{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![MLU Logo](../../data/MLU_Logo.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "# <a name=\"0\">Responsible AI - Disparate Impact</a>\n",
    "\n",
    "This notebook shows how to quantify disparate impact and covers the implementation of a basic disparate impact remover. We will use a Logistic Regression classifier to predict whether an individuals' income is $\\leq$ 50k or not using US census data.\n",
    "\n",
    "__Dataset:__ \n",
    "You will download a dataset for this exercise using [folktables](https://github.com/zykls/folktables). Folktables provides an API to download data from the American Community Survey (ACS) Public Use Microdata Sample (PUMS) files which are managed by the US Census Bureau. The data itself is governed by the terms of use provided by the Census Bureau. For more information, see the [Terms of Service](https://www.census.gov/data/developers/about/terms-of-service.html).\n",
    "\n",
    "__ML Problem:__ \n",
    "Ultimately, the goal will be to predict whether an individual's income is above \\\\$50,000. We will filter the ACS PUMS data sample to only include individuals above the age of 16, who reported usual working hours of at least 1 hour per week in the past year, and an income of at least \\\\$100. The threshold of \\\\$50,000 was chosen so that this dataset can serve as a comparable substitute to the [UCI Adult dataset](https://archive.ics.uci.edu/ml/datasets/adult). The income threshold can be changed easily to define new prediction tasks.\n",
    "\n",
    "1. <a href=\"#1\">Read the dataset</a>\n",
    "2. <a href=\"#2\">Data Processing</a>\n",
    "    * <a href=\"#21\">Exploratory Data Analysis</a>\n",
    "    * <a href=\"#22\">Select features to build the model</a>\n",
    "    * <a href=\"#23\">Feature Transformation</a>\n",
    "    * <a href=\"#24\">Train - Validation - Test Datasets</a>\n",
    "    * <a href=\"#25\">Data processing with Pipeline and ColumnTransformer</a>\n",
    "3. <a href=\"#3\">Train (and Tune) a Classifier</a>\n",
    "4. <a href=\"#4\">Test the Classifier</a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook assumes an installation of the SageMaker kernel `conda_pytorch_p39`. In addition, libraries from a requirements.txt need to be installed:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!pip install --no-deps -U -q -r ../../requirements.txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%%capture\n",
    "\n",
    "# Reshaping/basic libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# Plotting libraries\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline\n",
    "\n",
    "sns.set_style(\"darkgrid\", {\"axes.facecolor\": \".9\"})\n",
    "\n",
    "# ML libraries\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.preprocessing import OneHotEncoder, MinMaxScaler\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "# Operational libraries\n",
    "import sys\n",
    "from tqdm import tqdm\n",
    "\n",
    "sys.path.append(\"..\")\n",
    "\n",
    "# Fairness libraries\n",
    "from folktables.acs import *\n",
    "from folktables.folktables import *\n",
    "from folktables.load_acs import *\n",
    "from aif360.datasets import BinaryLabelDataset, Dataset\n",
    "from aif360.metrics import BinaryLabelDatasetMetric\n",
    "from aif360.algorithms.preprocessing import DisparateImpactRemover\n",
    "\n",
    "# Jupyter(lab) libraries\n",
    "import warnings\n",
    "\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "## 1. <a name=\"1\">Read the dataset</a>\n",
    "(<a href=\"#0\">Go to top</a>)\n",
    "\n",
    "To read in the dataset, we will be using [folktables](https://github.com/zykls/folktables) which provides access to the US Census dataset. Folktables contains predefined prediction tasks but also allows the user to specify the problem type.\n",
    "\n",
    "The US Census dataset distinguishes between household and individuals. To obtain data on individuals, we use `ACSDataSource` with `survey=person`. The feature names for the US Census data follow the same distinction and use `P` for `person` and `H` for `household`, e.g.: `AGEP` refers to age of an individual."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "income_features = [\n",
    "    \"AGEP\",  # age individual\n",
    "    \"COW\",  # class of worker\n",
    "    \"SCHL\",  # educational attainment\n",
    "    \"MAR\",  # marital status\n",
    "    \"OCCP\",  # occupation\n",
    "    \"POBP\",  # place of birth\n",
    "    \"RELP\",  # relationship\n",
    "    \"WKHP\",  # hours worked per week past 12 months\n",
    "    \"SEX\",  # sex\n",
    "    \"RAC1P\",  # recorded detailed race code\n",
    "    \"PWGTP\",  # persons weight\n",
    "    \"GCL\",  # grand parents living with grandchildren\n",
    "    \"SCH\",  # school enrollment\n",
    "]\n",
    "\n",
    "# Define the prediction problem and features\n",
    "ACSIncome = folktables.BasicProblem(\n",
    "    features=income_features,\n",
    "    target=\"PINCP\",  # total persons income\n",
    "    target_transform=lambda x: x > 50000,\n",
    "    group=\"RAC1P\",\n",
    "    preprocess=adult_filter,  # applies the following conditions; ((AAGE>16) && (AGI>100) && (AFNLWGT>1)&& (HRSWK>0))\n",
    "    postprocess=lambda x: x,  # applies post processing, e.g. fill all NAs\n",
    ")\n",
    "\n",
    "# Initialize year, duration (\"1-Year\" or \"5-Year\") and granularity (household or person)\n",
    "data_source = ACSDataSource(survey_year=\"2018\", horizon=\"1-Year\", survey=\"person\")\n",
    "# Specify region (here: California) and load data\n",
    "ca_data = data_source.get_data(states=[\"CA\"], download=True)\n",
    "# Apply transformation as per problem statement above\n",
    "ca_features, ca_labels, ca_group = ACSIncome.df_to_numpy(ca_data)\n",
    "\n",
    "# Convert numpy array to dataframe\n",
    "df = pd.DataFrame(\n",
    "    np.concatenate((ca_features, ca_labels.reshape(-1, 1)), axis=1),\n",
    "    columns=income_features + [\">50k\"],\n",
    ")\n",
    "\n",
    "# For further modelling you want to use only 2 groups\n",
    "df = df[df[\"RAC1P\"].isin([6, 8])].copy(deep=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "## 2. <a name=\"2\">Data Processing</a>\n",
    "(<a href=\"#0\">Go to top</a>)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.1 <a name=\"21\">Exploratory Data Analysis</a>\n",
    "(<a href=\"#2\">Go to Data Processing</a>)\n",
    "\n",
    "We look at number of rows, columns, and some simple statistics of the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "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>AGEP</th>\n",
       "      <th>COW</th>\n",
       "      <th>SCHL</th>\n",
       "      <th>MAR</th>\n",
       "      <th>OCCP</th>\n",
       "      <th>POBP</th>\n",
       "      <th>RELP</th>\n",
       "      <th>WKHP</th>\n",
       "      <th>SEX</th>\n",
       "      <th>RAC1P</th>\n",
       "      <th>PWGTP</th>\n",
       "      <th>GCL</th>\n",
       "      <th>SCH</th>\n",
       "      <th>&gt;50k</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>30.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9610.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>23.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2545.0</td>\n",
       "      <td>207.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>18.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>9610.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>40.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4140.0</td>\n",
       "      <td>303.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>38.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49</th>\n",
       "      <td>18.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>725.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    AGEP  COW  SCHL  MAR    OCCP   POBP  RELP  WKHP  SEX  RAC1P  PWGTP  GCL  \\\n",
       "0   30.0  6.0  14.0  1.0  9610.0    6.0  16.0  40.0  1.0    8.0   32.0  2.0   \n",
       "27  23.0  2.0  21.0  5.0  2545.0  207.0  17.0  20.0  2.0    6.0   35.0  NaN   \n",
       "33  18.0  1.0  16.0  5.0  9610.0    6.0  17.0   8.0  2.0    6.0   33.0  NaN   \n",
       "46  40.0  1.0  15.0  3.0  4140.0  303.0  16.0  22.0  1.0    8.0   38.0  2.0   \n",
       "49  18.0  1.0  18.0  5.0   725.0    6.0  17.0  12.0  2.0    6.0   60.0  NaN   \n",
       "\n",
       "    SCH  >50k  \n",
       "0   1.0   0.0  \n",
       "27  3.0   0.0  \n",
       "33  2.0   0.0  \n",
       "46  1.0   0.0  \n",
       "49  2.0   0.0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Print the first five rows\n",
    "# NaN means missing data\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The shape of the dataset is: (55502, 14)\n"
     ]
    }
   ],
   "source": [
    "# Check how many rows and columns we have in the data frame\n",
    "print(\"The shape of the dataset is:\", df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 55502 entries, 0 to 195664\n",
      "Data columns (total 14 columns):\n",
      " #   Column  Non-Null Count  Dtype  \n",
      "---  ------  --------------  -----  \n",
      " 0   AGEP    55502 non-null  float64\n",
      " 1   COW     55502 non-null  float64\n",
      " 2   SCHL    55502 non-null  float64\n",
      " 3   MAR     55502 non-null  float64\n",
      " 4   OCCP    55502 non-null  float64\n",
      " 5   POBP    55502 non-null  float64\n",
      " 6   RELP    55502 non-null  float64\n",
      " 7   WKHP    55502 non-null  float64\n",
      " 8   SEX     55502 non-null  float64\n",
      " 9   RAC1P   55502 non-null  float64\n",
      " 10  PWGTP   55502 non-null  float64\n",
      " 11  GCL     41987 non-null  float64\n",
      " 12  SCH     55502 non-null  float64\n",
      " 13  >50k    55502 non-null  float64\n",
      "dtypes: float64(14)\n",
      "memory usage: 6.4 MB\n"
     ]
    }
   ],
   "source": [
    "# Let's see the data types and non-null values for each column\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can clearly see that all columns are numerical (`dtype = float64`). However, when checking the column headers (and information at top of the notebook), we should notice that we are actually dealing with multimodal data. We expect to see a mix of categorical, numerical and potentially even text information.\n",
    "\n",
    "Let's cast the features accordingly. We start by creating list for each feature type."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "categorical_features = [\n",
    "    \"COW\",\n",
    "    \"SCHL\",\n",
    "    \"MAR\",\n",
    "    \"OCCP\",\n",
    "    \"POBP\",\n",
    "    \"RELP\",\n",
    "    \"SEX\",\n",
    "    \"GCL\",\n",
    "    \"SCH\",\n",
    "]\n",
    "\n",
    "sensitive_attribute = \"RAC1P\"\n",
    "\n",
    "numerical_features = [\"AGEP\", \"WKHP\", \"PWGTP\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# We cast categorical features to `category`\n",
    "df[categorical_features] = df[categorical_features].astype(\"object\")\n",
    "\n",
    "# We cast the sensitive attribute as `category`\n",
    "df[sensitive_attribute] = df[sensitive_attribute].astype(\"object\")\n",
    "\n",
    "# We cast numerical features to `int`\n",
    "df[numerical_features] = df[numerical_features].astype(\"int\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's check with `.info()` again to make sure the changes took effect."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 55502 entries, 0 to 195664\n",
      "Data columns (total 14 columns):\n",
      " #   Column  Non-Null Count  Dtype  \n",
      "---  ------  --------------  -----  \n",
      " 0   AGEP    55502 non-null  int64  \n",
      " 1   COW     55502 non-null  object \n",
      " 2   SCHL    55502 non-null  object \n",
      " 3   MAR     55502 non-null  object \n",
      " 4   OCCP    55502 non-null  object \n",
      " 5   POBP    55502 non-null  object \n",
      " 6   RELP    55502 non-null  object \n",
      " 7   WKHP    55502 non-null  int64  \n",
      " 8   SEX     55502 non-null  object \n",
      " 9   RAC1P   55502 non-null  object \n",
      " 10  PWGTP   55502 non-null  int64  \n",
      " 11  GCL     41987 non-null  object \n",
      " 12  SCH     55502 non-null  object \n",
      " 13  >50k    55502 non-null  float64\n",
      "dtypes: float64(1), int64(3), object(10)\n",
      "memory usage: 6.4+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Looks good, so we can now separate model features from model target to explore them separately."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model features:  ['COW', 'SCHL', 'MAR', 'OCCP', 'POBP', 'RELP', 'SEX', 'GCL', 'SCH', 'AGEP', 'WKHP', 'PWGTP', 'RAC1P']\n",
      "Model target:  >50k\n"
     ]
    }
   ],
   "source": [
    "model_target = \">50k\"\n",
    "model_features = categorical_features + numerical_features + [sensitive_attribute]\n",
    "\n",
    "print(\"Model features: \", model_features)\n",
    "print(\"Model target: \", model_target)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Double check that that target is not accidentally part of the features\n",
    "model_target in model_features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "All good here. We made sure that the target is not in the feature list. If we find the above statement showing `True` we need to remove the target by calling `model_features.remove(model_target)`.\n",
    "\n",
    "Let's have a look at missing values next.\n",
    "\n",
    "\n",
    "#### Missing values\n",
    "The quickest way to check for missing values is to use `.isna().sum()`. This will provide a count of how many missing values we have. In fact, we can also see the count of missing values with `.info()` as it provided a count of non-null values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AGEP         0\n",
       "COW          0\n",
       "SCHL         0\n",
       "MAR          0\n",
       "OCCP         0\n",
       "POBP         0\n",
       "RELP         0\n",
       "WKHP         0\n",
       "SEX          0\n",
       "RAC1P        0\n",
       "PWGTP        0\n",
       "GCL      13515\n",
       "SCH          0\n",
       ">50k         0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Show missing values\n",
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Before starting with the plots, let's have a look at how many unique instances we have per column. This helps us avoid plotting charts with hundreds of unique values. Let's filter for columns with fewer than 10 unique instances."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "COW      8.0\n",
      "MAR      5.0\n",
      "SEX      2.0\n",
      "GCL      2.0\n",
      "SCH      3.0\n",
      "RAC1P    2.0\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "shortlist_fts = (\n",
    "    df[model_features]\n",
    "    .apply(lambda col: col.nunique())\n",
    "    .where(df[model_features].apply(lambda col: col.nunique()) < 10)\n",
    "    .dropna()\n",
    ")\n",
    "\n",
    "print(shortlist_fts)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Target distribution\n",
    "\n",
