From a33bc33a9981a8f1185780540ce320b200d237b1 Mon Sep 17 00:00:00 2001
From: "lea.douchet_ird.fr" <ldouchet@hotmail.fr>
Date: Thu, 1 Dec 2022 17:13:30 +0700
Subject: [PATCH] R tips
---
01-introduction.html | 748 ++++++++++++++++++
01-introduction.qmd | 14 +
07-basic_statistics.qmd | 6 +-
public/01-introduction.html | 296 +++----
public/07-basic_statistics.html | 45 +-
.../figure-html/LocalMoransI_plt-1.png | Bin 44374 -> 44241 bytes
.../figure-html/MoransI-1.png | Bin 18621 -> 17179 bytes
.../figure-html/conclusion-1.png | Bin 47267 -> 46895 bytes
.../figure-html/kd_test-1.png | Bin 15730 -> 15703 bytes
public/search.json | 4 +-
10 files changed, 956 insertions(+), 157 deletions(-)
create mode 100644 01-introduction.html
diff --git a/01-introduction.html b/01-introduction.html
new file mode 100644
index 0000000..fb06b55
--- /dev/null
+++ b/01-introduction.html
@@ -0,0 +1,748 @@
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
+
+<head>
+
+<meta charset="utf-8" />
+<meta name="generator" content="quarto-1.1.189" />
+
+<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
+
+
+<title>Mapping and spatial analyses in R for One Health studies – 1 Introduction</title>
+<style>
+code{white-space: pre-wrap;}
+span.smallcaps{font-variant: small-caps;}
+div.columns{display: flex; gap: min(4vw, 1.5em);}
+div.column{flex: auto; overflow-x: auto;}
+div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
+ul.task-list{list-style: none;}
+ul.task-list li input[type="checkbox"] {
+ width: 0.8em;
+ margin: 0 0.8em 0.2em -1.6em;
+ vertical-align: middle;
+}
+pre > code.sourceCode { white-space: pre; position: relative; }
+pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
+pre > code.sourceCode > span:empty { height: 1.2em; }
+.sourceCode { overflow: visible; }
+code.sourceCode > span { color: inherit; text-decoration: inherit; }
+div.sourceCode { margin: 1em 0; }
+pre.sourceCode { margin: 0; }
+@media screen {
+div.sourceCode { overflow: auto; }
+}
+@media print {
+pre > code.sourceCode { white-space: pre-wrap; }
+pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
+}
+pre.numberSource code
+ { counter-reset: source-line 0; }
+pre.numberSource code > span
+ { position: relative; left: -4em; counter-increment: source-line; }
+pre.numberSource code > span > a:first-child::before
+ { content: counter(source-line);
+ position: relative; left: -1em; text-align: right; vertical-align: baseline;
+ border: none; display: inline-block;
+ -webkit-touch-callout: none; -webkit-user-select: none;
+ -khtml-user-select: none; -moz-user-select: none;
+ -ms-user-select: none; user-select: none;
+ padding: 0 4px; width: 4em;
+ color: #aaaaaa;
+ }
+pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; }
+div.sourceCode
+ { }
+@media screen {
+pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
+}
+code span.al { color: #ff0000; font-weight: bold; } /* Alert */
+code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */
+code span.at { color: #7d9029; } /* Attribute */
+code span.bn { color: #40a070; } /* BaseN */
+code span.bu { color: #008000; } /* BuiltIn */
+code span.cf { color: #007020; font-weight: bold; } /* ControlFlow */
+code span.ch { color: #4070a0; } /* Char */
+code span.cn { color: #880000; } /* Constant */
+code span.co { color: #60a0b0; font-style: italic; } /* Comment */
+code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */
+code span.do { color: #ba2121; font-style: italic; } /* Documentation */
+code span.dt { color: #902000; } /* DataType */
+code span.dv { color: #40a070; } /* DecVal */
+code span.er { color: #ff0000; font-weight: bold; } /* Error */
+code span.ex { } /* Extension */
+code span.fl { color: #40a070; } /* Float */
+code span.fu { color: #06287e; } /* Function */
+code span.im { color: #008000; font-weight: bold; } /* Import */
+code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */
+code span.kw { color: #007020; font-weight: bold; } /* Keyword */
+code span.op { color: #666666; } /* Operator */
+code span.ot { color: #007020; } /* Other */
+code span.pp { color: #bc7a00; } /* Preprocessor */
+code span.sc { color: #4070a0; } /* SpecialChar */
+code span.ss { color: #bb6688; } /* SpecialString */
+code span.st { color: #4070a0; } /* String */
+code span.va { color: #19177c; } /* Variable */
+code span.vs { color: #4070a0; } /* VerbatimString */
+code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */
+div.csl-bib-body { }
+div.csl-entry {
+ clear: both;
+}
+.hanging div.csl-entry {
+ margin-left:2em;
+ text-indent:-2em;
+}
+div.csl-left-margin {
+ min-width:2em;
+ float:left;
+}
+div.csl-right-inline {
+ margin-left:2em;
+ padding-left:1em;
+}
+div.csl-indent {
+ margin-left: 2em;
+}
+</style>
+
+<!-- htmldependencies:E3FAD763 -->
+<script id="quarto-search-options" type="application/json">{
+ "location": "sidebar",
+ "copy-button": false,
+ "collapse-after": 3,
+ "panel-placement": "start",
+ "type": "textbox",
+ "limit": 20,
+ "language": {
+ "search-no-results-text": "No results",
+ "search-matching-documents-text": "matching documents",
+ "search-copy-link-title": "Copy link to search",
+ "search-hide-matches-text": "Hide additional matches",
+ "search-more-match-text": "more match in this document",
+ "search-more-matches-text": "more matches in this document",
+ "search-clear-button-title": "Clear",
+ "search-detached-cancel-button-title": "Cancel",
+ "search-submit-button-title": "Submit"
+ }
+}</script>
+<style>html{ scroll-behavior: smooth; }</style>
+
+
+<link rel="stylesheet" href="styles.css" />
+</head>
+
+<body>
+
+<div id="quarto-search-results"></div>
+ <header id="quarto-header" class="headroom fixed-top">
+ <nav class="quarto-secondary-nav"
+ data-bs-toggle="collapse" data-bs-target="#quarto-sidebar"
+ aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation"
+ onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }"
+ >
+ <div class="container-fluid d-flex justify-content-between">
+ <h1 class="quarto-secondary-nav-title"></h1>
+ <button type="button"
+ class="quarto-btn-toggle btn" aria-label="Show secondary navigation">
+ <i class="bi bi-chevron-right"></i>
+ </button>
+ </div>
+ </nav>
+</header>
+<!-- content -->
+<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article">
+<!-- sidebar -->
+ <nav id="quarto-sidebar" class="sidebar collapse sidebar-navigation floating overflow-auto">
+ <div class="pt-lg-2 mt-2 text-left sidebar-header">
+ <div class="sidebar-title mb-0 py-0">
+ <a href="/">
+ Mapping and spatial analyses in R for One Health studies
+ </a>
+ <div class="sidebar-tools-main">
+ <a href="https://forge.ird.fr/espace-dev/personnels/longour/geohealth/documentation/rspatial-for-onehealth" title="Source Code" class="sidebar-tool px-1"><i class="bi bi-git"></i></a>
+</div>
+ </div>
+ </div>
+ <div class="mt-2 flex-shrink-0 align-items-center">
+ <div class="sidebar-search">
+ <div id="quarto-search" class="" title="Search"></div>
+ </div>
+ </div>
+ <div class="sidebar-menu-container">
+ <ul class="list-unstyled mt-1">
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/index.html" class="sidebar-item-text sidebar-link">Preface</a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/01-introduction.html" class="sidebar-item-text sidebar-link active"><span class='chapter-number'>1</span>Â <span class='chapter-title'>Introduction</span></a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/02-data_acquisition.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>2</span>Â <span class='chapter-title'>Data Acquisition</span></a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/03-vector_data.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>3</span>Â <span class='chapter-title'>Using vector data</span></a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/04-raster_data.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>4</span>Â <span class='chapter-title'>Using raster data</span></a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/05-mapping_with_r.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>5</span>Â <span class='chapter-title'>Mapping With R</span></a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/07-basic_statistics.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>6</span>Â <span class='chapter-title'>Basic statistics for spatial analysis</span></a>
+ </div>
+</li>
+ <li class="sidebar-item">
+ <div class="sidebar-item-container">
+ <a href="/references.html" class="sidebar-item-text sidebar-link">References</a>
+ </div>
+</li>
+ </ul>
+ </div>
+</nav>
+<!-- margin-sidebar -->
+ <div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
+ <div id="quarto-toc-target"></div>
+ </div>
+<!-- main -->
+<main class="content" id="quarto-document-content">
+
+<header id="title-block-header" class="quarto-title-block default">
+<div class="quarto-title">
+<h1 class="title"><span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></h1>
+</div>
+
+
+
+<div class="quarto-title-meta">
+
+
+
+ </div>
+
+
+</header>
+<nav id="TOC" role="doc-toc">
+ <h2 id="toc-title">Table of contents</h2>
+
+ <ul>
+ <li><a href="#use-of-r" id="toc-use-of-r"><span class="toc-section-number">1.1</span> <span class="header-section-number">1.1</span> Use of R</a>
+ <ul>
+ <li><a href="#installation" id="toc-installation"><span class="toc-section-number">1.1.1</span> <span class="header-section-number">1.1.1</span> Installation</a>
+ <ul>
+ <li><a href="#r" id="toc-r"><span class="toc-section-number">1.1.1.1</span> <span class="header-section-number">1.1.1.1</span> R</a></li>
+ <li><a href="#rstudio" id="toc-rstudio"><span class="toc-section-number">1.1.1.2</span> <span class="header-section-number">1.1.1.2</span> RStudio</a></li>
+ </ul></li>
+ <li><a href="#help" id="toc-help"><span class="toc-section-number">1.1.2</span> <span class="header-section-number">1.1.2</span> Help</a></li>
