql3bt365133nmgbU0mk8xmc5oQ4/PPP7e64pqUGnTcz0iVpk2b6v3339e8efM0bNgwS/nChQt17do1qyAmo+zatUuS5O/vL0mqV6+ePD09deDAAb344ot33fZux1qzZk3lyZNHkydPVmRkpJo3by4pZcTTe++9px9++EHlypWzhDGS1LZtW73zzjvy8fGxhFG2tG3bVu+++67Onj2rzp07P9Dx2lvbtm0VGhqqEiVKyMvLK916JpNJTk5OVlf9u3Hjhr7++us0ddMbdXX7qnR79uyxCkaXLFnyQO29nz6+sz0NGzaUp6enli9frp07dxI2AQAAAADs6oHCpjp16mjGjBkaOHCggoKC9MILL6h8+fK6deuWdu7cqVmzZqlChQp6/PHHFRgYqOeff15TpkyRg4ODWrVqZbkaXeHCha0CmYfx6aefqlWrVmrRooV69+6tggULKjY2VgcPHtSOHTu0YMECm9vlyZNHDRo00AcffCBfX18VK1ZM69at0+zZs+Xp6WlVt0KFCpKkWbNmKXfu3HJ1dVVAQIDNqVzNmzdXixYt9Morr+jy5cuqV6+e5Wp0VatWVY8ePf7V8d7p/Pnz2rJliyQpPj5eu3bt0vjx4+Xp6alnn31WkpQrVy5NmTJFvXr1UmxsrDp27Ch/f39duHBBu3fv1oULFzRjxgxJUsWKFSVJH3/8sXr16iVnZ2cFBgYqd+7ccnR0VMOGDfXLL78oICDAckW+evXqycXFRatWrdKQIUOs2jd06FAtXLhQDRo00LBhw1SpUiUlJycrPDxcK1as0EsvvaRatWqpXr16ev755/Xss88qLCxMDRo0UM6cORUREaENGzaoYsWKeuGFF+zad+l58803tXLlStWtW1dDhgxRYGCg4uPjdfLkSYWGhmrmzJkqVKiQ2rRpo48++kjdunXT888/r5iYGE2cONHmKKyKFSvq+++/1/z581W8eHG5urqqYsWKqlGjhgIDAzVixAglJibKy8tLixYtsqyBdT/ut4/feOMNnTlzRk2bNlWhQoV08eJFffzxx3J2dlbDhg3t2YUAAAAAANz/1ej+adeuXeZevXqZixQpYs6RI4c5Z86c5qpVq5rfeOMNc1RUlKVeUlKS+b333jOXLl3a7OzsbPb19TV3797dfPr0aav9NWzY0Fy+fPk0j3P7anQffPCBzXbs3r3b3LlzZ7O/v7/Z2dnZnC9fPnOTJk3MM2fOtNSxdXWvM2fOmDt06GD28vIy586d29yyZUvzvn37zEWLFjX36tXL6jEmT55sDggIMDs6Opolmb/44guz2Zz2anRmc8oV5V555RVz0aJFzc7Ozub8+fObX3jhBXNcXJxVvaJFi5rbtGmT5ngaNmxo88pld9IdV1NzdnY2Fy9e3Pzss8+ajx49mqb+unXrzG3atDF7e3ubnZ2dzQULFjS3adPGvGDBAqt6ISEh5gIFCpgdHBzS9NnHH39slmTu16+f1TbNmzc3SzIvWbIkzeNevXrV/Prrr5sDAwPNOXLkMHt4eJgrVqxoHjZsmDkyMtKq7pw5c8y1atUy58yZ0+zm5mYuUaKEuWfPnuawsDCr/rF1ntj6XdiSXr//04ULF8xDhgwxBwQEmJ2dnc3e3t7moKAg86hRo6yu9DdnzhxzYGCg2cXFxVy8eHHzhAkTzLNnz05zhbmTJ0+ag4ODzblz5zZLsmrn4cOHzcHBweY8efKY/fz8zIMHDzYvW7bM5tXobB232Xx/fbx06VJzq1atzAULFjTnyJHD7O/vb27durV5/fr19+wzAAAAAAAelMlsNpuzJOUCAAAAAABAtuOQ1Q0AAAAAAABA9kHYBAAAAAAAALshbAIAAAAAAIDdEDbBUP744w89/vjjKlCggEwmkxYvXnzPbdatW6egoCC5urqqePHimjlzZsY3FAAAAACA/yjCJhjKtWvXVLlyZU2dOvW+6p84cUKtW7dW/fr1tXPnTr322msaMmSIFi5cmMEtBQAAAADgv4mr0cGwTCaTFi1apPbt26db55VXXtGSJUt08OBBS9mAAQO0e/dubd68ORNaCQAAAADAfwsjm5DlEhISdPnyZatbQkKCXfa9efNmBQcHW5W1aNFCYWFhunXrll0eAwAAAAAApHLK6gbg/iRHls7qJmSYCTO7ady4cVZlY8aM0dixY//1viMjI5U3b16rsrx58yoxMVHR0dHKnz//v34MAAAAAACQirDJIJKVnNVNyDAhISEaPny4VZmLi4vd9m8ymax+vj1z9M5yAMYREhKi+Pj4rG4GAINwdXXVhAkTsroZAAD8ZxA2GcQtc1JWNyHDuLm42DVc+qd8+fIpMjLSqiwqKkpOTk7y8fHJkMcEkPHi4+M1adKkrG4GAIMYNmxYVjcBAID/FMImg8jOI5syUp06dfTLL79Yla1YsULVq1eXs7NzFrUKAAAAAIDsi7DJIJK4aKAk6erVqzp69Kjl5xMnTmjXrl3y9vZWkSJFFBISorNnz+qrr76SlHLlualTp2r48OHq16+fNm/erNmzZ+u7777LqkMAAAAAACBbI2wyiFuMbJIkhYWFqXHjxpafb6/11KtXL82dO1cREREKDw+33B8QEKDQ0FANGzZM06ZNU4ECBfTJJ5+oQ4cOmd52AAAAAAD+CwibDCJZjGySpEaNGlkW+LZl7ty5acoaNmyoHTt2ZGCrAAAAAADAbYRNBsE0OgAAAAAAYASETQbBJDoAAAAAAGAEhE0GcZORTQAAAAAAwAAImwyCkU0AAAAAAMAICJsMIkmmrG4CAAAAAADAPRE2GcQtM2ETAAAAAAB49BE2GQQjmwAAAAAAgBEQNhlEMiObAAAAAACAARA2GcRNOWZ1EwAAAAAAAO6JsMkgGNkEAAAAAACMgLDJIFizCQAAAAAAGAFhk0EkmR2yugkAAAAAAAD3RNhkELdYswkAAAAAABgAYZNBMLIJAAAAAAAYAWGTQSSzZhMAALAhJCRE8fHxWd2MR1pUVJSGDRuW1c14pLm6umrChAlZ3QwAQDZB2GQQN838qoDsiA+JD4cPjg+HD5PZU3x8vCZNmpTVzYDB8TcVAGBPJBgGkSym0QHZER8SkZn4MAkAAIDMQNhkEElmptEBAAAAAIBHH2GTQSQxsgkAAAAAABgAYZNB3GLNJgAAALthzTxrrIVnjTXuAODfIcEwCKbRAQAA2A9r5uFuCN4A4N8hbDIIFggHAAAAAABGQNhkELfMjlndBAAAAAAAgHsibDKIJDMjmwAAAAAAwKOPBMMgkuSQbW8PY/r06QoICJCrq6uCgoK0fv36u9b/5ptvVLlyZbm7uyt//vx69tlnFRMT81CPDQAAAAAA0kfYZBC3zI7Z9vag5s+fr6FDh2rUqFHauXOn6tevr1atWik8PNxm/Q0bNqhnz57q06eP9u/frwULFmjbtm3q27fvv/21AAAAAACAOxA2GUSy2SHb3h7URx99pD59+qhv374qW7asJk+erMKFC2vGjBk262/ZskXFihXTkCFDFBAQoMcee0z9+/dXWFjYv/21AAAAAACAOxA2GUSSTNn29iBu3ryp7du3Kzg42Ko8ODhYmzZtsrlN3bp1debMGYWGhspsNuv8+fP68ccf1aZNm4f+fQAAAAAAANtYINwgHmYEkFEkJCQoISHBqszFxUUuLi5p6kZHRyspKUl58+a1Ks+bN68iIyNt7r9u3br65ptv1KVLF8XHxysxMVFPPPGEpkyZYr+DAAAAAAAAkhjZZBhZva5SRt4mTJggDw8Pq9uECRPu2h8mk/WIKLPZnKbstgMHDmjIkCF64403tH37dv322286ceKEBgwYYLffDwAAAAAASMHIJoNIysYjm0JCQjR8+HCrMlujmiTJ19dXjo6OaUYxRUVFpRntdNuECRNUr149jRw5UpJUqVIl5cyZU/Xr19f48eOVP39+OxwFAAAAAACQCJsMI/kB1zYykvSmzNmSI0cOBQUFaeXKlXryySct5StXrlS7du1sbnP9+nU5OVmf6o6OKVfBM5vND9lqAAAAAABgC2GTQdxKdszqJjwyhg8frh49eqh69eqqU6eOZs2apfDwcMu0uJCQEJ09e1ZfffWVJOnxxx9Xv379NGPGDLVo0UIREREaOnSoatasqQIFCmTloQAAAAAAkO0QNhlEEstrWXTp0kUxMTF68803FRERoQoVKig0NFRFixaVJEVERCg8PNxSv3fv3rpy5YqmTp2ql156SZ6enmrSpInee++9rDoEAAAAAACyLcImg0g2Z99pdA9j4MCBGjhwoM375s6dm6Zs8ODBGjx4cAa3CgAAAAAAEDYZRDIjmwAAAAAAgAEQNhnErWTCJgAAAAAA8OgjbDKIZDNhEwAAAAAAePQRNhlEklizCQAAAAAAPPoImwwiMdkxq5sAAACA/7iQkBDFx8dndTMyXFRUlIYNG5bVzcgUrq6umjBhQlY3A0A2Q9hkEMmMbAIAAEAWi4+P16RJk7K6GbCj/0qoBiBzETYZRJKZsAkAAAAAADz6CJsMgml0AAAAAADACAibDIJpdAAAAAAAwAgImwwimWl0AAAAAADAAAibDCLZ7JDVTQAAAAAAALgnwiaDSCRsAgAAAAAABkDYZBBMowMAAAAAAEZA2GQQhE0AAAAAAMAICJsMIjGZaXQAAAAAAODRR9hkEMliZBMAAAAAAHj0ETYZBNPoAAAAAACAERA2GQRhEwAAAAAAMALCJoNgzSYAAAAAAGAEhE0GYWZkEwAAAAAAMADCJoNggXAAAAAAAGAEhE0GkcQ0OgAAAAAAYACETQbBAuEAAAAAAMAICJsMgjWbAAAAAACAERA2GQQjmwAAAAAAgBGwEJBBJJlN2fb2MKZPn66AgAC5uroqKChI69evv2v9hIQEjRo1SkWLFpWLi4tKlCihOXPmPNRjAwAAAACA9DGyySCYRpdq/vz5Gjp0qKZPn6569erp008/VatWrXTgwAEVKVLE5jadO3fW+fPnNXv2bJUsWVJRUVFKTEzM5JYDAADgvygkJETx8fFZ3QyboqKiNGzYsKxuhk2urq6aMGFCVjcDwEMgbDIIptGl+uijj9SnTx/17dtXkjR58mQtX75cM2bMsPli9Ntvv2ndunU6fvy4vL29JUnFihXLzCYDAADgPyw+Pl6TJk3K6mYYzqMaggG4N6bRGURysinb3hISEnT58mWrW0JCgs1+uHnzprZv367g4GCr8uDgYG3atMnmNkuWLFH16tX1/vvvq2DBgipdurRGjBihGzdu2P33BAAAAADAfx1hk0GYzaZse5swYYI8PDysbukNl42OjlZSUpLy5s1rVZ43b15FRkba3Ob48ePasGGD9u3bp0WLFmny5Mn68ccfNWjQILv/ngAAAAAA+K9jGp1BZOdpdCEhIRo+fLhVmYuLy123MZms+8NsNqcpuy05OVkmk0nffPONPDw8JKVMxevYsaOmTZsmNze3f9F6AAAAAADwT4RNBpGcnH3DJhcXl3uGS7f5+vrK0dExzSimqKioNKOdbsufP78KFixoCZokqWzZsjKbzTpz5oxKlSr18I0HAAAAAABWmEZnEFk91S0jbw8iR44cCgoK0sqVK63KV65cqbp169rcpl69ejp37pyuXr1qKTt8+LAcHBxUqFChB/9lAAAAAACAdBE2GYQ5G98e1PDhw/X5559rzpw5OnjwoIYNG6bw8HANGDBAUsq0vJ49e1rqd+vWTT4+Pnr22Wd14MAB/fHHHxo5cqSee+45ptABAAAAAGBnTKMziAcdAZSddenSRTExMXrzzTcVERGhChUqKDQ0VEWLFpUkRUREKDw83FI/V65cWrlypQYPHqzq1avLx8dHnTt31vjx47PqEAAAAAAAyLYImwzCnI3XbHoYAwcO1MCBA23eN3fu3DRlZcqUSTP1DgAyQkhIiOLj47O6GTZFRUVp2LBhWd0Mm1xdXdO9EikAAACMhbDJIMwPM98MAJDp4uPjNWnSpKxuhuE8qiEYAAAAHhxhk0EwjQ4AAAAAABgBYZNBMI0OAAAAAAAYAWGTUTCNDgAAAAAAGABhk0EwjQ4AAAAAABgBYZNRMLIJAAAAAAAYAGGTQbBmEwAAAAAAMALCJsMgbAIAAAAAAI8+wiajYBodAAAAAAAwAMImo2AaHQAAAAAAMADCJoMwM7IJAAAAAAAYAGGTURA2AQAAAAAAAyBsMggT0+gAAAAAAIABEDYZBSObgIcWEhKi+Pj4rG6GTVFRURo2bFhWN8MmV1dXTZgwIaubAQAAAMBgCJuMwszIJuBhxcfHa9KkSVndDMN5VEMwAAAAAI82wiajYGQTAAAAAAAwAMImo0jO6gYAAAAAAADcG2GTUTCNDgAAAAAAGABhk0GYmEYHAAAAAAAMgLDJKAibAAAAAACAARA2GQQjmwAAAAAAgBEQNhkFazYBAAAAAAADIGwyCkY2AQAAAAAAAyBsMghTcla3AAAAAAAA4N4csroBuE/mbHx7CNOnT1dAQIBcXV0VFBSk9evX39d2GzdulJOTk6pUqfJwDwwAAAAAAO6KsMkosjoQeoTCpvnz52vo0KEaNWqUdu7cqfr166tVq1YKDw+/63aXLl1Sz5491bRp0wd/UAAAAAAAcF8ImwzClGzKtrcH9dFHH6lPnz7q27evypYtq8mTJ6tw4cKaMWPGXbfr37+/unXrpjp16jzsrwEAAAAAANwDYZNRZPXoo0dkZNPNmze1fft2BQcHW5UHBwdr06ZN6W73xRdf6NixYxozZsyDPSAAAAAAAHggLBBuEKaHXNvICBISEpSQkGBV5uLiIhcXlzR1o6OjlZSUpLx581qV582bV5GRkTb3f+TIEb366qtav369nJw45QEAAAAAyEiMbDKKrB59lIG3CRMmyMPDw+o2YcKEu3aHyWQ9/c5sNqcpk6SkpCR169ZN48aNU+nSpe+6TwAAAAAA8O8xzMMgTMlZ3YKMExISouHDh1uV2RrVJEm+vr5ydHRMM4opKioqzWgnSbpy5YrCwsK0c+dOvfjii5Kk5ORkmc1mOTk5acWKFWrSpImdjgQAAAAAABA2GUU2nkaX3pQ5W3LkyKGgoCCtXLlSTz75pKV85cqVateuXZr6efLk0d69e63Kpk+frtWrV+vHH39UQEDAv2s8AAAAAACwQthkENl5zaYHNXz4cPXo0UPVq1dXnTp1NGvWLIWHh2vAgAGSUkZKnT17Vl999ZUcHBxUoUIFq+39/f3l6uqaphwAAAAAAPx7hE1GQdhk0aVLF8XExOjNN99URESEKlSooNDQUBUtWlSSFBERofDw8CxuJQAAAAAA/02ETQbByCZrAwcO1MCBA23eN3fu3LtuO3bsWI0dO9b+jQIAAAAAAIRNhkHYBAAAAAAADICwySCy89XoAAAAAABA9kHYZBSMbAIAAAAAAAZA2GQQrNkEAAAAAACMgLDJKAibAAAAAACAARA2GQRrNgEAAAAAACMgbDIKRjYBAAAAAAADIGwyCsImAAAAAABgAIRNBsE0OgAAAAAAYASETQbB1egAAAAAAIAREDYZBWETAAAAAAAwAMImoyBsAgAAAAAABkDYZBBMowMAAAAAAEZA2GQQhE0AAAAAAMAICJuMgrAJAAAAAAAYAGGTQZiSs7oFAAAAAAAA90bYZBSMbAIAAAAAAAZA2GQQrNkEAAAAAACMgLDJIJhGBwAAAAAAjICwySgY2QQAAAAAAAyAsMkoCJsAAAAAAIABEDYZBGs2AQAAAAAAIyBsMghTMmkTAAAAAAB49BE2GQVZEwAAAAAAMADCJoNgGh0AAAAAADACh6xuAO6PKTn73h7G9OnTFRAQIFdXVwUFBWn9+vXp1v3pp5/UvHlz+fn5KU+ePKpTp46WL1/+kL8JAAAAAABwN4RNRmHOxrcHNH/+fA0dOlSjRo3Szp07Vb9+fbVq1Urh4eE26//xxx9q3ry5QkNDtX37djVu3FiPP/64du7c+eAPDgAAAAAA7oppdAbBNLpUH330kfr06aO+fftKkiZPnqzly5drxowZmjBhQpr6kydPtvr5nXfe0c8//6xffvlFVatWzYwmAwAAAADwn0HYZBTZOGxKSEhQQkKCVZmLi4tcXFzS1L1586a2b9+uV1991ao8ODhYmzZtuq/HS05O1pUrV+Tt7f3wjQYAAAAAADYxjc4gTMnmbHubMGGCPDw8rG62RihJUnR0tJKSkpQ3b16r8rx58yoyMvK++vLDDz/UtWvX1Llz53/9ewEAAAAAANYY2WQQ2XkaXUhIiIYPH25VZmtU0z+ZTCarn81mc5oyW7777juNHTtWP//8s/z9/R+8sQAAAAAA4K4Im4wiG4dN6U2Zs8XX11eOjo5pRjFFRUWlGe10p/nz56tPnz5asGCBmjVr9tDtBQAAAAAA6WManUGYkrLv7UHkyJFDQUFBWrlypVX5ypUrVbdu3XS3++6779S7d299++23atOmzcP8CgAAAAAAwH1gZJNBZOdpdA9q+PDh6tGjh6pXr646depo1qxZCg8P14ABAySlTMs7e/asvvrqK0kpQVPPnj318ccfq3bt2pZRUW5ubvLw8Miy4wAAAAAAIDsibDIKM2nTbV26dFFMTIzefPNNRUREqEKFCgoNDVXRokUlSREREQoPD7fU//TTT5WYmKhBgwZp0KBBlvJevXpp7ty5md18AAAAAACyNcImgzAlZ3ULHi0DBw7UwIEDbd53Z4C0du3ajG8QAAAAAACQRNhkGEyjAwAAAAAARkDYZBRMowMAAAAAAAZA2GQQjGwCAAAAAABGQNhkEKzZBAAAAAAAjICwySiSGdoEAAAAAAAefYRNRkHWBAAAAAAADICwySBMjGwCAAAAAAAGQNhkECwQDgAAAAAAjICwySgImwAAAAAAgAEQNhmEyUzaBAAAAAAAHn2ETQZhSiJsAgAAAAAAjz7CJqMgawIAAAAAAAZA2GQUTKMDAAAAAAAGQNhkEKZkwiYAAAAAAPDoI2wyCFNyVrcAAAAAAADg3gibjIJpdAAAAAAAwAAIm4yCrAkAAAAAABgAYZNBmJKZRwcAAAAAAB59hE1GQdYEAAAAAAAMgLDJIEys2QQAAAAAAAzAZDaTYhhBi6AxWd2EDLN8+7isbgLsIDmydFY3wZBKrumd1U0wpCJf8V3Jw7iWj357WO7RSVndBENy33k6q5tgSGaP3FndBEMynzqT1U0wJJOjY1Y3wZB+uzQnq5sAPNJ412kUTKMDAAAAAAAGQNhkEEyjAwAAAAAARkDYZBRcjQ4AAAAAABgAYZNRMLIJAAAAAAAYgENWNwD3KTkb3x7C9OnTFRAQIFdXVwUFBWn9+vV3rb9u3ToFBQXJ1dVVxYsX18yZMx/ugQEAAAAAwF0RNhmEyWzOtrcHNX/+fA0dOlSjRo3Szp07Vb9+fbVq1Urh4eE26584cUKtW7dW/fr1tXPnTr322msaMmSIFi5c+G9/LQAAAAAA4A5MozOKJNZsuu2jjz5Snz591LdvX0nS5MmTtXz5cs2YMUMTJkxIU3/mzJkqUqSIJk+eLEkqW7aswsLCNHHiRHXo0CEzmw4AAAAAQLbHyCajMJuz7S0hIUGXL1+2uiUkJNjshps3b2r79u0KDg62Kg8ODtamTZtsbrN58+Y09Vu0aKGwsDDdunXLPr8fAAAAAAAgibDJOB6BUCijbhMmTJCHh4fVzdYIJUmKjo5WUlKS8ubNa1WeN29eRUZG2twmMjLSZv3ExERFR0fb5/cDAAAAAAAkMY3OOLLxNLqQkBANHz7cqszFxeWu25hMJqufzWZzmrJ71bdVDgAAAAAA/h3CJqMwZ9+wycXF5Z7h0m2+vr5ydHRMM4opKioqzeil2/Lly2ezvpOTk3x8fB6u0QAAAAAAwCam0RnFIzDdLcNuDyBHjhwKCgrSypUrrcpXrlypunXr2tymTp06aeqvWLFC1atXl7Oz84P9HgAAAAAAwF0xsskokh8slMnOhg8frh49eqh69eqqU6eOZs2apfDwcA0YMEBSyrS8s2fP6quvvpIkDRgwQFOnTtXw4cPVr18/bd68WbNnz9Z3332XlYcBAAAAAEC2RNhkFMnZdxrdg+rSpYtiYmL05ptvKiIiQhUqVFBoaKiKFi0qSYqIiFB4eLilfkBAgEJDQzVs2DBNmzZNBQoU0CeffKIOHTpk1SEAAAAAAJBtmczmB5zHhCzRquDgrG5Chvn17JSsbgLsIDmydFY3wZBKrumd1U0wpCJf8V3Jw7iWj357WO7RSVndBENy33k6q5tgSGaP3FndBEMynzqT1U0wJJOjY1Y3wZB+uzQnq5sAPNJ412kUjGwCAAAAAAAGQNhkFIRNAAAAAADAAAibjIIFwgEAAAAAgAEQNhmE2czIJgAAAAAA8OgjbDKKJMImAAAAAADw6CNsMgrWbAIAAAAAAAZA2GQUZtZsAgAAAAAAjz7CJoMwM7IJAAAAAAAYAGGTUbBmEwAAAAAAMADCJqPganQAAAAAAMAACJsMwpzMmk0AAAAAAODRR9hkEOakpKxuAgAAAAAAwD0RNhkF0+gAAAAAAIABEDYZxMrkBVndBAAAAAAAgHtyyOoGAAAAAAAAIPsgbAIAAAAAAIDdEDYBAAAAAADAblizCYBhbNstzflO2n9YuhBj0pTxZjWrf/dttu6S3psmHT0p+ftIfZ6WurazrrNinfTJbCn8nFSkgPS/vlLzBhl1FFmne8lq6le2tvzdcunwpQsav+N3bbtw2mbdWv5F9F3T7mnKmy39VMevxKQpb1uknD6p114rzhzSgPUL7d72rNSuTRV17VhTPt65dOJUtKZ+ulp795+xWdfbK6cG9mus0qXyqVABL/20ZLumfrraqk79uqXUvUsdFSzgKUcnB509G6f5P23TytUHMuNwMk3HxpXVvVV1+Xrm1PGzMfro27XadeSszbqNg0qqQ+PKKl3ET85Ojjp+Nkaf/bxZW/adstRp36CiWtcrqxIFfSVJf508r2kLN+rAichMOZ7M0r51FXV9qoa8vXLpZHi0pn62WnsO2O43b6+cGtSnkUqXSDnfFv6yXVM/X5PuvpvUL6MxLz+u9VuO6PW3F2fQEWSdZ4a3UqtudZXL002Hdp7StFELFH747udHvdaV1XNEG+Uv6quIU9H68v2l2vTbHsv9bXo8pjY96ylvIR9J0qnDEfp28m8KW3MwQ48ls7TtWksdn31M3n65depolGa+u0z7d5xKt37F6sX0/MutVbSkv2KirmjBnPUK/WGr5f6WHaur2RNVVbRkXknS0QNn9cXHK3V4r+2/mUbX/bX2av1sI+XyzKm/wo5p2vCvdeqg7efrbY+1q66eo59S/gB/RZyI0txxC7Xpl+2W+x0cHdRj1JNq0rmOvPJ6KDbyolZ+s0HfvrdEZrM5g48oc3R/tZ1a9W6oXJ7uOhR2XNNGzNOpv87ddZt6TwSp56gnlT/ATxEnLujLt37SpqU7LPd/ued95S3qm2a7Xz5brWkj5tn9GADcGyObABjGjRtSYEnp9aH3V/9MhDTgFSmokvTTZ9Lz3aV3PkkJl27buU8aPk56IlhaPDvl3+Fjpd3Z63O/2hQpq9erNde0/RvV9rfZCrtwWnMadlEB9zx33a7p0pmquehjy+3k1dg0dQq451FI1SbaGhWeUc3PMo0blNGL/Ztq3vdb1PfFudq7/4zef6uj/P1y26yfw9lRFy9d17zvN+vYiSibda5cidfX8zdr4PB56jNwrn5duU+vDm+tGtWKZeCRZK7mNUtreLdG+mLpn+o+Zp52HT6rj4c/qbzetvutaulC+nP/KQ2dtEg9x32j7X+d1kf/a6/SRfwsdYLKFNKKLYf0wnsL9Nz47xQZe0VTRzwlP89cmXVYGa7xY4F6sW8Tff3DFvX735fas/+M3ht7r/Pthub9sCXd8+22vH559MJzjbR7n+2A2eg6DWymp/o11vTRC/S/Nh8qLuqy3vl2kNxyuqS7TZlqxRQyvbdWLdymgcHvatXCbQqZ8awCqxa11ImOuKgvJvyiIa0/0JDWH2j3xsN6Y3Y/FSmdLzMOK0M1aFlR/V9tre9nrdOgjtO0b8dJjf+0l/zye9isn7egl96a0Uv7dpzUoI7TNP+zdXrhtTaq17y8pU6lGgFaG7pHrzw3W8OemamoiEt6Z1Zv+fjf/bXGiDoPa62nXmypaS99rcENxyru/CVNWDJSbrlc092mbM0Seu3LgVr13SYNrDNaq77bpFFfDVRg9eKWOl2Gt1GbPo017aWv1S8oRJ+Pnq+O/2uldi80y4zDynCdhrbSk4OCNX3kPA1p/JZioy7pncUj7t5vNUrotS8GaPX8TRpYb4xWz9+k1+YOUGBQar8NafyWni411HILaTdRkrR+8bYMPybcW7FixTR58uSsbgYyGWETAMNoUFsa2lcKvs9RR9//LOX3l14bLJUoJnVqKz3VWprzfWqdr36U6galBFHFi6b8WztI+iqbXQCyT2BNLTi+Wz8c361jl2P01o7fFXH9sp4pVe2u20XHX7O6Jd/xraqDyaTJddvp473rFX71YgYeQdbo9GR1ha7Yo2XL9yj8dKymfrpaUReuqF2bqjbrR0Zd1tRPV2vFqv26di3BZp1de09rw6YjCj8dq3MRF7Xw5+06duKCKpYvlJGHkqm6BQfp5z/26ec/9ulkRKw++m6tzsdeUccmlW3W/+i7tfr61zAdOHFep89f1PSFG3X6fJwaVClhqTN61q/6cc1uHT59Qaci4/T2FytlMplUo1zhzDqsDNe5fXWFrtyrZSv26tSZWE39fI0uRF9Ru1ZVbNaPjLqsKZ+t1vI1+3X1uu3zTZIcHEx6fUQbffHtRp07fymDWp+12vdpqO+nrNCmX/fo1KEIfTjsG7m4OatR+6D0t+nbSDvWH9IP01bqzLEo/TBtpXZtPKz2fRpZ6vz5+z5tW31AZ09c0NkTF/Tl+8sUfz1BZbJBOPxUr3pavnC7flsYptPHL+jTd0N1IeKS2napZbN+my41FRVxUZ++G6rTxy/ot4VhWvHTDnXs/ZilzvuvLNDS7//U8b8idOZEtD4es0gmB5Oq1C5uc59G1n5QC33/wRJtXLJdpw6c1cTnP5OLWw417lw73W2eHNRCO1bv1/wPl+r04QjN/3Cpdq09oCcHtbDUKVuzpDYv3aGty3frfHi0NiwO047V+1SqakBmHFaGe/KF5vr+w6Xa+MsOnTp4Vh8OmJ3Sb51sn3eS1H5gc+1Yc0DzPwrVmSORmv9RqHatO6gnBza31LkUc0VxUZctt5otKuvc8fPas+FQZhzWPfXu3Vsmk0kmk0nOzs4qXry4RowYoWvXrmV10zLFtm3b9Pzzz2d1M5DJCJsAZFu79kv1aliX1ash7T8k3UpM+Xn3fqmujTo792dOGzODs4ODKnjn1/rI41bl6yNPqJrv3QOOpS37aEv7IZrXuJtq+xdNc/+Q8o8pJv66fji+265tfhQ4OTkosFQ+bdtx0qp8244TKl+uoN0ep1qVIipcyCvbjDhxcnRQmWJ59ed+66k4f+4/pUolCtzXPkwmyd01hy5di0+3jquLk5wcHXX5LnWMxMnJQaVL5tO2nSetyrftPKkKZf/d+dara11dunRDoSv3/qv9PKryFfGRd14P7Vj3l6Xs1s1E7d1yTOWqp/8BvWxQMattJGn72oMqm842Dg4mNXyimlzdXPTX9pN2aXtWcXJ2VKlyBbRj01Gr8h2bjqpslSI2tylbuXCa+ts3HlGp8gXl6GT7I4WLq7OcnBx15dIN+zT8EZGvmJ988nlq+6p9lrJbNxO1d8MhlatVKt3tytYsabWNJIX9vk/lapW0/Lxv82FVaVROBf+eili8QmGVr1Na21bskdHlK+Yn73ye2rE69U3WrZuJ2rvxkMrWLJnudmVrlNCO1db9tn3VPpWtWcJmfSdnRzXpUlvL522wT8PtpGXLloqIiNDx48c1fvx4TZ8+XSNGjEhT79atW1nQuozl5+cnd3f3rG4GMhlhE4BsKzpW8vGyLvP1lhKTTIq7lFrH9846Xinl2YWXi7ucHBwUHW/97VlM/DX5uea0uU3UjasK2RqqgRsW6oX1C3X8SozmNemmGn6po0iCfAupU4nKem1raIa2P6t45HGXo6OD4uKs+y3u4nV5e9nut/uV0z2Hfv1pqH7/5SW9O66jPpmxStt3pr9OipF45naTk6ODYi/fcb5dui4fj/t7o/lMi+pydXHW71vT/0b6xY71dSHuqrbuzx7TNz3y/N1vF+88367J2/Phz7cKZQuqdfOK+mDq8n/bxEeWl1/KFK246MtW5RejL1vuS2+7i9FX7tjmirzv2KZYmfz66dAHWnL8I704obPe6ve5wo8Ye62wPJ7ucnRyVFzMVavyuJir8va1PTXVyze3zfpOzo7ySOccfW54C8VEXdbOzcfs0/BHhHfelKmGcVHW51zchcvyymt7GqIkeeX10MUo69GFF6MuWW3zw0fLtHbBn/p8x7taFjdb0za9qUXTVmjtgi12PIKs4fX3dEpb/eZ9j35Ls01U+n1dp2015fJw18pvNv7LFtuXi4uL8uXLp8KFC6tbt2565plntHjxYo0dO1ZVqlTRnDlzVLx4cbm4uMhsNuvSpUt6/vnn5e/vrzx58qhJkybavdv6y73x48fL399fuXPnVt++ffXqq6+qSpUqlvt79+6t9u3ba+LEicqfP798fHw0aNAgq0Br3rx5ql69unLnzq18+fKpW7duiopKnZq9du1amUwmrVq1StWrV5e7u7vq1q2rQ4esX6OXLFmi6tWry9XVVb6+vnrqqacs9905je5ex7Z79241btxYuXPnVp48eRQUFKSwsLB/+ytAJmOBcADZmslk/fPtWWCmu9WxUZYd2FpXNL2lRk9cidWJK6mJ286Ys8rvnkf9ytTStgunldMphz6q84Re2xqquJvZ6xvrO93ZbyaTjcIHdP3GTfUdNFdubjlUrUpRDerXWBERF7Vrb/YY3STZ7rf76bXgWoF6vn0djfjkZ8VdsX1u9WhVXcG1ymjAez/oZmLSv2/so+TOTjKZZL6vnkvLzc1Zr7/UWhOnLtely9nnedr4yeoa/G4Xy89jen0qycbT0mS6Z8/dueCyyWRKU3bmWJQGtXhPufK4qV7rKnppUne93PETwwdOktJ0WsrxP0j9v4tt9HTH5+qrUetKern357p1M/HftjRLNe5cR//7pLfl59EdP0r5z539YaPsTmnuNZmstmnYsZaadq2jd5+bqVMHz6pExSIa8N4ziomI0+/fPlrhyb007lRbQyb3tPz8RufJKf+xcR7dc/HzNK8p6b+otOxRX9tW7lVs5MUHa/ADSkhIUEKC9RRmFxcXubikv1bcP7m5uVlCn6NHj+qHH37QwoUL5ejoKElq06aNvL29FRoaKg8PD3366adq2rSpDh8+LG9vb33zzTd6++23NX36dNWrV0/ff/+9PvzwQwUEWI/OXLNmjfLnz681a9bo6NGj6tKli6pUqaJ+/fpJkm7evKm33npLgYGBioqK0rBhw9S7d2+Fhlp/mThq1Ch9+OGH8vPz04ABA/Tcc89p48aUc3LZsmV66qmnNGrUKH399de6efOmli1bZvO4zWbzPY/tmWeeUdWqVTVjxgw5Ojpq165dcnZ2vq9+xaODsAmwISQkRPHx2WNqRmb58JWsbkFavt5pRyjFxElOjmZ5eqTWuWCjzp0joowsLuG6EpOT5edm/c2zj2vONKOd7mZn9Fm1L1ZBklQkl6cK5/LUZw06W+53+PtTx+Eur6rZspmGX8Pp0uXrSkpKlre3db95ergr9uL1f7Vvs1k6G3FRknT0eJSKFvZRty61s0XYdPHKDSUmJcvHw7rfvPO4K/bS3futec3SGv1ssF6dvlRbD9gesdS9ZZCebVtTgz5YqKNnou3W7qx26XJKv905as7Lw11xD3m+Fcznpfx5PfXO6NRvl28/T1ctfkk9BszWuQz+MJYRtqzYq7/+Md3QOUfK21lvvzxWox88fXLr4oXLd25uEXch7cgnD59cirtjtFPirSRFnEw5147sOa3SlYuoXZ+GmvLq/H97KFnm8sXrSkpMkpev9eLznt4504xeui0u+oqN+rmUeCtJl+84Rzv0fkxd+zVUSN8vdOLwefs2PgtsCd2pQ2Gpo7OcXVI+9Hrl9VDsP9ZB87zjHLxT3PlL8vK3Ho1z5zb9xnfR/I+Wad2Pf0qSTu4/I/8ivuo6oq3hwqYtv+7SX9tTp/Dn+Pu5mqbffO+j3/JaP1c9/XIrLirtGnT+hX1UpVE5vdV96r9t/j1NmDBB48aNsyobM2aMxo4de89tt27dqm+//VZNmzaVlBL4fP311/LzS7kwxurVq7V3715FRUVZwquJEydq8eLF+vHHH/X8889rypQp6tOnj5599llJ0htvvKEVK1bo6lXr57CXl5emTp0qR0dHlSlTRm3atNGqVassYdNzzz1nqVu8eHF98sknqlmzpq5evapcuVJHOr799ttq2LChJOnVV19VmzZtFB8fL1dXV7399tvq2rWrVX9Urmx7ncY1a9bc89jCw8M1cuRIlSlTRpJUqlT601Px6CJsAmyIj4/XpEmTsroZhpIcafvbi6xUpby0dpN12cZtUvlAyfnvv36Vy0ubwqTeqZmJNm2TqpZXtnErOVn7YiP0WL4ArThz2FL+WL4A/X728F22tFbeK5+i4lPewBy7HKOWoZ9Z3T+8UgPlcnLRmztWKuJ6+m8ajSIxMVmHjkSqetVi2rDpiKW8erVi2rj56F22fAimlCuLZQeJScn66+R51SpfRGt3pPZTzXJF9ceu9KfSBNcK1OjnWuj1mcu0cc8Jm3W6t6yuPo/X0uAPf9LBk8b/APtPiYnJOnw0UtWrFtX6Lf8436oU1YY/H+58Cz8To96DvrAq69PjMbm75dCUWasVFW3M5+mNawm6cccC/LHnL6lqg0Ad239GUsqaLRVrl9Ccd5aku5+D20+qWoNALf58raWsWsMyOhhm+/y7zWRKDbiMKvFWko4cOKeqdUtq06rUy69WrVtSW1YftLnNwd2nVatRGauyanVL6sj+s0pKTLaUdXz2MT3dv7FGPT9XR/afzZgDyGQ3rsbrxlXrLyFjIi+qWpMKOrYnJRh3cnZUxccCNfuNH9Ldz8GtR1WtSXktmpY6rTWoaQUd+Mdz3MXNReZk6yE7yUnJMpmMt/qJrX6Ljbyoqo3LWfdbvUDNGZv+lVkObjumqo3La9H0lZayak0q6ODWtK8pwc88pksXLmvr8oxf4yokJETDhw+3KrvbqKalS5cqV65cSkxM1K1bt9SuXTtNmTJF06dPV9GiRS1BkyRt375dV69elY+Pj9U+bty4oWPHUo770KFDGjhwoNX9NWvW1OrVq63KypcvbxktJUn58+fX3r2pa/jt3LlTY8eO1a5duxQbG6vk5JTnc3h4uMqVK2epV6lSJat9SFJUVJSKFCmiXbt2WcKre7mfYxs+fLj69u2rr7/+Ws2aNVOnTp1UooTtNbrw6DL2KyWA/5Rr16Xwf7xvPRMhHTwieeSRCuSVPpolnb8gvTcq5f6u7aRvF0nvTk25Et2u/dJPodLEN1L30bOj1GOI9Nm3UtN60qqN0ubt0ryM/0IsU80+tFUf1n5Ce2MjtCP6rJ4uUVUF3PPomyM7JEkjKzdSXrfcGrHlF0nSs4E1dObqJR25dEHODo5qH1BBrYqU0QvrF0qSbiYn6fClC1aPcflmyoe/O8uNbMGiML02oo0OHYnU/oNn9XirKsrrl0dLQndJkvr1biBfn1ya8GHqUPOSxf0lSW6uOeTh4a6Sxf11KzFJp8JjJEndOtfSoSOROhdxUc5OjqpVo7haNC2vSVNXpnl8o/p2xXaN69dKB06e196jEXqyYUXl88mthWtS1mMY1PEx+Xnm0tjPf5OUEjSN69tSH367VvuORcgnT8raTvG3EnXtxk1JKVPnBjxZV69/+qsioi9Z6lxPuKUbCdljMdUfFodp1PC/z7e/zqlty8ry98ujJb+m9Fu/nvXl55Nb70z6x/kWkHq+eXq4q2TA3+fb6RjdvJWkE+HWo7+u/h3S3FludItnr1OXF5vr3N9XjesyuLkSbtzS2sXbLXVemtxdMZGXNPfdlL9zP89epw8WDlGngc20efke1WlRSVUfC9SIpyZbtun1SluFrTmgC+cuyj2Xixo+UU0V65TS6O4zMvsQ7e6nLzdq5LsddWTfWR3cHa5WnWrIP7+Hls3fKkl6dmiwfPzzaOJrP0qSls3fqieerq3nX26lX38MU9nKRdSiQ5DeHZkarnR8rr56Dm6m917+QefPxcnr7/Wfbly/qfjrNzP/IDPQ4mnL1XVEW509dl5nj0Xq6RGPK+HGTa35IXVtpZGznlf0uTh98XeQsnj6Ck1c/po6D2utzct2qk6bqqrauJyGN3/bss2WX3eq68jHFXU6JmUaXeWiempwC634an2mH2NGWDRjpboOb6tzx6J09th5dX2pTUq/LfjTUmfEzL6KiYjTF+NS3nMsnrFSE399VZ2Gtkrtt0Zl9VKLd632bTKZ1PyZelr53SYlJyUroz3IlDlJaty4sWbMmCFnZ2cVKFDAalpYzpzWo1qTk5OVP39+rV27Ns1+PD09Lf833bHug63piHdOPzOZTJZA6dq1awoODlZwcLDmzZsnPz8/hYeHq0WLFrp582a6+7n9uLf34+bmlt5hp3E/xzZ27Fh169ZNy5Yt06+//qoxY8bo+++/15NPPnnfj4OsR9gEwDD2H5J6DU19UX1vWsr/27c0a0KIdCFGikhdz1CF8ksz30sJm75dLPn7SK8NkYIbptapWkH68A3p49nSlNlS4QLSh2Olyqlf5GQLy8IPyiuHmwaXf0x+brl0+NIFPbduvs79PQLJzzWXCrinDlF3dnBUSNUmyueWW/FJiTpyKVrPrZ2vtRHZa5HXe1nzx1/Kk9tVvbrVlbd3Tp04Ga1X3vhR5/8e7u/jnVN5/a2H9n8+rbfl/4Gl86l543KKPH9JXXunrCvj5uqsYYOC5eebSwk3ExV+OlZvf7BMa/6wviqWka3celgeOd3U94na8vXIqWNnYzR00iJFxqRMT/L1yKl8PqnTcZ5qVElOTo56pWdTvdKzqaV86Yb9Gjc7ZQRAxyaVlcPZSe+/+LjVY81avFmf/bw5E44q463ZcEgeedzUs2td+Xjn1IlT0Xpl3EKdv3D7fMslfz/raUyzP+ll+X+ZUvnUvFE5RZy/pK59Z2Vq27Pagum/K4erswa93Um5PNx1aNcpjXpmutUIKP+CXlYjRg5uP6F3B32pniPbqMeI1oo4Fa0JA7/QoX8s1u/ll1sjP+4hb38PXbtyQycOntPo7jO0c/2jcTn1f+OP3/Yqj6e7nnmhsbz8cuvUkfMaPeArRf09xdfbL7f886dO+Tp/Nk6jX/hS/V9po7ZP11Zs1GXNeGeZNq5MvbLY411rKUcOJ42e3M3qseZNW6V5061HWxjdD5NClcMth16c1FO5Pd31V9hxhbT7wGokj19hb8uHcUk68OdRvdN7unq/0UE9R3dQxIkovdNrug6FpU41mz5innqNfkovTuopT788iom4qNA5a/XNhMWZeXgZZsHkX+XimkMvfthduTxz6q+w43rtyQ+t+s2/kLfM/+i3g1uPacJzM9Xr9afUc9STijgRpQnPztShf0zRk6SqjcspbxFfrfj60QzmcubMqZIl07/q3j9Vq1ZNkZGRcnJyUrFixWzWCQwM1NatW9WjRw9L2YMuov3XX38pOjpa7777rgoXLvxQ+5BSRj2tWrXKMqXvbu7n2CSpdOnSKl26tIYNG6ann35aX3zxBWGTwZjM91yNDfjvGTZsGNPoHlByZOmsboIhlVzTO6ubYEhFvuK7kodxLR/99rDco7PZQuSZxH2n8dchywpmj9z3roQ0zKfOZHUTDMnkmD2mcWe23y7Nue+6vXv31sWLF7V48eI0940dO1aLFy/Wrl27LGVms1kNGjTQlStX9N577ykwMFDnzp1TaGio2rdvr+rVq+ubb75Rv379NGPGDNWtW1fz58/XBx98oOLFi2vnzp3pPu7QoUO1a9curV27VhcuXFChQoX0v//9TwMGDNC+ffs0cuRIHT58WDt37lSVKlW0du1aNW7cWHFxcZaRR7t27VLVqlV14sQJFStWTGvXrlXTpk31+uuvq2vXrkpMTNSvv/6ql19+WVLK1eiGDh2qoUOH3vPYypcvr5EjR6pjx44KCAjQmTNn1KtXL3Xo0EHvvffeA/+ekHWMN/kXAAAAAIBsymQyKTQ0VA0aNNBzzz2n0qVLq2vXrjp58qTy5s0rSXrmmWcUEhKiESNGqFq1ajpx4oR69+4tV1fX+34cPz8/zZ07VwsWLFC5cuX07rvvauLEiQ/c3kaNGmnBggVasmSJqlSpoiZNmujPP/+0Wfdex+bo6KiYmBj17NlTpUuXVufOndWqVas0i7Hj0cfIJsAGRjY9OEY2PRxGNj0cRjY9HEY2PTxGNj0cRjY9HEY2PRxGNj0cRjY9nAcZ2ZRZmjdvrnz58unrr7/O6qYArNkEAAAAAICRXL9+XTNnzlSLFi3k6Oio7777Tr///rtWrsw+FxyBsRE2AQAAAABgILeno40fP14JCQkKDAzUwoUL1axZs6xuGiCJsAkAAAAAAENxc3PT77//ntXNANLFAuEAAAAAAACwG8ImAAAAAAAA2A1hEwAAAAAAAOyGsAkAAAAAAAB2Q9gEAAAAAAAAuyFsAgAAAAAAgN0QNgEAAAAAAMBuCJsAAAAAAABgN4RNAAAAAAAAsBvCJgAAAAAAANgNYRMAAAAAAADshrAJAAAAAAAAdkPYBAAAAAAAALshbAIAAAAAAIDdEDYBAAAAAADAbgibAAAAAAAAYDeETQAAAAAAALAbwiYAAAAAAADYDWETAAAAAAAA7IawCQAAAAAAAHZD2AQAAAAAAAC7IWwCAAAAAACA3RA2AQAAAAAAwG4ImwAAAAAAAGA3hE0AAAAAAACwG8ImAAAAAAAA2A1hEwAAAAAAAOyGsAkAAAAAAAB2Q9gEAAAAAAAAu3HK6gYga4WEhCg+Pj6rm/HIiYqKyuomGE7JNb2zugmGdLTx3KxugiEFrX8hq5tgSI43zVndBMO6mo+3TA/Dzccjq5tgTCZTVrfAkJKvX8/qJhiSU17/rG4CgGyId07/cfHx8Zo0aVJWN+ORM2zYsKxuAgAAAAAAhsQ0OgAAAAAAANgNYRMAAAAAAADshrAJAAAAAAAAdkPYBAAAAAAAALshbAIAAAAAAIDdEDYBAAAAAADAbgibAAAAAAAAYDeETQAAAAAAALAbwiYAAAAAAADYDWETAAAAAAAA7IawCQAAAAAAAHZD2AQAAAAAAAC7IWwCAAAAAACA3RA2AQAAAAAAwG4ImwAAAAAAAGA3hE0AAAAAAACwG8ImAAAAAAAA2A1hEwAAAAAAAOyGsAkAAAAAAAB2Q9gEAAAAAAAAuyFsAgAAAAAAgN0QNgEAAAAAAMBuCJsAAAAAAABgN4RNAAAAAAAAsBvCJgAAAAAAANgNYRMAAAAAAADshrAJAAAAAAAAdkPYBAAAAAAAALshbAIAAAAAAIDdEDYBAAAAAADAbgibAAAAAAAAYDdOWd0AAHhQ3UtWU7+yteXvlkuHL13Q+B2/a9uF0zbr1vIvou+adk9T3mzppzp+JSZNedsi5fRJvfZaceaQBqxfaPe2Z4Vtu6U530n7D0sXYkyaMt6sZvXvvs3WXdJ706SjJyV/H6nP01LXdtZ1VqyTPpkthZ+TihSQ/tdXat4go44i63RqUEm9mlWXr0dOHYuI0cQF67Tz2FmbdZtUKalO9SspsJCfnJ0cdTwiRjOXbdHmg6es6uVyc9GLT9RVkyqllMfdRWdjLmnSwj+0Yf/JTDiizNGxUWX1aFFdvp45dfxcjD78fq12HbHdb42rlVTHRpVVuvDf/XYuRrOWbNaW/ads1g+uEah3+rfR2p1HNWLakow8jEzXqVGllH7zSOm3ifPXpd9vVUuqY6NKCvxnv/2yRZvT7bfSmvB8Sr+9NP2XjDyMTNe2c0117P2YvH1z6dSxKM18/1ft32m7HySpYlAxPT+ipYqW8FfMhStaMHeDQhdss9xfr2k5denTQAUKe8vJ2VFnT8Xop683atXS3ZlxOJmmbeca6tjrdr9d0MwP7qPfXmqpoiX8UvvtxzCbdRu2qKCQ9zpr05qDenPYdxl1CFmqx5hOatOvmXJ55dJffx7RlBc/16kDZ9KtX7RcIfUa10WlgoorXzF/TR/2hRZ9HGpVp2L9suo04gmVDiounwLeGvPk+9r087Z09mhMz7zUWq2611MuD3cd2nlS00J+UPjhiLtuU69NFfV8ua3yF/VVxKloffnuL9r0q+3nY+fBwXr2tXZa/NlqffpG9ngvBxgRI5sAGEqbImX1erXmmrZ/o9r+NlthF05rTsMuKuCe567bNV06UzUXfWy5nbwam6ZOAfc8CqnaRFujwjOq+Vnixg0psKT0+tD7q38mQhrwihRUSfrpM+n57tI7n6SES7ft3CcNHyc9ESwtnp3y7/Cx0u4DGXAAWSg4qLRGdmyk2b9t1dMTvtHOo2c1dVB75fPKbbN+tZIFteWvcL04fbGeefdbbTt8Rh+/0E6BhfwsdZwcHTRzyFMq4JNHIz9bqifHzdVb3/yuqItXM+uwMlzzGqX1UtdGmhP6p555c552Hj6rT/73pPJ62+63qqUK6c8Dp/S/jxepx1vfKOyv05o0uL0CC/ulqZvPO7f+16mBdhxO/wOdUTWvXlovdWmkOcu2qtub32jnkbOaMqS98qXTb9VKF9SfB8I15JPF6j7+W4UdOqNJL7ZLt9+GZtN+a9Cigvq/3Erff7ZOg7rM0L4dpzR+eg/55fOwWT9vQU+9Na2H9u04pUFdZmj+53/ohVdaq17TcpY6Vy5d1/efr9Ownp/phY5TteLnHRo+7kkF1S2ZWYeV4RoEV1D/ka30/efrNKjrDO3beUrjp3VPv98KeOqtqd21b+cpDeo6Q/Nnp+232/zze6jv8Bbau/1kBh9F1unycjt1GNZWUwfP1os1X1Vs5EW9t2K03HK5pruNi7uLIk5EaXbIN4qJiLNZxzWni47vOaWpg2dnVNOzVKdBzfVU/yaaPuoH/a/V+4qLuqx35r8ot5wu6W5TJihAITOf06oft2pgswla9eNWhXzaR4FVi6WpW7pyEbXqXk/H92e/v3WA0RA2ATCUPoE1teD4bv1wfLeOXY7RWzt+V8T1y3qmVLW7bhcdf83qlmw2W93vYDJpct12+njveoVfvZiBR5D5GtSWhvaVgu9z1NH3P0v5/aXXBkslikmd2kpPtZbmfJ9a56sfpbpBKUFU8aIp/9YOkr5akCGHkGW6N6mmxZv2adGmfToRGauJP65T5MUr6tSgks36E39cpy9XhunAqfMKv3BRU5dsVHjURTWsWNxSp33dCsrj7qrhM3/R7uPnFBF7RbuOndPhs9GZdVgZ7pnmQfp5wz79vH6fTkbE6qP5a3U+7oo6Nqpss/5H89fqq9/CdODkeZ2OuqjpizYq/Hyc6lcuYVXPwWTS+H6tNWvJZp29cCkzDiVTdW9eTT9v2KfFG/bpZGSsPpy/LqXfGto+3z6cv05fLU/tt2mLUs63BpWLW9VzMJn0dt9W+nTJZp2Nzn799lSPulq+aId+W7Rdp09c0Kcf/KoLkZfVtnNNm/XbdKqpqIhL+vSDX3X6xAX9tmi7VizeoY696lnq7Ak7qU2rD+r0iQuKOBOnn7/dohNHzqt81aKZdVgZLrXfduj0iejUfutUw2b9Np1q/KPfovXboh1asXinOvasZ1XPwcGkV97pqHkz1ijyrO1AJTt48n9t9N07P2nDoq06uf+0Pug9VS7uLmrS7bF0tzkcdkyfvfy11s7fpFsJt2zW2fbbLs0d/b02LNqaUU3PUu37Ndb3Hy/XptDdOnUoQh/+72u5uOVQo6dsn3e3t9nxx1/6YcoKnTl6Xj9MWaFdGw6pfb/GVvVc3V00clpvfTziW129dD2jD+WhbNq0SY6OjmrZsmVWNwXIcIRNAAzD2cFBFbzza33kcavy9ZEnVM230F23Xdqyj7a0H6J5jbuptn/aDwtDyj+mmPjr+uF49poi8TB27Zfq3fGer14Naf8h6VZiys+790t1bdTZuT9z2pgZnBwdVLZI3jRT4LYcDFfl4gXuax8mk+Tu6qxL1+MtZQ0rFteeExF6tWsT/f7u81rweg8916KGHEwmu7Y/qzg5OqhM0bxppsBt2X9KlUrcf7/ldM2hy9fircr7Pl5bcVdu6OcN++zW3keFpd8O3Nlv4Q/Wby7OunRHv/V7vLbirt7Qzxuy0RP0b05OjipVtoB2bD5qVb5j81GVrVzY5jZlKxVOU3/7pqMqVa6gHJ1svzWuUrO4ChXzzTYjdVL6Lb92bD5mVb5jy1GVrVzE5jZlKxXWji22+q2AVb91699IF+OuafniHfZv+CMiX4C/fPJ7KWxF6nuGWzcTtWfdAZWrE5iFLXu05SviI++8Htqx7qCl7NbNRO3dfFTlqgeku13Z6gFW20jS9rUHVLaGdbA+aEJnbVu1X7vWH7Jvw+1ozpw5Gjx4sDZs2KDw8Ow1kh64E2ETAMPwcnGXk4ODouOvWZXHxF+Tn2tOm9tE3biqkK2hGrhhoV5Yv1DHr8RoXpNuquGX+iEkyLeQOpWorNe2htrcx39NdKzk42Vd5ustJSaZFHcptY7vnXW8UsqzC69cbnJydFDsFetvR2MuX5NPHvf72kePpkFyy+GsFdsPW8oK+nqoWdVScnQwafC0xfr81z/Vo2mQ+ra0PQrDaDxv99tl6+dp7OXr8vW4v37rHlxdri7OWhmW+oGhcskCavdYBY3/aoVd2/uouN1vMZfvON+uXJPP/fZb86C/+y31fKtcooDaPVZe479aadf2PiryeLnL0clRcTHW01DjYq7K29f29EMv31w26zs5O8rDM7Wv3XO5aNHm17U0bKzenNpd099dpp1bjt25O0Oy9Fvsnf1wTd6+uWxuk9Jv1s/ruFjrfitXpYhatK+mj9/MXmup3ck7n6ck6eJ565GCcVGXLPchLS//lCUP4i5csSq/GH3Zcp/N7fzy6OKd21y4Im+/1Od4w3ZBKlGxsL5452c7tti+rl27ph9++EEvvPCC2rZtq7lz51rdv2TJEpUqVUpubm5q3LixvvzyS5lMJl28eNFSZ9OmTWrQoIHc3NxUuHBhDRkyRNeuWT8vgUcFYRMAw7ljBlxKWTp1T1yJ1fxju7Q/7rx2xpzVG2HLtebcUfUrU0uSlNMphz6q84Re2xqquJs3Mq7RBnPnIJvbfW66Wx0bZdnBneebyWSyeQ7eqWX1QA1oU0evzg5V3NXUc8vBZFLslet665vfdfB0lJZvP6zZv21Vxwa2p5gZVdp+s/3cvVOLmoF6/ok6eu3TZYq7ktJv7i7OerNPK7391Upduhp/jz0YW5p+kyn9P3D/0KJmoPo/UUchs0Kt+u2tvi01/qvfdTGb99udfZTyPL1Lx9moL1n3/41rNzWw83QNeWam5k79Xc+/1FKVqhezT3sfFTafp3frN+v7/tlvbu459PLbHfTxm0t0+eKjOYXpYTXp9piWXP7acnNyTrnG0p19db9/5/4rGj9VQz8d/chyc3J2lGTjHLuP19W0fZ26jW8BT/V/q6M+ePFL3UpItFfz7ykhIUGXL1+2uiUkJKRbf/78+QoMDFRgYKC6d++uL774wnJcJ0+eVMeOHdW+fXvt2rVL/fv316hRo6y237t3r1q0aKGnnnpKe/bs0fz587Vhwwa9+OKLGXqcwMPianSADa6urho2bFhWN8NYaqZdkNbe4hKuKzE5WX5u1qOYfFxzphntdDc7o8+qfbEKkqQiuTxVOJenPmvQ2XL/7elMh7u8qmbLZma7NZzuxdc77QilmDjJydEsT4/UOhds1LlzRJSRxV29ocSk5DSjmLxzu6cZ7XSn4KDSeqN7c738+TL9ech6mHz05WtKTEq2WjfsRGSs/DxyysnRQYlJyfY7iCxw8Xa/eVg/T71yu6cZtXOn5jVKa3SvYL0yc6m2Hkztt0L+niro56GPBre3lN1+nm75dKg6vP6F4ddwut1vd47+8r6ffqteWm/0bK5XPl2Wtt98PTTpxdRLSd7utz9n/k8dRs/VGYP32+W460pKTJLXHaNxPL1zphm9dFtc9FWb9RNvJenyP9Z5MZvNijid8ofu+KFIFQnwU5c+DbQn7KR9DyILWPrNx1a/2X49tdlvXqn9VrSEv/IV9NK4j7tZ7jc5pJxvy8LGqG/7TxRxxphrOG1eEqa//kydQujskvIRyiufp2IjL1rKPf08FHf+opBiy/I9+mvHScvPzjlS+s3bP4/ioi5byj19cuvihct3bm4RdyHtyCcP31yKi04Z7VSqUhF5+eXRlOWvWO53dHJUhdol9fizDfVE0f8pOdn+KeCECRM0btw4q7IxY8Zo7NixNuvPnj1b3bunXCG5ZcuWunr1qlatWqVmzZpp5syZCgwM1AcffCBJCgwM1L59+/T2229btv/ggw/UrVs3DR06VJJUqlQpffLJJ2rYsKFmzJghV9f0F6cHsgJhE2DDhAkTsroJhvPzd+9k+GPcSk7WvtgIPZYvQCvOpE4TeSxfgH4/e/guW1or75VPUfEpH0KOXY5Ry9DPrO4fXqmBcjm56M0dKxVxPf03P9lVlfLS2k3WZRu3SeUDpb+/zFXl8tKmMKl3akanTdukquUzr50ZLTEpWQfDz6t22aJaszt16kztMkW0dk/6U2laVg/UmO7BCvkiVBv2nUhz/65j59SqRqDVN+BF8nrpwsWrhg+apJR+++vUedUqV0Rrd6Z+OKtVrqjW7Uq/31rUDNTo3i00atYybdxr3W8nI2LV5Y0vrcpeeLKe3F1z6MPv1uh8rPX0CiOy9FvZolqzM7WfapUrcs9+e6NXsEZ9FqoNNvqt85ivrMoGtq8rd9ccmvj9WkVmh35LTNKRg+dUtXYJbVqduqZL1doltGXtXza3ObjntGo1sF5Xp1qdkjpy4KySEtN/DppMJjk7Z4+3zin9FqGqdUpo05p/9FutB+23Ejpy4JySEpN1+kS0+neYanV/rxebys3dRTPfD9WFSOO+nt64Gq8bVyOtymIi4hTUvJKO7TopSXJydlKlhuX0+avzsqCFj6Yb1xJ049oFq7LY85dUtUEZHduXcrU4J2dHVaxTUnPeTn/628GwE6rWoKwWz1pjKavWsKwObktZw3PX+kMa0Gi81TbDJ/fQ6aPntWDqigwJmiQpJCREw4cPtypzcbF9Vb1Dhw5p69at+umnnyRJTk5O6tKli+bMmaNmzZrp0KFDqlHDejHMmjWtp9dv375dR48e1TfffGMpM5vNSk5O1okTJ1S2bFl7HBZgN9njFRPAf8bsQ1v1Ye0ntDc2Qjuiz+rpElVVwD2PvjmSshDpyMqNlNctt0Zs+UWS9GxgDZ25eklHLl2Qs4Oj2gdUUKsiZfTC+oWSpJvJSTp8yfqN0OWbKUOg7yw3qmvXpfCzqT+fiZAOHpE88kgF8kofzZLOX5De+3u0dtd20reLpHenplyJbtd+6adQaeIbqfvo2VHqMUT67FupaT1p1UZp83ZpnvXnDMObt3qHxvdqqQOnzmvPiQg9Va+i8nnl1o/r90iSBrerJ3/PXBr95XJJKUHTm71a6IMFa7X3RIRlVFTCzURdjb8pSVqwfre6Nqqilzs10ndrd6mIv5f6tKih79buypJjzAjfrNyuN/u00sGT57XneISealBR+bxza+HalMV0Bz31mPw9c2nMnN8kpQQm455rqYnfr9W+46n9Fn8rUddu3NTNxCQdOxdj9RhXrqc8T+8sN7J5K3forT5/n2/HUvvtx3Up59uLT9aTn1cujZmTcr61qBmoN59toYnz12rvP/ot4VairqbXbzeyX7/99PUmjXy7g44cOKeDu0+rVYfq8s/voWULUq7m9eyQ5vLxz6OJr6f83V+2YKue6FpLz49oqV8XblfZyoXV4slqeveV1MtpdnmugQ4fOKuI07FycnZUzfql1bRtFU19+5csOcaMkNJvT+nI/rM6uOcf/fbjNknSs4ObpfTb6JQPx8sWbEvpt5da6tefwlS20t/99uqPklIWej51LMrqMa5dSZm+eWd5drDo42V6OuQpnT0SqbNHIvR0yFNKuJ6g1d9usNR5ee6Lij4XqzmvfSspJZAqWi7lgibOOZzkW9BHJSoX042r8Tp3LCXMcs3pqoIl81n2kS/AXyUqF9Pl2Ku6cNr4Vy1d/NkadRnSQudOXNDZ41HqMqSFEm7c1NqftlnqvPRJT8VEXtTcd1LW/vr58zX6YNEwdRrUXJuX71GdFpVUtX4ZjWj3kaSUUOvUoQirx4m/nqArcVfTlNuTi4tLuuHSnWbPnq3ExEQVLFjQUmY2m+Xs7Ky4uDiZzWbLtNR/3v9PycnJ6t+/v4YMGZJm/0WK2F7YH8hKhE0ADGVZ+EF55XDT4PKPyc8tlw5fuqDn1s3Xub9HIPm55lIB99Sh1s4Ojgqp2kT53HIrPilRRy5F67m187U2Inss8no/9h+Seg1NfQPz3rSU/7dvadaEEOlCjBTxj88BhfJLM99LCZu+XSz5+0ivDZGCG6bWqVpB+vAN6ePZ0pTZUuEC0odjpcrlMueYMsuK7YflkdNVz7euJd88OXU0IkaDpy9WxN8jQnzz5FQ+r9QFSjs8VlHOjo56rWtTvda1qaV8yeb9GvN1ysLW5+OuauCUn/RSx4b6YVQPRV28qm/X7NTcFWGZe3AZaOW2w/LI6aa+j9eWr0dOHTsXo/99vMgyksbXI6fy+aT221MNK8nJyVGvdm+qV7un9tsvG/dr3BfLM739WWVl2GF55nJVv7a1LP025JPFqf3mmVP5vP/Rbw0qpvTbM0316jP/6LdN+zX2i+y5kLotfyzfpzwe7nrm+Uby8sutU0fPa/SgrxUVkTJF0Ns3l/zzeVjqnz97UaMHfa3+I1upbZdair1wRTPeC9XGVQcsdVzdnPXia4/LN28e3Uy4pdMnovX+qB/1x/LscyXEP1bsUx5PNz3Tv5G8fHPr1NEojX5xXmq/+eWWf/5/9Nu5ixr94jz1H9FSbbvUtNlv/yXz3/9ZOdxyaPC0vsrtlVN//XlUr7YYrxv/WB/Nv4ivzP8YVeNTwEszd35g+bnziCfUecQT2r12v0Y0GStJKl29uD5ckzo164WPekuSVsxdqw+em5ahx5QZFkxbqRyuzho0oYtyebjr0M6TGtV1qm5cS13ryL+gl1W/HQw7oXcHfKGer7ZVj5fbKuJUtCYMmK1DO09mwRE8uMTERH311Vf68MMPFRwcbHVfhw4d9M0336hMmTIKDbW+UE1YmPX7gmrVqmn//v0qWbJkhrcZsAeT+a6rACK7GzZsmCZNmpTVzUA2UDwTptFlR0cbz83qJhhS0JsvZHUTDMnxJi/5D8ucHVe/zwR+W7PRJSozE+fbQ0nac/DelZCGU17/rG6CIf0acX/h3+LFi9WlSxdFRUXJw8PD6r5Ro0YpNDRUP/30kwIDAzVs2DD16dNHu3bt0ksvvaQzZ87o4sWL8vDw0J49e1S7dm09++yz6tevn3LmzKmDBw9q5cqVmjJlSkYcIvCvcDU6AAAAAAAywOzZs9WsWbM0QZOUMrJp165diouL048//qiffvpJlSpV0owZMyxXo7s9Va9SpUpat26djhw5ovr166tq1aoaPXq08ufPn6nHA9wvptEBAAAAAJABfvkl/bXeqlWrZlmbqVq1anriiScs97399tsqVKiQ1VXmatSooRUr/jvTpGFshE0AAAAAAGSh6dOnq0aNGvLx8dHGjRv1wQcf6MUXX8zqZgEPjbAJAAAAAIAsdOTIEY0fP16xsbEqUqSIXnrpJYWEhGR1s4CHRtgEAAAAAEAWmjRpEhduQrbCAuEAAAAAAACwG8ImAAAAAAAA2A1hEwAAAAAAAOyGsAkAAAAAAAB2Q9gEAAAAAAAAuyFsAgAAAAAAgN0QNgEAAAAAAMBuCJsAAAAAAABgN4RNAAAAAAAAsBvCJgAAAAAAANgNYRMAAAAAAADshrAJAAAAAAAAdkPYBAAAAAAAALshbAIAAAAAAIDdEDYBAAAAAADAbgibAAAAAAAAYDeETQAAAAAAALAbwiYAAAAAAADYDWETAAAAAAAA7IawCQAAAAAAAHZD2AQAAAAAAAC7IWwCAAAAAACA3RA2AQAAAAAAwG4ImwAAAAAAAGA3hE0AAAAAAACwG8ImAAAAAAAA2A1hEwAAAAAAAOyGsAkAAAAAAAB2Q9gEAAAAAAAAu3HK6gbg/oWEhCg+Pt6u+4yKirLr/vDfVeQr/pw8jKD1L2R1Ewxp+xszsroJhlT8p+ezugmGVXiFOaubYEg3CuXO6iYY0g0/XlMfhmeOilndBEMKb8rzFID98UpmIPHx8Zo0aZJd9zls2DC77g8AAAAAAPy3MY0OAAAAAAAAdkPYBAAAAAAAALshbAIAAAAAAIDdEDYBAAAAAADAbgibAAAAAAAAYDeETQAAAAAAALAbwiYAAAAAAADYDWETAAAAAAAA7IawCQAAAAAAAHZD2AQAAAAAAAC7IWwCAAAAAACA3RA2AQAAAAAAwG4ImwAAAAAAAGA3hE0AAAAAAACwG8ImAAAAAAAA2A1hEwAAAAAAAOyGsAkAAAAAAAB2Q9gEAAAAAAAAuyFsAgAAAAAAgN0QNgEAAAAAAMBuCJsAAAAAAABgN4RNAAAAAAAAsBvCJgAAAAAAANgNYRMAAAAAAADshrAJAAAAAAAAdkPYBAAAAAAAALshbAIAAAAAAIDdEDYBAAAAAADAbgibAAAAAAAAYDeETQAAAAAAALAbwiYAAAAAAADYDWETAAAAAAAA7MYpqxsAAA+qXZsq6tqxpny8c+nEqWhN/XS19u4/Y7Out1dODezXWKVL5VOhAl76acl2Tf10tVWd+nVLqXuXOipYwFOOTg46ezZO83/appWrD2TG4WSaTg0qqVez6vL1yKljETGauGCddh47a7Nukyol1al+JQUW8pOzk6OOR8Ro5rIt2nzwlFW9XG4uevGJumpSpZTyuLvobMwlTVr4hzbsP5kJR5Sxtu2W5nwn7T8sXYgxacp4s5rVv/s2W3dJ702Tjp6U/H2kPk9LXdtZ11mxTvpkthR+TipSQPpfX6l5g4w6iqzTvXwV9a9aQ/7uOXU4NlpvblyjbRG2z7d/CspXQPPbd9Xh2Gi1/uErS/n37bqodsHCaeqvPnVczy37ya5tz0rtW1XR0+1ryMcrl06ejtYns1drzwHb/ebjlVODnm2kwBL5VCi/l35ctl1TZq+xqtOqSXm9NqR1mm2bdvpIN28lZcQhZIn2baqo61M15e2dSyfDozV11mrtucvrwqC+jVW6ZMrrwsIl2zX1s9U260pSkwZlNOaVJ7R+8xG9Pn5RRh1ClujQpLJ6tKouH8+cOn42RpO+Xatdh22fb42CSqpD48oqXcRPzs6OOnE2Rp8t3qwt+1JfF9o1rKg2dcuqeCFfSdJfJ89r+o8bdeBEZKYcT2Z5vEN1depRR94+uXXqeJRmTFqhfbvC061fsWpRDRjaXEWL+ysm+op++HqTlv203apOzlwuevaFJqrXuIxy53ZT5Lk4ffrxSm3bdDSjDyfTdK1dSc/Wry6/3Dl1NCpG7y5dpx0nbZ9v1YoW0PCW9RXg7yVXZ2edi7usBVv36KuNOy11mpUvqX6NaqqIj4ecHB0VHh2nuRt26JedBzPrkDKEyWTSokWL1L59+6xuCvCvEDYBMJTGDcroxf5NNXnaSu09cEZPtK6i99/qqF79ZyvqwpU09XM4O+ripeua9/1mdXqyus19XrkSr6/nb1b46RglJiarTs0SenV4a128eF3bdpzM4CPKHMFBpTWyYyNN+H61dh0/pw6PVdTUQe3V4a2vFBmXtt+qlSyoLX+Fa8qSjbp6PUFP1Cmvj19opx7vf6dDZy5IkpwcHTRzyFOKvXJdIz9bqqiLV5TXK7eux9/M7MPLEDduSIElpSdbS/8bfe/6ZyKkAa9IHdtK74+SduyT3pokeXtKwQ1T6uzcJw0fJw15TmpWX/p9vTR8rDRvqlS5XAYeTCZrWzJQbzzWWKP/+F1hkWf1TLnKmtu2g5p/94XOXU17vt2WO0cOfdS0tTadOSVf95xW9/X/7WflcEgdkO3p6qZfu/RS6NFDGXYcma1JvUANea6JPvp0pfb+dVZPtKisD0Z3VI/BcxQVnbbfnJ0ddfHSDX21YIs6PxGU7n6vXkvQM4NmW5Vlp6Cpcf0yerFfU02avlL7Dp7R4y2r6L1xHdXrhXu8LszfrE7tbb8u3JbXL49e6NNYu/edzqjmZ5lmNUtreLdGev+rVdp95JyebFxJk4c/qS6vfanzsWn7rWpgIW3df0rTF27Q1esJavtYeX04tL2effNbHQ5PeV0IKlNIy/88pD3frNHNW4nq0aqGpox8Sl1f+0oXLl7N7EPMEA2bldOA4S005f1Q7d99Wm2erKa3J3dT3y7TdeH85TT18xXw1NuTn1bo4h16d8xila9cWINfbq1Lcde0Yc1fkiQnJwe9O7W7LsZe11uv/qjoqMvyy5tHN65nj9dTSWpZsbRebdNIb/28WjtPnVPnWhX1ae/2emLSV4q4lPZ8u37zlr7dskuHIqJ14+YtVStWQGOebKYbNxO1YNteSdKl6/GateZPnbgQp1tJSWpYprjGdwhW7NXr2njkVJp9PgoiIyM1YcIELVu2TGfOnJGHh4dKlSql7t27q2fPnnJ3d8/qJgJ2Q9gEwFA6PVldoSv2aNnyPZKkqZ+uVo1qAWrXpqo+m/tHmvqRUZctI5laB1e0uc9de60/RCz8ebtaNKugiuULZZuwqXuTalq8aZ8WbdonSZr44zrVKVdUnRpU0pSfN6apP/HHdVY/T12yUY0qlVDDisUtYVP7uhWUx91VvT+Yr8TkZElShI0PKEbVoHbK7X59/7OU3196bXDKzyWKSfsPSXO+Tw2bvvpRqhskPd895efni6aMoPpqgfThGLs2P0v1rVxdPxzcq/kHUz4QvLlxjRoUKabuFaro/S3r093unYbB+vnIQSWbzQoOKGl136WEeKufHy9VRjcSb2nZscP2P4As0qVddS37fa+W/p7Sb1Nmr1HNKgF6smUVfTovbb9FRl3WJ7NT/r61aVYh3f2aZVbsxWsZ0+hHQOfbrwsr/n5d+Gy1agYFqF3rqvrsS9uvC1NmpfRbq+a2XxckycHBpNdHttUX32xQpfKFlCuna8YcQBbp1iJIS/7Yp5//SHldmPTtWtWuUFQdmlTW9B83pKk/6du1Vj/PWLhRDauVUP0qJSxh0xuf/mpV550vVqpJjVKqUa6wQjcZe7TJbR261dFvS3bqt59TRtjMnLRC1WuX0OMdqmvO9LQj5No8FaSoyEuaOWmFJOn0yWiVLptfHbvXtYRNLZ6oqtx53DS0zxdKSkp5PY2KvJRJR5Q5etWvpoVh+7QwLOV8e3fpOtUtVVRdalfS5OVp34f8FXFBf0VcsPx8btdlNStfUtUCClrCpm0nrEcvztu0U+2qlVW1YgUeybDp+PHjqlevnjw9PfXOO++oYsWKSkxM1OHDhzVnzhwVKFBATzzxRFY3E7Ab1mwCYBhOTg4KLJUvTQC0bccJlS9X0G6PU61KERUu5JVtvsl2cnRQ2SJ500yB23IwXJWLF7ivfZhMkrursy5dT/3A37Bice05EaFXuzbR7+8+rwWv99BzLWrIwWSya/uNYtd+qV4N67J6NVICp1uJKT/v3i/VtVFn5/7MaWNmcHZwUAW/vFp/+qRV+frTJxWUN/3zrVOZCiri4amPt226r8fpXLaifjnyl24k3vo3zX1kODk5qHSJfNq666RV+bZdJ1WhzL/7++bmmkMLZj2vhZ8P0HujnlKpAP9/tb9HiZOTg0qXzKdtO09alW/bcUIVyv67fuv1dF1dunRdoSv2/qv9PIqcHB1Uplhe/bnP+nXhz32nVKnkg7wu5NDla/Hp1nF1cZKTo+Nd6xiJk5ODSpXJrx1/HrMq3/7ncZWrlHaarySVq1hI2/88bl1/yzGVLptfjo4pH8Xq1C+tg3vPaPDLrTT/1+Ga9d0Ade39mBwcssfrqbOjg8oVyKtNdwRAm46Eq0qR+zvfyuT3U9WiBRR23Pb0WEmqVaKwivl5K+zEvadsZ4WBAwfKyclJYWFh6ty5s8qWLauKFSuqQ4cOWrZsmR5//PE026xdu1Ymk0kXL160lO3atUsmk0knT560lG3cuFENGzaUu7u7vLy81KJFC8XFxUmSEhISNGTIEPn7+8vV1VWPPfaYtm3bZtk2Li5OzzzzjPz8/OTm5qZSpUrpiy++sNx/9uxZdenSRV5eXvLx8VG7du2sHhtIDyObABiGRx53OTo6KC7O+hv6uIvX5e2VM52t7k9O9xz6cd5AOTs7KjnZrEnTVmr7zkfvW7GH4ZXLTU6ODoq9ct2qPObyNfnkKXpf++jRNEhuOZy1YnvqKJKCvh6q4VNYv277S4OnLVYRf0+92qWJnBwcNOvXP+16DEYQHSv5eFmX+XpLiUkmxV0yy98npY7vnXW8UsqzCy9XNzk5OOjCDevz7cL16/ItbPt5WszDUy/Xrq/Oi75Xktl8z8eo7J9PZXz89Mqa5XZp86PAI3fK8zTujhFIcZeu/au/b6fOxGrCJ7/q2KkLyumeQ53aBmn6u9307NC5OhNx8V+2Out55HFP+ft2Z7/9y9eFCmULqnVwJfUdPPdftvDR5Pn3+RZz2brfYi9fl4/H/U3jeaZldbm5OOv3relPZR3Uqb4uxF3V1gPpr2dkJHk83eXo5KC4mDvOt9hr8vKxfb55+eRSXOwd9WOuycnJUR6e7oqNuar8Bb1UpXqAVi/fq9eHfaeChb314sut5OjooG9mpx2dZzSe7n+fb1fveB9y9Zp8c9/9fciqV/vKO6ebHB0cNH3VFsvIqNtyueTQmpB+cnZKef/21s+rtflo5pxvCQkJSkhIsCpzcXGRi4tLmroxMTFasWKF3nnnHeXMaftcMT3kl3W7du1S06ZN9dxzz+mTTz6Rk5OT1qxZo6SklOnSL7/8shYuXKgvv/xSRYsW1fvvv68WLVro6NGj8vb21ujRo3XgwAH9+uuv8vX11dGjR3Xjxg1J0vXr19W4cWPVr19ff/zxh5ycnDR+/Hi1bNlSe/bsUY4cOR6qzfhvIGxCthUSEqL4+OzxTZox5M+0R7rzs6jJZKPwAV2/cVN9B82Vm1sOVatSVIP6NVZExMU0U+yMLG2/me6r21pWD9SANnU0bOYSxV29YSl3MJkUe+W63vrmdyWbzTp4Okp+HrnUs3n1/2TYJP19Lv7D7f413a2OjbJs4Y6TK+UY055wDiaTPm7eVpO3bdKJS3H3tesuZSvqr5gL2h2VvRYdlmz1kEnmf/H37cDhCB04HGH5ee/Bs5r9US91aFNNH3+e/qLYhnNnF5n00P3m5pZDr49oo4mf/KZLl2/cewMjs/F6ej+9FlwrUP3a19GIj39W3BXbfdSjVXUF1yqjF979IVutESbZON1MNgqtNrD1xiVliqskmRxMuhh3TZPfWarkZLOO/BUhH7/c6ti9TrYIm25L+zS99/uQnp/+IPcczqpcJL+GtXxM4TEXFbo7NeC8dvOmOkyZJ/ccOVSrRGG93KaBzsReSjPFLiNMmDBB48aNsyobM2aMxo4dm6bu0aNHZTabFRgYaFXu6+tr+bwyaNAgvffeew/cjvfff1/Vq1fX9OnTLWXly5eXJF27dk0zZszQ3Llz1apVK0nSZ599ppUrV2r27NkaOXKkwsPDVbVqVVWvnrKGXbFixSz7+f777+Xg4KDPP//cEoZ98cUX8vT01Nq1axUcHPzA7cV/B2ETsq34+HhNmjQpq5vxn9Go1fsZ/hiXLl9XUlKyvL2tvxHy9HBX7MXr6Wx1f8xm6ezf3/IfPR6looV91K1L7WwRNsVdvaHEpGT55LH+tto7t3ua0U53Cg4qrTe6N9fLny/Tn4esvymMvnxNiUnJSv7HO8UTkbHy88gpJ0cHJf697sR/ha932hFKMXGSk6NZnh6pdS7YqHPniCgji4u/ocTkZPndscC3r5u7oq+nPd9yOedQZf98Ku/rr3H1m0pKCaAcTCYdHTBcPX5ZoM1nU5+Hrk5OaluyjCZtS7vGh5FdupLyPPX2tO43Lw93xf3Lv2//ZDZLfx2JUKH82eOku3T5ekq/edmv3wrm91T+fJ56Z0wHS9nt6cGrloxQj+c/17nIiw/d5kfBxb/PNx+PO/ott7tiL92935rVLK3XnwtWyPSl2pbOiKVnWgap9+M19eL7C3X0TLTd2p3VLl+8rqTEZHnfMYrJ0ytnmtFLt8XFXJWXTy6rMi9vdyUmJunyxZSgLjb6qhITk5ScnPp6Gn4iWj6+ueXk5KDERGO/nl68nnK++ea6431ILvc0o53udDYuZdH1I+dj5JPLXQOb1rYKm8xmKTwmZX2rvyIuqLi/t/o1qpEpYVNISIiGDx9uVWZrVNM/3Tl6aevWrUpOTtYzzzyTZpTU/dq1a5c6depk875jx47p1q1bqlevnqXM2dlZNWvW1MGDKeuovfDCC+rQoYN27Nih4OBgtW/fXnXr1pUkbd++XUePHlXu3Lmt9hsfH69jx6ynkwJ3ImwCYBiJick6dCRS1asW04ZNRyzl1asV08bNdr40sCnlikXZQWJSsg6Gn1ftskW1ZnfqG4PaZYpo7Z703yi0rB6oMd2DFfJFqDbsO5Hm/l3HzqlVjcCUb8L/fn9cJK+XLly8+p8LmiSpSnlp7R3LDW3cJpUPlJz/frWtXF7aFCb17pxaZ9M2qWr5zGtnRruVnKx9F87rscLFtPxE6vPysULFtPJk2ufplZsJCv5+rlVZjwpVVLdgYb2w/Bedvmy9SG7bEoFycXTUokMHMqT9WSUxMVmHj0WqRpWiWv9n6t+3GlWKasOf9v37VjLAX8dPZY8AIDExWYePprwurN/8j9eFqsW0YcvD9Vv46Rj1HjjHqqxPj/pyd8uhKbNWKSo67RXHjCYxKVl/nTyvmuWLaO2O1H6qWb6o/tiZ/utCcK1Avd6nhUbPXKaNu9O+LkhS91bV9dzjtTTkw5908OR5u7c9KyUmJuvIXxGqVrO4Nq5NDTyq1SyuzX/Ynk54YO8Z1X6stFVZtVoldPhghGUx8P27T6txiwpWr6cFi3gr5sIVwwdNknQrKVkHzp1X3VJFtepA6vlVt2QRrT54/4GFyWRSDqe7vzczySTne9Sxl/SmzNlSsmRJmUwm/fXXX1blxYsXlyS5ubnZ3M7h76uw/nOk5q1b1msVprftP7e7M+Qym82WslatWunUqVNatmyZfv/9dzVt2lSDBg3SxIkTlZycrKCgIH3zzTdp9u3n55fu4wISC4QDMJgFi8LUpkUltQquqCKFvTXo+SbK65dHS0J3SZL69W6gkJdaW21Tsri/Shb3l5trDnl4uKtkcX8VLeJjub9b51oKqlpU+fN5qEghb3V6srpaNC2vlauzz4fZeat36Mm6FdSuTnkF5PPWSx0aKp9Xbv24PuXqTYPb1dNbvVpY6resHqg3e7XQRz+t094TEfLJ4y6fPO7K5Zo6N3/B+t3yyOmmlzs1UhF/Tz1WIUB9WtTQ/D92Z/rxZYRr16WDR1JuknQmIuX/5/7+7PTRLOmVt1Prd22Xct+7U6VjJ6WFy6SfQqXnuqbW6dkxJWz67Fvp+KmUfzdvl3ra/kLSsD7fHaYuZSuqU5kKKuHlrdH1GqlA7tz6Zl/KufFy7fr6sGnKcH6zpMOx0Va3mBvXlZCUpMOx0WkWAO9ctqJWnDiqiwnZb5r0/J/D1LZZJbVuWkFFC3lr8HON5e+bR4uXp/Rb/+71Nep/d/x9C/BXyYCUv2+eedxVMsBfxQql/n3r3aWualYppvx5PVQywF+vvthSpQL89fPyXZl5aBnqh0VhahNcSa2bV1TRwt4a1K+J/P/5utCrgV4bns7rglsOed5+XSic0m83byXpxKloq9vVa/G6fuOmTpyKzhYf/iXp2+Xb1a5hRT1ev7yK5ffWsKcbKp9Pbv20JuV8G9jxMY3t19JSP7hWoMb2a6mPv1+nfcci5OPhLh8Pd+V0S31d6NGqugY8VVdvzVmhiOhLljpuLs6ZfnwZZeG3m9WyXTW1eLyKChfz1YBhwfLP56GlP22XJD03sIlGjm1nqb/sp+3Km99D/YcGq3AxX7V4vIpaPlFVP85L/XZi6cIw5fFw0wsvtVTBIt6qWa+Unu79mJb8uC3N4xvVl+t3qEP1CnoyqLyK+3nrlTYNld8zt+b/mfI+ZGiLenqnU+r7kKdrV1ajMsVVxMdTRXw81T6onHrXD9LSnalhTd+GNVSnZBEV8vJQgJ+Xej1WTU9UK2tV51Hh4+Oj5s2ba+rUqbp27f6vDno70ImISJ0OvWvXLqs6lSpV0qpVq2xuX7JkSeXIkUMbNqReYfLWrVsKCwtT2bJlrR6nd+/emjdvniZPnqxZs2ZJkqpVq6YjR47I399fJUuWtLp5eHjc93Hgv4mRTQAMZc0ffylPblf16lZX3t45deJktF5540edj0r5ptnHO6fy+uex2ubzab0t/w8snU/NG5dT5PlL6tr7U0mSm6uzhg0Klp9vLiXcTFT46Vi9/cEyrfnj0Xuz8rBWbD8sj5yuer51LfnmyamjETEaPH2xImKvSJJ88+RUPq/UIdIdHqsoZ0dHvda1qV7r2tRSvmTzfo35OuXyzefjrmrglJ/0UseG+mFUD0VdvKpv1+zU3BVhmXtwGWT/IanX0NRvAt+blvL/9i