    "Let's check our target distribution."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[model_target].value_counts().plot.bar(color=\"black\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We notice that we are dealing with an imbalanced dataset. This means there are more examples for one type of results (here: 0; meaning individuals earning $\\leq$ 50k). This is relevant for model choice and potential up-sampling or down-sampling to balance out the classes."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Feature distribution(s)\n",
    "\n",
    "Let's now plot bar charts for the shortlist features of our dataset (as per above: shortlist - feature columns with less than 10 unique instance classes)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABNQAAAOZCAYAAADWKX21AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAA9hAAAPYQGoP6dpAAD+nklEQVR4nOzde1yVZb7//zeLg4dQUkDMUzYQh0Q5jG0GgpgsKzX3BJS6kzyMpZOaVpo6ZgrqgBq2zXKPjhKKYuZOJTOtqb5ZOIBOKmO4SUU7aEzKwvGAJ07r94c/7nGJp6UsYenr+Xisx7Du63Pf9+e61pqW67Pu+7qcLBaLRQAAAAAAAACuiamhEwAAAAAAAAAcCQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAANjVpEmT1KNHj4ZOAwAAoN64NHQCAAAAV7N27Vr98Y9/vGTb888/r/Hjx9f7OXfs2KG//e1vGjx4sFq2bFnvx78RlxqP1q1by8/PT88995xiY2NvSh7PPvustm3bZjz38PBQx44d9V//9V+Kj4+XyXTjv90uXLhQfn5+euSRR274WAAAAPWFghoAAHAYY8aMUYcOHay2+fv72+VcO3fu1DvvvKO4uLhGV1CrVTseFotFZWVlWrdunYYPH66FCxfqoYceuik5tG3bVq+88ook6V//+peys7P12muv6YcffqiXQueiRYv02GOPUVADAACNCgU1AADgMB588EF17dq1odO4IadPn1bz5s3r5VgXj8dTTz2lBx54QBs2bKiXglpNTY0qKyvVpEmTy8a0aNFCv/vd74zn/fv31+OPP66srCyNHTtWrq6uN5wHAABAY8McagAA4Jbx1Vdf6ZlnnlFoaKjCwsI0fPhw7du3zyrmu+++06RJk/Twww+ra9eueuCBB/THP/5R//rXv4yYt99+W3PmzJEkPfzwwwoICFBAQIAOHTqkQ4cOKSAgQGvXrq1z/oCAAL399ttWxwkICFBxcbHGjRun+++/X88884zR/uGHHyo+Pl7dunXTf/zHf+jll1/WP//5z+vuf8uWLdWkSRO5uFj/Zpqenq4BAwYoIiJC3bp1U3x8vD755JNL5j99+nStX79effr0UdeuXZWTk2NTDs2aNVNISIhOnz6to0ePXjbu9OnTmjVrlmJjYxUcHKzHHntM6enpslgsVvmcPn1a69atM16DSZMmSZLKy8v1pz/9ST169FBwcLAiIyM1dOhQ7d6926Z8AQAArgdXqAEAAIdRXl5ep0jTunVrSVJ2drYmTZqk6OhojR8/XmfOnNF7772nZ555RuvWrTNuFc3NzdXBgwcVHx8vb29v7du3T6tXr1ZxcbFWr14tJycn9ezZUz/88IM2bNigP/7xj2rVqpVxrisViS5n7Nixuvvuu/Xyyy8bBaM///nPeuutt9SrVy899dRTOnr0qFasWKGBAwcqOzv7mm4zvXA8ysrKtHz5cp0+fVr/+Z//aRWXmZmpHj16qG/fvqqsrNTHH3+ssWPHatGiRfrtb39rFZufn69NmzZp4MCBatWqldq3b29zfw8dOiRnZ+fL9sFiseiFF17Q1q1b9dRTTykoKEg5OTmaM2eODh8+rMmTJ0uS5syZoylTpqhbt27q16+fJKlTp06SpGnTpunTTz9VYmKifH19dezYMW3fvl379+9Xly5dbM4ZAADAFhTUAACAwxgyZEidbXv27NGpU6f0pz/9SU8//bRmzJhhtMXFxenxxx/XokWLjO3PPPOMfv/731sdIzQ0VK+88oq2b9+u7t27KzAwUPfdd582bNigRx55xGretuspqAUGBmru3LnG859//llvv/22XnrpJf3hD38wtj/66KOKi4vTypUrrbZfzsXj4ebmppSUFD3wwANW2z/99FM1bdrUeD5w4EDFx8crIyOjTkHt+++/10cffSQ/P79r6lt1dbUxJv/617/03nvvaffu3XrooYfUrFmzS+7zxRdfKD8/Xy+99JJeeOEFI6cxY8YoMzNTiYmJ6tSpk373u98pKSlJHTt2tLqtVDp/NWK/fv2MK9ak8wtUAAAA3AwU1AAAgMOYOnWq7rnnnjrbc3NzdeLECfXp08eq4GUymRQSEqKtW7ca2y4sLJ07d06nTp1SSEiIJGn37t3q3r17vec9YMAAq+efffaZampq1KtXL6t8vby8dPfdd2vr1q3XVFC7cDzMZrPWr1+vKVOm6I477tCjjz5qxF3Y5+PHj6u6ulq//vWv9fHHH9c55v3333/NxTRJOnDggCIjI43nTk5O+u1vf6uUlJTL7vP111/L2dlZzz77rNX23//+9/r000/19ddfKzEx8Yrnbdmypf7xj3/o8OHD8vHxueZ8AQAA6gMFNQAA4DC6det2yUUJfvjhB0nS4MGDL7mfu7u78fexY8f0zjvvaOPGjSorK7OKO3nyZP0le4GLVyb94YcfZLFYrIpeF7p4DrTLuXg8nnjiCT355JOaPn26fvvb38rNzU2S9OWXX+rPf/6zioqKVFFRYcQ7OTldNderad++vWbOnCknJye5ubmpc+fO8vT0vOI+P//8s9q0aWP1ukiSr6+v0X4148eP16RJk/Tb3/5WXbp0UWxsrJ588kl17NjRpvwBAACuBwU1AADg8GrnJZszZ468vb3rtDs7Oxt/v/TSS9q5c6eGDRumoKAgNW/eXDU1NXruueesJsS/nEsVoaTztz5ezsWrZNbU1MjJyUmLFy+2yq3W9a4CajKZFBERoczMTP3444+699579c033+iFF17Q/fffr2nTpsnb21uurq5as2aNNmzYUOcYF17Ndi2aN2+uqKio68r3RvTu3Vvdu3fXZ599pr/97W9KT0/X4sWL9fbbbys2Nvam5wMAAG4vFNQAAIDDq70qydPT84rFnePHjysvL08vvviiRo8ebWyvvcLtQpcrnHl4eEiSTpw4YbW9pKTkmvPt1KmTLBaLOnTocMlbWG9EbWHv9OnTks7Pn9akSROlp6cbV6xJ0po1a+r1vLZo37698vLyVF5ebnWV2oEDB4z2a9GmTRsNHDhQAwcOVFlZmeLi4rRw4UIKagAAwO5MDZ0AAADAjYqJiZG7u7sWLVqkysrKOu2185Rd6mowSVq2bFmdbbUT6l98G6i7u7tatWqlb775xmr7ypUrrznfRx99VM7OznrnnXfqXBVnsVj0r3/965qPdaHKykr97W9/k6urq3H7pLOzs5ycnKyuoDt06JC++OKL6zpHfXjwwQdVXV2trKwsq+1Lly6Vk5OTHnzwQWNb8+bN6xQvq6ur67wunp6eatOmjdUtrQAAAPbCFWoAAMDhubu7KykpSRMmTFB8fLx69+6t1q1bq6SkRF999ZXCw8M1depUubu76/7779eSJUtUWVkpHx8f/e1vf9OhQ4fqHLNLly6SpP/+7/9W79695erqqoceekjNmzfX008/rb/85S967bXXFBwcrG+++Ubff//9NefbqVMnvfTSS5o7d65+/vlnPfLII7rjjjt06NAhff755+rXr5+GDRt21eN8/fXXxlVdR48e1UcffaQffvhBw4cPN678io2NVUZGhp577jk98cQTKisr08qVK9WpUyft2bPnmnOuTz169FBERIT++7//Wz///LMCAgL0t7/9TV988YUGDx6sTp06GbFdunRRXl6eMjIy1KZNG+OqvtjYWD322GMKDAxU8+bNlZubq2+//dZq1U8AAAB7oaAGAABuCX379lWbNm30l7/8Renp6aqoqJCPj4+6d++u+Ph4I27u3LmaMWOGVq5cKYvFogceeECLFy9WTEyM1fG6deumsWPHatWqVcrJyVFNTY2++OILNW/eXKNGjdLRo0f16aefatOmTXrwwQe1ZMkSq9Uur2b48OHq3Lmzli5dqgULFkiS2rZtqwceeEA9evS4pmPMnz/f+LtJkyb61a9+paSkJKtVRSMjI/WnP/1JixcvVkpKijp06KDx48fr559/brCCmslk0p///GfNnz9fGzdu1Nq1a9W+fXtNmDBBv//9761iJ02apKlTp2revHk6e/as4uLiNH36dP3Xf/2X/va3v+mvf/2rLBaLOnXqpGnTpumZZ55pkD4BAIDbi5PlWmbfBQAAAAAAACCJOdQAAAAAAAAAm1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1ICb4KefftLUqVP18MMPq2vXrgoPD9eAAQO0bNkynT171oirrKxUZmamEhISFBYWprCwMCUkJCgzM1OVlZVWx+zdu7f+8z//s865PvvsMwUEBCgxMbFO2wcffKCAgABt2bKl/jsJAGgwa9euVUBAgAICAvTNN9/UabdYLIqNjVVAQIBGjBhRp/3EiRPq2rWrAgICtH///kueY9KkScY5AgICFBwcrMcee0xvvfWWzp07V+99AgA0Tnv27NGYMWP00EMPqWvXroqJidHQoUO1fPlyI6ZHjx5WnxkXPoYNGybp/GfTM888o9/85jf617/+Vec8U6dOVZcuXVRUVHTT+gbYwqWhEwBudZs3b9bYsWPl5uam3/3ud/L391dlZaW2b9+uN954Q8XFxZoxY4ZOnz6tESNGaNu2bXrooYcUHx8vJycn5eTk6E9/+pM+++wzLVq0SM2bN5ck/frXv9YHH3ygkydPqkWLFsb5duzYIRcXF3377beqrKyUq6urVZuzs7NCQ0Nv9jAAAG6CJk2aaMOGDerevbvV9m3btumXX36Rm5vbJff75JNP5OTkJG9vb61fv14vv/zyJePc3Nw0c+ZMSVJ5ebm++OIL/c///I9++uknzZ07t347AwBodHbs2KFBgwapXbt2evrpp+Xt7a1//vOf+sc//qHMzEw9++yzRmxQUJCGDh1a5xht2rSRJDk5OWn69Ol68sknNWfOHKWmphoxO3fu1OrVqzV06FAFBQXZv2PAdaCgBtjRwYMH9fLLL6tdu3ZatmyZ8eEhSQMHDtSPP/6ozZs3S5JmzZqlbdu26fXXX7e6uuyZZ55RVlaWpk+frtmzZys5OVnS+YLa6tWrtWPHDsXGxhrxO3bs0OOPP64NGzZo9+7dVsWz7du3KyAgQO7u7vbtOACgQcTGxuqTTz7RlClT5OLy73/mbdiwQV26dNGxY8cuud/69esVGxurdu3aacOGDZctqLm4uOh3v/ud8fyZZ57RgAED9PHHH+uPf/yjvLy86rU/AIDGZeHChWrRooU++OADtWzZ0qqtrKzM6rmPj4/VZ8al+Pn5adiwYVq4cKHi4uL0H//xH6qsrNTUqVN111136cUXX6z3PgD1hVs+ATtasmSJTp8+rT/96U9WxbRad999twYPHqxffvlFH3zwgX7zm99c8lbNgQMHKiIiQh988IF++eUXSecLatL5Alqtc+fOaffu3Xr00UfVsWNHq7ajR4/qhx9+MPYDANx6+vTpo2PHjulvf/ubsa2iokKffvqp+vbte8l9SkpK9M0336h3797q06ePDh06ZPX5cSVOTk4KDw+XxWLRwYMH66UPAIDG66effpKfn1+dYpokeXp6XtcxR44cqU6dOmnq1KmqqKhQRkaG9u7dq9dff924OwdojCioAXb05ZdfqmPHjgoPD79i3Ndff63q6mo9+eSTl4158sknVVVVpZycHElSx44d1aZNG6svPbW3edbOv3ZhW+3fV8sFAOC42rdvr9DQUH388cfGtq+//lonT55U7969L7nPhg0b1KxZMz300EPq1q2bOnXqpI8++uiaz/nzzz9L0iW/XAEAbi3t27fX7t27tXfv3qvGVlVV6ejRo3UeF84hLZ2frmDatGn6/vvvlZycrAULFqhnz57q0aOHvboB1AsKaoCdlJeX6/Dhw/L3979qbHFxsSQpMDDwsjG1bRdOFh0eHq5du3YZCxbs2LFDHTp0UJs2beoU1LZv3y5JXKEGALe4vn376vPPPze+sHz00Ue6//775ePjc8n4jz76SA8//LCaNm0q6fyiN5s2bVJVVdUl42u/EP30009699139de//lX+/v761a9+ZZ8OAQAajd///vc6e/asnnzySQ0YMEBvvPGGtmzZUmcBNUnasmWLIiMj6zwyMzPrxEZHR+uJJ57QBx98IGdnZ02ZMuVmdAe4IcyhBthJeXm5JOmOO+64auypU6euGlvbVntc6Xxx7JNPPjHmStuxY4fCwsIknS+2lZWV6YcfflDnzp21c+dOdejQ4bJfqAAAt4ZevXopJSVFX375pWJiYrR58+bLfjH57rvvtHfvXo0bN87Y1qdPHy1cuFBbtmzRb3/7W6v406dPKzIy0mrbr3/9a82ePVtOTk713hcAQOPywAMPaNWqVfrLX/6iLVu2aOfOnVqyZIlat26tmTNn6uGHHzZiQ0JC9NJLL9U5xt13333JY7dq1UrS+XnV2rZta5f8gfpEQQ2wk9qJ/2uLZVdSWyy7Uuylim4XzqMWEhKinTt3auzYsZIkf39/ubu7a8eOHbrrrrtUWFh42dt9AAC3jtatWysyMlIbNmzQ2bNnVV1drccee+ySsevXr1fz5s3VsWNH/fjjj5LO33rTvn17ffTRR3UKak2aNNHChQslSb/88ouWLFmisrIyNWnSxK59AgA0Ht26ddM777yjiooKfffdd/r888+1dOlSjR07VtnZ2fLz85N0vkAWFRV1Tcf89ttvlZWVJX9/f/3jH//Qhx9+eNUFDYCGRkENsBN3d3e1adNG+/btu2qsr6+vJGnPnj2XXRZ6z549kmR8QEnnbwO94447tH37dsXGxurYsWPGHGkmk0khISHavn27OnXqpMrKSm73BIDbxBNPPKHXX39dZrNZDz744CXnN7NYLPr44491+vTpS/7gcvToUZ06dcrqhxxnZ2erL0fR0dHq1auXpk6dahTaAAC3Bzc3N3Xr1k3dunVT586d9cc//lGffPKJRo8ebdNxqqurNXXqVLVp00bvvfeefv/732v27Nl66KGHmJ8TjRpzqAF29NBDD+mnn37Szp07rxj34IMPytnZWR9++OFlY7Kzs+Xi4qKYmBhjm7Ozs3Gr5/bt2+Xu7m41Z1vtPGq1c6lRUAOA20PPnj1lMplUUFCgJ5544pIx27Zt0y+//KIxY8borbfesnrMmDFDZ86c0eeff37F87Rp00ZDhgzRl19+qYKCAjv0BADgCIKDgyVJR44csXnf5cuX6//+7//0+uuvy93dXcnJyTp27JjS0tLqO02gXlFQA+zoueeeU/PmzTVlyhSZzeY67T/99JOWLVumu+66S/Hx8crNzdXKlSvrxL333nvKz89XQkJCnfkEwsPDdfToUa1du1YhISEymf79f+uwsDB9//33+uKLL3TnnXcaV8IBAG5td9xxh5KSkvTiiy9edpW02ts9n3vuOT3++ONWj379+qlz587XtNpnYmKimjVrpr/85S/13Q0AQCOTn58vi8VSZ/tXX30lSTYvUPPPf/5Tb731lnr06KFHHnlEkhQUFKRnn31W//u//6t//OMfN540YCfc8gnYUadOnZSWlqaXX35ZvXv31u9+9zv5+/uroqJCO3fu1CeffKL4+HhJ0h//+EcdOHBAycnJysnJMa5E27Jli7744gv9x3/8hyZNmlTnHLVXne3cuVMvvviiVVtoaKicnJxUUFCghx56iAmjAeA2EhcXd9m2iooK/fWvf1VUVNRl5z/r0aOHMjMzVVZWJk9Pz8seq1WrVoqPj9fKlSu1f/9+frwBgFvYzJkzdebMGfXs2VO/+tWvVFlZqR07dmjTpk1q37698d1Gkg4fPnzJO3DuuOMOo3g2Y8YMSdLrr79uFfPiiy9q06ZNmjZtmtasWSNnZ2c79gq4PhTUADt7+OGHtX79eqWnp+uLL77Qe++9Jzc3NwUEBGjSpEnq16+fpPMfLEuXLtXKlSu1fv16vfHGG7JYLPrVr36lyZMn65lnnpGrq2ud44eGhsrFxUVVVVXGCp+13N3dde+992rPnj3c7gkAMGzevFknTpzQQw89dNmYhx56SO+++64+/vhjDRo06IrHGzp0qFatWqXFixdr1qxZ9Z0uAKCRmDBhgj755BN99dVXev/991VZWal27drpmWee0QsvvGA151lRUZEmTJhQ5xjt27fXI488os8//1xffPGFJk6cqHbt2lnFuLu767XXXtOYMWO0fPlyDRkyxN5dA2zmZLnU9ZoAAAAAAAAALok51AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAwG1j5cqV6tu3r8LDwxUeHq7+/fvrq6++MtrPnTun5ORkRUREKCwsTC+++KLMZrPVMUpKSjR8+HCFhIQoMjJSs2fPVlVVlVXM1q1bFRcXp+DgYPXs2VNr166tk0tWVpZ69Oihrl276umnn9auXbvs02kAQL1zslgsloZOoqEdPnxY9TUMTk5O8vHxqddj2ouj5OooeUrkai+Okquj5CnZL9fa48JaQ78nHOm9eTMwHnUxJtYYj7oay5jUx+fM//t//0/Ozs66++67ZbFYlJ2drfT0dK1bt0733nuvpk2bpq+++kqpqalq0aKFZsyYIScnJ61atUqSVF1drSeffFJeXl6aMGGCjhw5ookTJ6pfv3565ZVXJEkHDx5U3759NWDAAD399NPKy8tTSkqKFi1apJiYGEnSxo0bNWHCBCUnJyskJETLli3TJ598ok8++USenp429amhX5dbTWN5vwNXw3u1/tnyOeNi51wcgsViqfc3nz2OaS+Okquj5CmRq704Sq6OkqfkWLk6ssYyzo0lj8aC8aiLMbHGeNR1K4xJjx49rJ6//PLLeu+991RQUKC2bdtqzZo1SktLU2RkpCQpJSVFvXv3VkFBgUJDQ7VlyxYVFxcrIyNDXl5eCgoK0tixY5WWlqbRo0fLzc1Nq1atUocOHTRp0iRJkq+vr7Zv366lS5caBbWMjAz169dPCQkJkqTk5GRt3rxZa9as0fDhw23q063wujRGjCscBe/VhkFBDQAAAMBtqbq6Wp988olOnz6tsLAwFRYWqrKyUlFRUUaMr6+v2rVrZxTUCgoK5O/vLy8vLyMmOjpaSUlJKi4u1n333aeCggKjIHdhTEpKiiSpoqJCu3fv1ogRI4x2k8mkqKgo7dy50+Z+ODk52bwPLq92PBlXNHa8V+ufLWNJQQ0AAADAbWXPnj0aMGCAzp07p+bNm2vBggXy8/NTUVGRXF1d1bJlS6t4T09PlZaWSpLMZrNVMU2S8fxqMeXl5Tp79qyOHz+u6urqOrd2enp66sCBAzb3h+kW7INxhaPgvdowKKgBAAAAuK3cc889ys7O1smTJ/Xpp59q4sSJWrFiRUOndd2YP6l+MS8VHAXv1frHHGoAAAAAcBlubm66++67JUnBwcH69ttvlZmZqV69eqmyslInTpywukqtrKxM3t7eks5faXbxapy1q4BeGHPxyqBms1nu7u5q2rSpTCaTnJ2dVVZWZhVTVlZW58q2a8H8SfbBuMJR8F5tGKaGTgAAAAAAGlJNTY0qKioUHBwsV1dX5eXlGW0HDhxQSUmJQkNDJUmhoaHau3evVTEsNzdX7u7u8vPzM2Ly8/OtzpGbm2scw83NTV26dLE6T01NjfLy8hQWFmanXgIA6hNXqAEAAAC4bcydO1cPPvig7rrrLp06dUobNmzQtm3blJ6erhYtWighIUGzZs2Sh4eH3N3dNXPmTIWFhRnFsOjoaPn5+WnChAl69dVXVVpaqnnz5mngwIFyc3OTJA0YMEBZWVmaM2eOEhISlJ+fr02bNmnRokVGHkOHDtXEiRMVHBysbt26admyZTpz5ozi4+MbYlgAADaioAYAAADgtlFWVqaJEyfqyJEjatGihQICApSenq4HHnhAkjR58mSZTCaNGTNGFRUVio6O1rRp04z9nZ2dtXDhQiUlJal///5q1qyZ4uLiNGbMGCOmY8eOWrRokVJTU5WZmam2bdtq5syZiomJMWJ69+6to0ePav78+SotLVVQUJCWLFlyXbd8AgBuPgpqAAAAAG4bKSkpV2xv0qSJpk2bZlVEu1j79u21ePHiKx4nIiJC2dnZV4xJTExUYmLiFWMAAI0Tc6gBAAAAAAAANqCgBgAAAAAAANjghgpqf/nLXxQQEKA//elPxrZz584pOTlZERERCgsL04svvlhnyeiSkhINHz5cISEhioyM1OzZs1VVVWUVs3XrVsXFxSk4OFg9e/bU2rVr65w/KytLPXr0UNeuXfX000/XWb4aAAAAAAAAqG/XXVDbtWuXVq1apYCAAKvtKSkp+vLLLzVv3jwtX75cR44c0ejRo4326upqjRgxQpWVlVq1apVmzZqldevWaf78+UbMwYMHNWLECEVEROjDDz/U4MGDNWXKFOXk5BgxGzduVGpqqkaNGqV169YpMDBQw4YNs1q+GgAAAAAAAKhv17UowalTp/Tqq69q5syZ+vOf/2xsP3nypNasWaO0tDRFRkZKOl9g6927twoKChQaGqotW7aouLhYGRkZ8vLyUlBQkMaOHau0tDSNHj1abm5uWrVqlTp06KBJkyZJknx9fbV9+3YtXbrUWBknIyND/fr1U0JCgiQpOTlZmzdv1po1azR8+HCb+uPk5HQ9w3DFY9XnMe3FUXJ1lDwlcrUXR8nVUfKU7JerI/QdAAAAAG7UdRXUpk+frtjYWEVFRVkV1AoLC1VZWamoqChjm6+vr9q1a2cU1AoKCuTv72+1HHR0dLSSkpJUXFys++67TwUFBUZB7sKY2hV5KioqtHv3bo0YMcJoN5lMioqK0s6dO23uj4+Pj837NMQx7cVRcnWUPCVytRdHydVR8pQcK9fbmclkksl0/bM01BY6XVxcZLFYrvs4NTU1qqmpue79AQC3txv9PLtZ6utz82bgsxloODYX1D7++GP93//9nz744IM6bWazWa6urmrZsqXVdk9PT5WWlhoxFxbTJBnPrxZTXl6us2fP6vjx46qurpanp2ed8xw4cMDWLunw4cNX/A+lyWRS69at5eJyXfXHK6qqqtLRo0cb5D+CTk5O8vHxuWr/G5qj5CmRq704Sq6Okqdkv1xrj4v6YzKZ5OnpWS+fQRd/ttqqqqpKZWVl/MMdAGCz+vw8u1lu9HPzZuCzGWg4Nv3X7J///Kf+9Kc/6d1331WTJk3sldNNZ7FYrviF0snJSS4uLho4cKCKiorq7bxBQUHKysqSk5NTg375vlr/GwtHyVMiV3txlFwdJU/JsXK9XZlMJrt8Btmq9jPLZDLxj3YAgM0ay+fZrYTPZqBh2VRQ2717t8rKyhQfH29sq66u1t///ndlZWUpPT1dlZWVOnHihNVVamVlZfL29pZ0vsp/8WqctauAXhhz8cqgZrNZ7u7uatq0qUwmk5ydnessQFBWVmbXXxGKioqu65ZSAABuFJ9BAIBbAZ9nAG4VNt3A/pvf/EYfffSRsrOzjUdwcLD69u1r/O3q6qq8vDxjnwMHDqikpEShoaGSpNDQUO3du9eqGJabmyt3d3f5+fkZMfn5+Vbnzs3NNY7h5uamLl26WJ2npqZGeXl5CgsLs2kAAACNx8qVK9W3b1+Fh4crPDxc/fv311dffWW0nzt3TsnJyYqIiFBYWJhefPHFOj/AlJSUaPjw4QoJCVFkZKRmz56tqqoqq5itW7cqLi5OwcHB6tmzp9auXVsnl6ysLPXo0UNdu3bV008/XefHIAAAAAC3L5sKau7u7vL397d6NG/eXHfeeaf8/f3VokULJSQkaNasWcrPz1dhYaEmT56ssLAwoxgWHR0tPz8/TZgwQd99951ycnI0b948DRw4UG5ubpKkAQMG6ODBg5ozZ47279+vrKwsbdq0SUOGDDFyGTp0qFavXq1169Zp//79SkpK0pkzZ6yungMAOJa2bdtq/PjxWrt2rdasWaPf/OY3GjVqlPbt2yfp/MrRX375pebNm6fly5fryJEjGj16tLF/dXW1RowYocrKSq1atUqzZs3SunXrNH/+fCPm4MGDGjFihCIiIvThhx9q8ODBmjJlinJycoyYjRs3KjU1VaNGjdK6desUGBioYcOG1bkyGgAAAMDtqd5nhJw8ebJMJpPGjBmjiooKRUdHa9q0aUa7s7OzFi5cqKSkJPXv31/NmjVTXFycxowZY8R07NhRixYtUmpqqjIzM9W2bVvNnDlTMTExRkzv3r119OhRzZ8/X6WlpQoKCtKSJUscYuJIAMCl9ejRw+r5yy+/rPfee08FBQVq27at1qxZo7S0NGMl6JSUFPXu3dtYSXrLli0qLi5WRkaGvLy8FBQUpLFjxyotLU2jR4+Wm5ubVq1apQ4dOmjSpEmSzq9GvX37di1dutT4nMnIyFC/fv2UkJAgSUpOTtbmzZu1Zs0aDR8+/CaOCAAAAIDG6IYLasuXL7d63qRJE02bNs2qiHax9u3ba/HixVc8bkREhLKzs68Yk5iYqMTExGvOFQDgOKqrq/XJJ5/o9OnTCgsLU2FhoSorKxUVFWXE+Pr6ql27dkZBraCgQP7+/lY/rkRHRyspKUnFxcW67777VFBQYBTkLoxJSUmRJFVUVGj37t0aMWKE0W4ymRQVFXXdc744OTld1343uq89ODk5NbqcbFWbv6P3oz4xJtYYj7oay5g09PkBAKjlOGsWAwBuC3v27NGAAQN07tw5NW/eXAsWLJCfn5+Kiork6upqteiNJHl6eqq0tFTS+QVsLr5Sufb51WLKy8t19uxZHT9+XNXV1fL09KxzngMHDlxXn3x8fK5rv8boVroS/FZ6XeoLY2KN8aiLMQEA4DwKagCARuWee+5Rdna2Tp48qU8//VQTJ07UihUrGjqtG3L48GFZLJbr2tfFxaVRFbHMZnOdRR4cjZOTk3x8fG7odbnVMCbWGI+6GsuY1OYBAEBDo6AGAGhU3NzcdPfdd0uSgoOD9e233yozM1O9evVSZWWlTpw4YXWVWllZmby9vSWdv3rq4tU4a1cBvTDm4pVBzWaz3N3d1bRpU5lMJjk7O9dZgKCsrOy6C1sWi+W6v4A2ti/zN9KXxuZW6kt9YUysMR51MSYAAJxn0yqfAADcbDU1NaqoqFBwcLBcXV2Vl5dntB04cEAlJSXGStKhoaHau3evVTEsNzdX7u7u8vPzM2Ly8/OtzpGbm2scw83NTV26dLE6T01NjfLy8hQWFmanXgIAAABwJFyhBgBoNObOnasHH3xQd911l06dOqUNGzZo27ZtSk9PV4sWLZSQkKBZs2bJw8ND7u7umjlzpsLCwoxiWHR0tPz8/DRhwgS9+uqrKi0t1bx58zRw4EC5ublJkgYMGKCsrCzNmTNHCQkJys/P16ZNm7Ro0SIjj6FDh2rixIkKDg5Wt27dtGzZMp05c0bx8fENMSwAAAAAGhkKagCARqOsrEwTJ07UkSNH1KJFCwUEBCg9PV0PPPCAJGny5MkymUwaM2aMKioqFB0dbbWqtLOzsxYuXKikpCT1799fzZo1U1xcnMaMGWPEdOzYUYsWLVJqaqoyMzPVtm1bzZw5UzExMUZM7969dfToUc2fP1+lpaUKCgrSkiVLGtVcZgAAAAAaDgU1AECjkZKScsX2Jk2aaNq0aVZFtIu1b99eixcvvuJxIiIilJ2dfcWYxMREJSYmXjEGAAAAwO2JOdQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsIFLQycAAAAAAADQWJhMJplMjf/6IycnJ0mSi4uLLBZLA2dzZTU1NaqpqWnoNOoVBTUAAAAAAACdL6Z5enrKxcVxyiVeXl4NncJVVVVVqays7JYqqjnOOwQAAAAAAMCOTCaTXFxcNHDgQBUVFTV0OreEoKAgZWVlyWQyUVADAAAAAAC4VRUVFWnnzp0NnQYascZ/UzAAAAAAAADQiFBQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABjYV1FauXKm+ffsqPDxc4eHh6t+/v7766iuj/dlnn1VAQIDVY+rUqVbHKCkp0fDhwxUSEqLIyEjNnj1bVVVVVjFbt25VXFycgoOD1bNnT61du7ZOLllZWerRo4e6du2qp59+Wrt27bKlKwAAAAAAAMB1cbEluG3btho/frzuvvtuWSwWZWdna9SoUVq3bp3uvfdeSVK/fv00ZswYY59mzZoZf1dXV2vEiBHy8vLSqlWrdOTIEU2cOFGurq565ZVXJEkHDx7UiBEjNGDAAKWlpSkvL09TpkyRt7e3YmJiJEkbN25UamqqkpOTFRISomXLlmnYsGH65JNP5OnpecODAgAAAAAAAFyOTVeo9ejRQ7GxsercubPuuecevfzyy2revLkKCgqMmKZNm8rb29t4uLu7G21btmxRcXGx3njjDQUFBSk2NlZjx45VVlaWKioqJEmrVq1Shw4dNGnSJPn6+ioxMVGPPfaYli5dahwnIyND/fr1U0JCgvz8/JScnKymTZtqzZo1NzYaAAAAAAAAwFVc9xxq1dXV+vjjj3X69GmFhYUZ2z/66CNFREToiSee0Ny5c3XmzBmjraCgQP7+/vLy8jK2RUdHq7y8XMXFxUZMZGSk1bmio6ONol1FRYV2796tqKiof3fCZFJUVJR27tx5XX1xcnK66sOeruX89no09PlvtTzJlVwdJU975goAAAAAtzqbbvmUpD179mjAgAE6d+6cmjdvrgULFsjPz0+S9MQTT6hdu3Zq06aN9uzZo7S0NH3//fd65513JElms9mqmCbJeF5aWnrFmPLycp09e1bHjx9XdXV1nVs7PT09deDAAVu7I0ny8fG5rv3qy8X9vdkauv/XylHylMjVXhwlV0fJU3KsXAEAqA+LFi3SX//6Vx04cEBNmzZVWFiYxo8fr1/96ldGzLPPPqtt27ZZ7de/f39Nnz7deF5SUqKkpCRt3bpVzZs315NPPqlx48bJxeXfX7G2bt2qWbNmad++fbrrrrv0wgsvKD4+3uq4WVlZSk9PV2lpqQIDA/X666+rW7duduo9AKC+2FxQu+eee5Sdna2TJ0/q008/1cSJE7VixQr5+fmpf//+RlxAQIC8vb01ZMgQ/fTTT+rUqVO9Jl6fDh8+LIvFctl2FxcXuxa9zGZznYUZbgYnJyf5+Phctf8NzVHylMjVXhwlV0fJU7JfrrXHBQCgsdq2bZsGDhyorl27qrq6Wm+++aaGDRumjz/+WM2bNzfimBsaAHAlNhfU3NzcdPfdd0uSgoOD9e233yozM9Pq15paISEhkqQff/xRnTp1kpeXV53VOM1msyTJ29tb0vmrtWq3XRjj7u6upk2bymQyydnZWWVlZVYxZWVl1130slgsV/xCae8vxlc7v7019PmvlaPkKZGrvThKro6Sp+RYuQIAUB/S09Otns+aNUuRkZHavXu37r//fmN77dzQl1I7N3RGRoa8vLwUFBSksWPHKi0tTaNHj5abm5vV3NCS5Ovrq+3bt2vp0qVGQe3CuaElKTk5WZs3b9aaNWs0fPhwe3QfAFBPrnsOtVo1NTXGggIXKyoqkvTvYlloaKj27t1rVQzLzc2Vu7u7cdtoaGio8vPzrY6Tm5ur0NBQSecLel26dFFeXp5VDnl5eVZzuQEAAADA1Zw8eVKS5OHhYbXdkeaGbuh5WZlntWE19Ot6Kz5gHw39utb362/TFWpz587Vgw8+qLvuukunTp3Shg0btG3bNqWnp+unn37SRx99pNjYWN15553as2ePUlNTdf/99yswMFDS+Q8QPz8/TZgwQa+++qpKS0s1b948DRw4UG5ubpKkAQMGKCsrS3PmzFFCQoLy8/O1adMmLVq0yMhj6NChmjhxooKDg9WtWzctW7ZMZ86cqTMfAQAAAABcTk1NjVJSUhQeHi5/f39ju6PNDc10C7e3hp6TG7hWt9p71aaCWllZmSZOnKgjR46oRYsWCggIUHp6uh544AH985//VF5enjIzM3X69GndddddevTRRzVy5Ehjf2dnZy1cuFBJSUnq37+/mjVrpri4OKu5CTp27KhFixYpNTVVmZmZatu2rWbOnGlcFi1JvXv31tGjRzV//nyVlpYqKChIS5YsueVeHAAAAAD2k5ycrH379mnlypVW2x1tbmhHmL/V3vNS384aak7uWxXvVftxhPeqk9O1zwltU0EtJSXlsm133XWXVqxYcdVjtG/fXosXL75iTEREhLKzs68Yk5iYqMTExKueDwAAAAAuNn36dG3evFkrVqxQ27Ztrxjb2OeGdoQ5URt7fo7MEV5/R8JY2s+t9l694TnUAAAAAMBRWCwWTZ8+XZ999pmWLVumjh07XnUf5oYGAFyMghoAAACA20ZycrLWr1+vuXPn6o477lBpaalKS0t19uxZSdJPP/2kBQsWqLCwUIcOHdIXX3yhiRMnXnZu6O+++045OTmXnBv64MGDmjNnjvbv36+srCxt2rRJQ4YMMXIZOnSoVq9erXXr1mn//v1KSkpibmgAcBA23fIJAAAAAI7svffekyQ9++yzVttTU1MVHx8vV1dX5oYGAFwVBTUAAAAAt409e/ZcsZ25oQEA14JbPgEAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMANBqLFi1SQkKCwsLCFBkZqZEjR+rAgQNWMc8++6wCAgKsHlOnTrWKKSkp0fDhwxUSEqLIyEjNnj1bVVVVVjFbt25VXFycgoOD1bNnT61du7ZOPllZWerRo4e6du2qp59+Wrt27ar/TgMAAABwOBTUAACNxrZt2zRw4ECtXr1aGRkZqqqq0rBhw3T69GmruH79+mnLli3GY8KECUZbdXW1RowYocrKSq1atUqzZs3SunXrNH/+fCPm4MGDGjFihCIiIvThhx9q8ODBmjJlinJycoyYjRs3KjU1VaNGjdK6desUGBioYcOGqayszP4DAQAAAKBRo6AGAGg00tPTFR8fr3vvvVeBgYGaNWuWSkpKtHv3bqu4pk2bytvb23i4u7sbbVu2bFFxcbHeeOMNBQUFKTY2VmPHjlVWVpYqKiokSatWrVKHDh00adIk+fr6KjExUY899piWLl1qHCcjI0P9+vVTQkKC/Pz8lJycrKZNm2rNmjU3ZSwAAAAANF4U1AAAjdbJkyclSR4eHlbbP/roI0VEROiJJ57Q3LlzdebMGaOtoKBA/v7+8vLyMrZFR0ervLxcxcXFRkxkZKTVMaOjo1VQUCBJqqio0O7duxUVFWW0m0wmRUVFaefOnTb3w8nJ6YYejcmN9qWxPG6lvjAmjMftNiYAADQGLg2dAAAAl1JTU6OUlBSFh4fL39/f2P7EE0+oXbt2atOmjfbs2aO0tDR9//33eueddyRJZrPZqpgmyXheWlp6xZjy8nKdPXtWx48fV3V1tTw9Pa1iPD0968zpdi18fHxs3qexunjcHNmt9LrUF8bEGuNRF2MCAMB5FNQAAI1ScnKy9u3bp5UrV1pt79+/v/F3QECAvL29NWTIEP3000/q1KnTzU7zmhw+fFgWi+W69nVxcWlURSyz2VxngQdH4+TkJB8fnxt6XW41jIk1xqOuxjImtXkAANDQKKgBABqd6dOna/PmzVqxYoXatm17xdiQkBBJ0o8//qhOnTrJy8urzmqcZrNZkuTt7S3p/FVWtdsujHF3d1fTpk1lMpnk7OxcZwGCsrKy6ypuWSyW6/4C2ti+zN9IXxqbW6kv9YUxscZ41MWYAABwHnOoAQAaDYvFounTp+uzzz7TsmXL1LFjx6vuU1RUJOnfxbLQ0FDt3bvXqhiWm5srd3d3+fn5GTH5+flWx8nNzVVoaKgkyc3NTV26dFFeXp7RXlNTo7y8PIWFhd1QHwEAAAA4PgpqAIBGIzk5WevXr9fcuXN1xx13qLS0VKWlpTp79qwk6aefftKCBQtUWFioQ4cO6YsvvtDEiRN1//33KzAwUNL5xQX8/Pw0YcIEfffdd8rJydG8efM0cOBAubm5SZIGDBiggwcPas6cOdq/f7+ysrK0adMmDRkyxMhl6NChWr16tdatW6f9+/crKSlJZ86cUXx8/E0fFwAAAACNC7d8AgAajffee0+S9Oyzz1ptT01NVXx8vFxdXZWXl6fMzEydPn1ad911lx599FGNHDnSiHV2dtbChQuVlJSk/v37q1mzZoqLi9OYMWOMmI4dO2rRokVKTU1VZmam2rZtq5kzZyomJsaI6d27t44ePar58+ertLRUQUFBWrJkSaOazwwAAABAw6CgBgBoNPbs2XPF9rvuuksrVqy46nHat2+vxYsXXzEmIiJC2dnZV4xJTExUYmLiVc8HAAAA4PbCLZ8AAAAAAACADSioAQAAAAAAADagoAYAAAAAAADYgIIaAAAAAAAAYAMKagAAAAAAAIANKKgBAAAAAAAANqCgBgAAAAAAANiAghoAAAAAAABgAwpqAAAAAAAAgA0oqAEAAAAAAAA2oKAGAAAAAAAA2MCmgtrKlSvVt29fhYeHKzw8XP3799dXX31ltJ87d07JycmKiIhQWFiYXnzxRZnNZqtjlJSUaPjw4QoJCVFkZKRmz56tqqoqq5itW7cqLi5OwcHB6tmzp9auXVsnl6ysLPXo0UNdu3bV008/rV27dtnSFQAAAAAAAOC62FRQa9u2rcaPH6+1a9dqzZo1+s1vfqNRo0Zp3759kqSUlBR9+eWXmjdvnpYvX64jR45o9OjRxv7V1dUaMWKEKisrtWrVKs2aNUvr1q3T/PnzjZiDBw9qxIgRioiI0IcffqjBgwdrypQpysnJMWI2btyo1NRUjRo1SuvWrVNgYKCGDRumsrKyGx0PAAAAAAAA4IpsKqj16NFDsbGx6ty5s+655x69/PLLat68uQoKCnTy5EmtWbNGkyZNUmRkpIKDg5WSkqKdO3eqoKBAkrRlyxYVFxfrjTfeUFBQkGJjYzV27FhlZWWpoqJCkrRq1Sp16NBBkyZNkq+vrxITE/XYY49p6dKlRh4ZGRnq16+fEhIS5Ofnp+TkZDVt2lRr1qypt4EBAAAAAAAALuW651Crrq7Wxx9/rNOnTyssLEyFhYWqrKxUVFSUEePr66t27doZBbWCggL5+/vLy8vLiImOjlZ5ebmKi4uNmMjISKtzRUdHG8eoqKjQ7t27rc5jMpkUFRWlnTt3XldfnJycrvqwp2s5v70eDX3+Wy1PciVXR8nTnrkCAAAAwK3OxdYd9uzZowEDBujcuXNq3ry5FixYID8/PxUVFcnV1VUtW7a0ivf09FRpaakkyWw2WxXTJBnPrxZTXl6us2fP6vjx46qurpanp2ed8xw4cMDW7kiSfHx8rmu/+nJxf2+2hu7/tXKUPCVytRdHydVR8pQcK1cAAAAAaCxsLqjdc889ys7O1smTJ/Xpp59q4sSJWrFihT1yu2kOHz4si8Vy2XYXFxe7Fr3MZnOdhRluBicnJ/n4+Fy1/w3NUfKUyNVeHCVXR8lTsl+utccFAAAAgFuZzQU1Nzc33X333ZKk4OBgffvtt8rMzFSvXr1UWVmpEydOWF2lVlZWJm9vb0nnr8S6eDXO2lVAL4y5eGVQs9ksd3d3NW3aVCaTSc7OznUWICgrK7vuopfFYrniF0p7fzG+2vntraHPf60cJU+JXO3FUXJ1lDwlx8oVAAAAABqL655DrVZNTY0qKioUHBwsV1dX5eXlGW0HDhxQSUmJQkNDJUmhoaHau3evVTEsNzdX7u7u8vPzM2Ly8/OtzpGbm2scw83NTV26dLE6T01NjfLy8hQWFnaj3QEAAAAAAACuyKYr1ObOnasHH3xQd911l06dOqUNGzZo27ZtSk9PV4sWLZSQkKBZs2bJw8ND7u7umjlzpsLCwoxiWHR0tPz8/DRhwgS9+uqrKi0t1bx58zRw4EC5ublJkgYMGKCsrCzNmTNHCQkJys/P16ZNm7Ro0SIjj6FDh2rixIkKDg5Wt27dtGzZMp05c0bx8fH1NzIAAAAAAADAJdhUUCsrK9PEiRN15MgRtWjRQgEBAUpPT9cDDzwgSZo8ebJMJpPGjBmjiooKRUdHa9q0acb+zs7OWrhwoZKSktS/f381a9ZMcXFxGjNmjBHTsWNHLVq0SKmpqcrMzFTbtm01c+ZMxcTEGDG9e/fW0aNHNX/+fJWWliooKEhLlixp8Mn9AQAAAAAAcOuzqaCWkpJyxfYmTZpo2rRpVkW0i7Vv316LFy++4nEiIiKUnZ19xZjExEQlJiZeMQYAAAAAAACobzc8hxoAAAAAAABwO6GgBgAAAAAAANiAghoAAAAAAABgAwpqAAAAAAAAgA0oqAEAAAAAAAA2oKAGAAAAAAAA2ICCGgAAAAAAAGADCmoAAAAAAACADSioAQAAAAAAADagoAYAAADgtrFo0SIlJCQoLCxMkZGRGjlypA4cOGAVc+7cOSUnJysiIkJhYWF68cUXZTabrWJKSko0fPhwhYSEKDIyUrNnz1ZVVZVVzNatWxUXF6fg4GD17NlTa9eurZNPVlaWevTooa5du+rpp5/Wrl276r/TAIB6R0ENAAAAwG1j27ZtGjhwoFavXq2MjAxVVVVp2LBhOn36tBGTkpKiL7/8UvPmzdPy5ct15MgRjR492mivrq7WiBEjVFlZqVWrVmnWrFlat26d5s+fb8QcPHhQI0aMUEREhD788EMNHjxYU6ZMUU5OjhGzceNGpaamatSoUVq3bp0CAwM1bNgwlZWV3ZzBAABcNwpqAAAAAG4b6enpio+P17333qvAwEDNmjVLJSUl2r17tyTp5MmTWrNmjSZNmqTIyEgFBwcrJSVFO3fuVEFBgSRpy5YtKi4u1htvvKGgoCDFxsZq7NixysrKUkVFhSRp1apV6tChgyZNmiRfX18lJibqscce09KlS41cMjIy1K9fPyUkJMjPz0/Jyclq2rSp1qxZc7OHBQBgIwpqAAAAAG5bJ0+elCR5eHhIkgoLC1VZWamoqCgjxtfXV+3atTMKagUFBfL395eXl5cREx0drfLychUXFxsxkZGRVueKjo42jlFRUaHdu3dbncdkMikqKko7d+60qQ9OTk4O8YB9NPTreis+YB8N/brW9+vvYsexAgAAAIBGq6amRikpKQoPD5e/v78kyWw2y9XVVS1btrSK9fT0VGlpqRFzYTFNkvH8ajHl5eU6e/asjh8/rurqanl6etY5z8Vzul2Nj4+PTfG4tVz8PgMaq1vtvUpBDQAAAMBtKTk5Wfv27dPKlSsbOpUbcvjwYVksloZO44pcXFxuuS/TjYXZbK6zIAauH+9V+3GE96qTk9M1/0hBQQ0AAADAbWf69OnavHmzVqxYobZt2xrbvby8VFlZqRMnTlhdpVZWViZvb28j5uLVOGtXAb0w5uKVQc1ms9zd3dW0aVOZTCY5OzvXWYCgrKzM5i/zFoul0RfUGnt+jswRXn9Hwljaz632XmUONQAAAAC3DYvFounTp+uzzz7TsmXL1LFjR6v24OBgubq6Ki8vz9h24MABlZSUKDQ0VJIUGhqqvXv3WhXDcnNz5e7uLj8/PyMmPz/f6ti5ubnGMdzc3NSlSxer89TU1CgvL09hYWH12WUAgB1QUAMAAABw20hOTtb69es1d+5c3XHHHSotLVVpaanOnj0rSWrRooUSEhI0a9Ys5efnq7CwUJMnT1ZYWJhRDIuOjpafn58mTJig7777Tjk5OZo3b54GDhwoNzc3SdKAAQN08OBBzZkzR/v371dWVpY2bdqkIUOGGLkMHTpUq1ev1rp167R//34lJSXpzJkzio+Pv9nDAgCwEbd8AgAAALhtvPfee5KkZ5991mp7amqqUciaPHmyTCaTxowZo4qKCkVHR2vatGlGrLOzsxYuXKikpCT1799fzZo1U1xcnMaMGWPEdOzYUYsWLVJqaqoyMzPVtm1bzZw5UzExMUZM7969dfToUc2fP1+lpaUKCgrSkiVLmL8JABwABTUAAAAAt409e/ZcNaZJkyaaNm2aVRHtYu3bt9fixYuveJyIiAhlZ2dfMSYxMVGJiYlXzQkA0LhwyycAAAAAAABgAwpqAAAAAAAAgA0oqAEAGo1FixYpISFBYWFhioyM1MiRI3XgwAGrmHPnzik5OVkREREKCwvTiy++KLPZbBVTUlKi4cOHKyQkRJGRkZo9e7aqqqqsYrZu3aq4uDgFBwerZ8+eWrt2bZ18srKy1KNHD3Xt2lVPP/20du3aVf+dBgAAAOBwKKgBABqNbdu2aeDAgVq9erUyMjJUVVWlYcOG6fTp00ZMSkqKvvzyS82bN0/Lly/XkSNHNHr0aKO9urpaI0aMUGVlpVatWqVZs2Zp3bp1mj9/vhFz8OBBjRgxQhEREfrwww81ePBgTZkyRTk5OUbMxo0blZqaqlGjRmndunUKDAzUsGHDVFZWdnMGAwAAAECjxaIEAIBGIz093er5rFmzFBkZqd27d+v+++/XyZMntWbNGqWlpSkyMlLS+QJb7969VVBQoNDQUG3ZskXFxcXKyMiQl5eXgoKCNHbsWKWlpWn06NFyc3PTqlWr1KFDB02aNEmS5Ovrq+3bt2vp0qXG6msZGRnq16+fEhISJEnJycnavHmz1qxZo+HDh9vULycnp+sekxvZ1x6cnJwaXU62qs3f0ftRnxgTa4xHXY1lTBr6/AAA1KKgBgBotE6ePClJ8vDwkCQVFhaqsrJSUVFRRoyvr6/atWtnFNQKCgrk7+8vLy8vIyY6OlpJSUkqLi7Wfffdp4KCAqMgd2FMSkqKJKmiokK7d+/WiBEjjHaTyaSoqCjt3LnT5n74+PjYvE9jdeG4Orpb6XWpL4yJNcajLsYEAIDzKKgBABqlmpoapaSkKDw8XP7+/pIks9ksV1dXtWzZ0irW09NTpaWlRszFRZ/a51eLKS8v19mzZ3X8+HFVV1fL09OzznkuntPtWhw+fFgWi8Xm/STJxcWlURWxzGZznfnoHI2Tk5N8fHxu6HW51TAm1hiPuhrLmNTmAQBAQ6OgBgBolJKTk7Vv3z6tXLmyoVO5YRaL5bq/gDa2L/M30pfG5lbqS31hTKwxHnUxJgAAnEdBDQDQ6EyfPl2bN2/WihUr1LZtW2O7l5eXKisrdeLECaur1MrKyuTt7W3EXLwaZ+0qoBfGXLwyqNlslru7u5o2bSqTySRnZ+c6CxCUlZU1qqvFblcmk0km0/Wvq1Q7B5OLi8sNFwZqampUU1NzQ8cAAACA46GgBgBoNCwWi2bMmKHPPvtMy5cvV8eOHa3ag4OD5erqqry8PD322GOSpAMHDqikpEShoaGSpNDQUC1cuFBlZWXGLZu5ublyd3eXn5+fEfP1119bHTs3N9c4hpubm7p06aK8vDw98sgjks4XTvLy8pSYmGiv7uMamEwmeXp6ysXlxv8JUx/F0aqqKpWVlVFUAwAAuM1QUAMANBrJycnasGGD/ud//kd33HGHMedZixYt1LRpU7Vo0UIJCQmaNWuWPDw85O7urpkzZyosLMwohkVHR8vPz08TJkzQq6++qtLSUs2bN08DBw6Um5ubJGnAgAHKysrSnDlzlJCQoPz8fG3atEmLFi0ychk6dKgmTpyo4OBgdevWTcuWLdOZM2cUHx9/08cF/2YymeTi4qKBAweqqKioQXMJCgpSVlaWTCYTBTUAAIDbjE0FtUWLFumvf/2rDhw4oKZNmyosLEzjx4/Xr371KyPm2Wef1bZt26z269+/v6ZPn248LykpUVJSkrZu3armzZvrySef1Lhx46x+bd66datmzZqlffv26a677tILL7xQ50tMVlaW0tPTVVpaqsDAQL3++uvq1q2bTQMAAGg83nvvPUnnP0sulJqaanwGTJ48WSaTSWPGjFFFRYWio6M1bdo0I9bZ2VkLFy5UUlKS+vfvr2bNmikuLk5jxowxYjp27KhFixYpNTVVmZmZatu2rWbOnKmYmBgjpnfv3jp69Kjmz5+v0tJSBQUFacmSJdzy2UgUFRVd14qrAAAAQH2wqaC2bds2DRw4UF27dlV1dbXefPNNDRs2TB9//LGaN29uxPXr18/qi0uzZs2Mv6urqzVixAh5eXlp1apVOnLkiCZOnChXV1e98sorkqSDBw9qxIgRGjBggNLS0pSXl6cpU6bI29vb+LKzceNGpaamKjk5WSEhIVq2bJmGDRumTz75pM6qbAAAx7Bnz56rxjRp0kTTpk2zKqJdrH379lq8ePEVjxMREaHs7OwrxiQmJnKLJwAAAIA6bJrRNz09XfHx8br33nsVGBioWbNmqaSkRLt377aKa9q0qby9vY2Hu7u70bZlyxYVFxfrjTfeUFBQkGJjYzV27FhlZWWpoqJCkrRq1Sp16NBBkyZNkq+vrxITE/XYY49p6dKlxnEyMjLUr18/JSQkyM/PT8nJyWratKnWrFlzA8MBAAAAAAAAXNn1L5El6eTJk5IkDw8Pq+0fffSRIiIi9MQTT2ju3Lk6c+aM0VZQUCB/f3+rW2aio6NVXl6u4uJiIyYyMtLqmNHR0SooKJAkVVRUaPfu3YqKivp3R0wmRUVFXdftH05OTld92NO1nN9ej4Y+/62WJ7mSq6Pkac9cAQAAAOBWd92LEtTU1CglJUXh4eHy9/c3tj/xxBNq166d2rRpoz179igtLU3ff/+93nnnHUmS2WyuM/9M7fPayacvF1NeXq6zZ8/q+PHjqq6urnNrp6enpw4cOGBzX3x8fGzepz419Hw8Dd3/a+UoeUrkai+Okquj5Ck5Vq4AAAAA0Fhcd0EtOTlZ+/bt08qVK6229+/f3/g7ICBA3t7eGjJkiH766Sd16tTp+jO1o8OHD8tisVy23cXFxa5FL7PZrKqqKrsd/3KcnJzk4+Nz1f43NEfJUyJXe3GUXB0lT8l+udYeFwAAAABuZddVUJs+fbo2b96sFStWqG3btleMDQkJkST9+OOP6tSpk7y8vLRr1y6rGLPZLEny9vaWdP6KrdptF8a4u7uradOmMplMcnZ2VllZmVVMWVnZdRW+LBbLFb9Q2vuL8dXOb28Nff5r5Sh5SuRqL46Sq6PkKTlWrgAAAADQWNg0h5rFYtH06dP12WefadmyZerYseNV9ykqKpL072JZaGio9u7da1UMy83Nlbu7u/z8/IyY/Px8q+Pk5uYqNDRUkuTm5qYuXbooLy/PaK+pqVFeXp7CwsJs6RIAAAAAAABgE5sKasnJyVq/fr3mzp2rO+64Q6WlpSotLdXZs2clST/99JMWLFigwsJCHTp0SF988YUmTpyo+++/X4GBgZLOLy7g5+enCRMm6LvvvlNOTo7mzZungQMHys3NTZI0YMAAHTx4UHPmzNH+/fuVlZWlTZs2aciQIUYuQ4cO1erVq7Vu3Trt379fSUlJOnPmjOLj4+tpaAAAAAAAAIC6bLrl87333pMkPfvss1bbU1NTFR8fL1dXV+Xl5SkzM1OnT5/WXXfdpUcffVQjR440Yp2dnbVw4UIlJSWpf//+atasmeLi4jRmzBgjpmPHjlq0aJFSU1OVmZmptm3baubMmYqJiTFievfuraNHj2r+/PkqLS1VUFCQlixZ0uAT/AMAAAAAAODWZlNBbc+ePVdsv+uuu7RixYqrHqd9+/ZavHjxFWMiIiKUnZ19xZjExEQlJiZe9XwAAAAAAABAfbHplk8AAAAAAADgdkdBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAcNv4+9//rj/84Q+Kjo5WQECAPv/8c6v2SZMmKSAgwOoxbNgwq5hjx45p3LhxCg8PV/fu3TV58mSdOnXKKua7777TM888o65duyo2NlaLFy+uk8umTZv0+OOPq2vXrurbt6+++uqr+u8wAMAuKKgBAAAAuG2cPn1aAQEBmjZt2mVjYmJitGXLFuPx5ptvWrWPHz9excXFysjI0MKFC/XNN99o6tSpRnt5ebmGDRumdu3aae3atZowYYLeeecdvf/++0bMjh07NG7cOD311FPKzs7Www8/rFGjRmnv3r3132kAQL1zaegEAAAAAOBmiY2NVWxs7BVj3Nzc5O3tfcm2/fv3KycnRx988IG6du0qSZoyZYqGDx+uCRMmyMfHR+vXr1dlZaVSUlLk5uame++9V0VFRcrIyFD//v0lSZmZmYqJidFzzz0nSXrppZeUm5urFStWaPr06fXYYwCAPXCFGgAAAABcYNu2bYqMjNRjjz2madOm6V//+pfRtnPnTrVs2dIopklSVFSUTCaTdu3aJUkqKChQ9+7d5ebmZsRER0fr+++/1/Hjx42YyMhIq/NGR0eroKDA5nydnJwc4gH7aOjX9VZ8wD4a+nWt79efK9QAAAAA4P8XExOjnj17qkOHDjp48KDefPNNPf/883r//ffl7Owss9ms1q1bW+3j4uIiDw8PlZaWSpLMZrM6dOhgFePl5WW0eXh4yGw2G9tqeXp6ymw225yzj4+Pzfvg1nHx+whorG619yoFNQAAAAD4//Xp08f4u3ZRgkceecS4aq0xOnz4sCwWS0OncUUuLi633JfpxsJsNquqqqqh07hl8F61H0d4rzo5OV3zjxQU1AAAAADgMjp27KhWrVrpxx9/VGRkpLy8vHT06FGrmKqqKh0/ftyYd83Ly6vOlWa1z2u/qF8qpqys7Lq+yFsslkZfUGvs+TkyR3j9HQljaT+32nvVpjnUFi1apISEBIWFhSkyMlIjR47UgQMHrGLOnTun5ORkRUREKCwsTC+++GKdD4qSkhINHz5cISEhioyM1OzZs+tUKbdu3aq4uDgFBwerZ8+eWrt2bZ18srKy1KNHD3Xt2lVPP/20MWcBAAAAANSHX375RceOHTOKZWFhYTpx4oQKCwuNmPz8fNXU1Khbt26SpNDQUH3zzTeqrKw0YnJzc3XPPffIw8PDiMnPz7c6V25urkJDQ+3cIwBAfbCpoLZt2zYNHDhQq1evVkZGhqqqqjRs2DCdPn3aiElJSdGXX36pefPmafny5Tpy5IhGjx5ttFdXV2vEiBGqrKzUqlWrNGvWLK1bt07z5883Yg4ePKgRI0YoIiJCH374oQYPHqwpU6YoJyfHiNm4caNSU1M1atQorVu3ToGBgRo2bJjKyspuZDwAAAAA3MJOnTqloqIiFRUVSZIOHTqkoqIilZSU6NSpU5o9e7YKCgp06NAh5eXlaeTIkbr77rsVExMjSfL19VVMTIxef/117dq1S9u3b9eMGTPUp08f4zahvn37ytXVVa+99pr27dunjRs3KjMzU0OHDjXyGDRokHJycvTuu+9q//79evvtt1VYWKjExMSbPygAAJvZdMtnenq61fNZs2YpMjJSu3fv1v3336+TJ09qzZo1SktLM+YXSElJUe/evVVQUKDQ0FBt2bJFxcXFysjIkJeXl4KCgjR27FilpaVp9OjRcnNz06pVq9ShQwdNmjRJ0vkPre3bt2vp0qXGB1lGRob69eunhIQESVJycrI2b96sNWvWaPjw4TYNwtVWcbD3Kh8NtZJI7Tkb+yomjpKnRK724ii5Okqekv1ydYS+AwBub4WFhRo0aJDxPDU1VZIUFxenpKQk7d27V9nZ2Tp58qTatGmjBx54QGPHjrVasTMtLU0zZszQ4MGDZTKZ9Oijj2rKlClGe4sWLZSenq7p06crPj5erVq10siRI9W/f38jJjw8XGlpaZo3b57efPNNde7cWQsWLJC/v/9NGAUAwI26oTnUTp48KUnGZcuFhYWqrKxUVFSUEePr66t27doZBbWCggL5+/tbzQ0QHR2tpKQkFRcX67777rvsEtIpKSmSpIqKCu3evVsjRoww2k0mk6KiorRz506b+9HQq+I09ISHDd3/a+UoeUrkai+Okquj5Ck1zlz//ve/Kz09XYWFhSotLdWCBQv0yCOPGO2TJk3SunXrrPaJjo62+tHn2LFjmjFjhr788kvji85rr72mO+64w4j57rvvNH36dH377bdq3bq1EhMT9fzzz1sdd9OmTXrrrbf0888/q3Pnzho/frxiY2Pt1HMAwM0QERGhPXv2XLb94osILuXOO+/U3LlzrxgTGBiolStXXjGmV69e6tWr11XPBwBofK67oFZTU6OUlBSFh4cbv6KYzWa5urqqZcuWVrGenp5WS0hfXECqfX61mPLycp09e1bHjx9XdXW1PD0965zn4jndrsXVVsWx9yofDbXSRe3qFY19VSBHyVMiV3txlFwdJU/JfrnasirO5Zw+fVoBAQFKSEiwmjLgQjExMcYVBZKsrhqQpPHjx6u0tFQZGRmqrKzU5MmTNXXqVOPLT3l5uYYNG6bIyEglJydr7969mjx5slq2bGlcPbBjxw6NGzdOr7zyih566CF99NFHGjVqlNauXcvVAwAAAMBt7roLasnJydq3b99Vf3VxBFdbacLeX4wbeqWLhj7/tXKUPCVytRdHydVR8pQaZ66xsbFXvQrMzc3NmBz6Yvv371dOTo4++OADde3aVZI0ZcoUDR8+XBMmTJCPj4/Wr1+vyspKpaSkyM3NTffee6+KioqUkZFhFNQyMzMVExOj5557TpL00ksvKTc3VytWrND06dPrsccAAAAAHM11FdSmT5+uzZs3a8WKFWrbtq2x3cvLS5WVlTpx4oTVVWplZWVWS0hfvBpn7SqgV1tm2t3dXU2bNpXJZJKzs3OdBQiud5lpAIBj2bZtmyIjI9WyZUv95je/0UsvvaRWrVpJknbu3KmWLVsaxTRJioqKkslk0q5du9SzZ08VFBSoe/fuVle2RUdHa/HixTp+/Lg8PDxUUFCgIUOGWJ03Ojpan3/+uc353sjcco1tXrqGmvfzwvM3Ng09JvXBkeaAvBkYj7oay5g09PkBAKhlU0HNYrFoxowZ+uyzz7R8+XJ17NjRqj04OFiurq7Ky8vTY489Jkk6cOCASkpKjOWfQ0NDtXDhQpWVlRm3bObm5srd3V1+fn5GzNdff2117AuXkHZzc1OXLl2Ul5dnzKtTU1OjvLw8VsUBgFtcTEyMevbsqQ4dOujgwYN688039fzzz+v999+Xs7OzzGazWrdubbWPi4uLPDw8rKYW6NChg1VM7Q8yZrNZHh4el5x+wNPTs84PPteiMc5Vd7344aquW2lMbqX3an1gPOpiTAAAOM+mglpycrI2bNig//mf/9Edd9xhfDFp0aKFmjZtqhYtWighIUGzZs2Sh4eH3N3dNXPmTIWFhRnFsOjoaPn5+WnChAl69dVXVVpaqnnz5mngwIHGlQIDBgxQVlaW5syZo4SEBOXn52vTpk1atGiRkcvQoUM1ceJEBQcHq1u3blq2bJnOnDmj+Pj4ehoaAEBj1KdPH+PvgIAABQQE6JFHHjGuWmuMbmSuOnvP42mrhpr3s1ZjGw+p4cekPjjSHJA3A+NRV2MZk/qYqxMAgPpgU0HtvffekyQ9++yzVttTU1ONQtbkyZNlMpk0ZswYVVRUKDo6WtOmTTNinZ2dtXDhQiUlJal///5q1qyZ4uLiNGbMGCOmY8eOWrRokVJTU5WZmam2bdtq5syZiomJMWJ69+6to0ePav78+SotLVVQUJCWLFnS6P6RDQCwr44dO6pVq1b68ccfFRkZKS8vLx09etQqpqqqSsePH7/q1AK1bZeLud6pBW5krrrG9mW+oefda2zjITX8mNSnW6kv9YHxqIsxAQDgPJsKaldaXrpWkyZNNG3aNKsi2sXat2+vxYsXX/E4ERERys7OvmJMYmIit3gCwG3ul19+0bFjx4xiWVhYmE6cOKHCwkIFBwdLkvLz81VTU6Nu3bpJOj+1wLx581RZWSlXV1dJ56cWuOeee+Th4WHE5OfnW82jduH0AwAAAABuX6aGTgAAgAudOnVKRUVFKioqkiQdOnRIRUVFKikp0alTpzR79mwVFBTo0KFDysvL08iRI3X33XcbVzH7+voqJiZGr7/+unbt2qXt27drxowZ6tOnj3GbUN++feXq6qrXXntN+/bt08aNG5WZmamhQ4caeQwaNEg5OTl69913tX//fr399tsqLCzkhxwAAAAA17fKJwAA9lJYWKhBgwYZz1NTUyVJcXFxSkpK0t69