+ <li><a href="#functions" id="toc-functions"><span class="toc-section-number">1.1.3</span> <span class="header-section-number">1.1.3</span> Functions</a></li>
+ </ul></li>
+ <li><a href="#spatial-in-r-history-and-evolutions" id="toc-spatial-in-r-history-and-evolutions"><span class="toc-section-number">1.2</span> <span class="header-section-number">1.2</span> Spatial in R : History and evolutions</a></li>
+ <li><a href="#the-package-sf" id="toc-the-package-sf"><span class="toc-section-number">1.3</span> <span class="header-section-number">1.3</span> The package <code>sf</code></a>
+ <ul>
+ <li><a href="#format-of-spatial-objects-sf" id="toc-format-of-spatial-objects-sf"><span class="toc-section-number">1.3.1</span> <span class="header-section-number">1.3.1</span> Format of spatial objects <code>sf</code></a></li>
+ </ul></li>
+ <li><a href="#package-mapsf" id="toc-package-mapsf"><span class="toc-section-number">1.4</span> <span class="header-section-number">1.4</span> Package <code>mapsf</code></a></li>
+ <li><a href="#the-package-terra" id="toc-the-package-terra"><span class="toc-section-number">1.5</span> <span class="header-section-number">1.5</span> The package <code>terra</code></a></li>
+ </ul>
+</nav>
+<section id="use-of-r" class="level2" data-number="1.1">
+<h2 data-number="1.1"><span class="header-section-number">1.1</span> Use of R</h2>
+<div class="callout-importan callout callout-style-default no-icon callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class='callout-icon no-icon'></i>
+</div>
+<div class="callout-caption-container flex-fill">
+REMINDER : R TIPS
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<ol type="1">
+<li><p>Comment your code ! (<code># important informations on the code</code>)</p></li>
+<li><p>Check your R objects ! (<code>plot()</code>, <code>print()</code>, <code>View()</code> , …)</p></li>
+<li><p>Listen to R outputs ! (Errors AND Warnings)</p></li>
+<li><p>Get help ! (<code>?name_of_function</code>, internet, others users)</p></li>
+<li><p>Keep calm and take a break !</p></li>
+</ol>
+</div>
+</div>
+<section id="installation" class="level3" data-number="1.1.1">
+<h3 data-number="1.1.1"><span class="header-section-number">1.1.1</span> Installation</h3>
+<div class="callout-note callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class='callout-icon'></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Note
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>The installation part is based on “<a href="https://intro2r.com/">An Introduction to R</a>†book writed by <em>Alex Douglas, Deon Roos, Francesca Mancini, Ana Couto & David Lusseau</em></p>
+</div>
+</div>
+<section id="r" class="level4" data-number="1.1.1.1">
+<h4 data-number="1.1.1.1"><span class="header-section-number">1.1.1.1</span> R</h4>
+<section id="windows-users" class="level5" data-number="1.1.1.1.1">
+<h5 data-number="1.1.1.1.1"><span class="header-section-number">1.1.1.1.1</span> Windows users</h5>
+<p>For Windows users select the ‘<a href="(https://cran.r-project.org/bin/windows/)">Download R for Windows</a>’ link and then click on the ‘base’ link and finally the download link ‘Download R 4.2.1 for Windows’. This will begin the download of the ‘.exe’ installation file. When the download has completed double click on the R executable file and follow the on-screen instructions. Full installation instructions can be found at the <a href="https://cran.r-project.org/bin/windows/">CRAN website</a>.</p>
+</section>
+<section id="mac-users" class="level5" data-number="1.1.1.1.2">
+<h5 data-number="1.1.1.1.2"><span class="header-section-number">1.1.1.1.2</span> Mac users</h5>
+<p>For Mac users select the ‘<a href="https://cran.r-project.org/bin/macosx/">Download R for (Mac) OS X</a>’ link. The binary can be downloaded by selecting the ‘R-4.2.1.pkg’. Once downloaded, double click on the file icon and follow the on-screen instructions to guide you through the necessary steps. See the ‘<a href="https://cran.r-project.org/bin/macosx/RMacOSX-FAQ.html">R for Mac OS X FAQ</a>’ for further information on installation.</p>
+</section>
+<section id="linux-users" class="level5" data-number="1.1.1.1.3">
+<h5 data-number="1.1.1.1.3"><span class="header-section-number">1.1.1.1.3</span> Linux users</h5>
+<p>For Linux users, the installation method will depend on which flavour of Linux you are using. There are reasonably comprehensive instruction <a href="https://cran.r-project.org/bin/linux/">here</a> for Debian, Redhat, Suse and Ubuntu. In most cases you can just use your OS package manager to install R from the official repository. On Ubuntu fire up a shell (Terminal) and use (you will need root permission to do this):</p>
+<div class="cell">
+<div class="sourceCode" id="cb1"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt update</span>
+<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install r-base r-base-dev</span></code></pre></div>
+</div>
+<p>which will install base R and also the development version of base R (you only need this if you want to compile R packages from source but it doesn’t hurt to have it).</p>
+<p>If you receive an error after running the code above you may need to add a ‘source.list’ entry to your etc/apt/sources.list file. To do this open the terminal and enter this:</p>
+<div class="cell">
+<div class="sourceCode" id="cb2"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install <span class="at">-y</span> <span class="at">--no-install-recommends</span> software-properties-common dirmngr</span>
+<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="co"># Add keys</span></span>
+<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="fu">wget</span> <span class="at">-qO-</span> https://cloud.r-project.org/bin/linux/ubuntu/marutter_pubkey.asc <span class="kw">|</span> <span class="fu">sudo</span> tee <span class="at">-a</span> /etc/apt/trusted.gpg.d/cran_ubuntu_key.asc</span>
+<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> add-apt-repository <span class="st">"deb https://cloud.r-project.org/bin/linux/ubuntu </span><span class="va">$(</span><span class="ex">lsb_release</span> <span class="at">-cs</span><span class="va">)</span><span class="st">-cran40/"</span></span></code></pre></div>
+</div>
+<p>Once you have done this then re-run the apt commands above and you should be good to go.</p>
+<p>Install the following packages to allow for future spatial data analysis:</p>
+<div class="cell">
+<div class="sourceCode" id="cb3"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install <span class="at">-y</span> libgdal-dev libproj-dev libgeos-dev libudunits2-dev libv8-dev libnode-dev libcairo2-dev libnetcdf-dev</span></code></pre></div>
+</div>
+</section>
+</section>
+<section id="rstudio" class="level4" data-number="1.1.1.2">
+<h4 data-number="1.1.1.2"><span class="header-section-number">1.1.1.2</span> RStudio</h4>
+<p>Whilst its eminently possible to just use the base installation of R (many people do), we will be using a popular Integrated Development Environment (IDE) called RStudio. RStudio can be thought of as an add-on to R which provides a more user-friendly interface, incorporating the R Console, a script editor and other useful functionality (like R markdown and Git Hub integration). You can find more information about RStudio <a href="https://rstudio.com/">here</a>.</p>
+<p>RStudio is freely available for Windows, Mac and Linux operating systems and can be downloaded from the <a href="https://rstudio.com/products/rstudio/download">RStudio site</a>. You should select the ‘RStudio Desktop’ version. Note: you must install R before you install RStudio.</p>
+<section id="windows-and-mac-users" class="level5" data-number="1.1.1.2.1">
+<h5 data-number="1.1.1.2.1"><span class="header-section-number">1.1.1.2.1</span> Windows and Mac users</h5>
+<p>For Windows and Mac users you should be presented with the appropriate link for downloading. Click on this link and once downloaded run the installer and follow the instructions. If you don’t see the link then scroll down to the ‘All Installers’ section and choose the link manually.</p>
+</section>
+<section id="linux-users-1" class="level5" data-number="1.1.1.2.2">
+<h5 data-number="1.1.1.2.2"><span class="header-section-number">1.1.1.2.2</span> Linux users</h5>
+<p>For Linux users scroll down to the ‘All Installers’ section and choose the appropriate link to download the binary for your Linux operating system. RStudio for Ubuntu (and Debian) is available as a <code>*.deb</code> package.</p>
+<p>To install the <code>*.deb</code> file navigate to where you downloaded the file and then enter the following command with root permission</p>
+<div class="cell">
+<div class="sourceCode" id="cb4"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install ./rstudio-2022.07.2-576-amd64.deb</span></code></pre></div>
+</div>
+<p>You can then start RStudio from the Console by simply typing</p>
+<div class="cell">
+<div class="sourceCode" id="cb5"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="ex">rstudio</span></span></code></pre></div>
+</div>
+<p>or you can create a shortcut on you Desktop for easy startup.</p>
+</section>
+</section>
+</section>
+<section id="help" class="level3" data-number="1.1.2">
+<h3 data-number="1.1.2"><span class="header-section-number">1.1.2</span> Help</h3>
+<p>The R help is very useful for the use of functions.</p>
+<div class="cell">
+<div class="sourceCode" id="cb6"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>?plot <span class="co">#displays the help page for the plot function</span></span>
+<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="fu">help</span>(<span class="st">"*"</span>) <span class="co">#for unconventional characters</span></span></code></pre></div>
+</div>
+<p>Calling the help opens a page (the exact behavior depends on the operating system) with information and usage examples about the documented function(s) or operators.</p>
