From 07f2164ac1a4e9218e7245f207e5ed771cf4975c Mon Sep 17 00:00:00 2001
From: Maggie Hei <mehei@microsoft.com>
Date: Wed, 12 May 2021 17:46:58 -0400
Subject: [PATCH 1/2] add causal analysis notebook

---
 .../causal_analysis/_causal_analysis.py       |   2 +-
 econml/tests/test_notebooks.py                |   2 +-
 ...ation for Employee Attrition Dataset.ipynb | 954 ++++++++++++++++++
 3 files changed, 956 insertions(+), 2 deletions(-)
 create mode 100644 notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb

diff --git a/econml/solutions/causal_analysis/_causal_analysis.py b/econml/solutions/causal_analysis/_causal_analysis.py
index d4be23ec0..9695560db 100644
--- a/econml/solutions/causal_analysis/_causal_analysis.py
+++ b/econml/solutions/causal_analysis/_causal_analysis.py
@@ -125,7 +125,7 @@ def _first_stage_reg(X, y, *, automl=True):
 
 def _first_stage_clf(X, y, *, make_regressor=False, automl=True):
     if automl:
-        model = GridSearchCVList([make_pipeline(StandardScaler(), LogisticRegression()),
+        model = GridSearchCVList([make_pipeline(StandardScaler(), LogisticRegression(max_iter=1000)),
                                   RandomForestClassifier(
                                       n_estimators=100, random_state=123),
                                   GradientBoostingClassifier(random_state=123)],
diff --git a/econml/tests/test_notebooks.py b/econml/tests/test_notebooks.py
index 008d883c8..7825c7489 100644
--- a/econml/tests/test_notebooks.py
+++ b/econml/tests/test_notebooks.py
@@ -9,7 +9,7 @@
 import traitlets
 
 _nbdir = os.path.join(os.path.dirname(__file__), '..', '..', 'notebooks')
-_nbsubdirs = ['.', 'CustomerScenarios']  # TODO: add AutoML notebooks
+_nbsubdirs = ['.', 'CustomerScenarios', 'Solutions']  # TODO: add AutoML notebooks
 _notebooks = [
     os.path.join(subdir, path) for subdir
     in _nbsubdirs for path in os.listdir(os.path.join(_nbdir, subdir)) if
diff --git a/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb b/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb
new file mode 100644
index 000000000..8afa84af6
--- /dev/null
+++ b/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb	
@@ -0,0 +1,954 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Causal Interpretation for Employee Attrition Dataset\n",
+    "\n",
+    "This notebook uses the popular kaggle Employee Attrition dataset to showcase how we could interpret a blackbox model from both the correlation and causation perspective, leveraging the power of model interpretation tools like [SHAP](https://shap.readthedocs.io/en/latest/index.html) and [EconML](https://aka.ms/econml). We start with a fine-tuned ML model and learn the top important features to predict employee attrition, it will help us to better understand the correlations between features and target and which features are the strongest predictors. In addition, this notebook will take a step further and focus more on figuring out which features cause the employees leave the company, instead of just predicting how likely they are going to leave. This extra causal interpretation could better help company to make corresponding changes in order to minimize the attrition rate.  \n",
+    "\n",
+    "It includes the following sessions:\n",
+    "1. [Train a Fine-tuned ML Model](#Train-a-Fine-tuned-ML-Model)\n",
+    "2. [Correlation Interpretation](#Correlation-Interpretation)\n",
+    "    * Feature Importance -- Learn the top predictors for a given ML model\n",
+    "3. [Causal Interpretation](#Causal-Interpretation)\n",
+    "    * Direct Causal Effect -- Do the top predictors also have a direct effect on outcome of interest?\n",
+    "    * Segmentation -- How to make individaulized plans to reduce the attrition?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Some imports to get us started\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
+    "from lightgbm import LGBMClassifier\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "pd.set_option(\"display.max_columns\", 100)\n",
+    "pd.set_option(\"display.max_rows\", 100)\n",
+    "pd.set_option(\"display.max_colwidth\", 100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Train a Fine-tuned ML Model\n",
+    "### Load the employee attrition data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Age</th>\n",
+       "      <th>Attrition</th>\n",
+       "      <th>BusinessTravel</th>\n",
+       "      <th>DailyRate</th>\n",
+       "      <th>Department</th>\n",
+       "      <th>DistanceFromHome</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>EducationField</th>\n",
+       "      <th>EmployeeCount</th>\n",
+       "      <th>EmployeeNumber</th>\n",
+       "      <th>EnvironmentSatisfaction</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>HourlyRate</th>\n",
+       "      <th>JobInvolvement</th>\n",
+       "      <th>JobLevel</th>\n",
+       "      <th>JobRole</th>\n",
+       "      <th>JobSatisfaction</th>\n",
+       "      <th>MaritalStatus</th>\n",
+       "      <th>MonthlyIncome</th>\n",
+       "      <th>MonthlyRate</th>\n",
+       "      <th>NumCompaniesWorked</th>\n",
+       "      <th>Over18</th>\n",
+       "      <th>OverTime</th>\n",
+       "      <th>PercentSalaryHike</th>\n",
+       "      <th>PerformanceRating</th>\n",
+       "      <th>RelationshipSatisfaction</th>\n",
+       "      <th>StandardHours</th>\n",
+       "      <th>StockOptionLevel</th>\n",
+       "      <th>TotalWorkingYears</th>\n",
+       "      <th>TrainingTimesLastYear</th>\n",
+       "      <th>WorkLifeBalance</th>\n",
+       "      <th>YearsAtCompany</th>\n",
+       "      <th>YearsInCurrentRole</th>\n",
+       "      <th>YearsSinceLastPromotion</th>\n",
+       "      <th>YearsWithCurrManager</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>41</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Travel_Rarely</td>\n",
+       "      <td>1102</td>\n",
+       "      <td>Sales</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Life Sciences</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>94</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Sales Executive</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>5993</td>\n",
+       "      <td>19479</td>\n",
+       "      <td>8</td>\n",
+       "      <td>Y</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>11</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>80</td>\n",
+       "      <td>0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>6</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>49</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Travel_Frequently</td>\n",
+       "      <td>279</td>\n",
+       "      <td>Research &amp; Development</td>\n",
+       "      <td>8</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Life Sciences</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>61</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Research Scientist</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>5130</td>\n",
+       "      <td>24907</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Y</td>\n",
+       "      <td>No</td>\n",
+       "      <td>23</td>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "      <td>80</td>\n",
+       "      <td>1</td>\n",
+       "      <td>10</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>10</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1</td>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>37</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Travel_Rarely</td>\n",
+       "      <td>1373</td>\n",
+       "      <td>Research &amp; Development</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Other</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>92</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Laboratory Technician</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>2090</td>\n",
+       "      <td>2396</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Y</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>15</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>80</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>33</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Travel_Frequently</td>\n",
+       "      <td>1392</td>\n",
+       "      <td>Research &amp; Development</td>\n",
+       "      <td>3</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Life Sciences</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>56</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Research Scientist</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>2909</td>\n",
+       "      <td>23159</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Y</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>11</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>80</td>\n",
+       "      <td>0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>8</td>\n",
+       "      <td>7</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>27</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Travel_Rarely</td>\n",
+       "      <td>591</td>\n",
+       "      <td>Research &amp; Development</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Medical</td>\n",
+       "      <td>1</td>\n",
+       "      <td>7</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>40</td>\n",
+       "      <td>3</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Laboratory Technician</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>3468</td>\n",
+       "      <td>16632</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Y</td>\n",
+       "      <td>No</td>\n",
+       "      <td>12</td>\n",
+       "      <td>3</td>\n",
+       "      <td>4</td>\n",
+       "      <td>80</td>\n",
+       "      <td>1</td>\n",
+       "      <td>6</td>\n",
+       "      <td>3</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Age Attrition     BusinessTravel  DailyRate              Department  \\\n",
+       "0   41       Yes      Travel_Rarely       1102                   Sales   \n",
+       "1   49        No  Travel_Frequently        279  Research & Development   \n",
+       "2   37       Yes      Travel_Rarely       1373  Research & Development   \n",
+       "3   33        No  Travel_Frequently       1392  Research & Development   \n",
+       "4   27        No      Travel_Rarely        591  Research & Development   \n",
+       "\n",
+       "   DistanceFromHome  Education EducationField  EmployeeCount  EmployeeNumber  \\\n",
+       "0                 1          2  Life Sciences              1               1   \n",
+       "1                 8          1  Life Sciences              1               2   \n",
+       "2                 2          2          Other              1               4   \n",
+       "3                 3          4  Life Sciences              1               5   \n",
+       "4                 2          1        Medical              1               7   \n",
+       "\n",
+       "   EnvironmentSatisfaction  Gender  HourlyRate  JobInvolvement  JobLevel  \\\n",
+       "0                        2  Female          94               3         2   \n",
+       "1                        3    Male          61               2         2   \n",
+       "2                        4    Male          92               2         1   \n",
+       "3                        4  Female          56               3         1   \n",
+       "4                        1    Male          40               3         1   \n",
+       "\n",
+       "                 JobRole  JobSatisfaction MaritalStatus  MonthlyIncome  \\\n",
+       "0        Sales Executive                4        Single           5993   \n",
+       "1     Research Scientist                2       Married           5130   \n",
+       "2  Laboratory Technician                3        Single           2090   \n",
+       "3     Research Scientist                3       Married           2909   \n",
+       "4  Laboratory Technician                2       Married           3468   \n",
+       "\n",
+       "   MonthlyRate  NumCompaniesWorked Over18 OverTime  PercentSalaryHike  \\\n",
+       "0        19479                   8      Y      Yes                 11   \n",
+       "1        24907                   1      Y       No                 23   \n",
+       "2         2396                   6      Y      Yes                 15   \n",
+       "3        23159                   1      Y      Yes                 11   \n",
+       "4        16632                   9      Y       No                 12   \n",
+       "\n",
+       "   PerformanceRating  RelationshipSatisfaction  StandardHours  \\\n",
+       "0                  3                         1             80   \n",
+       "1                  4                         4             80   \n",
+       "2                  3                         2             80   \n",
+       "3                  3                         3             80   \n",
+       "4                  3                         4             80   \n",
+       "\n",
+       "   StockOptionLevel  TotalWorkingYears  TrainingTimesLastYear  \\\n",
+       "0                 0                  8                      0   \n",
+       "1                 1                 10                      3   \n",
+       "2                 0                  7                      3   \n",
+       "3                 0                  8                      3   \n",
+       "4                 1                  6                      3   \n",