3NmhAiXYiRIqJS6xfKL818LyVs+nax5O8jvTZECm6YWqdqBenDN6SPZ0tTZkuFC0gfjpUql8ucY8osS48ekqeLm/5XvY78cubU4ZhoPbv0J529mvI89XfPqYK58txjL2kFeHipZoFC6r5kgb2b/EhYvfGQ8uRxU+8udeXjlVMnwv/P3n2HR1X0fRz+bAqQ3kNC76H33pEWmhRpCgKKNEFEFHkVEFAUEXhAQEBRiiIg0kR6R3qvoZeQAGmkEToB3j8WEjbZIOImIfF7e+UymZ1zdmY4Z2b3tzOz1/j4i8WERTzp3xzJ7mW6lGHWhK4Jvxct5EOjOsUJCY+lfU/jGwUnh6wMercR7m4O3Lx5l7MXw+k3ZAEnz2ae/a42bzuFi3M2urxeHQ93By5eusbg4YueajcHvL1Mr7efJndL+L1oYeO4EBIWS8e3v0/LoqerDXvP4OJoR/eWVfF0ceD8lUg++N9SQiMfjwuuDmT3SLzeWtcrjY2NNYO71Gdwl8RxYcX2AD7/0bhZ/2v1y5DF1oYx/Uy/VWvGsl3MWLYrDWqV+rZuOIGziz2dutfG3dORS+fDGfrBPMJDjbMw3T0d8c6e+CY89GoMQwbMp/cHjWjRtiJR1+KYOn4N2zcnvsaICL/OJ/1/pfeARnz/a2+uRVxn6W97Wfhz5lkuvObYGVwdstGnfhW8nBw4GxZJ79nLCIkxXm9eTg74uiZebwaDgQGNa5DT3YUHDx8SHBnDhDXbWbj3aEIe+yy2DGv5CtldnLh7P54LEVH8329rWHPsTLLnfxlMnTqVGjVqULFiRUaMGEHp0qWxsrJi3759nDp1igoVKiQ7plChQuTOnZsRI0YwatQozp49y/jx403yfPLJJ5QqVYp3332X3r17kyVLFjZv3ky7du3w9PSkT58+DBo0CHd3d/LkycM333zDrVu36N69OwCfffYZFSpUoESJEty9e5cVK1YkBKI6derE2LFjadmyJZ9//jm5cuUiKCiIJUuWMGjQIHLlypX6DScZluHRv9l1UtLUBx98YPE9iFLjnC+LzFy3l1Fa7NmUGcXmzzyf9qalA59NS+8iZEgFlvRM7yJkWLnX6eXSi7C6r3Z7Ebe99Hnwi3A9cSO9i5AhXanv9PeZJJmA0R/842NCQkL46quvWLlyJZcvXyZr1qwUL16cdu3a8e6772Jvb4/BYGDp0qW0atUKgB07dtCnTx/Onj1LpUqV6N+/P+3atePixYsJm3lv3bqVTz/9lAMHDmBnZ0eVKlVYsGABrq6u3Llzh48//pj58+cTFxdHxYoVmTBhApUqVQJg1KhRzJs3j8DAQOzs7KhVqxYTJkwgf/78AISGhjJ48GBWrVpFXFwcOXPmpH79+owbNw5n53/+wZH8d2gkExEREREREUllvr6+TJ48mcmTJ6eYJ+lckBo1anD06NFn5qlTpw47dpifCZctWzYmTZrEpEmTzD4+dOhQhg4dmmJ5fHx8mDNnToqPi6REezaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjE26V0ASV/ZsmXjgw8+SO9ipIrw8PD0LsJ/yk0fdScvwvreo/QuQoZUYEnP9C5ChnShzQ/pXYQMy/+XN9O7CBnSzVz26V2EDOmOmyG9i5AhPbLV5+gvwvPI/fQugohkQnp3+B83evTo9C5CqsmsQTQRERERERGRl5nC/yIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjE16F0BE5J9qW68MnZtUxNPVgQtXIvnfvC0cPnvFbN56FQrxWr0yFMnjha2NNReuRDLjj13sPn4pIU+r2qVoWqMYBXN6AnAqMIzvFu/gxMXQNKlPWmlbtwxvNn7cblcjGb/gGe1WvhBt65ahSO7H7XY1kh+W72J3wCWz+RtV8uOrXs3YcugcH323PDWrkeY6lyhLr3KV8LZ34EzUNT7fsZl9Iebb7WkVfHLwW6uOnIm6RtOFPyekL2jZgao5cyfLv+nSBd5eucSiZU8v+47AzPkQcAYiIg1MHvWIBrWefczewzDmOzgXCN4e0P116NjSNM+6rTDpJwi6CnlywPvvQMPaqVWL9NGiTQXadaqGu4cTly5GMG3iWo4fCU4xf6lyeejdvxF583sReS2Ohb/uZOXSgwmPj/3uTcqUz5fsuD07zjLsowWpUYV00bpRGd5oWQkPVwcuXo5k0qzNHDll/j71cHWgX9c6FC2QnVw+bixafZBvZ28xyTN5RHvKl0h+n+48eIFBo5emRhXSRYcapelWryKezg6cD43km2VbOXjBfLvVL1WI9jVK45fTiyw21pwPjWTamt3sPJ04LthYWdG9QSVerVQcbxdHAsOjmbhiGztOmR87MqoWrSvQ7o1qeHg4EngxgmmT1j3zPi1dNg+93mtIvif36bxdrFiWeJ+Om/wmZcrnTXbcnp1nGTrot1SpQ3po1awsHV+rjLu7I4GXrjHlh00cDbhsNq+7mwN9e9SjSCEfcuVwY/HyA0z5YZNJnlrVC9O5QzVy+rpiY2PF5SvRLFy6j3WbTqRFdUTkbyjYJCIZSsPKRRj4Rl3G/LKRI2ev0qZuab4d2Jr2Q+YQFhWXLH+5IrnYE3CJqYu3E3frLi1qluB/77ei2xfzOBMUAUCForlYt/s0R89t5u79eLo0rcSUj9rQYcjPRMTcSOsqpoqGlYrwYce6fP3rRo6cu0qb2qWZ9H5r2n2WQrsVzsWeE5f4bsnjdqtRggnvtaLbl/M4HRxhktfH3Yn329Xm4BnzLxgzsuaF/PisZj2G/bWB/aFX6FS8DLObv0bD+bO4eiN5uz3hlCUL/6vflJ2XL+Fp72DyWK81f5DFKnFisWs2O1Z36Mqqc6dTrR5p7fZt8CsErZvC+8P+Pv/lEOg9GNo2h2+GwMHj8MUEcHeFRnWMeQ4dh4Ejof/b0KAWbNgGA0fA3ClQpngqViYN1alfnN4DGjN57CoCjl6mWevyfPm/N3jnjWlEhF1Plt/H15Uvx7/OquWH+HrEMkqUzsV7g5oSG32L7VtOAfD5J79jY2OdcIyziz3Tf+7JX5nozVj96n68/1Y9xs/YyNHTV2jVsDTjhrSh8wezCbuW/D61tbUm5vpt5izeQ4fmFcye89Nxy7G1SbxPXRztmD2uC5t3nUm1eqS1xmWL8HGruny5aBOHLl6lXfVSTO3ZilZf/0xoTPJ2q1AwJ7vPBDFp5Q7ibt+lVeUSTH6nJZ0mzufUFeO40K9pdZpVKMbIheu5GB5NDb+8THjrVbpMWpCQJ6OrU784fd5vxOTxqwk4GkyzVuX5atzrdO88PcX7dNS4jqz+8xBjPl9GidK5ee/DJsTEJN6nIz/9HRvbp+9TO76f3ZO/Np9Ms3qltnq1i9KvZ30mTF3P8ROXadGkLGM+b0vX3j8RHpH8estia01M7C3mLthFu9YVzZ4zLu4OcxfsIuhyJPfvP6RalYIM/qAp0TG32HcwMJVr9GKCg4MZMWIEq1ev5tq1a/j6+tKqVSs+++wzPDw8nuscgYGB5M+fn0OHDlG2bNnULbDIv6BldCKSobzRqAJ//HWcP/46TmBIFP+bv4WwqDjavlLGbP7/zd/CL6v3c+JiGMFhMUxdvIPgsGhqly2YkGfYD6tZtPkIZ4IjuBQazZez1mMwGKhUPPmn2hlVp4YV+GP7cf7Y9rjdfttCWHQcbeum0G6/beHnNfs5ERhGcHgMU5fuICgsmlplCprkszIYGNWjKT8s38WViNi0qEqaeqdMRRaePMZvJ49xPjqKz3dsJuRGHJ1Lln3mcV/VacQfZ09yMCwk2WOxd+8QcftWwk+t3Hm5HX+fleczz5vY2lVhwDvQ6DlnHS34A3y94dP3oGA+aNcc2jSFmU9NvPl5EVSvAD07Q4G8xv9XrQA//54qVUgXr71elTV/HmLNn4cJvnSN6RPXERF+nRZtzL/Rata6AuFh15k+cR3Bl66x5s/DrF1xmLZvVEvIE3f9DtFRNxN+ylfOz52799m2KfO8ie3QvAIrNh3jz03HuHQlim9nbyH8WhytG5nv30IjrvPtrM2s+esEN27dNZsn7sYdomJuJfxUKp2Xu3fvs2lX5gkKd6lbnqV7jrNkz3EuhkfxzbKthMbE0b5GabP5v1m2lVmb9hMQHEbQtRgmrdrBpWsx1ClRICFP84rF+HHDXrafDORKZCwLdx5l5+lAutQ1H9TLiF7rUIU1Kw6z+s/DBF2KZNq36433aWvzdWzeqjwRYdeZ9u16gi5FsvrPw6xdeZh2r1dNyBMXl+Q+rVSAO3fv81cmuk/bt67IqnVHWbn2KJeCo5jywyYiIuJo2ayc2fyh4deZ/P0m1m4K4MZN8/fp4WPBbNt1lkvBUVwNjWHxHwe4cDGCUiVypWZVXtiFCxeoWLEiZ86cYf78+Zw7d47p06ezceNGqlWrRlRUVHoXUcSiFGwSkQzDxtqKovmysyfJUq49AZcoXTDHc53DYAD7bFmIvXknxTzZstpgY23N9WfkyUhsrK0omjd7siVwu/9huzlky5KsTd5pUZXouNv8sf24xcr7srC1sqKkV3a2BQeapG8LDqRC9pTbrV3RkuRxceXbfTuf63naFyvFn2dPcTv+/r8pboZ2OABqVDJNq1EJAk7D/Xjj30cCoLqZPIcC0qaMqc3GxorCfr4c3HvBJP3AnvMUL2X+jVPxkjk5sOd8svxFivlibW3+JZ5/i3JsXR/AnTuZ43qzsbHCr0B29h4x7d/2Hr1ESb/n69+eR/P6Jdmw8zR37sZb7JzpycbaimK5spssgQPYdTqIsvn+wbiQ1ZbYW4njQhYba+7Fm7bR3fvxlCtguX+L9GRjY0URP18OJL1P916gREnz92mxkrmS5d+/5wJFiqZ8nzZpXpYtGzLXfVqkkE+y2Ub7Dl2kZLGcFnue8mXykDuXG0ePp7ykMT317duXLFmysG7dOurUqUOePHlo0qQJGzZs4MqVKwwZMgQAg8HAsmXLTI51dXVl9uzZAOTPnx+AcuXKYTAYqFu3bkK+mTNnUqJECbJmzYqvry/9+vVLeCwoKIiWLVvi6OiIs7Mz7du3JywsLOHxESNGULZsWWbOnEmePHlwdHSkT58+PHjwgG+++QYfHx+8vb358ssvTcoWGxtLz5498fb2xtnZmVdeeYUjR45YsOUko1KwSUQyDFcnO2ysrYi6ftMkPTL2Fh4u9s91jk6NK5Itqy0b9qb86XS/trWIiL7B3oCgf1Xel4Wro/l2i7p+C8/nbLfOjYzttn5/YruVKZSDljVLMurndRYt78vCLZsdNlZWRNy+ZZIecetWsqVxT+RzceXjqrUYsH4lDx49+tvnKOPtQ1EPL347ecwiZc6orkWBh5tpmqc7xD8wEB2bmMczaR43Y3pm4Oxqj7WNFdFRpvdpdPRN3NwdzR7j5uFIdHSS/FE3sbGxxsU1+b3tVzwH+Qt6s/rPQ5YreDpLGBdiTO/T6JibeLiav0//qWKFfCiYx4s/N2ae+9TNwdhukXGm7RYZdxNP5+cbF7rWrYBdFlvWHU6clbnz1CXerFuBPJ6uGAxQtUge6pYsiJezZf4t0pvLs+5TD/P3qbu7wz+7T4s9uU8PW6zc6c3F2f7xfZq03W7h7vbvrg0H+yysXjyAjcs/5OuRbZk0bSP7D6XNHmF3797l+vXrJj9375qfhRUVFcXatWt59913sbOzM3nMx8eHTp068dtvv/HoOV477N27F4ANGzYQEhLCkiXG/R6nTZtG37596dmzJ8eOHWP58uUUKlQIgEePHtGqVSuioqLYunUr69ev5/z583To0MHk3OfPn2f16tWsWbOG+fPnM3PmTJo1a8bly5fZunUrY8aMYejQoezevTvhvM2aNSM0NJRVq1Zx4MABypcvT/369TVTS7Rnk2Re2bJl44MPPkjvYvyHpN2Ss6TjsMEAfz80Q6MqfvRsVY2PJv1BdNxts3nebFKRRlWK0nvMQu7FP/j3hX2JmG2352i4xpX96PlqNT6ckthu9llt+bx7E778eT2xNzLHDLAUJWkkgwHMXXFWBgPfNmzOxH07uRgb/Vyn7lCsFKciIzgSnrk2o38RxnZN9KTZDc/KYyYto0v6RsOAgWf2cEkfMpg/D4B/i7JcPB/O6RNX/10hX0KPkjaEwfBc/dvzaP5KSc4HRXDyXOa7T5ONCzxfuzUp50efxtXoP3M5UTcSx9MxS7cwvEMD/vikK48eweXIGP7YG0DLyiUsXPL0lfw+NX/PpZj/Wfdp88f36cnMd5+a66+eJ7jyLLdu3+OdfrOxs8tC+TJ5ebdHPa6GxnD4WOrPbho9ejQjR440SRs+fDgjRoxIlvfs2bM8evSIYsWKmT1XsWLFiI6OJiLi7/c28/LyAsDDwwMfH5+E9FGjRvHhhx/y/vvvJ6RVqmScErxhwwaOHj3KxYsXyZ3b+Jr9l19+oUSJEuzbty8h38OHD5k5cyZOTk4UL16cevXqcfr0aVatWoWVlRV+fn6MGTOGLVu2ULVqVTZv3syxY8cIDw8na9asAIwbN45ly5axaNEievbs+bf1kcxLwSbJtEaPHp3eRfhPqfTW/1L9OWLibhP/4CEeLqafgrk72xMVeyuFo4waVi7CsLca8X9TV7D3hPkZS539K/BW88r0HbuYc5evWazc6S3mhvl2c3OyJ/L637RbpSIM69qIwdNXsPdkYrvl8nYlp5cL/3uvVUKa1eNXz7u/H8BrQ2dl+D2cou/cJv7hQ7ySzGLytLPn2q3k7eZom4Uy3j6U8PRmZK36gLFNrAwGzvUeyJt//s6uK4kvfrPZ2NC8UFEm7NuRuhXJADzdk89QiowGG+tHuLok5okwkyfpjKiM6nrMLR7EP8Q9yewIVzf7ZLMonoiOvIGbe5L72s2B+PgHXI81DahnzWpD3QYlmDNjq2ULns4SxoUks5jcXOyJijXfbv9E1iw2NKhRlB9/y1z3afRNY7slncXk7mSfbLZTUo3LFmFEx4Z8NGcle86YjqfRN28zYOafZLGxxtUhG+GxNxnQvCZXopJvnJ0RxaZ4nzoQk8J9GhV1E3f35PlTuk/rNSjOnB8z130ae/0W8Q8eJpvF5OZqT3TMs6+3v/PoEVwJiQHg3IVw8ubxoFP7qmkSbPrkk08YOHCgSdqTgMs/9SToZnjBT1DCw8O5evUq9evXN/v4yZMnyZ07d0KgCaB48eK4urpy8uTJhGBTvnz5cHJySsiTPXt2rK2tsXrqi02yZ89OeHg4AAcOHODGjRvJNje/ffs258+bLvOW/x4Fm0Qkw4h/8JBTgWFUKZGHLQfPJaRXLp6Xvw6nPKA1quLHsLcbM3T6SnYcvWg2T2f/inRvUYX3xi/hZGCY2TwZVfyDh5y6FEaV4nnYciix3aoUz8vWZ7Rb48p+DOvWmCE/rGTHMdN2CwyJosNnc0zS+rSugX22LIyfv9nsN9xlNPcfPuR4RBg1c+dj7cXEdquZKx/rA88lyx937y6NFsw2SXuzZFmq58xNn7V/EnzdNPjWvKAfWa2tWXo683wr2IsqWwK2JNniasc+KOEHto9fqZQpATv3Q7f2iXl27oNymWTCRHz8Q86eDqF8pQLs2Jq4XLV85QLs2mZ+8/gTx69QtWZhk7TylQtw5mQIDx48NEmvXb84trY2bFyTeZaCgbHdTl8Io1LpvPy1N/G+rFQ6L9v3Jb9P/6n61f2wtbFm7V+ZZ6NmMI4LJy+HUa1IXjYdSxwHqhbJw+bjKY8LTcr5MbJjIwb/soptJ8yPpwD34h8QHnsTGysrGpQubLLULiOLj3/ImdMhlK+Unx1/PXWfVsrPzu3m63jy+GWq1jC9TytULsCZU8nv0zqP79MNazPXPojx8Q85cy6UiuXysW3X2YT0iuXysX33v79Pn2bA+I2TaSFr1qzPHVwqVKgQBoOBEydO0KpVq2SPnzp1Cjc3Nzw9PTEYDMlmfN2//+z9u5IuzUvq0aNHZgNZSdNtbW1NHjcYDGbTHj40XrsPHz7E19eXLVu2JDu3q6vrM8skmZ/2bBKRDGXeugO0rF2KFrVKkM/XnQ861sHHw4nFm40bEfZtW5MR7/gn5G9UxY+R7/jz7YKtHD8fgoezPR7O9jjYZUnI82aTivRpU53PZ64j5FpsQh67rLbJnj+j+nX9AVrVKsWrNYztNrBDHXzcnVi85XG7tanJyLcT261xZT9Gvu3PxIVbOX4hebvdi3/A+auRJj9xt+5y6849zl+NJD7JC+iM6scj++lQrBTtipakoJs7w2rUJYeTE78eN7bbx1VrMb5+E8C4OuBM1DWTn8jbt7j74AFnoq4l2wC8fbFSrLt4jpi7mW8Z4s1bcPKs8Qfgcojx96uP47j/+wEGP7W/aMeWxse+ngLnA2HxSliyCt7umJinS1tjsGnGPLhwyfj/XQegS7s0q1aqWzx/N/6vlqNx8zLkzutJ7/cb4p3dhRVLDwDwdp9XGPRZy4T8K5ceILuPC736NyR3Xk8aNy+Df4tyLJq3K9m5/VuUY+dfp4m7bn4JcUb224oDtKhfimb1SpI3pzv9u9Ylu6cTS9cZ79Peb9RkaD9/k2MK5/OicD4v7LPZ4upsT+F8XuTL5Z7s3M1fKcm2fee4ngmXC/+85SBtqpakVeUS5Pd2Z1CrOvi6OfH7zqMA9G9Wgy/faJyQv0k5P0Z1asz45Vs5eikEDyd7PJzsccyWOJ6WyuND/VKFyOnhQvkCOZnWqzVWVgZmbdqf5vVLLYt/20OTFuVo3KwMefJ60Lv/k/v0IABv967Hx0NfTci/YtlBvH1c6PVeA/Lk9aBxszL4Ny/L7/N3Jzu3f/Oy7NiWOe/ThUv306xxaZo2LEXe3O707fEK3l7OLF91GIAe3Wrz6YdNTY4pVMCbQgW8sbPLgquLPYUKeJM3d+IMmk7tq1CxXF58fVzIk8ud9q0r0rh+CdZvfvk+xPHw8KBhw4ZMnTqV27dN/31DQ0P59ddf6dChAwaDAS8vL0JCEr/N9uzZs9x6akZ1lizGe+7Bg8TtHpycnMiXLx8bN240+/zFixcnKCiI4ODEGV8nTpwgNjY2xaV9z6N8+fKEhoZiY2NDoUKFTH48PT1f+LySOWhmk4hkKOv3nsHFwY53Xq2Kp4sD569EMmDCUkIjjTNpPF0c8PFInP7bpm5pbGysGdylPoO7JE4tXrE9gJE/rQWg7StlyGJrwzf9Wpg81w/LdjHjj+Rv2jKi9fset1uLx+12NZL3v11KaFQK7VbH2G7/17k+/9c5sd3+3BHAyFlr07z86WXFudO4ZrXj/YrV8HJw4EzkNd5asYQrN4xLQrztHcjp6PyPz5vfxY3KOXLRefnvli7ySyHgNHQdkPhJ6ZjvjL+38n/E6E8gIhJCwhPz5/KF6WOMwaZ5y8DbAz7tD43qJOYpVxLGfwbf/gSTf4LcOWD8CChTPG3qlBa2bjyBs4sdnd6ujbuHI5cuRDD0w/mEhxpnxbl7OOKdPfF6Cw2JYciH8+n9fiNavFaRqGtxTJ2whu1bTpmcN2dud0qVzcP/9Z+bpvVJKxt3nsbZMRtvta2Kh5sDF4Ij+eirJYRdM/ZvHm4OZPc0vU9nj+2S8HvRgj40qlWMkPBY2vb9MSE9t68bZYrlYsAXi9KmImls7eEzuDpko1fjKng5O3AuJJK+PywjJNrYbl7ODvi4JY4LbauXwtbamiFt6zOkbeK48MfeAIbNN35RRBZba/o1rU4uDxdu3b3P9pMX+fTXNcTdMb9pcka0deMJnJ3t6PxWLdw9HAm8EMGQjxYQHma8Tz08HPHO7pKQPzQkhqEfLaB3/4a82qYikdduMHXiWvP3aZk8DB7wa5rWJ61s/usULk7Z6PJGdTzcHbgYeI3BwxcRFm4cTz3cHPD2Mr1Pf5rSLeH3ooV9aFivOCFhsXR863sAsmWz5YN3G+Hl6cjde/EEBUcxatxKNv9l2rYviylTplC9enUaN27MqFGjyJ8/PwEBAQwaNIicOXMmfMvbK6+8wpQpU6hatSoPHz5k8ODBJrOLvL29sbOzY82aNeTKlYts2bLh4uLCiBEj6N27N97e3jRp0oS4uDh27NjBe++9R4MGDShdujSdOnVi4sSJxMfH8+6771KnTh0qVqz4wnVq0KAB1apVo1WrVowZMwY/Pz+uXr3KqlWraNWq1b86t2R8hkf/dlc2STMffPABEyZMSO9iiJiVFns2ZUaP0mamd6ZzrXzmmDmV1i60+SG9i5Bh+bd+M72LkCHdzPV832wmpuJyafHBi8i+99/v0/VfdM8ly99nkmS2rvr4Hx9z6dIlRowYwZo1a4iMjMTHx4dWrVoxfPjwhH2Prl69yltvvcWOHTvIkSMH3377La+//joTJ06kW7duAPz44498/vnnXLlyhVq1aiUsY/v++++ZMGECFy5cwNPTk7Zt2zJp0iQAgoKCeO+999i4cSNWVlb4+/szefJksmfPDsCIESNYtmwZhw8fTihvt27diImJYdmyZQlpdevWpWzZskycOBGAuLg4hgwZwuLFi4mIiMDHx4fatWszevRokz2i5L9HwaYMRMEmeZkp2PRiFGx6MQo2vRgFm16cgk0vRsGmF6Ng04tRsOnFKNj0Yl4k2CTyX6KRTERERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLsUnvAohI5mB/7UF6FyFDuuGjbvhF5F73KL2LkCH5//Jmehchw1qz9Jf0LkKG1KTJ6+ldhAzphq9rehchQ7pewD69i5AhOQXdSe8iiEgmpJlNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxNuldABGRf6pV07J0bFMJdzdHAoOuMWXGJo6euGI2r7ubA32716VIQR9y5XBj8Z8HmPLj5hTP/Uqtogz/uAXbdp9l6JfLUqkG6aNd3dK82bgini4OXLgaybjftnL4rPl2q1euEG3rlsYvtxe2NtZcuBrJD3/uZlfAJbP5G1Uqwuiezdhy6BwfTv0zNauR5lo1KcvrrSrh4eZIYPA1Jv2U8vXm4eZA37fq4lfQh1y+bixaeYDJP5leb01eKcGn/ZsmO7Z+u/9x7/6D1KhCumjRpgLtOlXD3cOJSxcjmDZxLcePBKeYv1S5PPTu34i8+b2IvBbHwl93snLpwYTHx373JmXK50t23J4dZxn20YLUqEKa23cEZs6HgDMQEWlg8qhHNKj17GP2HoYx38G5QPD2gO6vQ8eWpnnWbYVJP0HQVciTA95/BxrWTq1apI/m7SrRrmsN3D0duXQ+gunjVnP8UFCK+UtVyEuvgf7kLehFZEQcv8/ZwcpF+83mrdO4JJ9+3Y6dm08ycmDmuNaeaF+zNN3qV8TT2YHzoZF8s3grhy6Y79/qly5Eu5ql8cvlRRYba86HRDJ99W52njIdFzrVLUf7GqXxcXMm5uZt1h8+y6Q/t3MvPvP0b6/VL0PnZhXxcHHg4pVIJszdwuEz5tutbsVCtKlfhiJ5vMhia82Fy5HMWLqLPccS2y1/Tg96vVYdv3ze5PByYcLczSxYeyitqpNmXm1VnnYdq+Lh7khgYARTp2zg+NGUx4XSZfLQu2998uXzIjIyjt/m72bF8sR2sba24vXO1WnUuBSenk4EB0fy4/eb2bf3QlpUx6ICAwPJnz8/hw4domzZsqn2PFu2bKFevXpER0fj6uqaas8jAprZJCIZTL2afvR75xV+WbibHu/P4WjAZcaMaIu3l5PZ/FlsrYmJvc3chbs5fzH8mefO7uVMn7frcuR4yi98MqqGFYvwYYe6zFy5lzc+/5VDZ68wuX8rfNzNt1v5IjnZcyKI/pOW0XnUPPafvsyEfi3xy+2VLK+PuxMD2tXm4JnLqV2NNPdKDT/6v/0Kv/y+m+4D53DkxGXGDmuLt6f5drN9fL39/PtuzgWmfL3duHmXlt2mmvxkpkBTnfrF6T2gMfNmb6dP1xkcOxLEl/97A6/szmbz+/i68uX41zl2JIg+XWcwf8523v3An5p1iybk+fyT3+nQ7H8JPz3emM6D+If8telEWlUr1d2+DX6FYOiA58t/OQR6D4YKpWHJDOjZGb6aZAwuPXHoOAwcCa82gmU/Gf8/cAQcyTzNRp1GJeg9yJ/5P/3Fu69P5/ihS4ya0hkvHxez+bPncGXU5M4cP3SJd1+fzoKZ2+jzcRNq1i+WLK+3rws9PmjEsYOBqVyLtNe4XBE+blOXGev20uGbXzl4/gpT+7TCxy2FcaFQTnafDqLf9GW8PnYe+85eZlLPlhTNlTguNK1YlPdb1GT6mt20/moOI+avo3H5IvRvUTOtqpXqGlQpwged6zLrjz10GTaXw6evMGFQa7J7mG+3cn652Hv8Eh+MW0rXYb9y4GQw4we2okjexHbLlsWGK+GxTF24nWsxN9KqKmmqbr1i9OnXkHm/7KB3j584djSY0WM64O2dwrjg48KXY9pz7GgwvXv8xLy5O+nbvxG1avsl5HnrnTo0b1GOKd+uo3vXH1ix/BAjRr1GocLZ06paz61bt24YDIaEHw8PD/z9/Tl69Gi6lmvLli0m5fLy8qJJkyYcOXIkXcslmYOCTSKSobRvVZFV64+xct0xLl2OYsqPm4m4FkfLJmXN5g8Nv87kGZtYuzmAG7fupnheKysDQz9qxqx5O7gaFptKpU8/nRuW54/tx1m2/TiBoVGM/20rYdFxtK1T2mz+8b9t5ee1+zkRGEZweAzfLd1BUHgMtcsUMMlnZTDw5TtN+H75Lq5cy3zt1qFlRVZuOMaKDcbrbfJPmwm/Fkdr/7Jm84eGX2fST5tYuyWAm8+43h7xiKiYmyY/mclrr1dlzZ+HWPPnYYIvXWP6xHVEhF+nRZuKZvM3a12B8LDrTJ+4juBL11jz52HWrjhM2zeqJeSJu36H6KibCT/lK+fnzt37bNt0Mq2qlepqV4UB70Cj55x1tOAP8PWGT9+DgvmgXXNo0xRmPjX55udFUL2CMRBVIK/x/1UrwM+/p0oV0kWbztVZu+wQa5YeJPjiNaaPW0NE6HWat6tkNn/ztpUID4ll+rg1BF+8xpqlB1n3xyFe61LDJJ+VlYHBX77GL9O3EHI5Oi2qkqberFeepbuPs3TXcS6GRTF2yVZCo+NoX9P8uDB2yVZmb9xPQFAYQRExTF6xg6CIGOqUTBwXyuTz5fCFq6w+cJqrUdfZdSqINQdOUyLPy/fm/0W93qQCy7ceZ/nW4wRejWLCr1sIi4zjtfplzOaf8OsW5q7cz8mLYQSHxTDt9x0Eh0ZTq1zBhDwnL4YxecFfrN99OlN98PC019pXZs2qI6xeeYSgS5FMm7KB8IjrtGhZ3mz+5i3LEx5+nWlTNhB0KZLVK4+wZtUR2nWskpCnQaOSzJu7k717zhMSEsOffxxk/94LtG1fxew505u/vz8hISGEhISwceNGbGxsaN68eXoXC4DTp08TEhLCypUriY6Oxt/fn9hY86/r7t+/n8al+3svY5lEwSYRyUBsbKwoUsiHfYcCTdL3HQqkZLGc/+rcXTtWJzb2NqvWH/tX53kZ2VhbUTRvdnafMF3qsDsgiNIFczzXOQwGcMhqS+zNOybpPVpUJfrGbf7YHmCx8r4sbGysKFLQh72HA03S9x0OpGTRf3e92WXLwu8/9GTxj70ZM6QNhfN7/6vzvUxsbKwo7OfLwSTLGA7sOU/xUrnMHlO8ZE4O7DmfLH+RYr5YW5t/qeLfohxb1wdw585/9wXm4QCokSSeUqMSBJyG+/HGv48EQHUzeQ5lklvWxsaawsV8ObDrnEn6gd3nKV4mt9ljipXJxYHdptfb/p3nKFIsB9Y2iddbp551iY2+xdplB5OeIsOzsbaiWO7s7EqyBG7XqSDK5H/+ccE+ybhw6MIViuX2puTj4FJODxdqFs/HtoCLlit8OrKxtqJovuwmS+AA9h6/RKnC/6DdsmUh9sadv8+cSdjYWFGkiC/79yUZF/ZdpHjJFMaFEjk5sM/0utm/7wJF/BLHhSy21ty7F2+S5+69eEqmMNakt6xZs+Lj44OPjw9ly5Zl8ODBBAcHExERYTb/1q1bqVy5MlmzZsXX15f/+7//Iz4+sb53796lf//+eHt7ky1bNmrWrMm+fftMzrFq1SqKFCmCnZ0d9erVIzAw0OxzeXt74+PjQ+XKlRk/fjyhoaHs3r2bwMBADAYDCxcupG7dumTLlo25c+cCMGvWLIoVK0a2bNkoWrQoU6dOTTjfvXv36NevH76+vmTLlo18+fIxevTohMdHjBhBnjx5yJo1Kzly5KB///4JjxkMBpYtW2ZSPldXV2bPng3wwmWStKc9m0Qkw3BxtsPG2irZLJDomJu4uzq88HlLFstJ04aleOf9Of+2iC8lV0dju0Vev2WSHhl3Ew+XvM91js4NK5Atqy3r959JSCtTMActa5bgjc/nWrS8LwsXJ2O7RSe93mJv4u724tfbpctRjJ60mvOXInCwz0K75hWY+vUbvDVgNpdDYv5lqdOfs6s91jZWREclabfom7i5O5o9xs3DkejoJPmjbmJjY42Lqz1RkabLSvyK5yB/QW/+91Xm2h/sn7oWBR5upmme7hD/wEB07CO8PYx5PJPmcTOmZwbObvZY21gTk+R6i4m8gZtHytdbTJJrKibqJja2j6+3azcoXiY3jVuV492O01Ot7OnJzeHxuBCXfFzwdHq+caFLvQrYZbVl3aHEcWHNwTO4Odoze0AHMICttTW/bTvCzA37nnGmjMP18bgQdd30eouMvUVVF/vnOkenJhWxy2rLxr2nU6OILyUXl5THBXd38+Opu7tDyuOCix1RUTfZv+8ibdtX5tiRIK5ejaZchXxUr1EEKytDqtXlaXfv3uXuXdNZzFmzZiVr1qx/e+yNGzf49ddfKVSoEB4eHty8aVrXK1eu0LRpU7p168bPP//MqVOn6NGjB9myZWPEiBEAfPzxxyxevJg5c+aQN29evvnmGxo3bsy5c+dwd3cnODiYNm3a0Lt3b/r06cP+/fv58MMP/7ZsdnZ2gOlsocGDBzN+/HhmzZpF1qxZmTFjBsOHD2fKlCmUK1eOQ4cO0aNHDxwcHOjatSuTJk1i+fLlLFy4kDx58hAcHExwsHGbikWLFjFhwgQWLFhAiRIlCA0NfaFle/+0TJL2FGz6D/vkk0+4c+e/86mKpLbn+0TPIh4l+dtg4FGyxOdjZ2fL0A+bMm7KWmKv3/73ZXuJPUrSRAYMydvSjMaV/ej1ajUGfrec6DhjG9lnteWLd/wZ9fMGYjL5p7PJm8jAo6SN+Q+cOBPCiTMhCX8fO3mFn/7XldealefbHze98HlfNknbyICBZ15wye5r8+cB8G9Rlovnwzl94uq/K2QmYEjynupJcxmelcdMWkaX7HozGJJ3ek/nT/E8YGefhcFfvsbEL5ZzPeZWCjkzh2TjgsHwXKOpf3k/+jSpxvszlhN1I3HsrFgoF+80qsyXv2/iWGAIebxc+bhNXa5dr8IPa/dYtvDpKHm7PfNyS9Coqh/vtKnGoAl/EJ3JX3OYY66bf2a7mbuvnzrPd5PWM3BQE2b+0gsewdWr0axdfZTGTcwvBbW00aNHM3LkSJO04cOHJwSDklqxYgWOjsYg+M2bN/H19WXFihVYWSWfwTt16lRy587NlClTMBgMFC1alKtXrzJ48GA+++wzbt++zbRp05g9ezZNmjQBYMaMGaxfv56ffvqJQYMGMW3aNAoUKMCECRMwGAz4+flx7NgxxowZk2KdIiMjGTlyJE5OTlSuXJlbt4x94IABA2jTpk1Cvi+++ILx48cnpOXPn58TJ07w/fff07VrV4KCgihcuDA1a9bEYDCQN29iEDsoKAgfHx8aNGiAra0tefLkoXLlys/R4qb+aZkk7SnY9B92584dJkyYkN7FkEyiTouxqf4csddvE//gYbJZJW4u9kS/4BuCnD5u+GZ35athiYOV1eMXMxuXfcibvX/iamjMC5f5ZRBzw9hunkk+dXV3sk822ymphhWL8FmXhgz+fiV7TyZ+s1Mub1dyerowoV/i1149abc909/ntWGzuRyRsfdwio17fL25Wu56M+fRIzh1NoRcvm5/nzkDuB5ziwfxD3FPMqvE1c0+2afaT0RH3sAtyafbbm4OxMc/4Hqs6RuyrFltqNugBHNmbOW/ztM9+QylyGiwsX6Eq0tinggzeZLOiMqorkff4kH8g2SzmFzcHZ59vSW9Pt0diL//gOuxt8hbwBufnG58PvGNhMcNj2dKrNr3Gd1bT87wezhF33w8LjgnGRcc7ZPNdkqqcbkijHijIYNmrmTPGdNv/OvbrDor9p1k6a7jAJwLicQuiy3DOjZgxro9zxWQeZnFPB4XPFxM+yt3Z3ui/mY8bVClCEPeacSnk1ewLyDlb0rMjGJjH48LSfp5V7fks5eeiIpKPhvW1c3eZFyIjb3F8KGLsc1ijbOzHZHXbvBOr3qEptEs4U8++YSBAweapD1rVlO9evWYNm0aAFFRUUydOpUmTZqwd+/eZHlPnjxJtWrVEgJsADVq1ODGjRtcvnyZmJgY7t+/T40aiXvN2draUrlyZU6ePJlwjqpVq5qco1q1xL0Qn5Yrl3Hp4c2bNylcuDC///473t7eCcvuKlZM3HMxIiKC4OBgunfvTo8ePRLS4+PjcXExDj7dunWjYcOG+Pn54e/vT/PmzWnUqBEA7dq1Y+LEiRQoUAB/f3+aNm1KixYtsLH5Z6GJf1omSXsKNolIhhEf/5Az50KpWC4v23afTUivWDYv2/ece8aRKQu6HEm3vrNM0rq/WRN7uyxM/mET4deu/6syvwziHzzk1KUwqhTLy+ZDifuUVCmeh62Hz6d4XOPKfnzWtRFDZqxi+zHTfRMCQ6JoP/xnk7R3W1XHPlsWxi3YQmhUnGUrkQ7i4x9y5nwolcrmZduexOut0r+43lJSKL83Fy5ds+g500t8/EPOng6hfKUC7NiauEykfOUC7Np2xuwxJ45foWrNwiZp5SsX4MzJEB48eGiSXrt+cWxtbdi4JvPtr/ZPlS0BW3aapu3YByX8wPbxK7wyJWDnfujWPjHPzn1QrkTalTM1xcc/4OzJEMpXLcjOzacS0stXLcCuLeaXKZ08cpkqdYqYpFWoVogzJ6/yIP4hwYHX6Nn2O5PHu/V9BTv7rEwbu5qI0MwxLpwMDqOqX142HU0cB6oWzcOWYymPC/7l/Rj5RiP+b84qtp1Ivg9Ttiw2yWaZPXj4CMPj/150FvLLIv7BQ04FhlG5ZB62HkgcByqXzMtfB1Nut0ZV/RjSozHDpq5kx5HMsX/VPxEf/5AzZ0KoUDE/O54aBypUzM/O7SmMCwFXqFbddFyoWKkAZ04nHxfu33tA5LUbWFtbUau2H1u3pM0XRzzvkrknHBwcKFSoUMLfFSpUwMXFhRkzZvDOO++Y5H306JFJkOhJGjyegfjU7ykd909mYW/btg1nZ2e8vLxwdk7+DYEODomBwocPje0/Y8YMqlQx3Yzd2toagPLly3Px4kVWr17Nhg0baN++PQ0aNGDRokXkzp2b06dPs379ejZs2MC7777L2LFj2bp1K7a2tib1e8LcBuD/tEyS9hRsEpEMZeGy/QwZ2IzTZ0MJOHWV5v5l8PZyZvlq41rvHl1q4eXhxFcTViUcU+jx5st22bLg6mJPofze3I9/wKXgSO7df8DFINM3+TduGtffJ03PyOauP8gX3f05cSmMo+dDaFO7FD7uTizaavzK3X6ta+Dl5sjwmWsBY6Dp87caM+63LRy7EILH40+/796P58bte9yLf8D5q5EmzxF329huSdMzst/+2M/QAc04dS6UgNNXebVRGbw9nVm21ni99epcC08PJ778NoXrzdl4vcXff0DgZWO7dOtQnROnrxIcEo2DfVbaNitP4fzeTPhhQ9pXMJUsnr+bj4e34sypq5w4doVmrcrhnd2FFUsPAPB2n1fw8HJi7Od/ALBy6QFatq1Ir/4NWfXHIYqXyol/i3KM/mxJsnP7tyjHzr9OE5cJl6DcvAVBVxL/vhwCJ8+CizPkyA7/+wHCImDMEOPjHVvCvKXw9RTjN9EdDoAlq2DcZ4nn6NIW3uwPM+ZB/RqwcQfsOgBzp6Rt3VLTkrk7GTSqDWdOXOXk0WCatqmIt48LKxcZ9wl6670GeHo7MXbYUgBWLNrHqx0r0/PDxqxecoBipY37M339ySIA7t+L59L5cJPnuBFnXC6cND0j+2XzQb58058TwWEcuRjCa9VL4evmxO/bjeNC/xY18HZxZOhc47jgX96PUW825pvFWzgaGIKH01Pjwp17AGw9foE365Xn1OVwjgWGktvLlb7NqrP1+HkeZvRpTY/NX32AEb2bcOpiGMfOhdCqXimyezixZKNxXHi3fU283BwZ+f0awBhoGt7Ln//N3cLxcyG4P55lfPdePDdvG9vNxtqK/Dk9ALC1scbLzYnCeby4fec+l8Nj0r6SqWDxwr0MHvIqZ06HcCLgCs2al8Pb25k/lxs34O/eoy6eXk6MebwX34o/DtKydQV6963PqhWHKV4iJ/5Ny/DV58sSzlm0WA48PZ04fy4MDy8nunSrhZWVgd/m706PKv5jBoMBKysrbt9OPp4VL16cxYsXmwSPdu7ciZOTEzlz5sTd3Z0sWbKwfft23njDOAvz/v377N+/nwEDBiScI+lG27t3m2+b/Pnz4+rq+lzlzp49Ozlz5uTChQt06tQpxXzOzs506NCBDh060LZtW/z9/YmKisLd3R07OzteffVVXn31Vfr27UvRokU5duwY5cuXx8vLi5CQxO0Gzp49m7Cc79+WSdKWgk0ikqFs3n4aF2c7unSsjoe7AxcvXWPwyMWERRg/afZwd8Tby8nkmJ8mJa7TLlrYh4Z1ixMSFkvHd35I07Knp/X7z+DqmI0ezavg6eLA+auR9J+0LGEGkqerAz7uie3WpnYpbGys+b9O9fm/TvUT0v/cGcCIWevSvPzpZdOO0zg729GtQ3U83By4GHSNj78wvd6yJ7neZk146nor5EOjOsUJCY+lfU/j9ebkkJVB7zbC3c2BmzfvcvZiOP2GLODk2dC0q1gq27rxBM4udnR6uzbuHo5cuhDB0A/nEx5qXFrp7uGId/bET05DQ2IY8uF8er/fiBavVSTqWhxTJ6xh+5ZTJufNmdudUmXz8H/9M+em9AGnoeuAxE+px3xn/L2V/yNGfwIRkRDyVKwjly9MH2MMNs1bBt4e8Gl/aFQnMU+5kjD+M/j2J5j8E+TOAeNHQJniaVOntLB1XQBOLvZ06lkHd08nLp0LZ+h7vxIe8vh683TEyydxGUXY1RiGvjeXXh/606J9ZaIi4pj2zWq2b0yb2RAvi7WHzuDikI2ejavg5eLAuZBI+k5fRkj043HB2QEft8T+rW2NUthaWzOkfX2GtE8cF/7YE8BnvxrHhRlrjUvl+jYzBqqib9xia8AFpqxIMgUvA9uw5wwujna83aoqnq4OXLgcyQfjlhIaaWw3D1cHsnsktlurV0pjY2PNx93q83G3xHZbsS2AL34wBvK83ByZ++WbCY91blaRzs0qcuBkMO9+9Xsa1Sx1bdl8EmcXOzp3qYm7hyOBFyP4dPBvhIcZx1N3D0e8vZ8aF0JjGTJ4IX36NeDVVhWIjLzBd5PWse2vxBmLWbLY8NY7dfD1deX27Xvs3XOeMV8u5+aNu8me/2Vw9+5dQkONY310dDRTpkzhxo0btGjRIlned999l4kTJ/Lee+/Rr18/Tp8+zfDhwxk4cCBWVlY4ODjQp08fBg0ahLu7O3ny5OGbb77h1q1bdO/eHYDevXszfvx4Bg4cSK9evThw4EDCN7r9WyNGjKB///44OzvTpEkT7t69y/79+4mOjmbgwIFMmDABX19fypYti5WVFb///js+Pj4J3yr34MEDqlSpgr29Pb/88gt2dnYJ+zq98sorTJkyhapVq/Lw4UMGDx6Mra3tvy6TpD3Do3+zy6mkqQ8++MCieyxZ+nzy35YWezZlRjd8FPN/EfYR8X+fSZKxC8vcm7mnpjVLf0nvImRITZq8nt5FyJBCa7mmdxEypGzRelvzIpyCNDa8iA1bP33uvN26dWPOnMRvPXZycqJo0aIMHjyY1157jcDAQPLnz8+hQ4coW7YsAFu3bmXQoEEcOXIEd3d3unbtyqhRoxL2Nrpz5w4ff/wx8+fPJy4ujooVKzJhwgQqVaqU8DwrVqzggw8+IDg4mMqVK/PWW2/x9ttvEx0djaurK1u2bKFevXoJfydlrlxPzJs3j7Fjx3LixAkcHBwoVaoUAwYMoHXr1syYMYOpU6dy9uxZrK2tqVSpEmPHjqVcuXIsW7aMr7/+mpMnT/LgwQNKlSrFqFGjqF/fGIy9evUqb731Fjt27CBHjhx8++23vP7660ycOJFu3bq9cJkk7SnYlIEo2CQvMwWbXoyCTS9GwaYXo2DTi1Ow6cUo2PRiFGx6MQo2vRgFm17MPwk2ifwXJf+eRRERERERERERkRekYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFmOT3gUQkczB/lBwehchQ7LzcEnvImRIt3M5pXcRMqSbuezTuwgZVpMmr6d3ETKk1avnp3cRMqR6PXqkdxEypPv2+hz9RdzyyZreRRCRTEg9soiIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWo2CTiIiIiIiIiIhYjIJNIiIiIiIiIiJiMQo2iYiIiIiIiIiIxSjYJCIiIiIiIiIiFqNgk4iIiIiIiIiIWIyCTSIiIiIiIiIiYjEKNomIiIiIiIiIiMUo2CQiIiIiIiIiIhajYJOIiIiIiIiIiFiMgk0iIiIiIiIiImIxCjaJiIiIiIiIiIjFKNgkIiIiIiIiIiIWY5PeBRAReRGdBjahyRvVcXS14/ShS3w35HeCzoQ+85gaTcvQ5aNm+Ob1JOTSNeZ8s4Kda44mPN7szZo061KD7Lk8ALh0JoR5E9ewf/PJVK1LWmnevjJtu9XE3dORS+fDmf7NagIOXUoxf6kK+ej5kT95C3oTGRHH77O3s+r3fQmP16hfnA7da5Mjtzs2ttZcuRTJkl92sHHFkbSoTppp1awsHdtUxt3dkcCga0z5YRNHAy6bzevu5kDfd+pRpJAPuXK4sXj5AabM2JTiuV+pXZThg19l266zDB21NLWqkC5aNyrDGy0r4eHqwMXLkUyatZkjp66Yzevh6kC/rnUoWiA7uXzcWLT6IN/O3mKSZ/KI9pQvkTvZsTsPXmDQ6MzTds3bVaJd1xqP79MIpo9bzfFDQSnmL1UhL70G+pO3oJfxPp2zg5WL9pvNW6dxST79uh07N59k5MAFqVWFNLfvCMycDwFnICLSwORRj2hQ69nH7D0MY76Dc4Hg7QHdX4eOLU3zrNsKk36CoKuQJwe8/w40rJ1atUgfrZqWpWObSri7Pe7fZmzi6Anz96m7mwN9u9elSMHH/dufB5jy4+YUz/1KraIM/7gF23afZeiXy1KpBumjTaMyvNEisX/7ds6z+7f33qyDX4Hs5PZx4/c1B/l2zpZk+do3LU/rhmXw8XQi5vodNu85w/T527h3/0Eq1ybtWLrdrK2t6NKqMk1rl8DT3ZGgkCim/rqNPUcCU78yqcRgMLB06VJatWr1XPlHjBjBsmXLOHz4cKqW62WRtL7dunUjJiaGZcuWpWu5XmbpeY0o2JSBZMuWjQ8++MBi5wsPD7fYuUTSUrt3G9CmRz3GD5zLlQsRvN6/EV/N60uPOqO4ffOu2WOKls/HJ1O78fPYVexcc4Tq/mX4ZNpbfNRmIqcfB1yuhcQwa/SfXL0YAUCDdpX57Kce9PP/5m8DWS+72o1L0uvjJnz35QoCDgfRtG1FRk19k56tJxMRGpssf/acrnzx3ZusXryfbz5dTImyeeg7pDmxUTfZsfEEAHGxt1jw41aCL14j/n48lWv7MXBka2KibnJg57m0rmKqqFerKP161GfC1PUcP3mZFv5lGTOyLV37/ER4RFyy/FlsrYmJvcXc33bRrlXFZ547u5czfbrX48jx4NQqfrqpX92P99+qx/gZGzl6+gqtGpZm3JA2dP5gNmHXkrebra01MddvM2fxHjo0r2D2nJ+OW46tTeKEbBdHO2aP68LmXWdSrR5prU6jEvQe5M+U0SsJOBxEs9cqMmpKZ3q89p35+zSHK6Mmd2b1kgOMGWq8T/t90ozY6Jts32gaJPf2daHHB404djAwjWqTdm7fBr9C0LopvD/s7/NfDoHeg6Ftc/hmCBw8Dl9MAHdXaFTHmOfQcRg4Evq/DQ1qwYZtMHAEzJ0CZYqnYmXSUL2afvR75xUmTF/P8RNXaOFfhjEj2tK178xn9G+3mbtwN+1amr9Pn8ju5Uyft+tmzv6tmh/vd63HuJ8e928NSjP+kzZ0GjibsMhn9G9L99Cxqfl2a1SzKH1er8VX09dy7MxV8vi6MaSPPwCTft6SmtVJM6nRbr061KBxrWJ8/f16Ll2NokqZfHz90av0GraAM4Ev1/ucbt26MWfOHABsbGxwd3endOnSvP7663Tr1g0rK+P4FhISgpubW5qWLTAwkPz583Po0CHKli1rsfPmy5ePS5eMr7Ht7OwoUKAA7733Hr169bLYc3z77bc8evTIYuf7N7Zs2UK9evWSpQ8ZMoRRo0alSRnMBSs/+ugj3nvvvTR5/qQUbMpARo8ebdHzWTJwJZKWWnWvw4LJ69i52jgrafwHvzLv0CjqtqrA6l93mj/mnboc3Haahd+tB2Dhd+spVa0QrbrXZUw/4+C/Z8Nxk2PmfLOSZl1qUrR8vgwfbGrzZnXWLj3ImqUHAPh+7GoqVC9M8/aVmTVpfbL8zdpVJjwklu/HrgYg+GIEhUvkoG3XGgnBpqP7A02O+WPebhq+Wo4S5fJmmmBT+9YVWbXuKCvXGa+1KTM2UblCflo2LceMOX8lyx8afp3JPxhnMjVpWCrF81pZGRg6qDmzft1O6RK5cHTIljoVSCcdmldgxaZj/LnpGADfzt5C5TL5aN2oDNPnbU+WPzTiOt/OMs6QaPZKSbPnjLtxx+TvBtWLcvfufTbtOm3h0qefNp2rs3bZIdYsPQjA9HFrqFCtEM3bVWLW5A3J8jdvW4nwkFimj1sDQPDFaxQpnoPXutQwCTZZWRkY/OVr/DJ9CyXL5cHRKXNdb7WrGn+e14I/wNcbPn382rtgPgg4DTMXJAabfl4E1StAz87Gv3vmNc6g+vl3GD/cosVPN+1bVWTV+mOsXGe8T6f8uJnK5fPTsklZZvy8LVn+0PDrTJ7xpH8zf5/C4/7to2bMmrfjcf+WNXUqkE46NqvAn0/3b3O2UOVJ/zbffP82cY6xf2te13y7lSycg2Onr7B+x6mEYzbsPEWxgj6pVIu0lxrt1rhWceYs3cOuwxcBWLr+CFXK5OP15hUYOWV1KtXkxfn7+zNr1iwePHhAWFgYa9as4f3332fRokUsX74cGxsbfHwyz785wOeff06PHj24ceMGs2fPpnfv3ri6utKhQweLnN/FxeVfn+PevXtkyZLFAqUxOn36NM7Ozgl/Ozo6WuzcL8LR0THdyqA9m0QkQ/HJ44F7dhcObj2VkHb/XjzHdp+neMX8KR5XrEI+k2MADmw5SbEUjrGyMlDn1fJks8vKqQOBFil7erGxsaZwsRwc3GUaADq46xzFyiRflgRQrHTuZPkP7DxH4eI5sbYxP3SUrVyAXPk8OZbB2+sJGxsrihTyYd+hQJP0fQcvUrJYzn917q6vVyc29harHr/Jy0xsbKzwK5CdvUdMl2juPXqJkn45LPY8zeuXZMPO09y5G2+xc6Yn433qy4Gk993u8xRP6T4tk4sDu8+bpO3feY4ixXKY3KedetYlNvoWa5cdtHzBM6DDAVCjkmlajUrGgNP9x5fTkQCobibPoYC0KWNqS7F/OxT47/u3jtWJjb3NqvWZsH+zfty/HU3Svx25RKkiL96/HT19Bb8C2ROCSzm8XahWLj+7Dl38V+V9WaRWu2WxtebefdMx4O69eEr7/btrOLVkzZoVHx8fcubMSfny5fn000/5448/WL16NbNnzwaMM1OeXhI2ePBgihQpgr29PQUKFGDYsGHcv38/2bm///57cufOjb29Pe3atSMmJsbk8VmzZlGsWDGyZctG0aJFmTp1asJj+fMbXwuXK1cOg8FA3bp1n+u4e/fu0a9fP3x9fcmWLRv58uVLNjnCyckJHx8fChUqxKhRoyhcuHBC/WJjY+nZsyfe3t44OzvzyiuvcOSI6VYMX3/9NdmzZ8fJyYnu3btz547pB0/dunUzmcUTFxdHp06dcHBwwNfXlwkTJlC3bl0GDBiQkCdfvnyMGjWKbt264eLiQo8ePQDYuXMntWvXxs7Ojty5c9O/f39u3rxpUt+PP/6YnDlz4uDgQJUqVdiyZUuyfwtvb298fHwSfhwdHdmyZQsGg8Hk3+Xw4cMYDAYCAwMBmD17Nq6urqxdu5ZixYrh6OiIv78/ISEhJuefOXMmJUqUIGvWrPj6+tKvX7+EegG0bt0ag8GQ8PeIESNMZqw9fPiQzz//nFy5cpE1a1bKli3LmjVrEh4PDAzEYDCwZMkS6tWrh729PWXKlGHXrl3J6vp3FGwSkQzFzcv4SUH0tesm6THXric8ltJxMUmW78Rci8M9yTH5ivqy5PRYll/4H/1Gt+eLHj8SdDZjz2pydrPH2saa6MgbJunRkTdw93Qye4ybp6PZ/Da21ri42iek2TtmZemuoazYP4LPp3Rm6tcrOZTkzW9G5eJsj421FVExN03So2Nu4e7m8MLnLVksJ00blWbs5LX/togvJVcnu8ftdsskPTrmJh6uL95uTytWyIeCebz4c2PmeTP75D6NiTK93mIib+DmYf4TSTcPR2KS3KcxUTdN7tPiZXLTuFU5Jn6xPHUKngFdiwKPJKtUPN0h/oGB6NjEPJ5J87gZ0zMDF2e7FPq3m7j/i/u0ZLGcNG1YirFTMmn/9qTdYk37t6jYf9duG3aeZsbCnUz/vCN//TqARZPf4WBAML/8sfffFvmlkFrttudIIB2bVSCXjysGA1QqlZdaFQvi8S/G6LT2yiuvUKZMGZYsWWL2cScnJ2bPns2JEyf49ttvmTFjBhMmTDDJc+7cORYuXMiff/7JmjVrOHz4MH379k14fMaMGQwZMoQvv/ySkydP8tVXXzFs2LCEZX179xqvsw0bNhASEpJQlr87btKkSSxfvpyFCxdy+vRp5s6dmxDgSEm2bNm4f/8+jx49olmzZoSGhrJq1SoOHDhA+fLlqV+/PlFRxo524cKFDB8+nC+//JL9+/fj6+trEuwyZ+DAgezYsYPly5ezfv16tm3bxsGDyT9oGTt2LCVLluTAgQMMGzaMY8eO0bhxY9q0acPRo0f57bff2L59e0IgB+Ctt95ix44dLFiwgKNHj9KuXTv8/f05e/bsM8v0T9y6dYtx48bxyy+/8NdffxEUFMRHH32U8Pi0adPo27cvPXv25NixYyxfvpxChQoBsG+fcV/VWbNmERISkvB3Ut9++y3jx49n3LhxHD16lMaNG/Pqq68mq8eQIUP46KOPOHz4MEWKFOH1118nPv6ffcCnZXQi8lKr17oi732dONV2eNfvAUi2PNtg4O9WbCdd020wGJKlXT4fTt/GY3B0tqNG07J8OKEzH7edlOEDTgBJG8hc/f8uP5i2/e2b93i3/VTs7LNQtkoBen7oT+jlqGRL7DK0ZNda8mvpednZZWHoR80YN2kNsddv//uyvcQeJb+Akt+3L6j5KyU5HxTByXOZ4L5Mwlw/9ayGS+mRR4/Azj4Lg798jYlfLOd6kuDff93j7izBkyY2PCuPmbQMz+xY+qL9my1DP2zKuClrM33/lvSeNN6nL366csVz0bV1Fcb9tJGAsyHk8nFlQLd6dIu+yewlu/9lYV8iFm63ibM383+9GjF/wls8egRXwmJYuSWAZnVL/MuCPp+7d+9y967pXqFZs2Yla9Z/tnS0aNGiHD161OxjQ4cOTfg9X758fPjhh/z22298/PHHCel37txhzpw55MqVC4DJkyfTrFkzxo8fj4+PD1988QXjx4+nTZs2gHEm04kTJ/j+++/p2rUrXl5eAHh4eJgs4/u744KCgihcuDA1a9bEYDCQN2/eFOsYHx/P3LlzOXbsGH369GHz5s0cO3aM8PDwhPYaN24cy5YtY9GiRfTs2ZOJEyfy9ttv88477wAwatQoNmzYkGx20xNxcXHMmTOHefPmUb9+fcAYeMmRI/nsuVdeecUkiNOlSxfeeOONhBlQhQsXZtKkSdSpU4dp06Zx5coV5s+fz+XLlxPO99FHH7FmzRpmzZrFV199lXCuJ/8OTzzZt+p53L9/n+nTp1OwYEEA+vXrx+eff57w+KhRo/jwww95//33E9IqVTJOw33y7+jq6vrM5Zjjxo1j8ODBdOzYEYAxY8awefNmJk6cyHfffZeQ76OPPqJZs2YAjBw5khIlSnDu3DmKFi363PVRsEmS+eSTT1K8iUXS2u51xzj11DR/2yzGbsvdy5no8MTZTa4eTsREXE96eILoiOQzn1w8HIlOMtsp/v4DQgKvAXD2aDBFyuShZfc6TP6/3/5tVdLN9ehbPIh/gJun6ewIV3eHZLOXnoi+dsNs/vj7D7j+1CeTjx49IiTY+AnUhdOh5MnvRYfutTNFsCn2+i3iHzxMNovJzcWe6Bd8457T1xVfH1e+Gv5aQprV43evG5d/xJs9f+RqaMwLl/llEBN3m/gHD5PNYnJzsScq9mYKRz2/rFlsaFCjKD/+tuNfn+tlknCfJpnF5OLuQHSU+XaLNjPr6en7NG8Bb3xyuvH5xDcSHjdYGa+3Vfs+o3vryYRcjrZwTV5+nu7JZyhFRoON9SNcXRLzRJjJk3RGVEYVe/225fs3Hzd8s7vy1bA2CWkJ/duyD3mz908Zv3970m5J+zfnf9e/9WhfgzV/nUjYz+hC8DXsstoyuGdD5izdbbFAfXpJrXaLibvN/437gyy21jg72nEt+gbvvlGLq+HJv1AhNYwePZqRI0eapA0fPpwRI0b8o/M8evQo4QO9pBYtWsTEiRM5d+4cN27cID4+3mQ/IIA8efKYBDiqVavGw4cPOX36NNbW1gQHB9O9e/eE5WJgDP48a7+jiIiIvz2uW7duNGzYED8/P/z9/WnevDmNGjUyOc/gwYMZOnQod+/eJUuWLAwaNIhevXoxfvx4bty4gYeHh0n+27dvc/68cYb8yZMn6d27t8nj1apVY/Nm89+CeeHCBe7fv0/lypUT0lxcXPDz80uWt2JF0y9xOXDgAOfOnePXX39NSHv06BEPHz7k4sWLHD9+nEePHlGkSBGT4+7evZusDtu2bcPJKXHlwD/Z8N3e3j4h0ATg6+ub8KVe4eHhXL16NSGQ9iKuX7/O1atXqVGjhkl6jRo1ki1hLF26tEk5npRBwSb5V+7cuZNseqbI32nye/9UOe/tm3eTfcNcVFgs5Wr7cf7x18/b2FpTqmpBZn6V8jKRkwcCKV/bj2U/bklIK1+nKCf3P3s/BIMhMcCVUcXHP+DsyauUq1qQnZsSNw0uV7Ugu7ecMnvMyaPBVKltOjiXr1aIsyeu8CD+YYrPZTAYsLXN2O31RHz8Q86cC6ViuXxs25U4tbhiuXxs3/1iG6AHBUfS7d2ZJmnd36yFvV0WJv+wkfBrKQdMM4r4+IecvhBGpdJ5+WtvYjtVKp2X7fv+/cbx9av7YWtjzdq/Tv595gzEeJ+GUL5qQXZuTrwvy1ctwK4t5jdBP3nkMlXqmL7wrVCtEGdOXuVB/EOCA6/Rs+13Jo936/sKdvZZmTZ2NRGhGf96exFlS8CWJN8lsWMflPCDJ91XmRKwcz90a5+YZ+c+KJc2EyZSXWL/lpdtu5/q38rmZfueF+zfLkfSre8sk7Tub9Z83L9tyhz92wNj/1a5dF7+2mfav23b/+L9W7astslmNT58+AiDAQy8+Gyzl0VqtdsT9+4/4Fr0DaytrahbpTAb0+hbSj/55BMGDhxokvZPZzWBMajyZN+kp+3evZuOHTsycuRIGjdujIuLCwsWLGD8+PHPPN+TwJXBYODhQ+NrthkzZlClShWTfNbW1ime43mOK1++PBcvXmT16tVs2LCB9u3b06BBAxYtWpSQd9CgQXTr1g17e3t8fX0Tyvbw4UN8fX3N7nnk6ur6zPql5Mk9lDRwZ242uoODaeDz4cOH9OrVi/79k7+fyZMnD0ePHsXa2poDBw4ka7ekm2/nz58/WR2efNvg02Uxt/eWra2tyd9Pr0Kws7NLlv9FmWujpGlPl+Xpf7d/InO8IxCR/5RlP22lQ7+GXL0YwZWLEXR4ryF3b99ny7IDCXk+nNiZyNBYZn/9JwB//LSVsYv70+7dBuxae5RqjUtTrqYfH7WZmHBM18HN2b/5BBFXY7B3zEqdV8tTqlphhnWeltZVtLglv+xk0JevcfbEVU4eCabJaxXx9nVh5e/Gdfpv9W+Ih7cz44YuBmDl73t5tWMVen7kz+rFByhWJjeNW5fn68G/J5yzw9u1OXPiCiHBUdjYWlO5VhHqNy/LlC//TJc6poaFS/cz5MNmnD4bSsCpKzT3L4u3lzPLVx0GoEfX2nh5OPLV/1YlHFOogDdgXDLn6mJPoQLe3L//gEvBkdy7/4CLl66ZPMeNm8aZpEnTM7LfVhxg2HtNOHU+jONnrtKyQWmyezqxdJ3xU7Peb9TE092RUVMSN6QsnM84/ds+my2uzvYUzufF/fgHBF42nV7S/JWSbNt3jus3Mt8M3CVzdzJoVBvOnLjKyaPBNG1TEW8fF1YuMu678NZ7DfD0dmLssKUArFi0j1c7Vqbnh41ZveQAxUob92f6+hPjC/379+K5dN70679vxBnbLWl6RnbzFgRdSfz7cgicPAsuzpAjO/zvBwiLgDFDjI93bAnzlsLXU6Bdc+OG4UtWwbjPEs/RpS282R9mzIP6NWDjDth1AOZOSdu6paaFy/YzZOCT/u0qzf3LGPu31cb7tEeXWnh5OPHVhKf6t/yP+7dsj/u3/N7cj3+qfwtK2r8ZPyxKmp6RLVh5gM/6NeHk+TCOn71Ky/rG/m3Z+sf92+s18XJ35Ivvnurf8hr7N7sn/Vvex/3bFWP/tuPAeTo2q8CZwPDHy+jc6NGhOtv2X+BhRp/W9FhqtFvxQj54uTtyNjACL3dHurethsFg4Nfl5veqsbQXWTKX1KZNmzh27JjZbwnfsWMHefPmZciQIQlp5pZkBQUFcfXq1YTlXbt27cLKyooiRYqQPXt2cubMyYULF+jUqZPZMjz5JrYHDx4kpD3PcQDOzs506NCBDh060LZtW/z9/YmKisLd3R0AT0/PhD2Fnla+fHlCQ0OxsbFJcZ+nYsWKsXv3brp06ZKQtnt3ystKCxYsiK2tLXv37iV3buMXa1y/fp2zZ89Sp06dFI97Up6AgACzZQXj5ukPHjwgPDycWrVqPfNc5jxZ4hYSEpIw0+nw4cP/6BxOTk7ky5ePjRs3Uq9ePbN5bG1tTf4dk3J2diZHjhxs376d2rVrJ6Tv3LnTZEaYpSjYJCIZzu9TN5Almy19v2yHo4s9pw9fYkinqSYzoLxzuvHoYeILtJMHLvJ13zl0GdSMNz9qSsila4x+dxanDyUO2m5eTgz69k3cvV24GXebiyevMqzzNA5ty/hfrf7X2uM4u9jTqWdd3LycuHQujGF9fyE8xDjV3N3TEW+fxOnUYVdiGNb3F3oNakLzDlWIiohj2phV7Nh4IiFPNjtb+n3aAs/szty7e5/gi9f4Zsgi/lp7PM3rl1o2bzuFi3M2urxeHQ93By5eusbg4YsIe7xk08PdAe8kyzN/mtwt4feihX1oWK84IWGxdHz7+7QserrauPM0zo7ZeKttVTzcHLgQHMlHXy0h7PGyVQ83B7J7mrbb7LGJLyaLFvShUa1ihITH0rbvjwnpuX3dKFMsFwO+WERmtHVdAE4u9nTqWQd3TycunQtn6Hu/mtynXk/fp1djGPreXHp96E+L9pWN9+k3q9m+MXPN+vo7Aaeh64DET2THfGf8vZX/I0Z/AhGREPJUbC2XL0wfYww2zVsG3h7waX9o9NR7kXIlYfxn8O1PMPknyJ0Dxo+AMsXTpk5pYfP207g429Gl41P928jFT/Vvjnh7mX6JxE+Tuib8XrSwDw3rPu7f3vkhTcuenjbuOo2LUzbefu2p/u3rJYQ+6d9cHcjuYdq/zfkmsX8rVtCHxjWN/dtr7xn7t9lLdvMI6NmhBl7ujkRfv82OAxf4fsH2NKtXakuNdstia0PPDjXJ4e3C7Tv32XX4Ap9/t5obt0xnxL8s7t69S2hoKA8ePCAsLIw1a9YwevRomjdvbhJQeaJQoUIEBQWxYMECKlWqxMqVK1m6dGmyfNmyZaNr166MGzeO69ev079/f9q3b5+wb8+IESPo378/zs7ONGnShLt377J//36io6MZOHAg3t7e2NnZsWbNGnLlykW2bNlwcXH52+MmTJiAr68vZcuWxcrKit9//x0fH5/nmpnUoEEDqlWrRqtWrRgzZgx+fn5cvXqVVatW0apVKypWrMj7779P165dqVixIjVr1uTXX38lICCAAgUKmD2nk5MTXbt2ZdCgQbi7u+Pt7c3w4cOxsrJKcZniE4MHD6Zq1ar07duXHj164ODgwMmTJ1m/fj2TJ0+mSJEidOrUiS5dujB+/HjKlSvHtWvX2LRpE6VKlaJp06bPPH+hQoXInTs3I0aMYNSoUZw9e/ZvZ6iZM2LECHr37o23tzdNmjQhLi6OHTt28N577wEkBKNq1KhB1qxZzS7hGzRoEMOHD6dgwYKULVuWWbNmcfjwYZMlhJZiePSiu5xKhvfBBx+YXS6XUrrIszTJlTrL6DK7Rx4pr5eXlN3OZf5b9OTZ4u1TnjIvz+Z4LuMvAUoPq1fPT+8iZEj1ntojRZ7ffXt90baknZ2/ffjcebt165bwLW42Nja4ublRpkwZ3njjDbp27ZqwzMpgMLB06VJatWoFwMcff8zMmTO5e/cuzZo1o2rVqowYMYKYmBjAGHxYtmwZvXr1YtSoUURFRdG0aVN+/PFHk0DDvHnzGDt2LCdOnMDBwYFSpUoxYMAAWrduDcCPP/7I559/zpUrV6hVq1bC8rZnHTdjxgymTp3K2bNnsba2plKlSowdO5Zy5coBxsDHgAEDEjbdTiouLo4hQ4awePFiIiIi8PHxoXbt2owePTphZtJXX33FhAkTuHPnDq+99hrZs2dn7dq1CbOCunXrRkxMDMuWLUs4Z+/evVm2bBnOzs58/PHHLFiwgFdeeYXRo0c/s1z79u1jyJAh7Nq1i0ePHlGwYEE6dOjAp59+ChiXvY0aNYqff/6ZK1eu4OHhQbVq1Rg5ciSlSpViy5Yt1KtXj+joaLMBtx07dtCnTx/Onj1LpUqV6N+/P+3atePixYvky5eP2bNnM2DAgIR/W4Bly5bRunVrk+V333//PRMmTODChQt4enrStm1bJk2aBMCff/7JwIEDCQwMJGfOnAQGBiZcI0/a7OHDh4waNYoffviB8PBwihcvztdff42/vz8AgYGB5M+fn0OHDlG2bFkAYmJicHNzY/PmzdStW9fsv6c5Cjb9hynYJJakYNOLUbDpxSjY9GIUbHpxCja9GAWbXoyCTS9GwSZJS/8k2CTp4+bNm+TMmZPx48fTvXv39C7Of46W0YmIiIiIiIhIhnbo0CFOnTpF5cqViY2N5fPPPwegZcuW6Vyy/yYFm0REREREREQkwxs3bhynT58mS5YsVKhQgW3btuHp6ZnexfpPUrBJRERERERERDK0cuXKceDAgb/PKGlCC5tFRERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi7FJ7wKISObwyMUpvYuQMRkM6V2CDOm2l4avF3HHTdfbi7rh65reRciQ6vXokd5FyJA2z5iR3kXIkIrO7JPeRciQ3AMepncRRCQT0swmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELEbBJhERERERERERsRgFm0RERERERERExGIUbBIREREREREREYtRsElERERERERERCxGwSYREREREREREbEYBZtERERERERERMRiFGwSERERERERERGLUbBJREREREREREQsRsEmERERERERERGxGAWbRERERERERETEYhRsEhERERERERERi1GwSURERERERERELMYmvQsg6Sdbtmx88MEHydLDw8PToTQiIiIiIiIikhko2PQfNnr0aLPp5gJQIiIiIiIiIiLPQ8voRERERERERETEYhRsEhERERERERERi9EyOhHJcJp3rELbt2ri7uXEpXPhTP96JQEHL6WYv1TFfPT8uCl5C3kTGR7H7zO3sWrh3oTH/dtWpMGr5chbKDsA505cYda36zlz7HKq1yUtNW9fibZda+Lu6cil8xFMH7uagEPPaLcK+ej5oT95C3oRGRHH77O3s2rRfrN56zQuySdj2rNz80k+/2B+alUhXbz2ShnebFIRD1cHLlyJZMK8LRw+c8Vs3roVCvFavTIUyeOFra01F69EMmPZLnYfT2znlnVK0ax6MQrk8gTgVGAYUxft4MTF0DSpT1rpUKM03epVxNPZgfOhkXyzbCsHL5hvt/qlCtG+Rmn8cnqRxcaa86GRTFuzm52nE9vNxsqK7g0q8Wql4ni7OBIYHs3EFdvYcSrlazgjal+zNN3qP9Vui7dyKKV2K12IdjVL45frcbuFRDJ99W52JmmTTnXL0b5GaXzcnIm5eZv1h88y6c/t3It/kBZVShOtmpalY5tKuLs5Ehh0jSkzNnH0hPl2c3dzoG/3uhQp6EOuHG4s/vMAU37cnOK5X6lVlOEft2Db7rMM/XJZKtUg7e07AjPnQ8AZiIg0MHnUIxrUevYxew/DmO/gXCB4e0D316FjS9M867bCpJ8g6CrkyQHvvwMNa6dWLdLHG+VL071qRbwdHTgbEclXG7ayP9j89VYhVw4+qleLAh5u2NnacvX6dRYcPMrsfYcS8thYWdGreiValypOdidHLkZGM3bzNrZdyFz922sNytCpWSU8XB24eCWSCb9s5sjpFMbTioVo06AshfN6kcXWmguXI/lx8U72HDNtk3qVCtOzXQ1yertwJTyW6Qu3s3X/ubSojoj8Dc1sEpEMpbZ/KXr9X1MW/LCVvm2/4/jBQEZ93xUvXxez+bPndOOLaV05fjCQvm2/47cZW+nzaTNqNCyRkKd0pfxsWXWUwW//xAedphMeEstXP3TDw9s5raqV6mo3KkmvQU1Y8ONW+nacxvFDlxj1XWe8fFJotxyufDGlM8cPXaJvx2n89tNf9BnclBr1iyfL6+3rwjsDG3PsQGAq1yLtNahchIFv1GXWn3t487O5HD5zhYkDW5Pd3cls/nJ+udgbcIkBE5bSdcSv7D8ZzPgBrSiSxyshT4WiuVi75zR9xvxO91HzCY2MY/KgNni5OqZVtVJd47JF+LhVXWas30v7cb9y8MIVpvZshY+r+XarUDAnu88E0feHZXQcP499Zy8z+Z2WFM2Z2G79mlanbbXSjF6ymVZjfub3nUeZ8NarJnkyusblivBxm7rMWLeXDt/8ysHzV5japxU+bubbrXyhnOw+HUS/6ct4fayx3Sb1bEnRXIlt0rRiUd5vUZPpa3bT+qs5jJi/jsbli9C/Rc20qlaqq1fTj37vvMIvC3fT4/05HA24zJgRbfH2Mt9uWWytiYm9zdyFuzl/8dlfipLdy5k+b9flyPHg1Ch6urp9G/wKwdABz5f/cgj0HgwVSsOSGdCzM3w1yRhceuLQcRg4El5tBMt+Mv5/4Ag4ciIVKpBOmhYrwqcN6zJ9x15a/fQr+4OvMKNDK3ydzV9vt+7fZ+6Bw3Sa+ztNfpjD1O17GFCnBh3KlkrIM6BOdTqWK80X6zbT9IefmX/oKN+99irFsmee/q1BVT8GvFmP2X/soeuQXzh86jITPm5Ddg/z7Va2aC72Hr/EwLFL6DZkLgdOBDPuo9YUyeudkKdkIV++eK85q7ef4M1PfmH19hN8+V5zShT0SatqPbdu3bphMBgSfjw8PPD39+fo0aMJeZ48tnv3bpNj7969i4eHBwaDgS1btpjkX7ZsWRrVQOSfU7BJRDKUNl1rsHbxAdYs3k/whQi+/3oVESGxNO9QxWz+Zh0qEx4Sw/dfryL4QgRrFu9n3ZKDtO2W+Ebrm8G/s2LBHi6cCuHyxWt8O3wpBisDZasWSKtqpbo2b1Zn7dKDrFl6kOCL1/h+7GoiQq/TvF0ls/mbtatEeEgs349dTfDFa6xZepB1yw7RtksNk3xWVgYGf9WWudM2E3olOi2qkqbeaFyB5X8d54+/jhMYEsWEeVsIi4rjtVfKmM0/Yd4Wflm9n5MXwwgOi2Ha4h0Eh0VTq2zBhDyffb+axZuOcDYogksh0Xw1az0Gg4FKxXOnVbVSXZe65Vm65zhL9hznYngU3yzbSmhMHO1rlDab/5tlW5m1aT8BwWEEXYth0qodXLoWQ50Sifdg84rF+HHDXrafDORKZCwLdx5l5+lAutStkFbVSnVv1ivP0t3HWbrrOBfDohi7ZCuh0XG0r2m+3cYu2crsjfsJCAojKCKGySt2EBQRQ52Sie1WJp8vhy9cZfWB01yNus6uU0GsOXCaEnmyp1W1Ul37VhVZtf4YK9cd49LlKKb8uJmIa3G0bFLWbP7Q8OtMnrGJtZsDuHHrborntbIyMPSjZsyat4OrYbGpVPr0U7sqDHgHGj3nrKMFf4CvN3z6HhTMB+2aQ5umMHNBYp6fF0H1CsZAVIG8xv9XrQA//54qVUgXb1Uuz6Ijx/n9yHHOR0bx1YathF6P443y5u/Tk2ERrDxxmnPXIrkSe53lAafYfjGQirlzJuRpWbIY03fuZev5QIJjYpl/8CjbLwTydpXM07+93qQCf245xvItxwi8GsXEuVsIj4yjTQPz4+nEuVuYu2IfJy8Yx9PpC7cTHBpNzfKJ/VvHJhXYd/wSPy/fy6WQKH5evpd9AUF08H85283f35+QkBBCQkLYuHEjNjY2NG/e3CRP7ty5mTVrlkna0qVLcXTMPB9IyX+Hgk0ikmHY2FpTuHgODu40nR59cOc5ipXNY/aYYmVyJ8t/YMdZCpfIibWN+S4wazZbbGysiYu9bZmCpzMbG2sKF/Pl4K7zJukHd5+jWJkU2q10bg7uTtJuO89RuHgOk3Z7o1ddYqJvsnbZQcsXPJ3ZWFtRNF929hw3nbK/5/glShfK8VznMBjAPlsWrt+8k2KebFltsLG2fmaejMTG2opiubKbLIED2HU6iLL5nr/dHLLaEnsrsU2y2FhzLz7eJN/d+/GUK/B853zZ2VhbUSx3dnYlWQK361QQZfL/g+stqy2xT11Lhy5coVhub0o+Di7l9HChZvF8bAu4aLnCpyMbGyuKFPJh36FAk/R9hwIpWSyn+YOeU9eO1YmNvc2q9cf+1Xkyi8MBUCPJ5xM1KkHAabj/+NY8EgDVzeQ5FJA2ZUxttlZWlPDNzo4ky9u2XwyiXK7nu0+LZfeiXM4c7A1KXKqfxdqau0n6tzvx8VR4znO+7GysrfDLnz3ZErg9xy5RqvA/HE9vJPZvJQv5sudooOk5jwZSqsjL2W5Zs2bFx8cHHx8fypYty+DBgwkODiYiIiIhT9euXVmwYAG3bye+Bp05cyZdu3ZNjyKL/Cvas0lEMgxnV3usbayJjrxhkh4deQN3T/Of+Lh5OhEdeTZZfhtba1xcHYi6FpfsmLcHNiYy/DqHkgRnMipnt8ftFpW03W4+o90cid550zR/1JN2syfq2g2Kl81D41bl6dthWqqVPT25OtlhY21F5HXTdoi6fgsPF/vnOkcn/4rYZbVlw97TKebp264WEdE32Hsi6F+V92Xh5vC43eJumaRHxt3E0znvc52ja90K2GWxZd3hMwlpO09d4s26FThw/grBkTFUKZyHuiULYm1lsGj508sz283p+dqtS70K2GW1Zd2hxHZbc/AMbo72zB7QAQxga23Nb9uOMHPDPouWP724OBvbLSomSX8VcxN3V4cXPm/JYjlp2rAU77w/598WMdO4FgUebqZpnu4Q/8BAdOwjvD2MeTyT5nEzpmcGbvZ22FhZce1mkvv05k08HZ59n/7V7x3c7e2wtrJi8rbd/H7keMJj2y9e4q3KFdgXdIWg6Biq5ctD/SIFsTZkjv7tyXgaFWvablGxN/Fwyfdc53ijqXE83bgncTz1cHUg6nqSc/6DMTo93bhxg19//ZVChQrh4eGRkF6hQgXy58/P4sWL6dy5M8HBwfz111989913fPHFF+lYYpF/TsEmEcl4Hj0y+dNgMCRN+pv8j5NJflDbt2tRt2lpPu72I/fvxSd7PENLUl2DAR49q+HMtPOTZDv7LHz85Wt8+/lyrsfcMnd05mGu3Z7jsEZV/OjRqhofffsH0XHmZ8m92aQijaoUpc/XC7l3P/Ns1gzJLh8M/M19+liTcn70aVyN/jOXE3Ujsd3GLN3C8A4N+OOTrjx6BJcjY/hjbwAtK5d4xtkynmTtZjA81/XmX96PPk2q8f4M03arWCgX7zSqzJe/b+JYYAh5vFz5uE1drl2vwg9r91i28OkpaSMZDGb7+OdhZ2fL0A+bMm7KWmKvZ44ZrpaSNPbx5Ho1PCuPmbSMLvmV9fcVfOOXhdhnsaVsTl8+rFuTS9ExrDxhDJyMWr+FL5s0YE2vrjwCgqJjWHI0gDalM1v/Zub123Mc17BaUd5pU52P/7eM6CT3ZPKxJnlaarl79y5375ouxc2aNStZs2Y1m3/FihUJy+Fu3ryJr68vK1aswMrKdKb9W2+9xcyZM+ncuTOzZs2iadOmeHllnv275L9DwSZJVZ988gl37mSOpSHyd1L/U6TrMbd4EP8AN0/TzSRd3R2SzXZ6IvpanJn8jsTff5AsSPJat5p07FGHT96ZxcUzYZYtfDq6Hv243TxMZzEZ2+2m2WOir93ALcmsJ1c3B2O7xd4ib0FvfHK6MfLbNxIeNzyeYbJy/3DeaTWJkMsZew+nmLjbxD94iIeL6ewINyf7ZJ/OJtWgchGGvt2IT6auYF8KM5Y6+VegW4vK9PtmMecuX7NYudNb9E1ju3k6m/YJ7k72yWbtJNW4bBFGdGzIR3NWsueMabtF37zNgJl/ksXGGleHbITH3mRA85pcibpu8TqkhxTbzfE52q1cEUa80ZBBM5O3W99m1Vmx7yRLdxlnUZwLicQuiy3DOjZgxro9afamLLXEXje2m7tbkvvUxZ7oFwyE5/Rxwze7K18Na5OQZvU4WrJx2Ye82fsnrobGvHCZMypP9+QzlCKjwcb6Ea4uiXkizORJOiMqo4q+dZv4hw/xcjC9Tz0c7JPNdkrqcqyxrzoTEYmHgz3v1aqaEGyKvnWbdxf/SRZra9zsshF24yYf1avJ5ZjM0b8ljKdJZhu6OdsTFWv+dcgTDar6MaRHIz6d9Cf7Akz7t8iYm8lmMbk52yeb7ZRaRo8ezciRI03Shg8fzogRI8zmr1evHtOmGWeDR0VFMXXqVJo0acLevXvJmzdxZlznzp35v//7Py5cuMDs2bOZNGlSqtVBJDUp2CSp6s6dO0yYMCG9iyFpwL/EkFR/jvj7Dzh74irlqhdi58bEr7YpV70QuzedNHvMySPBVKlb1CStfPVCnA24woP4hwlpbd+qyeu96jGk52zOBpj/Gt6MKj7+AWdPhlCuWkF2bk5sp3JVCrJ7yymzx5w8GkyV2n4maeWrFeTsias8iH9I8MVr9HptisnjXfvVx84+K9O/WUVEaMZ/gRz/4CGnAsOoXCIPWw4m7l9VuURe/jqU8hLLRlX8GNq9McOmr2THEfP74nRuUpG3W1Sh//glnAzMPIFNMLbbycthVCuSl03HEtupapE8bD6ecrs1KefHyI6NGPzLKradSHk/oXvxDwiPvYmNlRUNShc2WWqXkcU/eMjJ4DCq+uVl09Gn2q1oHrYcS7nd/Mv7MfKNRvzfHPPtli2LTbLZBA8ePsLw+L8Xnf3zsoiPf8iZc6FULJeXbbsTl0xXLJuX7Xte7OvPgy5H0q2v6Qa93d+sib1dFib/sInwaxm/f3sRZUvAlp2maTv2QQk/sH38jqJMCdi5H7q1T8yzcx+UyyQTdO4/fEhASBjV8+dl/ZnE+7JG/jxsPPP8S+8NGMhibZ0s/d6DB4TdMPZvjf0Ks/pk5unfTl8Mo3LJvGzd/9R4Wiovfx1I+T5tWK0oQ3o24rMpq9h5OHn/dvxcCJVL5WXBmsR9I6uUzsexM1ctW4EUfPLJJwwcONAkLaVZTQAODg4UKlQo4e8KFSrg4uLCjBkzGDVqVEK6h4cHzZs3p3v37ty5c4cmTZoQF5d82weRl52CTSKSoSyZs4NBX7fl7PErnDwSRJN2lfD2dWHlb3sBeGtAIzy8nRn36SIAVv62l1dfr0rPj5uwetF+ipXJQ+PXKvD1oIUJ52z7di26vNeAMR8vJOxqdMKMntu37nHn1r20r2QqWPLLTgZ92YazAVc4eTSYJq9VNLbbIuO+LW+918DYbsOWALDy93282rEKPT/0Z/WS/RQrnZvGrcvz9f8Z2/X+vXgunTf9yvCbccZZjEnTM7J5aw8wsmcTTgaGcexcCK3rlsLHw4klm48A8G7bmni7OTJixhrAGGga0cOf8fO2cPx8SMInrnfuxXPztvFaerNJRXq1qc6w71cTci02Ic+tO/e5ffd+OtTS8n7ecpCvOvkTEBzGkcAQ2lYvha+bE7/vNH7Fc/9mNcju4siQeWsBY6BpVKfGfLN0C0cvheDhZGyTu/fjuXHH2G6l8vjg7eLIqasRZHdxpE/jqlhZGZi1aX/6VDIV/LL5IF++6c+J4DCOXAzhtSfttv1xu7WogbeLI0PnGtvNv7wfo95szDeLt3A00Hy7bT1+gTfrlefU5XCOBYaS28uVvs2qs/X4eR5m9GlNjy1ctp8hA5tx+mwoAaeu0ty/DN5ezixfbbxPe3SphZeHE19NWJVwTKH8xq9Pt8uWBVcXewrl9+Z+/AMuBUdy7/4DLgaZzja8cdO4VCZpekZ28xYEPfXZyuUQOHkWXJwhR3b43w8QFgFjHn+W1LElzFsKX08xfhPd4QBYsgrGfZZ4ji5t4c3+MGMe1K8BG3fArgMw1/SziQxt1t6DfPOqP8dDwjh8JYT25Urh6+zE/IPG+/TDujXI7uTIx38a79NOFcpwNTaOC5HGKV8Vcuege5UK/HLgcMI5S+fwwcfJkZNhEWR3cuS9WlWxMhiYsTvz9G/zVx9geJ8mnLwYxvGzV2n5SmmyezixdKPxPu3ToSZebo58Pt04njasVpThvf2Z8Mtmjp+7ivvjsfLuU+Ppb2sOMm1YB95sXom/DpyndoWCVCqRh16fLzBfCAt71pK552EwGLCysjLZDPyJt99+m6ZNmzJ48GCszQQmRTICBZtEJEP5a80xnF3t6dSnHm5eTlw6G8aw3j8THhIDgLuXE96+Lgn5w65EM6zPHHoNbkbz16sSFX6daV+tZMf6xK/GadGxClmy2DBs4hsmzzX3u43MnbopTeqV2v5adxxnVzs69aqLm6cTl86FM6zfXMJDjF/nnazdrsYwrN9cen3kT/MOlYmKiGPamFXseGpG2X/Bhr1ncHG0o3vLqni6OHD+SiQf/G8poZHGTxg9XR3I7pG4TLN1vdLY2FgzuEt9Bnepn5C+YnsAn/9ofOPxWv0yZLG1YUy/FibPNWPZLmYs25UGtUp9aw+fwdUhG70aV8HL2YFzIZH0/WEZIdHGdvNydsDHLbHd2lYvha21NUPa1mdI28R2+2NvAMPmrwMgi601/ZpWJ5eHC7fu3mf7yYt8+usa4u6k/NX1Gc3aQ2dwcchGz8ZV8HJ53G7TE9vNM2m71Xjcbu3rM6T9U+22J4DPfjW224y1xqVyfZsZA1XRN26xNeACU1YkmaKSgW3efhoXZzu6dKyOh7sDFy9dY/DIxYRFGGcgebg74u1lupz6p0mJ3+xUtLAPDesWJyQslo7v/JCmZU9PAaeh64DEvYbGfGf8vZX/I0Z/AhGREPLUZwe5fGH6GGOwad4y8PaAT/tDozqJecqVhPGfwbc/weSfIHcOGD8CyhRPmzqlhVUnz+Bql42+Navg7ejAmYhIevy2jKvXH/dvjg74Oideb1YGAx/Wq0EuFxcePHxIUEwM47ZsZ8Hj4BRAVhtrBtSpTm5XF27du8/W8xcZtHwNcXczT/+2YfdpXByz0b11VTxcHbhwOZKBY5cQei1xPPXxcE7I3/oV43g66K0GDHqrQUL6yr+O88X3xvH02NmrDJuygl7tatKzXQ2uhMUwdPIKAs6Hpm3lntPdu3cJDTWWLTo6milTpnDjxg1atGiRLK+/vz8RERE4Ozsne0wkozA8eubusPJf9MEHH1hs6ZslzyUvt7RYRpcp2erTqhcRVdY1vYuQId1xy2S79KYhQ+bavz3NuF7MZF+0kEY2z5iR3kXIkIrO7JPeWHXv/wAAf75JREFURciQ3AMe/n0mSWb3rx8+d95u3boxZ07it1s6OTlRtGhRBg/+f/buO77m64/j+PtmyJDIkpAQI2JF7VCr9t6lVFtUq0O1FKWlC/1RHVRa2lKbKlVFrdqjdqzYYhOaGJk2Gb8/UtEroao3+SbX6/l45NHcc8/35v09vZF7P/ec831P7du3l5Q602n+/Plq27ZtuuPj4uLk4eGhtWvXqm7duv/YH8gOmNkEAAAAAEAmmTp1qqZOnfrAPg+aA+Lu7p7ufuaMILuz+ecuAAAAAAAAwMOh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi7EzOgAA65By+qzREXKk5GvXjI6QI7nnKmt0hBwpxZ7PmB5VQoCz0RFypNvOPOceRanJbxgdIUc6/PL3RkfIkQJn9zA6AgArxCsAAAAAAAAAWAzFJgAAAAAAAFgMxSYAAAAAAABYDMUmAAAAAAAAWAzFJgAAAAAAAFgMxSYAAAAAAABYDMUmAAAAAAAAWAzFJgAAAAAAAFgMxSYAAAAAAABYDMUmAAAAAAAAWAzFJgAAAAAAAFgMxSYAAAAAAABYDMUmAAAAAAAAWAzFJgAAAAAAAFgMxSYAAAAAAABYDMUmAAAAAAAAWAzFJgAAAAAAAFgMxSYAAAAAAABYjJ3RAZD9ODo6qm/fvhZ5rAsXLljkcQAAAAAAQM5AsQnpjBgxwmKPZamiFQAAAAAAyBlYRgcAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuxMzoAADyKzu+3VfOX6srFPbcO7ziub/vN0OlD5x54TK02wer6UTv5FvVR5MkLmjr0V21etDPtfhtbG3X54GnV71hdHvncFBMVp5UzN+qnzxcqJSUlk88oa3QZ3EEtXm0oFw8XHd52VGPemqjTB8/et3/hoIJ6ceizKl45QPmL+Oi7vlM0/+ulZn3KPlVaHfq3VonKAfLy89Tgp7/Q5t+2Z/apZJlW7YPVoUt1eXq56vSJC/p+9ArtDztz3/5lKxZWjz6NVDjAR9GXLmvOjM1aMm+nWZ/cLg566Y36qlmvlFxdnRT1Z6zGf71S2zcfy+zTyTKtnq6sDs9Xl5eXi06dvKjvv1mh/Xsi7tu/XIVCer1XIxUp6p06bj9t0eIFu9LuHzmmi8pXKpzuuG2bj+rDAT9nyjkYoX2D8urcIlhebrl18ly0Rv+4TmFHMv63rW5woNo1KK8ShbyVy95WJ85Ga8L8Ldq273Ran6IFvPR6+xoqWcRHft5uGv3jWs1evjurTifLtGtcXs+3qiIv99w6eTZaX09bqz2HMx43L/fc6tWljkoG5JN/fg/9smyXvp62Ll2/js0r6elG5ZU/r6viEm5o7bYjGjdrg27dTsrks8k6z1cqp+7VguXjkltHL0br01XrtSMi43GrXNBP/es9pQAvDznZ2+vPhATN3rVXU7fffT7Z2djo9RpV9HTZIOVzddHJ6Fh9uXaDNpw4neFj5kTb90iTZ0kHjkgXo00aMyxFDZ968DGhYdLn30rHTkk+XlL356RObcz7rFgvfTNJOvOnVMhPevsVqVHtzDoLY3QuV16vVg6WT+7cOhIdrWHr12n7nw9+7SZJlX39NKtDRx2JvqSWM3/MsE/LEiX1TfMWWnH8mHosWmjp6AAeATObAOQ4Hfs2V7u3murbd2aoV50hij0frxELB8jJxfG+x5SuWkzvT+up1bM2q2f1j7R61mZ9ML2nSgYHpPV5tl8LteheT9++M0OvVh6kiR/9rGfebqY2bzTMitPKdM++20bt+7bU2F6T9FbVgYqJitPnKz564Lg5ODso8uQFTRo0U9GRsRn2ccztoBN7T2tsr0mZFd0wdRoGqUe/Jvppyka90eUH7Qs7o+Ehz8s7X54M++f3c9fwkOe0L+yM3ujyg2ZN3aie7zRVrXql0vrY2dnos7Gdlc/XXf8bOFcvd/hWoz9drOiLl7PqtDJdnQZBeuPtxpo1faPeeGmC9u89o09HPnf/cfN117CRnbR/7xm98dIEzZqxST37NFGtunfHbej7v6hjq9FpX690HqekxGT9sfZQVp1Wpmv4ZAn17VxXU37bpq4f/aiw8HMaPeBp5fNyzbB/xZIFFbr/tPqOnK8XP5qpnYciNKpfW5Uo7J3WxzGXnc5diNd3czbqUtyVrDqVLNWgekm9/WI9TZu/Td0GztCew2c1alC7+46bvb2t4hKua9r8bTp2+mKGfRrXKqU3nntKk+du0XP9pmrE+OVqUL2kejz3D1WFHKR56RJ6v1FdjdsUqraTZmpHxDlNeLatfPNkPG7Xbt/WjzvD9MKPv6jZD9P03cZt6lOnpp6tUDatT586NdSpYjn9b8VaNf9humbt3qtv27dW6XzeGT5mTnT9ulQyUPqwz8P1Pxsp9XhPqlxOmjdBeq2z9Ok3qcWlO3bvl/oNlVo3lhZMSv1vvyHSnoOZcAIGaVGihD6sU1ffhm5Ty5k/asef5zS57dPyc834+XaHa65cGtmkqTZH3P9DHj9XVw16qrZCz97/w7OcwGQyacGCBfe9v0iRIgoJCbHoz+zWrZvatm37wD7/5udOnTpV7u7u/zkXrAPFJgA5Tts3m2j2lwu1aeFOnT54TiNfmyAHp1yq17HafY95+s0m2rXmgH4etVgRRyL186jFClt3UE+/2SStT+mqgdqyeJdCl+/R+TOXtHHBDu1as1/FKxbNitPKdE+/3UKzPp2njfNDdepAhL7sNlYOzg6q/3yt+x5zZMdxTXh3htb9vFm3b97OsM/2ZWGa+tFsbZwfmlnRDdP++epatnC3lv22WxGnLmnc6BW6eD5erdoHZ9i/RbvKuhAVr3GjVyji1CUt+223li/arWc610jr06R1RbnmcdKQAT/r4N4IXYiK14E9ETpx9HxWnVama//sk1q2OEy/LwrTmdPR+v7rlbp4IUGtnq6cYf+WbSvp4vkEff/1Sp05Ha3fF4Vp+ZIwdXju7u/05cs3FBtzNe2rUpUA3bh5W3+ssZ5i03PNKmvh+v1auH6/Tv0Zo9Ez1+l89GW1b1A+w/6jZ67Tj0t26NDJ84o4H6fvf9mkiKhYPVWxWFqfQyfPa8zsP7Rya7hVzcj5u04tKmvRmn1atGafTp+L0dfT1ulC9GU93TjjcYu6mKCQaWu17I+DunLtZoZ9nijup33h57Ry02FFXUxQ6N7TWrX5sEoF5MvMU8lSL1WtpLl79uuXPft1PDpGn65ar6iEy3q+UrkM+x86f1FLDobr2KVonYtP0MIDh7Xx5CkF+xdI69PmidIatzlU64+fUkRcvGbt2quNJ07p5Scz/t3PiWpXk/q8IjV+yFlHs3+TfH2k93tJxYpIHVpK7ZpLk2ff7TN9rlSjcmohKqBw6n+rVZam/5Ipp2CI7pUq65cD+zXnwH4dj43R/9avU+SVy3qhXMa/p3cMa9BQC8MPa3dkZIb325hMCmnaXF9v3aIzCfGZEd1iLly4oNdff12FChWSg4OD8ufPryZNmmjLli0Pdfz27dv12muvPVTfIUOGyGQyPfDr1KlTFv+5wN9RbAKQo+Qv4i2v/O7auXp/WtvtW4natzFcQU8Wv+9xpasGmh0jSTtW7VfQk4Fpt/dvOaIKdYNUIDD1zUTAE/4qU72Etq/Ya+GzyHr5i/rIy9dDO1bsSWu7fStRe9cfVFD1kgYmy77s7GxUvJSvdm07bta+c9sJBZXzz/CYoLIFtXPbCfP+W4+rRGlf2dqm/smt/lQJHdp3Vr3ebaaff++nH2b1UKdutWRjY8qcE8lidnY2KlHSVztD7xmH0BMq80TBDI8p/UTBdP13bDuhEqXujtu9mrWsoHWrDujGjYyLoDmNna2NShXJZ7YETpJC959W2eJ+D/UYJpPk7JhL8VduZEbEbMnO1kYlA/IpdO8947bntMqWeLhxy8je8HMqGZBPpYvllyT5+bipesWi2rL75H/Km13Y29iojG8+bbpnedvGk2dUseDDjVvpfN6qWMBPoWfuzibJZWurm4mJZv1uJCaq8kM+pjUKOyDVrGLeVrOKdCBcuv3XUO05INXIoM/uA1mTMbPZ29joCZ982nDa/Pm24fRpVfK9/3PjmaAyKuzmrm+23r8Y0/vJaoq+fl1zDuy/b5/son379tqzZ4+mTZumI0eOaOHChapbt65iYmIe6nhvb285Ozs/VN/+/fsrMjIy7atgwYL65JNPzNr8/TN+LfNffi7wdxSbAOQonvncJEmxFxLM2mMvJsjjr/sy4pHPTXEXzD/xirsQb3bMnK+WaN0v2zRx12daEjtJ327+RPO/XaF1v2y14BkYwzO/uyQp7rz5GMReiE+7D+byuDvL1s5GsdFXzdpjY67Kwyt3hsd4eLkoNuae/tFXZWdnKzf31BdqvgU89FT9INnY2ujDvrP00+QNeuaFanruJetYnuN2Z9zuHYfYq/LwcsnwGE/P3IqNTT/Ofx+3vytZ2k9Fi/no90VhFsttNHdXJ9nZ2igmwXwcouOvycvt4V7kv9AsWE4O9lodGp4ZEbMl9zx/jVv8NbP2mPir8nTP+Pf0YazaHK4JczZr3Ced9MfMPpo75hXtOhChGb9ZxwxOD2cn2dnY6NJV83GLvnpVeXM/+Pn2x1uvaP+7vTTvpec1c+ce/bLn7pv8jSdP66WqlVXYw10mSTWKFFKDEsXk4/Lo/y9yuksxkpeHeVteTykxyaTY+Lt98t7bxyO13Rp4OP31fLt2z79v167J+z5FjCLu7nq3Zi31XbZUSffZN7Oyr586lHlC769aYfHMlhYXF6eNGzfq888/V7169VS4cGFVrVpVgwYNUosWLTI85pNPPlG+fPkUFhYmKf1yNpPJpIkTJ+rpp5+Ws7OzihcvroULU/ercnFxUf78+dO+bG1t5erqmq7tjpEjR8rX11deXl568803dfv23Q9y7v25cXFxeu2115QvXz45OjrqiSee0OLFizM8h+joaFWtWlWtW7fWjRs3tG7dOplMJq1evVrBwcFydnZWjRo1FB5u/ndr0aJFqly5shwdHRUQEKChQ4cq8W+F7CFDhqTNEPPz81Pv3r3T7vvuu+9UvHhxOTo6Kl++fHrmmWce/D8HmYYNwgFka/U6Vtfb33RLu/3RM1+lfnPPCw9TBm33SnevyWR2TJ1nnlSDTtX12cvjdPrQORUrW0g9Pn9B0ZGxWvXTpkc+ByPUf76W+ox7Pe32hy1HSFK6jc7vGQJk4N7hMZkyaDQ74J47Taa/Hie13WRjUlzsVYV8uljJySk6ejhSXt6ueqZzdc2c9IfFchst3XMtg7YH9jdl3C5JTVtW0MnjFxR+6M//nDO7yejp8zC/o42rldQr7aprwOjfFJtwPXPCZWfpnj+mB/+e/oOKQQX14tNPauSk1TpwNFIF87urT7d66hZ7VVPn5fwPIO5IP0T/PMPy+Rlz5JzLXhUK+OqdurV0OjZOSw6mvlEctnKdhjdrqGWvv6gUSWdi4zRv7wG1K1fG0tFzFNM9w3rn6Wp6UJ8M2nK6jH4lM2q7szQuZOsWnYyLy/Cxctvb66umzfT+6pWKvWHMbM6bN2/q5k3zpbgODg5ycHBI19fFxUUuLi5asGCBqlWrlmGfO1JSUtSnTx8tWLBAGzduVPHi95+5P3ToUH3xxRf68ssvNWbMGL3wwgs6ffq0PD09H/o81q5dK19fX61du1bHjh3Ts88+qwoVKujVV19N1zc5OVnNmjXT5cuX9eOPP6pYsWI6ePCgWeHqjrNnz6px48YKDg7W5MmTZWd3t/TwwQcfaNSoUfL29laPHj308ssva9Om1Nfay5cvV+fOnfXNN9/oqaee0vHjx9OW8Q0ePFhz587V6NGjNXv2bJUpU0ZRUVHasyd15v6OHTvUu3dvzZgxQzVq1FBMTIw2bNjw0GMBy6LYhBxp0KBBumHQHxZkra1Ldyt8x91lTPYO9pJSZyrF/G2Wjrt3nnSznf4u9ny8PHzMZz7de8yrw57Vz18t0fq52yRJpw6clU+hvOrUv2WOKzZtWbhDh7fdvbKZvUPqP/ce+d0VExWX1u7u7abY83FCeglx15SUmCzPe2YxuXvkTjdr547Y6CvpZu94eDorMTFJCXGpBYCYS1eUmJik5OS7L7HPnLwkr7yusrOzUWJisoXPJGvFp42b+Ti4e+RW3H3GLSbmqjw90/dPTExSQrx54cTBwU71GgZp2sT1siZxl68rMSlZXm7mzzfPPM6KSbh2n6NSNXyyhD54pbHeH7NY2w/cfxNdaxSXkDpu985i8sjjrJj4jJ9vD+PVjjW17I+DWrRmnyTpRMQlOTnY673XGmna/K05vkgfe+26EpOT5X3PLCav3M7pZjvd62x86t/NIxej5ZXbWb2eqpZWbIq9dl09f12kXLa28nBy1PkrV9W/Xi2djbv/32drl9cz/Qyl6FjJzjZF7m53+1zMoM+9M6Jyqtjrfz3fnM1/T72cnXXpWvrnW+5cuVQuf34F+fhoSL36klILUDYmk4707qMX5/2quJs35O/mpgmt26YdZ/NXde5I7z5qOG2KzsRn7h5OI0aM0NChQ83aBg8erCFDhqTra2dnp6lTp+rVV1/VuHHjVKlSJdWpU0edOnVSuXJ390lLTExU165dtWPHDm3atEkFC2a8/PyObt266bnnnpMkffrppxozZoxCQ0PVtGnThz4PDw8PjR07Vra2tipVqpRatGih1atXZ1hsWrVqlUJDQ3Xo0CGVKFFCkhQQEJCu35EjR9SoUSO1adNGX3/9deoHAH8zfPhw1alTR5I0cOBAtWjRQjdu3JCjo6OGDx+ugQMH6sUXX0x7/P/973969913NXjwYJ05c0b58+dXw4YNZW9vr0KFCqlq1aqSpDNnzih37txq2bKlXF1dVbhwYVWsWPGhxwKWRbEJOdKNGzc0evRoo2Pgb5pMeDFTHvf6lRu6fs/+I9FRcapU/wkd35v6psrO3lZla5XUpI/n3PdxDoUeU6X6ZTT/2+VpbZUbPKGDfyvIODg5KCXZ/B1EclKyTKact+I4ddyizNqiI2NVuVE5HQ87JUmys7dTuTpBmjgw48sIP+4SE5N19HCkKlUN0KZ1d6d3V6oaoC1/ZLxM6eC+s6pWq4RZW6Uni+nIoUglJaUWkQ7siVC9Jk+YzVgpUMhT0Rcv5/hCk5Q6bkfCI1WpSlFt+ts4VapSVJs3HsnwmEP7z6paTfNPbitXDdCRw3fH7Y46DYJkb2+nVcuz//4c/0ZiUrIOnzqvqk8U0vqdd/9dqvpEYf2x6/h9j2tcraQ+eLWJPvpuiTbtsY79hP6NxKRkhZ84r6rlCuuP7XfHrUq5wtqw49gDjnwwRwf7dLPqkpNTZDJJJpnSZirmVLeTk3Ug8rxqFC2slUfuPr9qFi2k1Ufu/3y7l0km5cpgRsOtpCSdv3JVdjY2alKyuH4/lPHv/uOgQhlp3Wbztk3bpTIlJfu/3omVLyNt3iF163i3z+btUkUrmRB2OzlZ+y+cV61ChbTi+N3fy1qFCmvVifTPtys3b6rpjGlmbZ3LlVd1/0J6c8kiRcTHKyklJV2ffjVqysU+lz5Zv1aRlzP/Cq+DBg1Sv379zNoeNGOpffv2atGihTZs2KAtW7Zo2bJl+uKLLzRx4kR169ZNktS3b185ODho69atyps37z9m+HuhKnfu3HJ1ddWFCxf+1XmUKVPGbGaSr6+v9u3bl2HfsLAwFSxYMK3QlJHr16+rVq1aeu655/T111//Y25fX19JqRuoFypUSDt37tT27ds1fPjwtD5JSUm6ceOGrl27pg4dOigkJEQBAQFq2rSpmjdvrlatWsnOzk6NGjVS4cKF0+5r2rRp2jJDZL2c9w4KwGNvwbfL1al/S9VoVVmFgwqo//hXdfP6La2dc3dpw4AfXtNLQzrcPea7Farc4Al17Ntc/iV81bFvc1WsF2RWfNr6+251GtBKVZuUV75CeVWjVWW169VEmxftzNLzyyzzv16i5wa1U822VVWkjL8GTHlTN6/d1JqfNqb1eXfqW3r50+fTbtvZ26lY+SIqVr6I7HPZKW8BLxUrX0R+f22aK0mOuR3T+kipm5EXK19E3v7//CIpu/v1py1q2qaSmrSqIP8iedWjb2P55HfT4nmpz4mXe9bXgCFt0vovmbdT+Xzd9HqfxvIvkldNWlVQ09YVNffHu+80Fv+6Q3ncnPTGO01VoJCnqtYsrue61dLCuduz/Pwyy68/b1OzVhXVpEV5FSrspR69G8knn5sWz98lSXq5Rz29+2HrtP6LF+yST343vd6roQoV9lKTFuXVtGUF/TIr/XKlpi0raNOGcF22wqVis37fqTZ1y6pV7TIq4uepPi/UUT4vV81bnbo8oGfHWhr8+t1PqxtXK6nBrzfVNz+t1/5jkfJ0c5anm7NyO+VK62Nna6PihbxVvJC37O1s5e3hquKFvFXQxz2rTy/TzF6yU63ql1WLuk+ocAFP9e5aV/nyumrBytRx6/FcLX30pvmn/MULe6t4YW85OdrLPY+zihf2VpECd5edbNp5XE83Kq+GNUrK1zuPqpQtrFefraENO04oOadPa/rLlNBd6lDhCbUvV0bFvDw1qGEd+eZx1axdqRfFeKduTX3R6u4VW1+oXF71AgNU2MNdhT3c1a5ckLo/WVkLDxxO61POL78alwyUv7ubgv0LaFKnp2VjMmnC1h1Zfn6Z5eo16dDR1C9JOhuZ+v2ff11Q9KsfpPfuvkdWpzap9302Vjp+Svp1iTRvqfRyp7t9uj6TWmya8JN04nTqf7fslLrefRmT403atVMdnyirDkFlVMzDUx/WriM/V1fN3Jv6ezqgZi2NbJz6e5oi6Uh0tNlX9PXrupmUqCPR0bqemKhbSUnp+iTcvKkrt2/pSHS0bidn/oc3Dg4OypMnj9nXg4pNkuTo6KhGjRrp448/1ubNm9WtWzcNHjw47f5GjRrp3LlzWr58+QMe5S57e3uz2yaTScn/8tz/zWM4OTn94+M5ODioYcOGWrJkic6ePZthn7//zDuznu78zOTkZA0dOlRhYWFpX/v27dPRo0fl6Ogof39/hYeH69tvv5WTk5N69uyp2rVr6/bt23J1ddWuXbs0a9Ys+fr66uOPP1b58uUVd5/lmMhczGwCkOPMGb1UuZxy6a3RXeXq7qzDO05oUJsvzWZAeft7mv2hPLjtmD7t9p26fdxeXT9qr8iTF/Tpi98pfMfdK2B91/9HvfhRO701uqvcvfMoOjJOSyev08wRC7Ly9DLNz1/8plxOudTr21fk6pFbh7cd08Amw8zGzadQXrPZXV5+Hhq3+8u02x37t1bH/q21Z90B9a8/RJJUIjhAo9benUb+xlfdJEkrpq7Tly9/m6nnlNnWrzqoPG7OeqF7bXnmddHp4xf0Yd+fdCEqdWq+Z14X+fxtk/moP+P0QZ9Z6tG3sVo9E6yYS5f13ahl2rj27puxixcSNKj3TPXo01jjZ/bQpYsJmv9zqOZMz1lLNR9k/eqDypPHSZ1fekqeXi46deKiPug/Wxf+Wvrq5XXPuEXG6cP+s9WjdyO1bhes6EtX9F3Icm1cd9jscQv4e6ps+UJ6r8/MLD2frLJq2xG5uTjp5bbVlNc9t06cjVbfkfMVFZ36Cb2Xe27l83JN69+2fjnZ2dnq3W4N9G63Bmntizcc0P9+SH2j4u3hoh+Hd0m7r3OLYHVuEaydhyLU81PruK766i3hcnN11Mvtq8nLI7dORESr/2fzFHXp7+OWx+yYaV90Tfu+dLH8alKrtCIvxKt9r4mSpKnztipF0mvP1pS3p4tiE65r084TGj97o6zF0kNH5O7kqDdrPSkfl9w6cjFar/68QH8mpI6bt0tu+ea5+3yzMZn0Tr2aKujmpqTkZJ2Ji9PIdRs1e9fdK7Y62NmqT50a8nd307Vbt7X++EkNWLhMl+/Z1yYnOxAuvdjn7pKgz79N/b5t0xSNGCRdjJYi/zaxpKCvNO7z1GLTTwskHy/p/d5S4zp3+1R8Qhr1sfT1JGnMJMnfTxo1RCoflDXnlBWWHDkiD0cn9apWTd7OuXUkOlov/zZff/41A8k7d275/e359rgICgrSggUL0m63bt1arVq10vPPPy9bW1t16tTp/gcboFy5cjp79qyOHDly39lNNjY2mjFjhp5//nnVr19f69atk5/fw1+RslKlSgoPD1dgYOB9+zg5Oal169Zq3bq13nzzTZUqVUr79u1TpUqVZGdnp4YNG6phw4YaPHiw3N3dtWbNGrVr1+5fny/+G1PKg3brBP6jvn37Zspyt8x6XDy6Ji6Zs4zO2iVnsFcB/pkpuKzREXKkFHsmND+qhACm4D8K21u8zHwUl8rzu/ooDr/8vdERcqTA2T2MjpAjnejT7587/SU6OlodOnTQyy+/rHLlysnV1VU7duxQr1691KJFC02aNEkmk0nz589X27ZtNXfuXHXp0kUzZsxIu5pakSJF1KdPH/Xp00eSzPrf4e7urpCQkLRleXfce+wd3bp1U1xcnFnBq0+fPgoLC9O6desyPLZevXq6dOmSvvrqKwUGBurw4cMymUxq2rSppk6dqj59+iguLk6JiYl67rnntG/fPq1bt0758+fXunXrVK9ePcXGxsrd3V1S6tK8ihUr6uTJkypSpIiWL1+uli1b6oMPPlCHDh1kY2OjvXv3at++fRo2bJimTp2qpKQkPfnkk3J2dtbkyZP11VdfKSIiQlu2bNGJEydUu3ZteXh4aOnSpXrrrbe0d+9elSljJetScxBmNgEAAAAAkElcXFz05JNPavTo0Tp+/Lhu374tf39/vfrqq3r//ffT9X/mmWeUnJysLl26yMbGJlvNyvn111/Vv39/Pffcc7p69aoCAwP12WefpetnZ2enWbNm6dlnn02b4fQwmjRposWLF+uTTz7RF198IXt7e5UqVUqvvPKKpNSC2meffaZ+/fopKSlJZcuW1aJFi+Tl5SV3d3fNmzdPQ4YM0Y0bN1S8eHHNmjWLQpNBmNmETMXMpscHM5seDTObHg0zmx4NM5seHTObHg0zmx4NM5seDTObHg0zmx7Nv5nZBDyO+EsGAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuh2AQAAAAAAACLodgEAAAAAAAAi6HYBAAAAAAAAIuxMzoArJujo6P69u1r8ce9cOGCxR8T/43J1tboCDmSXT4foyPkSGcauBodIUfKu+e20RFyLNczN4yOkCNdy+9gdIQcyfNAstERcqTA2T2MjpAjHes0zugIOVQ/owMA2RrFJmSqESNGZMrjZkYBCwAAAAAA/HcsowMAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDFUGwCAAAAAACAxVBsAgAAAAAAgMVQbAIAAAAAAIDF2BkdAAAeReeBbdSsWx25uDsrfMcJfdv/R50+/OcDj6nZurK6fvC0fIt6K/LkRU373zxtXrwr7f5pe79QvsJ50x23aMIafdv/R4ufgxFeeKe5mnWuKRc3Z4XvPqVvB83RmSORDzymZosK6vpuS/kWzqvI05c07bNF2vz7ngz7duzVWC+930YLJqzR+I9/zYxTyHKdqpXTS08Fy9s1t45diNZni9dr16lzGfatVNhP/Zo+paI+HnK0t9efsQn6JXSvpm/andanYZlAvVq3qgp5ucnO1lZnLsVq6sZdWrT7UFadUpZo26KCOrWvKk9PF506fUljf1ijvQfOZtjX0yO33ny1nkoE5ldBPw/9unCnxv6wxqzPUzWKq/Oz1VXA1112djY6ey5Wc+Zv14o1B7PidLJM67aV1KFTNXl5uujUqYv6buwq7d8bcd/+5coXUo83G6hIEW9FR1/Wz7O2avHCu883W1sbPde5hho3Kau8eV0VERGtiePXanvoiaw4nSzTrnF5Pd+qirzcc+vk2Wh9PW2t9hzO+PfUyz23enWpo5IB+eSf30O/LNulr6etM+tja2ujrm2rqnntMsrr6aIzkTH6buYGbdtzKvNPJgu1b1heL7T4a9zORWv0jLXaE57xuNUNDlS7hhVUvLC3ctnb6sTZaE38dbO27Ttt1q9eleJ6rUNNFfBx07kL8Ro3Z6PW7ziWFaeTZTqXK69XKwfLJ3duHYmO1rD167T9z4zH7e8q+/ppVoeOOhJ9SS1nZvy6omWJkvqmeQutOH5MPRYttHR0w2zfI02eJR04Il2MNmnMsBQ1fOrBx4SGSZ9/Kx07Jfl4Sd2fkzq1Me+zYr30zSTpzJ9SIT/p7VekRrUz6ywA/BvMbAKQ43To00xPv9lY3w34Ub3r/U8xF+L16YL+cnJxvO8xpasU0/tTemjNz5vVs+Zgrfl5s96f2kMlKwek9eld7396rniftK9BbUZKkjYs2J7p55QVOrzZSO1er6/vPpijt5t9odgLCfr057fklNvhvseUqlxUg8a9rNVzQ9Wz4QitnhuqQeO7q2TFIun6lihfSM0619SJ+xQUcqKmZUtoYIu6+mFtqJ4ZM1O7Tp3T+G5t5evmmmH/a7du66etYeo6/he1+mqaxq/dpl6Na6pDlbJpfeKv3dAPa7fphe9/VruvZ2j+zoMa1r6xahYvnFWnlenq1S6lt15roBk/b9WrvaZq74Gz+vyTZ+TjnfG45bK3VVz8Nf04e4uOn7yQYZ/Ll2/ox9lb9OY7P+rlnlP1+6r9eq9vc1WpVCQTzyRr1a1XWm+81Ug/zdikHq9O0r69ERrx+bPy8cmTYf/8+d00/POO2rc3Qj1enaSfftysN3s31lO1S6b1eemVOmrZqqLGfr1C3V/8QYsX7taQYe0VWDxfVp1WpmtQvaTefrGeps3fpm4DZ2jP4bMaNaid8nll/Hyzt7dVXMJ1TZu/TcdOX8ywz+vP1lTbhuX01ZQ1euGdqVqwcq8+699aJYr4ZOapZKmG1UqqT5d6mvrbNr34wQyFHT6r0e/ef9wqlCqo0P2n1e/Leer2wY/aeTBCI/s/rRKF747JE4G++l+vlvp940F1GTRDv288qOG9WqpMsfxZdVqZrkWJEvqwTl19G7pNLWf+qB1/ntPktk/LzzXjcbvDNVcujWzSVJsjzty3j5+rqwY9VVuhZ63n7+gd169LJQOlD/s8XP+zkVKP96TK5aR5E6TXOkuffpNaXLpj936p31CpdWNpwaTU//YbIu2xrs8g/rVTp07JZDIpLCxMkrRu3TqZTCbFxcUZmguPH4pNAHKcp99opNmjFmvTol06feicRvWYJAenXKrX4cn7HtO2ZyPtWntQP3+1VGePRunnr5YqbP0hPd2zUVqf+OjLir2QkPZVtUl5/XnivPZuDM+K08p0bV+tp9lfL9fmpXt0OjxSo96eIQenXKrbrsoDj9n1x2HNGbNCZ4+d15wxKxS2MVxtX61n1s/R2UEDvu2mr/v/pCvx1zL7VLLMi09V0q879uvXHft14mKMPlu8XpHxl/VstXIZ9j8ceVFL94Tr+IVo/RmXoMVhh7XpyClVKlogrc/2k2e1+uBxnbgYo4iYeP24ebeORF1UpSJ+WXVama7j08FaumKvlizfq9MRMRr7wxpdvHhZbVpUzLB/1IUEjRm/RsvXHNCVqzcz7BO2L0IbthzV6YgY/RkVp19/26kTJy+qbJmCmXkqWap9x6patnSPfl+yR2dOR+v7sat04WKCWrWplGH/lm0q6cKFBH0/dpXOnI7W70v2aNnSPerQ6e6/hQ0bP6Gfftys0G3HFRkZp0W/7dKO0BN6puP9/73MaTq1qKxFa/Zp0Zp9On0uRl9PW6cL0Zf1dOPyGfaPupigkGlrteyPg7pyLePnW5OngjRtfqi2hJ3UnxfiNX/lHm3bc1rPtaycmaeSpZ5rVlmL1u3TwnX7dOrPGIX8mDpu7RpmPG4hP67Tj4u369CJ84o4H6dxczYqIipWtSrd/dCmU7PK2r7/tKYvDNXpyBhNXxiq7QfO6Nmm1jNu3StV1i8H9mvOgf06Hhuj/61fp8grl/VCuYzH7Y5hDRpqYfhh7Y7MeDaxjcmkkKbN9fXWLTqTEJ8Z0Q1Vu5rU5xWp8UPOOpr9m+TrI73fSypWROrQUmrXXJo8+26f6XOlGpVTC1EBhVP/W62yNP2XTDmF/6Rbt25q27atIT+7Ro0aioyMlJubmyE/H48vik0AcpT8Rbzlmd9du9YcSGu7fStR+zaFq3TVwPseV7pKMe1as9+sbefq/SpdtViG/e3sbVX/2Wpa/uNGywQ3WP5CXvLM56Zd6+8u1bp9K1H7thxTUHDR+x5XOrio2TGStHPdQZWuEmDW9uaIjtq++oDCNlhHYU6S7G1tFOSXT5uPmi8R2Xz0jCoUerjCUClfb1Us7KcdJ+7/KfWTxfxVxNtTO07+8xKMnMDOzkYlAvNr+65TZu3bd5/UE6ULZHzQI6hUvpD8C3po7/77LzHLSezsbFSihK92bDdf3rZz+0kFPZFxQS2oTAHt3H7SrG3H9hMqUdJXtrapL/Fy2dvq1q1Esz43byXqibLWUaSzs7VRyYB8Ct1r/nsauue0ypZ49AJuLntb3bqdftzKlbTcc9hIdrY2Klk0X7olcNv2nVbZ4g83biaT5OyYSwlXbqS1PRHoq217T5k/5t5T/+n/RXZib2OjJ3zyacNp83HbcPq0Kvne/xyfCSqjwm7u+mbrlvv26f1kNUVfv645B/bft8/jJOyAVPOez8JqVpEOhEt3fjX3HJBqZNBn9wHhb3LlyqX8+fPLZDIZHQWPGYpNAHIUj7+Wk8ReSDBrj72YIM989//ExiOfW/pjLiTI4z7HVG9ZSS5uzlo5c9N/TJw9pI3bxctm7XGXEtLuy/A47zyKu/eYi5fl+bflUHXaVFaxsv6a8ulvFkxsPHdnJ9nZ2ij6ivlMregrV5XX1fmBx64e+Ip2/6+X5rz1vGZt3aNfd5i/eXBxyKXtQ95U2LDe+v7Ftvp04VptOXb/pRU5iVseZ9nZ2igm7qpZe2zsNXl65P5Pj53bOZd+/7WPVi98R58NfUbffL9aO3af/ucDcwA3N2fZ2tkoNubecbsqT8+Mx83TM7diY+/pH3NVdna2cnNzkiTt2H5Sz3SsqgIFPGQySZWCi6hGzRLy9HLJnBPJYu55Un9PY+6ZURkTf1We7o/+fNu255Q6taisgvndZTJJVcoW1lPBxeT1H5/D2YW76/3Hzcvt4c7x+ebBcnKw1+ptdz9k8HLPrZiEex4z4Zq83B78b2ZO4eHkJDsbG126Zv57F33tmrydMz7HIu7uerdmLfVdtlRJKSkZ9qns66cOZZ7Q+6tWWDxzTnUpRvLyMG/L6yklJpkUG3+3T957+3iktmdndevWVe/evfXuu+/K09NT+fPn15AhQ8z6DBkyRIUKFZKDg4P8/PzUu3fvtPtMJpMWLFhg1t/d3V1Tp07N8Ofdu4xu6tSpcnd31/Lly1W6dGm5uLioadOmirzPrDvgUbFBOIBsrV6Hauod0jXt9scdQ1K/uecFm8kkpdznRVyae+42mUzp2u5o2uUpbV+5TzFRcf8ucDZRr10V9friubTbg7t8JymDMTKZ7h3KdO49xvS3Y/L6uev1/z2jDzqN1e2biRkcnfPdOzwm/fOYdR0/R8657FW+kK/6Nq2lM9FxWrrn7huyq7duqf2YH+WcK5eeLOavd1vU1tmYeG0/aUX7dKQfuH/+Hf0H167f0itvTZWTUy5VKl9YPV+tpz+j4hS2zzpmN0kZDtuDn28Z/H7+/XG+/Wal+g1opskzXpdSpD//jNXy3/eqSbOMl4LmWBmNw394uoVMXauBrzfWrNEvKSVFOnc+TkvWHVCLumX+Y9DsJcN/3x/iuEbVS+mVdjX07lcLFJtw/Z7HNO/7j8/hHCij08mo7c7SuJCtW3TyPvvl5La311dNm+n91SsVe+NGhn0eV/dOxLnzPDI9qE8GbZnl5s2bunnTfCmug4ODHBzuvxfmHdOmTVO/fv20bds2bdmyRd26dVPNmjXVqFEjzZ07V6NHj9bs2bNVpkwZRUVFac+ejC/M8qiuXbumkSNHasaMGbKxsVHnzp3Vv39/zZw506I/B483ik3IkRwdHdW3b1+jYyALbP09TId33l1WkitX6j9bHvncFHP+7p4G7nnzpJu59Hex5+Plkc98Bo+7t6tiL6TfF8HH30sV6gbpf53H/tf4htm6fK8O/20Zk/1f4+bpYz5O7l6uirv4gHG7mH7mk1teF8VeSp3tVLxcIXl459GY5e+l3W9rZ6snqgWq1Ut11Lrw20pOzpnvMuKuXVdiUrLyuph/Wu3p4pxuttO9zsWmjunR89HycnFWzwbVzIpNKSnSmejU597hyIsK8PHUq3WrWEWxKT7hmhKTktPNYvJwd1Zs3H/bzyslRToXGSdJOnbiggoX8tILHatZRbEpPv6akhKT081icvdIP3vpjpiYq/LwdLmnv7MSE5OUEH897XEHf/ir7HPZKk8eJ0VfuqJXXq+nqL/GMaeLS0j9Pb13FpNHHmfFxGc8bg/1uJeva+DI35TL3lZ5XJx0KfaKej7/lP7M4G9GThR3OXXcvB5h3BpWK6kPXm2s979ZpO0HzGdkRsddTTeLySOPc7rZTjlV7PXrSkxOlrez+bh5OTvr0rX055g7Vy6Vy59fQT4+GlKvvqTUApSNyaQjvfvoxXm/Ku7mDfm7uWlC67Zpx9n8VS050ruPGk6bojPx1vG8+zfyeqafoRQdK9nZpsjd7W6fixn0uXdGVGYZMWKEhg4datY2ePDgdLOUMlKuXDkNHjxYklS8eHGNHTtWq1evVqNGjXTmzBnlz59fDRs2lL29vQoVKqSqVataNPvt27c1btw4FSuWup3EW2+9pU8++cSiPwOg2IQcacSIEUZHwD2aTn45Ux73+pUbun7F/JO+mKg4VawXpON7U1/k2tnbqmzNkpo85P47Qh7aflwV65XR/O9WprVVqv+EDoUeT9e38Qu1FH8xQaHL91roLLLe9as3df2q+VWWYs7Hq2LtUjq+P7WgYWdvq7LVAzV5+P2Xvx3acVKVapfWgh/WprVVqlNah/7aVyZsQ7h61B1mdky/kC6KOHZev4xdkWMLTZJ0OylZB/88rxrFC2v1wbvPkxqBhbTmUPrnzf2YTCblsrN9cB+ZZP8PfXKKxMRkHTkWpeCKRbRhy9G09uCKRbRxq2Uvf25S6pXFrEFiYrKOHIlU5eCi2rThSFp75eCi2rzxSIbHHDxwTtVrFDdrC64SoCPhkUpKSjZrv30rSdGXrsjW1kZP1S6p9evM92LLqRKTkhV+4ryqliusP7bffX5VKVdYG3b89+fbrdtJuhSbOm51nyyu1Vsy/n+R0yQmJSv85HlVfaKw1v9tnKqWLaw/dt5/3BpVL6UPXmusj8cu1eawk+nu338sUlXLFtbsZbvS2p4sV0T7jvxp2RMwyO3kZO2/cF61ChXSiuN3x6lWocJadSL934UrN2+q6YxpZm2dy5VXdf9CenPJIkXExyspJSVdn341asrFPpc+Wb9WkZfNl7I/LiqUkdZtNm/btF0qU1Ky/+sdbPky0uYdUreOd/ts3i5VzKIJiIMGDVK/fv3M2h5mVpOUWmz6O19fX124kHo11g4dOigkJEQBAQFq2rSpmjdvrlatWsnOznJv3Z2dndMKTff+fMBSKDYByHHmf79Snfq11J/HL+jc8fPq9E4L3bx+S2t/2ZbWp/+4VxQdGaspQ3+VJC34fqVG/j5QHfo005Ylu1W9RUVVrFta7zT5zOyxTSaTGr1QUytnbVbyPW/WcroFE9bq2d5N9OfJizp34oKe7d1EN6/f0rp529P6vPNNV0VHxWnqpwslSb9NXKsv5/dVhzcbacvyvarepJwqPlVK/dt8JSm1qHU63HyN/41rN3U59kq69pxo2oZd+qxjU+0/e157zkSqQ9Wy8nV31c/bUguRfZrUlE8eF73/y3JJ0nPVyisy7rJO/PVRa6Uifur2VGX9tDks7TFfqVNFB86dV0R0vOztbFS7ZFG1rlRa/1uwJsvPL7PMmb9DH7zTQuFHo3Tg8Dm1bFpBPt55tHBpmCTp1W615e3lok9HLU07JjAg9fLpTk655O7mrMAAH92+naTTEdGSpBc6Pqnwo1E6FxkneztbVasSoCYNyuirb1em+/k51a9zQvXeB611JDxSBw+cU4uWFeXjk0eLFqa+ce/+al3l9XbV558ukiQt/m2X2jxdWT3ebKCli8MUVKaAmjYvr08/WZD2mKVK+ylvXlcdP3ZeXt6u6trtKdnYmPTzrK1GnGKmmL1kpz5+q5kOHT+v/Uf/VJsG5ZQvr6sWrExddtLjuVry9nTR/75dlnZM8cLekiQnR3u553FW8cLeup2YpFPnUn93gwLzy9vTRUdPXZS3p4u6P1NdJpNJMxduTx8gh5r1+04NfqOZDp38a9zql1M+L1fNX506bm88W0veHi76ZFzquDWqXkqDezTV6Blrtf/Yn/L8awbTzVuJunr9liTp52W79P1Hz6pLyyr6Y+dx1a5cTFXKFNLrn8zOOEQONGnXTo1q0kz7zp/XrshIPVe2rPxcXTVzb+q4DahZS/lyu6j/imVKkXQkOtrs+Ojr13UzKdGs/d4+CX8tzbq3PSe7ek0687frYJyNlA4dldzySH75pK9+kM5flD7/IPX+Tm2kn+ZLn41NvRJd2AFp3lJp5Md3H6PrM1KX3tKEn6QGNaXVm6QtO6Ufs2hi+sMumcuIvb292W2TyaTk5NTXnf7+/goPD9fKlSu1atUq9ezZU19++aXWr18ve3v7v7YzMP8w7/bt2//55//Xpe7AvSg2Achxfgn5XQ6OufTWqM5ycc+twztO6P2nR5nNgPIp6KmU5LvFokOhxzXi5XF68cN26vrB04o8eUEjXhqn8J3mV36qWC9I+Qrl1YoZG7LsfLLKL9+uVC5He7054lm5uDkrfPcpfdBprK7/7VLzPgU8lPK32UiHdpzUZz2mqOvAlurybktFnr6kET0mKXz3KQPOIOst23dE7rkd9UaDJ+XtmltHz0erx9QFioxL/aTZ2zW3fN3vbpZuMpnUp0lNFfB0U1JysiKi4zR62UbNCb07S845l70+alNf+dxcdfN2ok5cjNHAn5dp2T7rmDEhSWv/OCw3V0d1fb6GvDxz6+SpS3pv8Fyd/2sJp5dHbvl4my/PnDS2W9r3pYrnV6N6QYo8H69OL42XJDk62qtvz8byzuuim7cSdSYiRsNGLtHaPw5n2XlltnVrDymPm5M6d60lTy8XnTp5Ue+/97MunE8dN08vF/n8bVlrVFS8Pnhvjt54q6Fat62s6Ogr+vabFdrwx90lm7ly2emlV+rI19dd16/fUui24/p8+EJdvXIz3c/PqVZvCZebq6Nebl9NXh65dSIiWv0/m6eov5b7ernnVj4v8+fbtC/u7gVYulh+NalVWpEX4tW+10RJUi57O732bC35+bjp+o3b2hJ2Qp98+7uuXLOecVu1NVxuLo7q/nQ1ebnn1omz0er35d1xy+ueW/n/Nm5P1y8nOztbDXipoQa81DCtfckf+/W/8akF931H/9RHYxfr9Q619FqHmjp3Pk4fjlmsA8ejsvbkMtGSI0fk4eikXtWqyds5t45ER+vl3+brz79mIHnnzi2/PK7/8CiPnwPh0ot97m6m9Pm3qd+3bZqiEYOki9FS5N8m1hT0lcZ9nlps+mmB5OMlvd9balznbp+KT0ijPpa+niSNmST5+0mjhkjlg7LmnDKTk5OTWrdurdatW+vNN99UqVKltG/fPlWqVEne3t5mm3kfPXpU1zJYxgkYzZRCCROABTR1y5xldNbO5OxkdIQc6Uy3QKMj5Eh59/y7Tz5xl/1V69wAP7Ndy/9on/o/7pL5OPiRXKjCpd0fxbFO44yOkCPZ5H/4D4m6deumuLg4LViwQHXr1lWFChUUEhKSdn/btm3Trig3depUJSUl6cknn5Szs7MmT56sr776ShEREfLy8tJzzz2nPXv26Mcff1RycrLee+89bdiwQT/88IO6deumU6dOqWjRotq9e7cqVKigdevWqV69eoqNjU37GX369Em7Op0kLViwQE8//TSzm2BRNkYHAAAAAAAAkru7uyZMmKCaNWuqXLlyWr16tRYtWiQvLy9J0qhRo+Tv76/atWvr+eefV//+/eXs7PwPjwpkPWY2AbAIZjY9GmY2PRpmNj0aZjY9OmY2PRpmNj0aZjY9GmY2PRpmNj2afzOzCXgcMbMJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZDsQkAAAAAAAAWQ7EJAAAAAAAAFkOxCQAAAAAAABZjSklJSTE6BABklps3b2rEiBEaNGiQHBwcjI6TYzBuj4ZxezSM26Nj7B4N4/ZoGLdHw7g9GsYNyNkoNgGwagkJCXJzc1N8fLzy5MljdJwcg3F7NIzbo2HcHh1j92gYt0fDuD0axu3RMG5AzsYyOgAAAAAAAFgMxSYAAAAAAABYDMUmAAAAAAAAWAzFJgBWzcHBQYMHD2ZjyX+JcXs0jNujYdweHWP3aBi3R8O4PRrG7dEwbkDOxgbhAAAAAAAAsBhmNgEAAAAAAMBiKDYBAAAAAADAYig2AQAAAAAAwGIoNgEAAAAAAMBiKDYBAAAAAADAYig2AQDS3Lp1S+Hh4UpMTDQ6So6SmJioVatWafz48bp8+bIk6c8//9SVK1cMTpa9xcXFaeLEiRo0aJBiYmIkSbt27dK5c+cMTgYAlpWQkKAFCxbo0KFDRkcBgCxhSklJSTE6BABY2q5du2Rvb6+yZctKkn777TdNmTJFQUFBGjJkiHLlymVwwuzl2rVr6tWrl6ZNmyZJOnLkiAICAtS7d2/5+flp4MCBBifMvk6fPq2mTZvqzJkzunnzZtrY9enTRzdu3NC4ceOMjpgt7d27Vw0bNpSbm5tOnTql8PBwBQQE6KOPPtLp06c1ffp0oyPCCiUnJ+vYsWO6cOGCkpOTze6rXbu2QalgjTp27KjatWvrrbfe0vXr11W+fHmdOnVKKSkpmj17ttq3b290RADIVMxsAmCVXn/9dR05ckSSdOLECXXq1EnOzs765Zdf9O677xqcLvsZNGiQ9uzZo3Xr1snR0TGtvWHDhvr5558NTJb9vf322woODlZsbKycnJzS2p9++mmtXr3awGTZW79+/dStWzcdPXrU7DnXrFkz/fHHHwYmyxlmzJihmjVrys/PT6dPn5YkhYSE6LfffjM4Wfa1detWBQYGqnTp0qpdu7bq1q2b9lWvXj2j42U7CxcufKgvZOyPP/7QU089JUmaP3++UlJSFBcXp2+++UbDhg0zOF32df78eXXp0kV+fn6ys7OTra2t2ReAnMPO6AAAkBmOHDmiChUqSJJ++eUX1a5dWz/99JM2bdqkTp06KSQkxNB82c2CBQv0888/q1q1ajKZTGntQUFBOn78uIHJsr+NGzdq06ZN6WbLFS5cmOVgD7B9+3aNHz8+XXuBAgUUFRVlQKKc4/vvv9fHH3+sPn36aPjw4UpKSpIkubu7KyQkRG3atDE4YfbUo0cPBQcHa8mSJfL19TX7tw7ptW3b9h/7mEymtOcfzMXHx8vT01OStGzZMrVv317Ozs5q0aKFBgwYYHC67Ktbt246c+aMPvroI35PgRyOYhMAq5SSkpK2RGLVqlVq2bKlJMnf31+XLl0yMlq2dPHiRfn4+KRrv3r1Ki/0/kFycnKGb7bOnj0rV1dXAxLlDI6OjkpISEjXHh4eLm9vbwMS5RxjxozRhAkT1LZtW3322Wdp7cHBwerfv7+BybK3o0ePau7cuQoMDDQ6So5w7zJD/Dv+/v7asmWLPD09tWzZMs2ePVuSFBsbazabE+Y2btyoDRs2pH1gCCDnYhkdAKsUHBysYcOGacaMGVq/fr1atGghSTp58qTy5ctncLrsp0qVKlqyZEna7TsFpgkTJqh69epGxcoRGjVqZDZTzmQy6cqVKxo8eLCaN29uXLBsrk2bNvrkk090+/ZtSanjdubMGQ0cOJC9TP7ByZMnVbFixXTtDg4Ounr1qgGJcoYnn3xSx44dMzoGHhN9+vTRCy+8oIIFC8rPz09169aVlLq87s5+kkjP399fbCkMWAdmNgGwSiEhIXrhhRe0YMECffDBB2mfZM+dO1c1atQwOF32M2LECDVt2lQHDx5UYmKivv76ax04cEBbtmzR+vXrjY6XrY0ePVr16tVTUFCQbty4oeeff15Hjx5V3rx5NWvWLKPjZVsjR45U8+bN5ePjo+vXr6tOnTqKiopS9erVNXz4cKPjZWtFixZVWFiYChcubNb++++/KygoyKBU2V+vXr30zjvvKCoqSmXLlpW9vb3Z/eXKlTMoWfb0sHunsbF6xnr27KmqVasqIiJCjRo1ko1N6mf8AQEB7Nn0ACEhIRo4cKDGjx+vIkWKGB0HwH/A1egAPFZu3LghW1vbdG8yIO3bt08jR47Uzp07lZycrEqVKum9997jE9iHcP36dc2ePdts7F544QWzDcORsTVr1mjXrl1p49awYUOjI2V7U6ZM0UcffaRRo0ape/fumjhxoo4fP64RI0Zo4sSJ6tSpk9ERs6U7b/b/zmQyKSUlhb2HMmBjY5M2y/V+bxcYt4eXlJSkffv2qXDhwvLw8DA6Trbl4eGha9euKTExUc7Ozuler8XExBiUDMC/RbEJgNWKi4vT3Llzdfz4cQ0YMECenp7atWuX8uXLpwIFChgdDwAe2YQJEzRs2DBFRERISt1YfciQIerevbvBybKvO1ftu597Z4o97ry8vOTq6qpu3bqpS5cuyps3b4b93NzcsjhZztCnTx+VLVtW3bt3V1JSkurUqaPNmzfL2dlZixcvTltWB3PTpk174P0vvvhiFiUB8F9RbAJglfbu3asGDRrI3d1dp06dUnh4uAICAvTRRx/p9OnTmj59utERs5WMNmqWUj+1dnBwSHelNdw1bdo05c2bN21fsHfffVc//PCDgoKCNGvWLN7APkBoaKjWrVunCxcupNuM+KuvvjIoVfaWmJiomTNnqkmTJsqfP78uXbqk5OTkDDf4B/6LW7duaf78+Zo8ebI2bNig5s2bq3v37mratCkXjngIBQsW1IIFCxQcHKwFCxbozTff1Nq1azV9+nStXbtWmzZtMjoiAGQqik0ArFLDhg1VqVIlffHFF3J1ddWePXsUEBCgzZs36/nnn9epU6eMjpit/H25REYKFiyobt26afDgwRkuRXmclSxZUt9//73q16+vLVu2qEGDBgoJCdHixYtlZ2enefPmGR0xW/r000/14YcfqmTJksqXL5/Z889kMmnNmjUGpsvenJ2ddejQIQqZj+D48eMKCQnRoUOHZDKZVLp0ab399tsqVqyY0dGytYiICE2ZMkXTpk3TzZs39eKLL2ro0KGys2P71/txdHTUsWPHVLBgQb322mtydnZWSEiITp48qfLly9/3Q57HUUJCgvLkyZP2/YPc6Qcg++MvBACrtH37do0fPz5de4ECBRQVFWVAouxt6tSp+uCDD9StWzdVrVpVKSkp2r59u6ZNm6YPP/xQFy9e1MiRI+Xg4KD333/f6LjZSkRERNoG9AsWLNAzzzyj1157TTVr1mSZxAN8/fXXmjx5srp162Z0lBznySef1O7duyk2/UvLly9X69atVaFCBdWsWVMpKSnavHmzypQpo0WLFqlRo0ZGR8y2/P399fHHH6tLly7q3r27PvvsM73zzjvy9PQ0Olq2lS9fPh08eFC+vr5atmyZvvvuO0nStWvXZGtra3C67MXDw0ORkZHy8fGRu7t7hh9+sbcakPNQbAJglRwdHTP8dCw8PFze3t4GJMrepk2bplGjRqljx45pba1bt1bZsmU1fvx4rV69WoUKFdLw4cMpNt3DxcVF0dHRKlSokFasWKG+fftKSn0OXr9+3eB02ZeNjY1q1qxpdIwcqWfPnnrnnXd09uxZVa5cWblz5za7n6uqZWzgwIHq27evPvvss3Tt7733HsWm+7h586Z+/fVXTZ48WVu2bFGLFi20ZMkSCk3/4KWXXlLHjh3l6+srk8mU9vzatm2bSpUqZXC67GXNmjVpz6e1a9canAaApbCMDoBVeu2113Tx4kXNmTNHnp6e2rt3r2xtbdW2bVvVrl1bISEhRkfMVpydnbVnzx4VL17crP3o0aMqX768rl27ppMnT6pMmTK6du2aQSmzpxdeeEGHDx9WxYoVNWvWLJ05c0ZeXl5auHCh3n//fe3fv9/oiNnSF198oT///JPfxUfAVdUejaOjo/bt25fu37kjR46oXLlyunHjhkHJsqfQ0FBNmTJFs2fPVtGiRdWtWzd17tyZItO/MHfuXEVERKhDhw4qWLCgpNQPd9zd3dWmTRuD0wFA5mJmEwCrNHLkSDVv3lw+Pj66fv266tSpo6ioKFWvXl3Dhw83Ol62U7BgQU2aNCndJ/6TJk2Sv7+/JCk6OprLNWfg22+/1YcffqiIiAj9+uuv8vLykiTt3LlTzz33nMHpsq/+/furRYsWKlasmIKCgtJd3pq9ru7v5MmTRkfIkby9vRUWFpau2BQWFsYG6xmoVq2aChUqpN69e6ty5cqSpI0bN6br17p166yOlmM888wzkmRWyORqaunt3bv3ofsycxPIOZjZBMCqrVmzRrt27VJycrIqVaqkhg0bGh0pW1q4cKE6dOigUqVKqUqVKjKZTNq+fbsOHTqkX3/9VS1bttT333+vo0ePcpUwWMSbb76pSZMmqV69euk2CJekKVOmGJQM1uqTTz7R6NGjNXDgQNWoUUMmk0kbN27U559/rnfeeUcffvih0RGzlYe5GAQz6e4vKSlJn376qcaNG6fz58/ryJEjaVfFLVKkiLp37250xGzjzkVK/ultKc83IGeh2AQAkCSdPn1a33//vY4cOaKUlBSVKlVKr7/+uuLi4lShQgWj42VrcXFxmjRpktkVrrp37y43Nzejo2Vbrq6umj17tlq0aGF0lBxn+vTpD7y/a9euWZQkZ0lJSVFISIhGjRqlP//8U5Lk5+enAQMGqHfv3g+8Iifwb33yySeaNm2aPvnkE7366qvav3+/AgICNGfOHI0ePVpbtmwxOmK2cfr06Yfuy4URgJyDYhMAq/HNN9/otddek6Ojo7755psH9u3du3cWpcqZ4uLiNHPmTE2ePFlhYWF8kvgAO3bsUJMmTeTk5JR2Jb8dO3bo+vXrWrFihSpVqmR0xGypcOHCWr58ORvlPoJ7l7Pevn1b165dU65cueTs7KyYmBiDkuUcly9flpRa9MSDRUdHpy0PjoiI0IQJE3Tjxg21atVKTz31lMHpsq/AwECNHz9eDRo0kKurq/bs2aOAgAAdPnxY1atXV2xsrNERASBTUWwCYDWKFi2qHTt2yMvLS0WLFr1vP5PJpBMnTmRhspxjzZo1mjx5subNm6fChQurffv2at++vSpWrGh0tGzrqaeeUmBgoCZMmCA7u9StEBMTE/XKK6/oxIkT+uOPPwxOmD1NmTJFy5Yt05QpU+Ts7Gx0nBzv6NGjeuONNzRgwAA1adLE6DiwAvv27VOrVq0UERGh4sWLa/bs2WratKmuXr0qGxsbXb16VXPnzlXbtm2NjpotOTk56fDhwypcuLBZsengwYOqWrWqrly5YnTEbImZm4D1oNgEAI+5s2fPaurUqZo8ebKuXr2qjh07aty4cdqzZ4+CgoKMjpftOTk5affu3elm6Bw8eFDBwcFcve8+KlasqOPHjyslJUVFihRJt0H4rl27DEqWc+3YsUOdO3fW4cOHjY6SbVSqVEmrV6+Wh4eHKlas+MClcjznzDVr1kx2dnZ677339OOPP2rx4sVq3LixJk6cKEnq1auXdu7cqa1btxqcNHsKDg5Wnz591LlzZ7Ni09ChQ7Vq1Spt2LDB6IjZEjM3AevB1egA4DHWvHlzbdy4US1bttSYMWPUtGlT2draaty4cUZHyzHy5MmjM2fOpCs2RUREsETnAZgNYXm2trZpexEhVZs2beTg4JD2PfsyPbzt27drzZo1KleunCpUqKAffvhBPXv2TNs4vFevXqpWrZrBKbOvwYMHq0uXLjp37pySk5M1b948hYeHa/r06Vq8eLHR8bKtjJYX/n3mJoCcg5lNAKzSM888o+DgYA0cONCs/csvv1RoaKh++eUXg5JlL3Z2durdu7feeOMNs8uB29vbM7PpIfXu3Vvz58/XyJEjza5wNWDAALVv314hISFGR4SVWbhwodntlJQURUZGauzYsfL399fvv/9uUDJYExsbG0VFRcnHx0eSzGbnSNL58+fl5+fHnn4PsHz5cn366afauXNn2lVxP/74YzVu3NjoaDkOMzeBnIeZTQCs0vr16zV48OB07U2bNtXIkSMNSJQ9bdiwQZMnT1ZwcLBKlSqlLl266NlnnzU6Vo4ycuRImUwmde3aVYmJiZJSi3VvvPGGPvvsM4PTZX87d+5Mu4pfUFAQ+4M9hHtnhZlMJnl7e6t+/foaNWqUMaFygICAAG3fvj1ts+s74uLiVKlSJfbyy8C9M8GYGfbvNGnShD3ULISZm0DOw8wmAFbJyclJYWFhKlmypFn74cOHVbFiRV2/ft2gZNnTtWvXNHv2bE2ePFmhoaFKSkrSV199pZdffpmlYA/p2rVraXsQBQYGsun1P7hw4YI6deqkdevWyd3dXSkpKYqPj1e9evU0e/ZseXt7Gx0RVubemTp3nD9/Xv7+/rp165ZBybInGxsbNWvWLG0Z4qJFi1S/fn3lzp1bknTz5k0tW7aMmU3/4NatW7pw4YKSk5PN2gsVKmRQouyNmZuA9aDYBMAqValSRa1atdLHH39s1j5kyBAtWrRIO3fuNChZ9hceHq5JkyZpxowZiouLU6NGjdK9+MNd8fHxSkpKkqenp1l7TEyM7OzslCdPHoOSZW/PPvusjh8/rhkzZqh06dKSUjdVf/HFFxUYGKhZs2YZnDDnSEpK0r59+1S4cOF0m+vi7pvXtm3batq0aXJzc0u7LykpSatXr9bKlSsVHh5uVMRs6aWXXnqoflOmTMnkJDnT0aNH9fLLL2vz5s1m7SkpKTKZTBTp7uPOnmB33Dtz09fX16BkAP4tik0ArNLChQvVvn17Pf/886pfv74kafXq1Zo1a5Z++eUXNid+CElJSVq0aJEmT55MsekBmjVrplatWqlnz55m7ePGjdPChQu1dOlSg5Jlb25ublq1apWqVKli1h4aGqrGjRsrLi7OmGA5QJ8+fVS2bFl1795dSUlJql27trZs2SJnZ2ctXrxYdevWNTpitnLnzavJZNK9L3vt7e1VpEgRjRo1Si1btjQiHqxUzZo1ZWdnp4EDB8rX1zfdEsTy5csblAwAsgbFJgBWa8mSJfr0008VFhYmJycnlStXToMHD1adOnWMjgYr4unpqU2bNqXNzrnj8OHDqlmzpqKjow1Klr25urpqw4YNqlChgln77t27VadOHSUkJBgTLAcoWLCgFixYoODgYC1YsEBvvvmm1q5dq+nTp2vt2rXatGmT0RGzpaJFi2r79u3Kmzev0VHwGMidO7d27tyZ7kql+HeYuQnkXDb/3AUAcqYWLVpo06ZNunr1qi5duqQ1a9ZQaILF3bx5M21j8L+7ffs2e4M9QP369fX222+bbfh67tw59e3bVw0aNDAwWfZ36dIl5c+fX5K0dOlSdejQQSVKlFD37t21b98+g9NlXydPnqTQhCwTFBSkS5cuGR0jx+nTp48mTZokSWkzNytVqiR/f3+tW7fO2HAA/hWKTQCs2q1bt3T27FmdOXPG7AuwlCpVquiHH35I1z5u3DhVrlzZgEQ5w9ixY3X58mUVKVJExYoVU2BgoIoWLarLly9rzJgxRsfL1vLly6eDBw8qKSlJy5YtU8OGDSWlblJva2trcLrsq3fv3vrmm2/StY8dO1Z9+vTJ+kCwap9//rneffddrVu3TtHR0UpISDD7Qsbmzp2btsRw0aJFOnXqlA4fPqw+ffrogw8+MDgdgH+DZXQArBIbcyKrbNq0SQ0bNlSVKlXSZuSsXr1a27dv14oVK/TUU08ZnDB7W7lypQ4fPqyUlBQFBQWlFU5wf0OGDFFISIh8fX117do1HTlyRA4ODpo8ebImTJigLVu2GB0xWypQoIAWLlyYrgi8a9cutW7dWmfPnjUoGazR3/cK+ztehzyYo6Ojjh07poIFC+q1116Ts7OzQkJCdPLkSZUvX55CHZCD2BkdAAAyQ7du3WRnZ6fFixdnuDEnYCk1a9bUli1b9OWXX2rOnDlp+4NNmjRJxYsXNzpetteoUSM1atTI6Bg5ypAhQ/TEE08oIiJCHTp0SLs0va2trQYOHGhwuuwrOjra7Ep0d+TJk4flTrC4tWvXGh0hR7ozc9PX11fLli3Td999J4mZm0BORLEJgFUKCwtjY05kmQoVKmjmzJlGx8hRevfurcDAQPXu3dusfezYsTp27JhCQkKMCZZDPPPMM2a34+Li9OKLLxqUJmcIDAzUsmXL9NZbb5m1//777woICDAoFaxV9erVlStXrgzvo7h5fy+99JI6duyY9kHhnQ8jtm3bxms6IIeh2ATAKrExJ7LKP+0BVqhQoSxKkrP8+uuvWrhwYbr2GjVq6LPPPqPY9ACff/65ihQpomeffVaS1LFjR/3666/y9fXV0qVLVa5cOYMTZk/9+vXTW2+9pYsXL6p+/fqSUpe8jho1iucbLK5jx46aN29e2nK6O86fP68GDRpo//79BiXL3pi5CVgP9mwCYJXWrFmjDz/8UJ9++qnKli0re3t7s/vz5MljUDJYGxsbmwcu02Rfjow5Ojpq//79CgwMNGs/duyYnnjiCd24ccOgZNlfQECAfvzxR9WoUUMrV65Ux44d9fPPP2vOnDk6c+aMVqxYYXTEbOv777/X8OHD066CWKRIEQ0ZMkRdu3Y1OBmszZNPPqmgoCBNmTIlrS0yMlL169dXmTJlNHfuXAPTAUDmo9gEwCqxMSeyyp49e8xu3759W7t379ZXX32l4cOHq127dgYly96eeOIJ9ejRI92SpjFjxuj777/XwYMHDUqW/Tk5OenIkSPy9/fX22+/rRs3bmj8+PE6cuSInnzyScXGxhodMdu7ePGinJyc5OLiYnQUWKno6GjVrl1bjRs31ujRo3Xu3DnVr19f5cuX1+zZs9PNeMJdq1ev1urVq3XhwgUlJyeb3Td58mSDUgH4t1hGB8AqsTEnssqdSzT/XXBwsPz8/PTll19SbLoPljQ9Og8PD0VERMjf31/Lli3TsGHDJKUW0ymkPxxvb2+jI8DKeXl5afny5apVq5YkacmSJapUqZJmzpxJoekBhg4dqk8++UTBwcFc4AXI4ZjZBABAJjh69KgqVKigq1evGh0l22JJ06N56623tHjxYhUvXly7d+/WqVOn5OLiop9//lmff/65du3aZXTEbOn8+fPq379/2oyJe18CU6hDZjh69Khq1aqlRo0aacaMGRRP/oGvr6+++OILdenSxegoAP4jik0ArNq1a9d05swZ3bp1y6ydDXRhKQkJCWa3U1JSFBkZqSFDhujw4cMKCwszJlgOwpKmf+f27dv6+uuvFRERoW7duqlixYqSpJCQELm4uOiVV14xOGH21KxZM505c0ZvvfVWhjMm2rRpY1AyWAsPD48Mi0nXrl2Tg4ODbG1t09piYmKyMlqO4eXlpdDQUBUrVszoKAD+I4pNAKzSxYsX9dJLL+n333/P8H4+wYalZLRBeEpKivz9/TV79mxVr17doGTZW/369TVv3jy5u7ubtSckJKht27Zas2aNMcFgtVxdXbVhwwZVqFDB6CiwUtOmTXvovi+++GImJsm53nvvPbm4uOijjz4yOgqA/4g9mwBYpT59+ig2NlZbt25VvXr1NH/+fJ0/f17Dhg3TqFGjjI4HK3Lv/mA2Njby9vZWYGCg7Oz4M3s/69atSzfjUJJu3LihDRs2GJAoZ5kxY4bGjx+vEydOaMuWLSpcuLBCQkJUtGhRZujch7+/f7qlc4AlUUD6727cuKEffvhBq1atUrly5dJdTfirr74yKBmAf4tXwQCs0po1a/Tbb7+pSpUqsrGxUeHChdWoUSPlyZNHI0aMUIsWLYyOCCtRp04doyPkKHv37k37/uDBg4qKikq7nZSUpGXLlqlAgQJGRMsxvv/+e3388cfq06ePhg8fnjZT093dXSEhIRSb7iMkJEQDBw7U+PHjVaRIEaPjwMotXbpUtra2atKkiVn7ihUrlJSUpGbNmhmULHvbu3dv2uzD/fv3GxsGwH/CMjoAVilPnjzau3evihQpoiJFimjmzJmqWbOmTp48qTJlyujatWtGR0QOtnDhwofu27p160xMkvP8fdlhRi9BnJycNGbMGL388stZHS3HCAoK0qeffqq2bdvK1dVVe/bsUUBAgPbv36+6devq0qVLRkfMljw8PHTt2jUlJibK2dk53YwJ9tCBJZUrV06fffaZmjdvbta+bNkyvffee9qzZ49ByQAgazCzCYBVKlmypMLDw1WkSBFVqFAh7ZPscePGydfX1+h4yOHatm37UP1MJhP7g93j5MmTSklJUUBAgEJDQ80uQZ8rVy75+PiYbaKL9E6ePJm2KfjfOTg4cPXDBwgJCTE6Ah4jR48eVVBQULr2UqVK6dixYwYkyt7atWv3j31MJpN+/fXXLEgDwBIoNgGwSn369FFkZKQkafDgwWrSpIlmzpypXLlyaerUqcaGQ46XnJxsdIQcq3DhwpIYw/+iaNGiCgsLSxvLO37//fcM39wiFfvpICu5ubnpxIkT6ZZsHjt2TLlz5zYmVDbm5uZmdAQAFkaxCYBVeuGFF9K+r1ixok6dOqXDhw+rUKFCyps3r4HJYC1u3LihVatWqWXLlpKkQYMG6ebNm2n329nZ6ZNPPpGjo6NREbO16dOnP/D+rl27ZlGSnGfAgAF68803dePGDaWkpCg0NFSzZs3SiBEjNHHiRKPjZVtnzpx54P2FChXKoiR4HLRu3Vp9+vTR/PnzVaxYMUmphaZ33nmH5dUZmDJlitERAFgYezYBAPAIxo8fr8WLF2vRokWSUi+rXqZMGTk5OUmSDh8+rAEDBqhfv35Gxsy2PDw8zG7fvn1b165dU65cueTs7Mz+Of9gwoQJGjZsmCIiIiRJBQoU0JAhQ9S9e3eDk2Vff98vLCMseYUlxcfHq2nTptqxY4cKFiwoSTp79qyeeuopzZs3T+7u7sYGBIBMRrEJgFVKSkrS1KlTtXr1al24cCHdkp01a9YYlAzWonbt2urbt6+efvppSTLbqFmSfvzxR3377bfasmWLkTFzlKNHj+qNN97QgAED0l3BCakSExM1c+ZMNWnSRPnz59elS5eUnJwsHx8fo6Nle/duyHz79m3t3r1bX331lYYPH/5Qe8YA/0ZKSopWrlypPXv2yMnJSeXKlVPt2rWNjgUAWYJiEwCr9NZbb2nq1Klq0aKFfH19032aPXr0aIOSwVrkz59fq1evVpkyZSRJ3t7e2r59e9r+HEeOHFGVKlUUHx9vYMqcZ8eOHercubMOHz5sdJRsy9nZWYcOHUq3ZxMezZIlS/Tll19q3bp1RkcBAMBqsGcTAKs0e/ZszZkzJ90lhwFLiY+Pl53d3T+jFy9eNLs/OTnZbA8nPBxbW1v9+eefRsfI1p588knt3r2bYpOFlChRQtu3bzc6BqzAN998o9dee02Ojo765ptvHti3d+/eWZQKAIxBsQmAVcqVK5cCAwONjgErVrBgQe3fv18lS5bM8P69e/em7dOB9BYuXGh2OyUlRZGRkRo7dqxq1qxpUKqcoWfPnnrnnXd09uxZVa5cOd2VrcqVK2dQsuwtISHB7Pad59yQIUNUvHhxg1LBmowePVovvPCCHB0dHziD2mQyUWwCYPVYRgfAKo0aNUonTpzQ2LFjH7ghLPCo3n77ba1atUo7d+5Md8W569evKzg4WA0bNtTXX39tUMLszcbGxuy2yWSSt7e36tevr1GjRsnX19egZNnfvWMnpY5fSkqKTCYTG13fR0YbhKekpMjf31+zZ89W9erVDUoGAID1odgEwCo9/fTTWrt2rTw9PVWmTBnZ29ub3T9v3jyDksFanD9/XhUqVFCuXLn01ltvqUSJEjKZTDp8+LDGjh2rxMRE7d69W/ny5TM6arZ28eJFmUwm5c2b1+goOcbp06cfeD/L6zK2fv16s9s2Njby9vZWYGCg2ZJYAADw31FsAmCVXnrppQfeP2XKlCxKAmt28uRJvfHGG1q5cqXu/Dk1mUxq1KiRvvvuu7Qr08FcXFycPvjgA/3888+KjY2VJHl4eKhTp04aNmwYlwR/gMuXL2vr1q26ffu2qlatSpHuIXz88ccaOHCgnJ2dJUmxsbHy8PAwOBWsHVfFBfC4o9gEAMB/FBMTo2PHjkmSAgMD5enpaXCi7CsmJkbVq1fXuXPn9MILL6h06dJKSUnRoUOH9NNPP8nf31+bN2+mGJCBvXv3qlmzZoqKilJKSory5MmjuXPnqmHDhkZHy9ZsbW0VGRkpHx8fSVKePHkUFhZGMRiZiqviAnjcUWwCAABZpk+fPlq9erVWrVqVbolhVFSUGjdurAYNGvBGLAPNmzdXbGysRo0aJUdHRw0dOlTh4eE6fPiw0dGyNRsbG0VFRaUVm1xdXbVnzx6KTchUefPm1fTp07kqLoDHFsUmAFapYsWKGW4MbjKZ5OjoqMDAQHXr1k316tUzIB3w+CpSpIjGjx+vJk2aZHj/smXL1KNHD506dSprg+UAPj4+Wrp0qYKDgyVJ0dHR8vHxUXx8vFxcXAxOl31RbIIR/Pz8tG7dOpUoUcLoKABgiPSXMwEAK9C0aVOdOHFCuXPnVr169VS3bl25uLjo+PHjqlKliiIjI9WwYUP99ttvRkcFHiuRkZEqU6bMfe9/4oknFBUVlYWJco5Lly6pUKFCabe9vLzk7OysixcvGpgq+zOZTLp8+bISEhIUHx8vk8mkK1euKCEhwewLsKR33nlHX3/9tfhcH8DjiktvALBKly5d0jvvvKOPPvrIrH3YsGE6ffq0VqxYocGDB+t///uf2rRpY1BK4PGTN29enTp1SgULFszw/pMnT8rLyyuLU+UMd4omjo6OkqSUlBSzQsodefLkMSpitpSSkmI2uyQlJUUVK1Y0u20ymZSUlGREPFiRdu3amd1es2aNfv/9d66KC+CxxDI6AFbJzc1NO3fuVGBgoFn7sWPHVLlyZcXHx+vw4cOqUqWKLl++bFBK4PHTvXt3HTt2TCtXrlSuXLnM7rt586aaNGmiYsWKadKkSQYlzL5sbGzSLQ++Uyj5+/cUTcytX7/+ofrVqVMnk5PA2v3TlXD/jqviArB2zGwCYJUcHR21efPmdMWmzZs3p80KSE5OloODgxHxgMfW0KFDFRwcrOLFi+vNN99UqVKlJEkHDx7Ud999p5s3b2rGjBkGp8ye1q5da3SEHIkiErLKlClTdObMGRUsWFA2NuxWAuDxRrEJgFXq1auXevTooZ07d6pKlSoymUwKDQ3VxIkT9f7770uSli9fbraUAkDmK1iwoLZs2aKePXtq0KBBafuZmEwmNWrUSGPHjpW/v7/BKbMniib/3fHjxzVlyhQdP35cX3/9tXx8fLRs2TL5+/s/cC8x4GEVLVpUkZGRaRvSA8DjimV0AKzWzJkzNXbsWIWHh0uSSpYsqV69eun555+XJF2/fj3t6nQAsl5sbKyOHj0qSQoMDJSnp6fBibKvf7OBNXs2ZWz9+vVq1qyZatasqT/++EOHDh1SQECAvvjiC4WGhmru3LlGR4QVuPfqhwDwuKLYBAAAkM1ltF/T/bBnU8aqV6+uDh06qF+/fnJ1ddWePXsUEBCg7du3q23btjp37pzREWEFKDYBQCqW0QGwWnFxcZo7d65OnDih/v37y9PTU7t27VK+fPlUoEABo+MBwEP7+35Np06d0sCBA9WtWzdVr15dkrRlyxZNmzZNI0aMMCpitrdv3z799NNP6dq9vb0VHR1tQCJYq4kTJ8rFxeWBfXr37p1FaQDAGMxsAmCV9u7dq4YNG8rNzU2nTp1SeHi4AgIC9NFHH+n06dOaPn260REB4JE0aNBAr7zyip577jmz9p9++kk//PCD1q1bZ0ywbK5gwYKaM2eOatSoYTazaf78+erfv7+OHz9udERYARsbGxUsWFC2trb37WMymXTixIksTAUAWY/LJACwSv369VO3bt109OhRsz2ZmjVrpj/++MPAZADw32zZskXBwcHp2oODgxUaGmpAopzh+eef13vvvaeoqCiZTCYlJydr06ZN6t+/v7p27Wp0PFiRHTt26OTJk/f9otAE4HFAsQmAVdq+fbtef/31dO0FChRQVFSUAYkAwDL8/f01bty4dO3jx4/nSn4PMHz4cBUqVEgFChTQlStXFBQUpNq1a6tGjRr68MMPjY4HK/Gwe6sBgLVjzyYAVsnR0THDqzeFh4fL29vbgEQAYBmjR49W+/bttXz5clWrVk2StHXrVh0/fly//vqrwemyL3t7e82cOVOffPKJdu/ereTkZFWsWFHFixc3OhqsCDuUAEAqZjYBsEpt2rTRJ598otu3b0tK/aTxzJkzGjhwoNq3b29wOgB4dM2bN9fRo0fVunVrxcTEKDo6Wm3atNGRI0fUvHlzo+Nle/7+/ipbtqzatWtHoQkWN3jw4H/cHBwAHgdsEA7AKiUkJKh58+Y6cOCALl++LD8/P0VFRal69epaunSpcufObXREAEAWunbtmnr16qVp06ZJko4cOaKAgAD17t1bfn5+GjhwoMEJYW3i4uIUGhqqCxcuKDk52ew+9gkDYO0oNgGwamvWrNGuXbuUnJysSpUqqWHDhkZHAoD/LC4uTpMmTdKhQ4dkMpkUFBSkl19+WW5ubkZHy7befvttbdq0SSEhIWratKn27t2rgIAALVy4UIMHD9bu3buNjggrsmjRIr3wwgu6evWqXF1dzfZyMplMiomJMTAdAGQ+ik0ArE5iYqIcHR0VFhamJ554wug4AGBRO3bsUJMmTeTk5KSqVasqJSVFO3bs0PXr17VixQpVqlTJ6IjZUuHChfXzzz+rWrVqcnV11Z49exQQEKBjx46pUqVKGe7zBzyqEiVKqHnz5vr000/l7OxsdBwAyHJsEA7A6tjZ2alw4cJKSkoyOgoAWFzfvn3VunVrTZgwQXZ2qS/lEhMT9corr6hPnz76448/DE6YPV28eFE+Pj7p2q9evcoVxGBx586dU+/evSk0AXhssUE4AKv04YcfatCgQUxTB2B1duzYoffeey+t0CSlFtnfffdd7dixw8Bk2VuVKlW0ZMmStNt3CkwTJkxQ9erVjYoFK9WkSRN+HwE81pjZBMAqffPNNzp27Jj8/PxUuHDhdBuC79q1y6BkAPDf5MmTR2fOnFGpUqXM2iMiIuTq6mpQquxvxIgRatq0qQ4ePKjExER9/fXXOnDggLZs2aL169cbHQ9WpkWLFhowYIAOHjyosmXLyt7e3uz+1q1bG5QMALIGezYBsEpDhw6VyWTS/f6JGzx4cBYnAgDL6N27t+bPn6+RI0eqRo0aMplM2rhxowYMGKD27dsrJCTE6IjZ1v79+/Xll19q586daReOeO+991S2bFmjo8HK2NjcfwGJyWRiqT8Aq0exCYBVuXbtmgYMGKAFCxbo9u3batCggcaMGaO8efMaHQ0ALOLWrVsaMGCAxo0bp8TEREmSvb293njjDX322WdycHAwOGH2c/v2bb322mv66KOPFBAQYHQcAACsHsUmAFZlwIAB+u677/TCCy/IyclJP/30k+rWratffvnF6GgAYFHXrl3T8ePHlZKSosDAQDYi/gfu7u7atWsXxSYAALIAxSYAVqVYsWIaPny4OnXqJEkKDQ1VzZo1dePGDdna2hqcDgAs6+zZszKZTCpQoIDRUbK9l156SWXLllW/fv2MjgIr9c033+i1116To6Ojvvnmmwf27d27dxalAgBjUGwCYFVy5cqlkydPmr3xcnJy0pEjR+Tv729gMgCwjOTkZA0bNkyjRo3SlStXJEmurq5655139MEHHzxwr5jH2fDhwzVy5Eg1aNBAlStXTnfhCN78478qWrSoduzYIS8vLxUtWvS+/Uwmk06cOJGFyQAg61FsAmBVbG1tFRUVJW9v77Q2V1dX7d2794Ev/AAgpxg0aJAmTZqkoUOHqmbNmkpJSdGmTZs0ZMgQvfrqqxo+fLjREbMl3vwDAJB1KDYBsCo2NjZq1qyZ2Qa5ixYtUv369c0+xZ43b54R8QDgP/Pz89O4cePSXTr9t99+U8+ePXXu3DmDkgG4Y+/evSpXrlyG9y1YsEBt27bN2kAAkMXsjA4AAJb04osvpmvr3LmzAUkAIHPExMSoVKlS6dpLlSqlmJgYAxIBuFeTJk20adOmdBvS//rrr+ratauuXr1qUDIAyBoUmwBYlSlTphgdAQAyVfny5TV27Nh0GxCPHTtW5cuXNyhV9ne/jcFNJpMcHR0VGBioNm3ayNPTM4uTwRq98cYbatCggTZv3ixfX19J0s8//6yXX35ZU6dONTYcAGQBltEBAADkIOvXr1eLFi1UqFAhVa9eXSaTSZs3b1ZERISWLl2qp556yuiI2VK9evW0a9cuJSUlqWTJkkpJSdHRo0dla2urUqVKKTw8XCaTSRs3blRQUJDRcWEF3n77ba1atUobNmzQsmXL9Morr2jGjBlq37690dEAINNRbAIAAMhh/vzzT3377bc6fPiwUlJSFBQUpJ49e8rPz8/oaNlWSEiINmzYoClTpihPnjySpISEBHXv3l21atXSq6++queff17Xr1/X8uXLDU4La9GlSxdt27ZN586d008//aQ2bdoYHQkAsgTFJgAAAFi9AgUKaOXKlelmLR04cECNGzfWuXPntGvXLjVu3FiXLl0yKCVysoULF6Zru337tvr27avGjRubbep/7wb/AGBtKDYBAABkc3v37n3ovve7AtbjzsXFRYsXL1bdunXN2tetW6dWrVrp8uXLOnHihCpUqKCEhARjQiJHs7Gxeah+JpNJSUlJmZwGAIzFBuEAAADZXIUKFWQymfRPnxHyJvb+2rRpo5dfflmjRo1SlSpVZDKZFBoaqv79+6ddhj40NFQlSpQwNihyrOTkZKMjAEC2wcwmAACAbO706dMP3bdw4cKZmCTnunLlivr27avp06crMTFRkmRnZ6cXX3xRo0ePVu7cuRUWFiYptbgHPIpt27YpJiZGzZo1S2ubPn26Bg8erKtXr6pt27YaM2aMHBwcDEwJAJmPYhMAAEAOEh0dLS8vL0lSRESEJkyYoOvXr6t169Zcie4hXLlyRSdOnFBKSoqKFSsmFxcXoyPBijRt2lT16tXTe++9J0nat2+fKlWqpG7duql06dL68ssv9frrr2vIkCHGBgWATEaxCQAAIAfYt2+fWrVqpYiICBUvXlyzZ89W06ZNdfXqVdnY2Ojq1auaO3du2pIwAFnP19dXixYtUnBwsCTpgw8+0Pr167Vx40ZJ0i+//KLBgwfr4MGDRsYEgEzHnk0AAAA5wLvvvquyZcvqxx9/1I8//qiWLVuqefPmmjhxoiSpV69e+uyzzyg2/U27du00depU5cmTR+3atXtg33nz5mVRKliz2NhY5cuXL+32+vXr1bRp07TbVapUUUREhBHRACBLUWwCAADIAbZv3641a9aoXLlyqlChgn744Qf17Nkz7QpYvXr1UrVq1QxOmb24ubnJZDKlfQ9ktnz58unkyZPy9/fXrVu3tGvXLg0dOjTt/suXL8ve3t7AhACQNSg2AQAA5AAxMTHKnz+/JMnFxUW5c+eWp6dn2v0eHh66fPmyUfGypSlTpmT4PZBZmjZtqoEDB+rzzz/XggUL5OzsbLaX2t69e1WsWDEDEwJA1qDYBAAAkEPcmaVzv9sAjDVs2DC1a9dOderUkYuLi6ZNm6ZcuXKl3T958mQ1btzYwIQAkDXYIBwAACAHsLGxUbNmzdIumb5o0SLVr19fuXPnliTdvHlTy5YtU1JSkpExs5WKFSs+dEFu165dmZwGj5P4+Hi5uLjI1tbWrD0mJkYuLi5mBSgAsEbMbAIAAMgBXnzxRbPbnTt3Ttena9euWRUnR/j7Zuk3btzQd999p6CgIFWvXl2StHXrVh04cEA9e/Y0KCGs1f32CPv70lcAsGbMbAIAAIDVe+WVV+Tr66v//e9/Zu2DBw9WRESEJk+ebFAyAACsD8UmAAAAWD03Nzft2LFDxYsXN2s/evSogoODFR8fb1AyAACsj43RAQAAAIDM5uTkpI0bN6Zr37hxoxwdHQ1IBACA9WLPJgAAAFi9Pn366I033tDOnTtVrVo1Sal7Nk2ePFkff/yxwekAALAuLKMDAADAY2HOnDn6+uuvdejQIUlS6dKl9fbbb6tjx44GJwMAwLpQbAIAAAAAAIDFsGcTAAAAHgtxcXGaOHGi3n//fcXExEiSdu3apXPnzhmcDAAA68KeTQAAALB6e/fuVcOGDeXm5qZTp07plVdekaenp+bPn6/Tp09r+vTpRkcEAMBqMLMJAAAAVq9fv37q1q2bjh49anb1uWbNmumPP/4wMBkAANaHYhMAAACs3vbt2/X666+nay9QoICioqIMSAQAgPWi2AQAAACr5+joqISEhHTt4eHh8vb2NiARAADWi2ITAAAArF6bNm30ySef6Pbt25Ikk8mkM2fOaODAgWrfvr3B6QAAsC6mlJSUFKNDAAAAAJkpISFBzZs314EDB3T58mX5+fkpKipK1atX19KlS5U7d26jIwIAYDUoNgEAAOCxsXbtWu3cuVPJycmqVKmSGjZsaHQkAACsDsUmAAAAWLVffvlFCxYs0O3bt9WwYUO99tprRkcCAMCq2RkdAAAAAMgsP/zwg3r06KHixYvL0dFRv/76q06ePKkRI0YYHQ0AAKvFzCYAAABYrbJly6pt27b63//+J0maOnWqevXqpcuXLxucDAAA60WxCQAAAFYrd+7c2rdvnwICAiRJSUlJcnJy0pkzZ5Q/f36D0wEAYJ1sjA4AAAAAZJbr16/LxcUl7batra0cHBx07do1A1MBAGDd2LMJAAAAVm3ixIlmBafExERNnTpVefPmTWvr3bu3EdEAALBKLKMDAACA1SpSpIhMJtMD+5hMJp04cSKLEgEAYP0oNgEAAAAAAMBi2LMJAAAAj6W4uDijIwAAYJUoNgEAAMDqff755/r555/Tbnfo0EGenp4qUKCA9uzZY2AyAACsD8UmAAAAWL3x48fL399fkrRy5UqtWrVKy5YtU7NmzTRgwACD0wEAYF24Gh0AAACsXmRkZFqxafHixerYsaMaN26sIkWK6MknnzQ4HQAA1oWZTQAAALB6Hh4eioiIkCQtW7ZMDRs2lCSlpKQoKSnJyGgAAFgdZjYBAADA6rVr107PP/+8ihcvrujoaDVr1kySFBYWpsDAQIPTAQBgXSg2AQAAwOqNHj1aRYoUUUREhL744gu5uLhISl1e17NnT4PTAQBgXUwpKSkpRocAAAAAAACAdWDPJgAAADwWZsyYoVq1asnPz0+nT5+WJIWEhOi3334zOBkAANaFYhMAAACs3vfff69+/fqpWbNmiouLS9sU3N3dXSEhIcaGAwDAylBsAgAAgNUbM2aMJkyYoA8++EC2trZp7cHBwdq3b5+ByQAAsD4UmwAAAGD1Tp48qYoVK6Zrd3Bw0NWrVw1IBACA9aLYBAAAAKtXtGhRhYWFpWv//fffFRQUlPWBAACwYnZGBwAAAAAy24ABA/Tmm2/qxo0bSklJUWhoqGbNmqURI0Zo4sSJRscDAMCqmFJSUlKMDgEAAABktgkTJmjYsGGKiIiQJBUoUEBDhgxR9+7dDU4GAIB1odgEAACAx8qlS5eUnJwsHx8fo6MAAGCV2LMJAAAAVq9+/fqKi4uTJOXNmzet0JSQkKD69esbmAwAAOvDzCYAAABYPRsbG0VFRaWbzXThwgUVKFBAt2/fNigZAADWhw3CAQAAYLX27t2b9v3BgwcVFRWVdjspKUnLli1TgQIFjIgGAIDVYmYTAAAArJaNjY1MJpMkKaOXvU5OThozZoxefvnlrI4GAIDVotgEAAAAq3X69GmlpKQoICBAoaGh8vb2TrsvV65c8vHxka2trYEJAQCwPhSbAAAAAAAAYDFcjQ4AAACPhRkzZqhmzZry8/PT6dOnJUmjR4/Wb7/9ZnAyAACsC8UmAAAAWL3vv/9e/fr1U/PmzRUXF6ekpCRJkoeHh0JCQowNBwCAlaHYBAAAAKs3ZswYTZgwQR988IHZHk3BwcHat2+fgckAALA+FJsAAABg9U6ePKmKFSuma3dwcNDVq1cNSAQAgPWi2AQAAACrV7RoUYWFhaVr//333xUUFJT1gQAAsGJ2RgcAAAAAMtuAAQP05ptv6saNG0pJSVFoaKhmzZqlESNGaOLEiUbHAwDAqphSUlJSjA4BAAAAZLYJEyZo2LBhioiIkCQVKFBAQ4YMUffu3Q1OBgCAdaHYBAAAgMfKpUuXlJycLB8fH6OjAABglVhGBwAAgMfGhQsXFB4eLpPJJJPJJG9vb6MjAQBgddggHAAAAFYvISFBXbp0kZ+fn+rUqaPatWvLz89PnTt3Vnx8vNHxAACwKhSbAAAAYPVeeeUVbdu2TUuWLFFcXJzi4+O1ePFi7dixQ6+++qrR8QAAsCrs2QQAAACrlzt3bi1fvly1atUya9+wYYOaNm2qq1evGpQMAADrw8wmAAAAWD0vLy+5ubmla3dzc5OHh4cBiQAAsF4UmwAAAGD1PvzwQ/Xr10+RkZFpbVFRURowYIA++ugjA5MBAGB9WEYHAAAAq1SxYkWZTKa020ePHtXNmzdVqFAhSdKZM2fk4OCg4sWLa9euXUbFBADA6tgZHQAAAADIDG3btjU6AgAAjyVmNgEAAAAAAMBi2LMJAAAAAAAAFsMyOgAAAFi9pKQkjR49WnPmzNGZM2d069Yts/tjYmIMSgYAgPVhZhMAAACs3tChQ/XVV1+pY8eOio+PV79+/dSuXTvZ2NhoyJAhRscDAMCqsGcTAAAArF6xYsX0zTffqEWLFnJ1dVVYWFha29atW/XTTz8ZHREAAKvBzCYAAABYvaioKJUtW1aS5OLiovj4eElSy5YttWTJEiOjAQBgdSg2AQAAwOoVLFhQkZGRkqTAwECtWLFCkrR9+3Y5ODgYGQ0AAKtDsQkAAABW7+mnn9bq1aslSW+//bY++ugjFS9eXF27dtXLL79scDoAAKwLezYBAADgsbN161Zt3rxZgYGBat26tdFxAACwKhSbAAAAAAAAYDF2RgcAAAAAMsPChQvVrFkz2dvba+HChQ/sy+wmAAAsh5lNAAAAsEo2NjaKioqSj4+PbGzuv1WpyWRSUlJSFiYDAMC6UWwCAAAAAACAxbCMDgAAAFYtOTlZU6dO1bx583Tq1CmZTCYFBASoffv26tKli0wmk9ERAQCwKsxsAgAAgNVKSUlRq1attHTpUpUvX16lSpVSSkqKDh06pH379ql169ZasGCB0TEBALAqzGwCAACA1Zo6dar++OMPrV69WvXq1TO7b82aNWrbtq2mT5+url27GpQQAADrw8wmAAAAWK3GjRurfv36GjhwYIb3f/rpp1q/fr2WL1+exckAALBe978sBwAAAJDD7d27V02bNr3v/c2aNdOePXuyMBEAANaPYhMAAACsVkxMjPLly3ff+/Ply6fY2NgsTAQAgPWj2AQAAACrlZSUJDu7+29Tamtrq8TExCxMBACA9WODcAAAAFitlJQUdevWTQ4ODhnef/PmzSxOBACA9aPYBAAAAKv14osv/mMfrkQHAIBlcTU6AAAAAAAAWAx7NgEAAAAAAMBiKDYBAAAAAADAYig2AQAAAAAAwGIoNgEAAAD4fzt2LAAAAAAwyN96EjsLIwDYyCYAAAAANrIJAAAAgI1sAgAAAGAjmwAAAADYBPnYOfAe8C2UAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 1100x1100 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "corr_matrix = df.corr()\n",
    "sns.clustermap(corr_matrix, annot = True, fmt = \".2f\", cmap = \"viridis\", figsize=(11,11))\n",
    "plt.title(\"Correlation Between Features\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Base Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = df[\"Outcome\"]\n",
    "X = df.drop(\"Outcome\", axis=1)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=17)\n",
    "\n",
    "rf_model = RandomForestClassifier(random_state=46).fit(X_train, y_train)\n",
    "y_pred = rf_model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.77\n",
      "Recall: 0.706\n",
      "Precision: 0.59\n",
      "F1: 0.64\n",
      "Auc: 0.75\n"
     ]
    }
   ],
   "source": [
    "print(f\"Accuracy: {round(accuracy_score(y_pred, y_test), 2)}\")\n",
    "print(f\"Recall: {round(recall_score(y_pred,y_test),3)}\")\n",
    "print(f\"Precision: {round(precision_score(y_pred,y_test), 2)}\")\n",
    "print(f\"F1: {round(f1_score(y_pred,y_test), 2)}\")\n",
    "print(f\"Auc: {round(roc_auc_score(y_pred,y_test), 2)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.80      0.87      0.83       150\n",
      "           1       0.71      0.59      0.64        81\n",
      "\n",
      "    accuracy                           0.77       231\n",
      "   macro avg       0.75      0.73      0.74       231\n",
      "weighted avg       0.77      0.77      0.77       231\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_importance(model, features, num=len(X), save=False):\n",
    "    feature_imp = pd.DataFrame({'Value': model.feature_importances_, 'Feature': features.columns})\n",
    "    plt.figure(figsize=(10, 10))\n",
    "    sns.set(font_scale=1)\n",
    "    sns.barplot(x=\"Value\", y=\"Feature\", data=feature_imp.sort_values(by=\"Value\",\n",
    "                                                                     ascending=False)[0:num])\n",
    "    plt.title('Features')\n",
    "    plt.tight_layout()\n",
    "    plt.show()\n",
    "    if save:\n",
    "        plt.savefig('importances.png')\n",
    "\n",
    "plot_importance(rf_model, X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Feature Engineering"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Missing Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# It is known that variable values other than Pregnancies and Outcome cannot be 0 in a human.\n",
    "# Therefore, an action decision must be taken regarding these values. Values that are 0 can be assigned NaN.\n",
    "\n",
    "zero_columns = [col for col in df.columns if (df[col].min() == 0 and col not in [\"Pregnancies\", \"Outcome\"])]\n",
    "\n",
    "zero_columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "for col in zero_columns:\n",
    "    df[col] = np.where(df[col] == 0, np.nan, df[col])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "               n_miss  ratio\n",
      "Insulin           374 48.700\n",
      "SkinThickness     227 29.560\n",
      "BloodPressure      35  4.560\n",
      "BMI                11  1.430\n",
      "Glucose             5  0.650\n"
     ]
    }
   ],
   "source": [
    "na_columns = missing_values_table(df, na_name=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                 TARGET_MEAN  Count\n",
      "Glucose_NA_FLAG                    \n",
      "0                      0.349    763\n",
      "1                      0.400      5\n",
      "\n",
      "\n",
      "                       TARGET_MEAN  Count\n",
      "BloodPressure_NA_FLAG                    \n",
      "0                            0.344    733\n",
      "1                            0.457     35\n",
      "\n",
      "\n",
      "                       TARGET_MEAN  Count\n",
      "SkinThickness_NA_FLAG                    \n",
      "0                            0.333    541\n",
      "1                            0.388    227\n",
      "\n",
      "\n",
      "                 TARGET_MEAN  Count\n",
      "Insulin_NA_FLAG                    \n",
      "0                      0.330    394\n",
      "1                      0.369    374\n",
      "\n",
      "\n",
      "             TARGET_MEAN  Count\n",
      "BMI_NA_FLAG                    \n",
      "0                  0.351    757\n",
      "1                  0.182     11\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def missing_vs_target(dataframe, target, na_columns):\n",
    "    temp_df = dataframe.copy()\n",
    "    for col in na_columns:\n",
    "        temp_df[col + '_NA_FLAG'] = np.where(temp_df[col].isnull(), 1, 0)\n",
    "    na_flags = temp_df.loc[:, temp_df.columns.str.contains(\"_NA_\")].columns\n",
    "    for col in na_flags:\n",
    "        print(pd.DataFrame({\"TARGET_MEAN\": temp_df.groupby(col)[target].mean(),\n",
    "                            \"Count\": temp_df.groupby(col)[target].count()}), end=\"\\n\\n\\n\")\n",
    "\n",
    "\n",
    "missing_vs_target(df, \"Outcome\", na_columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Filling NA Values\n",
    "for col in zero_columns:\n",
    "    df.loc[df[col].isnull(), col] = df[col].median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Empty DataFrame\n",
      "Columns: [n_miss, ratio]\n",
      "Index: []\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "missing_values_table(df, na_name=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Outlier Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pregnancies False\n",
      "Glucose False\n",
      "BloodPressure False\n",
      "SkinThickness True\n",
      "Insulin True\n",
      "BMI False\n",
      "DiabetesPedigreeFunction False\n",
      "Age False\n",
      "Outcome False\n"
     ]
    }
   ],
   "source": [
    "for col in df.columns:\n",
    "    print(col, check_outlier(df, col))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pregnancies False\n",
      "Glucose False\n",
      "BloodPressure False\n",
      "SkinThickness True\n",
      "Insulin True\n",
      "BMI False\n",
      "DiabetesPedigreeFunction False\n",
      "Age False\n",
      "Outcome False\n"
     ]
    }
   ],
   "source": [
    "# Outlier Analysis and Suppression\n",
    "for col in df.columns:\n",
    "    print(col, check_outlier(df, col))\n",
    "    if check_outlier(df, col):\n",
    "        replace_with_thresholds(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Extraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Categorizing the age variable and creating a new age variable\n",
    "\n",
    "df.loc[(df[\"Age\"] >= 21) & (df[\"Age\"] < 50), \"NEW_AGE_CAT\"] = \"mature\"\n",
    "df.loc[(df[\"Age\"] >= 50), \"NEW_AGE_CAT\"] = \"senior\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# BMI below 18.5 is Underweight, between 18.5 and 24.9 is Normal, between 24.9 and 29.9 is Overweight and above 30 is Obese\n",
    "\n",
    "df['NEW_BMI'] = pd.cut(x=df['BMI'], bins=[0, 18.5, 24.9, 29.9, 100], labels=[\"Underweight\", \"Healthy\", \"Overweight\", \"Obese\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert glucose value to a categorical variable\n",
    "\n",
    "df[\"NEW_GLUCOSE\"] = pd.cut(x=df[\"Glucose\"], bins=[0, 140, 200, 300], labels=[\"Normal\", \"Prediabetes\", \"Diabetes\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating a categorical variable by considering age and body mass index together 3 breakdowns captured\n",
    "\n",
    "df.loc[(df[\"BMI\"] < 18.5) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_BMI_NOM\"] = \"underweightmature\"\n",
    "df.loc[(df[\"BMI\"] < 18.5) & (df[\"Age\"] >= 50), \"NEW_AGE_BMI_NOM\"] = \"underweightsenior\"\n",
    "df.loc[((df[\"BMI\"] >= 18.5) & (df[\"BMI\"] < 25)) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_BMI_NOM\"] = \"healthymature\"\n",
    "df.loc[((df[\"BMI\"] >= 18.5) & (df[\"BMI\"] < 25)) & (df[\"Age\"] >= 50), \"NEW_AGE_BMI_NOM\"] = \"healthysenior\"\n",
    "df.loc[((df[\"BMI\"] >= 25) & (df[\"BMI\"] < 30)) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_BMI_NOM\"] = \"overweightmature\"\n",
    "df.loc[((df[\"BMI\"] >= 25) & (df[\"BMI\"] < 30)) & (df[\"Age\"] >= 50), \"NEW_AGE_BMI_NOM\"] = \"overweightsenior\"\n",
    "df.loc[(df[\"BMI\"] > 18.5) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_BMI_NOM\"] = \"obesemature\"\n",
    "df.loc[(df[\"BMI\"] > 18.5) & (df[\"Age\"] >= 50), \"NEW_AGE_BMI_NOM\"] = \"obesesenior\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating a categorical variable by considering Age and Glucose values together\n",
    "\n",
    "df.loc[(df[\"Glucose\"] < 70) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_GLUCOSE_NOM\"] = \"lowmature\"\n",
    "df.loc[(df[\"Glucose\"] < 70) & (df[\"Age\"] >= 50), \"NEW_AGE_GLUCOSE_NOM\"] = \"lowsenior\"\n",
    "df.loc[((df[\"Glucose\"] >= 70) & (df[\"Glucose\"] < 100)) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_GLUCOSE_NOM\"] = \"normalmature\"\n",
    "df.loc[((df[\"Glucose\"] >= 70) & (df[\"Glucose\"] < 100)) & (df[\"Age\"] >= 50), \"NEW_AGE_GLUCOSE_NOM\"] = \"normalsenior\"\n",
    "df.loc[((df[\"Glucose\"] >= 100) & (df[\"Glucose\"] <= 125)) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_GLUCOSE_NOM\"] = \"hiddenmature\"\n",
    "df.loc[((df[\"Glucose\"] >= 100) & (df[\"Glucose\"] <= 125)) & (df[\"Age\"] >= 50), \"NEW_AGE_GLUCOSE_NOM\"] = \"hiddensenior\"\n",
    "df.loc[(df[\"Glucose\"] > 125) & ((df[\"Age\"] >= 21) & (df[\"Age\"] < 50)), \"NEW_AGE_GLUCOSE_NOM\"] = \"highmature\"\n",
    "df.loc[(df[\"Glucose\"] > 125) & (df[\"Age\"] >= 50), \"NEW_AGE_GLUCOSE_NOM\"] = \"highsenior\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Derive Categorical variable with Insulin Value\n",
    "\n",
    "def set_insulin(dataframe, col_name=\"Insulin\"):\n",
    "    if 16 <= dataframe[col_name] <= 166:\n",
    "        return \"Normal\"\n",
    "    else:\n",
    "        return \"Abnormal\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"NEW_INSULIN_SCORE\"] = df.apply(set_insulin, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"NEW_GLUCOSE*INSULIN\"] = df[\"Glucose\"] * df[\"Insulin\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"NEW_GLUCOSE*PREGNANCIES\"] = df[\"Glucose\"] * df[\"Pregnancies\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "      <th>NEW_AGE_CAT</th>\n",
       "      <th>NEW_BMI</th>\n",
       "      <th>NEW_GLUCOSE</th>\n",
       "      <th>NEW_AGE_BMI_NOM</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM</th>\n",
       "      <th>NEW_INSULIN_SCORE</th>\n",
       "      <th>NEW_GLUCOSE*INSULIN</th>\n",
       "      <th>NEW_GLUCOSE*PREGNANCIES</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148.000</td>\n",
       "      <td>72.000</td>\n",
       "      <td>35.000</td>\n",
       "      <td>125.000</td>\n",
       "      <td>33.600</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>senior</td>\n",
       "      <td>Obese</td>\n",
       "      <td>Prediabetes</td>\n",
       "      <td>obesesenior</td>\n",
       "      <td>highsenior</td>\n",
       "      <td>Normal</td>\n",
       "      <td>18500.000</td>\n",
       "      <td>888.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85.000</td>\n",
       "      <td>66.000</td>\n",
       "      <td>29.000</td>\n",
       "      <td>125.000</td>\n",
       "      <td>26.600</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>mature</td>\n",
       "      <td>Overweight</td>\n",
       "      <td>Normal</td>\n",
       "      <td>obesemature</td>\n",
       "      <td>normalmature</td>\n",
       "      <td>Normal</td>\n",
       "      <td>10625.000</td>\n",
       "      <td>85.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183.000</td>\n",
       "      <td>64.000</td>\n",
       "      <td>29.000</td>\n",
       "      <td>125.000</td>\n",
       "      <td>23.300</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "      <td>mature</td>\n",
       "      <td>Healthy</td>\n",
       "      <td>Prediabetes</td>\n",
       "      <td>obesemature</td>\n",
       "      <td>highmature</td>\n",
       "      <td>Normal</td>\n",
       "      <td>22875.000</td>\n",
       "      <td>1464.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89.000</td>\n",
       "      <td>66.000</td>\n",
       "      <td>23.000</td>\n",
       "      <td>94.000</td>\n",
       "      <td>28.100</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>mature</td>\n",
       "      <td>Overweight</td>\n",
       "      <td>Normal</td>\n",
       "      <td>obesemature</td>\n",
       "      <td>normalmature</td>\n",
       "      <td>Normal</td>\n",
       "      <td>8366.000</td>\n",
       "      <td>89.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137.000</td>\n",
       "      <td>40.000</td>\n",
       "      <td>35.000</td>\n",
       "      <td>168.000</td>\n",
       "      <td>43.100</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "      <td>mature</td>\n",
       "      <td>Obese</td>\n",
       "      <td>Normal</td>\n",
       "      <td>obesemature</td>\n",
       "      <td>highmature</td>\n",
       "      <td>Abnormal</td>\n",
       "      <td>23016.000</td>\n",
       "      <td>0.000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin    BMI  DiabetesPedigreeFunction  Age  Outcome NEW_AGE_CAT     NEW_BMI  NEW_GLUCOSE NEW_AGE_BMI_NOM  \\\n",
       "0            6  148.000         72.000         35.000  125.000 33.600                     0.627   50        1      senior       Obese  Prediabetes     obesesenior   \n",
       "1            1   85.000         66.000         29.000  125.000 26.600                     0.351   31        0      mature  Overweight       Normal     obesemature   \n",
       "2            8  183.000         64.000         29.000  125.000 23.300                     0.672   32        1      mature     Healthy  Prediabetes     obesemature   \n",
       "3            1   89.000         66.000         23.000   94.000 28.100                     0.167   21        0      mature  Overweight       Normal     obesemature   \n",
       "4            0  137.000         40.000         35.000  168.000 43.100                     2.288   33        1      mature       Obese       Normal     obesemature   \n",
       "\n",
       "  NEW_AGE_GLUCOSE_NOM NEW_INSULIN_SCORE  NEW_GLUCOSE*INSULIN  NEW_GLUCOSE*PREGNANCIES  \n",
       "0          highsenior            Normal            18500.000                  888.000  \n",
       "1        normalmature            Normal            10625.000                   85.000  \n",