+</section>
+<section id="functions" class="level3" data-number="1.1.3">
+<h3 data-number="1.1.3"><span class="header-section-number">1.1.3</span> Functions</h3>
+<p>The basic syntax is:</p>
+<div class="cell">
+<div class="sourceCode" id="cb7"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>afunction <span class="ot"><-</span> <span class="cf">function</span>(arg1, arg2){</span>
+<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a> arg1 <span class="sc">+</span> arg2</span>
+<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a>}</span>
+<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a><span class="fu">afunction</span>(<span class="dv">10</span>, <span class="dv">5</span>)</span></code></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre><code>[1] 15</code></pre>
+</div>
+</div>
+</section>
+</section>
+<section id="spatial-in-r-history-and-evolutions" class="level2" data-number="1.2">
+<h2 data-number="1.2"><span class="header-section-number">1.2</span> Spatial in R : History and evolutions</h2>
+<p>Historically, 4 packages make it possible to import, manipulate and transform spatial data:</p>
+<ul>
+<li>The package <code>rgdal</code> <span class="citation" data-cites="rgdal">(<a href="#ref-rgdal" role="doc-biblioref">Bivand, Keitt, and Rowlingson 2022</a>)</span> which is an interface between R and the <a href="http://www.gdal.org/">GDAL</a> <span class="citation" data-cites="GDAL">(<a href="#ref-GDAL" role="doc-biblioref">GDAL/OGR contributors, n.d.</a>)</span> and <a href="https://proj.org/">PROJ</a> <span class="citation" data-cites="PROJ">(<a href="#ref-PROJ" role="doc-biblioref">PROJ contributors 2021</a>)</span> libraries allow you to import and export spatial data (shapefiles for example) and also to manage cartographic projections<br />
+</li>
+<li>The package <code>sp</code> <span class="citation" data-cites="sp">(<a href="#ref-sp" role="doc-biblioref">E. J. Pebesma and Bivand 2005</a>)</span> provides class and methods for vector spatial data in R. It allows displaying background maps, inspectiong an attribute table etc.<br />
+</li>
+<li>The package <code>rgeos</code> <span class="citation" data-cites="rgeos">(<a href="#ref-rgeos" role="doc-biblioref">Bivand and Rundel 2021</a>)</span> gives access to the <a href="http://trac.osgeo.org/geos/">GEOS</a> spatial operations library and therefore makes classic GIS operations available: calculation of surfaces or perimeters, calculation of distances, spatial aggregations, buffer zones, intersections, etc.<br />
+</li>
+<li>The package <code>raster</code> <span class="citation" data-cites="raster">(<a href="#ref-raster" role="doc-biblioref">Hijmans 2022a</a>)</span> is dedicated to the import, manipulation and modeling of raster data.</li>
+</ul>
+<p>Today, the main developments concerning vector data have moved away from the old 3 (<code>sp</code>, <code>rgdal</code>, <code>rgeos</code>) to rely mainly on the package <code>sf</code> (<span class="citation" data-cites="sf">(<a href="#ref-sf" role="doc-biblioref">E. Pebesma 2018a</a>)</span>, <span class="citation" data-cites="pebesma2018">(<a href="#ref-pebesma2018" role="doc-biblioref">E. Pebesma 2018b</a>)</span>). In this manual we will rely exclusively on this package to manipulate vector data.</p>
+<p>The packages <code>stars</code> <span class="citation" data-cites="stars">(<a href="#ref-stars" role="doc-biblioref">E. Pebesma 2021</a>)</span> and <code>terra</code> <span class="citation" data-cites="terra">(<a href="#ref-terra" role="doc-biblioref">Hijmans 2022b</a>)</span> come to replace the package <code>raster</code> for processing raster data. We have chosen to use the package here <code>terra</code> for its proximity to the <code>raster</code>.</p>
+</section>
+<section id="the-package-sf" class="level2" data-number="1.3">
+<h2 data-number="1.3"><span class="header-section-number">1.3</span> The package <code>sf</code></h2>
+<p><img src="img/sf.gif" align="right" width="150"/> The package <code>sf</code> was released in late 2016 by Edzer Pebesma (also author of <code>sp</code>). Its goal is to combine the feature of <code>sp</code>, <code>rgeos</code> and <code>rgdal</code> in a single, more ergonomic package. This package offers simple objects (following the <a href="https://en.wikipedia.org/wiki/Simple_Features"><em>simple feature</em></a> standard) which are easier to manipulate. Particular attention has been paid to the compatibility of the package with the <em>pipe</em> syntax and the operators of the <code>tidyverse</code>.</p>
+<p><code>sf</code> directly uses the GDAL, GEOS and PROJ libraries.</p>
+<div class="quarto-figure quarto-figure-center">
+<figure>
+<p><img src="img/sf_deps.png" class="img-fluid" width="600" /></p>
+</figure>
+</div>
+<p><a href="https://r-spatial.org/r/2020/03/17/wkt.html">From r-spatial.org</a></p>
+<div class="callout-note callout callout-style-simple no-icon">
+<div class="callout-body d-flex">
+<div class="callout-icon-container">
+<i class='callout-icon no-icon'></i>
+</div>
+<div class="callout-body-container">
+<p>Website of package <code>sf</code> : <a href="https://r-spatial.github.io/sf/">Simple Features for R</a></p>
+</div>
+</div>
+</div>
+<p>Many of the spatial data available on the internet are in shapefile format, which can be opened in the following way</p>
+<div class="cell">
+<div class="sourceCode" id="cb9"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(sf)</span></code></pre></div>
+<div class="cell-output cell-output-stderr">
+<pre><code>Linking to GEOS 3.9.3, GDAL 3.5.2, PROJ 8.2.1; sf_use_s2() is TRUE</code></pre>
+</div>
+<div class="sourceCode" id="cb11"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>district <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/district.shp"</span>)</span></code></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>Reading layer `district' from data source
+ `C:\Users\UNiK\Documents\R_works\IRD\Rspatial\rspatial-for-onehealth\data_cambodia\district.shp'
+ using driver `ESRI Shapefile'
+Simple feature collection with 197 features and 10 fields
+Geometry type: MULTIPOLYGON
+Dimension: XY
+Bounding box: xmin: 211534.7 ymin: 1149105 xmax: 784612.1 ymax: 1625495
+Projected CRS: WGS 84 / UTM zone 48N</code></pre>
+</div>
+</div>
+<div class="callout-important callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class='callout-icon'></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Shapefile format limitations
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>For the multiple limitations of this format (multi-file, limited number of records…) we advise you to prefer another format such as the geopackage <code>*.gpkg</code>. All the good reasons not to use the shapefile are <a href="http://switchfromshapefile.org/">here</a>.</p>
+</div>
+</div>
+<p>A geopackage is a database, to load a layer, you must know its name</p>
+<div class="cell">
+<div class="sourceCode" id="cb13"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">st_layers</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>)</span></code></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>Driver: GPKG
+Available layers:
+ layer_name geometry_type features fields crs_name
+1 country Multi Polygon 1 10 WGS 84 / UTM zone 48N
+2 district Multi Polygon 197 10 WGS 84 / UTM zone 48N
+3 education Multi Polygon 25 19 WGS 84 / UTM zone 48N
+4 hospital Point 956 13 WGS 84 / UTM zone 48N
+5 cases Multi Point 972 2 WGS 84 / UTM zone 48N
+6 road Multi Line String 6 9 WGS 84 / UTM zone 48N</code></pre>
+</div>
+</div>
+<div class="cell">
+<div class="sourceCode" id="cb15"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a>road <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"road"</span>)</span></code></pre></div>
+<div class="cell-output cell-output-stdout">
+<pre class="code-out"><code>Reading layer `road' from data source
+ `C:\Users\UNiK\Documents\R_works\IRD\Rspatial\rspatial-for-onehealth\data_cambodia\cambodia.gpkg'
+ using driver `GPKG'
+Simple feature collection with 6 features and 9 fields
+Geometry type: MULTILINESTRING
+Dimension: XY
+Bounding box: xmin: 212377 ymin: 1152214 xmax: 784654.7 ymax: 1625281
+Projected CRS: WGS 84 / UTM zone 48N</code></pre>
+</div>
+</div>
+<section id="format-of-spatial-objects-sf" class="level3" data-number="1.3.1">
+<h3 data-number="1.3.1"><span class="header-section-number">1.3.1</span> Format of spatial objects <code>sf</code></h3>
+<div class="quarto-figure quarto-figure-center">
+<figure>
+<p><img src="img/sf.png" class="img-fluid" width="600" /></p>
+</figure>
+</div>
+<p>Objects<code>sf</code> are objects in <code>data.frame</code> which one of the columns contains geometries. This column is the class of sfc (<em>simple feature column</em>) and each individual of the column is a sfg <em>(simple feature geometry)</em>. This format is very practical insofa as the data and the geometries are intrinsically linked in the same object.</p>
+<div class="callout-note callout callout-style-simple no-icon">
+<div class="callout-body d-flex">
+<div class="callout-icon-container">
+<i class='callout-icon no-icon'></i>
+</div>
+<div class="callout-body-container">
+<p>Thumbnail describing the simple feature format: <a href="https://r-spatial.github.io/sf/articles/sf1.html">Simple Features for R</a></p>
+</div>
+</div>
+</div>
+<div class="callout-tip callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class='callout-icon'></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Tip
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>A benchmark of vector processing libraries is available <a href="https://github.com/kadyb/vector-benchmark">here</a>.</p>
+</div>
+</div>
+</section>
+</section>
+<section id="package-mapsf" class="level2" data-number="1.4">
+<h2 data-number="1.4"><span class="header-section-number">1.4</span> Package <code>mapsf</code></h2>