+       "\n",
+       "   WorkLifeBalance  YearsAtCompany  YearsInCurrentRole  \\\n",
+       "0                1               6                   4   \n",
+       "1                3              10                   7   \n",
+       "2                3               0                   0   \n",
+       "3                3               8                   7   \n",
+       "4                3               2                   2   \n",
+       "\n",
+       "   YearsSinceLastPromotion  YearsWithCurrManager  \n",
+       "0                        0                     5  \n",
+       "1                        1                     7  \n",
+       "2                        0                     0  \n",
+       "3                        3                     0  \n",
+       "4                        2                     2  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "file_url = \"https://msalicedatapublic.blob.core.windows.net/datasets/EmployeeAttrition/Employee-Attrition.csv\"\n",
+    "attritionData = pd.read_csv(file_url)\n",
+    "attritionData.head(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Dropping Employee count as all values are 1 and hence attrition is independent of this feature\n",
+    "attritionData = attritionData.drop([\"EmployeeCount\"], axis=1)\n",
+    "# Dropping Employee Number since it is merely an identifier\n",
+    "attritionData = attritionData.drop([\"EmployeeNumber\"], axis=1)\n",
+    "attritionData = attritionData.drop([\"Over18\"], axis=1)\n",
+    "\n",
+    "# Since all values are 80\n",
+    "attritionData = attritionData.drop([\"StandardHours\"], axis=1)\n",
+    "\n",
+    "# change the unit of income related variables\n",
+    "attritionData[[\"MonthlyIncome/1K\", \"MonthlyRate/1K\"]] = (\n",
+    "    attritionData[[\"MonthlyIncome\", \"MonthlyRate\"]] / 1000\n",
+    ")\n",
+    "attritionData = attritionData.drop([\"MonthlyIncome\", \"MonthlyRate\"], axis=1)\n",
+    "\n",
+    "# Converting target variables from string to numerical values\n",
+    "target_map = {\"Yes\": 1, \"No\": 0}\n",
+    "attritionData[\"Attrition_numerical\"] = attritionData[\"Attrition\"].apply(\n",
+    "    lambda x: target_map[x]\n",
+    ")\n",
+    "target = attritionData[\"Attrition_numerical\"]\n",
+    "\n",
+    "attritionXData = attritionData.drop([\"Attrition_numerical\", \"Attrition\"], axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Split data into train and test\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "x_train, x_test, y_train, y_test = train_test_split(\n",
+    "    attritionXData, target, test_size=0.2, random_state=0, stratify=target\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "categorical = []\n",
+    "for col, value in attritionXData.iteritems():\n",
+    "    if value.dtype == \"object\":\n",
+    "        categorical.append(col)\n",
+    "\n",
+    "# Store the numerical columns in a list numerical\n",
+    "numerical = attritionXData.columns.difference(categorical)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Make training pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.compose import ColumnTransformer\n",
+    "\n",
+    "# We create the preprocessing pipelines for both numeric and categorical data.\n",
+    "numeric_transformer = Pipeline(\n",
+    "    steps=[(\"imputer\", SimpleImputer(strategy=\"median\")), (\"scaler\", StandardScaler())]\n",
+    ")\n",
+    "\n",
+    "categorical_transformer = Pipeline(\n",
+    "    steps=[\n",
+    "        (\"imputer\", SimpleImputer(strategy=\"constant\", fill_value=\"missing\")),\n",
+    "        (\"onehot\", OneHotEncoder(handle_unknown=\"error\", drop=\"first\")),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "transformations = ColumnTransformer(\n",
+    "    transformers=[\n",
+    "        (\"num\", numeric_transformer, numerical),\n",
+    "        (\"cat\", categorical_transformer, categorical),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Append classifier to preprocessing pipeline.\n",
+    "# Now we have a full prediction pipeline.\n",
+    "clf = Pipeline(\n",
+    "    steps=[(\"preprocessor\", transformations), (\"classifier\", LGBMClassifier())]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Train a LightGBM classification model, which you want to explain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import GridSearchCV\n",
+    "\n",
+    "param_grid = {\n",
+    "    \"classifier__learning_rate\": [0.1, 0.05, 0.01],\n",
+    "    \"classifier__max_depth\": [3, 5, 10],\n",
+    "}\n",
+    "search = GridSearchCV(clf, param_grid, n_jobs=-1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'classifier__learning_rate': 0.1, 'classifier__max_depth': 3}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "search.fit(x_train, y_train)\n",
+    "search.best_params_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Correlation Interpretation\n",
+    "We explain this ML model by understanding the top important features to predict the employee attrition, internally using shap value."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get the fitted model and transformer\n",
+    "fitted_model = search.best_estimator_[\"classifier\"]\n",
+    "fitted_transformer = search.best_estimator_[\"preprocessor\"]\n",
+    "# get the feature name after featurization\n",
+    "column_names = numerical.tolist()\n",
+    "column_names += (\n",
+    "    search.best_estimator_[\"preprocessor\"]\n",
+    "    .transformers_[1][1]\n",
+    "    .steps[1][1]\n",
+    "    .get_feature_names(categorical)\n",
+    "    .tolist()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Passing 1176 background samples may lead to slow runtimes. Consider using shap.sample(data, 100) to create a smaller background data set.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import shap\n",
+    "\n",
+    "# use interventional approach\n",
+    "background = shap.maskers.Independent(\n",
+    "    fitted_transformer.transform(x_train), max_samples=2000\n",
+    ")\n",
+    "explainer = shap.TreeExplainer(\n",
+    "    fitted_model, data=background, feature_names=column_names\n",
+    ")\n",
+    "shap_values = explainer(fitted_transformer.transform(x_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 576x684 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# plot the feature importance\n",
+    "shap.summary_plot(shap_values, fitted_transformer.transform(x_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "From the summary plot above, we could see the most important features sorted by their importance level. Taking the top 5 important features as an example, employees who often work overtime, have frequently changed jobs or live far away from their worksite are more likely to leave the company, and employees with higher income and stock options are less likely to leave. However, it doesn't mean these are the drivers that directly cause the employee to leave, it might have hidden variables that affect both the top features and outcome. For example, maybe the inefficient collaboration environment forces the employee to work overtime and also causes them to leave, instead of working overtime itself. In order to correctly find the direct reason and make improvements accordingly, we have to train a different model controlling on all the possible hidden variables (confounders) and learn the direct causal effect for a given feature. That's what the causal interpretation tool is doing. In the following session, we will explain the causal relationship for the top 5 important features."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Causal Interpretation\n",
+    "### Direct Causal Effect --  Do the top predictors also have a direct effect on outcome of interest?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "classification = True\n",
+    "k = 5\n",
+    "# get top feature names according to shap values\n",
+    "vals = np.abs(shap_values.values).mean(0)\n",
+    "feature_importance = pd.DataFrame(\n",
+    "    list(zip(shap_values.feature_names, vals)), columns=[\"features\", \"importance\"]\n",
+    ")\n",
+    "feature_importance.sort_values(by=[\"importance\"], ascending=False, inplace=True)\n",
+    "top_features = feature_importance.iloc[:k][\"features\"]\n",
+    "# extract the raw feature name for top features\n",
+    "top_features = [i.split(\"_\")[0] for i in top_features]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n",
+      "[Parallel(n_jobs=-1)]: Done   2 out of   5 | elapsed:  1.9min remaining:  2.8min\n",
+      "[Parallel(n_jobs=-1)]: Done   5 out of   5 | elapsed:  2.5min finished\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<econml.solutions.causal_analysis._causal_analysis.CausalAnalysis at 0x2821a410648>"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from econml.solutions.causal_analysis import CausalAnalysis\n",
+    "\n",
+    "ca = CausalAnalysis(\n",
+    "    top_features,\n",
+    "    categorical,\n",
+    "    heterogeneity_inds=None,\n",
+    "    classification=True,\n",
+    "    nuisance_models=\"automl\",\n",
+    "    heterogeneity_model=\"forest\",\n",
+    "    n_jobs=-1,\n",
+    ")\n",
+    "ca.fit(x_train, y_train.values)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th>point</th>\n",
+       "      <th>stderr</th>\n",
+       "      <th>zstat</th>\n",
+       "      <th>p_value</th>\n",
+       "      <th>ci_lower</th>\n",
+       "      <th>ci_upper</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>feature</th>\n",
+       "      <th>feature_value</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>OverTime</th>\n",
+       "      <th>YesvNo</th>\n",
+       "      <td>0.211192</td>\n",
+       "      <td>0.023247</td>\n",
+       "      <td>9.084544</td>\n",
+       "      <td>1.041338e-19</td>\n",
+       "      <td>0.165628</td>\n",
+       "      <td>0.256756</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>StockOptionLevel</th>\n",
+       "      <th>num</th>\n",
+       "      <td>-0.017507</td>\n",
+       "      <td>0.029796</td>\n",
+       "      <td>-0.587555</td>\n",
+       "      <td>5.568309e-01</td>\n",
+       "      <td>-0.075907</td>\n",
+       "      <td>0.040893</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>NumCompaniesWorked</th>\n",
+       "      <th>num</th>\n",
+       "      <td>0.024221</td>\n",
+       "      <td>0.007400</td>\n",
+       "      <td>3.272942</td>\n",
+       "      <td>1.064345e-03</td>\n",
+       "      <td>0.009716</td>\n",
+       "      <td>0.038725</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MonthlyIncome/1K</th>\n",
+       "      <th>num</th>\n",
+       "      <td>-0.011077</td>\n",
+       "      <td>0.012029</td>\n",
+       "      <td>-0.920860</td>\n",
+       "      <td>3.571233e-01</td>\n",
+       "      <td>-0.034653</td>\n",
+       "      <td>0.012499</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>DistanceFromHome</th>\n",
+       "      <th>num</th>\n",
+       "      <td>0.003981</td>\n",
+       "      <td>0.002086</td>\n",
+       "      <td>1.908791</td>\n",
+       "      <td>5.628909e-02</td>\n",
+       "      <td>-0.000107</td>\n",
+       "      <td>0.008069</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                     point    stderr     zstat       p_value  \\\n",
+       "feature            feature_value                                               \n",
+       "OverTime           YesvNo         0.211192  0.023247  9.084544  1.041338e-19   \n",
+       "StockOptionLevel   num           -0.017507  0.029796 -0.587555  5.568309e-01   \n",
+       "NumCompaniesWorked num            0.024221  0.007400  3.272942  1.064345e-03   \n",
+       "MonthlyIncome/1K   num           -0.011077  0.012029 -0.920860  3.571233e-01   \n",
+       "DistanceFromHome   num            0.003981  0.002086  1.908791  5.628909e-02   \n",
+       "\n",
+       "                                  ci_lower  ci_upper  \n",
+       "feature            feature_value                      \n",
+       "OverTime           YesvNo         0.165628  0.256756  \n",
+       "StockOptionLevel   num           -0.075907  0.040893  \n",
+       "NumCompaniesWorked num            0.009716  0.038725  \n",
+       "MonthlyIncome/1K   num           -0.034653  0.012499  \n",
+       "DistanceFromHome   num           -0.000107  0.008069  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "global_summ = ca.global_causal_effect(alpha=0.05)\n",
+    "global_summ"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# helper function to plot error bar\n",
+    "def errorbar(res):\n",
+    "    xticks = res.index.get_level_values(0)\n",
+    "    lowererr = res[\"point\"] - res[\"ci_lower\"]\n",
+    "    uppererr = res[\"ci_upper\"] - res[\"point\"]\n",
+    "    xticks = [\n",
+    "        \"{}***\".format(t)\n",
+    "        if p < 1e-6\n",
+    "        else (\"{}**\".format(t) if p < 1e-3 else (\"{}*\".format(t) if p < 1e-2 else t))\n",
+    "        for t, p in zip(xticks, res[\"p_value\"])\n",
+    "    ]\n",
+    "    plot_title = \"Direct Causal Effect of Each Feature with 95% Confidence Interval, \"\n",
+    "    plt.figure(figsize=(15, 5))\n",
+    "    plt.errorbar(\n",
+    "        np.arange(len(xticks)),\n",
+    "        res[\"point\"],\n",
+    "        yerr=[lowererr, uppererr],\n",
+    "        fmt=\"o\",\n",
+    "        capsize=5,\n",
+    "        capthick=1,\n",