       "2          highmature            Normal            22875.000                 1464.000  \n",
       "3        normalmature            Normal             8366.000                   89.000  \n",
       "4          highmature          Abnormal            23016.000                    0.000  "
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.columns = [col.upper() for col in df.columns]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Observations: 768\n",
      "Variables: 17\n",
      "cat_cols: 7\n",
      "num_cols: 10\n",
      "cat_but_car: 0\n",
      "num_but_cat: 3\n"
     ]
    }
   ],
   "source": [
    "cat_cols, num_cols, cat_but_car = grab_col_names(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Label Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "binary_cols = [col for col in df.columns if df[col].dtypes == \"O\" and df[col].nunique() == 2]\n",
    "\n",
    "for col in binary_cols:\n",
    "    df = label_encoder(df, col)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### One Hot Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['NEW_AGE_BMI_NOM', 'NEW_AGE_GLUCOSE_NOM', 'NEW_BMI', 'NEW_GLUCOSE']\n"
     ]
    }
   ],
   "source": [
    "cat_cols = [col for col in cat_cols if col not in binary_cols and col not in [\"OUTCOME\"]]\n",
    "print(cat_cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = one_hot_encoder(df, cat_cols, drop_first=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>PREGNANCIES</th>\n",
       "      <th>GLUCOSE</th>\n",
       "      <th>BLOODPRESSURE</th>\n",
       "      <th>SKINTHICKNESS</th>\n",
       "      <th>INSULIN</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DIABETESPEDIGREEFUNCTION</th>\n",
       "      <th>AGE</th>\n",
       "      <th>OUTCOME</th>\n",
       "      <th>NEW_AGE_CAT</th>\n",
       "      <th>NEW_INSULIN_SCORE</th>\n",
       "      <th>NEW_GLUCOSE*INSULIN</th>\n",
       "      <th>NEW_GLUCOSE*PREGNANCIES</th>\n",
       "      <th>NEW_AGE_BMI_NOM_obesesenior</th>\n",
       "      <th>NEW_AGE_BMI_NOM_underweightmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_hiddensenior</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_highmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_highsenior</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_lowmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_lowsenior</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_normalmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_normalsenior</th>\n",
       "      <th>NEW_BMI_Healthy</th>\n",
       "      <th>NEW_BMI_Overweight</th>\n",
       "      <th>NEW_BMI_Obese</th>\n",
       "      <th>NEW_GLUCOSE_Prediabetes</th>\n",
       "      <th>NEW_GLUCOSE_Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148.000</td>\n",
       "      <td>72.000</td>\n",
       "      <td>35.000</td>\n",
       "      <td>125.000</td>\n",
       "      <td>33.600</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>18500.000</td>\n",
       "      <td>888.000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85.000</td>\n",
       "      <td>66.000</td>\n",
       "      <td>29.000</td>\n",
       "      <td>125.000</td>\n",
       "      <td>26.600</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10625.000</td>\n",
       "      <td>85.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183.000</td>\n",
       "      <td>64.000</td>\n",
       "      <td>29.000</td>\n",
       "      <td>125.000</td>\n",
       "      <td>23.300</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>22875.000</td>\n",
       "      <td>1464.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89.000</td>\n",
       "      <td>66.000</td>\n",
       "      <td>23.000</td>\n",
       "      <td>94.000</td>\n",
       "      <td>28.100</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>8366.000</td>\n",
       "      <td>89.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137.000</td>\n",
       "      <td>40.000</td>\n",
       "      <td>35.000</td>\n",
       "      <td>168.000</td>\n",
       "      <td>43.100</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23016.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PREGNANCIES  GLUCOSE  BLOODPRESSURE  SKINTHICKNESS  INSULIN    BMI  DIABETESPEDIGREEFUNCTION  AGE  OUTCOME  NEW_AGE_CAT  NEW_INSULIN_SCORE  NEW_GLUCOSE*INSULIN  \\\n",
       "0            6  148.000         72.000         35.000  125.000 33.600                     0.627   50        1            1                  1            18500.000   \n",
       "1            1   85.000         66.000         29.000  125.000 26.600                     0.351   31        0            0                  1            10625.000   \n",
       "2            8  183.000         64.000         29.000  125.000 23.300                     0.672   32        1            0                  1            22875.000   \n",
       "3            1   89.000         66.000         23.000   94.000 28.100                     0.167   21        0            0                  1             8366.000   \n",
       "4            0  137.000         40.000         35.000  168.000 43.100                     2.288   33        1            0                  0            23016.000   \n",
       "\n",
       "   NEW_GLUCOSE*PREGNANCIES  NEW_AGE_BMI_NOM_obesesenior  NEW_AGE_BMI_NOM_underweightmature  NEW_AGE_GLUCOSE_NOM_hiddensenior  NEW_AGE_GLUCOSE_NOM_highmature  \\\n",
       "0                  888.000                            1                                  0                                 0                               0   \n",
       "1                   85.000                            0                                  0                                 0                               0   \n",
       "2                 1464.000                            0                                  0                                 0                               1   \n",
       "3                   89.000                            0                                  0                                 0                               0   \n",
       "4                    0.000                            0                                  0                                 0                               1   \n",
       "\n",
       "   NEW_AGE_GLUCOSE_NOM_highsenior  NEW_AGE_GLUCOSE_NOM_lowmature  NEW_AGE_GLUCOSE_NOM_lowsenior  NEW_AGE_GLUCOSE_NOM_normalmature  NEW_AGE_GLUCOSE_NOM_normalsenior  \\\n",
       "0                               1                              0                              0                                 0                                 0   \n",
       "1                               0                              0                              0                                 1                                 0   \n",
       "2                               0                              0                              0                                 0                                 0   \n",
       "3                               0                              0                              0                                 1                                 0   \n",
       "4                               0                              0                              0                                 0                                 0   \n",
       "\n",
       "   NEW_BMI_Healthy  NEW_BMI_Overweight  NEW_BMI_Obese  NEW_GLUCOSE_Prediabetes  NEW_GLUCOSE_Diabetes  \n",
       "0                0                   0              1                        1                     0  \n",
       "1                0                   1              0                        0                     0  \n",
       "2                1                   0              0                        1                     0  \n",
       "3                0                   1              0                        0                     0  \n",
       "4                0                   0              1                        0                     0  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Standardization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = StandardScaler()\n",
    "df[num_cols] = scaler.fit_transform(df[num_cols])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "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>PREGNANCIES</th>\n",
       "      <th>GLUCOSE</th>\n",
       "      <th>BLOODPRESSURE</th>\n",
       "      <th>SKINTHICKNESS</th>\n",
       "      <th>INSULIN</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DIABETESPEDIGREEFUNCTION</th>\n",
       "      <th>AGE</th>\n",
       "      <th>OUTCOME</th>\n",
       "      <th>NEW_AGE_CAT</th>\n",
       "      <th>NEW_INSULIN_SCORE</th>\n",
       "      <th>NEW_GLUCOSE*INSULIN</th>\n",
       "      <th>NEW_GLUCOSE*PREGNANCIES</th>\n",
       "      <th>NEW_AGE_BMI_NOM_obesesenior</th>\n",
       "      <th>NEW_AGE_BMI_NOM_underweightmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_hiddensenior</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_highmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_highsenior</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_lowmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_lowsenior</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_normalmature</th>\n",
       "      <th>NEW_AGE_GLUCOSE_NOM_normalsenior</th>\n",
       "      <th>NEW_BMI_Healthy</th>\n",
       "      <th>NEW_BMI_Overweight</th>\n",
       "      <th>NEW_BMI_Obese</th>\n",
       "      <th>NEW_GLUCOSE_Prediabetes</th>\n",
       "      <th>NEW_GLUCOSE_Diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.640</td>\n",
       "      <td>0.866</td>\n",
       "      <td>-0.032</td>\n",
       "      <td>0.680</td>\n",
       "      <td>-0.183</td>\n",
       "      <td>0.167</td>\n",
       "      <td>0.468</td>\n",
       "      <td>1.426</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.024</td>\n",
       "      <td>0.882</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.845</td>\n",
       "      <td>-1.205</td>\n",
       "      <td>-0.528</td>\n",
       "      <td>-0.011</td>\n",
       "      <td>-0.183</td>\n",
       "      <td>-0.852</td>\n",
       "      <td>-0.365</td>\n",
       "      <td>-0.191</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.503</td>\n",
       "      <td>-0.858</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.234</td>\n",
       "      <td>2.017</td>\n",
       "      <td>-0.694</td>\n",
       "      <td>-0.011</td>\n",
       "      <td>-0.183</td>\n",
       "      <td>-1.333</td>\n",
       "      <td>0.604</td>\n",
       "      <td>-0.106</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.317</td>\n",
       "      <td>2.129</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.845</td>\n",
       "      <td>-1.074</td>\n",
       "      <td>-0.528</td>\n",
       "      <td>-0.702</td>\n",
       "      <td>-0.553</td>\n",
       "      <td>-0.634</td>\n",
       "      <td>-0.921</td>\n",
       "      <td>-1.042</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.654</td>\n",
       "      <td>-0.849</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-1.142</td>\n",
       "      <td>0.504</td>\n",
       "      <td>-2.679</td>\n",
       "      <td>0.680</td>\n",
       "      <td>0.331</td>\n",
       "      <td>1.549</td>\n",
       "      <td>5.485</td>\n",
       "      <td>-0.020</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.326</td>\n",
       "      <td>-1.042</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PREGNANCIES  GLUCOSE  BLOODPRESSURE  SKINTHICKNESS  INSULIN    BMI  DIABETESPEDIGREEFUNCTION    AGE  OUTCOME  NEW_AGE_CAT  NEW_INSULIN_SCORE  NEW_GLUCOSE*INSULIN  \\\n",
       "0        0.640    0.866         -0.032          0.680   -0.183  0.167                     0.468  1.426        1            1                  1                0.024   \n",
       "1       -0.845   -1.205         -0.528         -0.011   -0.183 -0.852                    -0.365 -0.191        0            0                  1               -0.503   \n",
       "2        1.234    2.017         -0.694         -0.011   -0.183 -1.333                     0.604 -0.106        1            0                  1                0.317   \n",
       "3       -0.845   -1.074         -0.528         -0.702   -0.553 -0.634                    -0.921 -1.042        0            0                  1               -0.654   \n",
       "4       -1.142    0.504         -2.679          0.680    0.331  1.549                     5.485 -0.020        1            0                  0                0.326   \n",
       "\n",
       "   NEW_GLUCOSE*PREGNANCIES  NEW_AGE_BMI_NOM_obesesenior  NEW_AGE_BMI_NOM_underweightmature  NEW_AGE_GLUCOSE_NOM_hiddensenior  NEW_AGE_GLUCOSE_NOM_highmature  \\\n",
       "0                    0.882                            1                                  0                                 0                               0   \n",
       "1                   -0.858                            0                                  0                                 0                               0   \n",
       "2                    2.129                            0                                  0                                 0                               1   \n",
       "3                   -0.849                            0                                  0                                 0                               0   \n",
       "4                   -1.042                            0                                  0                                 0                               1   \n",
       "\n",
       "   NEW_AGE_GLUCOSE_NOM_highsenior  NEW_AGE_GLUCOSE_NOM_lowmature  NEW_AGE_GLUCOSE_NOM_lowsenior  NEW_AGE_GLUCOSE_NOM_normalmature  NEW_AGE_GLUCOSE_NOM_normalsenior  \\\n",
       "0                               1                              0                              0                                 0                                 0   \n",
       "1                               0                              0                              0                                 1                                 0   \n",
       "2                               0                              0                              0                                 0                                 0   \n",
       "3                               0                              0                              0                                 1                                 0   \n",
       "4                               0                              0                              0                                 0                                 0   \n",
       "\n",
       "   NEW_BMI_Healthy  NEW_BMI_Overweight  NEW_BMI_Obese  NEW_GLUCOSE_Prediabetes  NEW_GLUCOSE_Diabetes  \n",
       "0                0                   0              1                        1                     0  \n",
       "1                0                   1              0                        0                     0  \n",
       "2                1                   0              0                        1                     0  \n",
       "3                0                   1              0                        0                     0  \n",
       "4                0                   0              1                        0                     0  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(768, 27)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Final Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = df[\"OUTCOME\"]\n",
    "X = df.drop(\"OUTCOME\", axis=1)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=17)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "rf_model = RandomForestClassifier(random_state=46).fit(X_train, y_train)\n",
    "y_pred = rf_model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.83      0.85      0.84       150\n",
      "           1       0.71      0.67      0.69        81\n",
      "\n",
      "    accuracy                           0.79       231\n",
      "   macro avg       0.77      0.76      0.76       231\n",
      "weighted avg       0.79      0.79      0.79       231\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Importance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    Value                            Feature\n",
      "1   0.138                            GLUCOSE\n",
      "10  0.131                NEW_GLUCOSE*INSULIN\n",
      "5   0.099                                BMI\n",
      "11  0.098            NEW_GLUCOSE*PREGNANCIES\n",
      "7   0.097                                AGE\n",
      "6   0.094           DIABETESPEDIGREEFUNCTION\n",
      "2   0.059                      BLOODPRESSURE\n",
      "0   0.051                        PREGNANCIES\n",
      "4   0.051                            INSULIN\n",
      "24  0.050            NEW_GLUCOSE_Prediabetes\n",
      "3   0.046                      SKINTHICKNESS\n",
      "19  0.017   NEW_AGE_GLUCOSE_NOM_normalmature\n",
      "15  0.014     NEW_AGE_GLUCOSE_NOM_highmature\n",
      "23  0.014                      NEW_BMI_Obese\n",
      "21  0.010                    NEW_BMI_Healthy\n",
      "22  0.008                 NEW_BMI_Overweight\n",
      "9   0.006                  NEW_INSULIN_SCORE\n",
      "8   0.005                        NEW_AGE_CAT\n",
      "12  0.005        NEW_AGE_BMI_NOM_obesesenior\n",
      "16  0.002     NEW_AGE_GLUCOSE_NOM_highsenior\n",
      "14  0.002   NEW_AGE_GLUCOSE_NOM_hiddensenior\n",
      "20  0.001   NEW_AGE_GLUCOSE_NOM_normalsenior\n",
      "17  0.000      NEW_AGE_GLUCOSE_NOM_lowmature\n",
      "13  0.000  NEW_AGE_BMI_NOM_underweightmature\n",
      "18  0.000      NEW_AGE_GLUCOSE_NOM_lowsenior\n",
      "25  0.000               NEW_GLUCOSE_Diabetes\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 640x480 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def plot_importance(model, features, num=len(X), save=False):\n",
    "    feature_imp = pd.DataFrame({'Value': model.feature_importances_, 'Feature': features.columns})\n",
    "    print(feature_imp.sort_values(\"Value\",ascending=False))\n",
    "    plt.figure(figsize=(10, 10))\n",
    "    sns.set(font_scale=1)\n",
    "    sns.barplot(x=\"Value\", y=\"Feature\", data=feature_imp.sort_values(by=\"Value\",\n",
    "                                                                     ascending=False)[0:num])\n",
    "    plt.title('Features')\n",
    "    plt.tight_layout()\n",
    "    plt.show();\n",
    "    if save:\n",
    "        plt.savefig('outputs/importances.png')\n",
    "\n",
    "plot_importance(rf_model, X, 10, save=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Save Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('outputs/diabetes_rf_model.pkl', 'wb') as f:\n",
    "    pickle.dump(rf_model, f)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.13 ('dsprojects')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  },
  "papermill": {
   "duration": 46.236702,
   "end_time": "2020-11-08T15:21:41.703929",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2020-11-08T15:20:55.467227",
   "version": "2.1.0"
  },
  "vscode": {
   "interpreter": {
    "hash": "78fd003daa28446435b2b6538571e501a8b37e58f7b5c6cbe8ad03b3dfc8ae3a"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}