+<p>The free R software spatial ecosystem is rich, dynamic and mature and several packages allow to import, process and represent spatial data. The package <a href="https://CRAN.R-project.org/package=maps"><code>mapsf</code></a> <span class="citation" data-cites="mapsf">(<a href="#ref-mapsf" role="doc-biblioref">Giraud 2022</a>)</span> relies on this ecosystem to integrate the creation of quality thematic maps into processing chains with R.</p>
+<p>Other packages can be used to make thematic maps. The package <code>ggplot2</code> <span class="citation" data-cites="ggplot2">(<a href="#ref-ggplot2" role="doc-biblioref">Wickham 2016</a>)</span>, in association with the package <code>ggspatial</code> <span class="citation" data-cites="ggspatial">(<a href="#ref-ggspatial" role="doc-biblioref">Dunnington 2021</a>)</span>, allows for example to display spatial objects and to make simple thematic maps. The package <code>tmap</code> <span class="citation" data-cites="tmap">(<a href="#ref-tmap" role="doc-biblioref">Tennekes 2018</a>)</span> is dedicated to the creation of thematic maps, it uses a syntax close to that of <code>ggplot2</code> (sequence of instructions combined with the ‘+’ sign). Documentation and tutorials for using these two packages are readily available on the web.</p>
+<p>Here, we will mainly use the package <code>mapsf</code> whose functionalities are quite complete and the handling rather simple. In addition, the package is relatively light.</p>
+<p><img src="img/logo_mapsf.png" align="right" width="120"/></p>
+<p><code>mapsf</code> allows you to create most of the types of map usually used in statistical cartography (choropleth maps, typologies, proportional or graduated symbols, etc.). For each type of map, several parameters are used to customize the cartographic representation. These parameters are the same as those found in the usual GIS or cartography software (for example, the choice of discretizations and color palettes, the modification of the size of the symbols or the customization of the legends). Associated with the data representation functions, other functions are dedicated to cartographic dressing (themes or graphic charters, legends, scales, orientation arrows, title, credits, annotations, etc.), the creation of boxes or the exporting maps.<br />
+<code>mapsf</code> is the successor of <a href="http://riatelab.github.io/cartography/docs/"><code>cartography</code></a> <span class="citation" data-cites="cartography">(<a href="#ref-cartography" role="doc-biblioref">Giraud and Lambert 2016</a>)</span>, it offers the same main functionalities while being lighter and more ergonomic.</p>
+<p>To use this package several sources can be consulted:</p>
+<ul>
+<li><p>The package documentation accessible <a href="http://riatelab.github.io/mapsf/">on the internet</a> or directly in R (<code>?mapsf</code>),</p></li>
+<li><p>A <a href="https://raw.githubusercontent.com/riatelab/mapsf/master/vignettes/web_only/img/mapsf_cheatsheet.pdf"><em>cheat sheet</em></a>,</p></li>
+</ul>
+<div class="quarto-figure quarto-figure-center">
+<figure>
+<p><img src="img/mapsf_cheatsheet.png" class="img-fluid" width="600" /></p>
+</figure>
+</div>
+<ul>
+<li><p>The <a href="https://riatelab.github.io/mapsf/articles/">vignettes</a> associated with the package show sample scripts,</p></li>
+<li><p>The <a href="https://rgeomatic.hypotheses.org/">R Geomatics</a> blog which provides resources and examples related to the package and more generally to the R spatial ecosystem.</p></li>
+</ul>
+</section>
+<section id="the-package-terra" class="level2" data-number="1.5">
+<h2 data-number="1.5"><span class="header-section-number">1.5</span> The package <code>terra</code></h2>
+<p><img src="img/logo_terra.png" align="right" width="150"/> The package <code>terra</code> was release in early 2020 by Robert J. Hijmans (also author of <code>raster</code>). Its objective is to propose methods of treatment and analysis of raster data. This package is very similar to the package <code>raster</code>; but it has more features, it’s easier to use, and it’s faster.</p>
+<div class="callout-note callout callout-style-simple no-icon">
+<div class="callout-body d-flex">
+<div class="callout-icon-container">
+<i class='callout-icon no-icon'></i>
+</div>
+<div class="callout-body-container">
+<p>Website of package <code>terra</code> : <a href="https://rspatial.org/terra/">Spatial Data Science with R and “terraâ€</a></p>
+</div>
+</div>
+</div>
+<div class="callout-tip callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class='callout-icon'></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Tip
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>A benchmark of raster processing libraries is available <a href="https://github.com/kadyb/raster-benchmark">here</a>.</p>
+</div>
+</div>
+<div id="quarto-navigation-envelope" class="hidden">
+<p><span class="hidden" data-render-id="quarto-int-sidebar-title">Mapping and spatial analyses in R for One Health studies</span> <span class="hidden" data-render-id="quarto-int-navbar-title">Mapping and spatial analyses in R for One Health studies</span> <span class="hidden" data-render-id="quarto-int-next"><span class="chapter-number">2</span>Â <span class="chapter-title">Data Acquisition</span></span> <span class="hidden" data-render-id="quarto-int-prev">Preface</span> <span class="hidden" data-render-id="quarto-int-sidebar:/index.html">Preface</span> <span class="hidden" data-render-id="quarto-int-sidebar:/01-introduction.html"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/02-data_acquisition.html"><span class="chapter-number">2</span>Â <span class="chapter-title">Data Acquisition</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/03-vector_data.html"><span class="chapter-number">3</span>Â <span class="chapter-title">Using vector data</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/04-raster_data.html"><span class="chapter-number">4</span>Â <span class="chapter-title">Using raster data</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/05-mapping_with_r.html"><span class="chapter-number">5</span>Â <span class="chapter-title">Mapping With R</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/07-basic_statistics.html"><span class="chapter-number">6</span>Â <span class="chapter-title">Basic statistics for spatial analysis</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/references.html">References</span> <span class="hidden" data-render-id="footer-left">UMR 228 ESPACE-DEV</span> <span class="hidden" data-render-id="footer-right"><img src="img/ird_footer.png" height="50" /></span></p>
+</div>
+<div id="quarto-meta-markdown" class="hidden">
+<p><span class="hidden" data-render-id="quarto-metatitle">Mapping and spatial analyses in R for One Health studies - <span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></span> <span class="hidden" data-render-id="quarto-twittercardtitle">Mapping and spatial analyses in R for One Health studies - <span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></span> <span class="hidden" data-render-id="quarto-ogcardtitle">Mapping and spatial analyses in R for One Health studies - <span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></span> <span class="hidden" data-render-id="quarto-metasitename">Mapping and spatial analyses in R for One Health studies</span></p>
+</div>
+<div id="refs" class="references csl-bib-body hanging-indent" role="doc-bibliography">
+<div id="ref-rgdal" class="csl-entry" role="doc-biblioentry">
+Bivand, Roger, Tim Keitt, and Barry Rowlingson. 2022. <span>“Rgdal: Bindings for the ’Geospatial’ Data Abstraction Library.â€</span> <a href="https://CRAN.R-project.org/package=rgdal">https://CRAN.R-project.org/package=rgdal</a>.
+</div>
+<div id="ref-rgeos" class="csl-entry" role="doc-biblioentry">
+Bivand, Roger, and Colin Rundel. 2021. <span>“Rgeos: Interface to Geometry Engine - Open Source (’GEOS’).â€</span> <a href="https://CRAN.R-project.org/package=rgeos">https://CRAN.R-project.org/package=rgeos</a>.
+</div>
+<div id="ref-ggspatial" class="csl-entry" role="doc-biblioentry">
+Dunnington, Dewey. 2021. <span>“Ggspatial: Spatial Data Framework for Ggplot2.â€</span> <a href="https://CRAN.R-project.org/package=ggspatial">https://CRAN.R-project.org/package=ggspatial</a>.
+</div>
+<div id="ref-GDAL" class="csl-entry" role="doc-biblioentry">
+GDAL/OGR contributors. n.d. <em><span>GDAL/OGR</span> Geospatial Data Abstraction Software Library</em>. Open Source Geospatial Foundation. <a href="https://gdal.org">https://gdal.org</a>.
+</div>
+<div id="ref-mapsf" class="csl-entry" role="doc-biblioentry">
+Giraud, Timothée. 2022. <span>“Mapsf: Thematic Cartography.â€</span> <a href="https://CRAN.R-project.org/package=mapsf">https://CRAN.R-project.org/package=mapsf</a>.
+</div>
+<div id="ref-cartography" class="csl-entry" role="doc-biblioentry">
+Giraud, Timothée, and Nicolas Lambert. 2016. <span>“Cartography: Create and Integrate Maps in Your r Workflowâ€</span> 1. <a href="https://doi.org/10.21105/joss.00054">https://doi.org/10.21105/joss.00054</a>.
+</div>
+<div id="ref-raster" class="csl-entry" role="doc-biblioentry">
+Hijmans, Robert J. 2022a. <span>“Raster: Geographic Data Analysis and Modeling.â€</span> <a href="https://CRAN.R-project.org/package=raster">https://CRAN.R-project.org/package=raster</a>.
+</div>
+<div id="ref-terra" class="csl-entry" role="doc-biblioentry">
+———. 2022b. <span>“Terra: Spatial Data Analysis.â€</span> <a href="https://CRAN.R-project.org/package=terra">https://CRAN.R-project.org/package=terra</a>.
+</div>
+<div id="ref-sf" class="csl-entry" role="doc-biblioentry">
+Pebesma, Edzer. 2018a. <span>“<span></span>Simple Features for r: Standardized Support for Spatial Vector Data<span></span>â€</span> 10. <a href="https://doi.org/10.32614/RJ-2018-009">https://doi.org/10.32614/RJ-2018-009</a>.