+    "        barsabove=True,\n",
+    "    )\n",
+    "    plt.xticks(np.arange(len(xticks)), xticks, rotation=45)\n",
+    "    plt.title(plot_title)\n",
+    "    plt.axhline(0, color=\"r\", linestyle=\"--\", alpha=0.5)\n",
+    "    plt.ylabel(\"Average Treatment Effect\")\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1080x360 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "errorbar(global_summ)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We learn the Average Treatment Effect(ATE) for each of the top 5 important features, assuming they are the treatment. From the summary table and the error bar plot above, we see the causal effect directions we learnt here are in line with the correlation directions we learnt above. However, features like `StockOptionLevel` or `MonthlyIncome/1K` although they are the strongest predictors on how likely employees will leave, we are less confident to say these are the drivers causing them leave. This is super valuable for the managers when they are trying to make plans to reduce the employee attrition rate, improving work life balance or providing extra support for employees who are living far away from the company might be more effective than raise their salary/stocks.          "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Segmentation -- How to make individaulized plans to reduce the attrition?\n",
+    "From the analysis above, we learnt the direct treatment effect of each top features from an overall average level. However, people in different life stage or working experience might have different response to each of this potential reasons. Since the salary related features are not sigificant in an average level, we are interested to find the sub-groups who will respond positively to the income raise. If we could find a sub-group who have sigificant effect on income, we could further help the managers to refine their strategy and make individualized plans to different employees. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "local_summ = ca.local_causal_effect(x_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAqsAAAHBCAYAAABOnPJQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOzdd3xO5//H8dfJEJIQOyQEIYjYsfeuVSv2pnZrlA5FW7uqtVo6UGrG9m3tKrV3tfYejZmoFQnZ5/dH/O4KCaq4b/F+Ph7345H7nM8553Pu3Dn3J9d9XdcxTNNERERERMQW2Vk7ARERERGRpKhYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGbpWJVRERERGyWilURERERsVkqVkVERETEZqlYFRERERGb5WDtBETE9hiGkdnRwaGbq6tr0zjTTGvtfCT5szOMW2FhYUuiY2KmmqYZYu18RMR2GKZpWjsHEbEhhmFkdXF23tegfr0MLZoEOLlnzoxhWDsrSc5ME4JDQli4bGnkzytXXQ+/e7eEaZpXrJ2XiNgGtayKSAIpU6Z8v3Xz5pkmjP3c0dq5yOujEH7UqFbVydXZJdOcBQveB/pbOycRsQ3qsyoiCTilSNGkbauWKlTFKtq2aunolCJFE2vnISK2Q8WqiCQQHR2d1iNrVmunIa8pj6xZiY6OVj9pEbFQsSoiCZhg2Bm6NIh12Bl2mKBe0iJioU8kEXmihs1b0H/gRwmWHT1+nCy5vDl85MhLyyMuLo78xYpTsERJHh4cWsC/BGt++eWRbVauWUPN+m+SJZc3Xvl9qVanLvMWLHxZKSdbUVFRtOn8FgX8S+Ca2T3R1/5BfwUF4ZrZHfecuSyP7r37vKRsReRVpmJVRJ7om4kTWLR0KVu2bwcgJiaGHn360r9Pbwr6+T2XY8TGxj4xZsOmTdy8eZMrwcFs3rbtifHTZv5Ir37v0qVjB04ePMD5o0cYM2I4q9atex4pv7KCg5/PzFDlSpdi2pTJeHp4PPU2Zw4fJvj8OYLPn+P7r796LnmISPKmYlVEnsjTw4MxI4bTq28/wsPDGf/119jZGTR6802atGqNV35fCpYoyeTvvrNsc+HiReoHNMUrvy/Z8+ajZfsOXA0Otqyv3agxn4wYQf2ApmTOmZPNW7exfuNGSlaqRJZc3nj7FWTIsOEJ8pg9P5AG9epRp1Yt5swPtCzv2L07Fy5epF2XrrjnzMUHQ4ZwJyyMT0aM4MvRo2jRtClpUqfGzs6OUiVKMH/mDMu2CxYvoXj5Cnjm8aFGvfrs//PPBDl+OnIkdZs0IXPOnFSvW4+rwcEMHzMGr/y+5CtajFVr11riu/fuwzv9+9O8XTvcc+aifPUa/HHgQIJjlagYf36+xf35ctIky7r/b3mcv3ARfiVKkM0nLx9+/DEA0dHR5CxQgJ2791ji4+LiyFukKL9u/O2pfoe3Q0P5ce5cajVoSN2AgKfa5nFSpEjB2927U75MGezt7f/z/kREkqJiVUSeStuWLSngm5/OPXsyaco3fDtpEg2aNadm9WqcOXSQnxYt4rvpP/DzqtVAfDHV9+1enDrwJwf37CYmNob3Bg1OsM+5CxYy4pOPuXr2LOXKlI5vrX2nN1fPneXA7l00rF/PEnvj5k1Wr1tHq2bNaN28GT+vXs3t0FAAfvz+e7Jny8ac6dMIPn+OsSNHsmfvPu7eu0fjBg2SPKftu3bRf+BAJo8bx/ljRwlo3IhGLVtx6/ZtS8zCpcv4cvRogo4fJ2WqlNSoV59MGTNy9vAhBg7ozzv9BxATE2OJX7BkKd06debiqZM0a9yY5u3aExERAUD69OkI/HEmV86eYe4P05k4eQpr169PkNOvv/3G7k2b2bxuHbPnzWfT1q04OjrSMqAp8xb9033ht81bAKhWpXKS5xcTE8Pa9evp0K0b+YsWY+WaNXTr3Ilt6//5yn7cV1/hmccnyceOXbuT3P+zKF6+PLkLFqJ1p86cO3/+ue5bRJInFasi8tS+/nIcm7ZspX+f3hw9fpyMGTLQs0sXHB0dye2diy4dO7J4+XIAcnh5UbNaNZycnEiXNi39e/dh644dCfbXsmlTihUpgp2dHSlTpiRFihScOXeOv69fJ7WrKyX9/S2xC5YsIX26dFSpVJFa1avj6uLCkuX/SzLXv6//TYb06XF0THoWrsBFi2jVvBnlypTG0dGRnl26kDlTJtY9UEC2at6MAvnzkzJlShrWq090TAw9u3TBwcGBFgEBXPv7by5dvmyJr16lMjWqVcXR0ZG+b/cCsJx3rerV8cmdG8Mw8C9WjIb167F1e8LXZPAHH+Dq6kJu71yULV2aAwcPAdCudSuW//Qz9+7dA2DewoW0atYUO7vEL+MjxnxO3iJFGTNuHGVKleLgnt0smTePpo0akSpVKkvcgD59uHT6VJKPcmVKJ/n6/RsZ0mdg87q1HP19H3u3biFTxow0ad2GqKio57J/EUm+VKyKyFNzd89MhgwZKJA/P0FBFzhy7FiCVrgx48YRHBLfHzLk2jU6du9O3iJFyeqdm4DWrbl+/XqC/WXPni3B88AfZ3Lk2DGKlilLpVpvJBi0M2d+IC0CArCzs8PBwYFmTRozJ3B+krlmSJ+B6zduEB0dnWTMpctXyJHdK8GynF7ZuXzl6j/nnDmz5Wdn51RkzpTpgefOAISFh1uWZfP0tPxsGAbZPD24fCX+Zky/bNhAtTp18cqXH4/ceViwZCnXb9xIcPwHj5cqVSrLvv18fcnt7c2KNWu4ExbGyrVraNOyZZLndvrsGSIiIijkV5BCfn5kzJAhydiXwdXVBf9ixXBwcCB9unSM+2w0ly5f4vDRo1bNS0Rsn+5gJSLPJFs2T0oUK8b6lSsSXT901CiioqLZsXEDGTNkYMeu3dR66Ct546H7uBYtXJjAH2cSGxvLoqXLaPtWF4KOH+Pk6dMcOnKEoAsXmL9oEQCRkZHcDg3l6PHjFMifH7uH9lW6VEmcU6Vi+YoVNG+S+Bzznh5Z+etCUIJl54Mu0Kxx43/1Wjzo4qVLlp9N0+Tipct4ZM1KZGQkbTq/xddffkmThg3i+3y++y4xMU8eWPb/2rVqxfyFi+KL0AJ+5M2TJ8nYWVOncvnKFRYuWUr/gQO5cyeM5k0a0zwgAD9fX0vcFxMn8uXESUnuZ9mCQMqXKfPUOT4twzAwMB6Z1UFE5GFqWRWRZ1KnZi0uXbnCD7NmExERQWxsLEePH2f33r0A3AkLx8XZGbc0aQi5do0vJk587P6ioqIIXLSYW7dvY29vT5o0qTEMA3t7e2bPD6Skf3H2b9/Ozo0b2blxI/u3b6d40aKWgVaZM2Xi7AN9IFO7ujL84495f/AQFi1bxp2wMEzTZP+ff9L2rS4AtGjalAWLl7Brz15iYmKYOmMmISEhvFGz5jO/Lhs3b2Hjps3ExMTw9bffYZomFcqWJSo6msjISDJkiO+asH3XLn5auepf7btZk8bs3L2br7/7jjYtWzwx3iNrVt7t/Q57Nm9mwawfiYyMokGz5tQPaGqJeb9fP8vo/MQejytUIyMjiYiIwDRNoqNjLO+DxOz9/XeOnzxJXFwcoXfu8MGQIWRxd6dggQL/6jUQkdePilUReSauri6sWLyY9Rs24Fvcnxz5fenVrx83b90CYPAH73Pi1Ck8fXyo07gJtZ+iAFy0bBmFSpYiSy5vhn32GbOnTQVgyfLl9OzSBXf3zAkevbp2ZcGSJURHR/Nev758M3Uq2XzyMvDjTwDo2qkjk8d9ybQZM8lTsBA5fAvw3keDqPfGGwBULFeOsSNH0rNfP7zy5WfhkiUsC5xPWje3Z35dWgQ04bsfpuOZx4cFS5awcPYsUqVKRWpXV8Z99hk9+vTFI3ceJn/3PY3erP+v9p3WzY26td/g/F9BBDRq9K+2LVKoEGNGDOfkgT8Z/MEH/2rbpBQrV56MXjm4cPEirTt1IqNXDgIXLwbiZ4Nwz5mLCxcvAnDur79o2roNWby9KVK6DJcuX2FZYCBOTk7PJRcRSb4MfQUjIg9ydna+fXjPnjTu7pmfHCwJdO/dhwzp0zN62NAXdoyho0YRdOEiM7779oUdw5qCg0MoWKpU6N27d5/9PwYRSVbUsioi8ooIuXaNuQsW0qVjR2unIiLy0qhYFRF5BYydMIGCJUvS6M36z206KRGRV4G6AYhIAuoGINakbgAi8jC1rIqIiIiIzVKxKiLyBLUbNea7H36wdhoiIq8lFasiIq+YwUOHUaxsObLk8savRAm+nJRwUv+z587TuGUrsvnkxadwESZ8PTnR/Zw4dYr02bLTpvNbLyNtEZFnomJVROQV45TSibkzfuDS6VMsCwxkxuw5zJo3D4DY2Fiat29P8aJFOXf0CKuWLeX7GTNYtHRpgn2Ypkmf996nRPHi1jgFEZGnpmJVRGzWpCnfkK9oMbLk8qZgiZIsXr4ciJ9wvn5AU7zy+5I9bz5atu/A1eBgy3a1GzXm05EjqdukCZlz5qR63XpcDQ5m+JgxeOX3JV/RYqxau9YS3713H97p35/m7drhnjMX5avX4I8DB5LM69eNv1GxZi088/hQtmo1ftu82bJu/caNlKxUiSy5vPH2K8iQYcOf++vyycCB+Pn6Ym9vTz4fHxrUrcvO3XsAOHn6NGfOnuWj9wbg6OhI3jx5aN+6NTPmzE2wj5lz5pDNw4PKFSo89/xERJ4nFasiYpNOnj7NyLFjWbFkMVfPneXXVSstt+aMi4uj79u9OHXgTw7u2U1MbAzvDRqcYPuFS5fx5ejRBB0/TspUKalRrz6ZMmbk7OFDDBzQn3f6DyAmJsYSv2DJUrp16szFUydp1rgxzdu1JyIi4pG8Dh0+QqcePRg9bCgXTp5g5Cef0KbzW1y+cgWAHn360v+d3lw9d5YDu3fRsH69JM/RM49Pko+mbdo81etkmibbd+2iQP78ltfm/5f/v7i4OI4cPWp5Hhwcwvivvuaz4cOe6hgiItakYlVEbJKDvQOmaXL02HHu3btHFnd3fPPlAyCHlxc1q1XDycmJdGnT0r93H7bu2JFg+1bNm1Egf35SpkxJw3r1iY6JoWeXLjg4ONAiIIBrf//NpcuXLfHVq1SmRrWqODo60vftXgCP7BPgh9mzaduyJRXLlcPOzo7qVatQtnRpVq6Jb6lNkSIFZ86d4+/r10nt6kpJf/8kz/HS6VNJPpbc/1r/SYaNHs3de/d4q0N7APLmyYNXtmyM+uILIiMjOXr8OHMCAwm9c8eyzXuDB/Nu795kzpTpqY4hImJNKlZFxCZ558rJd19N4tvp0/H2K0hA6zacOHUKiL+TU8fu3clbpChZvXMT0Lo1169fT7C9e+Z/5ol1dk6VoDBzdnYGICw83LIsm6en5WfDMMjm6WFpLX1Q0IULTJ81K0Er6NYd27kSfBWAwB9ncuTYMYqWKUulWm+w5pdf/vuLkYQvJ01i6f9+4udFC3FxcQHA0dGRhXNm88efB8hbtBhv9exF25YtSZ8uHQBr16/n0qVLdG7f7oXlJSLyPDlYOwERkaQ0bdSIpo0aER4ezuBhw3mn/wDWr/iZoaNGERUVzY6NG8iYIQM7du2mVoMG/+lYFy9dsvxsmiYXL13GI2vWR+KyeXryTo/ufPrRR4nup2jhwgT+OJPY2FgWLV1G27e6EHT8mKWYfJB7zlxJ5lOuTBmWLwhMcv24r75ixuw5rP3fcjw9PBKsy583Lz8tWmh5/vHwEVQoVw6AjZs3c+zECXIXLARAeHg4MbGxFPAvwdHf9yV5PBERa1GxKiI26eTp01y6dImypUvj5OSEq4sL9vb2ANwJC8fF2Rm3NGkIuXaNLyZO/M/H27h5Cxs3baZShfJ8M3UapmlSoWzZR+I6t29Hk1atqVa5MuVKlyY6Opp9f/xBNg8PPLJmZen/fqLOG7VI6+ZGmjSpMQzDkvfDgs+fe6ZcJ3w9makzZrL2f8vxyp79kfWHjxwhV86cODo6suaX9cwODGTVksUAfDxwIAN697HETvrmG06dOc3k8eOfKRcRkRdNxaqI2KSoyEiGffYZx0+cxN7eniKFCzHpi7EADP7gfbq90xtPHx+yZ8tOt06dWL9x4386XouAJnz3w3RadexIbm9vFs6eRapUqR6JK1q4MNOnTOHTESM5efo09g4OFC9ShC9HjwZg0bJlfDBkCNHR0Xh5ZWf2tKmkTJnyP+X2sI9HjMDR0ZEyVapalj3YErv055+ZPvNHIqMiKVTAjwU//khBPz8AUru6ktrV1bKdi4sLKVI4Jeg2ISJiS4wHR4yKiDg7O98+vGdPGnf316d46d67DxnSp2f0sKHWTuW1FxwcQsFSpULv3r3rZu1cRMQ2aICViIiIiNgsFasiIiIiYrPUZ1VEXnvff/2VtVMQEZEkqGVVRERERGyWilURERERsVnqBiAiycr2XbsYO34C+/bvxzAMvLJnp3XzZvTs2tUy32lcXBwF/EvgYG/Pob17MAyDxi1bsWPXLgCioqOJi4sjpZMTANmzZ2ff1i0U8C9ByLVr2Nv9839+kcKF+eXnn17+iYqIvCbUsioiycaaX34hoFVrateqycE9u7l46iTTpkxm977fuRMWZonbsGkTN2/e5EpwMJu3bQNg+YJAgs+fI/j8Od7r25f6depYnu/busWy7Zzp0yzLg8+fU6EqIvKCqVgVkWTBNE3eHzSYAX370LNLFzKkTw+An68vc6ZPI63bP9N2zp4fSIN69ahTqxZz5id9S9P/4q+gIFwzuzN3wQIKlihJllzefDpyJJevXKFeQABZcnlTp3FjQq5ds2xz+uxZmrRqjVd+XwqWKMnk776zrLtw8SL1A5rild+X7Hnz0bJ9B64GB1vW127UmKGjRln2XaNefYIuXHgh5yYi8jKpWBWRZOH02bOcDwqiaaNGj427cfMmq9eto1WzZrRu3oyfV6/mdmjoC8tr89Zt7N68iQ2rV/H1d9/ToWs3vhg1ivPHjmJnZ8f4r74G4O7du9QPaErN6tU4c+ggPy1axHfTf+DnVauB+K4Lfd/uxakDf3Jwz25iYmN4b9DgBMcKXLyEz0eMIOjEcTJmyMCIMZ+/sPMSEXlZVKyKSLLw99/XAciaJctj4xYsWUL6dOmoUqkitapXx9XFhSXL//fUx+nYrTueeXwsj/cGDXps/MABA3BxccHP15dCfgWoUL4cBfLnJ2XKlDSsV58/Dx0CYM369WTMkIGeXbrg6OhIbu9cdOnYkcXLlwOQw8uLmtWq4eTkRLq0aenfuw9bd+xIcKzWLZpTsEABUqRIQbOAJvx56OBTn5eIiK3SACsRSRYyZIj/2v/K1avkypkzybg58wNpERCAnZ0ddnZ2NGvSmDmB83mrQ/unOs6PU7+nTq1aT52Xe+Z/blubKpVzgufOzqkIDw8HICjoAkeOHcMzj49lfWxsLIULFQIg5No1PhgyhB27dnPnzh2ABP1wHz6Wc6pUhIfffeo8RURslYpVEUkWfHLnJodXdpb+9BPv9e2baMwfBw5w6MgRgi5cYP6iRQBERkZyOzSUo8ePUyB//peZcgLZsnlSolgx1q9ckej6oaNGERUVzY6NG8iYIQM7du2mVoMGLzlLEZGXT90ARCRZMAyDL0ePZtykr5g6YyY3bt4E4PjJk3Ts3p1bt28ze34gJf2Ls3/7dnZu3MjOjRvZv307xYsWfWEDrZ5WnZq1uHTlCj/Mmk1ERASxsbEcPX6c3Xv3AnAnLBwXZ2fc0qQh5No1vpg40ar5ioi8LCpWRSTZqFOrFovnzWXlmjX4+Zcgm09eOvfoSUl/fxwdHFiyfDk9u3TB3T1zgkevrl1ZsGQJ0dHRTzxGuy5dcc+Zy/IoVLLUc8nd1dWFFYsXs37DBnyL+5Mjvy+9+vXj5q1bAAz+4H1OnDqFp48PdRo3oXbNms/luCIits4wTdPaOYiIDXF2dr59eM+eNO7umZ8cLPKcBQeHULBUqdC7d++6PTlaRF4HalkVEREREZulYlVEREREbJaKVRERERGxWSpWRURERMRmqVgVEREREZulYlVEJAk7d++hTJWqZMqRk7JVq1nmPE3KitWrKVK6DJly5KRm/Tc5ceqUZd3mbduo07gxHrnz4JXf95FtBw8dRrGy5ciSyxu/EiX4ctKk534+IiKvIhWrIiKJuHHzJs3atqVn1y5cPHmCbp070axtO27dvp1o/KkzZ+jS620+HzmCCyeOU6lCBVq270BMTAwALs7OtG/Vms+GD0t0e6eUTsyd8QOXTp9iWWAgM2bPYda8eS/s/EREXhUqVkVEErFi9WqyZ8tGhzZtcHJyolO7dmTJ4s6K1asTjQ9cvJiqlSpRu2ZNUqZMycAB/fn7+nW279oFQInixWnVvBm5cuZMdPtPBg7Ez9cXe3t78vn40KBuXXbu3vOiTk9E5JWhYlVEJBGHjx6lcMGCCZYVLVSYw0ePJhp/5OhRCj0Q7+joSAFf3yTjH8c0Tbbv2kWB/Pn/9bYiIsmNilURkUSEh4fj5pYmwTI3tzSEhYUlGh8WHk7ah+LTPib+cYaNHs3de/d4q0P7f72tiEhyo2JVRARYuGQJ7jlz4Z4zFyUqVsLFxYXQ0DsJYm7fDsXV1TXR7V1dXLj9UPytx8Qn5ctJk1j6v5/4edFCXFxc/t1JiIgkQypWRUSAFk2bEnz+HMHnz7Fv6xYKFijAwcOHE8QcOHQIP99HR/ID+D0UHx0dzbHjx5OMT8y4r75ixuw5rFq2FE8Pj2c7ERGRZEbFqohIIt6sW5egCxeYExhIVFQUs+bN48rVq7xZt26i8S2bNuW3zZv5ZcMGIiMjGTthIunTpaNC2bIAxMXFERERQXRUNAARERFERERYtp/w9WSmzpjJqqVL8Mqe/cWfoIjIK8IwTdPaOYiIDXF2dr59eM+eNO7uma2ditXt2LWbdz/8kDPnzpHH25uJY8dSplRJALbv2kWTlq0IPn/OEv/zqtV8PHw4l65coWihQkyZOIF8Pj4AbNm+nbqNmzxyjLCQYABcM7vj6OhICkdHy7pyZcqwfEHgizxFmxMcHELBUqVC796962btXETENqhYFZEEVKyKNalYFZGHqRuAiIiIiNgsFasiIiIiYrNUrIqIiIiIzVKxKiIiIiI2S8WqiMgrZsv27Xjlf/r5W0VEXmUO1k5ARORl2b5rF2PHT2Df/v0YhoFX9uy0bt6Mnl27Ym9vD8TPh1rAvwQO9vYc2rsHwzBo3LIVO3btAiAqOpq4uDhSOjkBkD17dvZt3UIB/xKEXLuGvd0/bQBFChfml59/+lc5du/dhwzp0zN62NDnc9IiIq84tayKyGthzS+/ENCqNbVr1eTgnt1cPHWSaVMms3vf79wJC7PEbdi0iZs3b3IlOJjN27YBsHxBoOXuVu/17Uv9OnUS3O3q/82ZPs2yPPj8uX9dqIqIyKNUrIpIsmeaJu8PGsyAvn3o2aULGdKnB8DP15c506eR1u2fKT1nzw+kQb161KlViznzX8yE/BEREXTv3QevfPnxyJ2HMlWqcuzECabOmMnCpUv5dvp03HPmokKNmgBcuXqVxi1bkdU7N2WqVOXAwUMvJC8REVukbgAikuydPnuW80FBNG3U6LFxN27eZPW6dSyeM4eIyAg6dOvO7dBQ3NKkea75zFu4iCPHjnFwz27SpE7NiVOnSJ82Hd06d+L3P/54pBtApx49yZXDizOHD3HlajBN27Z9rvmIiNgytayKSLL399/XAciaJctj4xYsWUL6dOmoUqkitapXx9XFhSXL//fUx+nYrTueeXwsj/cGDUo0LkUKR8LCwjh56hQAvvnykdQdwy5dvsy2HTsY+emnODs7k9s7F2936/bUOYmIvOrUsioiyV6GDPFf+1+5epVcOXMmGTdnfiAtAgKws7PDzs6OZk0aMydwPm91aP9Ux/lx6vfUqVXriXGtmjXj8pUrvDNgAFeDQ2hQry6jhw4lTerUj8RevnIFVxcXS9cFgBxe2Z8qHxGR5EAtqyKS7Pnkzk0Or+ws/SnpAU9/HDjAoSNHmDlnDt5+BfH2K8i8BQvZt/8Pjh4//lzzcXBw4MP+/dmzeTO7N/3GsWPHmThlCgB2dkaCWI+sWQkLD+fGzZuWZX8FXXiu+YiI2DIVqyKS7BmGwZejRzNu0ldMnTHTUvgdP3mSjt27c+v2bWbPD6Skf3H2b9/Ozo0b2blxI/u3b6d40aLPfaDV5m3bOHT4CLGxsbi4uOCYIgX2dvFTZ2XOlIlzf/1lifX08KB82bJ8PHw49+7d4+y583wzbdpzzUdExJapWBWR10KdWrVYPG8uK9eswc+/BNl88tK5R09K+vvj6ODAkuXL6dmlC+7umRM8enXtyoIlS4iOjn7iMdp16Yp7zlyWR6GSpRKNCw4JoX23bnjkzkOhUqXJ7ulJv7d7AdChTVsuXLxINp+8VH7jDQBmfPsNFy9dxtuvIK07daKTBliJyGvEME3T2jmIiA1xdna+fXjPnjRJDfgReZGCg0MoWKpU6N27d92eHC0irwO1rIqIiIiIzVKxKiIiIiI2S8WqiIiIiNgsFasiIiIiYrNUrIqIiIiIzVKxKiLykOjoaPoP/IjsefORPW8+Bnz0ETExMYnGht65Q6cePcjqnZtcBfwYM258gvXvDBhAsbLlSO2ehe9++CHBuqioKNp0fosC/iVwzezOml9+eWHnJCLyqlKxKiLykM/HT2DPvn3s27qVvVu3sGPXbr6YOCnR2Pc+GsTt26Ec+2M/v6z4mR/nzmX+wkWW9YUK+DH+8zGUKF4s0e3LlS7FtCmT8fTweCHnIiLyqlOxKiLykDmBgXzY/13c3TOTxd2dD/v3Z/b8+SzI7PcAACAASURBVI/E3b17lyX/+x9DBw0irZsbPrlz06trV2Y9ENv9rc5UrVQJJ6eUj2yfIkUK3u7enfJlymBvb/9Cz0lE5FWlYlVE5AE3b93i0uXLFC5Y0LKsaOFCXLh4kduhoQliT505Q0xMDAX9CliWFSlciCNHj760fEVEkjsVqyIiDwgPDwfAze2fGyj9/89hYWEJYsPCw0nt6oqd3T+X0rRubtx5KE5ERJ6dilURkQe4uLgAEPpAK+rt27cBcHV1TRDr6uLCnbAw4uLiLMtu3b5N6ofiRETk2alYFRF5QLq0afH08ODg4cOWZQcOHSabpyduadIkiPXJnRsHBweOHD1mWXbw0GEK+Pq+tHxFRJI7FasiIg9p27Iln4+fQHBwCMHBIYydMIEObdo8Eufs7ExAw4YM+2w0t0NDOX32LN9Mm0bHB2KjoqKIiIggLi6O2JgYIiIiEkyDFRkZSUREBKZpEh0dvz42NvalnKeIyKtAxaqIyEMGDuhPieLF8a9QAf8KFShdsiTv9+sLQOOWrfhi4kRL7Lgxn+Hq6kq+IkWpUb8+7Vu3pnWL5pb1DZq3IKNXDnbs2sWHH39CRq8cfD5+gmV