e5Wdna2TJ0+qTZs2euCBBzR27FirFTvT0tI0Y8YMDR48WCaTSY8++qimTJlitLdo0ULp6emaPn264uPj1apVK40cOVL9+/c3YsLDw5WWlqZ58+bpzTffVOfOnbVgwQL5+/vfhFEAAAAA0JhRUAMANCoRERFXnGIgPT39qse48847NXfu3CvGBAYGauXKlVeM6dWrl3r16nXV8wEAAAC4vXDLJwAAAAAAAGADCmoAAAAAAACADSioAQAAAAAAADagoAYAAAAAAADYgIIaAAAAAAAAYAMKagAAAAAAAIANKKgBAAAAAAAANqCgBgAAAAAAANiAghoAAAAAAABgAwpqAAAAAAAAgA0oqAEAAAAAAAA2oKAGAAAAAAAA2ICCGgAAAAAAAGADCmoAAAAAAACADSioAQAAAAAAADagoAYAAAAAAADYgIIaAAAAAAAAYAMKagAAAAAAAIANKKgBAAAAAAAANqCgBgAAAAAAANiAghoAAAAAAABgAwpqAAAAAAAAgA0oqAEAAAAAAAA2oKAGAAAAAAAA2ICCGgAAAAAAAGADCmoAAAAAAACADSioAQAAAAAAADawuaD297//XX/4wx8UHR2tgIAAff7551btkyZNUkBAgNVj2LBhVjHHjh3TuHHjFB4eru7du2vy5Mk6deqUVcx3332nZ555Rl27dlVsbKwWL15cJ5dNmzbp8ccfV9euXdW3b1999dVXtnYHAAAAAAAAsInNBbXTp08rICBA06ZNu2xMTEyMtmzZYjzefPNNq/bx48eruLhYGRkZWrhwob755htNnTrVaC8vL9ewYcPUrl07rV27VhMmTNA777yj999/34jZsWOHxo0bp6eeekrZ2dl6+OGHNWrUKO3du9fWLgEAAAAAAADXzMXWHWJjYxUbG3vFGDc3N3l7e1+ybf/+/crJydEHH3ygrl27SpKmTJmi4cOHa8KECfLx8dH69etVWVmplJQUubm56d5771VRUZEyMjLUv39/SVJmZqZiYmL03HPPSZJeeukl5ebmasWKFZo+fbqt3QIAAAAAAACuic0FtWuxbds2RUZGqmXLlvrNb36jl156Sa1atZIk7dy5Uy1btjSKaZIUFRUlk8mkXbt2qWfPniooKFD37t3l5uZmxERHR2vx4sU6fvy4PDw8VFBQoCFDhlidNzo6us4tqNfCycnphtpvlJOTk93PcbnzXvi/jZWj5CmRq704Sq6Okqdkv1wdoe8AAAAAcKPqvaAWExOjnj17qkOHDjp48KDefPNNPf/883r//ffl7Owss9ms1q1bWyfh4iIPDw+VlpZKksxmszp06GAV4+XlZbR5eHjIbDYb22p5enrKbDbbnLOPj4/N+9Sni/txszV0/6+Vo+Qpkau9OEqujpKn5Fi5AgAAAEBjUe8FtT59+hh/1y5K8MgjjxhXrTVGhw8flsViuWy7i4uLXYteZrNZVVVVdjv+5Tg5OcnHx+eq/W9ojpKnRK724ii5Okqekv1yrT0uAAAAANzK7HLL54U6duyoVq1a6ccff1RkZKS8vLx09OhRq5iqqiodP37cmHfNy8urzpVmtc9rC1uXiikrK7uuwpfFYrniF0p7fzG+2vntraHPf60cJU+JXO3FUXJ1lDwlx8oVAAAAABoLm1f5tNUvv/yiY8eOGcWysLAwnThxQoWFhUZMfn6+ampq1K1bN0lSaGiovvnmG1VWVhoxubm5uueee+Th4WHE5OfnW50rNzdXoaGhdu4RAAAAAAAAbmc2F9ROnTqloqIiFRUVSZIOHTqkoqIilZSU6NSpU5o9e7YKCgp06NAh5eXlaeTIkbr77rsVExMjSfL19VVMTIxef/117dq1S9u3b9eMGTPUp08f4zahvn37ytXVVa+99pr27dunjRs3KjMzU0OHDjXyGDRokHJycvTuu+9q//79evvtt1VYWKjExMT6GBcAAAAAAADgkmy+5bOwsFCDBg0ynqempkqS4uLilJSUpL179yo7O1snT55UmzZt9MADD2js2LFWK3ampaVpxowZGjx4sEwmkx599FFNmTLFaG/RooXS09M1ffp0xcfHq1WrVho5cqT69+9vxISHhystLU3z5s3Tm2++qc6dO2vBggXy9/e/roEAAAAAAAAAroXNBbWIiAjt2bPnsu3p6elXPcadd96puXPnXjEmMDBQK1euvGJMr1691KtXr6ueDwAAAAAk6e9//7vS09NVWFio0tJSLViwQI888ojRbrFYNH/+fP3v//6vTpw4ofDwcCUlJalz585GzLFjxzRjxgx9+eWXxgUCr732mu644w4j5rvvvtP06dP17bffqnXr1kpMTNTzzz9vlcumTZv01ltv6eeff1bnzp01fvx4xcbG2n0MAAA3zu5zqAEAAABAY3H69GkFBARo2rRpl2xfvHixli9frqSkJK1evVrNmjXTsGHDdO7cOSNm/PjxKi4uVkZGhhYuXKhvvvlGU6dONdrLy8s1bNgwtWvXTmvXrtWECRP0zjvv6P333zdiduzYoXHjxumpp55Sdna2Hn74YY0aNUp79+61X+cBAPWGghoAAACA20ZsbKxefvll9ezZs06bxWJRZmamXnjhBT3yyCMKDAzUnDlzdOTIEX3++eeSpP379ysnJ0czZ85USEiIunfvrilTpujjjz/W4cOHJUnr169XZWWlUlJSdO+996pPnz569tlnlZGRYZwrMzNTMTExeu655+Tr66uXXnpJ9913n1asWHFzBgIAcEMoqAEAAACAzi+4VlpaqqioKGNbixYtFBISop07d0qSdu7cqZYtW6pr165GTFRUlEwmk3bt2iVJKigoUPfu3a3mkY6Ojtb333+v48ePGzGRkZFW54+OjlZBQYHNeTs5OTnEA/bR0K/rrfiAfTT061rfr7/Nc6gBAAAAwK2otLRUkuTp6Wm13dPTU2azWZJkNpvVunVrq3YXFxd5eHgY+5vNZnXo0MEqxsvLy2jz8PCQ2Ww2tl3qPLbw8fGxeR/cOi5+HwGN1a32XqWgBgAAAAAO7PDhw7JYLA2dxhW5uLjccl+mGwuz2ayqqqqGTuOWwXvVfhzhverk5HTNP1JQUAMAAAAASd7e3pKksrIytWnTxtheVlamwMBASeevsDh69KjVflVVVTp+/Lixv5eXV50rzWqf135Rv1RMWVnZdX2Rt1gsjb6g1tjzc2SO8Po7EsbSfm619ypzqAEAGpW///3v+sMf/qDo6GgFBAQYk0DXslgseuuttxQdHa1u3bppyJAh+uGHH6xijh07pnHjxik8PFzdu3fX5MmTderUKauY7777Ts8884y6du2q2NhYLV68uE4umzZt0uOPP66uXbuqb9+++uqrr+q9vwCAxqNDhw7y9vZWXl6esa28vFz/+Mc/FBYWJkkKCwvTiRMnVFhYaMTk5+erpqZG3bp1kySFhobqm2++UWVlpRGTm5ure+65Rx4eHkZMfn6+1flzc3MVGhpqr+4BAOoRBTUAQKNy+vRpBQQEaNq0aZdsX7x4sZYvX66kpCStXr1azZo107Bhw3Tu3DkjZvz48SouLlZGRoYWLlyob775RlOnTjXay8vLNWzYMLVr105r167VhAkT9M477+j99983Ynbs2KFx48bpqaeeUnZ2th5++GGNGjVKe/futV/nAQB2d+rUKRUVFamoqEjS+YUIioqKVFJSIicnJw0aNEh//vOf9cUXX2jPnj2aMGGC2rRpo0ceeUSS5Ovrq5iYGL3++uvatWuXtm/frhkzZqhPnz7GbUJ9+/aVq6urXnvtNe3bt08bN25UZmamhg4dauQxaNAg5eTk6N1339X+/fv19ttvq7CwUImJiTd/UAAANuOWTwBAoxIbG6vY2NhLtlksFmVmZuqFF14wvtjMmTNHUVFR+vzzz9WnTx/t379fOTk5+uCDD4wV2KZMmaLhw4drwoQJ8vHx0fr161VZWamUlBS5ubnp3nvvVVFRkTIyMtS/f39JUmZmpmJiYvTcc89Jkl566SXl5uZqxYoVmj59uk19upHVohrbSlMNvfpVYxsPqeHHpD7U5u/o/agvjEddjWVM6uP8hYWFGjRokPE8NTVVkhQXF6dZs2bp+eef15kzZzR16lSdOHFCv/71r7VkyRI1adLE2CctLU0zZszQ4MGDZTKZ9Oijj2rKlClGe4sWLZSenq7p06crPj5erVq10siRI43PGEkKDw9XWlqa5s2bpzfffFOdO3fWggUL5O/vf8N9BADYHwU1AIDDOHTokEpLSxUVFWVsa9GihUJCQrRz50716dNHO3fuVMuWLY1imiRFRUXJZDJp165d6tmzpwoKCtS9e3e5ubkZMdHR0Vq8eLGOHz8uDw8PFRQUaMiQIVbnj46OrnML6rW4lVZfY5Leum6lMbmV3qv1gfGo61YYk4iICO3Zs+ey7U5OTho7dqzGjh172Zg777xTc+fOveJ5AgMDtXLlyivG9OrVS7169bpywgCARomCGgDAYZSWlkqSPD09rbZ7enoaEzubzWa1bt3aqt3FxUUeHh7G/mazWR06dLCKqS2KmM1meXh4yGw21ymUXHgeW9zI6muNbaWphl6dqbGNh9TwY1Ifale0coSVAm8GxqOuxjImtqy+BgCAPVFQAwDAzm5kRaPG9mW+oVdnamzjITX8mNSnW6kv9YHxqIsxAQDgPBYlAAA4DG9vb0lSWVmZ1faysjLjqiUvLy8dPXrUqr2qqkrHjx839vfy8qpzpVnt8wuPc3HMhecBAAAAcPuioAYAcBgdOnSQt7e38vLyjG3l5eX6xz/+obCwMElSWFiYTpw4ocLCQiMmPz9fNTU16tatmyQpNDRU33zzjSorK42Y3Nxc3XPPPfLw8DBi8vPzrc6fm5ur0NBQe3UPAAAAgIOgoAYAaFROnTqloqIiFRUVSTq/EEFRUZFKSkrk5OSkQYMG6c9//rO++OIL7dmzRxMmTFCbNm2MVT99fX0VExOj119/Xbt27dL27ds1Y8YM9enTx5h3p2/fvnJ1ddVrr72mffv2aePGjcrMzNTQoUONPAYNGqScnBy9++672r9/v95++20VFhYqMTHx5g8KAAAAgEaFOdQAAI1KYWGhBg0aZDxPTU2VJMXFxWnWrFl6/vnndebMGU2dOlUnTpzQr3/9ay1ZskRNmjQx9klLS9OMGTM0ePBgmUwmPfroo5oyZYrR3qJFC6Wnp2v69OmKj49Xq1atNHLkSPXv39+ICQ8PV1pamubNm6c333xTnTt31oIFC+Tv738TRgEAAABAY0ZBDQDQqERERGjPnj2XbXdyctLYsWM1duzYy8bceeedmjt37hXPExgYqJUrV14xplevXurVq9eVEwYAAABw2+GWTwAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG9hcUPv73/+uP/zhD4qOjlZAQIA+//xzq3aLxaK33npL0dHR6tatm4YMGaIffvjBKubYsWMaN26cwsPD1b17d02ePFmnTp2yivnuu+/0zDPPqGvXroqNjdXixYvr5LJp0yY9/vjj6tq1q/r27auvvvrK1u4AAAAAAAAANrG5oHb69GkFBARo2rRpl2xfvHixli9frqSkJK1evVrNmjXTsGHDdO7cOSNm/PjxKi4uVkZGhhYuXKhvvvlGU6dONdrLy8s1bNgwtWvXTmvXrtWECRP0zjvv6P333zdiduzYoXHjxumpp55Sdna2Hn74YY0aNUp79+61tUsAAAAAAADANbO5oBYbG6uXX35ZPXv2rNNmsViUmZmpF154QY888ogCAwM1Z84cHTlyxLiSbf/+/crJydHMmTMVEhKi7t27a8qUKfr44491+PBhSdL69etVWVmplJQU3XvvverTp4+effZZZWRkGOfKzMxUTEyMnnvuOfn6+uqll17SfffdpxUrVlzvWAAAAAAAAABX5VKfBzt06JBKS0sVFRVlbGvRooVCQkK0c+dO9enTRzt37lTLli3VtWtXIyYqKkomk0m7du1Sz549VVBQoO7du8vNzc2IiY6O1uLFi3X8+HF5eHiooKBAQ4YMsTp/dHR0nVtQr4WTk9MNtd8oJycnu5/jcue98H8bK0fJUyJXe3GUXB0lT8l+uTpC3wEAAADgRtVrQa20tFSS5OnpabXd09NTZrNZkmQ2m9W6dWvrJFxc5OHhYexvNpvVoUMHqxgvLy+jzcPDQ2az2dh2qfPYwsfHx+Z96tPF/bjZGrr/18pR8pTI1V4cJVdHyVNyrFwBAAAAoLGo14Kaozp8+LAsFstl211cXOxa9DKbzaqqqrLb8S/HyclJPj4+V+1/Q3OUPCVytRdHydVR8pTsl2vtcQEAAADgVlavBTVvb29JUllZmdq0aWNsLysrU2BgoKTzV2MdPXrUar+qqiodP37c2N/Ly6vOlWa1z2sLW5eKKSsru67Cl8ViueIXSnt/Mb7a+e2toc9/rRwlT4lc7cVRcnWUPCXHyhUAAAAAGgubFyW4kg4dOsjb21t5eXnGtvLycv3jH/9QWFiYJCksLEwnTpxQYWGhEZOfn6+amhp169ZNkhQaGqpvvvlGlZWVRkxubq7uueceeXh4GDH5+flW58/NzVVoaGh9dgkAAAAAAACwYnNB7dSpUyoqKlJRUZGk8wsRFBUVqaSkRE5OTho0aJD+/Oc/64svvtCePXs0YcIEtWnTRo888ogkydfXVzExMXr99de1a9cubd++XTNmzFCfPn2M24T69u0rV1dXvfbaa9q3b582btyozMxMDR061Mhj0KBBysnJ0bvvvqv9+/fr7bffVmFhoRITE+tjXAAAAAAAAIBLsvmWz8LCQg0aNMh4npqaKkmKi4vTrFmz9Pzzz+vMmTOaOnWqTpw4oV//+tdasmSJmjRpYuyTlpamGTNmaPDgwTKZTHr00Uc1ZcoUo71FixZKT0/X9OnTFR8fr1atWmnkyJHq37+/ERMeHq60tDTNmzdPb775pjp37qwFCxbI39//ugYCAAAAAAAAuBY2F9QiIiK0Z8+ey7Y7OTlp7NixGjt27GVj7rzzTs2dO/eK5wkMDNTKlSuvGNOrVy/16tXrygkDAAAAAAAA9ahe51ADAAAAAAAAbnUU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAAALABBTUAAAAAAADABhTUAAAAAAAAABtQUAMAAAAAAABsQEENAAAAAAAAsAEFNQAAAAAAAMAGFNQAAAAAAAAAG1BQAwAAAAAAAGxAQQ0AAAAAAACwAQU1AAAAAAAAwAYU1AAAAAAAAAAbUFADAAAAAAAAbEBBDQAAAAAu8PbbbysgIMDq8fjjjxvt586dU3JysiIiIhQWFqYXX3xRZrPZ6hglJSUaPny4QkJCFBkZqdmzZ6uqqsoqZuvWrYqLi1NwcLB69uyptWvX3pT+AQBunEtDJwAAAAAAjc29996rjIwM47mzs7Pxd0pKir766ivNmzdPLVq00IwZMzR69GitWrVKklRdXa0RI0bIy8tLq1at0pEjRzRx4kS5urrqlVdekSQdPHhQI0aM0IABA5SWlqa8vDxNmTJF3t7eiomJubmdBQDYjIIaAAAAAFzE2dlZ3t7edbafPHlSa9asUVpamiIjIyWdL7D17t1bBQUFCg0N1ZYtW1RcXKyMjAx5eXkpKChIY8eOVVpamkaPHi03NzetWrVKHTp00KRJkyRJvr6+2r59u5YuXUpBDQAcALd8AgAcCrfhAABuhh9//FHR0dF6+OGHNW7cOJWUlEiSCgsLVVlZqaioKCPW19dX7dq1U0FBgSSpoKBA/v7+8vLyMmKio6NVXl6u4uJiI6a2IHdhTO0xbOHk5OQQD9hHQ7+ut+ID9tHQr2t9v/5coQYAcDjchgMAsKdu3bopNTVV99xzj0pLS7VgwQINHDhQH330kcxms1xdXdWyZUurfTw9PVVaWipJMpvNVsU0Scbzq8WUl5fr7Nmzatq06TXn6+PjY3Mfceu4+H0ENFa32nuVghoAwOFwGw4AwJ5iY2ONvwMDAxUSEqKHHnpImzZtsqnQdbMcPnxYFoulodO4IhcXl1vuy3RjYTab61xpj+vHe9V+HOG96uTkdM0/UlBQAwA4nNrbcJo0aaLQ0FCNGzdO7dq1u+ptOKGhoZe9DScpKUnFxcW67777LnsbTkpKynXleyO3DjS22w4a+laIxjYeUsOPSX2ozd/R+1FfGI+6GsuYNNT5W7Zsqc6dO+unn35SVFSUKisrdeLECaur1MrKyowfe7y8vLRr1y6rY9ROP3BhzMVTEpjNZrm7u9tctLNYLI2+oNbY83NkjvD6OxLG0n5utfcqBTUAgENxtNtwpFvrVhx+sa3rVhqTW+m9Wh8Yj7pu1zE5deqUDh48KG9vbwUHB8vV1VV5eXl67LHHJEkHDhxQSUmJQkNDJUmhoaFauHChysrK5OnpKUnKzc2Vu7u7/Pz8jJivv/7a6jy5ubnGMQAAjRsFNQCAQ3G023CkG7sVp7HddtDQl+o3tvGQGn5M6kPt7Q2OcNvYzcB41NVYxsSWW3FuxOzZs/XQQw+pXbt2OnLkiN5++22ZTCY98cQTatGihRISEjRr1ix5eHjI3d1dM2fOVFhYmFEMi46Olp+fnyZMmKBXX31VpaWlmjdvngYOHCg3NzdJ0oABA5SVlaU5c+YoISFB+fn52rRpkxYtWmT3/gEAbhwFNQCAQ2vst+FIN3Z5e2P7Mt/Ql+o3tvGQGn5M6tOt1Jf6wHjUdbuMyS+//KJXXnlFx44dU+vWrfXrX/9aq1evVuvWrSVJkydPlslk0pgxY1RRUaHo6GhNmzbN2N/Z2VkLFy5UUlKS+vfvr2bNmikuLk5jxowxYjp27KhFixYpNTVVmZmZatu2rWbOnMlcnQDgICioAQAcGrfhAADq23//939fsb1JkyaaNm2aVRHtYu3bt9fixYuveJyIiAhlZ2dfT4oAgAZmaugEAACwxezZs7Vt2zYdOnRIO3bs0OjRoy95G05+fr4KCws1efLky96G89133yknJ+eSt+EcPHhQc+bM0f79+5WVlaVNmzZpyJAhDddxAAAAAI0GV6gBABwKt+EAAAAAaGgU1AAADoXbcAAAAAA0NG75BAAAAAAAAGxAQQ0AAAAAAACwQb0X1N5++20FBARYPR5//HGj/dy5c0pOTlZERITCwsL04osvymw2Wx2jpKREw4cPV0hIiCIjIzV79mxVVVVZxWzdulVxcXEKDg5Wz549tXbt2vruCgAAAAAAAFCHXeZQu/fee5WRkWE8d3Z2Nv5OSUnRV199pXnz5qlFixaaMWOGRo8erVWrVkmSqqurNWLECHl5eWnVqlU6cuSIJk6cKFdXV73yyiuSpIMHD2rEiBEaMGCA0tLSlJeXpylTpsjb25sJowEAAAAAAGBXdimoOTs7y9vbu872kydPas2aNUpLS1NkZKSk8wW23r17q6CgQKGhodqyZYuKi4uVkZEhLy8vBQUFaezYsUpLS9Po0aPl5uamVatWqUOHDpo0aZIkydfXV9u3b9fSpUspqAEAAAAAAMCu7FJQ+/HHHxUdHa0mTZooNDRU48aNU7t27VRYWKjKykpFRUUZsb6+vmrXrp1RUCsoKJC/v7+8vLyMmOjoaCUlJam4uFj33XefCgoKjILchTEpKSnXla+Tk9MNtd8oJycnu5/jcue98H8bK0fJUyJXe3GUXB0lT8l+uTpC3wEAAADgRtV7Qa1bt25KTU3VPffco9LSUi1YsEADBw7URx99JLPZLFdXV7Vs2dJqH09PT5WWlkqSzGazVTFNkvH8ajHl5eU6e/asmjZtalPOPj4+NsXXt4v7crM1dP+vlaPkKZGrvThKro6Sp+RYuQIAAABAY1HvBbXY2Fjj78DAQIWEhOihhx7Spk2bbC503SyHDx+WxWK5bLuLi4tdi15ms7nOogs3g5OTk3x8fK7a/4bmKHlK5GovjpKro+Qp2S/X2uMCAAAAwK3MLrd8Xqhly5bq3LmzfvrpJ0VFRamyslInTpywukqtrKzMmHPNy8tLu3btsjpG7SqgF8ZcvDKo2WyWu7v7dRXtLBbLFb9Q2vuL8dXOb28Nff5r5Sh5SuRqL46Sq6PkKTlWrgAuz2QyyWS6/sXba2/XdnFxuaH/JtTU1Kimpua69wcAAHAUdi+onTp1SgcPHpS3t7eCg4Pl6uqqvLy8/4+9u4+Lqs7///+c4UItlBIQQ60MVEhQMPdD0LBslpmabcqmbpDpz1ZbNa0sdM1VUT+Ahq1ruaurhqEYuamUpe1ubbm6QJeQix/U0C50KWXGTcUrLn9/+PWsE16NAjMDj/vtNrcbM+c1c17nnJk5zHPOvI8GDBggSdq/f7/KysoUGRkpSYqMjNSyZctks9nk5+cnScrLy5OPj49CQkKMmn/84x9288nLyzMeAwAAoKUwm83y8/OTp+e1/1t3rUfkV1dXy2azEaoBAIBmr8EDtQULFujuu+9WUFCQDh8+rJdeeklms1kPPPCA2rZtq4SEBKWnp8vX11c+Pj6aP3++oqKijDDMYrEoJCREycnJeu6551ReXq7FixcrMTFR3t7ekqSRI0cqOztbCxcuVEJCggoKCrR161YtX768oRcHAADApZnNZnl6eioxMVElJSVO6yMsLEzZ2dkym80EagAAoNlr8EDt+++/1zPPPKMffvhB7du31x133KH169erffv2kqQZM2bIbDZr8uTJqqyslMVi0ezZs437e3h4aNmyZZozZ45GjBihNm3aaOjQoZo8ebJR06VLFy1fvlxpaWnKyspSx44dNX/+fMXFxTX04gAAALiFkpISFRYWOrsNAACAFqHBA7Xf/e53l5zeqlUrzZ492y5E+7FOnTppxYoVl3yc6Oho5ebmXk2LAAAAAAAAwFW7+tFrAQAAAAAAgBaIQA0AAAAAAABwAIEaAAAAAAAA4IAGH0MNzmc2m2U2Xz4rNZlMkiRPT0/V1dVdsra2tpYzdgEAAAAAAIhArdkxm83y8/OTp+eVb1p/f//L1lRXV8tmszV4qHYl4Z8jwZ9E+AcAAAAAABoXgVozYzab5enpqcTERJWUlDTIY4aFhSk7O1tms7lBgypHw78rCf6kxgn/GuOoP4nwDwAAAAAAd0Sg1kyVlJSosLDQ2W1ckruEf4111J/UeEf+AQAAAACAxkOgBqdz9fCvMYI/qfGO/AMAAAAAAI2LQA24Qq4e/AEAAAAAgKZx+UGhAAAAAAAAABgI1AAAAAAAAAAHEKgBAAAAAAAADiBQAwAAAAAAABxAoAYAAAAAAAA4gEANAAAAAAAAcACBGgAAAAAAAOAAAjUAAAAAAADAAQRqAAAAAAAAgAM8nd0AgIZlNptlNl8+KzeZTJIkT09P1dXVXba+trZWtbW119wfAAAAAADujkANaEbMZrP8/Pzk6XnlL21/f/8rqquurpbNZmvQUK0xwj+CPwAAAABAYyNQA5oRs9ksT09PJSYmqqSkpMEeNywsTNnZ2TKbzQ0WVjVW+NcYwR8AAAAAAOcjUAOaoZKSEhUWFjq7jUtqjPCvMYI/AAAAAAB+jEANgFO5Q/gHAHAvVzqkwMU4Os7oxTAMAQAAzReBGgAAAJqNqxlS4GKudJzRi2EYAgAAmi8CNQC4AldytANnTgUA52us8UQdxTAEAAA0bwRqAHAZjh7t4MwzpwIAzmJIAXv8DBYAgIZFoAYAl8EJFAAA7oyfwQIA0PAI1ADgCnG0AwDAHfEzWAAAGh6BGgAAANAC8MUQAAAN5+oHUgAAAAAAAABaIAI1AAAAAAAAwAFuH6hlZ2erX79+ioiI0MMPP6ydO3c6uyUAQDPCfgYA0NjY1wCA+3HrQG3Lli1KS0vTxIkTtWnTJoWGhmrs2LGy2WzObg0AnOLcwNNXcpF0xbVms1vvLq4a+xkAQGNjXwMA7smtT0qQmZmp4cOHKyEhQZKUkpKiDz/8UBs2bNC4ceOu+HHMZrPq6uouOV2S+vTpo+uvv/7amj5Pjx49jMdvqA+rjdFrY/R57vEk1++1pW9/yX165blq1o033miEZVfC39//iuqqq6v1n//857JnZTOZTFc8b3fQVPuZy91XavjXtaMa6/XlKFdZHxLr5MdYH/ZcZX2c60FqHuukue1npIbZ11zLfqapuMrzsDlxpfeZ5oTnasNzp+eqI/sZU52rv/NeRGVlpSIjI7VkyRLde++9xu3Tpk3TsWPH9Mc//tGJ3QEA3B37GQBAY2NfAwDuy7WjwUv4z3/+o5qaGvn5+dnd7ufnJ6vV6qSuAADNBfsZAEBjY18DAO7LbQM1AAAAAAAAwBncNlC78cYb5eHhUW+wTpvNdsVjAgEAcDHsZwAAjY19DQC4L7cN1Ly9vdWzZ0/l5+cbt9XW1io/P19RUVFO7AwA0BywnwEANDb2NQDgvtz6LJ9jxozRtGnTFB4erl69eunVV1/VqVOnNGzYMGe3BgBoBtjPAAAaG/saAHBPbh2oDRo0SEeOHNGSJUtUXl6usLAwrVy5ksOjAQANgv0MAKCxsa8BAPdkqqurq3N2EwAAAAAAAIC7cNsx1AAAAAAAAABnIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACtRaqsrJSlZWVzm4DgBPw+gcAAACAa+Pp7Aaam3MfUr29vZ3cSX3//Oc/tXr1ahUVFamiokKS5OPjo8jISI0ZM0axsbFO7tD9lJaWau3atSoqKpLVapUk+fv7KzIyUklJSQoJCXFyh//lTr2i4fH6b9lced8EuAL2kfWxTtBSsc+EK+O92bWY6urq6pzdhLtzhw+qmzZt0syZMzVgwABZLBb5+flJkmw2m/75z3/qL3/5i+bPn6+HHnrIuY3+P+7wRrFt2zZNnDhRPXv2vOA63bVrl/7whz8oLi7OyZ26V6+Se2x/yX36dLfXPxqGO+ybmpK7vF6bCuvjv9xtH9kUWCdoadhnwh3w3ux6CNSukbt8UB0wYIBGjRqlxMTEC07Pzs7Wq6++qr/+9a9N3Fl97vJG8eCDD+qee+7RlClTLjj9pZde0l//+ldt3ry5iTurz516dZft7y59Su71+kfDcJd9U1Nxp9drU2B92HOnfWRTYZ2gJWGfCXfBe7MLqsM1ue++++rWrl170elr166t69+/fxN2dGHh4eF1+/btu+j0ffv21UVERDRhRxc3ZMiQusWLF190+pIlS+oeeOCBJuzowiIiItxmnbpTr+6y/d2lz7o693r9o2G4y76pqbjT67UpsD7sudM+sqmwTtCSsM+Eu+C92fVwUoJrVFZWppiYmItOj4mJ0ffff9+EHV1Yt27d9MYbb1x0+oYNG1zm5x1ff/21hgwZctHpgwcP1jfffNOEHV1Yp06dtG3btotO37Ztm4KCgpqwo4tzp17dZfu7S5+Se73+0TDcZd/UVNzp9doUWB/23Gkf2VRYJ2hJ2GfCXfDe7Ho4KcE1OvdBNTk5+YLTXeWD6rRp0/TEE09o+/btio2NtTuUOT8/XwcOHNCf/vQnJ3d51rk3ittuu+2C013ljWLy5Ml69tln9dFHHyk2Nlb+/v6SJKvVqvz8fG3fvl2LFi1ycpdnuVOv7rL93aVPyb1e/2gY7rJvairu9HptCqwPe+60j2wqrBO0JOwz4S54b3Y9jKF2jT766CM98cQT6ty58yU/qP7kJz9xcqfSwYMH9dprr+mLL75QeXm5JCkgIECRkZEaOXKkOnfu7OQOz9q6daueffZZxcXFXfKNYsCAAU7uVPr888+1Zs0aFRUV1Vuno0aNUlRUlJM7/C936dVdtr+79HmOu7z+0TDcad/UFNzt9drYWB/1ucs+simxTtBSsM+EO+G92bUQqDUAPqg2PN4oWjZ32f7u0idaJvZN9ni92mN9AMB/sc8EcDUI1AAAAAAAAAAHcFICSDo7xtKoUaOc3Uaz8uKLL+o3v/mNs9u4Iu7UKxoer38AuDj2kfWxTgDA9fDe3PQI1BqZu3xQDQwMVKdOnZzdxhVxlzeKQ4cO6d///rez27gi7tSru2x/d+lTcq/XPxqGu+ybmoo7vV6bAuvDnjvtI5sK6wQtCftMuAvem5seZ/lsZB06dJDZ7Pq55TPPPOPsFq7Y999/7xanrl6wYIGzW7isuro6mUwmt+j1nEOHDum7775zdhuX5S7PU8m9Xv9oGO6yb2oq7vR6bQqsj7PccR/ZVFgnaEnYZ8Jd8N7c9BhDDWjBwsPD9eabbyo4ONjZrQAA4FLYRwIAgEvhCLVG9t1332nJkiVKS0tzah+7du1Su3bt1KVLF0lSbm6ucnJy9N133ykoKEhJSUkaPHiwU3s83759+1RUVKTIyEgFBwdr3759ysrKUmVlpR588EHFxMQ4u0VJ0unTp1VcXKwbbrhBISEhdtPOnDmjrVu36qGHHnJOc+e52POvpqZGf/rTn3TDDTdIkkv8xGfevHkaOHCg+vbt6+xWHHLy5Elt3bpV3377rQICAjR48GDdeOONzm7LsHbtWu3cuVPx8fEaPHiwcnNz9ac//Um1tbW67777NHnyZHl6sktoKVxl3+Qsrv56bQrusp9tCu60j2xK7vI/DtDYWvo+E66F92bXwhFqjWz37t0aOnSoSkpKnNrHgw8+qOnTpys2NlZ//vOfNX/+fD388MMKDg7WV199pT//+c96/vnn9Ytf/MKpfUrSP/7xD02YMEHXX3+9Tp06pZdfflnTpk1TaGioamtr9cknn2jVqlVO/2f/q6++0tixY1VWViaTyaQ77rhDL774ojp06CBJslqtiouLc/q2l6TQ0FCFhoaqbdu2drd/8sknCg8PV5s2bWQymZSVleWkDv8rNDRUJpNJN998sxISEjR06FAFBAQ4u616Bg0apHXr1umGG27Qd999p8TERB07dky33nqrDhw4IA8PD73++utGiO1Mf/jDH7Ry5UpZLBZ9/vnnGjVqlFatWqXRo0fLbDZr9erV+uUvf6nJkyc7u1U0EVfZNzUVd3q9NgV32c82FXfaRzYVd/ofB2hsLW2fCdfFe7Pr4XCEa/T+++9fcvqBAweaqJNL++abb3TLLbdIktatW6fnn39ew4cPN6ZHRERo2bJlLhGo/eEPf9DYsWP19NNP65133tGzzz6rX/7yl3r66aclSYsWLdKKFSuc/o9+RkaGunXrpjfeeEPHjx9XamqqfvnLX2rNmjUKCgpyam8/9swzz+j111/XtGnT7NZbz549lZ6eXu/bDWd75ZVX9Pe//12vvPKKlixZori4OA0fPlzx8fEuM4bF/v37VVNTI+nsc7JDhw5688031bZtW504cUKTJk3S4sWLtWjRIid3Km3atEnp6em67777tHv3bg0bNkzp6el68MEHJUm33XabXnjhBQK1ZsRd9k1NxZ1er03BXfazTcXd9pFNwZ3+xwGuFftMuAvem10Pgdo1mjhxokwmky51oJ/JZGrCji6sdevW+s9//qNOnTrp0KFD6tWrl9303r176+DBg07qzt6XX35pDKg4cOBAJScna8CAAcb0IUOGaOPGjc5qz1BYWKjMzEy1b99e7du317JlyzRnzhwlJiYqKytLbdq0cXaLhnHjxunOO+/Uc889p379+umZZ56Rl5eXs9u6qO7duysmJkbJycn629/+pg0bNmjixIny8/PTsGHDNGzYMCMgdgVFRUVKSUkxjm64/vrr9eSTT7rMYP+HDx9WeHi4pLNHYpjNZoWFhRnTb7/9dh0+fNhZ7aERuMu+yRlc/fXaFNxlP9tU3G0f2RTc6X8c4Fqxz4S74L3Z9bjGoR5uLCAgQC+99JJ27959wcumTZuc3aIk6ac//alee+01SdJPfvITvfvuu3bTt27dqptvvtkZrV3QuZ2W2WyWt7e33c8wrr/+eh0/ftxZrRlOnz5tN+aUyWRSSkqK7r77biUlJenrr792XnMX0KtXL23cuFFHjhxRQkKC9u7d6/L/HHh5eWnQoEFatWqV3nvvPQ0fPlybN2/W/fff7+zWJP33eXrmzJl6P0sNDAzUkSNHnNFWPf7+/iotLZUkff3116qpqTGuS1Jpaanat2/vrPbQCNxl39SU3OX12lTcYT/blNxxH9mY3O1/HOBasM+Eu+C92fVwhNo16tmzp3bt2qV77733gtMv921HUzn3c46kpCSFh4crMzNTH3/8sTGGWlFRkZYuXersNiVJnTp10tdff20EfK+//rpuuukmY/p3333nEmNq3XbbbfrXv/5V7+xfs2bNkiT9+te/dkZbl3T99ddrwYIFeueddzRmzBjjJ1DuICgoSE8++aQmTZqkvLw8Z7cjSXrsscfk6empiooKffXVV+revbsxrayszBjI2tmGDBmiadOm6Z577lF+fr4ef/xxLVy4UD/88INMJpOWLVtmd3QK3J+77Juakru8XpuCu+xnm5o77yMbmjv+jwNcLfaZcBe8N7seArVr9Pjjj+vkyZMXnX7zzTe7xCC2gYGBxln9PvjgA9XV1Wnnzp36/vvvFRUVpddee00RERHOblOS9Mtf/lK1tbXG9fM/9EhnB1O+8847m7qtevr376933nnngmdRmTVrlmpra5WTk9P0jV2BwYMH64477lBxcbHL/d4+KCjokuOkmUwm3XXXXU3Y0YVNmjTJ7vp1111nd/3vf/+7y5ypdPLkyWrdurWKioo0fPhwjRs3TqGhoXrhhRd06tQp9evXT1OmTHF2m2hA7rJvairu9HptCu6yn3UWV95HNhV3/h8HcBT7TLgL3ptdD2f5BAAAAAAAABzAGGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4ABPZzcAtEQHDhxQZmam/vnPf+r777+XJHXq1EnR0dEaMWKEQkND7epLSkq0atUqffLJJ7LZbLruuut0++23a8iQIXrooYfk4eEhSerRo4cSExM1a9asJl8mAIDz7dmzR0uXLtW//vUvWa1W3XDDDQoJCVG/fv306KOPGnU1NTXKzc1Vbm6u9uzZo5MnT6pDhw6Kjo7WI488ooiICEnSxo0b9Zvf/EZvvPGGcdv5Hn30Uf3nP//R22+/3WTLCABoeOfe78/x8PCQn5+f7rrrLj399NMKDAysd5/s7GzNnTtXvXr10p///OeLPrbVatWqVav0wQcf6LvvvpPJZNJtt92me++9V0lJSWrXrp0kaefOndq4caN27typPXv2qLq6Wnv27Kn3eAcPHtQ999xjXDebzQoMDFTPnj01adIkhYWFXcuqAK4YgRrQxD744AM9/fTT8vDw0JAhQxQaGiqz2az9+/frr3/9q1577TW9//776tSpkyTpz3/+s2bPni0/Pz/9/Oc/1y233KITJ06ooKBAzz//vMrLy/XEE084eakAAM72+eefa9SoUQoKCtLDDz+sgIAAfffdd/riiy+UlZVlBGqnT5/WpEmTtH37dv3kJz/R+PHj5evrq3//+9/aunWrNm3apA8//FAdO3Z08hIBAJra5MmT1blzZ1VWVqqoqEibNm3SZ599prffflutWrWyq928ebM6deqknTt36ptvvtEtt9xS7/F27typcePG6eTJk3rwwQfVs2dPSVJxcbFWrFihTz/9VK+88ookadu2bXrjjTfUvXt3de7cWV9//fUle33ggQf005/+VLW1tdq3b59ee+01/eMf/9D69esJ1dAkCNSAJvTtt9/qmWeeUVBQkFavXq0OHTrYTX/22We1bt06mc1nf41dVFSk2bNnKzIyUn/605/k4+Nj1I4ePVr/+te/9OWXXzbpMgAAXNOyZcvUtm1bvfHGG8a3/efYbDbj74ULF2r79u36zW9+o9GjR9vVTZo0SatXr26CbgEAruinP/2pcUTyww8/rBtvvFErVqzQ+++/r0GDBhl1Bw4cUGFhoV5++WXNmjVLmzdv1qRJk+we69ixY5o0aZI8PDy0adMmBQcH201/+umntX79euP6L3/5S/3qV79S69atNXfu3MsGarfffrt+/vOfG9f79OmjX//613rttdc0d+7cq10FwBVjDDWgCa1cuVInT55UWlpavTBNkjw9PTVq1CjddNNNkqSXX35ZJpNJGRkZdmHaORERERo2bFij9w0AcH3ffvutQkJC6oVpkuTn5ydJ+v777/X666/rrrvuqhemSWd/4jN27FiOTgMASJL69u0r6WyAdr7NmzfL19dX8fHxGjBggDZv3lzvvjk5OTp06JCmT59eL0yTJH9/f02YMMHueuvWra+61zvvvFPS2Z+EAk2BQA1oQh988IFuueUW9e7d+7K1p06dUkFBgfr27augoKAm6A4A4M46deqkXbt2ae/evRet+cc//qHq6mo9+OCDDj12RUWFjhw5Uu9SVVV1rW0DAFzYv//9b0mq92XN5s2b1b9/f3l7e+uBBx7Q119/rZ07d9rV/P3vf1fr1q01YMCAJun122+/lSTdcMMNTTI/gJ98Ak2koqJChw8f1r333ltv2rFjx1RdXW1cv+666/TNN9+oqqpK3bt3b8o2AQBu6v/7//4//epXv9JDDz2kXr166Y477lBMTIyio6Pl5eUlSdq3b5+ksyexccSFjmY7p1u3blfdMwDAtZz7AqWyslJffPGFXn75ZXl7e+vuu+82aoqLi7V//3799re/lSTdcccd6tixozZv3qxevXoZdfv379ett94qb2/vRun11KlTOnLkiGpra7V//36lpaVJku6///5GmR/wYwRqQBOpqKiQdDYs+7FHH31Uu3fvNq4nJycbR7Fdf/31TdMgAMCt3XXXXcrJydGf/vQn7dixQ4WFhVq5cqXat2+v+fPn65577jH2RY7uW2bNmqWuXbvWuz09PV21tbUN0j8AwPl+/AVKp06d9MILL9gNBbB582b5+/srOjpakmQymTRo0CC99dZbmj59ujw8PCSd/fzTmJ9lXnrpJb300kvGdR8fHz377LO67777Gm2ewPkI1IAmcm5ncvLkyXrT5s6dqxMnTshqteq5556TJGPMtBMnTjRdkwAAt9arVy+9/PLLqqys1O7du/Xee+9p9erVmjJlinJzc69639KrVy9jkOrz+fr66j//+U+D9A4AcL5zX6AcP35cGzZs0CeffGJ3hFlNTY3eeecdRUdH241V1qtXL73yyivKz8+XxWKRdPbzTGN+lhkxYoTuv/9+mUwmtWvXTt26dWu0o+GACyFQA5pI27ZtFRAQcMGzcp47Gu38ndItt9wiT0/PS46FAwDAhXh7e6tXr17q1auXbr31Vv3mN7/Ru+++q9tuu02StGfPHoWFhTm5SwCAqzn/C5R7771XjzzyiKZOnap3331X119/vQoKClReXq533nlH77zzTr37b9682QjUbrvtNpWUlKiysrJRgq5bbrlFsbGxDf64wJXipARAE/rZz36mb775pt6AnRfSpk0b3Xnnnfr000/13XffNUF3AIDmKDw8XJJ0+PBh/fSnP5WHh8cFz8YGAMD5PDw89Mwzz+jw4cPKzs6WdDYw8/Pz0+9///t6lwceeEB/+9vfdPr0aUnS3XffrdOnT+uvf/2rMxcDaDQEakATevzxx9WmTRvNmDFDVqu13vS6ujq76xMnTlRdXZ2Sk5MveLh0cXGxNm3a1Gj9AgDcR0FBQb39iCRt27ZN0tkjBW666SY9/PDD2rFjh9asWVOvtra2Vq+88oq+//77Ru8XAOD6oqOj1atXL7366qtGOPazn/1M999/f71LYmKiTpw4ob///e+SpJEjRyogIEDp6en66quv6j22zWbTH/7wh6ZeJKDB8JNPoAndeuutysjI0NSpU3X//fdryJAhCg0NVV1dnQ4ePKi3335bZrPZGPSzT58+mjVrllJSUjRw4ED9/Oc/1y233KITJ07o448/1t///nc99dRTdvMoLi6+4I7pf/7nf9S3b9+mWEwAgBPMnz9fp06dUv/+/XXbbbepqqpKn3/+ubZu3apOnTpp2LBhkqTp06frwIEDmj9/vv7617/q7rvvVrt27fTdd9/p3Xff1f79+zV48GAnLw0AwFWMHTtWU6ZM0cqVK3XixAn169fvgnWRkZFq37693nrrLQ0aNEi+vr5aunSpxo0bp4ceekgPPvigevbsKUn6v//7P7399tuKiooy7v/vf/9bb775pqSzn2kkGZ9rgoKC9NBDDzXiUgKOI1ADmti9996rzZs365VXXtE///lPbdiwQSaTSUFBQYqPj9cvf/lLhYaGGvUjR45URESEXnnlFeXm5uo///mPrrvuOt1+++1KS0vTgw8+aPf4X3zxhb744ot6850yZQqBGgA0Y8nJyXr33Xe1bds2vf7666qqqlJQUJAeeeQR/frXv1a7du0knR1SYMWKFdq4caNyc3P1hz/8QadPn1aHDh0UHR2tjIwMBQYGOnlpAACu4r777tPNN9+sl19+Wa1atdJdd911wTqz2ayf/exn2rx5s/7zn//oxhtvVO/evbV582atWrVKH374od58802ZzWbddtttGjdunJKSkoz7Hzx4UL///e/tHvPc9f/5n/8hUIPLMdVd6LcBAAAAAAAAAC6IMdQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOIBADQAAAAAAAHAAgRoAAAAAAADgAAI1AAAAAAAAwAGezm7AFRw6dEh1dXXObqNZMJlMCgwMZJ3C5fFcbRzn1ivsNefnGa+l5oHt2Dy0hO3IfubCmvM2d4aW8FpC88BzteE5sp8hUJNUV1fHk6+BsU7hLniuoim0hOdZS1jGloDt2DywHVsetnnjYL3CXfBcdQ5+8gkAcBkvvfSSevToYXe5//77jelnzpxRSkqKoqOjFRUVpSeffFJWq9XuMcrKyjRu3Dj17t1bMTExWrBggaqrq+1qPvroIw0dOlTh4eHq37+/Nm7cWK+X7Oxs9evXTxEREXr44Ye1c+fOxlloAAAAAG6HQA0A4FK6deumHTt2GJd169YZ01JTU/XBBx9o8eLFWrNmjQ4fPqxJkyYZ02tqajR+/HhVVVUpJydH6enp2rRpk5YsWWLUHDhwQOPHj1d0dLTefPNNPfbYY5o5c6a2b99u1GzZskVpaWmaOHGiNm3apNDQUI0dO1Y2m61pVgIAAAAAl0agBgBwKR4eHgoICDAu7du3lyQdP35cGzZs0PTp0xUTE6Pw8HClpqaqsLBQRUVFkqQdO3aotLRUL7zwgsLCwhQfH68pU6YoOztblZWVkqScnBx17txZ06dPV3BwsJKSkjRgwACtXr3a6CEzM1PDhw9XQkKCQkJClJKSotatW2vDhg1NvToAAAAAuCDGUAMAuJRvvvlGFotFrVq1UmRkpKZOnaqgoCAVFxerqqpKsbGxRm1wcLCCgoJUVFSkyMhIFRUVqXv37vL39zdqLBaL5syZo9LSUt1+++0qKipSTEyM3TwtFotSU1MlSZWVldq1a5fGjx9vTDebzYqNjVVhYeFVLZPJZLqq+7mDc8vWnJexJWA7Ng8tYTs252UDALgXAjUAgMvo1auX0tLS1LVrV5WXl2vp0qVKTEzU5s2bZbVa5eXlpXbt2tndx8/PT+Xl5ZIkq9VqF6ZJMq5frqaiokKnT5/W0aNHVVNTIz8/v3rz2b9//1UtV0s4I11LWMaWgO3YPLAdAQBofARqAACXER8fb/wdGhqq3r176+6779bWrVvVunVrJ3Z2bZrzqcw5XXvzwHZsHlrCdjy3jAAAOBuBGgDAZbVr10633nqrvv32W8XGxqqqqkrHjh2zO0rNZrMpICBA0tkjzX58Ns5zZwE9v+bHZwa1Wq3y8fFR69atZTab5eHhUe8EBDabrd6RbVeqJZzKvCUsY0vAdmwe2I4AADQ+TkoAAHBZJ06c0IEDBxQQEKDw8HB5eXkpPz/fmL5//36VlZUpMjJSkhQZGam9e/fahWF5eXny8fFRSEiIUVNQUGA3n7y8POMxvL291bNnT7v51NbWKj8/X1FRUY20pAAAAADcCYEaAMBlLFiwQB9//LEOHjyozz//XJMmTZLZbNYDDzygtm3bKiEhQenp6SooKFBxcbFmzJihqKgoIwyzWCwKCQlRcnKydu/ere3bt2vx4sVKTEyUt7e3JGnkyJE6cOCAFi5cqH379ik7O1tbt27V6NGjjT7GjBmj9evXa9OmTdq3b5/mzJmjU6dOadiwYU5YKwAAAABcDT/5BAC4jO+//17PPPOMfvjhB7Vv31533HGH1q9fr/bt20uSZsyYIbPZrMmTJ6uyslIWi0WzZ8827u/h4aFly5Zpzpw5GjFihNq0aaOhQ4dq8uTJRk2XLl20fPlypaWlKSsrSx07dtT8+fMVFxdn1AwaNEhHjhzRkiVLVF5errCwMK1cufKqf/IJAAAAoHkx1THAgr7//nvGmWggJpNJHTt2ZJ3C5fFcbRzn1ivsNefnGa+l5oHt2Dy0hO3IfubCmvM2d4aW8FpC88BzteE5sp/hJ58AAAAAAACAAwjUAAAAAAAAAAdc0xhqf/rTn7Ro0SKNGjVKzz//vCTpzJkzSk9P15YtW+zGtzl/3JmysjLNmTNHH330ka677jo99NBDmjp1qjw9/9vORx99pPT0dH355Ze66aab9Otf/7reYNDZ2dlatWqVysvLFRoaqt/+9rfq1avXtSySyzKbzTKbXT//NJlMkiRPT0+3OOS0trZWtbW1zm4DABpMU+8vnPG+z3s3ALgnPtM0PPaJgPNcdaC2c+dO5eTkqEePHna3p6amatu2bVq8eLHatm2refPmadKkScrJyZEk1dTUaPz48fL391dOTo4OHz6sadOmycvLS88884wk6cCBAxo/frxGjhypjIwM5efna+bMmQoICDAGjd6yZYvS0tKUkpKi3r1769VXX9XYsWP17rvvys/P72oXyyWZzWb5+fnZBY6uzl0G7q6urpbNZmMnBKBZcOb+oinf93nvBgD3w2eaxsE+EXCeq3o3O3HihJ577jnNnz9ff/zjH43bjx8/rg0bNigjI0MxMTGSzgZsgwYNUlFRkSIjI7Vjxw6VlpYqMzNT/v7+CgsL05QpU5SRkaFJkybJ29tbOTk56ty5s6ZPny5JCg4O1meffabVq1cbgVpmZqaGDx+uhIQESVJKSoo+/PBDbdiwQePGjbumleJqzGazPD09lZiYqJKSEme302yEhYUpOztbZrOZHRCAZqEl7C947wYA99QS9lFNjX0i4FxXFajNnTtX8fHxio2NtQvUiouLVVVVpdjYWOO24OBgBQUFGYFaUVGRunfvbpf2WywWzZkzR6Wlpbr99ttVVFRkBHLn16SmpkqSKisrtWvXLo0fP96YbjabFRsbq8LCQoeX59whva7qXH8lJSVXtXy4NJPJ5PLPATS8c9ucbd+wWJ+ugf0FAMBVsY8C0Fw4HKi98847+r//+z+98cYb9aZZrVZ5eXmpXbt2drf7+fmpvLzcqPnxobPnrl+upqKiQqdPn9bRo0dVU1NT76edfn5+2r9/v6OLpMDAQIfvg+bDHQ7lRuPh9Q8AAAAAcJRDgdp3332n//3f/9Urr7yiVq1aNVZPTe7QoUMuPdikp6cnoU8jslqtqq6udnYbaGImk0mBgYEu//p3N+fWKwAAAAA0Zw4Fart27ZLNZrM722ZNTY0++eQT44ybVVVVOnbsmN1RajabTQEBAZLOHg20c+dOu8e1Wq2SZFdz7rbza3x8fNS6dWuZzWZ5eHjIZrPZ1dhstqsKnurq6lz6A7Ur99YcuPr2R+Ni+wMAAAAAHOXQOYvvvPNObd68Wbm5ucYlPDxcQ4YMMf728vJSfn6+cZ/9+/errKxMkZGRkqTIyEjt3bvXLgzLy8uTj4+PQkJCjJqCggK7eefl5RmP4e3trZ49e9rNp7a2Vvn5+YqKinJoBQAAAAAAAACOcOgINR8fH3Xv3t3utuuuu0433HCDcXtCQoLS09Pl6+srHx8fzZ8/X1FRUUYYZrFYFBISouTkZD333HMqLy/X4sWLlZiYKG9vb0nSyJEjlZ2drYULFyohIUEFBQXaunWrli9fbsx3zJgxmjZtmsLDw9WrVy+9+uqrOnXqlN3RcwAAAAAAAEBDu6qzfF7KjBkzZDabNXnyZFVWVspisWj27NnGdA8PDy1btkxz5szRiBEj1KZNGw0dOlSTJ082arp06aLly5crLS1NWVlZ6tixo+bPn6+4uDijZtCgQTpy5IiWLFmi8vJyhYWFaeXKlYw1BgAAAAAAgEZ1zYHamjVr7K63atVKs2fPtgvRfqxTp05asWLFJR83Ojpaubm5l6xJSkpSUlLSFfcKAAAAAAAAXCuHxlADAAAAAAAAWjoCNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAKDFWLdunYYMGaI+ffqoT58+GjFihLZt22ZMP3PmjFJSUhQdHa2oqCg9+eSTslqtdo9RVlamcePGqXfv3oqJidGCBQtUXV1tV/PRRx9p6NChCg8PV//+/bVx48Z6vWRnZ6tfv36KiIjQww8/rJ07dzbOQgMAGhyBGgAAAIAWo2PHjnr22We1ceNGbdiwQXfeeacmTpyoL7/8UpKUmpqqDz74QIsXL9aaNWt0+PBhTZo0ybh/TU2Nxo8fr6qqKuXk5Cg9PV2bNm3SkiVLjJoDBw5o/Pjxio6O1ptvvqnHHntMM2fO1Pbt242aLVu2KC0tTRMnTtSmTZsUGhqqsWPHymazNd3KAABcNQI1AAAAAC1Gv379FB8fr1tvvVVdu3bV008/reuuu05FRUU6fvy4NmzYoOnTpysmJkbh4eFKTU1VYWGhioqKJEk7duxQaWmpXnjhBYWFhSk+Pl5TpkxRdna2KisrJUk5OTnq3Lmzpk+fruDgYCUlJWnAgAFavXq10UdmZqaGDx+uhIQEhYSEKCUlRa1bt9aGDRucsFYAAI4iUAMAAADQItXU1Oidd97RyZMnFRUVpeLiYlVVVSk2NtaoCQ4OVlBQkBGoFRUVqXv37vL39zdqLBaLKioqVFpaatTExMTYzctisRiPUVlZqV27dtnNx2w2KzY2VoWFhQ4vh8lkcosLGoeztysX57+unN1Dc7tcKc/GelEDAAAAgCvas2ePRo4cqTNnzui6667T0qVLFRISopKSEnl5ealdu3Z29X5+fiovL5ckWa1WuzBNknH9cjUVFRU6ffq0jh49qpqaGvn5+dWbz/79+x1ensDAQIfvg+bjx881tDy8BzgHgRoAAACAFqVr167Kzc3V8ePH9Ze//EXTpk3T2rVrnd3WVTt06JDq6uqc3cYleXp6Evw0EqvVWu+kGGgZTCaTAgMD3eI9wF2cW6dXgkANAAAAQIvi7e2tW265RZIUHh6uf/3rX8rKytLAgQNVVVWlY8eO2R2lZrPZFBAQIOns0UA/PhvnubOAnl/z4zODWq1W+fj4qHXr1jKbzfLw8Kh3AgKbzXZVoVNdXZ3Lf5h29f7cmTtsfzQungPOwRhqAAAAAFq02tpaVVZWKjw8XF5eXsrPzzem7d+/X2VlZYqMjJQkRUZGau/evXZhWF5ennx8fBQSEmLUFBQU2M0jLy/PeAxvb2/17NnTbj61tbXKz89XVFRUIy0lAKAhcYQaAAAAgBZj0aJF+ulPf6qbbrpJJ06c0Ntvv62PP/5Yq1atUtu2bZWQkKD09HT5+vrKx8dH8+fPV1RUlBGGWSwWhYSEKDk5Wc8995zKy8u1ePFiJSYmytvbW5I0cuRIZWdna+HChUpISFBBQYG2bt2q5cuXG32MGTNG06ZNU3h4uHr16qVXX31Vp06d0rBhw5yxWgAADiJQAwAAANBi2Gw2TZs2TYcPH1bbtm3Vo0cPrVq1SnfddZckacaMGTKbzZo8ebIqKytlsVg0e/Zs4/4eHh5atmyZ5syZoxEjRqhNmzYaOnSoJk+ebNR06dJFy5cvV1pamrKystSxY0fNnz9fcXFxRs2gQYN05MgRLVmyROXl5QoLC9PKlSsZZwwA3ASBGgAAAIAWIzU19ZLTW7VqpdmzZ9uFaD/WqVMnrVix4pKPEx0drdzc3EvWJCUlKSkp6ZI1AADXxBhqAAAAAAAAgAMI1AAAAAAAAAAHEKgBAAAAAAAADiBQAwAAAAAAABxAoAYAAAAAAAA4gEANAAAAAAAAcIBDgdq6des0ZMgQ9enTR3369NGIESO0bds2Y/qjjz6qHj162F1mzZpl9xhlZWUaN26cevfurZiYGC1YsEDV1dV2NR999JGGDh2q8PBw9e/fXxs3bqzXS3Z2tvr166eIiAg9/PDD2rlzpyOLAgAAAAAAAFwVT0eKO3bsqGeffVa33HKL6urqlJubq4kTJ2rTpk3q1q2bJGn48OGaPHmycZ82bdoYf9fU1Gj8+PHy9/dXTk6ODh8+rGnTpsnLy0vPPPOMJOnAgQMaP368Ro4cqYyMDOXn52vmzJkKCAhQXFycJGnLli1KS0tTSkqKevfurVdffVVjx47Vu+++Kz8/v2teKQAAAAAAAMDFOBSo9evXz+76008/rddee01FRUVGoNa6dWsFBARc8P47duxQaWmpMjMz5e/vr7CwME2ZMkUZGRmaNGmSvL29lZOTo86dO2v69OmSpODgYH322WdavXq1EahlZmZq+PDhSkhIkCSlpKToww8/1IYNGzRu3DjH1oAkk8nk8H2akqv35+5MJhPruAU6t83Z9g2L9QkAAACgJXAoUDtfTU2N3n33XZ08eVJRUVHG7Zs3b9Zbb72lgIAA3X333ZowYYJxlFpRUZG6d+8uf39/o95isWjOnDkqLS3V7bffrqKiIsXExNjNy2KxKDU1VZJUWVmpXbt2afz48cZ0s9ms2NhYFRYWXtWyBAYGXtX90Dyc/3xEy8PrHwAAAADgKIcDtT179mjkyJE6c+aMrrvuOi1dulQhISGSpAceeEBBQUHq0KGD9uzZo4yMDH311Vd6+eWXJUlWq7VeeHHuenl5+SVrKioqdPr0aR09elQ1NTX1ftrp5+en/fv3O7o4kqRDhw6prq7uqu7bFDw9PQl9GpHVaq03jh+aP5PJpMDAQJd//bubc+sVAAAAAJozhwO1rl27Kjc3V8ePH9df/vIXTZs2TWvXrlVISIhGjBhh1PXo0UMBAQEaPXq0vv32W918880N2nhDqqurc+kP1K7cW3Pg6tsfjYvtDwAAAABwlENn+ZQkb29v3XLLLQoPD9fUqVMVGhqqrKysC9b27t1bkvTNN99IOnukmdVqtas5d/3cuGsXq/Hx8VHr1q114403ysPDQzabza7GZrNxFBcAAAAAAAAancOB2o/V1taqsrLygtNKSkok/Tcsi4yM1N69e+3CsLy8PPn4+Bg/G42MjFRBQYHd4+Tl5SkyMlLS2UCvZ8+eys/Pt+shPz/fbiw3AAAAAAAAoDE4FKgtWrRIn3zyiQ4ePKg9e/Zo0aJF+vjjjzVkyBB9++23Wrp0qYqLi3Xw4EG9//77mjZtmn7yk58oNDRU0tmTC4SEhCg5OVm7d+/W9u3btXjxYiUmJsrb21uSNHLkSB04cEALFy7Uvn37lJ2dra1bt2r06NFGH2PGjNH69eu1adMm7du3T3PmzNGpU6c0bNiwhlszAAAAAAAAwAU4NIaazWbTtGnTdPjwYbVt21Y9evTQqlWrdNddd+m7775Tfn6+srKydPLkSd1000267777NGHCBOP+Hh4eWrZsmebMmaMRI0aoTZs2Gjp0qCZPnmzUdOnSRcuXL1daWpqysrLUsWNHzZ8/X3FxcUbNoEGDdOTIES1ZskTl5eUKCwvTypUr+cknAAAAAAAAGp1DgVpqaupFp910001au3btZR+jU6dOWrFixSVroqOjlZube8mapKQkJSUlXXZ+AAAAAAAAQEO65jHUAAAAAAAAgJaEQA0AAAAAAABwAIEaAAAAAAAA4AACNQCAy/rTn/6kHj166H//93+N286cOaOUlBRFR0crKipKTz75pKxWq939ysrKNG7cOPXu3VsxMTFasGCBqqur7Wo++ugjDR06VOHh4erfv782btxYb/7Z2dnq16+fIiIi9PDDD2vnzp2Ns6AAAAAA3AqBGgDAJe3cuVM5OTnq0aOH3e2pqan64IMPtHjxYq1Zs0aHDx/WpEmTjOk1NTUaP368qqqqlJOTo/T0dG3atElLliwxag4cOKDx48crOjpab775ph577DHNnDlT27dvN2q2bNmitLQ0TZw4UZs2bVJoaKjGjh0rm83W+AsPAAAAwKURqAEAXM6JEyf03HPPaf78+fL19TVuP378uDZs2KDp06crJiZG4eHhSk1NVWFhoYqKiiRJO3bsUGlpqV544QWFhYUpPj5eU6ZMUXZ2tiorKyVJOTk56ty5s6ZPn67g4GAlJSVpwIABWr16tTGvzMxMDR8+XAkJCQoJCVFKSopat26tDRs2NOWqAAAAAOCCCNQAAC5n7ty5io+PV2xsrN3txcXFqqqqsrs9ODhYQUFBRqBWVFSk7t27y9/f36ixWCyqqKhQaWmpURMTE2P32BaLxXiMyspK7dq1y24+ZrNZsbGxKiwsdHh5TCZTk11aiqZcpy3lwnptHpeWsB0BAHAFns5uAACA873zzjv6v//7P73xxhv1plmtVnl5ealdu3Z2t/v5+am8vNyoOT9Mk2Rcv1xNRUWFTp8+raNHj6qmpkZ+fn715rN//36HlykwMNDh++DSfrz90DB4rjYPbEcAABofgRoAwGV89913+t///V+98soratWqlbPbaTCHDh1SXV1do8/H09OzxQRNVqu13okmcPVMJpMCAwOb7LmKxtEStuO5ZQQAwNkI1AAALmPXrl2y2WwaNmyYcVtNTY0++eQTZWdna9WqVaqqqtKxY8fsjlKz2WwKCAiQdPbIpR+fjfPcWUDPr/nxmUGtVqt8fHzUunVrmc1meXh41DsBgc1mu6rAqq6urkk+3DbXD9AX0lTrtKVhvTYPbEcAABofY6gBAFzGnXfeqc2bNys3N9e4hIeHa8iQIcbfXl5eys/PN+6zf/9+lZWVKTIyUpIUGRmpvXv32oVheXl58vHxUUhIiFFTUFBgN++8vDzjMby9vdWzZ0+7+dTW1io/P19RUVGNtPQAAAAA3AVHqAEAXIaPj4+6d+9ud9t1112nG264wbg9ISFB6enp8vX1lY+Pj+bPn6+oqCgjDLNYLAoJCVFycrKee+45lZeXa/HixUpMTJS3t7ckaeTIkcrOztbChQuVkJCggoICbd26VcuXLzfmO2bMGE2bNk3h4eHq1auXXn31VZ06dcru6DkAAAAALROBGgDArcyYMUNms1mTJ09WZWWlLBaLZs+ebUz38PDQsmXLNGfOHI0YMUJt2rTR0KFDNXnyZKOmS5cuWr58udLS0pSVlaWOHTtq/vz5iouLM2oGDRqkI0eOaMmSJSovL1dYWJhWrlzZYsYoAwAAAHBxBGoAAJe2Zs0au+utWrXS7Nmz7UK0H+vUqZNWrFhxyceNjo5Wbm7uJWuSkpKUlJR0xb0CAAAAaBkYQw0AAAAAAABwAIEaAAAAAAAA4AACNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAgBZj+fLlSkhIUFRUlGJiYjRhwgTt37/frubRRx9Vjx497C6zZs2yqykrK9O4cePUu3dvxcTEaMGCBaqurrar+eijjzR06FCFh4erf//+2rhxY71+srOz1a9fP0VEROjhhx/Wzp07G36hAQANjkANAAAAQIvx8ccfKzExUevXr1dmZqaqq6s1duxYnTx50q5u+PDh2rFjh3FJTk42ptXU1Gj8+PGqqqpSTk6O0tPTtWnTJi1ZssSoOXDggMaPH6/o6Gi9+eabeuyxxzRz5kxt377dqNmyZYvS0tI0ceJEbdq0SaGhoRo7dqxsNlvjrwgAwDUhUAMAAADQYqxatUrDhg1Tt27dFBoaqvT0dJWVlWnXrl12da1bt1ZAQIBx8fHxMabt2LFDpaWleuGFFxQWFqb4+HhNmTJF2dnZqqyslCTl5OSoc+fOmj59uoKDg5WUlKQBAwZo9erVxuNkZmZq+PDhSkhIUEhIiFJSUtS6dWtt2LChSdYFAODqEagBAAAAaLGOHz8uSfL19bW7ffPmzYqOjtYDDzygRYsW6dSpU8a0oqIide/eXf7+/sZtFotFFRUVKi0tNWpiYmLsHtNisaioqEiSVFlZqV27dik2NtaYbjabFRsbq8LCQoeWwWQyucUFjcPZ25WL819Xzu6huV2ulGdjvagBAAAAwJXV1tYqNTVVffr0Uffu3Y3bH3jgAQUFBalDhw7as2ePMjIy9NVXX+nll1+WJFmtVrswTZJxvby8/JI1FRUVOn36tI4ePaqamhr5+fnZ1fj5+dUb0+1yAgMDHapH8/Lj5xlaHt4DnINADQAAAECLlJKSoi+//FLr1q2zu33EiBHG3z169FBAQIBGjx6tb7/9VjfffHNTt3lZhw4dUl1dnbPbuCRPT0+Cn0ZitVrrnRADLYPJZFJgYKBbvAe4i3Pr9EoQqAEAAABocebOnasPP/xQa9euVceOHS9Z27t3b0nSN998o5tvvln+/v71zsZptVolSQEBAZLOHjV07rbza3x8fNS6dWuZzWZ5eHjUOwGBzWZzOHiqq6tz+Q/Trt6fO3OH7Y/GxXPAORwaQ23dunUaMmSI+vTpoz59+mjEiBHatm2bMf3MmTNKSUlRdHS0oqKi9OSTT9bbiXB6aQAAAADOUldXp7lz5+pvf/ubXn31VXXp0uWy9ykpKZH037AsMjJSe/futQvD8vLy5OPjo5CQEKOmoKDA7nHy8vIUGRkpSfL29lbPnj2Vn59vTK+trVV+fr6ioqKuaRkBAI3PoUCtY8eOevbZZ7Vx40Zt2LBBd955pyZOnKgvv/xSkpSamqoPPvhAixcv1po1a3T48GFNmjTJuD+nlwYAAADgTCkpKXrrrbe0aNEiXX/99SovL1d5eblOnz4tSfr222+1dOlSFRcX6+DBg3r//fc1bdo0/eQnP1FoaKiksycXCAkJUXJysnbv3q3t27dr8eLFSkxMlLe3tyRp5MiROnDggBYuXKh9+/YpOztbW7du1ejRo41exowZo/Xr12vTpk3at2+f5syZo1OnTmnYsGFNvl4AAI5x6Cef/fr1s7v+9NNP67XXXlNRUZE6duyoDRs2KCMjwzibTWpqqgYNGqSioiJFRkYap5fOzMyUv7+/wsLCNGXKFGVkZGjSpEny9va2O720JAUHB+uzzz7T6tWrFRcXJ8n+9NLS2Z3ihx9+qA0bNmjcuHHXvFIAAAAANE+vvfaaJOnRRx+1uz0tLU3Dhg2Tl5eX8vPzlZWVpZMnT+qmm27SfffdpwkTJhi1Hh4eWrZsmebMmaMRI0aoTZs2Gjp0qCZPnmzUdOnSRcuXL1daWpqysrLUsWNHzZ8/3/hMI0mDBg3SkSNHtGTJEpWXlyssLEwrV65krDEAcANXPYZaTU2N3n33XZ08eVJRUVEqLi5WVVWV3Wmfg4ODFRQUZARqFzu99Jw5c1RaWqrbb7/9oqeXTk1NlfTf00uPHz/emH61p5c+x5HTojqDq/fn7hw9NS6ah/NPMY2Gw/oEALi6PXv2XHL6TTfdpLVr1172cTp16qQVK1ZcsiY6Olq5ubmXrElKSlJSUtJl5wcAcC0OB2p79uzRyJEjdebMGV133XVaunSpQkJCVFJSIi8vL7Vr186u3s/P77Knjpacc3rpczjFbMvGN4AtG69/AAAAAICjHA7UunbtqtzcXB0/flx/+ctfNG3atCv6BseVufopZjnFdOPiNNMtE6eYbhyOnGYaAAAAANyVw4Gat7e3brnlFklSeHi4/vWvfykrK0sDBw5UVVWVjh07ZneUms1mszt1tCudXvocVz/FrCv31hy4+vZH42L7AwAAAAAc5dBZPi+ktrZWlZWVCg8PNwbwPGf//v0qKyszTg3N6aUBAAAAAADg7hw6Qm3RokX66U9/qptuukknTpzQ22+/rY8//lirVq1S27ZtlZCQoPT0dPn6+srHx0fz589XVFSUEYadf3rp5557TuXl5Rc8vXR2drYWLlyohIQEFRQUaOvWrVq+fLnRx5gxYzRt2jSFh4erV69eevXVVzm9NAAAAAAAAJqEQ4GazWbTtGnTdPjwYbVt21Y9evTQqlWrdNddd0mSZsyYIbPZrMmTJ6uyslIWi0WzZ8827s/ppQEAAAAAAODuHArUUlNTLzm9VatWmj17tl2I9mOcXhoAAAAAAADu7JrHUAMAAAAAAABaEgI1AAAAAAAAwAEEagAAAAAAAIADCNQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOMDT2Q0AAAAAAAC4CrPZLLPZ9Y8/MplMkiRPT0/V1dU5uZtLq62tVW1trbPbaFAEagAAAAAAADobpvn5+cnT033iEn9/f2e3cFnV1dWy2WzNKlRzn2cIAAAAAABAIzKbzfL09FRiYqJKSkqc3U6zEBYWpuzsbJnNZgI1AAAAAACA5qqkpESFhYXObgMuzPV/FAwAAAAAAAC4EAI1AAAAAAAAwAEEagAAAAAAAIADCNQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOIBADQAAAAAAAHAAgRoAAAAAAADgAAI1AAAAAAAAwAEEagAAAAAAAIADCNQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOIBADQAAAAAAAHAAgRoAAAAAAADgAAI1AAAAAAAAwAEEagAAAAAAAIADHArUli9froSEBEVFRSkmJkYTJkzQ/v377WoeffRR9ejRw+4ya9Ysu5qysjKNGzdOvXv3VkxMjBYsWKDq6mq7mo8++khDhw5VeHi4+vfvr40bN9brJzs7W/369VNERIQefvhh7dy505HFAQAAAAAAABzmUKD28ccfKzExUevXr1dmZqaqq6s1duxYnTx50q5u+PDh2rFjh3FJTk42ptXU1Gj8+PGqqqpSTk6O0tPTtWnTJi1ZssSoOXDggMaPH6/o6Gi9+eabeuyxxzRz5kxt377dqNmyZYvS0tI0ceJEbdq0SaGhoRo7dqxsNtvVrgsAgJOtW7dOQ4YMUZ8+fdSnTx+NGDFC27ZtM6afOXNGKSkpio6OVlRUlJ588klZrVa7x+BLGwAAAACNzaFAbdWqVRo2bJi6deum0NBQpaenq6ysTLt27bKra926tQICAoyLj4+PMW3Hjh0qLS3VCy+8oLCwMMXHx2vKlCnKzs5WZWWlJCknJ0edO3fW9OnTFRwcrKSkJA0YMECrV682HiczM1PDhw9XQkKCQkJClJKSotatW2vDhg3XsDoAAM7UsWNHPfvss9q4caM2bNigO++8UxMnTtSXX34pSUpNTdUHH3ygxYsXa82aNTp8+LAmTZpk3J8vbQAAAAA0hWsaQ+348eOSJF9fX7vbN2/erOjoaD3wwANatGiRTp06ZUwrKipS9+7d5e/vb9xmsVhUUVGh0tJSoyYmJsbuMS0Wi4qKiiRJlZWV2rVrl2JjY/+7IGazYmNjVVhY6PBymEwml7+g8Th723Jx7uvK2T00x8u16Nevn+Lj43Xrrbeqa9euevrpp3XdddepqKhIx48f14YNGzR9+nTFxMQoPDxcqampKiwsNPYPrvqljbusf3fi7Od5c7ywXpvHpSVsx2t1JcPYcEQ0AOByPK/2jrW1tUpNTVWfPn3UvXt34/YHHnhAQUFB6tChg/bs2aOMjAx99dVXevnllyVJVqvVLkyTZFwvLy+/ZE1FRYVOnz6to0ePqqamRn5+fnY1fn5+9XaGVyIwMNDh+6D5+PFzDS0Lr3/XVVNTo3fffVcnT55UVFSUiouLVVVVZfdlSnBwsIKCglRUVKTIyMiLfmkzZ84clZaW6vbbb7/olzapqamS/vulzfjx443p1/KljcTzrDHw3t04eK42D2zHSzs3jE1ERIRqamr04osvauzYsXrnnXd03XXXSTp7RPS2bdu0ePFitW3bVvPmzdOkSZOUk5Mj6b9HRPv7+ysnJ0eHDx/WtGnT5OXlpWeeeUbSf4+IHjlypDIyMpSfn6+ZM2cqICBAcXFxkv57RHRKSop69+6tV199VWPHjtW7775b77MOAMC1XHWglpKSoi+//FLr1q2zu33EiBHG3z169FBAQIBGjx6tb7/9VjfffPPVd9qIDh06pLq6Ome3cVGenp58cGhEVqu13reJaP5MJpMCAwNd/vXvbs6t12uxZ88ejRw5UmfOnNF1112npUuXKiQkRCUlJfLy8lK7du3s6v38/C77hYzkvC9tpKbbz7Sk/QXv3Q2L98TmoSVsx4bYz6xatcruenp6umJiYrRr1y795Cc/MY6IzsjIML6ASU1N1aBBg4wvcM4dEZ2ZmSl/f3+FhYVpypQpysjI0KRJk+Tt7W13RLR09kugzz77TKtXrzYCtfOPiJbOfsb68MMPtWHDBo0bN86h9eLq3KFHd9VQR2/iLNZl43GH56oj/V1VoDZ37lx9+OGHWrt2rTp27HjJ2t69e0uSvvnmG918883y9/evdxjzucOnAwICJJ39YPPjQ6qtVqt8fHzUunVrmc1meXh41BvLxmazXdUHibq6Opf+p8OVe2sOXH37o3Gx/V1P165dlZubq+PHj+svf/mLpk2bprVr1zq7rWvSVM+zlvRc5rXbOFivzQPb0TE/HsbGHY+I5qjElq2lfJkG99fcnqsOBWp1dXWaN2+e/va3v2nNmjXq0qXLZe9TUlIi6b9hWWRkpJYtWyabzWZ8+5+XlycfHx+FhIQYNf/4xz/sHicvL0+RkZGSJG9vb/Xs2VP5+fm69957JZ39CWp+fr6SkpIcWSQAgIvx9vbWLbfcIkkKDw/Xv/71L2VlZWngwIGqqqrSsWPH7I5Ss9lsdl/IuNqXNgAA13WhYWysVqvbHRHtDkcltqSjqJsaR203LJ6rjccdnquOHAnt0EkJUlJS9NZbb2nRokW6/vrrVV5ervLycp0+fVqS9O2332rp0qUqLi7WwYMH9f7772vatGn6yU9+otDQUElnv5UJCQlRcnKydu/ere3bt2vx4sVKTEyUt7e3JGnkyJE6cOCAFi5cqH379ik7O1tbt27V6NGjjV7GjBmj9evXa9OmTdq3b5/mzJmjU6dOadiwYY4sEgDAxdXW1qqyslLh4eHy8vJSfn6+MW3//v0qKyszvnCJjIzU3r177cKwC31pU1BQYDePi31pc34P+fn5ioqKaqSlBAA4w7lhbH73u985u5Vrcu6oRFe/oHE4e7s2xwsah7O3a0Nvf4eOUHvttdckSY8++qjd7WlpaRo2bJjxQScrK0snT57UTTfdpPvuu08TJkwwaj08PLRs2TLNmTNHI0aMUJs2bTR06FBNnjzZqOnSpYuWL1+utLQ0ZWVlqWPHjpo/f74x1oAkDRo0SEeOHNGSJUtUXl6usLAwrVy5kiQZANzYokWL9NOf/lQ33XSTTpw4obffflsff/yxVq1apbZt2yohIUHp6eny9fWVj4+P5s+fr6ioKCMMO/9Lm+eee07l5eUX/NImOztbCxcuVEJCggoKCrR161YtX77c6GPMmDGaNm2awsPD1atXL7366qt8aQMAzczFhrHx9/fniGgAwGU5FKjt2bPnktNvuummKxrnplOnTlqxYsUla6Kjo5Wbm3vJmqSkJH7iCQDNiM1m07Rp03T48GG1bdtWPXr00KpVq3TXXXdJkmbMmCGz2azJkyersrJSFotFs2fPNu7PlzYAgMupq7v0MDbnHxE9YMAASRc+IpphbACgZbvqs3wCANDQzg3UfDGtWrXS7Nmz7UK0H+NLGwDApaSkpOjtt9/WH/7wB2MYG0lq27atWrduzRHRAIArQqAGAAAAoMW43DA2EkdEAwAuj0ANAAAAQItxuWFsJI6IBgBcnkNn+QQAAAAAAABaOgI1AAAAAAAAwAEEagAAAAAAAIADCNQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOIBADQAAAAAAAHAAgRoAAAAAAADgAAI1AAAAAAAAwAEEagAAAAAAAIADCNQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOIBADQAAAAAAAHAAgRoAAAAAAADgAAI1AAAAAAAAwAEEagAAAAAAAIADCNQAAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAcQKAGAAAAAAAAOIBADQAAAAAAAHAAgRoAAAAAAADgAAI1AAAAAAAAwAEEagAAAAAAAIADHArUli9froSEBEVFRSkmJkYTJkzQ/v377WrOnDmjlJQURUdHKyoqSk8++aSsVqtdTVlZmcaNG6fevXsrJiZGCxYsUHV1tV3NRx99pKFDhyo8PFz9+/fXxo0b6/WTnZ2tfv36KSIiQg8//LB27tzpyOIAAAAAAAAADnMoUPv444+VmJio9evXKzMzU9XV1Ro7dqxOnjxp1KSmpuqDDz7Q4sWLtWbNGh0+fFiTJk0yptfU1Gj8+PGqqqpSTk6O0tPTtWnTJi1ZssSoOXDggMaPH6/o6Gi9+eabeuyxxzRz5kxt377dqNmyZYvS0tI0ceJEbdq0SaGhoRo7dqxsNtu1rA8AAAAAAADgkhwK1FatWqVhw4apW7duCg0NVXp6usrKyrRr1y5J0vHjx7VhwwZNnz5dMTExCg8PV2pqqgoLC1VUVCRJ2rFjh0pLS/XCCy8oLCxM8fHxmjJlirKzs1VZWSlJysnJUefOnTV9+nQFBwcrKSlJAwYM0OrVq41eMjMzNXz4cCUkJCgkJEQpKSlq3bq1NmzY0DBrBgAAAAAAALiAaxpD7fjx45IkX19fSVJxcbGqqqoUGxtr1AQHBysoKMgI1IqKitS9e3f5+/sbNRaLRRUVFSotLTVqYmJi7OZlsViMx6isrNSuXbvs5mM2mxUbG6vCwkKHl8NkMrn8BY3H2duWi3NfV87uoTleAAAAAKC587zaO9bW1io1NVV9+vRR9+7dJUlWq1VeXl5q166dXa2fn5/Ky8uNmvPDNEnG9cvVVFRU6PTp0zp69Khqamrk5+dXbz4/HtPtSgQGBjp8HzQfP36uoWXh9Q8AAAAAcNRVB2opKSn68ssvtW7duobsxykOHTqkuro6Z7dxUZ6enoQ+jchqtdY7KQaaP5PJpMDAQJd//bubc+sVAAAAAJqzqwrU5s6dqw8//FBr165Vx44djdv9/f1VVVWlY8eO2R2lZrPZFBAQYNT8+Gyc584Cen7Nj88MarVa5ePjo9atW8tsNsvDw6PeCQhsNttVBU91dXUu/YHalXtrDlx9+6Nxsf0BAAAAAI5yaAy1uro6zZ07V3/729/06quvqkuXLnbTw8PD5eXlpfz8fOO2/fv3q6ysTJGRkZKkyMhI7d271y4My8vLk4+Pj0JCQoyagoICu8fOy8szHsPb21s9e/a0m09tba3y8/MVFRXlyCIBAAAAAAAADnEoUEtJSdFbb72lRYsW6frrr1d5ebnKy8t1+vRpSVLbtm2VkJCg9PR0FRQUqLi4WDNmzFBUVJQRhlksFoWEhCg5OVm7d+/W9u3btXjxYiUmJsrb21uSNHLkSB04cEALFy7Uvn37lJ2dra1bt2r06NFGL2PGjNH69eu1adMm7du3T3PmzNGpU6c0bNiwhlkzAAAAAAAAwAU49JPP1157TZL06KOP2t2elpZmBFkzZsyQ2WzW5MmTVVlZKYvFotmzZxu1Hh4eWrZsmebMmaMRI0aoTZs2Gjp0qCZPnmzUdOnSRcuXL1daWpqysrLUsWNHzZ8/X3FxcUbNoEGDdOTIES1ZskTl5eUKCwvTypUrGWsMAAAAAAAAjcqhQG3Pnj2XrWnVqpVmz55tF6L9WKdOnbRixYpLPk50dLRyc3MvWZOUlKSkpKTL9gQAAAAAAAA0FId+8gkAAAAAAAC0dARqAAAAAAAAgAMI1AAAAAC0GJ988omeeOIJWSwW9ejRQ++9957d9OnTp6tHjx52l7Fjx9rV/PDDD5o6dar69Omjvn37asaMGTpx4oRdze7du/XII48oIiJC8fHxFxzyZuvWrbr//vsVERGhIUOGaNu2bQ2/wACARkGgBgAAAKDFOHnypHr06HHJMZ/j4uK0Y8cO4/Liiy/aTX/22WdVWlqqzMxMLVu2TJ9++qlmzZplTK+oqNDYsWMVFBSkjRs3Kjk5WS+//LJef/11o+bzzz/X1KlT9Ytf/EK5ubm65557NHHiRO3du7fhFxoA0OAcOikBAAAAALiz+Ph4xcfHX7LG29tbAQEBF5y2b98+bd++XW+88YYiIiIkSTNnztS4ceOUnJyswMBAvfXWW6qqqlJqaqq8vb3VrVs3lZSUKDMzUyNGjJAkZWVlKS4uTo8//rgk6amnnlJeXp7Wrl2ruXPnOrRMJpPJoXpncIce3ZXJZGL9NiDWZeNxh+eqI/0RqAEAAADAeT7++GPFxMSoXbt2uvPOO/XUU0/pxhtvlCQVFhaqXbt2RpgmSbGxsTKbzdq5c6f69++voqIi9e3bV97e3kaNxWLRihUrdPToUfn6+qqoqEijR4+2m6/FYqn3E9QrERgYeHULimbB39/f2S0AV6S5PVcJ1AAAAADg/4mLi1P//v3VuXNnHThwQC+++KJ+9atf6fXXX5eHh4esVqvat29vdx9PT0/5+vqqvLxckmS1WtW5c2e7mnMfJK1Wq3x9fWW1Wut9uPTz85PVanW450OHDqmurs7h+zUlT0/PZvdh2lVYrVZVV1c7u41mg+dq43GH56rJZLriLykI1AAAAADg/xk8eLDx97mTEtx7773GUWuuqK6uzuUDNVfvz525w/Z3J6zLxtPcnquclAAAAAAALqJLly668cYb9c0330g6e6TZkSNH7Gqqq6t19OhRY9w1f3//ekeanbt+7siXC9XYbDaOjAEAN0GgBgAAAAAX8f333+uHH34wwrKoqCgdO3ZMxcXFRk1BQYFqa2vVq1cvSVJkZKQ+/fRTVVVVGTV5eXnq2rWrfH19jZqCggK7eeXl5SkyMrKRlwgA0BAI1AAAAAC0GCdOnFBJSYlKSkokSQcPHlRJSYnKysp04sQJLViwQEVFRTp48KDy8/M1YcIE3XLLLYqLi5MkBQcHKy4uTr/97W+1c+dOffbZZ5o3b54GDx5sjLszZMgQeXl56fnnn9eXX36pLVu2KCsrS2PGjDH6GDVqlLZv365XXnlF+/bt00svvaTi4mIlJSU1/UoBADiMMdQAAAAAtBjFxcUaNWqUcT0tLU2SNHToUM2ZM0d79+5Vbm6ujh8/rg4dOuiuu+7SlClT7M7YmZGRoXnz5umxxx6T2WzWfffdp5kzZxrT27Ztq1WrVmnu3LkaNmyYbrzxRk2YMEEjRowwavr06aOMjAwtXrxYL774om699VYtXbpU3bt3b4K1AAC4VgRqAAAAAFqM6Oho7dmz56LTV61addnHuOGGG7Ro0aJL1oSGhmrdunWXrBk4cKAGDhx42fkBAFwPP/kEAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACNQCAy1i+fLkSEhIUFRWlmJgYTZgwQfv377erOXPmjFJSUhQdHa2oqCg9+eSTslqtdjVlZWUaN26cevfurZiYGC1YsEDV1dV2NR999JGGDh2q8PBw9e/fXxs3bqzXT3Z2tvr166eIiAg9/PDD2rlzZ8MvNAAAAAC3Q6AGAHAZH3/8sRITE7V+/XplZmaqurpaY8eO1cmTJ42a1NRUffDBB1q8eLHWrFmjw4cPa9KkScb0mpoajR8/XlVVVcrJyVF6ero2bdqkJUuWGDUHDhzQ+PHjFR0drTfffFOPPfaYZs6cqe3btxs1W7ZsUVpamiZOnKhNmzYpNDRUY8eOlc1ma5qVAQAAAMBlEagBAFzGqlWrNGzYMHXr1k2hoaFKT09XWVmZdu3aJUk6fvy4NmzYoOnTpysmJkbh4eFKTU1VYWGhioqKJEk7duxQaWmpXnjhBYWFhSk+Pl5TpkxRdna2KisrJUk5OTnq3Lmzpk+fruDgYCUlJWnAgAFavXq10UtmZqaGDx+uhIQEhYSEKCUlRa1bt9aGDRuaerUAAAAAcDEEagAAl3X8+HFJkq+vrySpuLhYVVVVio2NNWqCg4MVFBRkBGpFRUXq3r27/P39jRqLxaKKigqVlpYaNTExMXbzslgsxmNUVlZq165ddvMxm82KjY1VYWGhw8thMpma7NJSNOU6bSkX1mvzuLSE7QgAgCvwdHYDAABcSG1trVJTU9WnTx91795dkmS1WuXl5aV27drZ1fr5+am8vNyoOT9Mk2Rcv1xNRUWFTp8+raNHj6qmpkZ+fn715vPjMd2uRGBgoMP3waX9ePuhYfBcbR7YjgAAND4CNQCAS0pJSdGXX36pdevWObuVa3bo0CHV1dU1+nw8PT1bTNBktVrrnWgCV89kMikwMLDJnqtoHC1hO55bRgAAnI1ADQDgcubOnasPP/xQa9euVceOHY3b/f39VVVVpWPHjtkdpWaz2RQQEGDU/PhsnOfOAnp+zY/PDGq1WuXj46PWrVvLbDbLw8Oj3gkIbDbbVQVWdXV1TfLhtrl+gL6QplqnLQ3rtXlgOwIA0PgYQw0A4DLq6uo0d+5c/e1vf9Orr76qLl262E0PDw+Xl5eX8vPzjdv279+vsrIyRUZGSpIiIyO1d+9euzAsLy9PPj4+CgkJMWoKCgrsHjsvL894DG9vb/Xs2dNuPrW1tcrPz1dUVFRDLjIAAAAAN0SgBgBwGSkpKXrrrbe0aNEiXX/99SovL1d5eblOnz4tSWrbtq0SEhKUnp6ugoICFRcXa8aMGYqKijLCMIvFopCQECUnJ2v37t3avn27Fi9erMTERHl7e0uSRo4cqQMHDmjhwoXat2+fsrOztXXrVo0ePdroZcyYMVq/fr02bdqkffv2ac6cOTp16pSGDRvW1KsFAAAAgIvhJ58AAJfx2muvSZIeffRRu9vT0tKMIGvGjBkym82aPHmyKisrZbFYNHv2bKPWw8NDy5Yt05w5czRixAi1adNGQ4cO1eTJk42aLl26aPny5UpLS1NWVpY6duyo+fPnKy4uzqgZNGiQjhw5oiVLlqi8vFxhYWFauXJlixmjDAAAAMDFEagBAFzGnj17LlvTqlUrzZ492y5E+7FOnTppxYoVl3yc6Oho5ebmXrImKSlJSUlJl+0JAAAAQMvCTz4BAAAAAAAABxCoAQAAAAAAAA4gUAMAAAAAAAAc4HCg9sknn+iJJ56QxWJRjx499N5779lNnz59unr06GF3GTt2rF3NDz/8oKlTp6pPnz7q27evZsyYoRMnTtjV7N69W4888ogiIiIUHx9/wbFwtm7dqvvvv18REREaMmSItm3b5ujiAAAAAAAAAA5xOFA7efKkevToccnBoOPi4rRjxw7j8uKLL9pNf/bZZ1VaWqrMzEwtW7ZMn376qWbNmmVMr6io0NixYxUUFKSNGzcqOTlZL7/8sl5//XWj5vPPP9fUqVP1i1/8Qrm5ubrnnns0ceJE7d2719FFAgAAAAAAAK6Yw2f5jI+PV3x8/CVrvL29FRAQcMFp+/bt0/bt2/XGG28oIiJCkjRz5kyNGzdOycnJCgwM1FtvvaWqqiqlpqbK29tb3bp1U0lJiTIzMzVixAhJUlZWluLi4vT4449Lkp566inl5eVp7dq1mjt3rkPLZDKZHKpvaq7en7szmUys4xbo3DZn2zcs1icAAACAlsDhQO1KfPzxx4qJiVG7du1055136qmnntKNN94oSSosLFS7du2MME2SYmNjZTabtXPnTvXv319FRUXq27evvL29jRqLxaIVK1bo6NGj8vX1VVFRkUaPHm03X4vFUu8nqFciMDDw6hYUzYK/v7+zW4AT8foHAAAAADiqwQO1uLg49e/fX507d9aBAwf04osv6le/+pVef/11eXh4yGq1qn379vZNeHrK19dX5eXlkiSr1arOnTvb1ZwLPaxWq3x9fWW1WusFIX5+frJarQ73fOjQIdXV1Tl8v6bi6elJ6NOIrFarqqurnd0GmpjJZFJgYKDLv/7dzbn1CgAAAADNWYMHaoMHDzb+PndSgnvvvdc4as0V1dXVufQHalfurTlw9e2PxsX2BwAAAAA4yuGTEjiqS5cuuvHGG/XNN99IOnuk2ZEjR+xqqqurdfToUWPcNX9//3pHmp27fu5IrQvV2Gw2juQCAAAAAABAo2r0QO3777/XDz/8YIRlUVFROnbsmIqLi42agoIC1dbWqlevXpKkyMhIffrpp6qqqjJq8vLy1LVrV/n6+ho1BQUFdvPKy8tTZGRkIy8RAAAAAAAAWjKHA7UTJ06opKREJSUlkqSDBw+qpKREZWVlOnHihBYsWKCioiIdPHhQ+fn5mjBhgm655RbFxcVJkoKDgxUXF6ff/va32rlzpz777DPNmzdPgwcPNsbdGTJkiLy8vPT888/ryy+/1JYtW5SVlaUxY8YYfYwaNUrbt2/XK6+8on379umll15ScXGxkpKSGmK9AAAAAAAAABfk8BhqxcXFGjVqlHE9LS1NkjR06FDNmTNHe/fuVW5uro4fP64OHTrorrvu0pQpU+zO2JmRkaF58+bpsccek9ls1n333aeZM2ca09u2batVq1Zp7ty5GjZsmG688UZNmDBBI0aMMGr69OmjjIwMLV68WC+++KJuvfVWLV26VN27d7+qFQEAAAAAAABcCYcDtejoaO3Zs+ei01etWnXZx7jhhhu0aNGiS9aEhoZq3bp1l6wZOHCgBg4ceNn5AQAAAAAAAA2l0cdQAwAAAAAAAJoTAjUAAAAAAADAAQRqAAAAAAAAgAMI1AAAAAAAAAAHEKgBAAAAAAAADiBQAwAAAAAAABxAoAYAAAAAAAA4gEANAAAAAAAAcACBGgAAAAAAAOAAAjUAAAAAAADAAQRqAAAAAAAAgAMI1AAAAAC0GJ988omeeOIJWSwW9ejRQ++9957d9Lq6Ov3+97+XxWJRr169NHr0aH399dd2NT/88IOmTp2qPn36qG/fvpoxY4ZOnDhhV7N792498sgjioiIUHx8vFasWFGvl61bt+r+++9XRESEhgwZom3btjX48gIAGgeBGgAAAIAW4+TJk+rRo4dmz559wekrVqzQmjVrNGfOHK1fv15t2rTR2LFjdebMGaPm2WefVWlpqTIzM7Vs2TJ9+umnmjVrljG9oqJCY8eOVVBQkDZu3Kjk5GS9/PLLev31142azz//XFOnTtUvfvEL5ebm6p577tHEiRO1d+/exlt4AECD8XR2AwAAAADQVOLj4xUfH3/BaXV1dcrKytKvf/1r3XvvvZKkhQsXKjY2Vu+9954GDx6sffv2afv27XrjjTcUEREhSZo5c6bGjRun5ORkBQYG6q233lJVVZVSU1Pl7e2tbt26qaSkRJmZmRoxYoQkKSsrS3FxcXr88cclSU899ZTy8vK0du1azZ0716FlMplMV7s6mow79OiuTCYT67cBsS4bjzs8Vx3pj0ANAAAAACQdPHhQ5eXlio2NNW5r27atevfurcLCQg0ePFiFhYVq166dEaZJUmxsrMxms3bu3Kn+/furqKhIffv2lbe3t1FjsVi0YsUKHT16VL6+vioqKtLo0aPt5m+xWOr9BPVKBAYGOr6waDb8/f2d3QJwRZrbc5VADQAAAAAklZeXS5L8/Pzsbvfz85PVapUkWa1WtW/f3m66p6enfH19jftbrVZ17tzZrubcB0mr1SpfX19ZrdZ6Hy7Pn48jDh06pLq6Oofv15Q8PT2b3YdpV2G1WlVdXe3sNpoNnquNxx2eqyaT6Yq/pCBQAwAAAAA3VldX5/KBmqv3587cYfu7E9Zl42luz1VOSgAAAAAAkgICAiRJNpvN7nabzWYcseLv768jR47YTa+urtbRo0eN+/v7+9c70uzc9fMf58c1588HAODaCNQAAAAAQFLnzp0VEBCg/Px847aKigp98cUXioqKkiRFRUXp2LFjKi4uNmoKCgpUW1urXr16SZIiIyP16aefqqqqyqjJy8tT165d5evra9QUFBTYzT8vL0+RkZGNtXgAgAZEoAYAAACgxThx4oRKSkpUUlIi6eyJCEpKSlRWViaTyaRRo0bpj3/8o95//33t2bNHycnJ6tChg3HWz+DgYMXFxem3v/2tdu7cqc8++0zz5s3T4MGDjXF3hgwZIi8vLz3//PP68ssvtWXLFmVlZWnMmDFGH6NGjdL27dv1yiuvaN++fXrppZdUXFyspKSkpl8pAACHMYYaAAAAgBajuLhYo0aNMq6npaVJkoYOHar09HT96le/0qlTpzRr1iwdO3ZMd9xxh1auXKlWrVoZ98nIyNC8efP02GOPyWw267777tPMmTON6W3bttWqVas0d+5cDRs2TDfeeKMmTJigESNGGDV9+vRRRkaGFi9erBdffFG33nqrli5dqu7duzfBWgAAXCsCNQAAAAAtRnR0tPbs2XPR6SaTSVOmTNGUKVMuWnPDDTdo0aJFl5xPaGio1q1bd8magQMHauDAgZduGADgkvjJJwAAAAAAAOAAAjUAAAAAAADAAQRqAAAAAAAAgAMI1AAAAAAAAAAHEKgBAAAAAAAADiBQAwAAAAAAABxAoAYAAAAAAAA4gEANAAAAAAAAcIDDgdonn3yiJ554QhaLRT169NB7771nN72urk6///3vZbFY1KtXL40ePVpff/21Xc0PP/ygqVOnqk+fPurbt69mzJihEydO2NXs3r1bjzzyiCIiIhQfH68VK1bU62Xr1q26//77FRERoSFDhmjbtm2OLg4AAAAAAADgEIcDtZMnT6pHjx6aPXv2BaevWLFCa9as0Zw5c7R+/Xq1adNGY8eO1ZkzZ4yaZ599VqWlpcrMzNSyZcv06aefatasWcb0iooKjR07VkFBQdq4caOSk5P18ssv6/XXXzdqPv/8c02dOlW/+MUvlJubq3vuuUcTJ07U3r17HV0kAAAAAAAA4Io5HKjFx8fr6aefVv/+/etNq6urU1ZWln7961/r3nvvVWhoqBYuXKjDhw8bR7Lt27dP27dv1/z589W7d2/17dtXM2fO1DvvvKNDhw5Jkt566y1VVVUpNTVV3bp10+DBg/Xoo48qMzPTmFdWVpbi4uL0+OOPKzg4WE899ZRuv/12rV279mrXBQAAAAAAAHBZDTqG2sGDB1VeXq7Y2FjjtrZt26p3794qLCyUJBUWFqpdu3aKiIgwamJjY2U2m7Vz505JUlFRkfr27Stvb2+jxmKx6KuvvtLRo0eNmpiYGLv5WywWFRUVOdy3yWRy+Qsaj7O3LRfnvq6c3UNzvAAAAABAc+fZkA9WXl4uSfLz87O73c/PT1arVZJktVrVvn17+yY8PeXr62vc32q1qnPnznY1/v7+xjRfX19ZrVbjtgvNxxGBgYEO3wfNx4+fR2hZeP0DAAAAABzVoIGauzp06JDq6uqc3cZFeXp6Evo0IqvVqurqame3gSZmMpkUGBjo8q9/d3NuvQIAAABAc9aggVpAQIAkyWazqUOHDsbtNptNoaGhks4eDXTkyBG7+1VXV+vo0aPG/f39/esdaXbu+rlg6UI1NpvtqoKnuro6l/5A7cq9NQeuvv3RuNj+AAAAAABHNegYap07d1ZAQIDy8/ON2yoqKvTFF18oKipKkhQVFaVjx46puLjYqCkoKFBtba169eolSYqMjNSnn36qqqoqoyYvL09du3aVr6+vUVNQUGA3/7y8PEVGRjbkIgEAAAAAAAB2HA7UTpw4oZKSEpWUlEg6eyKCkpISlZWVyWQyadSoUfrjH/+o999/X3v27FFycrI