+</div>
+<div id="ref-pebesma2018" class="csl-entry" role="doc-biblioentry">
+———. 2018b. <span>“Simple Features for R: Standardized Support for Spatial Vector Data.â€</span> <em>The R Journal</em> 10 (1): 439. <a href="https://doi.org/10.32614/rj-2018-009">https://doi.org/10.32614/rj-2018-009</a>.
+</div>
+<div id="ref-stars" class="csl-entry" role="doc-biblioentry">
+———. 2021. <span>“Stars: Spatiotemporal Arrays, Raster and Vector Data Cubes.â€</span> <a href="https://CRAN.R-project.org/package=stars">https://CRAN.R-project.org/package=stars</a>.
+</div>
+<div id="ref-sp" class="csl-entry" role="doc-biblioentry">
+Pebesma, Edzer J., and Roger S. Bivand. 2005. <span>“Classes and Methods for Spatial Data in <span></span>r<span></span>â€</span> 5. <a href="https://CRAN.R-project.org/doc/Rnews/">https://CRAN.R-project.org/doc/Rnews/</a>.
+</div>
+<div id="ref-PROJ" class="csl-entry" role="doc-biblioentry">
+PROJ contributors. 2021. <em><span>PROJ</span> Coordinate Transformation Software Library</em>. Open Source Geospatial Foundation. <a href="https://proj.org/">https://proj.org/</a>.
+</div>
+<div id="ref-tmap" class="csl-entry" role="doc-biblioentry">
+Tennekes, Martijn. 2018. <span>“<span></span>Tmap<span></span>: Thematic Maps in <span></span>r<span></span>â€</span> 84. <a href="https://doi.org/10.18637/jss.v084.i06">https://doi.org/10.18637/jss.v084.i06</a>.
+</div>
+<div id="ref-ggplot2" class="csl-entry" role="doc-biblioentry">
+Wickham, Hadley. 2016. <span>“Ggplot2: Elegant Graphics for Data Analysis.â€</span> <a href="https://ggplot2.tidyverse.org">https://ggplot2.tidyverse.org</a>.
+</div>
+</div>
+</section>
+
+</main> <!-- /main -->
+<script id = "quarto-html-after-body" type="application/javascript">
+window.document.addEventListener("DOMContentLoaded", function (event) {
+ const toggleBodyColorMode = (bsSheetEl) => {
+ const mode = bsSheetEl.getAttribute("data-mode");
+ const bodyEl = window.document.querySelector("body");
+ if (mode === "dark") {
+ bodyEl.classList.add("quarto-dark");
+ bodyEl.classList.remove("quarto-light");
+ } else {
+ bodyEl.classList.add("quarto-light");
+ bodyEl.classList.remove("quarto-dark");
+ }
+ }
+ const toggleBodyColorPrimary = () => {
+ const bsSheetEl = window.document.querySelector("link#quarto-bootstrap");
+ if (bsSheetEl) {
+ toggleBodyColorMode(bsSheetEl);
+ }
+ }
+ toggleBodyColorPrimary();
+ const icon = "";
+ const anchorJS = new window.AnchorJS();
+ anchorJS.options = {
+ placement: 'right',
+ icon: icon
+ };
+ anchorJS.add('.anchored');
+ const clipboard = new window.ClipboardJS('.code-copy-button', {
+ target: function(trigger) {
+ return trigger.previousElementSibling;
+ }
+ });
+ clipboard.on('success', function(e) {
+ // button target
+ const button = e.trigger;
+ // don't keep focus
+ button.blur();
+ // flash "checked"
+ button.classList.add('code-copy-button-checked');
+ var currentTitle = button.getAttribute("title");
+ button.setAttribute("title", "Copied!");
+ setTimeout(function() {
+ button.setAttribute("title", currentTitle);
+ button.classList.remove('code-copy-button-checked');
+ }, 1000);
+ // clear code selection
+ e.clearSelection();
+ });
+ function tippyHover(el, contentFn) {
+ const config = {
+ allowHTML: true,
+ content: contentFn,
+ maxWidth: 500,
+ delay: 100,
+ arrow: false,
+ appendTo: function(el) {
+ return el.parentElement;
+ },
+ interactive: true,
+ interactiveBorder: 10,
+ theme: 'quarto',
+ placement: 'bottom-start'
+ };
+ window.tippy(el, config);
+ }
+ const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
+ for (var i=0; i<noterefs.length; i++) {
+ const ref = noterefs[i];
+ tippyHover(ref, function() {
+ // use id or data attribute instead here
+ let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
+ try { href = new URL(href).hash; } catch {}
+ const id = href.replace(/^#\/?/, "");
+ const note = window.document.getElementById(id);
+ return note.innerHTML;
+ });
+ }
+ var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
+ for (var i=0; i<bibliorefs.length; i++) {
+ const ref = bibliorefs[i];
+ const cites = ref.parentNode.getAttribute('data-cites').split(' ');
+ tippyHover(ref, function() {
+ var popup = window.document.createElement('div');
+ cites.forEach(function(cite) {
+ var citeDiv = window.document.createElement('div');
+ citeDiv.classList.add('hanging-indent');
+ citeDiv.classList.add('csl-entry');
+ var biblioDiv = window.document.getElementById('ref-' + cite);
+ if (biblioDiv) {
+ citeDiv.innerHTML = biblioDiv.innerHTML;
+ }
+ popup.appendChild(citeDiv);
+ });
+ return popup.innerHTML;
+ });
+ }
+ var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
+ var filterRegex = new RegExp('/' + window.location.host + '/');
+ var isInternal = (href) => {
+ return filterRegex.test(href) || localhostRegex.test(href);
+ }
+ // Inspect non-navigation links and adorn them if external
+ var links = window.document.querySelectorAll('a:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external)');
+ for (var i=0; i<links.length; i++) {
+ const link = links[i];
+ if (!isInternal(link.href)) {
+ // target, if specified
+ link.setAttribute("target", "_blank");
+ }
+ }
+});
+</script>
+<nav class="page-navigation">
+ <div class="nav-page nav-page-previous">
+ <a href="/index.html" class="pagination-link">
+ <i class="bi bi-arrow-left-short"></i> <span class="nav-page-text">Preface</span>
+ </a>
+ </div>
+ <div class="nav-page nav-page-next">
+ <a href="/02-data_acquisition.html" class="pagination-link">
+ <span class="nav-page-text"><span class='chapter-number'>2</span>Â <span class='chapter-title'>Data Acquisition</span></span> <i class="bi bi-arrow-right-short"></i>
+ </a>
+ </div>
+</nav>
+</div> <!-- /content -->
+<footer class="footer">
+ <div class="nav-footer">
+ <div class="nav-footer-left">
+ <div class='footer-contents'>UMR 228 ESPACE-DEV</div>
+ </div>
+ <div class="nav-footer-right">
+ <div class='footer-contents'>{height="50"}
+</div>
+ </div>
+ </div>
+</footer>
+
+</body>
+
+</html>
\ No newline at end of file
diff --git a/01-introduction.qmd b/01-introduction.qmd
index 0825536..04abe3b 100644
--- a/01-introduction.qmd
+++ b/01-introduction.qmd
@@ -6,6 +6,20 @@ bibliography: references.bib
## Use of R
+::: callout-importan
+## REMINDER : R TIPS
+
+1. Comment your code ! (`# important informations on the code`)
+
+2. Check your R objects ! (`plot()`, `print()`, `View()` , ...)
+
+3. Listen to R outputs ! (Errors AND Warnings)
+
+4. Get help ! (`?name_of_function`, internet, others users)
+
+5. Keep calm and take a break !
+:::
+
### Installation
::: callout-note
diff --git a/07-basic_statistics.qmd b/07-basic_statistics.qmd
index 7f9a9ab..7f69259 100644
--- a/07-basic_statistics.qmd
+++ b/07-basic_statistics.qmd
@@ -207,6 +207,8 @@ We will compute the Moran's statistics using `spdep`[@spdep] and `Dcluster`[@DCl
library(spdep) # Functions for creating spatial weight, spatial analysis
library(DCluster) # Package with functions for spatial cluster analysis
+set.seed(345) # remove random sampling for reproducibility
+
queen_nb <- poly2nb(district) # Neighbors according to queen case
q_listw <- nb2listw(queen_nb, style = 'W') # row-standardized weights
@@ -502,5 +504,7 @@ mf_layout(title = "Cluster using kulldorf scan statistic")
Both methods identified significant clusters. The two methods could identify a cluster around Phnom Penh after standardization for population counts. However, the identified clusters does not rely on the same assumption. While the Moran's test wonder whether their is any autocorrelation between clusters (i.e. second order effects of infection), the Kulldorff scan statistics wonder whether their is any heterogeneity in the case distribution. None of these test can inform on the infection processes (first or second order) for the studied disease and previous knowledge on the disease will help selecting the most accurate test.
-
+::: callout-tip
+In this example, Cambodia is treated as an island, i.e. there is no data outside of its borders. In reality, some clusters can occurs across country's borders. You should be aware that such district will likely not be detected by these analysis. This border effect is still a hot topic in spatial studies and there is no conventional ways to deal with it. You can find in the literature some suggestion on how to deals with these border effect as assigning weights, or extrapolating data.