9sXLlyeiVgwsXL9K6UycyeuUgcPHil3eyIiI2zjBN09o5iIgNcXZ2vn14z5407u6ZrZ2KvIaCg0MoWKpU6N27d92eHC0irwO1rIqIiIiIzVKxKiIJGGDGxCZ+a1GRFy0mNgYD9JWfiFioWBWRBFKkSHHl1Jkz1k5DXlMnT58mRYoUl62dh4jYDhWrIpJAWHj47ImTJ9/TiHR52WJiYpg0Zcq9sPDwOdbORURshwZYiUgChmGkcnV1Xe+RJUuRVs2aubi7ZzYMw7B2WpKMmaZJcHCIGbh4cfjlq1cPhIWF1TRN85618xIR26BiVUQeYRiGA1AtZcqU9VM6OWXhORarcbGx2WNjY4vZ29vvsbO3v/rcdiwvXFxsbJbY2NhS9vb2f9jZ2194bjs2TSIiI69GRESsBDaapqlO0yJioWJVRF6K+82zHwE9gPqmaR60ckryDAzDKAysBL4Fxpj6EBGRF0zFqoi8cIZhOBJf3PgD9UzT1ACaV5hhGJ7EF6z7gF6maUZbOSURScY0wEpEXijDMNyAVUBWoJIK1VefaZqXgEqAJ7DSMIw0Vk5JRJIxFasi8sIYhpEd2AqcARqapnnHyinJc3L/d9kAOAtsu/+7FhF57lSsisgLYRhGcWAnMJv4r4o1aCaZuf877QXMAXYahlHMyimJSDKkPqsi8twZhlEP+BHoaZrmEiunIy+BYRhNie+X3ME0zdXWzkdEkg+1rIrIc2UYRi9gOvCmCtXXx/3fdQPgB8Mwelo7HxFJPtSyKiLPhWEYdsBY4E2grmmaumfra8gwjNzAauBn4EPTNOOsnJKIvOJUrIrIf2YYhjPx/RYzAY1M07xh5ZTEigzDyAAsB0KAdroblYj8F+oGICL/iWEYmYGNQARQU4WqmKZ5HagJRAEb779HRESeiYpVEXlmhmHkJ37E/3qgrWmakVZOSWzE/fdCW2AD8TMF5LNySiLyilI3ABF5JoZhVAIWAx+ZpjnD2vmI7TIMozPwGdDMNM0t1s5HRF4tKlZF5F8zDKMNMAFobZrmr9bOR2yfYRg1gXlAP9M051s7HxF5dahYFZGnZhiGAQwGugL1TNM8bOWU5BViGEYhYCUwDRhl6gNIRJ6CilUReSqGYTgC3wNFgPqmaV6xckryCjIMwwNYAfwJ9DBNM9rKKYmIjdMAKxF5IsMw0gJriJ+aqrIKVXlWpmleBioD7sBqwzDcrJySiNg4Fasi8liGYeQAtgHHiJ9DNczKKckr7v57qBFwAth+/z0mIpIoFasikiTDMEoAO4i/fWof0zRjrZySJBOmacYAvYEfgB2GYfhbOSURsVHqsyoiiTIM401gBtDNNM3l1s5Hki/DMJoQ3x+6s2maK6ydj4jYFgdrJyAitscwjHeAQcSP+N9j7XwkeTNNc5lhGJeA5YZheJmmOcXaOYmI7VDLqohYGIZhD3wJ1AbqmqZ5zsopyWvEMAxvYPX9x/vqdiIioGJVRO4zDMOZ+Enb0wJNTNO8aeWU5DVkGEZ6YBlwg/hb+N61ckoiYmUaYCUiGIbhDmwC7gBvqFAVazFN8wbwBhAO/Hb/vSkirzEVqyKvOcMwfIFdxH/12sE0zSgrpySvOdM0I4H2wFpg5/33qIi8ptQNQOQ1ZhhGVWAB8IFpmrOsnY/IwwzD6Ah8DrQwTXOTdbMREWtQy6rIa8owjPbAQqCVClWxVaZp/gi0BhYZhtHOyumIiBWoZVXkNWMYhgF8AnQkfmqqo9bNSOTJDMPwA1YRP/fvCFMfXiKvDRWrIq8RwzBSANOAAsCbpmletXJKIk/NMIwswArgCPE3q1D/apHXgLoBiLwmDMNIS/yAFTegigpVedXcf89WAdIBa+6/p0UkmVOxKvIaMAwjJ7ADOAgEmKYZbtWERJ7R/fduE+AwsP3+e1tEkjEVqyLJnGEYJYkvVL8zTbOf7gokrzrTNGNN0+wLTCW+YC1h7ZxE5MVRn1WRZMwwjIbE91HtYprmz9bOR+R5e+A93tU0zZ+snY+IPH8O1k5ARF4MwzD6Ah8AdU3T3GftfEReBNM0fzIM4zLwk2EYOU3TnGTtnETk+VLLqkgyYxiGPTAeqEH81FTnrZuRyIt3v+/qamA90F/dXUSSDxWrIsmIYRguwHzAlfiBVLesnJLIS3N/doClwB2gjQYSiiQPGmAlkkzcn4NyM3ADqKNCVV4399/zdYBbwKb7fxMi8opTsSqSDNy/u88u4CegsyZLl9fV/fd+J+JvHrDTMIwCVk5JRP4jdQMQecUZhlEdCCS+n95ca+cjYisMw2gHjANamqa50dr5iMizUcuqyCvMMIyOxPdRba5CVSQh0zTnAM2BQMMwOlg7HxF5NmpZFXkFGYZhAMOAtsSP+D9m5ZREbJZhGL7AKmAOMNTUB5/IK0UtqyKvAMMw6hmGkf7+z07AbOANoIwKVZHHu/83UhaoDcy6/zeEYRjpDcOoZ9XkROSJ1LIqYuMMw0gN/AUUBO4By4kf8d/WNM271sxN5FViGIYzMBdIBzQBUgGHgRymad6xZm4ikjS1rIrYvrbAb0BKYCfwO9BMharIv3P/b6YZ8AewA3ACNgFtrJiWiDyBilURG3a/b2ovYCOwDfjaNM0BujuPyLMxTTPWNM3+wBRgO7AB6HX/b01EbJCKVRHbVoH4ryyHEj+gKtYwjAXqZyfybO73/14AxBD/NzUUyACUt2ZeIpI09VkVsWGGYewFihHfRzWC+O4AvwHLTNMMtWZuIq8iwzDcgMZAVaAa8V0B0gP7TdMsZc3cRCRxKlZFbJhhGLOBI8Tf7/yMptwReX7uf/WfGwgA/EzTbG/llEQkESpWRURERMRmOVg7gdeJYRi5nRwd+6RwdKgXFxfnau185PVmGEaUaZrbwiMivzJNc5e18xF5WoZhuNjZ2fVwc3NrGxsTkwXQ4Ch5MQwjzt7e/vTNmzenA3P07ZZ1qGX1JTEMw9cphePO5lUqulQpWtghjYuzrq5iVfeioth7/KQ5feW6e3cjI1uaprnC2jmJPIlhGClTp3bdUrZs2YJ9evdO5Z0rF/b29tZOS5Kp6OhoDhw8yIiRo8IvXrw4/86dO92sndPrSMXqS5LaOdXS9m/UaNzhjeqqUcWm7Dl2goFTfwwKu3cvh7VzEXkSwzCa+/v7/7Bz+zZXFanysoSGhpIjl/e90NDQQqZpnrF2Pq8bTV31kkTFxLxRu5S/ClWxOSXy+QBkMgxDxarYPDc3t4BOHTuqUJWXKk2aNLz5Zn2Iv2WvvGQqVl+SqOgY54xuaaydhsgj7OzsSOvqEk38XJMiNs3Bwd49a9Ys1k5DXkM5vHKkRNdJq1Cx+vIYdla4QcrKnXvo8Nm4l3a8nuMns3jT1kTX/bhmPZ/OnPvScpGnZ2cY6g8krwjDsLN7+R9d1arXYMqUb/71dj17vc2Qjz+2PN+1azd+hQrhli49U6dNf54pJso7jw8rV6164cd5Hdjb2xloMJ9VaDYAK6nS70PLz5FR0djb2+Fw/2ut2qX8Gdi6eaLbNRo8nPdaBlChkN+/Puasdb+y/dBRpr7Xx7Ls/e9+4M/TZ1k3dgT//wHw3U+rOR50gYm9u//rYzxOxzo1n8t+/jx9lv5TpjF3yPt4ZEhvWf7xD3OIM01GdUm+UyUu3rSVlTv3cObyFSoU8mNMt06Pje85fjKHzp23vLcAfvliFCkc9acvycfnY8eyevUaNm/6zbKscUAA27ZtJ/jKZcu17eNPPuH3/X+weuXzHUv446zZfPPNN+zZ/eikGt9+MyXB80+GDqVd27YM/PDDR2IT453Hh+DgYOzt7bGzs6OAry9ffvEF5cqVfS65J1dTpnzDrNmzOXT4MPXr12PxwoWPja9WvQY7d+3C0dHRsuxa8FWcnJxedKryFPSJZSWbJn5u+bnn+MlUK16EZlUqvtBjFvfJw7SVa4mIiiJlihSYpsnBM+dI5+rK6UtXyJvdE4DfT52m4r8shuPi4l5EyokqmsebhuXLMHJ2IFP69cIwDDb/eYjfT54i8OOn+wB4GjGxsQmKvP8iIiqKmNg4XFOl/E/7yejmRuc6tdhz/CTXQ5/uBlZ9Axq+8PeWiDVVrlSZocOGc/fuXZydnTFNkx07dpIpU0YOHjxI0aJFAdi8eQv16/+7OxU/72vb+fPnKViw4L/aZuGCQOrXq0dsbCyTvvqKgGbNuHzxAoYVvq170e7evUtMTAxp0vy3bnNZPbIyaNBHbNiwkavBV59qmy/HjuXtt3v9p+PKi6FuADbGNE3m/fobTT4eSc0Bg+nz1XdcCLkGwJAfZnP15i0GTZtFlX4fMn7RcgC+WvozDQYNo2q/gbQeMZZth44kum/fHNlxdHDg4JlzAJy6dJlMad2oWNiP30+eBuKLqmN/BeGfL89jc4H4Vt5Z636l05gJVO77IRf/vp7geGH3Iug5YQqj5iwgNi6OaSvXMnDqTMv60j3fZdmW7bQYNoZq737EpzPnEh0TY1m/eNM2Gg4eTo3+gxi/aDk9Huhi0KNhXa6HhrJ0y3Zuh4fzeeBiPmrTnDQuzsz/dRNNPx1Njf6D6PPVd1x+IK95v/5GwCejqNpvIAGfjGLFjt2Wdb+fPE2t94aweNNW3hw0jJ4TphAZHc3wWfOp+d5gqr37EW1GfsHZK0934TNNk30nTjF8diB1P/yUc0+53eNULVaYykULkdbV5T/vSyS5KFHCHycnJ3bs3AnAwYMH8fTw4M369dm8eQsA9+7dY+++fVSpXAXTNBk/YQI++fKTMbM7tevW4/Tp05b9eefx4fOxYylTthyuadw4cybh4O/Q0FCq16hJ127diY2NfWxunTq/xfsfxP8T7ZUzF2fPnqVFy1akSZuOoKAgoqKiGDxkCLl98pI5S1aat2zJtWvXEt2Xvb09bdu0ISQkxBLzxx9/ULFSZTJkykwWD086dX6LO3fuJLp9UFAQtd6oTeYsWcmY2Z3GAQFcuXLFsr5a9RoMHjKEmrXewC1deipWqsxff/1lWX/y5EnebNgI96weZHLPQsdOnS3r1v3yC6VKlyF9xkwU9y/Brxs2PPZ1eZBpmvy2aROd3+qCZ3Yvjhw5+tTbJqVJ48Y0atiQjBnVxTQ5ULFqY9bs3seCjVv4sudbrBozjLzZPRnwzXRiYmMZ+VZ7sqRLy+iuHdg08XP6N28MQN7snsz6aAC/jh9Ny+qVGfLDbG6EPnqxcrC3p4h3LvafjL/w7j95mmI+uSnmk5v9p+Iv1IfOnsfRwYH8Xtkfm8v/W71rL8M6t+W3iWMSfCV//XYoPcdPpmCuHAxu1xL7JPqYbdx/gO8HvMPiYYM4cOYca/b8DsDe4yf5/ufVjOrSgbVfjCBTWjdLkQ3g5OjIJx1a8+1Pq/h0xlzK+PlSsXBBFm/ayurde5n0TjfWfjGCInm8+fD7mZbWkazp0/NNv15sGD+a91o0YWzgEk5fumzZ7527dzl3JZjFQz/i6z49WLVrL6cvXWHZ8CH8Om4UI95qh5uz82N/h39dDeHbn1bRaMgIvly4FK9MGZk35H0KeecE4OqNm1Tv/1GSj7GBSx67/39r2sp11BwwmPajx7Fh/5/Pdd8itsDBwYFy5cqxefNmIL4FtVKlSlSsWJFNW+KX7di5EycnJ/z9izNn7lwmffU1/1u2lEsXgihapDANGjUi5oF/lmfPmcOc2bMIvXWTnDlzWpZfvXqVqtWqU7p0KaZN/f5fzfEadP4cXl5eLFwQSOitm3h5eTFo8BD27vudHdu2EnT+HOnTpadr98S7YEVHRzNr9mzy5MlDxowZgfgBkmM++4yrly+xf99ejh07xoiRoxLdPi4ujv793+XCX+c5deI4MTGx9H333QQxc+fNZ/y4L7kWfJWMmTLyyadDAQgLC6PmG7UpWcKfc2dOczHoLzp16gjAgQMHaNO2HV98MZa/Q4IZM+YzmjVvwaVLlx77epw4cYIhH3+Mdx4f+vTti49PHv7c/ztly5aJf72CgkifMVOSj7ff6f20L/1TGTZiBBkzu1OyVGmWLF36XPct/426AdiYNbv30bJaJbw9sgLQ/c06LN+6gyPn/6JIbu9Et6ldyt/yc4NypZm19leO/hWUaL9W/3x52HIwvuV1/8kz1CldgqJ5vBkxO5C4uDh+P3maonm8sbeze6pcmlaugFfmTAmOcSHkb7qN+5qmlSvQqnrlx55v+zeqk9Y1/mZe5fx8ORF0EcqVZt3e/dQpU4KCueJnU2pbsyoLf9uSYFu/nDloUL4Ma3bvY0mXQQAs3bKDdxrXxzNT/IW8U+0azP1lI+eDQ/DOmoVqxYtYti/r50uR3Ln449RZ8nh6AGACbzeuT8oUKQBwtLfnbmQk568G45fTC+/HjELed+IU3/xvJVdv3KRmiWKM6dYJ3xzZH4nLkj4dG8Z/9tjX5Xnp1ag+ubJmIWUKR3YcPsbHM+aQ1tUV/7x5XsrxRV6WqlUqs2LFSgA2bdlM2zZtqFihAm916UpcXBybN2+mQoUK2NvbM3fefPr26Y2fX/w1cviwYUydNp3du/dQvnw5AHr16ImPj0+CY5w+c4ZKVaryds+e9O3bh//KNE2mTpvG9q1bcHd3B2DE8GFk8fAkPDwcF5f4b1Bat2mLg4MDd+/exdHRkXlz51j64RYp8s81zcPDg3feeZuvv56c6PFy5sxpKbydnJz48P33CWjWLEFM+3ZtKVSoEACtWrZk5Kj4wnflqlW4uDjzyQODxSpXqgTA1GnT6dihg+V5rZo1KV++PD//vIKePXs8ksdvmzYxaNBggi5coEXz5ixZtAh//+KPxHl5eXHj78RbmZ+30aNGUaCAL6lSpWLN2rW0aduOjBkzUqXy4z/D5OVQsWpjQm7dImv6f1ooHR0cyJw2Lddu3U5ym3m//sbP23dz7dZtDAPuRUZxOyw80djiefPw/Yo13IuM5MCZs3zUpjmuqVKROW1aTl+6wh+nzliK3KfJJUv6dI8c45d9+0nr6kKjCmWeeL4ZHuiX5JTC0ZL337duU9I3r2WdYRi4p0v7yPa5PbLini4trqlSAXDl+g0+mTmXB2deiI2LI+TmLbyzZmH17r0E/rqZK9dvYGISERVN0Tz//BOQ2jkVLin/6Vdap3QJrt26zWfzFvH37VCqFCtEnyYNE+17evNOGBdC/iZPNg98snmS/aEi3hr+vzUXoFKRgtQu5c/G/QdUrEqyU7lSZT75dCjh4eFs376D77/9Fjc3N7J5enLw4EG2bNlq6a966dJFcuT4Z1rhFClSkC2bJ5cu/9MS6JXD65FjLFi4kIwZM9Cly1vPJedr164RHh5O5arVEix3cnLi4sWL5MuXD4D58+ZSv1494uLi2LptG42bBLDx1/UULVqUkydP8t4HH/D77/sJDw8nLi6OTJkSv/aEhITQr39/tm3bTuj9Pu8PdxnI4v7PP+TOzs6E3b8mX7hwgdy5E79unP/rLzZv3syMmf9084qOjqZY0SKJxoeEhHDq9GmKFC5M4cKF8fGx/vWoTJnSlp8bvPkmbVq3ZunSZSpWbYSKVRuTOW1arty4YXkeExvLtVu3yZTWDeCRDvV/nDrDzNXrmfJuL3w8PbCzsyPgk1EkNQ9Rfq/spHBwZPnWnaRPnZp0qeNbNYv55Gbn0WMcPR9Ev6YNnyqXxPIB6Fi7Bsf+usC7U6Yx4e2upHqG0ZQZ07px9cZNy3PTNAm+eeuJ22VJn473WjShlG++R9ZduX6DkbMX8FWfHhTzyY29nR3vTPwmwWtlPDQriYO9PZ3r1qJz3Vpcu3Wbj6b9yNz1G+nRoO4j+69ZohiVixRi26EjrNmzj/GLllOmQD5qlypBWb/8ODrE/7ldvXGTlsPHJHkOj5sN4r+yMwx01zpJjvz9i5MyZUqmTp2Gu3tmS8FWqVIl1v3yC3v27uXLL74AwNMzW4K+mNHR0Vy6dBlPD0/LssSubR99+CH7fv+d+m82YOWKny0tn88qY8aMpEqVij27dpInz5MLNjs7OypXqoRPnjxs2LiRokWL8vY7vfH19WXOrFm4ubkxd948y1f3Dxs0eAhRUVHs37eXjBkzsm3bdipXrfpUuXp5eXH2bOI3bvLKnp13+/VlxPDhT7WvFs2b06hhQ1auWsXcefN4t39/atWqSZvWran9xhukuP/NVlBQEAULJ17wArRp3fqR2RaeFzs7O10rbYj6rNqY2qX8WfTbVs5euUpUdAzfr1hDutSu+OWMbwVInyY1F6/9bYm/GxmJvb0daV1diTNNFm/aypXrN5LaPfZ2dhTJk4s56zdSzCe3ZXkxn9ws2LgFRwcH8mbP9lS5PO4Yn3ZoTdb06Xh3yjTuRUb+69ehVolirN39O0fPBxETG8v8DZsS7Yf7sCaVyvH9ijUE3R8IFnbvHhv2/0lMbCz3oqIASOfqigH89sdB/jxz9rH723fiFCcvXiI2Lo5UTk442tsn2f8WIIWjA9WKF+GLHm+xfMQQivnk4ce166k78FNOXYzvG5slfTo2Tfw8ycfjCtWY2Fgio6OJjY3DNE0io6MTDEp70J2799hx+BgRUVHExsWx4/Ax1uzZR5WihR57ziKvInt7e8qXL88X48ZRqWIly/KKFSsw6auvcXJyolix+FkB2rRuxdeTp3D06FEiIyP5dOhQMmfOROnSpZ54jB9nziBHjhzUf7MB4eH/fINlmiYREREJHk8qduzs7OjWtSsD3n/f0r/z2rVrLFu+PMlttm/fwZGjRy0zCty5c4fUqV1JkyYN586dY9Kkr5Lc9k7YHVycXXBzcyMkJITRY5L+p/lh9erWJSwsnJGjRnHv3j0iIyPZsjV+wGvXLl34YcZMNm/ZQmxsLBEREWzZupVz584luT8nJycCmjRh+dKlnD55gsoVK/HZZ2PwzO7FwYMHgfgCOfTWzSQfjytUY2JiiIiIICYmhri4OCIiIoi6/xnwsFu3brFm7Vru3btHbGwsa9auZe68eTRq1PCpXx95sdSyamPqlinJjTt3GDBlGnfu3sM3Z3bG9epimUKpY+0ajFu0nOkr11G/XCn6NGlA5SKFaDX8c1I4OtCgXBl8snk89hj+eX3YcfjYQ8WqNzfvhFHOz9dSjD0pl8exs7Pj4/atGDl3If0mT2XC293+1etQyjcfXeq9wYdTZ3IvIpK6ZUpSIKeXpXUyKc2rVMTOMHj/2+mE3LyNq3MqivvkpkrRwnhnzUKH2jXoMWEymPEj68sU8H3s/q6H3mFs4BJCbt3CydGRsn6+tK35dC0Rbq4uNKtSgWZVKhAUHJKge8GzmrlmPdNXrbM8r9TnA4r75Obb/u8A0O/r7ymax5uOdWoSExvLtJVrOR8cjIGBZ8YMDGrTItFWZ5HkoGqVyqxZs4aKFStYllWqWJGQkBDq1KljGQzVvl07QkJCaNCoMTdv3qREiRL8tHw5Dk+4vkD8tW3GD9Pp0rUb9eq/ycoVPwOw/48/cEmdcLql3fdnJ3icz0aPYsznn1O1eg2Cg4PJlCkTDRs0oEnjxpaYFi1bWXL38MjKZ6NG8UatWgB8+cUX9OjVk68nT8E3f36aNg3g+6nTEj3W0E8+oWOnzqTPmIkcObzo1aMn69atSzT2Ya6urvyydg3vDniPiTlyYmdnR/169ahUsSLFixdj1o8zGTRoMMdPnMDBwQF/f3++mjjhqfadIUMGevXqSa9ePTl58uR/nrYKYNTo0QwfMdLy3CV1GipXqsTGDb8CULf+m1SsUJ6PBg4kOjqaYcOG0+rECQzDwDtXLqZ+/x01qlf/z3nI82Gomfvl+D/27js6qqKN4/h30hukEnqRjjTpIEjvXVGKFBFEBUFpSgkgoaM0FVApAtJBkN4VkCKd0EG6IQkECEkI6dl5/9i8qzEBQZLckDyfc/aY7J2993cjuftkdu6MUkofmj0tU86Llx5MJhMth41mZLdO1Cj95AJTPLs3R40P8797r77W+oTRWYR4Ei8vr73z5s6p3bpVK6OjiCxmtK8vY8eNH6219jU6S1YjwwBEhvXLCT+iY2OJjo1l7ubtaEjSGyyEEEKIzE+GAYgMa+uhY4xfvBKNpmie3Ezp3dMypZQQQgghsgYpVkWGNaXPe0ZHEEIIIYTBZBiAEEIIIYTIsKRYFRlW72kzWb1nn9ExhBAiQ6vfoCGzZs02OoYQaUaKVSGeUWxcPG99PoHGg0ckeT44NJRPv5tPo8E+NB48gmFzF3L/KeaGFUKIzOSzIUMpVbo0ru4eFClWnEmTJ6fY7t69e3jnyk3VaslXO/zu+zmUKPUy2VzdKFaiJHv27k3r2CIDk2JViGf0w5YdeLomnwfwi+VrsLayYv24UawbaMAu6QAAIABJREFUNxKTycS0VY+f3FsIITIjBwd7Vq9cSci9u2zeuIE5c+cx/4cFydoNGDiI0i+/nOz5hYt+ZOasmaxasZzw0Afs+fUXihQunKydyDqkWBXJLNm5m1bDfanXfyivjxjLjqPmqTdvhzyg74zZNB48gkaDfPj0u/ncCwuzvK73tJnMWreJPtNnUeeTIbz35VfcCwvjuw1baDx4BK2G+/LbqbOW9mMWLWPCkpUMnj2Puv2H0G3CFC7c9H9srkPnL/LOxKk0GDiMLuO/5MiFS5Ztv5+7QKcxk6nXfyjNhozim7Ub0uAnA9cCg9hz6jTvNEk+WXTQ/fs0rPQKTg72ODnY07BSBa4FBqVJDiGE8aZOm0bBlwrj6u5B0eIlWLFyJWBeJrRxk6Z458qNl3dOXm/XjqCgv64F9Rs0ZLiPDw0bNSabqxu1XqtNUFAQoz7/HO9cuSn4UmE2bNxoaf9uj568/8GHtHn9dbK7uVO5SlWOH3/8lMjbd+ygarXqeHjloGKlyuz65RfLtm3bt1PulVdwdfcgT778DBk6NNV/LmN8fSlTpgzW1taULFmS19u25cCBA0na7Ny1C39/f7p165bkeZPJxGhfX6ZNnUr58uVRSpE3b17y58+f6jnFi0OKVZHEzdvBzNm4lZkf92b3jEnM/fRjiiauiGXSms6N6rFp4mjWjPEhIcHE1H/0HG4/cpzBHd5gx5Rx2Nva0uvLr/HI5sKWyb70bN6YCUtXEp+QYGm/7chx3qxbi11TJ9CockU+/XY+MXFxyXL9cSuAkfMX80m7NuycMp6+r7di6JyFBIeGAjD2x+V0bVKf3TMm8ZPvcOpVePx60g0GDnvsY+CslFd+AfNyihOXrqL/m22xs7VNtr1j/TrsOu5HRFQ0EVFRbD96gpplk/caCCFefJcuXeLz0b7s2LaVsAch7Nu7h3JlzUsZm0wmBg4cgP/NG1y+dJH4+AQ+GTAgyeuXLV/BVzOmc/fObRwdHXmtTl28c3gTeMufET4+fPBhb+L/tpTy0mXL6NO7N/fvBtOxYwfavvEG0dHRyXKdOnWKzl268uWXX3Av+A6TJk3krfYdLMu59nyvF58OHkzYgxAuXTjPG6+/8dhz9PDK8dhHqzZtn+rnpLVm3759lClT2vJcVFQUn/Tvz6yZ3yRbKCcgIAB/f3/+uPQHhYsWo+BLhfmk/wCioqKe6ngic5JiVSRhbW3+J3E1MIjo2Fi8XF0pnDsXAHk8PahRuhR2tjZkd3aiW5MGnPjjSpLXN69WhcJ5cmNva0u9CuWIN5loX682NtbWNK1aiQcPIwgO/as3tmqpElR/uSQ21taWZUz/uU+Adft+p2WNqlQsXhQrKyuqv1yS8kVfsvTU2trYcCv4HqERETg7OFDmpYKPPcdfpk187GPaR70e+7o1vx0gp4c71V8umeL28kULcz8snEaDhtNwkA+hERH0bN74sfsTQry4bGxs0Fpz9tw5oqKiyJ07Ny8nfqRdqFAhmjZpgr29Pe7u7gz59FP27v0tyeu7dulM6dKlcXBw4I3XXycuLo6+fT/CxsaGzm93Ijg4mFu3blnaN2rUkCaNG2Nra8uggQMBUhzHOWfuPLq/8w51atfGysqKxo0aUbNmTTZsMPfU2tnZcfXqVe7du0e2bNmoVq3qY88x5N7dxz42rl/3VD+nESNHEhkVyQfv/7Xk9mhfX9q2aUPp0qWTtff3N5/zpi1bOHbkMId/P8ixY8fwHTPmqY4nMieZZ1UkkS+HFyO7dWLVnn2MXbycV4oW5pN2bSiUKych4Q+Ztvpn/K5c41HiX/SR0TFJXu/pms3ytYOdHR7ZXJJ8DxD1t9fk8nCzfK2Uwtvdjbt/K2b/L/B+CCf+uMKGg4csz8UnmCiRLx8Akz94lwVbd/LmqAnk8/bivRZNqFU2+YXwv7oXFsbiHb/yw2f9U9xuMpn4+KtvaVSlIt980psEk4mZazcybO4iZvR9P8XXCCFeXEWKFOGH+fOYOXMWPd/rRa1atZjyxWRKlixJcHAw/QcOZP/+A4SHhwPw8GHSmy1z5cxl+drRyYmc3t6W752cnACIiIiwPFcgfwHL10op8ufLR0BAYLJcN27eZO/evfyw4K8xonFxcVR4xfxp05rVqxk/cQIlSr1M0SJFGDlyBC1btHieH8VjTZo8mVWrf2L3L7twdnYGzD2/69Zv4OTxYym+xsnJEYBPBw/Cw8MDgIEDB/D56NFMmjgxTXKKjE+KVZFMo8oVaFS5AlExMXyzdiMTlqxkzuCPmb1+M3HxCSzxGYybiwt+V67xwdRvnutYt0NCLV9rrQl+EEoON9dk7XJ5uPF2g7p82KZ5ivspWSA/kz/oQYLJxPajxxk2ZyE7pozD0d4+Wdu6/Yc8Ns8rRQozo98HyZ4/d/1PQsIf0mXCFADi4xN4GBVFsyGjmP5RL3J5uBMU8oCO9WpbivJ2dWrSdfwUEkwmrK3kQwwhMpsO7dvToX17Hj16xGdDhvLBh73Zu2c3w31GEBsby4ljR/Hy8mL//gPUqVfvuY71p/+flq+11vjfukXevHmStSuQPz8D+n/C2Mf0RFasWIE1q1eTkJDAsuXLad+hI3fv3LYUk3+X3c39sXlq1arFlk0bH7t98hdfMGfuPHb/sot8iZ0KAHv27CUwMJCixUsA5iEBkZGR5MmXn1MnT1C8eHHs7e2TDQ/QWj/2WCLzk2JVJHHzdjB3HjygfNHC2NrY4GhvZym0IqOjcbS3w8XRkZDwhyzcuvO5j3fkwiUOX7hEpeJFWbn7NzSaCsWKJGvXtlYNBsyaS9VSxSlftDDxCQmcv/EnOd3dyOHmys7jJ3mtbBmyOTni4uCIUgqrxxSIe2akPI3Kk9QoXYp140Zavj997QYTlq5kyfDBuLo4Y2NtTb4cXqzeu58ezRpj0ibW/naQwnlyS6EqRCZ06dIl/G/dolbNmtjb2+Pi4oy1tTUADyMe4uzkjKurK8HBwUyYNOm5j7dr1y/s3LWLenXr8vU336C1pk7t2sna9XrvPVq2bk3Dhg2pVbMmcXFxHDl6lPz58pE3b15WrlpFq5YtcXNzw9XVFaWUJfc/hYc++E9Zv5wyhdnffsfuX3ZRsGDSIVm9er1Hhw7tLd+vWrWahYsWsWXzJjw9PbGysqJTx45