6dOige++9V5IUHBysuLg4/fa3v9XOnTv12Wefad68eRo8eLDxM6EhQ4bIy8tLzz//vL788ktt2bJFWVlZGjNmjNHHqFGjtH37dr3yyivat2+fXnrpJRUXFyspKakh1gsAAAAAAABwQQ7/5LO4uFijRo0yrqelpUmShg4dqvT0dP3qV7/SqVOnNGvWLB07dkx33HGHVq5cqVatWhn3ycjI0Lx58/TYY4/JbDbrvvvu08yZM43pbdu21apVqzR37lwNGzZMN954oyZMmKARI0YYNX369FFGRoYWL16sF198UbfeequWLl2q7t27X9WKAAAAAAAAAK6Ew4FadHS09uzZc9HpJpNJU6ZM0ZQpUy5ac8MNN2jRokWXnE9oaKjWrVt3yZqBAwdq4MCBl24YAAAAAAAAaEANOoYaAAAAAAAA0NwRqAEAAAAAAAAOIFADAAAAAAAAHECgBgBwKZ988omeeOIJWSwW9ejRQ++9957d9Lq6Ov3+97+XxWJRr169NHr0aH399dd2NT/88IOmTp2qPn36qG/fvpoxY4ZOnDhhV7N792498sgjioiIUHx8vFasWFGvl61bt+r+++9XRESEhgwZom3btjX48gIAAABwPwRqAACXcvLkSfXo0UOzZ8++4PQVK1ZozZo1mjNnjtavX682bdpo7NixOnPmjFHz7LPPqrS0VJmZmVq2bJk+/fRTzZo1y5heUVGhsWPHKigoSBs3blRycrJefvllvf7660bN559/rqlTp+oXv/iFcnNzdc8992jixInau3dv4y08AAAAALdAoAYAcCnx8fF6+umn1b9//3rT6urqlJWVpV//+te69957FRoaqoULF+rw4cPGkWz79u3T9u3bNX/+fPXu3Vt9+/bVzJkz9c477+jQoUOSpLfeektVVVVKTU1Vt27dNHjwYD366KPKzMw05pWVlaW4uDg9/vjjCg4O1lNPPaXbb79da9eubZoVAQAAAMBlEagBANzGwYMHVV5ertjYWOO2tm3bqnfv3iosLJQkFRYWql27doqIiDBqYmNjZTabtXPnTklSUVGR+vbtK29vb6PGYrHoq6++0tGjR42amJgYu/lbLBYVFRU53LfJZGqyS0vRlOu0pVxYr83j0hK2IwAArsDT2Q0AAHClysvLJUl+fn52t/v5+clqtUqSrFar2rdvbzfd09NTvr6+xv2tVqs6d+5sV+Pv729M8/X1ldVqNW670HwcERgY6PB9cGk/3jZoGDxXmwe2IwAAjY9ADQCARnbo0CHV1dU1+nw8PT1bTNBktVpVXV3t7DaaDZPJpMDAwCZ7rqJxtITteG4ZAQBwNgI1AIDbCAgIkCTZbDZ16NDBuN1msyk0NFTS2SOXjhw5Yne/6upqHT161Li/v79/vSPNzl0/F0hdqMZms11VYFVXV9ckH26b6wfoC2mqddrSsF6bB7YjAACNjzHUAABuo3PnzgoICFB+fr5xW0VFhb744gtFRUVJkqKionTs2DEVFxcbNQUFBaqtrVWvXr0kSZGRkfr0009VVVVl1OTl5alr167y9fU1agoKCuzmn5eXp8jIyMZaPAAAAABugkANAOBSTpw4oZKSEpWUlEg6eyKCkpISlZWVyWQyadSoUfrjH/+o999/X3v27FFycrI6dOige++9V5IUHBysuLg4/fa3v9XOnTv12Wefad68eRo8eLDxM6EhQ4bIy8tLzz//vL788ktt2bJFWVlZGjNmjNHHqFGjtH37dr3yyivat2+fXnrpJRUXFyspKanpVwoAAAAAl8JPPgEALqW4uFijRo0yrqelpUmShg4dqvT0dP3qV7/SqVOnNGvWLB07dkx33HGHVq5cqVatWhn3ycjI0Lx58/TYY4/JbDbrvvvu08yZM43pbdu21apVqzR37lwNGzZMN954oyZMmKARI0YYNX369FFGRoYWL16sF198UbfeequWLl2q7t27N8FaAAAAAODKCNQAAC4lOjpae/bsueh0k8mkKVOmaMqUKRetueGGG7Ro0aJLzic0NFTr1q27ZM3AgQM1cODASzcMAAAAoMXhJ58AAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACNQAAAAA4z0svvaQePXrYXe6//35j+pkzZ5SSkqLo6GhFRUXpySeflNVqtXuMsrIyjRs3Tr1791ZMTIwWLFig6upqu5qPPvpIQ4cOVXh4uPr376+NGzc2yfIBAK6dp7MbAAAAAABX061bN2VmZhrXPTw8jL9TU1O1bds2LV68WG3bttW8efM0adIk5eTkSJJqamo0fvx4+fv7KycnR4cPH9a0adPk5eWlZ555RpJ04MABjR8/XiNHjlRGRoby8/M1c+ZMBQQEKC4urmkXFgDgMAI1AAAAAPgRDw8PBQQE1Lv9+PHj2rBhgzIyMhQTEyPpbMA2aNAgFRUVKTIyUjt27FBpaakyMzPl7++vsLAwTZkyRRkZGZo0aZK8vb2Vk5Ojzp07a/r06ZKk4OBgffbZZ1q9erXDgZrJZLr2BW5k7tCjuzKZTKzfBsS6bDzu8Fx1pD8CNQAAAAD4kW+++UYWi0WtWrVSZGSkpk6dqqCgIBUXF6uqqkqxsbFGbXBwsIKCgoxAraioSN27d5e/v79RY7FYNGfOHJWWlur2229XUVGREcidX5Oamupwr4GBgVe/oHB75z/PAFfW3J6rBGoAAAAAcJ5evXopLS1NXbt2VXl5uZYuXarExERt3rxZVqtVXl5eateund19/Pz8VF5eLkmyWq31Pjieu365moqKCp0+fVqtW7e+4n4PHTqkuro6h5ezKXl6eja7D9Ouwmq11hufD1eP52rjcYfnqslkuuIvKQjUAAAAAOA88fHxxt+hoaHq3bu37r77bm3dutWhoKup1NXVuXyg5ur9uTN32P7uhHXZeJrbc5WzfAIAAADAJbRr10633nqrvv32W/n7+6uqqkrHjh2zq7HZbMaYa/7+/vXO+nnu+uVqfHx8XDK0AwDYI1ADAAAAgEs4ceKEDhw4oICAAIWHh8vLy0v5+fnG9P3796usrEyRkZGSpMjISO3du1c2m82oycvLk4+Pj0JCQoyagoICu/nk5eUZjwEAcG0EagAAAABwngULFujjjz/WwYMH9fnnn2vSpEkym8164IEH1LZtWyUkJCg9PV0FBQUqLi7WjBkzFBUVZYRhFotFISEhSk5O1u7du7V9+3YtXrxYiYmJ8vb2liSNHDlSBw4c0MKFC7Vv3z5lZ2dr69atGj16tPMWHABwxRo8UHvppZfUo0cPu8v9999vTD9z5oxSUlIUHR2tqKgoPfnkk/UOdS4rK9O4cePUu3dvxcTEaMGCBfUGrvvoo480dOhQhYeHq3///tq4cWNDLwoAAACAFuj777/XM888o/vvv19PPfWUbrjhBq1fv17t27eXJM2YMUM/+9nPNHnyZCUlJcnf318vvfSScX8PDw8tW7ZMZrNZI0aM0HPPPaeHHnpIkydPNmq6dOmi5cuXKy8vTz//+c+VmZmp+fPnKy4ursmXFwDguEY5KUG3bt2UmZlpXPfw8DD+Tk1N1bZt27R48WK1bdtW8+bN06RJk5STkyNJqqmp0fjx4+Xv76+cnBwdPnxY06ZNk5eXl5555hlJ0oEDBzR+/HiNHDlSGRkZys/P18yZMxUQEMAOCAAAAMA1+d3vfnfJ6a1atdLs2bM1e/bsi9Z06tRJK1asuOTjREdHKzc392paBAA4WaMEah4eHsZgm+c7fvy4NmzYoIyMDMXExEg6G7ANGjRIRUVFioyM1I4dO1RaWqrMzEz5+/srLCxMU6ZMUUZGhiZNmiRvb2/l5OSoc+fOmj59uiQpODhYn332mVavXk2gBgAAAAAAgEbVKGOoffPNN7JYLLrnnns0depUlZWVSZKKi4tVVVWl2NhYozY4OFhBQUEqKiqSJBUVFal79+7y9/c3aiwWiyoqKlRaWmrUnAvkzq859xiOMplMLn9B43H2tuXi3NeVs3tojhcAAAAAaO4a/Ai1Xr16KS0tTV27dlV5ebmWLl2qxMREbd68WVarVV5eXmrXrp3dffz8/FReXi7p7Kmizw/TJBnXL1dTUVGh06dPO3ya6cDAQIfq0bz8+LmEloXXPwAAAADAUQ0eqMXHxxt/h4aGqnfv3rr77ru1detWh4OupnLo0CHV1dU5u42L8vT0JPRpRFartd5JL9D8mUwmBQYGuvzr392cW68AAAAA0Jw1yhhq52vXrp1uvfVWffvtt4qNjVVVVZWOHTtmd5SazWYzxlzz9/fXzp077R7j3FlAz6/58ZlBrVarfHx8riq0q6urc+kP1K7cW3Pg6tsfjYvtD8AVmc1mmc2NMjLHBZ37ubanp2eTvSfW1taqtra2SeYFAADQ0Bo9UDtx4oQOHDiggIAAhYeHy8vLS/n5+RowYIAkaf/+/SorK1NkZKQkKTIyUsuWLZPNZpOfn58kKS8vTz4+PgoJCTFq/vGPf9jNJy8vz3gMAAAAd2U2m+Xn5ydPz0b/N62epjwivrq6WjabjVANAAC4pQb/T23BggW6++67FRQUpMOHD+ull16S2WzWAw88oLZt2yohIUHp6eny9fWVj4+P5s+fr6ioKCMMs1gsCgkJUXJysp577jmVl5dr8eLFSkxMlLe3tyRp5MiRys7O1sKFC5WQkKCCggJt3bpVy5cvb+jFAQAAaFJms1menp5KTExUSUmJs9tpFGFhYcrOzpbZbCZQAwAAbqnBA7Xvv/9ezzzzjH744Qe1b99ed9xxh9avX6/27dtLkmbMmCGz2azJkyersrJSFotFs2fPNu7v4eGhZcuWac6cORoxYoTatGmjoUOHavLkyUZNly5dtHz5cqWlpSkrK0sdO3bU/PnzFRcX19CLAwAA4BQlJSUqLCx0dhsAAAC4gAYP1H73u99dcnqrVq00e/ZsuxDtxzp16qQVK1Zc8nGio6OVm5t7NS0CAAAAAAAAV63pRrsFAAAAAAAAmgECNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAcQqAEAAAAAAAAOIFADAAAAAAAAHECgBgAAAAAAADiAQA0AAAAAAABwAIEaAAAAAAAA4AACNQAAAAAAAMABBGoAAAAAAACAAwjUAAAAAAAAAAd4OrsBAM2L2WyW2ez6Wb3JZJIkeXp6qq6uzsndXF5tba1qa2ud3QYAAAAAQARqABqQ2WyWn5+fPD3d563F39/f2S1ckerqatlsNkI1AAAAAHAB7vOpF4DLM5vN8vT0VGJiokpKSpzdTrMRFham7Oxsmc1mAjUAAAAAcAEEagAaXElJiQoLC53dBgAAAAAAjYJADQAAAGgETT2uqDPGB2WMTwBAS0WgBgAAADQwZ44r2pTjgzLGJwCgpSJQAwAAABpYSxhXlDE+AQAtGYEaAPz/7d1faNX1H8fx1znJMMyL9ifJicHMmm1nbYHQRhaptVocm1bD4WEgE1kMJsbYYSSaEM00d6G0xgqW/1rh1k7EsoSoTeRgRJ0WA6GZM02nblktco3c6WJ4/J2fm+7s7JzP+X73fIAXOx+QF9vnc16c9znn+wUAIEa4rigAAPYUv4s6AAAAAAAAADbAQA0AAAAAAACIAAM1AAAAAAAAIAKWH6gdOnRIy5cvl8vl0ksvvaTu7m7TkQAANkLPAABija4BAOux9EDts88+U11dnSorK9Xe3q7MzEyVl5drcHDQdDQAgA3QMwCAWKNrAMCaLH2Xz+bmZpWUlOiFF16QJG3fvl1ff/212tratHHjxkn/P06nU8FgMFYxo+Z0js09H3nkEc2ZM8dwGvt48MEHJY39fq//jhEd9mpsWGmvOhwO0xGmldV6ZiacQSudh6ni72gP/B1jw249I01P1yT66xlpZpyJeJsJz6UmsFenn5X2aiQ94wgm+jPvBEZGRpSbm6s9e/Zo5cqVoce9Xq/+/PNPvfPOOwbTAQCsjp4BAMQaXQMA1pXYo8FbuHLliq5du6aUlJSwx1NSUjQwMGAoFQDALugZAECs0TUAYF2WHagBAAAAAAAAJlh2oHb33XfrjjvuuOlinYODg0pNTTWUCgBgF/QMACDW6BoAsC7LDtSSkpKUlZUlv98femx0dFR+v195eXkGkwEA7ICeAQDEGl0DANZl6bt8rl+/Xl6vV9nZ2crJydG+fft09epVrVmzxnQ0AIAN0DMAgFijawDAmiw9UCsqKtJvv/2mPXv26PLly1qyZInee+89Ph4NAJgW9AwAINboGgCwJkcwGAyaDgEAAAAAAABYhWWvoQYAAAAAAACYwEANAAAAAAAAiAADNQAAAAAAACACDNQAAAAAAACACDBQAwAAAAAAACLAQA0AAAAAAEkjIyMaGRkxHQO4LfaqebNMB4C19fb26uDBgwoEAhoYGJAkpaamKjc3Vx6PR/fff7/hhMD4rpdPUlKS4SSAdXGOrIv+BoAbjh8/rvfff1+BQEB//fWXJOmuu+5Sbm6u1q9fr4KCAsMJgTHs1cTiCAaDQdMhYE2dnZ2qrKxUVlaWHnvsMaWkpEiSBgcHdfz4cfX09KihoUHLli0znBQYQwEB0eMcWR/9bR8MRoHotbe3a8uWLSosLBz3OfGLL77Q66+/ruLiYrNBMeOxVxMPAzVM2apVq7RixQpt2rRp3PW9e/fq6NGj+vTTT+OcDLgZBQREj3NkD/S3PTAYBaZHYWGhysrKtG7dunHXDx06pH379uno0aNxTgaEY68mHgZqmLKcnBz5fD5lZGSMu/7zzz+ruLhY3d3dcU4G3IwCAqLHObIH+tseGIwC08PlcumTTz7hOREJj72aeLgpAaYsPT1dnZ2dE653dnZq/vz5cUwETOz8+fPKz8+fcD0/P1/9/f1xTARYD+fIHuhve+jr65Pb7Z5w/bnnntOZM2fimAiwpsWLF6u1tXXC9ba2Nr4+jYTAXk083JQAU1ZVVaXq6mqdOHFCBQUFSk1NlSQNDAzI7/fr2LFj2r17t+GUwJjrBVRTUzPuOgUE3B7nyB7ob3u4Phid6JMKDEaByfF6vaqoqNCxY8dUUFAQ9vVpv9+vs2fPqqmpyXBKgL2aiPjKJ6Ly3Xff6cCBAwoEArp8+bIkKS0tTbm5uSorK1NeXp7hhMCYEydOqKKiQgsWLLhlAS1dutRwUiBxcY7sg/62viNHjqi6ulrLli275WC0sLDQcFIg8Z07d04tLS364YcfbnpOXLt2rRYsWGA4ITCGvZpYGKgBmDEoICB6nCMgcTAYBQDAHAZqAAAAAAAAQAS4KQFipr6+XrW1taZjAACACNDfAHCD1+tVWVmZ6RjAbbFX44+BGmLm4sWL+vXXX03HACaFAgKixzmyB/rbHhiMAtNj3rx5Sk9PNx0DuC32avxxl0/EzJtvvmk6AjBp99xzj5xO3mMAosE5sgf62x76+/vV399vOgZgea+88orpCMCksFfjj2uoAQAAAAAAABHgbWREZXh4WN9++616e3tvWvvnn3/k8/niHwqYggsXLvDVGCBKnCProL/t4dSpU2pra9OpU6dCP2/btk21tbXy+/2G0wHW0NPTo7Nnz4Z+9vl8Wrt2rZ544gmVlpaqo6PDYDog3MGDB1VTUxPalz6fT0VFRXrmmWdUX1+vf//913DCmYWBGqbs9OnTKioqksfjkdvtlsfj0aVLl0LrQ0NDvLCCZfzxxx+8gASixDmyBvrbHrq6uvT8889r586dWr16tbq6uuTxePTLL7/o/PnzKi8vZ6gGTEJtbW1ooHb48GFt27ZN2dnZqqiokMvl0pYtW9Ta2mo4JSA1NDSovr5ew8PDqqurU1NTk+rq6uR2u7V69WodPnxYDQ0NpmPOKFxDDVP21ltvafHixWptbdXQ0JDeeOMNlZaW6sCBA5o/f77peECYL7/88pbr//vOJIDxcY7sgf62h4aGBpWXl2vz5s3q6OhQdXW1SktLtXnzZknS7t279e677yo/P99wUiCxnTlzRvfdd58k6YMPPtCrr76qkpKS0LrL5VJjY6NefPFFUxEBSVJ7e7t27Nihp59+WidPntSaNWu0Y8cOrVq1SpKUkZGhXbt2qaqqynDSmYOBGqbs+++/V3Nzs5KTk5WcnKzGxka99tprWrdunfbv368777zTdEQgpLKyUg6HQ7e6bKTD4YhjIsB6OEf2QH/bw08//RS6gcSzzz6rmpoaFRYWhtbdbrc+/vhjU/EAy5g9e7auXLmi9PR0Xbx4UTk5OWHrDz/8sM6dO2coHXDDpUuXlJ2dLUnKzMyU0+nUkiVLQusPPfRQ2CfOEXt85RNTNjw8rFmzbsxkHQ6Htm/frieffFIej0d9fX3mwgH/Jy0tTXv37tXJkyfH/dfe3m46IpDwOEf2QH/bx/UBttPpVFJSkubOnRtamzNnjoaGhkxFAyzj8ccfV0tLiyRp6dKl+vzzz8PWjxw5ooULF5qIBoRJTU0NXfu0r69P165dC7sWam9vr5KTk03Fm5H4hBqmLCMjQz/++KMWLVoU9vjWrVslSS+//LKJWMC4srKy1NPTo5UrV467frtP3QDgHNkF/W0P6enp6uvrC73Q/+ijj3TvvfeG1i9cuKC0tDRT8QDLuP51aY/Ho+zsbDU3N+ubb77RokWLdPr0aQUCAb399tumYwJyu93yer1asWKF/H6/NmzYoJ07d+r333+Xw+FQY2Nj2CeVEXsM1DBlTz31lDo6OlRcXHzT2tatWzU6OqoPP/ww/sGAcWzYsEF///33hOsLFy7U/v3745gIsB7OkT3Q3/ZQWlqq0dHR0M8PPPBA2HpXV5ceffTReMcCLGfevHny+XxqamrSV199pWAwqO7ubvX39ysvL08tLS1yuVymYwKqqqrS7NmzFQgEVFJSoo0bNyozM1O7du3S1atXtXz5cm3atMl0zBnFEeStZAAAAAAAAGDSuIYaAAAAAAAAEAEGagAAAAAAAEAEGKgBAAAAAAAAEWCgBgAAAAAAAESAgRoAAAAAAAAQAQZqAAAAAAAAQAQYqAEAAAAAAAAR+A/wlUj2a0ZXVwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1500x1000 with 6 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(nrows=2, ncols=3, figsize=(15, 10))\n",
    "fig.suptitle(\"Feature Bar Plots\")\n",
    "\n",
    "fts = range(len(shortlist_fts.index.tolist()))\n",
    "for i, ax in zip(fts, axs.ravel()):\n",
    "    df[shortlist_fts.index.tolist()[i]].value_counts().plot.bar(color=\"black\", ax=ax)\n",
    "    ax.set_title(shortlist_fts.index.tolist()[i])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.2 <a name=\"22\">Select features to build the model</a>\n",
    "(<a href=\"#2\">Go to Data Processing</a>)\n",
    "\n",
    "During the extended EDA in the DATAPREP notebook, we learned that `GCL` is a feature that is equally present for both outcome types and also contains a lot of missing values. Therefore, we can drop it from the list of features we want to use for model build. We also drop `OCCP` and `POBP` as those features have too many unique categories."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "to_remove = [\"GCL\", \"OCCP\", \"POBP\"]\n",
    "\n",
    "# Drop to_remove features from the respective list(s) - if applicable\n",
    "for ft in to_remove:\n",
    "    if ft in model_features:\n",
    "        model_features.remove(ft)\n",
    "    if ft in categorical_features:\n",
    "        categorical_features.remove(ft)\n",
    "    if ft in numerical_features:\n",
    "        numerical_features.remove(ft)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Let's also clean up the dataframe and only keep the features and columns we need\n",
    "df = df[model_features + [model_target]].copy(deep=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.3 <a name=\"23\">Feature transformation</a>\n",
    "(<a href=\"#2\">Go to Data Processing</a>)\n",
    "\n",
    "In the paper [Certifying and Removing Disparate Impact](https://arxiv.org/pdf/1412.3756.pdf) a definition for Disparate Impact was introduced as the ratio of probability of positive outcomes for the disfavored group $(A=0)$ to probability of positive outcomes for the favored group $(A=1)$:  \n",
    "\n",
    "$\\large DI = \\frac{Pr(Y=y|A=0)}{Pr(Y=y|A=1)}$\n",
    "    \n",
    "\n",
    "To be 'disparate impact free' the value calculated with the above equation needs to be $>$0.8."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Create a Dataset construct for AIF360\n",
    "binaryLabelDataset = BinaryLabelDataset(\n",
    "    df=df,\n",
    "    label_names=[\">50k\"],\n",
    "    protected_attribute_names=[\"RAC1P\"],\n",
    "    favorable_label=1.0,\n",
    "    unfavorable_label=0.0,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# We need to declare what the attribute value of the (un)privileged group is\n",
    "priv_group = [{\"RAC1P\": 6}]\n",
    "unpriv_group = [{\"RAC1P\": 8}]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's calculate the disparate impact (DI) value with the __AIF360__ inbuilt method `BinaryLabelDatasetMetric()`. You need to pass the data frame into the metric and then you can calculate DI by using `.disparate_impact()`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.4042999944218583\n"
     ]
    }
   ],
   "source": [
    "# Let's look at the DI value\n",
    "print(\n",
    "    BinaryLabelDatasetMetric(\n",
    "        binaryLabelDataset,\n",
    "        unprivileged_groups=unpriv_group,\n",
    "        privileged_groups=priv_group,\n",
    "    ).disparate_impact()\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.4 <a name=\"24\">Train - Validation - Test Datasets</a>\n",
    "(<a href=\"#2\">Go to Data Processing</a>)\n",
    "\n",
    "To get a training, test and validation set, we will use sklearn's [train_test_split()](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) function. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train - Test - Validation datasets shapes:  (42458, 11) (5551, 11) (7493, 11)\n"
     ]
    }
   ],
   "source": [
    "train_data, test_data = train_test_split(\n",
    "    df, test_size=0.1, shuffle=True, random_state=23\n",
    ")\n",
    "\n",
    "train_data, val_data = train_test_split(\n",
    "    train_data, test_size=0.15, shuffle=True, random_state=23\n",
    ")\n",
    "\n",
    "# Print the shapes of the Train - Test Datasets\n",
    "print(\n",
    "    \"Train - Test - Validation datasets shapes: \",\n",
    "    train_data.shape,\n",
    "    test_data.shape,\n",
    "    val_data.shape,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2.5 <a name=\"25\">Data processing with Pipeline and ColumnTransformer</a>\n",
    "(<a href=\"#2\">Go to Data Processing</a>)\n",
    "\n",
    "Let's build a data processing pipeline. We need pre-processing split per data type, and then combine everything back into a composite pipeline. To achieve this, we will use sklearns `Pipeline` and `ColumnTransformer`.\n",
    "\n",
    "__Step 1 (set up pre-processing per data type):__\n",
    "> For the numerical features pipeline, the __numerical_processor__ below, we impute missing values with the mean using sklearn's `SimpleImputer`, followed by a `MinMaxScaler` (don't have to scale features when using Decision Trees, but it's a good idea to see how to use more data transforms). If different processing is desired for different numerical features, different pipelines should be built - just like shown below for the two text features.\n",
    "\n",
    " > In the categorical features pipeline, the __categorical_processor__ below, we impute with a placeholder value and encode with sklearn's `OneHotEncoder`. If computing memory is an issue, it is a good idea to check categoricals' unique values, to get an estimate of many dummy features will be created by one-hot encoding. Note the __handle_unknown__ parameter that tells the encoder to ignore (rather than throw an error for) any unique value that might show in the validation/and or test set that was not present in the initial training set.\n",
    " \n",
    "__Step 2 (combining pre-processing methods into a transformer):__ \n",