+:::
diff --git a/public/01-introduction.html b/public/01-introduction.html
index a129197..fb06b55 100644
--- a/public/01-introduction.html
+++ b/public/01-introduction.html
@@ -1,13 +1,15 @@
<!DOCTYPE html>
-<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
-<meta charset="utf-8">
-<meta name="generator" content="quarto-1.1.251">
+<head>
-<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
+<meta charset="utf-8" />
+<meta name="generator" content="quarto-1.1.189" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
-<title>Mapping and spatial analyses in R for One Health studies - 1 Introduction</title>
+
+<title>Mapping and spatial analyses in R for One Health studies – 1 Introduction</title>
<style>
code{white-space: pre-wrap;}
span.smallcaps{font-variant: small-caps;}
@@ -104,25 +106,7 @@ div.csl-indent {
}
</style>
-
-<script src="site_libs/quarto-nav/quarto-nav.js"></script>
-<script src="site_libs/quarto-nav/headroom.min.js"></script>
-<script src="site_libs/clipboard/clipboard.min.js"></script>
-<script src="site_libs/quarto-search/autocomplete.umd.js"></script>
-<script src="site_libs/quarto-search/fuse.min.js"></script>
-<script src="site_libs/quarto-search/quarto-search.js"></script>
-<meta name="quarto:offset" content="./">
-<link href="./02-data_acquisition.html" rel="next">
-<link href="./index.html" rel="prev">
-<script src="site_libs/quarto-html/quarto.js"></script>
-<script src="site_libs/quarto-html/popper.min.js"></script>
-<script src="site_libs/quarto-html/tippy.umd.min.js"></script>
-<script src="site_libs/quarto-html/anchor.min.js"></script>
-<link href="site_libs/quarto-html/tippy.css" rel="stylesheet">
-<link href="site_libs/quarto-html/quarto-syntax-highlighting.css" rel="stylesheet" id="quarto-text-highlighting-styles">
-<script src="site_libs/bootstrap/bootstrap.min.js"></script>
-<link href="site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
-<link href="site_libs/bootstrap/bootstrap.min.css" rel="stylesheet" id="quarto-bootstrap" data-mode="light">
+<!-- htmldependencies:E3FAD763 -->
<script id="quarto-search-options" type="application/json">{
"location": "sidebar",
"copy-button": false,
@@ -145,17 +129,22 @@ div.csl-indent {
<style>html{ scroll-behavior: smooth; }</style>
-<link rel="stylesheet" href="styles.css">
+<link rel="stylesheet" href="styles.css" />
</head>
-<body class="nav-sidebar floating">
+<body>
<div id="quarto-search-results"></div>
<header id="quarto-header" class="headroom fixed-top">
- <nav class="quarto-secondary-nav" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
+ <nav class="quarto-secondary-nav"
+ data-bs-toggle="collapse" data-bs-target="#quarto-sidebar"
+ aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation"
+ onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }"
+ >
<div class="container-fluid d-flex justify-content-between">
- <h1 class="quarto-secondary-nav-title"><span class="chapter-number">1</span> <span class="chapter-title">Introduction</span></h1>
- <button type="button" class="quarto-btn-toggle btn" aria-label="Show secondary navigation">
+ <h1 class="quarto-secondary-nav-title"></h1>
+ <button type="button"
+ class="quarto-btn-toggle btn" aria-label="Show secondary navigation">
<i class="bi bi-chevron-right"></i>
</button>
</div>
@@ -167,7 +156,9 @@ div.csl-indent {
<nav id="quarto-sidebar" class="sidebar collapse sidebar-navigation floating overflow-auto">
<div class="pt-lg-2 mt-2 text-left sidebar-header">
<div class="sidebar-title mb-0 py-0">
- <a href="./">Mapping and spatial analyses in R for One Health studies</a>
+ <a href="/">
+ Mapping and spatial analyses in R for One Health studies
+ </a>
<div class="sidebar-tools-main">
<a href="https://forge.ird.fr/espace-dev/personnels/longour/geohealth/documentation/rspatial-for-onehealth" title="Source Code" class="sidebar-tool px-1"><i class="bi bi-git"></i></a>
</div>
@@ -182,42 +173,42 @@ div.csl-indent {
<ul class="list-unstyled mt-1">
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./index.html" class="sidebar-item-text sidebar-link">Preface</a>
+ <a href="/index.html" class="sidebar-item-text sidebar-link">Preface</a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./01-introduction.html" class="sidebar-item-text sidebar-link active"><span class="chapter-number">1</span> <span class="chapter-title">Introduction</span></a>
+ <a href="/01-introduction.html" class="sidebar-item-text sidebar-link active"><span class='chapter-number'>1</span>Â <span class='chapter-title'>Introduction</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./02-data_acquisition.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">2</span> <span class="chapter-title">Data Acquisition</span></a>
+ <a href="/02-data_acquisition.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>2</span>Â <span class='chapter-title'>Data Acquisition</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./03-vector_data.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">3</span> <span class="chapter-title">Using vector data</span></a>
+ <a href="/03-vector_data.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>3</span>Â <span class='chapter-title'>Using vector data</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./04-raster_data.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">4</span> <span class="chapter-title">Using raster data</span></a>
+ <a href="/04-raster_data.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>4</span>Â <span class='chapter-title'>Using raster data</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./05-mapping_with_r.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">5</span> <span class="chapter-title">Mapping With R</span></a>
+ <a href="/05-mapping_with_r.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>5</span>Â <span class='chapter-title'>Mapping With R</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./07-basic_statistics.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">6</span> <span class="chapter-title">Basic statistics for spatial analysis</span></a>
+ <a href="/07-basic_statistics.html" class="sidebar-item-text sidebar-link"><span class='chapter-number'>6</span>Â <span class='chapter-title'>Basic statistics for spatial analysis</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
- <a href="./references.html" class="sidebar-item-text sidebar-link">References</a>
+ <a href="/references.html" class="sidebar-item-text sidebar-link">References</a>
</div>
</li>
</ul>
@@ -225,36 +216,14 @@ div.csl-indent {
</nav>
<!-- margin-sidebar -->
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
- <nav id="TOC" role="doc-toc" class="toc-active">
- <h2 id="toc-title">Table of contents</h2>
-
- <ul>
- <li><a href="#use-of-r" id="toc-use-of-r" class="nav-link active" data-scroll-target="#use-of-r"><span class="toc-section-number">1.1</span> Use of R</a>
- <ul>
- <li><a href="#installation" id="toc-installation" class="nav-link" data-scroll-target="#installation"><span class="toc-section-number">1.1.1</span> Installation</a>
- <ul class="collapse">
- <li><a href="#r" id="toc-r" class="nav-link" data-scroll-target="#r"><span class="toc-section-number">1.1.1.1</span> R</a></li>
- <li><a href="#rstudio" id="toc-rstudio" class="nav-link" data-scroll-target="#rstudio"><span class="toc-section-number">1.1.1.2</span> RStudio</a></li>
- </ul></li>
- <li><a href="#help" id="toc-help" class="nav-link" data-scroll-target="#help"><span class="toc-section-number">1.1.2</span> Help</a></li>
- <li><a href="#functions" id="toc-functions" class="nav-link" data-scroll-target="#functions"><span class="toc-section-number">1.1.3</span> Functions</a></li>
- </ul></li>
- <li><a href="#spatial-in-r-history-and-evolutions" id="toc-spatial-in-r-history-and-evolutions" class="nav-link" data-scroll-target="#spatial-in-r-history-and-evolutions"><span class="toc-section-number">1.2</span> Spatial in R : History and evolutions</a></li>
- <li><a href="#the-package-sf" id="toc-the-package-sf" class="nav-link" data-scroll-target="#the-package-sf"><span class="toc-section-number">1.3</span> The package <code>sf</code></a>
- <ul>
- <li><a href="#format-of-spatial-objects-sf" id="toc-format-of-spatial-objects-sf" class="nav-link" data-scroll-target="#format-of-spatial-objects-sf"><span class="toc-section-number">1.3.1</span> Format of spatial objects <code>sf</code></a></li>
- </ul></li>
- <li><a href="#package-mapsf" id="toc-package-mapsf" class="nav-link" data-scroll-target="#package-mapsf"><span class="toc-section-number">1.4</span> Package <code>mapsf</code></a></li>
- <li><a href="#the-package-terra" id="toc-the-package-terra" class="nav-link" data-scroll-target="#the-package-terra"><span class="toc-section-number">1.5</span> The package <code>terra</code></a></li>
- </ul>
-</nav>
+ <div id="quarto-toc-target"></div>
</div>
<!-- main -->
<main class="content" id="quarto-document-content">
<header id="title-block-header" class="quarto-title-block default">
<div class="quarto-title">
-<h1 class="title"><span id="introductionx" class="quarto-section-identifier d-none d-lg-block"><span class="chapter-number">1</span> <span class="chapter-title">Introduction</span></span></h1>
+<h1 class="title"><span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></h1>
</div>
@@ -267,15 +236,56 @@ div.csl-indent {
</header>
-
+<nav id="TOC" role="doc-toc">
+ <h2 id="toc-title">Table of contents</h2>
+
+ <ul>
+ <li><a href="#use-of-r" id="toc-use-of-r"><span class="toc-section-number">1.1</span> <span class="header-section-number">1.1</span> Use of R</a>
+ <ul>
+ <li><a href="#installation" id="toc-installation"><span class="toc-section-number">1.1.1</span> <span class="header-section-number">1.1.1</span> Installation</a>
+ <ul>
+ <li><a href="#r" id="toc-r"><span class="toc-section-number">1.1.1.1</span> <span class="header-section-number">1.1.1.1</span> R</a></li>
+ <li><a href="#rstudio" id="toc-rstudio"><span class="toc-section-number">1.1.1.2</span> <span class="header-section-number">1.1.1.2</span> RStudio</a></li>
+ </ul></li>
+ <li><a href="#help" id="toc-help"><span class="toc-section-number">1.1.2</span> <span class="header-section-number">1.1.2</span> Help</a></li>