MmTqNShUrEhcXx4wZX9GqZcv/lEVkDlKsiiRi4+P5bsMWrgfdwcpKUSJ/Poa8/RYAvVo2w3fRUhoMHE4uD3ferFOL389ffK7jNa1aidW79zHk+x/InyMHX37Y09Iz+XclC+RndPfOzFq3iZu3g7G2tqJUgfwM6mC+OWDHkRNMX7WO+IQEcnt6MP69btincBPUf2Vna5Nkuqrszk4oVJLnvvigBzN+WkeLoZ8DUKpgfsb17JZsX0KIF19MTAwjR47i/IULWFtbU7FCBWbPmgnA6FGj6P5uDzy8clCwYAH6fNib7du3P9fx3u7UiZmzZtHuzbcoVrQoP69Zg6OjY7J2FStWYNHCBQwf7sPFS5ewsbGhUqVKfD1jOgDLV6xkwMBBxMXFUahgQVYsX4aDg8NzZfunocOGY2tryysVK1me+39PrJOTk2WYA0B2V1dsbGzIleuvYRFfzZjOR337UahwEZycnHizXTs+HzUqVTOKF4uSrvX0oZTSh2ZPS/bRRlY2ZtEyXF2c+aRdG6OjZHlvjhof5n/3Xn2t9ePnwxEiA/Dy8to7b+6c2q1btTI6Srp5t0dPvLy8+PKLZ/9USKSe0b6+jB03frTW2tfoLFmNfD4phBBCCCEyLClWhRBCCCFEhiVjVoVhRr3zttERhBAiw1vww3yjIwhhKOlZFUIIIYQQGZYUq0IIIYQQIsOSYQDimZ28fJUFW3dy7sZNFIrcnh40r16Z9vVqW+YUNZlMtB0xFmsrK9aOHYFSiv7ffI/f1WsAxMUnoLXGztb8TzCXhzsrRg2lrc8YQh5GYGX116wJJfLn4/tB/dL/RIUQIhXt27+f8RMmcuTIEZRSFCpYkK5dutCvX1/LXKcmk4nCRYthY2PD5UsXUUrRvGUr9u/fD0BsbCwmk8ky3VTBggU4c+oUhYsW486dO0nmTK1YoQJ7dv+a/icqRCqTYlU8k/1nzjFy/mJ6t2nO2B5dcXVx5mpAEPO3bKdljWpkS1wq7/CFS4RHRpKQYOL4pStULlksycpQczdt42pgEJPefzfZMSb0eidVl0oVQgijbdq8mc5dujJ+7FiWLv4RT09Pzp49y9jx4+ne/R3c3MxLT+/YuZOQkBDi4+PZvWcP9evVS7JSlO+YMZw9d47VK1cmO8bKFcvTbOlUIYwkwwDEU9NaM3XlWt5p0oD29Wrj6mJenq9I3txM6NXdUqgCbDx4mLqvlKNWudJs/P1wmuQJvB9Ctd4D2PT7EV4fMZZ6/Ycya90mgkND+WjGbOr1H0rv6bMICf9rTe4/g+/Sf+YcGg8ewesjxrL8lz2WbbdDHtB3xmwaDx5Bo0E+fPrdfO6FhVm29542k9nrNlv23evLrwi6H5Im5yaEyDy01vQfMJChQz6jb9+P8PT0BKBMmTKsXL7cUqgCLFi4kNfbtqVlyxYsWLAwTfLcuHEDa1s7Fi76kaLFS+Dq7sFwHx8CAgJo1LgJru4eNGjYiODgYMtrLl++TItWrfHOlZuixUswY8ZXlm1//vknjZs0xTtXbry8c/J6u3YEBQVZttdv0BCfESMs+36tdh1u3ryZJucmMicpVsVT8w++S+D9EBpVrvDEdmGPHrHv9DmaVatM82qV2X3yNBFRUWmW69ilyywb+RnzPv2E5b/swWfejwxq/zrbvhyLlVL8uOMXAKJjY+k7Yzavli7Jlsm+fP3xh6zavY89fqcBMGlN50b12DRxNGvG+JCQYGLqqp+THGvrkWMMeKstO6aMwy2bC99v3Jpm5yWEyBwuX77M9evX6dC+/RPbhYSEsHHjJrp06UzXLl34ed06wv72B3Nq2717N6dOnuDAvt+YPuMrOr3dmRnTp3EnKBArKysmf/ElAJGRkTRq0pRmTZoQ4P8n27ZsZubs2fy8bh1gHrowcOAA/G/e4PKli8THJ/DJgAFJjrVk6TKmTZ3C3Tu38crhxajPR6fZeYnMR4pV8dQeREQA4OXm+sR22w4fx9XZmSolilGjdCmcHOzZcezkUx9nxPwfaTBwmOUxdeXaJ7bv2bwxjvb2FMmbm2J581KpWFEK58mNva0t9SqU49KftwDzEAY3Fxfa16uNjbU1+b1z8Ebtmuw4al60KY+nBzVKl8LO1obszk50a9KAE39cSXKsFtWqUDRvHmxtbGhSpaJl30II8Th3794DIE+ePE9st3TpMjw9PWlQvz7NmjYlW7ZsrFi56qmP83bnLnh45bA8Puk/4IntR47wwdnZmTJlylC+XDnq1KlN6dKlcXBw4I3XX+fkSfN1e9PmzeTw8qJv34+wtbWlaNGifPjB+6xIHIpQqFAhmjZpgr29Pe7u7gz59FP27v0tybG6de1C2bJlsbOzo1PHjpz0e/r3BCFkzKp4am7OLgDcCw0jbw6vx7bb+PthmlStiJWVFVZA48oV2XTwMG+89upTHWdcz27PNGbVM3t2y9cOdrZ4umb72/d2RMbEABB0P4SrgUE0GDjMst1k0hTPnxeAkPCHTFv9M35XrvEoOhqAyOiYpMf6x76jYpJuF0KIf/LyMn/sHxgYSOHChR/bbsHChbzdqaP52mllRccOHVi4cCEfvN/rqY6zbOmSZxqzmitXLsvXTk5O5Mr51/eOTk5EJHZQ3Lx5kzNnz+LhlcOyPSEhgQqvvAJAcHAw/QcOZP/+A4SHhwPw8OFfw6+AJPt2cnIiIuLRU+cUQopV8dQK5MxBbk8Pdh73o3vThim2uXDTn8u3Agm6H8KWw8cAiI2LIyIqmmuBQRTOkzs9IyeR092dlwsVYO7gj1PcPnv9ZuLiE1jiMxg3Fxf8rlzjg6nfpHNKIURmU7x4cQoVKsSq1asZOmRIim2OHz/BqdOnuXHzJouXLAUgOjqasLAwzp07R+nSxt10mj9/fqpWqcJve/ekuH24zwhiY2M5cewoXl5e7N9/gDr16qVvSJGpyTAA8dSUUgzu8AaLtu/ip737CXtk/sv4etAdRsz/kYeRUWw8eJjShQqy6vNhLBk+mCXDB7Pq82GUKpifjQePGJq/VtnS3H0Qytp9B4mJiyPBZOJaYBBnrt0AIDI6Gkd7O1wcHQkJf8jCrTsNzSuEyByUUnw1YzqTJn/Bt99+R0iI+cbMCxcu8HaXLoSGhrJg4UKqVa3K+bNnOHHsKCeOHeX82TNUrlSJBQsXGZq/ZYsW3AoI4Ps5c4mOjiYhIYFz587x+++HAHgY8RBnJ2dcXV0JDg5mwqRJhuYVmY8Uq+KZ1Cpbmml9erH31BnajhhLw4HDGfXDYsq8VBAbayt2HjtJh3qv4emaPcmjQ73abD1yjPiEhH89xvC5i6jbf4jl8cbIcamS3cnBnm8+6c3v5y7QxmcMTQaPYNziFZaiu1fLZty4fYcGA4fTe/osasr0WUKIVNKyRQs2rF/Hug0bKFy0GJ45vOnStRvVq1bD1taWFStX0rfvR+TKlSvJo1+/vixdtoy4uLh/PUaHjp3I7uZueRQrUTJVsru4uLBj21a2bd/GS0WK4p0rN+/1ep+QB+aie/SoUVy8eBEPrxzUb9iQls2bp8pxhfg/pbU2OkOWoJTSh2ZPQyn1742FSGdvjhof5n/3Xn2t9QmjswjxJF5eXnvnzZ1Tu3WrVkZHEVnMaF9fxo4bP1pr7Wt0lqxGelaFEEIIIUSGJcWqEEIIIYTIsKRYFUIIIYQQGZYUq0IIIYQQIsOSYlUIIYQQQmRYUqwKQ526eo3O476k9sef0WX8l5Y5Tx9nr98Z2o0aT+2PP6PXlK+5cfuOZdvuk6fp4DuJBgOH0XjwCD777gfuhDywbP9p737ajRpP/QHDaPrZSHwXLuVhZFRanZoQQqSZAwcOUqFiJVyyu1KxUmXLnKePs279ekqUehmX7K7UrlOXixcvJtn+/Zy5FCpchGyubrRs3YagoCDLtvDwcLq/24NcefLimcObps1bcPny5TQ5LyFSIsWqMEzYo0cMmjWPDvVeY9fUCbxZpxYDZ899bAH5551gPl+4hAFvtWXn1PFULlGMT7+db5m79eVCBZg94CN+mTaRjRM/J18OL8YtWWF5/aulS/HDkP78On0ia8b4EJ9g4pufN6TLuQohRGoJCQmhddu29O3bl/t3g+nduzet27YlNDQ0xfZ//PEH3d7pzrSpU7gXfId69eryert2xMfHA/Dr7t0M9/Fh5fLl3A4MIKe3N127vWN5/ajPR3P16lXOnj5FUMAtihUtyjvd302XcxUCpFgVBtrrd4Zcnu60rlkdO1sb2taqQQ5XV/b4nU6x/ZbDx6hSsji1ypbG3taWns0bExrxCL8r1wDI6e6GZ/ZslvZWVoqAu/ct3+fx8sTV2RkArZNvF0KIF8HP69ZTsEABevZ4F3t7e3q915M8uXPz87r1KbZfsnQpDRrUp0Xz5jg4ODDCx4e7d++xb/9+ABYuXES3rl2pVq0qzs7OTJwwnt/27ePaNfO19fqN67Ru3QovLy/s7Ozo0rkzZ8+dS7fzFUKKVWGYywGBFM+XN8lzJfLn5UpAYIrtrwQEJWlvY21Nkby5k7S/EhBIg4HDqP3xZyz/ZS/dmzZMso/9Z85Rf8AwGgwcxh6/M3RuKOtXCyFeLGfOnKF8+fJJnqtQoQJnzpxJsf3pM2d45W/tbW1tKVumDGdOn0lxf97e3uTNm5czZ88C8FGfPmzfvoM7d+4QFRXFwkWLaN68WWqflhCPZWN0AJF1RcXE4uLomOQ5FydHIqNjHtM+Jnl7x6Tti+bNwy/TJhIW8YgNBw9RMJd3kva1ypbm1+kTufMglI0HDpHb0yOVzkYIIdJHREQEbm5uSZ5zc3Pj4cOHKbZ/FPEIN9ek7V3dXHkYYW4f8egRbm6uSffn6mrZX/ly5XBydiJPvvxYW1tTtGgRftm5M7VOR4h/JT2rIt1sO3Kcuv2HULf/EDqOmYSjvR0R0dFJ2kRERuHkYJ/i6x3t7XkUlXQ8a0RUyu1dXZxpWaMag2fPJzo2Ntn2nO5uvFrmZYZ8/8NznJEQQqS9pcuWkd3Nnexu7pQtXx4XFxfCwsKStAkNDSVbtmwpvt7ZxZmw8KTtw0LDyOZibu/i7Jx8f2Fhlv2179ARD3cPQu7dJTz0AW936kSz5i1ISLxfQIi0JsWqSDdNq1Ziz4zJ7JkxmRWjhlIsbx4u+wckafPHrQCK5M2T4uuL5s3NH7f++sg/PiGBq4FBFM2TcvsEUwLhkZGERTx6zHYTAffuk2Ay/cczEkKItNf57bcJD31AeOgDzpw6RdmyZTl16lSSNn5+fpQpUybF15crWxa/v7WPi4vj7LlzlClrbm/e31/3Cty9e5eAgADKJu7vpJ8fH37wAa6urjg4OPDJxx9z5uxZ/P39U/tUhUiRFKvCMHVeKUvQ/RA2HjxMXHw8Gw4cIjg0jLrly6bYvlnVyhy5eImDZy8QGxfPgq07cXV25pVihQFzz23gvftorQkJf8i0VT9TKJc3OT3cAVi//xD3EnsPAu+HMHvdJqqUKIa1lfwaCCFeHK+3bcONmzdZsHARsbGxzP9hAQGBgbzetk2K7Tu//Ta7dv3C1m3biImJYcLEiXh6elD7tdcA6N79HX5cvJijR48RGRnJcJ8R1H7tNQoXNl9bq1erxtx584iIiCAuLo5Zs2fj6elJvnz50u2cRdYmY1aFYVydnZnS5z2+XPETX65YQ37vHEzt/R7ZnZ0AOHn5KgNmzWHPjMkAFMzlzejunZm6ai13Q8MokT8vU3r3xMbaGoCbd4KZtW4T4Y8icXawp0Kxokz/6H3L8c7duMl3G7fwKCqa7M5OvFqmFH3atEj/ExdCiOfg4eHB+p9/pm+/fvTt14/ixYqx/uefcXc3/2G+b/9+WrRsRXioeZ7pEiVKsGjhAvoPGMitW7eoWKEC69auxcbGXALUr1ePcWPH0u6tt3jw4AG1a9dm8Y+LLMebP28u/QcOpEix4sTFxVGmdOkkrxcirSmttdEZsgSllD40expKKaOjCJHMm6PGh/nfvVdfa33C6CxCPImXl9feeXPn1G7dqpXRUUQWM9rXl7Hjxo/WWvsanSWrkc8/hRBCCCFEhiXFqhBCCCGEyLCkWBVCCCGEEBmWFKtCCCGEECLDkmJViMc4/scVGg8eYXQMIYR4oezZuxfvXLmNjiEyEZl3QqS6k5evsmDrTs7duIlCkdvTg+bVK9O+Xm3LnKYmk4m2I8ZibWXF2rEjUErR/5vv8bt6DYC4+AS01tjZmv+J5vJwZ8WoobT1GUPIwwisrP6aVaFE/nx8P6jfM2Ucs2gZri7OfNIu5XkJhRAive3bv5/xEyZy5MgRlFIUKliQrl260K9fX6wTp+gzmUwULloMGxsbLl+6iFKK5i1bsX//fgBiY2MxmUw4ODgAULBgAc6cOkXhosW4c+eOZT8AFStUYM/uX58p47s9euLl5cWXX0xOpbMW4t9JsSpS1f4z5xg5fzG92zRnbI+uuLo4czUgiPlbttOyRjWyOTkCcPjCJcIjI0lIMHH80hUqlyzGjH4fWPYzd9M2rgYGMen9d5MdY0Kvd6hVtnS6nZMQQqS1TZs307lLV8aPHcvSxT/i6enJ2bNnGTt+PN27v4ObmxsAO3buJCQkhPj4eHbv2UP9evXYsmmjZT++Y8Zw9tw5Vq9cmewYK1csp2ULmVtavHikWBWpRmvN1JVreadJA9rXq215vkje3Ezo1T1J240HD1P3lXLExMWx8ffDVC5ZLNXzxMTFMXnZavadOUdCgoncnh6M7dmVE39cYduR4yil+HnfQQp4e/Pj8EHcDQ1j/OIVnLp2nTyenrSoXiXVMwkhxD9prek/YCBDh3xG374fWZ4vU6YMK5cvT9J2wcKFvN62LVHRUSxYsJD69eqlep7o6Gh69/mITZs3Ex8fT6GCBVm6ZDF79/7GsuXLUUrx/Zw5lChenKNHDhMYGMh773/AwYMHealQIbp17ZrqmUTWJsWqSDX+wXcJvB9Co8oVntgu7NEj9p0+x5Q+7xEbF4fPvB/5tGMULo6OqZpn86GjXAkIYu2YETg72HPjTjCuTk68WacW52/8mWwYwKgfFpPHy5Otk8dwNzSMQbPnpWoeIYRIyeXLl7l+/Tod2rd/YruQkBA2btzE+nU/Ex0dTae3OxMWFoarq2uq5ln042LOnj3L5UsXyZ49OxcvXsTDw4PevT/kyNGjyYYBdOnajZdeeonAW/4EBgbSum3bVM0jhNxgJVLNg4gIALzcnnzh3Hb4OK7OzlQpUYwapUvh5GDPjmMnn/o4I+b/SIOBwyyPqSvXptjO1tqayJgYbty+A0Dh3LnwdM2eYts7D0I5cfkqH7/RGgc7O/J756Bj/dopthVCiNR09+49APLkyfPEdkuXLsPT05MG9evTrGlTsmXLxoqVq576OG937oKHVw7L45P+A1JsZ2dnx8OIh1y8eAmAl19+mVy5cqXY9tatW+z97Te+mDwJJycnihYtysf9Pn7qTEI8DelZFanGzdkFgHuhYeTN4fXYdht/P0yTqhWxsrLCCmhcuSKbDh7mjddefarjjOvZ7anGrDarVpm7oWFMXLqKe2Hh1K1Qlo/faIOLo0OytndDw3Cyt8fVxdnyXG5Pj6fKI4QQz8PLyxOAwMBAChcu/Nh2CxYu5O1OHc3XTisrOnbowMKFC/ng/V5PdZxlS5c81ZjVrl06ExgYwAcffkjQ7du83rYtX34xmezZk/+xHxAQiIuLC56enpbnChUq+FR5hHha0rMqUk2BnDnI7enBzuN+j21z4aY/l28Fsm7/7zQOTDsLAAAgAElEQVQbMopmQ0ax+dARzt34k2uBQamax8bamh7NG7Ns5GcsHfEp1wJvs2Sn+c5XpVSStjncXImMiSHs0SPLc0H3Q1I1jxBCpKR48eIUKlSIVatXP7bN8eMnOHX6NHPnzSdPvvzkyZefRT/+yJGjRzl37lyq5rGxscFn+HBO+Z3E78Rxzp07x5SpUwGwskpaNuTNm4eIiAhCQv66Xt64cTNV8wghxapINUopBnd4g0Xbd/HT3v2Wwu960B1GzP+Rh5FRbDx4mNKFCrLq82EsGT6YJcMHs+rzYZQqmJ+NB4+kap5jly7zx60AEkwmHO3tsbW2tkyd5ZE9G4H37lva5nR3o0KxIsxcu5Ho2Fhu3b3Hyt2/pWoeIYRIiVKKr2ZMZ9LkL/j22+8shd+FCxd4u0sXQkNDWbBwIdWqVuX82TOcOHaUE8eOcv7sGSpXqsSChYtSNc/uPXs4deoUCQkJuLi4YGdnZ5nyKmdOb65dv2Zpmy9fPmq/9hpDhg4jKiqKq1ev8s3Mb1I1jxBSrIpUVatsaab16cXeU2doO2IsDQcOZ9QPiynzUkFsrK3YeewkHeq9hqdr9iSPDvVqs/XIMeITEv71GMPnLqJu/yGWxxsjx6XY7n74Q0bMM49vbTdqHDk93OnSyHznbJua1Qm6/4CGA4fz7qTpAPi+24U7D0JpNmQUQ75fQJuaNVLvByOEEE/QskULNqxfx7oNGyhctBieObzp0rUb1atWw9bWlhUrV9K370fkypUryaNfv74sXbaMuLi4fz1Gh46dyO7mbnkUK1EyxXa3b9+mU+fOuHt6UaxESfLnz8/gQYMA6NmjB3/e/BPPHN5Ur2EeurX4x0X437pF7rz5ePOt9rzXo2fq/WCEAJTW2ugMWYJSSh+aPS3Zx89CZARvjhof5n/3Xn2t9QmjswjxJF5eXnvnzZ1Tu3WrVkZHEVnMaF9fxo4bP1pr7Wt0lqxGelaFEEIIIUSGJcWqEEIIIYTIsKRYFUIIIYQQGZYUq0IIIYQQIsOSYlUIIYQQQmRYUqwKw8QnJPDlijU0GuRDo0E+TFm55rFTV0VERTNy/mLqDRhK089GMn/LjiTbJyxdyVufT6B6n4Gs3rMvyba4+HiGzllAW58xVOs9gP1nUncCbSGESE9xcXH0+/gTvLxz4uWdk48/6U98fHyKbcPDw+nctStuHp7kzpuPcePHJ9keGBhIi1atyebqRqHCRZg7b36S7da2drhkd7VMd9WwUeM0Oy8hHkeKVWGYH7bs4My1G6wYNYTloz7D78o1Fm7blWLbqSvX8DAqig3jP2fOoH6s3/87Ww4dtWwvljcvn3V6k5cLFkjx9eWLFObz7p3xdndLk3MRQoj0Mn7CBA4dOsTZ06c4c8qP/fv3M3HSpBTbfvxJf0JDw7hx7Sp7d//KvPk/8OPixZbtnbt0JW+ePNwODGDl8uUMGTqUvb8lXRDl0MEDhIc+IDz0Abt27vjnIYRIc1KsCsNs/P0IPZs3xtM1O16urvRo1piNBw8naxcdG8vO4yfp06YF2ZwcKZDTmw71a7Phb23fqluLKiWLY29rk+z1tjY2dGpQhwrFimAt89wKIV5wCxYuwsdnOLly5SJ37tz4+AznhwULk7WLjIxk5apVjB87Bjc3N4oXL87H/fqyILHt1atXOXDwIBPGj8PZ2Zlq1arSpXNny3YhMgopVoUhwh9FEvwglGL581qeK1kgH7dDHhARFZWk7c07wSQkmCiaN7fluRL583HlVmC65RVCiIzgwYMH3Lp1i1fKl7c8V7FCBf7880/CwsKStL106RLx8fGUK1fO8lyFChU4feYMAKfPnCFfvnx4eXkl2X4mcfv/NW3eglx58tK0eQv8/PzS4rSEeCIpVoUhomJiAMjm6Gh5ziXx60fRMUnaRkbH4ORgj5XVX/9cszk5EhmTtJ0QQmR2ERERALi5/TWk6f9fP3z4MGnbR4/Ili1bkmunm6urpV1ERARurq5JXuPm5srDxGMA/LJrJ9euXObKH5eoVfNVmjRrzr1791L3pIT4F1KsCkM42tsDJOlF/f/Xzg72Sdo6OdgTGR2DyWSyPPcwMgon+6TthBAis3NxcQFI0osaGhoKQLZs2ZK2dXbm4cOHSa6doWFhlnYuLi6EhYcneU1oaBjZEo8BULdOHezs7HBxcWGEjw8eHu7s2bs3dU9KiH8hxaowRHZnJ7zd3fjjVoDluUv+AeR0d7P0sP5fwZzeWFtbcSUwyPLcH/4BFPnbsAAhhMgK3N3dyZcvH36nTlmeO+nnR/78+XH9Ry9piRIlsLGxSfKxvt9JP8qWKQNAubJl8ff35/79+39t9/OjTOL2lFhZWaG1Tq3TEeKpSLEqDNOyRlV+2LKD+2Hh3A8LZ8HWHbSuWT1ZOwc7OxpWqsB367cQERXFn8F3Wbn7N9r8rW1cfDwxcXGYtCY+wURMXFySabBi48zbNeYps2Li4kj4W2+DEEK8KLq/043x4ydw+/Ztbt++zYQJE+nZ491k7ZycnGj/1luMGPU5YWFhXL58ma9nzqRHYtsiRYrwao0a+IwYSWRkJEeOHGXJ0qWW7efOnePEiZPEx8cTFRXFpMmTCQ6+S53atdP1fIVIfuu0EOmkZ/PGhEU8ooOvecqVJlUr0b1pQwD6f/M9rxQtTPdmjQAY3KEdk5atotUwX+xtbXmzbi2aV69i2dfHX3/HictXAfC7co0ZP63jvRZN6NWyKQDtR08gKOQBAEO+XwDAyG6daFmjavqcrBBCpJIRPj7cvx9C6bLmG6fe7tSJYUOHAtC8ZSteq1XT8v03X3/Fh336UKDQSzg6OvJRn95069rVsq+lSxbT64MPyZk7Dx4eHkyaONFSjAbfvUvffv3w97+Fvb09FSpUYNuWLXh7e6fzGYusTkl3fvpQSulDs6ehZOokkQG9OWp8mP/de/W11ieMziLEk3h5ee2dN3dO7datWhkdRWQxo319GTtu/Gitta/RWbIaGQYghBBCCCEyLClW04lSyiRjJEVGlWAyKSDltW6FyFjiH7e0qBBpKS4uzoRcJw0hxWo6cbSzu3st6LbRMYRIJjo2lnth4Q7ALaOzCPFvoqOiLp07d14KBpHuTpw8+Qi4YXSOrEiK1XSSYDItW7B1Z4xJeldFBrN6z/4EO1ubk1rr+//eWghjPYqMXDb7229jgoODjY4ishA/Pz/27v3NFthsdJasSG6wSidKKRcnB/u9XtmzF2tUuYKLm4uzkputhFG01kTFxrL/zPmHf/gHREbHxtbQWl83OpcQ/0YppZycnMbb2dl90qlTR5viRYvZWVtbGx1LZFJxcXEcPXYscv2GDVYxMTFdEhIS1hidKSuSYjUdKaVsgLo21taN7GxsPMkstaqGeJOplZVSF62s1GWj46Q2rbVnQoKpiY219U8oYo3Okyo0xCckRMTGxx8AtmitHxkdSYhnoZR62drauq2jg0NBZWX1QlarWmu7+Pj4N21srLcrZZXpPtlISEgork2m4tY2Npte1M4ZU0JCbGRU1Hmt9c9a64B/f4VIC1KsiuemlHobGAhU1VpnynEOSqm5QLjWepDRWYQQmYNSahrgorV+3+gsaUEpZQUcAaZqrZcbnUe8uKRYFc9FKeUMXAQ6aK0PGp0nrSilcgLngJpa60tG5xFCvNiUUiWBfUBprXWmHYCrlKoJLAdKySc44r+SG6zE8/oM2JeZC1UArfUdYBIwzegsQohMYSowKTMXqgBa6wPAAczvFUL8J9KzKv4zpVRB4DhQQWvtb3SetKaUsgPOAp9orbcanUcI8WJSSjUHZgBltNaZYxz8Eyil8gMngYpa6z+NziNePNKzKp7HF8DXWaFQBUh8UxkITFdK2RqdRwjx4kn8o3caMCArFKoAie8R32B+zxDimUmxKv4TpVRtoDowxegs6Wwz5kmhPzI4hxDixfQRcB3YYnSQdPYlUEMp9ZrRQcSLR4YBiGemlLIGjgETtdarjM6T3pRSpYDfgJe11neNziOEeDEopXIA54HaWusLRudJb0qpDsAQoIrWWlYhE09NelbFf9EDeAisNjqIERLfZJYBY4zOIoR4oYwFlmbFQjXRKuAR8K7RQcSLRXpWxTNRSrlinqqqhdb6hNF5jKKUcsf8c2istT5ldB4hRMamlHoF2A6U1Fo/MDqPUZRSlYBNmH8OYUbnES8GKVbFM1FKTQFctda9jM5iNKVUb6A9UF/LL5IQ4jES19beDazQWn9ndB6jKaXmAQ+01p8anUW8GKRYFU9NKVUC2I95upU7RucxWuLyuScAX621rBcthEiRUupNYCTmqZuy/FjNxEVWzmJeZOUPo/OIjE+KVfHUlFKbgN1a66lGZ8kolFL1gfmYV2eJNjqPECJjUUo5AheAd7XWu43Ok1EopQYDdbTWrYzOIjI+ucFKPBWlVFOgOOa58kQirfWvmHtXBxqdRQiRIQ0EjkmhmszXQEmlVBOjg4iMT3pWxb9KnAD/NPCp1nqT0XkyGqVUYeAoUE5rHWB0HiFExqCUyov52llZa33d6DwZjVKqFTAZKK+1jjM6j8i4pGdVPI0+wE3ME+KLf9BaXwO+ByYanUUIkaFMAr6TQvWxNgH+QG+jg4iMTXpWxRNl9Umsn5ZSKhvmqazaaa0PGZ1HCGEspVQN4CeghNY6wug8GZVS6mVgD+ZFVu4ZHEdkUFKsiidSSn0LxGit+xudJaNTSnXDvJRiDa21yeg8QghjKKWsgEPAN1rrxUbnyeiUUl8BtlrrPkZnERmTDAMQj6WUKg+8AfganeUFsSTxv50NTSGEMFoXwAQsNTrIC8IXaKeUKmd0EJExSc+qSFHiJNa/Aqu01t8anedFoZSqDqxBPvoTIkv625CgN7TWh43O86JQSvUB3gQayCIr4p+kZ1U8zuuAJzDX6CAvksTxqr8Cw4zOIoQwxDDgFylUn9kcIAfQ1uggIuORnlWRjFLKAfMk1j0T5xEVz+Bv09VUSZwpQAiRBcg0ds9HKdUAcwfJy7LIivg76VkVKRkInJBC9b9JfJOaBnxpdBYhRLqaAkyVQvW/0Vr/AvgBA4zOIjIW6VkVSUivYOpIXGLxPNBDVq4RIvOTpZdTR2Lv9BHMvdOBRucRGYP0rIp/mgh8L4Xq89FaRwGDgRlKKRuj8wgh0k7i7/gMYJAUqs8n8b1nLrLIivgbKVaFReKd7A2Qi0RqWQs8AN4zOogQIk31Au4DPxsdJJOYADRUSlUzOojIGGQYgAAsk1gfBGZrrX80Ok9moZR6BdgOlNRaPzA6jxAidSmlPDDfkNpYa33K6DyZhVLqHczLsL4qi6wI6VkV/9cZUPw1sb1IBVprP8y9LZ8bnUUIkSY+B9ZKoZrqFmOuUd42OogwnvSsCpRSLsAlZF37NKGUyoH5ZqvaWusLRucRQqSOxHXt92Keaumu0XkyG6VUDWA15k+mZJGVLEx6VgWYJ7H+VQrVtJH4JjYemJ64MpgQ4gWX+Ls8HRgnhWra0Fr/DuwBhhocRRhMelazOJnEOn0opWwxTwk2WGu92eg8Qojno5RqiXku5XJa6zij82RWSql8wCmgstb6utF5hDGkWM3ilFJrMC8AMN7oLJmdUqoZ8BVQRmsda3QeIcR/o5SyA84B/bTW24zOk9kppUYAr2it3zQ6izCGDAPIwpRS9YCKmFdbEmlMa70VuAz0MzqLEOK5fAxckkI13UwFKiul6hodRBhDelazqMRJrI8DY7XWPxmdJ6tQSpUADmC+ISPY6DxCiGejlMqJuVf1Va31H0bnySqUUm8BI4CKWusEo/OI9CU9q1nXe5gnrF9jdJCsRGt9CVgEjDM6ixDiPxkHLJRCNd39BIQii6xkSdKzmgUppdyBi0CTxHlARTpSSrlh/vk301qfNDqPEOLpKKUqApsxT6UUZnSerEYWWcm6pFjNgpRSMwAHrfWHRmfJqpRSvYCuQB0tv4RCZHiJU1X9BizSWs8zOk9WpZT6HojUWg8wOotIP1KsZjFKqVKYL7gyibWBlFLWmMcMT9BarzI6jxDiyZRSHTDP91lZxkwa52+LrLymtb5odB6RPqRYzUISewa2Atu11tONzpPVKaXqAD9i/kgryug8QoiUKaWcgAtAV631b0bnyeqUUgOBhlrr5kZnEelDbrDKWpoDhYBZBucQgNZ6L3AYGGx0FiHEEw0GDkmhmmHMBIoopaRYzSKkZzWLSJzE+izwSeJ8nyIDUEoVAo4BFbTW/samEUL8k1IqP3ASqKS1vml0HmGWWKhOB8rKIiuZn/SsZh39gMtSqGYsWusbwGxgksFRhBApmwzMkkI1Y9FabwGuAn2NziLSnvSsZgFKKW/MA9JrJs7zKTIQpZQz5qmsOmqtDxidRwhhppSqBSzHPK78kdF5RFJKqZLAPqC0LLKSuUmxmgUopeYAD7XWg4zOIlKmlOoMDACqaq1NRucRIqtTSlkBR4BpWutlRucRKVNKTQOctdYfGJ1FpB0ZBpDJKaUqAK2BsUZnEU+0DIgFuhkdRAgBwDtADOaeVZFxjQHaJC4YIDIp6VnNxBKnqtoLLNFazzE6j3gypVQVYD3mjxzDjc4jRFallMqOeWhOa631MaPziCdTSn0AvA3UlUVWMifpWc3c3gKyA/ONDiL+ndb6KOalBIcbnUWILM4H2CaF6gtjHuAGvGl0EJE2pGc1k1FKOWmtI/82iXW3xPk8xQtAKZUbOANU11pfUUrZAwla63iDowmRaSmlbABrrXWMUqoY8DtQRmt92+Bo4ikppeoCC4FSWuuo/78XGptKpBbpWc1ElFJlMa9QBeZJrA9Lofpi0VoHAVMSHwATgc7GJRIiS+gCTEj8egrwpRSqLxat9R7gKH8tsrIt8T1RZAI2RgcQqSoXEJ84ifUnQCWD84j/ZgZwTinVEIjH/P9VCJF2/n/tbASUBtobnEf8N58Cx5VSCzBfO3Ni/qRKvOCkZzVzcQVCMU8wPxuIVUpNUkrZGhtLPC2l1GdACWAQ5qL1Ieb/r0KItOOK+XdtBubfvVKJv4viBaCUslVKTcI8o8q3mN8DQ5FrZ6YhxWrm4grYA7UBf8APiMb8F6Z4MfgDO4EKwB2gDHLBFSKtuQJlgSDMn0jtAP40NJF4FvGY3+v8MP9/qwvYIdfOTEOGAWQu7sCrmH9ZewONtdZ+xkYSz0JrvVwp9RvwHZAPqAFsNjaVEJmeN9AcuAVEAq9orQONjSSeVuJ0VaOVUuuBBcA9zO+Fuw0NJlKN9KxmLtUxT9+xBvNKSFKovoC01gH8tZCDFeZeViFE2qkAKMAXaCOF6otJa30SqAKsxfxeWN3YRCK1yNRVmUjiOtY2iXdFikxAKVUEqKK1XmF0FiEyK6VUR+Co1vqq0VlE6lBK1QPitNb7jc4inp8Uq0IIIYQQIsNKtTGrSqkSQDXAIbX2KbKUcGBv4jyjaSJx4u/awEuAdVodR2QaUcBBo3rblFIlgarINVWACfO9CHu01rHpfXCllDPQAPNUUCq9jy9eOGHAbq11cGrt8Ll7VpVS2Z3sbHdYKVW2bN5cJkc7WxkHK56J1hAeFZ1wJvC2nY2V1YrI2LgeWmtTah5DKVXT3s5uc75cOdXLRQpb29hYywVXPJbWmohHUaZDp05bA4cjIiNbpNdqOEopVxcnp53W1talq1cob3JxcpJrahYXH5+g/7h+PeGav79VTGxcO631jvQ6tq2tbQ9ra+tZFStWjC1SpIiNtbX8nS8ez2Qycfv27YR9+/bZ2draznv48GE/nQof4T93sepsb7f+1SIFm/SrX9PeSsn7v/jvomLj8Fm3PfL6vRDfuISEL1Jrv0opN3s721vffj7C+bXKFVNrtyILiE9IYOCkKdH7jp1Y8/DRoy7pcczsLi6bW9Sr02D84AH2VlZSp4q/HD19hm4DP4uMjo0tlh43gSmlqrq5ue0+fPiwU/HixdP6cCITCQ0NpVatWpHnz58faDKZvn/e/T3XlVAp5RKXkNCkZ80qUqiK5+ZoZ0uPmpWd7G2sP0jlXbeqUqaMSQpV8axsrK3x+fA9h9i4uDeUUnZpfTylVPaY2NgGw/p8IIWqSKZKubI0rFUTpWiXHsdzdnbu3r9/f3spVMWzcnNzY/LkyU5ubm59UmN/z3s1fMnN0THGxcE+NbIIQfGcXkTGxRdMzX3aWFuXqVK2dLbU3KfIOnJ6euLs6GgC8qTD4Qrn9PKKye7ikg6HEi+iKuXKODk7OqXLdHYODg6VqlWrJp/7i/+katWqREVFFUmNfT1vsWprY20l0wkkGrZ2K5tOXzA6xgvN1toarXWqXhxtrK0d7Gyz9oqznT8dxuL1m4yO8cKysbE2Aenxj8jW1tYmy11TO348kEVr1hkd44VgZ2eLlZVVet10Z2tvn7U6o+rWrcvMmTONjpEp2NvbYzKZUuVGflnBKhP74cBRjlz3J+RRJNkcHGhaujhvVS5n2b7p9AV+uXCFG/cfUPWl/AxrVs/AtCIrmTT3B349dITg+yG4Z89Gh+ZN+bDjW5bt5du8laR9TGwsdapW5nvfkekdVWRBm37dw4LVazh/5SrFChVkw9xvk2y/ffcuo6Z/zdHTZ1BKUb3CK/j270cODw+DEovM6tNPP2XDhg0EBgbi5eXF+++/z7BhwwCIiYmhb9++7Nq1i3v37pE3b14+++wzevToYXn9+fPn6devHydOnMDOzo6WLVvyzTff4OTkZNQp/SdSrGZidtbWDGtWj3zurgSGhTN6w05cnRxo/LJ5/JGHsxPtq5TjlH8QDyKjDE4rshJ7OztmjhxGkfz5uBEQSM8Ro/F0c+Wtpo0BOLV+taVtQkICdbr2oHntWkbFFVmMW/ZsvPtWO27cCmDHvuRzyo+c9jU2NtbsX7UcgEHjJzHm61l8M1r+mBKpy8HBgTVr1lCqVCkuX75M06ZN8fb2pmfPnsTHx5M7d2527dpF4cKFOXz4MM2aNaNAgQI0bNgQgE6dOlGnTh22bt1KeHg4rVu3ZsyYMUyaNMngM3s2maJYXXviLBtPn+dRTCzZHR3oVr0itYsXJvhhBF//coBr90LQWlM6T0761K2Bh7P5L4pha7dSMpc3f9y5y6U793jJy51hzeqx5cxFtpy9hL2NNR/WqU61lwoAMH3XPmysrAiNjOZ0QBB53LLTr96rFPX2SjHXiZsBLD50gqCwcLyzu9CjZhVeyW8e9nb85i1+OHCMuw8jsLe1oX6Jorxbs3Kq/ly6VP/rhqL87m7UKFyQ84HBlmL11SLmoaHX74ZIsZpG5q1ey6J1G3n46BHurtkZ9G43WtatTWBwMMOmfs2Fa9cwmTRVypbGt18fvD3NPTOdPx1GhVIlOXXxD05dvETJwi8xc+Qwlm7awvJNW7C3s2d03w9pUKMaAJ9NmY6ttQ33QkM55HeaQvnyML5/P8oUK5pirn3HTjBt4WJuBgaRN6c3Q3v1oGbFVwD47ehxJs39gcDguzg62NO2YX2GvPduqv5cBrzz1431RQrkp3HNGhw7e95SrP7db8dO8Cgqmia1Xk3VDALmLF/Fwp/WEh4RgYebG5++34NWDeoTcOcOQyZN4fyVK5hMmqrlyzJuYH+8vTwB88f2FUu/jN/5C/hduEipIoX5duxoFq/bwNL1G3Cws8d3wMc0Svx/NnjCZGxsbLgX8oDfT57kpXz5mPjZIMqWSPnGnb1HjjJ17g/cCAggX65cDO/zAbUqVzJvO3yECbO/J+D2HRwdHXijSSOG9U7dezL/f6yftm5Lcbt/UBB9u3XB2ckRgJb16/LNj0tSNUNWM2XKFL766itCQ0PJkSMHEyZMoGPHjvz555/06NEDPz8/TCYTtWvX5ttvvyV37tyA+WP7GjVqcPjwYQ4fPkz58uVZs2YNs2fP5ttvv8XR0ZFZs2bRunVrALp3746trS137tzh119/pXjx4sydO5dKlSqlmGv79u34+Phw5coVChUqxJQpUyyF4LZt2xg8eDA3b97E2dmZbt268cUXqTaRDQBjx461fF2yZEneeOMN9u/fT8+ePXF2dmbMmDGW7dWrV6devXocOHDAkvH69evMnTsXOzs7vLy8aNOmDfv27UvVjOnhhS9Wbz0IY+mRk3zVoTX53F0JeRRJRIx5zmStNa9XKE25fLmJiYtn6s59zPntMEP/9nH3nj+uMbpVQ3K7ZsN30y98tmYLbcqXZnGPDuy6cIWZ/2PvvMNjTt4A/tn03gtJSAgSIkF0p0ZvIThEiF5OvXN6cGqindOJThJBdMEhooRTjwhBEKJL7z2b/f2xbmWTTXHq+e3nefZ5dr/zfmfemZ397jsz78wb/Bf1Blug+G5n7rmIJ3h0cmJ6x1YcuX2P+ceC2TSgBypK0k35NC6BpafOM6OTE3ZmpoS+eI3XibOs69cdQy1NVp65xKAm9XCytSYjJ5cXCUnF1rHvRr9i06qXN+W3rm1KbSeRSET462iaV6tUqqycT8OTFy9Z6ePH4bUrqVzBgpj4BJLT0gDIzxcxtJcLDWs5kJWdzaQlvzN//UZWz5wmuf9I8Dm2LJhDRbPyDJ81lz4TpzC4Rzf+2u3D/pNBeKxYQ4sG9VB6d+7h4eBzrP/NgzWzprP94BFG/TafM9s3oaoivYn9fuRTfvFaytrfZlC/ph2XboUydr4XJzato5yRIdOWr2TK0EF0b+NEWkYGj5+/KLaOjj36FptW1646m+b/Vmo7iUQirt8Jp0vL5jLT958KonPLZqj9n/nOfW4in7/gj63bCdzijXXFCsTExZOclgqAKF/E8L4/0qhObbKys5m4wIs5q9awbt777/Pw6TNsW+qFpZkZQ6bOoNeYCQzp3ZNrB/cRcOJPpi/9nVaNGqKkJO6fh04F4e05j/UL5rA1YD/Dp8/kvL8vqqrS/fPe40gmzF3IhoVzaeBgz8UbNxk9ay6ndnnKQeYAACAASURBVG6hnLExk72WMu2nEfRo35a0jAweRT0rto4OnZyLTatvX5Mtiz3/VdsN7d2LY2fP0aJhfUQiEYeDgmnVqOG/yksOREREMHv2bG7duoWNjQ1v3rwhMTEREJ/bOWnSJFq1akVGRgYDBgxg/PjxBAS8X33x8/PjxIkTWFtb07lzZ3744Qd++eUX3r59y7Zt2xg+fDidOnVC6d3/tK+vL4cOHWL//v2sWLECZ2dnIiMjUVOTdgW+ffs2rq6uHDx4kGbNmhEUFETPnj25d+8e5ubmDB48mCVLljBgwABSU1O5d+9esXXU09MrNq1p06YEBpa+p0AkEnHhwgVcXV1lpmdlZXHt2jXc3Nwk1yZNmsSOHTtwcHAgKSmJAwcOMGjQoFLL+tb4zxurigoCEMGz+ESMtTUx0NSQzJya6mhjqiPeBK6sqEivuvZ4Hg+Wut/J1hpLQ31APNO47+8wutaqDkCLapVZc/Yv4tLSJfnUqWiGo6U5AC517Dh8+x53Xr2lrqWFVL4n7kbQpnpV7M3LAeBY0Zwa5U258vQFne1tUVJU4E1yCsmZWeiqq2FTzrjYOu4e4VZsWlnxuXKT7Lw8Ota0+ei85JQNRUVFRCJ4GPUMMxNjTAwNJDOnFuVMsShnCoCqijIj+/Ri9DzpP87ubZyoaiWe/W7ftAkbdu/DvVtXAJydWjBz5RrexsZJ8mnqWId/juca1suFHQcPc/X2HZrXl54x2H38BD3btaGhgz0Azeo6UrdmDc5cvoJb184oKynx7PUbEpKTMdDVpbZt8X3m5oHdH9tMLN/mQ2Z2Nq5dOhZJS0hOJvjqNXYt+28tWf0XUBJvZuThk6eYm5pgYmQomTm1KF8Oi/LiZ5eqigqj3FwZ5SE98HBp35ZqlawA6NCiGet9/RnU0wWA7m1bM2Ppct7GxkryaVa/Hi0a1AdgRN/ebAvYz5XQUFo0bCCVr/+RQHp1bE+j2rUAaN6gHvXsa3L64l8McOmGsrISz169IiEpGQM9XerUqF5sHcOOH/m4RiqGevY12RN4nNqduyMSiahTozorZ8/4LGX9P6CkpIRIJOLu3btUrFiR8uXLS2ZOrayssLKyAsQbdqZNm4aLi4vU/e7u7tjZ2QHQs2dPvLy8GDduHABubm6MGDGCly9fSvJp164d7du3B8TG3IoVKzh37hwdOnSQytfb25vBgwfTokULyX1Nmzbl8OHDjB49GhUVFR4/fkxcXBxGRkY0bFj8gCUpqfgJqbLi4eFBRkYGo0aNKpImEokYNmwYVatWlWqfDh06MHjwYLS0tBAKhXTv3p2RIz/16ZCfn/+8sVpeV4ef2zTlaNh9Vp65hJ2ZKUOa1qOCvh5JGZlsCrlG+OtoMnJyAcjMzZW6X//dMg6AqpIieurvP6spi5snKzdPcs1YS1PyXiAQYKylQXx60cA2Malp3Hn1ltP3Hkqu5eWLqGwsNlZmdHRi743bjPQ9QHldbVzr16ZBpQof0xTFEnAjjJBHUXj16IDa//mu+C+JpVl5Fv/6MzsPH2Xa8pXUq2nH9OFDsK5YgfikJOav38SNu+GkZYj7T3ohVwxjfX3JezVVVYz034/M1d/NAGRkZUmumZm8H/AIBALKGRsTHR9fRK9X0TFcDbtDwMnTkmt5eXnUsK4MwLrZM1jrv5e2Q0ZiaVaesW6uODVqUCSfT8GG3QEcuxCC31IvNNSKbnA+Enwey/LlSzSY5fw7LM3NWDZ9Ctv3H2TKoqXUd7DHY8worC0rEpeYyLxVa7kedoe0d8+3f/rpPxTcTKSupoqRgX6Bz+LvMj3zfZ82MzWRvBcIBJQ3MeFtbFwRvV6+ecuV0NvsPX5Cci0vT0iNdy4t3gvmsmanH636uWNlYc74QQNo3aTxxzTFB5Gfn8+AX6fg3NoJ3z+WkicUsmj9RsbMnse2pV5fTI/vCWtra7Zv386qVasYPHgwzZo14/fff8fW1paYmBgmTJhASEgIKSkpAKSmpkrdX65cOcl7DQ0NTE1NpT4DpL1b1QKoWLGi5L1AIKBChQq8evWqiF5RUVGcO3eOLVu2SK7l5uZSp4745LCDBw+yYMECqlatSpUqVfjtt9/o0qXLxzRFsXh5ebFnzx7Onz+PpqamVJpIJOKnn34iIiKCoKAg/jmjOTExkbZt2+Lp6cmIESNITk5m2LBhjB07lnXr1n0WPT8X/3ljFaBZ1Uo0q1qJrNxctl66wZrgv1jcsxM7L98kV5jPyr7O6KqrEf46mmkHTpSeYQnEpqVL3otEImLTMjDULLqrzlhLk+617RjQSPZB9FVMDJnRyQlhfj7nHz5l0Z9n2TXMVaYx+aN38b5QNcqbMte5bbHpAX+H8Wd4BF4uHTHS0ixWTs7noXPLZnRu2YyMrCwWb9rKzBVr8F++mGVbd5Kbm8uRdSsx0NXlxt1wXH+dVnqGJfA6JlbyXiQS8TY2FlNDwyJy5Y2NGdyjOxMHDZCZj13VKqybPQOhUMjRs+cZt2AR1/ftkmlMFt61X5B6NWuwZeHcYtO99wSw+/if+C31oryxbL/v/aeC6NmudDcXOf+OLq1b0aV1KzIyM/Fav5FpS38nYM1KlnpvJjc3j2NbNmKgp8v1sDv0HvvzR5X1Ovp9mHCRSMSbmBjKyfjezUxNGNq7F5OGDymSBlDTphobFs5FKBRyOCiY0bPncuvoQTQKTDT8g137zsXqU9/Bnu1LP3zGPikllVdvoxncq4fENaV/d2c6Dx2JUChEHo7039GnTx/69OlDeno6kydPZvjw4YSEhDB9+nRycnIIDQ3FyMiIixcv0qxZs48q6/nz55L3IpGIFy9eYG5uXkSuYsWKTJw4kQULFsjMx9HRkQMHDiAUCtm1axe9evUiPj6+iDEJoFXC2cnNmjXjxInibZNFixbh7e3N+fPnsbCQXsUViUSMGTOGa9eucebMGXR1dSVpkZGRZGdnM2bMGACMjIwYOnSoZNb5v8R/3lh9mZhMXFo6NcqboKyoiLqyMv9E08rIzUVNWQlNFRWSMjLZeyPso8u79eI1t56/xsGiHEdu3wORiJrm5YrItbezYW7gaWpXMKNGeROE+fk8jI7DSFsTQ00NQh5F0aCSBVqqqmiqKiNAQHFRwAJG/rsoj/tv3uH4nQd4uXTERKfoD0WYny9+iUSIRCJy8vIQCAQoyx+2n4QnL17yJjaOejVroKKsjIa6OgqK4hFvekYGGmpqaGtqEp+UxHr/vR9d3qVbt7j49y0a1XZgx8EjiETQwKFmEbm+ndozbNZcfnCsTT27GuQJhdyOeEh5YyNMDQ05fj4Ep0YN0NHSQltTE4FAIPHZLkzBXfsfwsa9+/E9chy/ZV6YF5hxK0j4o8c8fvac7m3kR6p9DiKfv+BNTAz17e1RUVZBQ10NRQXxbz8tMxN1dTW0tTSJS0xkrU/xfvNl5eKNvwm5foPGdeqwbd9+RCJo+G6pvyCuXTszeOoMmtavS337muTlCQm9/wAzE2NMjY0IDD5HmyaN0dF+1z8RSPQuTPjJY/9KV6FQSF6ekNw8ISKRiOzsHBCIXSIM9HSxNDdj58HDjHV3Iz8/H7/DR6lWyUpuqP5LIiIiePHiBU2bNkVVVRUtLS1JW6ampqKpqYmuri4xMTEsXLjwo8s7ffo0p0+fplWrVqxcuRKRSCRZ6i/IiBEj6NSpE23btqVp06bk5uZy7do1KlSogLm5OXv27KFr167o6emhq6srflYW0wcKzux+CEuWLGHt2rWcP38eS8ui8XLGjh3LpUuXCA4ORr/AahyAjY0N6urqeHt7M2zYMFJSUti2bRu1ahX93X3r/OeN1VyhEJ8rN3mRkISCQIC1sSGjW4mXhNwa1GZ5UAh9N+3CRFuTzva23HxedKr/Q2hZrTKBYffxPBGMma4OHp1bo6pUtBmrmBgysU1zdvz1Ny+TklEUCKhiYsTI5mKflvMPn7Ap5CrC/HxMtLWY2qFlkU1aH8v2v/5GSUGBcbsPS64VnIndc/02/tdvS9J6bvClppkpXj2K+g7K+XBycnNZvt2HyOcvUFBQwK6KNfPGiSPPjXd3Y8rS5dTt0RczUxP6d+3MhRs3P6o851Yt8TkSyJh5nliam7F+jofMTUl2VauwdPJElm3dwZMXL1FUVMS+ahVmjxb7MR09e54F6zeRJxRibmrCSo+pRTZpfSxLt2xHWUmJrqPej/ALz8TuP3WGlg3qYVToASzn05CTm8OyTVt5HPUMBUUFalatysJfxbOnvwweyK+ei6nVqRvmpiYMcOnG+avXP6q8bm1bs2P/IUbN/A0rCws2es6T2T9r2lRjucc0lnhvIvLZC5QUFbG3rcacCeK+ciToDPNWrSUvLw+LcuVYM3dWkU1aH8vBU6eZ7LVU8tm2bUfMy5lyce8uALwXzmP+mnU0dOkNgIOtDat/m/lJdfh/Ijs7Gw8PD+7du4eioiKOjo5s2LABgLlz5+Lu7o6enh6WlpaMGTOGP/+UfUpDWXFzc2P16tW4uLhQtWpVDh8+jLqMmXlHR0d8fHyYNm0aDx48QElJiXr16rF69WoAdu3axYQJE8jNzcXKyoq9e/cW2aT1sUydOhVlZWUcHN6fkf7PTOyzZ89Yt24dqqqqUoZs//792bBhA9ra2hw+fJipU6dK8mnRosV/MuiBQCT698FSBAKBY3ld7eCNA3rqli793+ePoBB01NQY2rT+11blu0UkEuG8dgcikUj2NPO/QF1VdeUEd7fxw37s8amy/OaYsuwPDHR0mDZi6NdW5bukiat7amxCYl2RSPToc5YjEAjqV65Y4fQZ3+3f1TN1kudi9HV18RhTdGOInA9jd+AxvNZt9E9OTe33ucsyMjK6GRAQUKdVq+9ndWPQoEEYGRmxbNmyr63Kd09KSgrGxsbZ2dnZH23Bf2y4VTly5MiRI0eOHDlyPhtyY1WOHDly5MiRI0fON8t/3mf1S/JLm4/bgShHzudiyaRfvrYKcuQUy7IZU7+2CnLkALB9+/avrYKcf4F8ZlWOHDly5MiRI0fON4vcWJUjR44cOXLkyJHzzfJ/4QYQ/jqaPddv8zA6FgQCTLW1aGVrTVeH6pLzI/NFIobu2IeigoBNA3oiEAj47chp7r2JBiBPmE++SITKuzjXxtparOvXnaE7AkjKyEJB4f3mdWtjQxbJj3+SU0au3wlnnf8ebj94iEAA5qamuLRphXu3rpIz+/Lz82npPhRFRUWCt29CIBAw1OM3btwVx6LOzcsjPz9fcsSUmYkxJzato6X7UOISk6TOSa1RxRr/3+XhS+WUzrXbYazZ6Ufo/fsIEGBRvhw92rdlUE8Xqb7ZrLcbioqKnN/tg0AgYNDkaVwPuwNAbm4e+aL3fdPc1JRTO7fStHc/4hISUVR83zftqlZl75oVX76icv6ThISEsGDBAq5evYpAIMDKygp3d3fGjx8v1T+trKxQUlIiMjISgUBAx44dCQkJASAnJ4f8/HzJkVOWlpaEh4djZWVFdHS01Lmpjo6OXLhw4ctXVM73b6xee/qCZafOM6BRXSa1a46OuhrP4hPxv36bNtWroPXunL9bz1+Rlp2NMD+fsFdvqWVRXioy1K6rt3iWkMT0jkWP8JjaoeVnC5Uq5/sm+Mo1Ji5axsTBA1g+bRL6Ojo8jHrGGl9/erZrg867qCcX/75FcmoaeUIhV26H0bh2LakzSVf57BLfN2t6kTJWeUz9bOFS5Xy/nPnrMhPmLmTSiKGsnD0DfV1dIp48ZdUOH37s2AEdbXHfDLl+g6TUFPKEQi7fDKVJ3TpSkaFWbN1BxNOnrJ8/p0gZa+fN/qKhUuV8PwQGBuLq6oqnpye7du3C0NCQu3fvMm/ePAYPHoyenjg89alTp0hISCAvL4+zZ8/i5OQkFS1qzpw53L17l3379hUpIyAg4LOFT5XzYXzXxqpIJGJjyFV61XWga63qkuuWhvpM69BSSvb0/cc0rmxJTl4eQfceUcui/CfXJzollWE79zOh9Q/svn6blMwsOttXp4uDLcuDLvIoOpYqJkZMad8CPQ3xAcWvk1LYGHKVh9FxaKgo08WhOt1r2wEQk5rGqjOXeBKXgEgkws7MlNEtG2PwLvzr9AMnqF7ehIjoOB5Fx2JlaMCkds1lRrOS8+URiUTMX7+RkX164d6tq+R6NStLVs2UDr267+Rp2v3QmKycHPadDKKxjMg/H8vLt9G0GjiMRb9OYI3fbhKTU+jv3Jn+zl2YsnQ5YRGPqFm1Cis9pmD47o8g6tVrFqzfSFjEQzQ1NHDv1oXBPboD8Domhum/r+L+kyfk54uob2/H3HGjMTEUx5R3mzwdx+rVuR0RQVjEI2wqWbF82qRiI1rJ+XKIRCLmrlzLT/1dGdTTRXLdpnIl1s6dLSW79/iftG/ejKzsbPYeP0GTunU+uT4v37ylWR83lk6fzKrtviQkJeHeozvuPbrx68LF3L7/AHvbaqyeM0sSROLpi5fMW7WW2w8eoKWhycCe3RnauxcAr6KjmbpoGfcePyY/X0SDWvYsmPgzJkbi8MR9x0+kbs0ahN57wO37D7C1rsyK2R5YlDMtVkc5Xw6RSMT48eOZPn26VOjQmjVrsnevdDTArVu30qNHDzIzM9m6dStOTk6fXJ+oqCgqVarEtm3bmDdvHrGxsYwdO5axY8fi7u7OtWvXqFevHnv27MHERPx8e/ToERMmTODatWvo6Ogwbtw4fvlFvFH2+fPnDBkyhNDQUPLz82nevDnr16+nfHmxXdKyZUuaNGnC1atXuXbtGg4ODuzatUtmhKvvhe/aZ/V1UgrRKWk0r1qpRLnUrGyuPX1OKxtrnGyr8NeTZ6Rn53w2vcJevmWNazeW9urModBwFp88z4hmDfAd2heBQMC+v8XLZ1m5eXgcOkndihbsHNyHec7tCAy7z+XIZ4D4B+tSx44dg3uzaUBPhPkiNl64KlXW2YhIhjdtgN8wV3TUVfG9euuz1UvOhxH16jUv30bTuWXzEuWSUlI5c+Ua3Vq3onsbJ05d+ovU9PTPpteV0DCOea9h74qlbD1wiJ89FzPrpxFc3euLgoIA7z3iGYjMrCzcp3rQvH5dLvnvZLvnPHYeDuTUpcsA5OeLGNrLhRC/HZzZLo6INX/9RqmyDp05i8eo4VwL8MNAV4cVO3w/W73klJ2nL1/y4s0burYu+TD4pJQUgi79hUu7NvRo35aTFy6S8i/DSpaFv26G8uf2Texfv5ote/cxbs4Cfpswlr+PHEBBoMAGP39A3Df7/zKZFo0acPVgADt/X8yO/Yc4eeEiAKJ8EcP7/sjl/Xs4v9sHoVDInFXSUX0Ongxi1rjR3Aw8iIGeLsu3bPts9ZLzYTx69IinT5/St2/fEuUSEhI4cuQIAwYMwN3dnQMHDpCcnPzZ9AoODubOnTtcvnyZ5cuX06dPH1atWkVsbCwKCgosWiReccjIyKB169Z07NiRN2/ecOrUKVavXs3BgwcBsevCpEmTePXqFZGRkeTl5TF+/Hipsnx8fFixYgXx8fEYGxsza9asz1avb4Hv2lhNzsoCwECzaBi1gpyNiERbTY1aFcpT19IcDWVlLjx6WuZylp46T9+NfpKXdyGDsTB969dCTVkZS0N9KhkZYG9eDktDfVSUlGhibUlkbDwA16NeoKuuRtda1VFSVMBMT4dONW05/043Ux1t6lpaoKyoiJaaKr3q2nPn1Vupspxsq2BlpI+yoiItqlWW5C3n65Pw7qFp+m6msTgOB59FX0ebJnVq0aJ+XTTVNQg8V3a/qV+8luLYo6/kNW+dd4nyY936oqGmRjUrS6pXqkQDB3uqWlmiqqJC+6ZNCH8cCcDZq9cx0NXFvVtXlJWUsDQ3o1+XTgSePQ+ARTlTmtevi6qKMrraWozs04ur7/wY/8GlrRM2laxQUVama6sWkrzlfF0Skv7pm0Ylyh08FYS+jg4/1HWkZcOGaGqoE3jmbJnLGT93AQ6dnCWvOStLDgM5fuAANNTVsalcCVvryjSsXYtqlaxQVVWhQ4tm3H34GIAzf13BQE+XQT1dUFZSwsrCHLfuXTlyJhgAi/LlaNGwAaoqKuhqazPKzZWrt25LldWjQztsrSujoqyMc5vWhD/8rMHL5HwAsbGxAJiZmZUo5+vri6GhocQw1NbWZvfu3WUup2/fvujp6UlehQ3GwsyePRtNTU1q1qxJrVq1aNmyJXZ2dqipqdGzZ09u3hSH1A4MDMTY2Jhx48ahrKxMlSpV+Omnn/D3Fw+2rKys6NChA6qqqujr6zNt2jTOnTsnVdbAgQOxt7dHRUWFfv36SfL+Xvmu3QB03jlMJ6RnUk5Xu1i5oPuPaFmtMgoCAQgENK9WiaD7j+hY06ZM5Uxu1+KDfFb1Nd4bz6pKikU+Z+XmAeJl/mfxifTd6CdJzxeJqGwsXqpKyshkU8g1wl9Hk5GTC0Bmbm4JZSmRVShdztdDX0cHgOj4BCqWL1es3L6TQXR1aomCggIKQJeWzdl3MgjXzmXbxPfH9Mkf5LNqZKAvea+mpoqxfoHPqqpkZIoHgS+jY3gY9QzHHu9nN/Lz86luXRmA+KQk5q/fxI274aRlZACQnpEpVVaRvN8NMOV8XfR1xdFeo+PjqFiCQRBw/E+6tW0t7psK4Nzaib3H/6RfAbeWklj128wP8lk1Nng/sFNXUyv0WZWMTHH/evn2LRFPnuLQyVmSni/Mp0bVKgDEJSYyb9VarofdIS1d3Df/6aOyy1IlPVO678r5ehgZiQdRr1+/pnLlysXKbd26FTc3t3f9UwFXV1e2bt3KyJEjy1TO7t27P8hntVy5989xDQ2NIp/T3q06REVFcefOHYlfLYBQKKROHbELTUxMDBMmTCAkJISUlBQAUlNTSywr7TOuaHwLfNfGqrmeDibaWoQ8esqP9RxkyjyOieNpXCIxKWkER4hH5bl5QtJzcnkWn4ilob7M+74ExlqaVDU1YknPTjLTd16+Sa4wn5V9ndFVVyP8dTTTDpyQKSvn26OShTkWpiYcPx/CqL4/ypS5++gxD5485VV0DIeCxLNC2Tm5pKan8yjqGVWtvp6PkpmJMQ42Vdm9fInM9GVbd5Kbm8uRdSsx0NXlxt1wXH+dJlNWzrdF5QoWWJQrR2DwOUb3lx2C/k7EQ+4/juTl27ccOHkagOycHFLT0nn4NIpqlay+nMKFMDc1oVZ1WwLWrpSZvtR7M7m5eRzbshEDPV2uh92h99ifv7CWcv4t1apVw8rKij179jB9etFNpQB///03t2/fJioqip07dwKQlZVFcnIy4eHh2NnZfUmVpahYsSINGjTg4sWLMtOnT59OTk4OoaGhGBkZcfHiRZo1+/8OSvRduwEIBAJGNm9IwN93OHbnAalZ2QC8SEhi6cnzpGVnc/r+Y2xMjVjv5sKqPs6s6uPMejcXqpgYEnT/8VfVv75VBeLT0jlxN4KcvDyE+fk8i0/kwZsYADJyc1FTVkJTRYWkjEz23gj7qvrK+TAEAgGzRo9kw54A/I4eIylFPHJ+/PwFP3stJSUtjX0nT1PL1oaTm9dzZN0qjqxbxcnN67GvVoV9J4O+qv6tGtbnbVw8/sdOkJ2Tg1Ao5FHUM27dewBAekYGGmpqaGtqEp+UxHr/vaXkKOdbQSAQMOfnsaz39cfn4GGS3s3uPI56xvi5C0hJTWPvsRPUrlGdMz7bOb5lI8e3bOSMz3YcbG3Ye+zrDpqdGjfmTWwsuw4fJTtb3DcfPo3i5t1wANIyM1FXV0NbS5O4xETW+viVkqOcbwmBQMDq1avx8vJi3bp1JCQkAHD//n1cXV1JSkpi69atNGzYkAcPHhAaGkpoaCgPHjygXr16bN269avq36VLF16+fIm3tzdZWVkIhULCw8O5fFns75+amoqmpia6urrExMSwcOHCr6rvt8B3PbMK0KBSBWZ3ac2eG2Hs+OtvFBTE56y2rl4FJQUFLjx8wsjmjdB/t4P+H5xr1WDrxesMbFwXJcWSbfrFf56TOmdVT12dTe49P1p3dRVl5ndrz9ZL19l19Ra5+fmY6+nQt754J7hbg9osDwqh76ZdmGhr0tnelpvPX310uXK+HE6NGrBx3mzW7drD0q07UFRQwNzUlB5tW6OkpETg2QvMHjMSYwPpGf6B3Z3x2riVSUMHoqxU8s94/MLFUuesGurrEbx900frrqmuzg6v+SzatJWVO3eRm5eLlbk5Y93EbgHj3d2YsnQ5dXv0xczUhP5dO3PhxvftV/U90bpJYzYvWsianb4s8d6MgoICFuXL0atDO5SUFDl65ixzfx6HcSGf60G9XFi4dgNTRw0vtW+OmT1P6pxVI319zu/++E12mhrq+C5fiue6DSzfup3c3DwqVbBg/KABAPwyeCC/ei6mVqdumJuaMMClG+evXv/ocuV8Obp06UJgYCALFixg2rRpKCoqYmVlxaBBg1BWVsbf3581a9ZILZcDTJgwgV9//ZVFixahrKxcYhk//vij1DmrpqamREZ+vF+9lpYWQUFBTJo0idmzZ5OTk0O1atWYPVt80sbcuXNxd3dHT08PS0tLxowZw59//vnR5f6XEYhEon9/s0DgWF5XO3jjgJ66n1AnOf/HiEQinNfuQCQSCUqXLhvqqqorJ7i7jR/2Y49PlaWc/zOauLqnxiYk1hWJRJ91l41AIKhfuWKF02d8t8ufqXJksjvwGF7rNvonp6bK9s/4hBgZGd0MCAio06pVyadCyJEji5SUFIyNjbOzs7PVPjav79oNQI4cOXLkyJEjR85/G7mxKkeOHDly5MiRI+ebRW6sypEjR44cOXLkyPlmkRurcuTIkSNHjhw5cr5Z5MbqO85GRLL8dMjXVuP/gnyRiHH+h3mekPS1VfnPcfjMWSYvWf611fguCTx3gZ+9ln5tNb4bDp46zcSFi762Gv9JboXfo+dP40oXpHDttAAAIABJREFUlFMmfH19cXd3/9pqfJfs3r0bV1fXz17OFzNW772JZpz/YXpu8GH87sOSs0KL4/KTZ4zw2U/PDT5M2X+cF4lFDRuRSMT0AyfoumY7mTlFIzPlCoWM8j1Av83+JZYlzM/H98pNfqxn/9E6FeTE3QgGbw+g1wZf5h4NIiH9fYSUjJwc/jgdQv8tu+m7aRezD5/idVKKJP2PoBBc1u3kR29fyetV4sfFNP6U+gP4XwtlwJbd9Pb2Y9mpC1Lfge+VmwzZEUBvbz8Gbt3DppCr5AqFACgIBLjUscPnyrd3jNHf4ffoOmoc9s496frTeMmZocVx+q/LtBk8AnvnnvSdOIXI5y8kaZsDDtBl1Dhqu/SmqdsgFm3cQk6BCGKrfHZh27Ebtbr9KHlduhlabFlCoZA/dvgWG0CgLDrJwv/YCZr3H4yDcy+GzZpLTHxCmXTMzsnF44/VtHIfSu3uvWk/dBQB7w6HLyup6Rn84rWU2i69adRnAGv8Sg6FGB0fz7CZc3Bw7kXz/oPZc/ykVPrj5y/o88sU7J170nbISM5cfh/6+OzV67j+Oo26PfvSsHd/xs734k1snCS9U/Om3H34iHuRTz6oDl+LG3fu0nHwcKq37USnISMkZ4gWx6mQi7Rydad62078OGYCkc+eS9I2+u+lw6Bh2HfoSuOefVi4doNUX/U5eJiWrgNw6OhMvW49+XXhIlJSi4+YIxQK+X3zNsYUE1CgLDrJYtfho/zQy5Ua7TozZMoMYuKkw0dfDQ3DZdRY7Np3pn73XmzeEyCV/uf5EDoMHEaNdp1p0rMvR9+FXy0LqenpTJi3EPsOXanXrSerdviUKB8dF8fgydOp0a4zP/Ryxf/oMUnarfB7uP86FceuLtTu3B33X6fyKCpKkl7HrgaqKiqcCrlUZv2+JpcuXaJWrVpoaGhQu3ZtyXmhxXHo0CGqVq2KhoYGTZs25cED6eest7c3FStWRFNTk86dO/PmzRtJmp2dHVpaWpKXsrIyDg6yg/6AuC/OnDmTGTNmfJROhSlJx8mTJ2NjY4O2tjaVKlXCy8tL6t41a9ZQr149VFVV6dWrV4nlyCIlJYV+/fqho6ODqakp8+fPL1H+9evXdOrUCU1NTSpWrMimTdJHF96/f58ffvgBDQ0NqlWrxpEjR6TSExISGDx4MAYGBujq6vLDDz9I0nr37s2NGzcIDS3+v+tT8EWM1dSsbOYFnqFrrersHt6PzvbVmRd4hrTsbJnyrxKTWX46hOHNGuA/zBUHi/IsPBaMMD9fSu7UvUeUdPDW7uu30SsQbrQ4rkW9QF9DnQr6esXKlFWnf7j98g07Lv/NtA4t8R3aBz0NNX4/9T6eu++VW7xJTmVtv+74DOmDmZ4Oy09Lx3vv4lCdgJH9JS9z/X9/ms2n1j/o3iOC7j9icc9ObB3Ui9SsLDaGvDcMWtlYs8a1O3tHurHKtRtP4xI5eOv9n2kTa0vCXr4hPi39X9fpU5OUksqI2fNw796VG/t2079rZ0bMnkdKMWHsnr58xaTFy/EYNZwb+/xpVMuBn+YuJO+dUS7Mz8fzl3FcD9hFwIplXA27y9pde6TyaNOkEbcPB0hePzjWLla/4KvXMNLXx7pi8aF9S9OpMJdDb7Ns6w5WzZzGlb2+GOnp8evi38ukozBfiLGBPtsXLeDWwT0smvQzizZuKdHgLsz8dd6kpqdzwWcr/r8vYu+Jkxw8XbwB8YvXUkwNDbmy15dVM6exePM2robdASA3L4+Rs+fTtG4dbuzzZ/qIoUxctIxnr14DYmNjRO+eXPDdxtmdm9HS0GBigZlUBQUFnJ1a4h/47UeBS0pJYehUDwb1dCH02CEGuHRj6DSPYg3IJy9e8MsCL2aNH01o4CEaO9Zm+IxZ5OWJ+0V+vpDFUydxM/AgB9av4WrobVbveH/eacuGDTjkvZawE0c45+9DnlCI14aNxep35q/LGBsYYG1ZsViZ0nQqzF9/32Kx92bWzJvNjcP7MDLQ5+f5npL0yOcvGD1rDj+5uRJ67DDBfjto0bC+1P1zV61h7i/juXPiCIFbvLG3KVtIbYA5K1aTkprGpQB/9q5ZwZ6jx9n/56li5cfPXYipsRE3Du9jzbzZeK335krobQCSU1P5sVN7zu3y4dqhAGpVt2XwlBnkF3ge9+jQFr/DR8us39ciISGBLl26MH78eBITExkzZgxdunQhKUn2ZMjDhw/p378/K1asICEhAScnJ7p160ZenjjMeHBwMNOmTSMgIICYmBhMTU1xc3OT3B8eHk5aWprk5ejoSO/evYvV7+jRo5QrVw5bW9tiZUrTqTCl6aimpsb+/ftJSkrixIkTeHt7s2XLFkm6mZkZM2fOZPjw4cXqVBLjxo0jKSmJ58+fExISwqZNmyRRumTh6uqKubk5MTExBAQEMHnyZM6fPw9Abm4uXbt2pV27diQkJLB8+XL69evH48fvgyL16NEDdXV1IiMjSUhIYMWKFZI0BQUF3Nzc2LBhw7+qS1n5Isbq5SfPMNHWpF2NaigrKtLerhoGmupciZQ9ij4bEUkti/LUt6qAipISfevVIjkzi/DX0RKZxIxM9t+8w5Af6svM41l8IpefPOfHuiXPlgJcj3qJg0X5EmXKolNBgu4/orWtNTbljFFTVmZg47rcfR3N22RxlKLolDQaVq6ArroayoqKtLKx5tlnXBb/1Pqfvv8I51o1MNPTQUtVlQGNHDn/8AnZ737c5vq6aKi8P3BZIBBI7gVQU1amiokRN559O0EMTv91GTMTE37s0A5VFWX6dGqPiaEBpy5dkSl/6MxZmtSpRauG9VFVUWGMW18SkpK5cUdslI/s0wsHm2ooKylR3tiI7m1a8ffde/9av7NXr9O4VvEzCGXRqTD7TwXh0qY1tW1t0FBTY/LQgVy/c5fnb96Wqo+Gmho/D+yPpVl5BAIBdarb0rCWAzfv3S9TfTKzsgg8f4GJg93R0dKikoU5A7s7E3BStgHw7PUbbobf59ch7mioqVHb1oburVux/10kr+t3wklNT+Mn196oqqjg1KgBDWvZc+jMWQCcnVrSqmF9NNXV0VBTY5CLM7fuP5AyEBrXrsXZa9/+4fAnL1zEvJwpfbp0QlVFBdeunTE1NOJkiOzwjQdPBvFDXUecGjdCVVWFcQMHkJCUzPUwcdS7UW6u1KpuK+6rJsa4tG/LjTt3JPdXMCuPno4OIF7REggEPH83CJDFmb+u0KSEgVdZdCpMwIk/6dmhHXVqVEdDXZ0pI4dxLSyM56/Feqze4UPfrp1o1+wHlJWU0NbUpKqVleT+P7ZuZ9zAATSs7YCioiIGerpYWZiXqOM/ZGZlERh8jskjhqKjrUXlChUY1Mul2Ehdz1695u+7d5kyYhga6urUqVEdl3ZtCXgn37JRQ7q2dkJHWwsVZWVGuPbm1dtoXsfESvJo4ujI5Zu3yMzKKpOOX4uDBw9iaWnJ0KFDUVVVZfjw4ZiZmXHw4EGZ8j4+PrRp04bOnTujpqbGrFmziI2NJSRE7Ia3bds2Bg4cSMOGDdHU1GTRokVcuHCBJ0+KrniEh4dz48YNBg4cWKx+gYGBODk5lViH0nQqTGk6zp8/n5o1a6KoqIitrS09evSQCq3ao0cPunfvjpGRUYl6ySIjI4Pdu3fj6emJnp4e1apVY8KECVLGcEEiIyO5dOkSXl5eaGpq0rBhQwYMGCCJ4nXhwgWSkpLw8PBATU2NLl260KpVK3x8xCsHQUFBPHnyhFWrVqGvr4+ioiL160vbXa1btyYwMPCD6/IhfBFjNSoukUpG0lFOrI0NeRqfKFs+PpHKBeSVFBWwNNQnqoD8ppCr9KhTE1111SL3i0Qi1p69zLCm9VEpEH2iJP0sSpm1LItOhfMsWGc9DXUMtTQk8p0dbLn57BWJGZlk5+URdP8R9SwtpPIIuv8I1027GLPrEMfulLwkURqfWv/C+VUyMkCYL5JyZTh+5wG9vX3pv2U3UXEJdLKXHtlW1NflSVwC3woPnkZR3bqS1DW7KtZEPH0qUz7iSRTVrStLPisrKVGtkiUPnkbJlL8WdpdqVpZS1y7evEX9Xv1oP3QUa/x2FzsD+k95lStYFJv+b3QSy7+vs6GeHqZGhjwsIF9WHbNzcgiLeEjVEmbTCvLk5SuEwnxsK1lJronbuxhdn0ZRztgIA933v9UaVawldYt4+pSqVpYoFfjNl5TftTt3sa5YAYUC0b2qWFYgOi6e+KSPc7n53DyIfEKNKtZS1+yqVeFBMS4MYvkqks/KSkrYVK5UrPy10DCqVZL+LQRfvoJDR2ccOjpzKuQSw0twR3kQ+YTKFUvuBx+q04PIJ9So+r7ORvr6mBoZ8SBS/Pu8FX4PJSUlOg8dST3nngybNpNX0eLBuFAo5Pb9B6SkpeHkNpCGLr35ZYGXJIxsaTx5/oI8oRDbAr+tmtWqlqhrOWNjDPR0peWfyH6WXA29jY6WFuUKGC9mpiaoKCtL/Ra/RcLCwqhdW3pg4ujoSFgxg47C8srKytjb20vkC6ebmJhgbm7OnQKDp3/Ytm0bbdq0oUKF4lebwsLCSpxVLYtOpcmXpKNIJOLChQvUrFmzRB3KSkREBHl5eVKuD6W1t4WFhZRhXFA+LCyMmjVrolQg2lzB9MuXL2Nra8vw4cMxNDTEwcGBAwcOSJVRo0YNXr16RWxsLJ+LLxJuNSs3Dy1VFalrmqoqZOYW9TMFyMzNQ7OQvJaqisQn8sazl8SlZtDerhoxMpa9jt+NwFhbE8eK5tx5+aZIemHSsrNRVyk57FppOhUmS4a8psr7OlcyMkBVWQn3rXtQEAgor6uNp0sHiWxXhxoM+aE+WqoqPHgby6I/z6KmpETr6lX4N3xq/QunKyoooKasREaB/DrZ29LJ3paXicmce/gE/UIuGeoqKkSnpPKtkJGZhY6mltQ1bS1N0jMzZctnZaKtqSl1TUdTS6b8nuMnuXnvPofXrpRc69jsB3p3bI+JgT4Pnkbxi+cSRCIR4/rLdlZPTktDS7Nkt5YP0QkgPSsLHa3C8u/rXFYdRSIRM/5YjZWZGe1+aFyijhJdM7PQVFeXMha1tTRJzyimvTNl1K2AfHpmFjolpBck/HEkK3b4scpjqtR1LQ1x2OWUtDQM9b7dIFIZmZnoaEn3VR0tLdIyMj5Qvmjb+B89xo27dzm22VvqulPjRoSdOMKbmFj2HjuBRaEwlgVJSU1Du1AI64/RqST59Exxnd/ExLLv+El2LFuERflyLFy7gTGz53HIey1xiYnk5uVx9MxZ/P5YhqaGOpM8FzPz95WsmTurRD0B0jMz0dSQ7qsFy5YlL1NXGd/Py7fReCxbgceYUSgpSU+uaGlqkFyCb/C3QFpaGnp60i50enp6pKbKfraXJl/W/PLy8vD19WXlypWURGJiIjrvVgW+VB0K4uHhQUZGBqNGjSpRh7KSlpaGtra2VF/8nO394sULTp8+zfr169m4cSPnz5/H2dmZq1evYm8vXrn+p30TExMxNjb+JPUszCefWT0XESnZEDR61yEA1JSVSM+WNorSs3NQLyYur3ohowcgLTsHdRVlsnLz2HjhKqNbNkYgKBqRMyE9g/037zCsqWz3AFloqapKGW17b4RJ6vDbkdOl6iQLNWUlMgrXOed9nRedOIu2qiq7h/cjYKQbLW2s+e3IaYkPaRUTQ3TV1VBUUMDOzBRnhxpcfBxVpvp8Cf3VlJVIL5BfvkhEVm6e1NL/P1jo62JlqM+qYOklysycHLTUis6MfwkOB5+TbBjqOHw0ABrqaqSmS/vQpqalo6ku20DUUFMvYhykpKcVkT8cfI4/dviyzXMeJgXiqFe1sqSckSEKCgrUsK7M2P6unLggexkXQFdLi7T093/k6/33Suow1OO3D9LpHzTV1EhNLyz/vs5l0VEkEjF71TqevnzJ+jkeUg/RktBQVyM9M1NqGT41LR3NYvzMNdTVSSv0/aQUkNdUl1EXGflFPI1iqMccfhszkqZ160il/dN2hQ2Nr8mhU0HYte+MXfvOtHMfAojbonBfTUlLkxjbhSleXrptDp0K4vfNW9n5+2JMjAxl5lXexJiWjRowcuZvxeqso60l9V2s9fGT1GHQ5GkfpJNUHdKKymuqi+uspqZKjw7tqGJliZqqKhOHDuL2/QfEJSairiqO9uju0o3yJsboaGkxbuAAgi9foSwhxzXV1UnPkO6rBcuWJS9T10Lfz5uYWPr/Mgn3Ht3o3bljkXzS0jPQ1f52+qKfn59kY5OdnR0gjnOfnCy9EpGUlIS2trbMPEqTL2t+x44dIycnh+7du5eos76+PikFZtA9PT0ldejYseNnqcM/eHl5sWfPHk6dOoVmoYH0v0VLS4vU1FSpvvg521tDQwMLCwtGjRqFsrIybdq0oXXr1pw48d4F5p/21dfX//gKFsMnN1Zb2lhLNgSt6yfuRFZG+jwttNz7JC4BK0PZFbMy1JdaHs4T5vM8PglLQ31eJyUTk5rGrCMnGbB1NxP3iv0kRvjs58qT50REx5KUkcn4PUcYsHU3nifOkpaVzYCtu3kcEy+zvMpGBrwssNO+dz0HSR3mOrctVSeZdTCSlk/OzCI+LUNS5ydxCXS0t0FTVQUVJSWca9UgKj6RuGI2HMkyzIvjS+hvZSj9nT6JTUBRQYCZnuwRrDA/n9dJ0iO/54nJUq4EX5JuTi0lG4ZObFoHgG0lK+4XWqa7F/mEapWsZOZhU9mK+wWWAXPz8ngU9RybSu+X+o8En2Phhk1sWTgH28qVZGUjQUGgUOIfZ3Xryjx58VLy+SfX3pI6bFk4t8w6lVSH+KRkouPii61zYR1FIhFz1qwn7OFDtnnOLzLzWRKVLcxRVFQg4ukzybV7kU+oVsDPUErXSla8iY0jscAfz73ISGzeuVbYVKrEw2fPEBZwUxDn977uD6OeMXDaLCYNGUi31kXjnT9+9gJTQ4Nvala1e7s2hJ88RvjJY5zaKfYzs7WuzL3HkVJy4Y8eY1NMHxPLv98wkZuXx8OnT7Gp/H5Z+/DpM8xfvY4dSxdR3dpaVjYShEIhL16/kWrrgtSoWoUnz9/vSRgzwE1Sh+1LF5VZp6J1eF/n+KQkouPisH3nxmJbuTKyHpMikQgdbS3MTEw+6DlakMoVK6CkqCi1jF9ae7+JjSGxgBFQWP5tbCz9JvyKS7u2jBngViSP19Ex5OTmFvtb/Bq4ublJNjaFh4v94B0cHIrsBL9165Zk1q0wheVzc3O5e/euRL5wemxsLK9evSqS39atW+nXrx+qqiVPeNSuXVtqZ/+MGTMkdfjH4CpNp9LqIEvHRYsW4e3tTXBwMBYWJbtvfQg2NjYoKSlJuRyU1t4vXrwgPj5epryDgwN3796V+i0XTpf1uyn4P3Dv3j3MzMw+26wqfCGf1caVLYlOTSPo3iNyhUJO3XtIfFoGjSvL9mlqaWNN6IvX3Hj2klyhkL03bqOtpkpNM1MsDfXZNvBHVvVxZlUfZ37rKjbGlvbqjGNFM+pZWrDFvZckfZzTD2ipqrKqj3OxxnGDShUIe1nyhpKSdJJFm+pVCX7wmIfRcWTl5rHj8t/UNDOlnK54tGJjaszJ8Idk5uSSJ8znWNh9tNVUMXq3JBvy6CkZObmIRCIevInhyO17NLZ+315/BIXwR1DZz4X91Pq3qV6Vw6H3eJ2UQnp2Dr5Xb9KiWmVU3/m9HAu7T0pmFiKRiGfxiey9EUadimaS/LNy83gcE0ddy7JtcPgStG3SmFfR0ew7GURObi4Bf54iOi6edk1kL2t3c2rJpZuhnL9+g+ycXNb770VPR5v69mLfpKNnzzN/3Ua2LJiDXZWif/6n/7pM0js3iEdRz1jt50+7pk2K1a9VowZcKcYvqaw6FaZnuzYcPB1MWMRDMrOy+H3bDurb16Ri+XJl0nHu2g3cDL/Pdq/5MmeApiz7gynL/pBZtrqaGp2bN2P59p2kpqcT9eo1Ow4doXeHdjLlLc3KU6dGdX7ftpPMrCxuP3jI4TNn6dVB/Ayob2+HtoYm63cHkJ2Ty7lrN7gSGoZLGyeJ/u5TZ/LzQDd6tW8js4wrt8No2bDsqzJfi/bNm/LyzVsCjv9JTm4uewKPEx0XR/vmTWXKd2/Xhos3/ubclatk5+Swdqcfejo6NHi3Ye9IUDBzVq5m21Iv7KpVLXL/7sBjkmOiXr55y5KNW2hStw6KxewJaN2kEZdvlXwqRGk6FebHjh3Y/+cpbt9/QGZWFku8N9PAwYGKZuLnSp8undj/5ymevnhJTm4uK7btpFZ1W4wNDN6ld2TngUPExieQnpHJOp9dODVuJPkjnuS5mEmei2WWra6mRmenlvy+aQspaWk8ffGSbfsO0KdLJ5nyluZmONrZsXTjFjKzsgi994CDJ09LZk+j4+JwHf8rnZ1aMmGw7PM/L98KpVGd2qirqZXYjl8bFxcXoqKi2LZtGzk5OWzZsoVXr17h4uIiU75///6cPn2aEydOkJ2dzcKFCzE0NKR58+YADB48mB07dnD9+nUyMjKYPn06zZs3p3KBQUxMTAzHjx9nyJAhperXtWtXzp49W6JMaToVpjQdlyxZwtq1awkODsbSsuhEQV5eHllZWeTl5ZGfn09WVhY5OTmS9EGDBjFo0CCZZWtoaNCnTx88PDxITk7m0aNHrFy5kmHDhsmUt7a2pkmTJsyYMYOMjAyuXbuGj48PQ4cOBaB58+bo6uri6elJdnY2x48fJzg4WHIurYuLC+np6WzevBmhUMi5c+cIDg6mU6f3ff/s2bN06dKlxDb+WL6Iz6q2miqzOrdmw/krrD9/BTM9HWZ1aS1ZAg5/Hc2co6cJGNkfEC8bT2zTjI0XrhKfloG1sSEzuzih+G55Ub+AL1TOu9GArroaKu8MpYLp2qoqIJC+Vpi6luZ4X7jKy8TkYjdalabTuYhI9v59RzKbXMuiPO6NHfE8Hkxadg41zU35td37jj+hdVM2hVxl2M59CPPzqWioz6zOrSX5HbvzgLVn/yJfJMJIS5Mf6zrQrkY1yf1xqek0ryZ7BuJL6N+2RlXi0tKZsv84OXl51LeqwPBmDSXp15+9xO9aKDl5QnTV1WhibYlbw/dLrpefPMPevJzEOP8W0NPRxnvuLOas2cCcNeupZG6G99xZEiPs+p1whs2cw+3D4rMbK1ewYOmUicxft5G3cfHYVbFmw5yZkg0+y7ftJC0jg/6T35/vZ2ZiLJnJPX7+Ih5/rCYrOwcjA326t27FT67FH8HSsn5dFqzz5smLl8VutCpNp8PB59jgv1eiQ+PatZg42J3R8zxJSU2jgUNNfp/6qyS/knR8FR2D39HjqCgr03LAUMk9zk4tmT9hDABvYuLo0lL2Ax9g9phRzFq1lmZug1FVUaG/c2dc2r7fudtx+GhGufamm1NLAP6YPhmPP1bRsHd/dLW1mTJ0MA0dxDMAykpKbJg7k5kr1rBhdwDljAz5feqvWJqLjZnN+w6SkJyMl/cWvLzf75w9sWktZiYmiEQijp49zx/TJxer77eCno4OmxctYNbylcxavpJKFSzY7LUQ3XdLd9duhzF4ynTCT4rP9rSuWIHlHtOZu3Itb2JjqVmtKpu9Fkh8JJdu3EJaegauEyZKyjA3NZXM5Ibee8Dvm7eRlp6Bno42LRs1ZPLwoRRHq0YNmbtyLZHPXxR71FppOh06FcQ6310SHZrUrcPkEUMZNfM3klPTaFjLgRWz3v+2enZox5uYWHqP+5nc3Dzq2tuxdt5sSfro/m4kpaTS1n0IigoKNGtQjzkTxkrSX0fH0LVN8bvG5/48Do9lf9CkZ1/UVFVx79GNngUGVu3chzC6fz+6txMPhFb95sG0Jb9T17knetraTPtpBI1q1wJg99HjRL16xbZ9+9m2b78kj21LvCTG+sGTp3Hv0a1Yfb4VDAwMOHr0KKNHj2b06NFUq1aNo0ePSpaEQ0JC6NixI2nvjgC0sbHBx8eH8ePH8/LlSxwdHTly5Ihkg4+TkxOenp64uLiQmJhIixYt8PPzkyrTx8cHOzs7HB0dS9WvU6dOjB8/noiICGyKOaqsNJ38/Pzw9PSUzCaXpuPUqVOLnP/arFkzyUzuggULmDt3riRNXV2dFi1acO7cOQCeP39e4kH7a9asYeTIkVhYWKCurs7YsWOlgh7Y2dkxY8YMyXFa/v7+DBs2DGNjYwwMDFiyZAktWrQAxJvJjhw5wvDhw/H09MTCwgI/Pz+qvNv8qK+vT2BgIGPGjGHChAlYWVnh4+MjmXkViUT4+fmxe3fJZ2R/LIKy+OsUe7NA4FheVzt444Ce386a2b/kbEQkt56/ZmLbZl9blVLJFQoZ53+YNa7dUVL87wUhyxeJmLD7CJPaNS/ihiASiXBeuwORSPTv1utkoK6qunKCu9v4YT/2+FRZfjUOnznLxb9vsXTKxNKFvzLZObl0/Wkcx7zXoKz0RcbFH8WxcyGc/usyK2ZMKZLWxNU9NTYhsa5IJHr0OXUQCAT1K1escPqM7/b//DP14KnThFz/m+Ue0762KqWSnZNDx8HDObljyzfRV2/du8/81Ws5sH5NkbTdgcfwWrfRPzk1teSIC58AIyOjmwEBAXVatSrqMvNfwtfXl1OnTpV4Fum3QnZ2tmRpXrmYfT3fEnv27OHgwYMyjdWUlBSMjY2zs7OzP3p5QG6syvmmkBurcr5F5MaqnG8FubEq57/CpzRW/3vTcnLkyJEjR44cOXL+b5Abq3LkyJEjR44cOXK+WeTGqhw5cuTIkSNHjpxvFrmx+h1x5+Ub+m32/9pqyJEjk6u379Dgx8/uZidHzgdz5VYojl1lH7UkR87X5ty5c1