    " > The selective preparations of the dataset features are then put together into a collective `ColumnTransformer`, to be finally used in a Pipeline along with an estimator. This ensures that the transforms are performed automatically on the raw data when fitting the model and when making predictions, such as when evaluating the model on a validation dataset via cross-validation or making predictions on a test dataset in the future.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "### STEP 1 ###\n",
    "##############\n",
    "\n",
    "# Preprocess the numerical features\n",
    "numerical_processor = Pipeline(\n",
    "    [(\"num_imputer\", SimpleImputer(strategy=\"mean\")), (\"num_scaler\", MinMaxScaler())]\n",
    ")\n",
    "# Preprocess the categorical features\n",
    "categorical_processor = Pipeline(\n",
    "    [\n",
    "        (\"cat_imputer\", SimpleImputer(strategy=\"constant\", fill_value=\"missing\")),\n",
    "        (\"cat_encoder\", OneHotEncoder(handle_unknown=\"ignore\")),\n",
    "    ]\n",
    ")\n",
    "\n",
    "### STEP 2 ###\n",
    "##############\n",
    "\n",
    "# Combine all data preprocessors from above\n",
    "data_processor = ColumnTransformer(\n",
    "    [\n",
    "        (\"numerical_processing\", numerical_processor, numerical_features),\n",
    "        (\"categorical_processing\", categorical_processor, categorical_features),\n",
    "    ],\n",
    "    remainder=\"drop\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "Now, we want to use the data processing pipeline to prepare the data before we perform the DI removal."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Learn the transformation & extract feature names\n",
    "data_processor.fit(train_data)\n",
    "\n",
    "# To extract feature names we first need to fit the data processor as this will generate the one hot encoding\n",
    "ft_names = numerical_features + list(\n",
    "    data_processor.transformers_[1][1]\n",
    "    .named_steps[\"cat_encoder\"]\n",
    "    .get_feature_names(categorical_features)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def data_prep(data, fitted_transformation, feature_names):\n",
    "    \"\"\"\n",
    "    Function to create an AIF360 dataset based on processed data\n",
    "    \"\"\"\n",
    "    # We join the encoded data with the target and sensitive attribute to create a new AIF360 dataset\n",
    "    prep = np.concatenate(\n",
    "        (\n",
    "            fitted_transformation.transform(data).todense(),\n",
    "            data[[model_target]].values,\n",
    "            data[[sensitive_attribute]].values,\n",
    "        ),\n",
    "        axis=1,\n",
    "    )\n",
    "\n",
    "    # Add column names and convert to data frame\n",
    "    prep_df = pd.DataFrame(\n",
    "        prep, columns=feature_names + [model_target] + [sensitive_attribute]\n",
    "    )\n",
    "\n",
    "    # Create a Dataset construct for AIF360 for training data\n",
    "    df_aif360 = BinaryLabelDataset(\n",
    "        df=prep_df,\n",
    "        label_names=[model_target],\n",
    "        protected_attribute_names=[sensitive_attribute],\n",
    "        favorable_label=1.0,\n",
    "        unfavorable_label=0.0,\n",
    "    )\n",
    "    return df_aif360"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Use function to create AIF360 datasets\n",
    "train_aif360 = data_prep(train_data, data_processor, ft_names)\n",
    "val_aif360 = data_prep(val_data, data_processor, ft_names)\n",
    "test_aif360 = data_prep(test_data, data_processor, ft_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Find out which index the sensitive attribute has to delete later\n",
    "sensitive_attribute_index = train_aif360.feature_names.index(sensitive_attribute)\n",
    "\n",
    "# Initialize DI remover\n",
    "di = DisparateImpactRemover(repair_level=0.9)\n",
    "\n",
    "# Perform repair\n",
    "train_repd = di.fit_transform(train_aif360)\n",
    "\n",
    "# Convert to dataframe\n",
    "df_transform_train = train_repd.convert_to_dataframe()[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "To visualize the change, you can plot the distribution of one of the numerical features from the training dataset before and after transformation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1600x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "# Initialize figure\n",
    "fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(16, 6))\n",
    "\n",
    "# Set title of figure\n",
    "fig.suptitle(\"Comparison of Feature before and after Transformation\")\n",
    "\n",
    "# Set title\n",
    "ax1.title.set_text(\"Normal (scaled) distribution\")\n",
    "ax2.title.set_text(\"Transformed distribution\")\n",
    "\n",
    "# Create plots\n",
    "sns.histplot(train_aif360.convert_to_dataframe()[0], x=\"AGEP\", hue=\"RAC1P\", ax=ax1)\n",
    "sns.histplot(df_transform_train, x=\"AGEP\", hue=\"RAC1P\", ax=ax2)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "## 3. <a name=\"3\">Train (and Tune) a Classifier</a>\n",
    "(<a href=\"#0\">Go to top</a>)\n",
    "\n",
    "We use a Logistic Regression estimator and the transformed data for training. Then we will try to find the best possible repair level."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.1 Model Training\n",
    "\n",
    "Get the correct training data and corresponding labels. Make sure to delete the sensitive feature before training the model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Extract features (and delete sensitive attribute)\n",
    "X_train = np.delete(train_repd.features, sensitive_attribute_index, axis=1)\n",
    "\n",
    "# Extract label\n",
    "y_train = train_repd.labels.ravel()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We train the classifier with `.fit()` on our training dataset. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize model\n",
    "lr = LogisticRegression(solver=\"lbfgs\", penalty=\"none\")\n",
    "\n",
    "# Train model\n",
    "lr.fit(X_train, y_train)\n",
    "\n",
    "# Predict\n",
    "y_train_pred = lr.predict(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model performance on the training set:\n",
      "Training accuracy: 0.7949974092043902\n"
     ]
    }
   ],
   "source": [
    "print(\"Model performance on the training set:\")\n",
    "print(\"Training accuracy:\", accuracy_score(y_train, y_train_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Create copy of training dataset and save over the labels with the new predictions\n",
    "train_repd_pred = train_repd.copy()\n",
    "train_repd_pred.labels = lr.predict(X_train)\n",
    "\n",
    "# Create metric\n",
    "metric = BinaryLabelDatasetMetric(\n",
    "    train_repd_pred, privileged_groups=priv_group, unprivileged_groups=unpriv_group\n",
    ").disparate_impact()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model fairness on the training set:\n",
      "Training DI: 0.25723920758280966\n"
     ]
    }
   ],
   "source": [
    "print(\"Model fairness on the training set:\")\n",
    "print(\"Training DI:\", metric)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3.2 Fairness Tuning\n",
    "\n",
    "Clearly this is worse than where we started before the transformation. Let's see if we can find the best possible repair level."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 11/11 [02:20<00:00, 12.74s/it]\n"
     ]
    }
   ],
   "source": [
    "# Create list to store DI values at different repair levels\n",
    "DIs = []\n",
    "\n",
    "# Loop over different repair levels\n",
    "for level in tqdm(np.arange(0.0, 1.1, 0.1)):\n",
    "    # Initialize DI remover\n",
    "    di = DisparateImpactRemover(repair_level=level)\n",
    "\n",
    "    # Perform repair\n",
    "    train_repd = di.fit_transform(train_aif360)\n",
    "    val_repd = di.fit_transform(val_aif360)\n",
    "\n",
    "    # Extract features (and delete sensitive attribute)\n",
    "    X_tr = np.delete(train_repd.features, sensitive_attribute_index, axis=1)\n",
    "    X_va = np.delete(val_repd.features, sensitive_attribute_index, axis=1)\n",
    "\n",
    "    # Extract label\n",
    "    y_tr = train_repd.labels.ravel()\n",
    "    y_va = val_repd.labels.ravel()\n",
    "\n",
    "    # Initialize model\n",
    "    lr = LogisticRegression(solver=\"lbfgs\", penalty=\"none\")\n",
    "\n",
    "    # Train model\n",
    "    lr.fit(X_tr, y_tr)\n",
    "\n",
    "    # Predict with model\n",
    "    val_repd_pred = val_repd.copy()\n",
    "    val_repd_pred.labels = lr.predict(X_va)\n",
    "\n",
    "    # Create metric\n",
    "    metric = BinaryLabelDatasetMetric(\n",
    "        val_repd_pred, privileged_groups=priv_group, unprivileged_groups=unpriv_group\n",
    "    )\n",
    "    # Append DI value\n",
    "    DIs.append(metric.disparate_impact())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's visualize the repair level and corresponding DI on the validation dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "plt.plot(np.arange(0.0, 1.1, 0.1), DIs, marker=\"o\")\n",
    "plt.plot([0, 1], [1, 1], \"g\")\n",
    "plt.plot([0, 1], [0.8, 0.8], \"r\")\n",
    "plt.ylim([0.2, 1.2])\n",
    "plt.ylabel(\"Disparate Impact (DI)\")\n",
    "plt.xlabel(\"repair level\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 4. <a name=\"4\">Test the Classifier</a>\n",
    "(<a href=\"#0\">Go to top</a>)\n",
    "\n",
    "Let's now evaluate the performance and fairness of the trained classifier on the test dataset. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model performance on the test set:\n",
      "Test accuracy: 0.7967933705638623\n"
     ]
    }
   ],
   "source": [
    "# Transform the test dataset\n",
    "test_repd = di.fit_transform(test_aif360)\n",
    "\n",
    "# Extract features and labels from AIF360 dataset construct\n",
    "X_te = np.delete(test_repd.features, sensitive_attribute_index, axis=1)\n",
    "y_te = test_repd.labels.ravel()\n",
    "\n",
    "# Use the last (and most fair) fitted model to make predictions on the test dataset\n",
    "y_te_pred = lr.predict(X_te)\n",
    "\n",
    "print(\"Model performance on the test set:\")\n",
    "print(\"Test accuracy:\", accuracy_score(y_te, y_te_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From our previous notebook, we might remember that the accuracy was around 80%, so pretty much the same as we see above. So far so good, but let's check if the outcomes are fairer on the test set. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.2948283978569347"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Predict with model\n",
    "test_repd_pred = test_repd.copy()\n",
    "test_repd_pred.labels = y_te_pred\n",
    "\n",
    "# Create metric\n",
    "BinaryLabelDatasetMetric(\n",
    "    test_repd_pred, privileged_groups=priv_group, unprivileged_groups=unpriv_group\n",
    ").disparate_impact()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is much lower than the values we had originally (before the transformation when DI was around 0.4). So we are in fact even further away from not having DI impact. Let's wrap up by visualizing this."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Create dataframe that contains predictions and the sensitive attribute\n",
    "di_df = pd.concat(\n",
    "    [\n",
    "        test_data.reset_index(drop=True)[[\"RAC1P\", \">50k\"]],\n",
    "        pd.Series(y_te_pred, name=\"y_test_pred\"),\n",
    "    ],\n",
    "    axis=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1600x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "# Initialize figure\n",
    "fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(16, 6))\n",
    "\n",
    "# Set title of figure\n",
    "fig.suptitle(\"Comparison of Model Predictions and Baseline\")\n",
    "\n",
    "# Set title\n",
    "ax1.title.set_text(\"Baseline target distribution\")\n",
    "ax2.title.set_text(\"Predictions with bias mitigation\")\n",
    "\n",
    "# Create plots\n",
    "di_df.groupby([\"RAC1P\", model_target]).size().unstack().plot(\n",
    "    kind=\"bar\", stacked=True, color=sns.husl_palette(2), ax=ax1\n",
    ")\n",
    "di_df.groupby([\"RAC1P\", \"y_test_pred\"]).size().unstack().plot(\n",
    "    kind=\"bar\", stacked=True, color=sns.husl_palette(2), ax=ax2\n",
    ")\n",
    "# Align y-axis\n",
    "ax2.sharey(ax1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We notice that the results for the disfavored group have worsened. This could be explained by the fact that we are dealing with an imbalance in the class label itself and outcome '0' will be favored by the model in general. It appears that group 6 does not gain much advantage despite the DI transformation. As final check, we can look at model predictions for the dataset without DI transformation and compare what would have happened if we hadn't intervened."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Create predictions for the test data without DI transformation\n",
    "lr.fit(data_processor.transform(train_data), train_data[model_target])\n",
    "noDI_test_preds = lr.predict(data_processor.transform(test_data))\n",
    "\n",
    "# Join the predictions to the dataframe we need for plotting\n",
    "di_df = pd.concat(\n",
    "    [\n",
    "        di_df,\n",
    "        pd.Series(noDI_test_preds, name=\"y_test_pred_noDI\"),\n",
    "    ],\n",
    "    axis=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1600x600 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "# Initialize figure\n",
    "fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(16, 6))\n",
    "\n",
    "# Set title of figure\n",
    "fig.suptitle(\"Comparison of Model Predictions and Baseline\")\n",
    "\n",
    "# Set title\n",
    "ax1.title.set_text(\"Baseline target distribution\")\n",
    "ax2.title.set_text(\"Predictions with bias mitigation\")\n",
    "ax3.title.set_text(\"Predictions without bias mitigation (DI transformation)\")\n",
    "\n",
    "# Create plots\n",
    "di_df.groupby([\"RAC1P\", model_target]).size().unstack().plot(\n",
    "    kind=\"bar\", stacked=True, color=sns.husl_palette(2), ax=ax1\n",
    ")\n",
    "di_df.groupby([\"RAC1P\", \"y_test_pred\"]).size().unstack().plot(\n",
    "    kind=\"bar\", stacked=True, color=sns.husl_palette(2), ax=ax2\n",
    ")\n",
    "di_df.groupby([\"RAC1P\", \"y_test_pred_noDI\"]).size().unstack().plot(\n",
    "    kind=\"bar\", stacked=True, color=sns.husl_palette(2), ax=ax3\n",
    ")\n",
    "\n",
    "# Align y-axis\n",
    "ax2.sharey(ax1)\n",
    "ax3.sharey(ax1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As expected, in the model that was trained without DI remover, group 6 had an even higher number of predictions for the < 50k class and was therefor more unfair. For group 8 we notice that there are slightly fewer positive outcomes when DI transformation is considered. Generally, what we should notice is that while a model might have good accuracy, we still need to check outcome distributions per target class as errors might be disproportionately concentrated in a certain group. For this particular dataset DI removal did not have the desired effect and we should look into other options."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is the end of this notebook."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_pytorch_p39",
   "language": "python",
   "name": "conda_pytorch_p39"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}