+ <li><a href="#functions" id="toc-functions"><span class="toc-section-number">1.1.3</span> <span class="header-section-number">1.1.3</span> Functions</a></li>
+ </ul></li>
+ <li><a href="#spatial-in-r-history-and-evolutions" id="toc-spatial-in-r-history-and-evolutions"><span class="toc-section-number">1.2</span> <span class="header-section-number">1.2</span> Spatial in R : History and evolutions</a></li>
+ <li><a href="#the-package-sf" id="toc-the-package-sf"><span class="toc-section-number">1.3</span> <span class="header-section-number">1.3</span> The package <code>sf</code></a>
+ <ul>
+ <li><a href="#format-of-spatial-objects-sf" id="toc-format-of-spatial-objects-sf"><span class="toc-section-number">1.3.1</span> <span class="header-section-number">1.3.1</span> Format of spatial objects <code>sf</code></a></li>
+ </ul></li>
+ <li><a href="#package-mapsf" id="toc-package-mapsf"><span class="toc-section-number">1.4</span> <span class="header-section-number">1.4</span> Package <code>mapsf</code></a></li>
+ <li><a href="#the-package-terra" id="toc-the-package-terra"><span class="toc-section-number">1.5</span> <span class="header-section-number">1.5</span> The package <code>terra</code></a></li>
+ </ul>
+</nav>
<section id="use-of-r" class="level2" data-number="1.1">
-<h2 data-number="1.1" class="anchored" data-anchor-id="use-of-r"><span class="header-section-number">1.1</span> Use of R</h2>
+<h2 data-number="1.1"><span class="header-section-number">1.1</span> Use of R</h2>
+<div class="callout-importan callout callout-style-default no-icon callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class='callout-icon no-icon'></i>
+</div>
+<div class="callout-caption-container flex-fill">
+REMINDER : R TIPS
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<ol type="1">
+<li><p>Comment your code ! (<code># important informations on the code</code>)</p></li>
+<li><p>Check your R objects ! (<code>plot()</code>, <code>print()</code>, <code>View()</code> , …)</p></li>
+<li><p>Listen to R outputs ! (Errors AND Warnings)</p></li>
+<li><p>Get help ! (<code>?name_of_function</code>, internet, others users)</p></li>
+<li><p>Keep calm and take a break !</p></li>
+</ol>
+</div>
+</div>
<section id="installation" class="level3" data-number="1.1.1">
-<h3 data-number="1.1.1" class="anchored" data-anchor-id="installation"><span class="header-section-number">1.1.1</span> Installation</h3>
+<h3 data-number="1.1.1"><span class="header-section-number">1.1.1</span> Installation</h3>
<div class="callout-note callout callout-style-default callout-captioned">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
-<i class="callout-icon"></i>
+<i class='callout-icon'></i>
</div>
<div class="callout-caption-container flex-fill">
Note
@@ -286,78 +296,78 @@ Note
</div>
</div>
<section id="r" class="level4" data-number="1.1.1.1">
-<h4 data-number="1.1.1.1" class="anchored" data-anchor-id="r"><span class="header-section-number">1.1.1.1</span> R</h4>
+<h4 data-number="1.1.1.1"><span class="header-section-number">1.1.1.1</span> R</h4>
<section id="windows-users" class="level5" data-number="1.1.1.1.1">
-<h5 data-number="1.1.1.1.1" class="anchored" data-anchor-id="windows-users"><span class="header-section-number">1.1.1.1.1</span> Windows users</h5>
+<h5 data-number="1.1.1.1.1"><span class="header-section-number">1.1.1.1.1</span> Windows users</h5>
<p>For Windows users select the ‘<a href="(https://cran.r-project.org/bin/windows/)">Download R for Windows</a>’ link and then click on the ‘base’ link and finally the download link ‘Download R 4.2.1 for Windows’. This will begin the download of the ‘.exe’ installation file. When the download has completed double click on the R executable file and follow the on-screen instructions. Full installation instructions can be found at the <a href="https://cran.r-project.org/bin/windows/">CRAN website</a>.</p>
</section>
<section id="mac-users" class="level5" data-number="1.1.1.1.2">
-<h5 data-number="1.1.1.1.2" class="anchored" data-anchor-id="mac-users"><span class="header-section-number">1.1.1.1.2</span> Mac users</h5>
+<h5 data-number="1.1.1.1.2"><span class="header-section-number">1.1.1.1.2</span> Mac users</h5>
<p>For Mac users select the ‘<a href="https://cran.r-project.org/bin/macosx/">Download R for (Mac) OS X</a>’ link. The binary can be downloaded by selecting the ‘R-4.2.1.pkg’. Once downloaded, double click on the file icon and follow the on-screen instructions to guide you through the necessary steps. See the ‘<a href="https://cran.r-project.org/bin/macosx/RMacOSX-FAQ.html">R for Mac OS X FAQ</a>’ for further information on installation.</p>
</section>
<section id="linux-users" class="level5" data-number="1.1.1.1.3">
-<h5 data-number="1.1.1.1.3" class="anchored" data-anchor-id="linux-users"><span class="header-section-number">1.1.1.1.3</span> Linux users</h5>
+<h5 data-number="1.1.1.1.3"><span class="header-section-number">1.1.1.1.3</span> Linux users</h5>
<p>For Linux users, the installation method will depend on which flavour of Linux you are using. There are reasonably comprehensive instruction <a href="https://cran.r-project.org/bin/linux/">here</a> for Debian, Redhat, Suse and Ubuntu. In most cases you can just use your OS package manager to install R from the official repository. On Ubuntu fire up a shell (Terminal) and use (you will need root permission to do this):</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt update</span>
-<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install r-base r-base-dev</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb1"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt update</span>
+<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install r-base r-base-dev</span></code></pre></div>
</div>
<p>which will install base R and also the development version of base R (you only need this if you want to compile R packages from source but it doesn’t hurt to have it).</p>
<p>If you receive an error after running the code above you may need to add a ‘source.list’ entry to your etc/apt/sources.list file. To do this open the terminal and enter this:</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb2"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install <span class="at">-y</span> <span class="at">--no-install-recommends</span> software-properties-common dirmngr</span>
+<div class="sourceCode" id="cb2"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install <span class="at">-y</span> <span class="at">--no-install-recommends</span> software-properties-common dirmngr</span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="co"># Add keys</span></span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="fu">wget</span> <span class="at">-qO-</span> https://cloud.r-project.org/bin/linux/ubuntu/marutter_pubkey.asc <span class="kw">|</span> <span class="fu">sudo</span> tee <span class="at">-a</span> /etc/apt/trusted.gpg.d/cran_ubuntu_key.asc</span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> add-apt-repository <span class="st">"deb https://cloud.r-project.org/bin/linux/ubuntu </span><span class="va">$(</span><span class="ex">lsb_release</span> <span class="at">-cs</span><span class="va">)</span><span class="st">-cran40/"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> add-apt-repository <span class="st">"deb https://cloud.r-project.org/bin/linux/ubuntu </span><span class="va">$(</span><span class="ex">lsb_release</span> <span class="at">-cs</span><span class="va">)</span><span class="st">-cran40/"</span></span></code></pre></div>
</div>
<p>Once you have done this then re-run the apt commands above and you should be good to go.</p>
<p>Install the following packages to allow for future spatial data analysis:</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb3"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install <span class="at">-y</span> libgdal-dev libproj-dev libgeos-dev libudunits2-dev libv8-dev libnode-dev libcairo2-dev libnetcdf-dev</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb3"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install <span class="at">-y</span> libgdal-dev libproj-dev libgeos-dev libudunits2-dev libv8-dev libnode-dev libcairo2-dev libnetcdf-dev</span></code></pre></div>
</div>
</section>
</section>
<section id="rstudio" class="level4" data-number="1.1.1.2">
-<h4 data-number="1.1.1.2" class="anchored" data-anchor-id="rstudio"><span class="header-section-number">1.1.1.2</span> RStudio</h4>
+<h4 data-number="1.1.1.2"><span class="header-section-number">1.1.1.2</span> RStudio</h4>
<p>Whilst its eminently possible to just use the base installation of R (many people do), we will be using a popular Integrated Development Environment (IDE) called RStudio. RStudio can be thought of as an add-on to R which provides a more user-friendly interface, incorporating the R Console, a script editor and other useful functionality (like R markdown and Git Hub integration). You can find more information about RStudio <a href="https://rstudio.com/">here</a>.</p>
<p>RStudio is freely available for Windows, Mac and Linux operating systems and can be downloaded from the <a href="https://rstudio.com/products/rstudio/download">RStudio site</a>. You should select the ‘RStudio Desktop’ version. Note: you must install R before you install RStudio.</p>
<section id="windows-and-mac-users" class="level5" data-number="1.1.1.2.1">
-<h5 data-number="1.1.1.2.1" class="anchored" data-anchor-id="windows-and-mac-users"><span class="header-section-number">1.1.1.2.1</span> Windows and Mac users</h5>
+<h5 data-number="1.1.1.2.1"><span class="header-section-number">1.1.1.2.1</span> Windows and Mac users</h5>
<p>For Windows and Mac users you should be presented with the appropriate link for downloading. Click on this link and once downloaded run the installer and follow the instructions. If you don’t see the link then scroll down to the ‘All Installers’ section and choose the link manually.</p>
</section>
<section id="linux-users-1" class="level5" data-number="1.1.1.2.2">
-<h5 data-number="1.1.1.2.2" class="anchored" data-anchor-id="linux-users-1"><span class="header-section-number">1.1.1.2.2</span> Linux users</h5>
+<h5 data-number="1.1.1.2.2"><span class="header-section-number">1.1.1.2.2</span> Linux users</h5>