LhUv8f+frbHr8Bwl9Hs+f67f+1d+fhMZ3tA8e/J5tMlskuQRBBbLUUreX92VuKotYkSFB0RzdtUbuXtnShaNFnlakwAAAerklEQVSm9tjeVm21r6+11doTImKNRPbMZJlkkvP7I4ykCeLtYHB/rutcV3OeO+c8J9fTcc85z7kfzsUngKLg7exEm5pV6VKvlqm0U76qMnjRGqytFBaE9ERRFMav28aZ6wVrTxvz8slXVexull3xcnZibt9XGLxoNamZ2VhZ3X5fqKqXB5/1KL5ayd18vX0fWnt7Bt/HylziyfD7ydPMDV/J8chzKEpBSaHuL7QhtFsXU53L/Px8WocOxtramp0LF6AoCoPHjOePU2eAgoLr+fn5lLErWCL3Vgmt1qGDSUxJNY1zgNrVqhL+5Wf31cePZnyNu1bLJ6/duZyRePIcOX6C2YuXcSwiAgUF33I+9OjwIgN7di8yNlv06Ye1tTV7VixBURQGjvyE308UFDXPzTWSr94em7dKZv1fn74kJqdgXajiSZ3q1Vk1+5v76uOHUz/HzcWFMW+bZ7lL8fjYt28fU6ZM4fDhwyiKgp+fH6GhoQwfPrzI+PTz88PGxobo6GgURaFjx47s21dQxzwnJ4f8/Hzsb9a7rVy5MqdPn8bPz4/4+PgitYYbNmzI3r1776uPAwcOxNPTkxkzZpjpqp9MT32yeiTmCjO27iGkaSM+bN8SrcaeS0kphP9+nBdqVcPp5uoYf12+ht5gIC8/nxPX4qjvW860OhTA8sN/cSk5lVEdi781+fFLrXm+Ssm1BoW4m52HjvD+ZzN4f1AIX33yIW5aLecuXmL20nB6tn/BtCzof4/+RZpOjzEvj0PHT9CsQX3TqlYAs5YsL/i9saOKnWPWmI9p2/T5h3ZN4smw48BBRkz8Nx++NpiZ40bj5uLC2QsxzFq0hN4dX0J7sz7xvt//IFWXjjEvj4N/HqN5o2dNq1gBfBO2iLMxMXw3eUKxc8yZNI52d1iUQ4i72bBhA8HBwUydOpXly5fj4eHBqVOnmDRpEoMGDcLV1RWArVu3kpycjNFoZNeuXbRt27bIUqITJkzg1KlTrFmzptg5Vq9e/cCL4YsCT3Wyqqoq8/cdplejenSpX8u0v7KHG5+81LpI7LaI8zTzr0yO0cj2M1HU9y1n9v7kGI3M2X2Q32OukqfmU9bZiZEdWnHyWhx7zl1AQWHz6bNUcHXhm8AuJOkzmbVzPxHXb+CtdaJdzWpm75N4dFRVZfJ383k9sBeh3bqY9gf4VWbWp0VrV67Zso32/2pGdk4Oa7Zsp9nN4uPmZMjJYeysOew69DvGvDx8vcvy1aiRHDlxkvU796AoCuEbN1PFtwJr53xDfFISo7+axdEzEVT09qb7i+3M3ifxaKiqysSZc3izfzADe95+fF7DvwpzJo4rErtq02Y6tGxBtsHAqk2/0bzRs38/3D9mMOQw5suv2XHgIHl5+VTw8WbW+DEc+us4v27bgaIoLF+3Hv+KFVn/w/fEJyby8eczOHryNL7lfIoU9xePP1VVGT58OKNGjWLYsGGm/c888wyrVq0qEhsWFkaPHj3IysoiLCyMtm3vvDDE/yo7O5s33niD9evXYzQa8fPzIzw8nN27d7Ns2TIUReH777+nRo0aHD16lNjYWAYPHsz+/fupUqUKAwYMMHufHjdPdbIam5pOfLqeltXvvma7LtvAkZjLjO38Arl5eXy+ZTdvGHJwLGNn1v7siIzmUlIq80N74GBnx9WUNJzL2NG5bk3OxScUmwYwY+sefFycWfxqIMkZmUzasN2s/RGP1sVrsVyNi6fzXVaAAkhN17Hj0BHmTRyLITeXd6d+ji7jDZwdzbs62M/bdnAu5hI7Fs7HycGB6CtXcXV2pl+Xzhw/e67YNID3P5tBRR8fDoYv5kZSMq+Nm2TW/ohHJ+bqVa5cv06Xdnevv5mans72/Qf4YdoUDDk5DJswhXS93vREwFz+s3kLZy/EsCd8KU6ODkRfvoyrs5aQ7t04HhFZbBrAiElTqVS+HEfWriY+MYnBn4wxa3/EoxUVFUVMTAxBQUF3jUtOTmbdunWsX7+e7OxsAgMDSUtLw8XFvGWOFy1axMmTJ4mOjkar1RIZGYm7uztvvfUWR44cKTYNoG/fvvj7+xMXF0dsbKzcveUpf8EqLTsbAHdHzV3jdp2NxtnenvoVy9GocgUcbG3ZGxVT6vNM37qHoPnLTNu8vYdLjLO1siIrJ5erKWkAVHJ3veMysYn6DE7FxjOoeWPsbW0o76qlW4Pape6TsHzJaQXjwNvD/a5xv+7chZvWmebP1qfVc41w1DiwYXfp5029N206DXsEmbZJc+eVGGdrY0tGVhbRV64CUL1yJbzc3UqMvZ6QyJETp/h46CA09vZUrlCeAd0tf+lIUTrJqbfG5t1f+vhl63bctFr+1aghrZs0wdFBw4Ydd1+nvbDhE6dQr1NX0zZhZvEVnaBgyUh9ZibRly8DUN3PD687/H9z/UYCh48dZ9Sbr6Gxt8fPtwKv9u5Z6j4Jy5eQkABA+fLl7xq3dOlSPDw8aNeuHR07dsTZ2fm+lg0NCgrC1dXVtA0fPrzEODs7O3Q6HZGRkQDUrl0bHx+fEmOvXr3Knj17mD59Og4ODlSrVo1333231H16Uj3Vd1a1NydMJ2dk4ePifMe47RFRtA7wx0pRQFFoGVCF7RFRdHym5HWG/25k+1almrPapmZVkjIymb3zAMmZWTT3r8yr/9cYB7vid3CT9JlobG3Qam4vDFHW2bx3K8Sj5abVAhCflEylciV/sAGs2bKdLm1bY2VlhRXwcuuWrNmyneDOpXuJ7+tRI0s1Z/WVF9oQn5TEp9/MJiE5mfb/as7HQ1/FuYQvVPFJSThqNKZrAPD1Lluq/gjL53bzzlN8UiKV7pIQrN60mW4vtisYm1bQtV1bVm3aTN9C01ruZtb4T0s1Z7V7+xeJS0hk1BdfcSM5iQ4tWzD6rddLfLoQl5hYMDYL3T3z9fEuVX/E4+HWm/OxsbH4+/vfMS4sLIx+/frdHJ9WBAcHExYWxuuvv16q86xYsaJUdz1DQkK4du0aQ4cO5fr16/To0YMZM2agLfT5eMu1a9dwcnLCw8PDtM/Pz69U/XmSPdV3Viu4ainr7MS+u9wlPX8jkZjEFLacPktI2ApCwlawI+I85+ITuZSUYtb+WFtZEfhcfWb3fYVvg7pxKTmFn/88BVCQKBfi4eRAVq4RXbbBtO+GTm/W/ohHq4pvBXy9y7Jpz747xpyKOk/khRhWbtpCs6AQmgWF8PO2HZw4e46oi5fM2h8ba2ve7hvIxnmzWf/9t5y7eIkf1vwMgJVS9KPE28ODjKwsUtN1pn1X42+YtT/i0fGv6Iuvjw8bdu6+Y8zJs+eIOB9N+PqNPPdKL557pRdrNm/heEQk52IumrU/NjbWDBvQn82LfuC3nxZw7kIM88ML5iZaWRUdmz6enjfHZrpp39W4eLP2RzxaAQEB+Pn5sXLlyjvGHD16lOPHjzN//nx8fHzw8fFh4cKFHDlyhNOnT5u1PzY2Nnz66aecPHmSEydOcOrUKaZPnw4UH58VKlRAr9eTnJxs2nfx4kWz9udx9FQnq4qi8HrLJqw+epKNJyNNid+V5FSmb9mD3mBgW8R5anh78l2/7swK7MqswK5816871cp6sD3ivFn7c+LqdWISk8nLz0djZ4ONlZUpSXXVaIgv9A+/p5Mjdcp789OBPzAYjVxPS2fd8Qiz9kc8WoqiMPat1/l+5WqWrd9oSvzOX77Cu9Omk67Xs2bLNurXrMGWH75j3dxZrJs7iy0/fEfdgGqs2WLeOcyHjp0gIjqGvLw8HOw12NramEpeebq5crnQP/jlvDx5rm4dvvjxJ7INBi7FXmfR2nVm7Y94dBRFYcK77/Dd0nCW/PKrKfE7f/ESwydOIV2nZ9XG32hQuxY7lixk04/z2fTjfHYsWUi9mjVYtfG3e5zh/hz88y/OnI8uGJsaDba2toXGphtXYq+bYsuV9eL5+vWY9t38grF5LZafVv9s1v6IR0tRFL799lumTZvG3LlzTYlfREQEwcHBpKamEhYWRpMmTYiMjOTYsWMcO3aMyMhIGjduTFhYmFn7s2vXLo4fP05eXh5OTk7Y2dmZSl55e3tz4cIFU6yvry8tW7bko48+Iisri+joaGbOnGnW/jyOnupkFeD5KhUZ93I7Dl24zOBFawhasJwZW/dSw8cLGysr9p67wMv1auPm6FBk61q/NrvPRmPMy7/nOT7fvJve85aatqGL/1NiXEpmFp9v3k3QguUMXfwfvJyd6NHwGQDa16nODV0GQQuW8/6qDQB82L4liboMQn5cydRNu+hQO8B8fxhhEdo2fZ75k8ax7cAhWg8YTKOeQbz/2Qwa1KyBjY0NG3btJbTby3i5uxXZBrzSlV937ibXaLznOYb/+3Pqd+tt2toOHFpiXEJKCu9O/ZyGPYJoN2go5b28GNK7BwC9X2pPbPwNGvUMouew9wH48uMPuZ6QSNOgEN6ZNJXAjh3M94cRj1y75s344bN/s3Xfflr06Uf9Tt0YMXkqz9auhY2NNet37GJgz+54ebgX2Qb26s7abdtLNTbfHjeJOh06m7ZWQf1LjEtITmHYhMnU69SV1kEhlPcuy2vBfQAIfLkT1+Ljqd+pG91eewuAb8aO5vqNBJ7r1os3Ph1PUJdO5vvDCIvw8ssvs2HDBtauXYufnx9ubm707duXpk2bYmtrS3h4OMOHDzfdVb21jRgxgqVLl5Kbm3vPc/Tu3RsnJyfTVrVq1RLj4uLiCAwMxMXFhapVq1KpUiVGjhwJwJAhQ7h06RJubm48/3zBdKxly5Zx5coVvL296dGjB0OHlvyZ/DRRVFX9339ZURqWc3HeOT+kp3lfnRNPLVVV6TpnEaqqKveOLh1NmTIzR4T2G34rsRLifjUPDtUlJKc0UlU16kGeR1GU5/wrVdy2Y+lC+UwVJVqxYSPT5s4PT9PpHvhycJ6enn+uXr362TZt7l71QYiSpKen4+XlZTAYDPb3jr67p/7OqhBCCCGEsFySrAohhBBCCIslyaoQQgghhLBYkqwKIYQQQgiLJcmqEEIIIYSwWJKs3gdjXj7f7zlE8ILlBC9Yzrw9h8jLL7l0VWZODtO37KHPvGWE/LiCFb8fL9KepM9kwvpt9Pp+KYMWrmbL6XMlHmfbmSi6zF7IhhNSQ1XcWa7RyMTZ39O4ZzCNewYzac48jHl5JcbqMjJ5b9p0GnTvQ9PAEGYvK7q8YHxSEkM+nUC9rr1o2X8QKzdtKdJevUMX6nbtaSp1FfKRrKsu7i7XaGTc17No0PkVGnR+hfHffIvReKfxmcGISf+m7ktdaNytJ7MWLSnSHp+YyKCRo6jdvjP/6hVM+PqNRdqrtGxHrRc7mcpd9R3xwQO7LvH4y83N5Z133sHd3R13d3eGDRuG8Q5l1dLT0+nbty9arRZvb28mT55cpD02NpZOnTrh6OhIpUqVWLBggaktLS2NFi1a4OnpiVarpX79+vzyyy8P9NqeJE/1cqv3a+Ufx4mMS2Bu31dQgQnrt7HqjxMEP9+gWOy8PYfJyMkhbGAv0jKz+fTXrZR1dqRtzWoATN+6hwquWpYODuRSUirj122lvKuWuhVuL6uZlpXNmqMnqeTu+rAuUTym5i5fyV8Rkfy2YC6qqjL40wl8F76KYf2Di8VOnjsPXUYGe5eEkZSaxoBPPqVC2bJ0f7EtAO9Nm06VChU4tGop5y5e4tXR4/HzLU+TenVNx/jPrK8I8Kv80K5PPN5mL17KX6fPsG1xGKqqMvCjUcxduozhA0OLxU745lvSdXr2rw4nMTWFkPc+ooK3Nz1fag/A8In/pkpFX/74dQ1nYy4y4MOPqVLRl6YN6puOsXbeHGr4V3lo1yceX1OmTOHgwYOcOXMGVVXp2LEjU6dOZdy4ccVihw0bRmpqKpcvX+bGjRu88MILVK5cmdDQgnEcHBxMQEAAN27c4NSpU3To0IGAgABatWqFRqNh3rx51KhRA2traw4cOED79u05c+YMlSpVetiX/diRO6v3YXtEFIHP1cPN0QF3RwcCG9dnW0TxsovZuUb2RsUQ2rQhTmXKUMHNha71a7H1TEHs9bR0Iq7fILRZI+xtbanh40WbGlXZfqbosebvPUyPhs+gtS/zUK5PPL7WbNnO2/0C8XJ3o6yHO2/3DWTNlm3F4rKys9mwZy/vDwpF6+REFd8KDHilK6u3bAXgUux1/jwdwQevhuJgb0+DmjV4pV0b/mPm1bDE02X1xs0MG9AfLw93ynp6MCy0PytLWMUqKzubDTt3M/K1wWidnfCvWJGBvbqbVry6dC2Wo6dO8dFrQ3DQaHi2di26t3+R1WZeEUs8PcLCwhg7diw+Pj6UK1eOsWPH8uOPPxaLy8zMZMWKFUydOhVXV1cCAgIYMWKEKTY6Opr9+/czbdo0HB0dadKkCSEhIabVsOzs7KhduzbW1taoqoqVlRVGo5FLl8y7LPaTSpLVUtJnG0jUZ+Lv6W7aV7WsBwm6DDIMOUVir6Wmka+q+BWO9fLgYlIKABcTU/B0csBFY19iO8Cfl66RoM+gfe3qD+qSxBMiTacnLjGRWv7+pn11qlcl9kYCuoyMIrEXrl4jLy+fmlX8bsdWq8rZm2u1n425iI+XJ+4ut2vS165Wlci/reU+aNQ4mvTpz6DR4zgTfQEh7iRNp+N6QgK1q1Uz7XsmoDqx8TdI1+uLxF64fAVjXh41q/oXiY28OcYioy/g4+WFu6tL0fYLMUWOE/rBxzTu2pPQDz7mTJR5l8UWT46UlBSuXr1Kgwa3n442bNiQy5cvk5aWViT27NmzGI1G6tWrVyT2xIkTAJw4cQJfX188PT1LbL+lRYsW2Nvb06xZM1q2bEnz5s0fxKU9cSRZLaWs3II5LI5l7Ez7nOzsbrYVXZYtO9eIxtYGK+X2IkyOZezIysk1HavwcUztN4+TnWtk3t7DvN26GYpitoWcxBMqMysLAK2To2mf1tEJAH1m1t9is3HUaLCyuv2/vrOTIxk34zKzsnB2dCzyO9pC7QBLv5jKrsU/sHPRAhrVqc3AUWNJ/tsHuxC33Bo7Wicn0z6ts1ORNlNsVhaODkXHp9bJiYysTFN74eOY2jMzTT+Hz/ySfauWsWfFUhrXe4aQ9z8iOVXGpyhOf/PLkqvr7al2t/5bp9MVi3V2di4yNl1dXU1xer2+yHH+3n7Lvn370Ov1bNq0ifbt2xc5nrgz+SuVksa2YHpvpuF2YqrPybnZZlsk1t7WhqxcI/mFlrLNMOSgsbM1HSvDUDTBzTDkmI6z/MhfNKtaicoebua/EPHEcdBogIIXp25Jzyj4EHZy0Pwt1p6MrCzyC70YqNNn4HgzzkGjQf+3u7HphdoBmtSvi52tLY4aDe/0C8LV2ZnDJ06Z96LEE+PW2EkvNK7SdfoibaZYjYaMzKLjM12vx1HjYGrX6f8+PvU4OjiYfm76bIOC8emgYfiAEFy0zhw6dsy8FyWeCE43v/gUvouampoKgLOzc7FYnU5XZGympqaa4pycnIrdjS3cXpitrS0dO3Zk165drFy50jwX84STZLWUnOzL4OnkwIXEZNO+CwnJeDo5FrtLWsHVBStF4VKhx/oXEpLxu5l8+nm6kajPID0r29QenZhsSk6PXYll65koQsJWEBK2gsi4BBYf/JPpW/Y8yEsUjykXZyd8PD2JKPQ4/sz5C5Tz8ix2l9TftwLW1lacjbk9T+pM9AUC/PwAqFHFj+sJiaSkpxdqj6bGXV6mUhQFCn0xE6IwF2dnynl5FXkcfzrqPOXLli12l9S/UkVsrK2LPNY/HXXe9LJUzar+XE+4QUqhpKBwe0msFCsZnqJEbm5u+Pr6cqzQl5m//vqLihUr4lJoKhRAjRo1sLGx4eTJk0Vi69YtePG0Xr16XLlyhaSkpBLbS2I0GomKKv7eiyhOktX70K5WdVb+fpyUjExSMjJZ+cfxEueU2tva0KJ6FRYf/JMMQw6xqemsO3HGFFvORUutcmVZfOhPsnONnItPYNfZaF682T6lWwfmBHdjVmBXZgV2pVpZD3o3qsubrZo+1OsVj4+e7dsxZ/lKEpJTSEhOYW74SnrffHu6MI29PZ1btuCrhYvRZWRw8Vosi9auo8/N2Mrly/Fs7Vp8+dNisrKzOR55jl937KLXSy8CEHXxEqejzmPMyyPbYOD7FatJTk3j+XrPPNTrFY+XXp06MHvxUhKSkklISmb24qUEvtyxWJzG3p7ObVvz5YIfSdfriblylZ/W/Ezgy50AqFyhPA3r1GH6/B/Jys7m2JlIftmyjT6dC451LuYip86ew2gsGJ9zly4nKTWFJg3qFTuXEACDBg1i8uTJxMXFERcXx5QpUxgyZEixOAcHBwIDAxkzZgxpaWlERUUxc+ZMU2zVqlVp3rw5o0ePJjMzkyNHjrBkyRIGDx4MwJEjR9i9ezcGg4GcnByWLFnCrl27aNeu3UO93seVlK66D0GN66PLNvDm8rUAtA7wp0/jgg/B8eu2Uae8t+nnN1o1Yc6ugwxauAo7Gxs6161pKlsFMLJ9S2btPED/H1fgbG/HoOaNTWWrtIVevAKwsbJCY2eLk1QFEHfwdr8gUnU6Xhr6JgBd27TmzeA+AAweM57Gz9Qx/Tzu7TcYO2sOLfoNooydHf27djaVrQL4etRIxnw9iyZ9+uPi7MxHgweZylYlpaYxfvZ3xCUkYmdrS+1qVflp2iQ8XKW8mrizYQNCSElL54WQQQB0e7Edb/XvB8DAkZ/wXL26vB1S8PPEd4cxZsbXNO8ZhH2ZMoT26GYqWwUwa/wYPvniSxp17YmrszOfvPmaqWxVUkoKY7+axfWEG9jZ2lInoDqLv/wCTzeZUiVKNnbsWJKSkqhVqxYA/fr1Y/To0QB07NiRFi1amH6ePXs2r7/+Or6+vmg0Gt555x1T2SqA8PBwhgwZgpeXF+7u7nzxxRe0atUKgJycHN577z3Onz+PtbU1AQEBhIeHywtWpaSo/+D5iKIoDcu5OO+cH9LT5d7RQtybqqp0nbMIVVXN9maZpkyZmSNC+w0f0ruHuQ4pnjLNg0N1CckpjVRVfaDP7BRFec6/UsVtO5YulM9UUaIVGzYybe788DSdru+DPpenp+efq1evfrZNmzYP+lTiCZSeno6Xl5fBYDDY3zv67mQagBBCCCGEsFiSrAqL8iDeg1Dl9R/xD5nzTn8pzvWwTiUeQwXD4+GNERmP4n9lzrHzT5NVfUZOrsx7FWajyzZgY2VlMOcxc3JzU9N0uvx7RwpRnKqqZGZl2wD6ewb/c3p9Rqb1QziPeEylpqerObnG5HtHmkV6SkrKvaOEKEFycjK2trZZ9468t3+arJ435BpzCpdoEuKf+P3iFextbQ6Y85iqqu76be9/MwrXxxOitI5FnEVRlGQg7iGc7pwuIyPv/EVZglEUp6oqG3fu1mcbDMXXUn4AUlJS1v/8889mSTbE02f9+vWqjY3NbnMc6x8lq6qq5quqOnnC+m2Zx67EkifJgPgfZefmsvvsBebtPZylN+RMMvPh/5uUmhb1wedfGmKuXpPHWqJUcnJz2fP7H7w5cUpmTm7uOPUhDBxVVfOAKQNGfpK5/+ifGI15D/qU4jGgqiqXY2MZPf2r3ItXr10HNj+M8+bn5y9du3ZtxsSJE/Pj4h7GdzXxJNDpdCxcuJBRo0ZlpaWlTTPHMf9RNYBbbKytXrW3sf0oMyenupWVkg+yRKi4HyqqiuJgZ/u73pDzqaqqO8x9BkVRnB3s7afnq2pgTm6u1kpR5JuVuKu8/HwrZ0eHiIzMrKnGvLzlD/PctjY2Qxw09iN1GZnVra2s8pBll59q+fn5VrY2Nhk21tY/Z2RlfaCqatK9f8s8FEWpotVqv8rOzn4pLy/P1srKSr7tiztSVRVVVRWtVnsgJSVllKqq+81xXLMkq6aDKYo1IMVAxf8iW1XVh5JAKopSBpB5geJeDDfvdD4yiqLYAHb3DBRPunxVVbPvHfbgKIqiAPbI3Shxb1nmfhJl1mRVCCGEEEIIc5LSVUIIIYQQwmJJsiqEEEIIISyWJKtCCCGEEMJiSbIqhBBCCCEsliSrQgghhBDCYkmyKoQQQgghLJYkq0IIIYQQwmJJsiqEEEIIISyWJKtCCCGEEMJiSbIqhBBCCCEsliSrQgghhBDCYkmyKoQQQgghLJYkq0IIIYQQwmJJsiqEEEIIISyWJKtCCCGEEMJiSbIqhBBCCCEsliSrQgghhBDCYkmyKoQQQgghLJYkq0IIIYQQwmJJsiqEEEIIISyWJKtCCCGEEMJiSbIqhBBCCCEsliSrQgghhBDCYkmyKoQQQgghLJYkq0IIIYQQwmJJsiqEEEIIISyWJKtCCCGEEMJiSbIqhBBCCCEsliSrQgghhBDCYkmyKoQQQgghLJYkq0IIIYQQwmJJsiqEEEIIISyWJKtCCCGEEMJiSbIqhBBCCCEsliSrQgghhBDCYkmyKoQQQgghLJYkq0IIIYQQwmL9PzN3/FtqAoOcAAAAAElFTkSuQmCC\n",
+      "text/plain": [
+       "<Figure size 864x576 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12, 8))\n",
+    "ca.plot_heterogeneity_tree(\n",
+    "    x_test, \"MonthlyIncome/1K\", max_depth=2, min_impurity_decrease=1e-8\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This shallow tree interpreter gives us a clear guidance on what we should target on. Employees with years of total working experience less than 1.5 have siginificant negative effect on monthly income, that means increase income will definitely reduce the rate of attrition for them. On the other side, employees who have already worked for this company in a long time and are relatively happy with the work life balance here might be less responsive to the income raise, salary might not be an important driver if they decide to leave."
+   ]
+  }
+ ],
+ "metadata": {
+  "authors": [
+   {
+    "name": "mesameki"
+   }
+  ],
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

From da1c5bb40841d117255201d7e010a77ec32bc173 Mon Sep 17 00:00:00 2001
From: Maggie Hei <mehei@microsoft.com>
Date: Fri, 14 May 2021 18:04:04 -0400
Subject: [PATCH 2/2] Update notebooks/Solutions/Causal Interpretation for
 Employee Attrition Dataset.ipynb

Co-authored-by: Keith Battocchi <kebatt@microsoft.com>
---
 .../Causal Interpretation for Employee Attrition Dataset.ipynb  | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb b/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb
index 8afa84af6..498565ac2 100644
--- a/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb	
+++ b/notebooks/Solutions/Causal Interpretation for Employee Attrition Dataset.ipynb	
@@ -8,7 +8,7 @@
     "\n",
     "This notebook uses the popular kaggle Employee Attrition dataset to showcase how we could interpret a blackbox model from both the correlation and causation perspective, leveraging the power of model interpretation tools like [SHAP](https://shap.readthedocs.io/en/latest/index.html) and [EconML](https://aka.ms/econml). We start with a fine-tuned ML model and learn the top important features to predict employee attrition, it will help us to better understand the correlations between features and target and which features are the strongest predictors. In addition, this notebook will take a step further and focus more on figuring out which features cause the employees leave the company, instead of just predicting how likely they are going to leave. This extra causal interpretation could better help company to make corresponding changes in order to minimize the attrition rate.  \n",
     "\n",
-    "It includes the following sessions:\n",
+    "It includes the following sections:\n",
     "1. [Train a Fine-tuned ML Model](#Train-a-Fine-tuned-ML-Model)\n",
     "2. [Correlation Interpretation](#Correlation-Interpretation)\n",
     "    * Feature Importance -- Learn the top predictors for a given ML model\n",