<p>For Linux users scroll down to the ‘All Installers’ section and choose the appropriate link to download the binary for your Linux operating system. RStudio for Ubuntu (and Debian) is available as a <code>*.deb</code> package.</p>
<p>To install the <code>*.deb</code> file navigate to where you downloaded the file and then enter the following command with root permission</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb4"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install ./rstudio-2022.07.2-576-amd64.deb</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb4"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="fu">sudo</span> apt install ./rstudio-2022.07.2-576-amd64.deb</span></code></pre></div>
</div>
<p>You can then start RStudio from the Console by simply typing</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb5"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="ex">rstudio</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb5"><pre class="sourceCode bash cell-code"><code class="sourceCode bash"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="ex">rstudio</span></span></code></pre></div>
</div>
<p>or you can create a shortcut on you Desktop for easy startup.</p>
</section>
</section>
</section>
<section id="help" class="level3" data-number="1.1.2">
-<h3 data-number="1.1.2" class="anchored" data-anchor-id="help"><span class="header-section-number">1.1.2</span> Help</h3>
+<h3 data-number="1.1.2"><span class="header-section-number">1.1.2</span> Help</h3>
<p>The R help is very useful for the use of functions.</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb6"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>?plot <span class="co">#displays the help page for the plot function</span></span>
-<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="fu">help</span>(<span class="st">"*"</span>) <span class="co">#for unconventional characters</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb6"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>?plot <span class="co">#displays the help page for the plot function</span></span>
+<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="fu">help</span>(<span class="st">"*"</span>) <span class="co">#for unconventional characters</span></span></code></pre></div>
</div>
<p>Calling the help opens a page (the exact behavior depends on the operating system) with information and usage examples about the documented function(s) or operators.</p>
</section>
<section id="functions" class="level3" data-number="1.1.3">
-<h3 data-number="1.1.3" class="anchored" data-anchor-id="functions"><span class="header-section-number">1.1.3</span> Functions</h3>
+<h3 data-number="1.1.3"><span class="header-section-number">1.1.3</span> Functions</h3>
<p>The basic syntax is:</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb7"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>afunction <span class="ot"><-</span> <span class="cf">function</span>(arg1, arg2){</span>
+<div class="sourceCode" id="cb7"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>afunction <span class="ot"><-</span> <span class="cf">function</span>(arg1, arg2){</span>
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a> arg1 <span class="sc">+</span> arg2</span>
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a>}</span>
-<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a><span class="fu">afunction</span>(<span class="dv">10</span>, <span class="dv">5</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a><span class="fu">afunction</span>(<span class="dv">10</span>, <span class="dv">5</span>)</span></code></pre></div>
<div class="cell-output cell-output-stdout">
<pre><code>[1] 15</code></pre>
</div>
@@ -365,34 +375,34 @@ Note
</section>
</section>
<section id="spatial-in-r-history-and-evolutions" class="level2" data-number="1.2">
-<h2 data-number="1.2" class="anchored" data-anchor-id="spatial-in-r-history-and-evolutions"><span class="header-section-number">1.2</span> Spatial in R : History and evolutions</h2>
+<h2 data-number="1.2"><span class="header-section-number">1.2</span> Spatial in R : History and evolutions</h2>
<p>Historically, 4 packages make it possible to import, manipulate and transform spatial data:</p>
<ul>
-<li>The package <code>rgdal</code> <span class="citation" data-cites="rgdal">(<a href="references.html#ref-rgdal" role="doc-biblioref">Bivand, Keitt, and Rowlingson 2022</a>)</span> which is an interface between R and the <a href="http://www.gdal.org/">GDAL</a> <span class="citation" data-cites="GDAL">(<a href="references.html#ref-GDAL" role="doc-biblioref">GDAL/OGR contributors, n.d.</a>)</span> and <a href="https://proj.org/">PROJ</a> <span class="citation" data-cites="PROJ">(<a href="references.html#ref-PROJ" role="doc-biblioref">PROJ contributors 2021</a>)</span> libraries allow you to import and export spatial data (shapefiles for example) and also to manage cartographic projections<br>
+<li>The package <code>rgdal</code> <span class="citation" data-cites="rgdal">(<a href="#ref-rgdal" role="doc-biblioref">Bivand, Keitt, and Rowlingson 2022</a>)</span> which is an interface between R and the <a href="http://www.gdal.org/">GDAL</a> <span class="citation" data-cites="GDAL">(<a href="#ref-GDAL" role="doc-biblioref">GDAL/OGR contributors, n.d.</a>)</span> and <a href="https://proj.org/">PROJ</a> <span class="citation" data-cites="PROJ">(<a href="#ref-PROJ" role="doc-biblioref">PROJ contributors 2021</a>)</span> libraries allow you to import and export spatial data (shapefiles for example) and also to manage cartographic projections<br />
</li>
-<li>The package <code>sp</code> <span class="citation" data-cites="sp">(<a href="references.html#ref-sp" role="doc-biblioref">E. J. Pebesma and Bivand 2005</a>)</span> provides class and methods for vector spatial data in R. It allows displaying background maps, inspectiong an attribute table etc.<br>
+<li>The package <code>sp</code> <span class="citation" data-cites="sp">(<a href="#ref-sp" role="doc-biblioref">E. J. Pebesma and Bivand 2005</a>)</span> provides class and methods for vector spatial data in R. It allows displaying background maps, inspectiong an attribute table etc.<br />
</li>
-<li>The package <code>rgeos</code> <span class="citation" data-cites="rgeos">(<a href="references.html#ref-rgeos" role="doc-biblioref">Bivand and Rundel 2021</a>)</span> gives access to the <a href="http://trac.osgeo.org/geos/">GEOS</a> spatial operations library and therefore makes classic GIS operations available: calculation of surfaces or perimeters, calculation of distances, spatial aggregations, buffer zones, intersections, etc.<br>
+<li>The package <code>rgeos</code> <span class="citation" data-cites="rgeos">(<a href="#ref-rgeos" role="doc-biblioref">Bivand and Rundel 2021</a>)</span> gives access to the <a href="http://trac.osgeo.org/geos/">GEOS</a> spatial operations library and therefore makes classic GIS operations available: calculation of surfaces or perimeters, calculation of distances, spatial aggregations, buffer zones, intersections, etc.<br />
</li>
-<li>The package <code>raster</code> <span class="citation" data-cites="raster">(<a href="references.html#ref-raster" role="doc-biblioref">Hijmans 2022a</a>)</span> is dedicated to the import, manipulation and modeling of raster data.</li>
+<li>The package <code>raster</code> <span class="citation" data-cites="raster">(<a href="#ref-raster" role="doc-biblioref">Hijmans 2022a</a>)</span> is dedicated to the import, manipulation and modeling of raster data.</li>
</ul>
-<p>Today, the main developments concerning vector data have moved away from the old 3 (<code>sp</code>, <code>rgdal</code>, <code>rgeos</code>) to rely mainly on the package <code>sf</code> (<span class="citation" data-cites="sf">(<a href="references.html#ref-sf" role="doc-biblioref">E. Pebesma 2018a</a>)</span>, <span class="citation" data-cites="pebesma2018">(<a href="references.html#ref-pebesma2018" role="doc-biblioref">E. Pebesma 2018b</a>)</span>). In this manual we will rely exclusively on this package to manipulate vector data.</p>
-<p>The packages <code>stars</code> <span class="citation" data-cites="stars">(<a href="references.html#ref-stars" role="doc-biblioref">E. Pebesma 2021</a>)</span> and <code>terra</code> <span class="citation" data-cites="terra">(<a href="references.html#ref-terra" role="doc-biblioref">Hijmans 2022b</a>)</span> come to replace the package <code>raster</code> for processing raster data. We have chosen to use the package here <code>terra</code> for its proximity to the <code>raster</code>.</p>
+<p>Today, the main developments concerning vector data have moved away from the old 3 (<code>sp</code>, <code>rgdal</code>, <code>rgeos</code>) to rely mainly on the package <code>sf</code> (<span class="citation" data-cites="sf">(<a href="#ref-sf" role="doc-biblioref">E. Pebesma 2018a</a>)</span>, <span class="citation" data-cites="pebesma2018">(<a href="#ref-pebesma2018" role="doc-biblioref">E. Pebesma 2018b</a>)</span>). In this manual we will rely exclusively on this package to manipulate vector data.</p>
+<p>The packages <code>stars</code> <span class="citation" data-cites="stars">(<a href="#ref-stars" role="doc-biblioref">E. Pebesma 2021</a>)</span> and <code>terra</code> <span class="citation" data-cites="terra">(<a href="#ref-terra" role="doc-biblioref">Hijmans 2022b</a>)</span> come to replace the package <code>raster</code> for processing raster data. We have chosen to use the package here <code>terra</code> for its proximity to the <code>raster</code>.</p>
</section>
<section id="the-package-sf" class="level2" data-number="1.3">
-<h2 data-number="1.3" class="anchored" data-anchor-id="the-package-sf"><span class="header-section-number">1.3</span> The package <code>sf</code></h2>
-<p><img src="img/sf.gif" align="right" width="150"> The package <code>sf</code> was released in late 2016 by Edzer Pebesma (also author of <code>sp</code>). Its goal is to combine the feature of <code>sp</code>, <code>rgeos</code> and <code>rgdal</code> in a single, more ergonomic package. This package offers simple objects (following the <a href="https://en.wikipedia.org/wiki/Simple_Features"><em>simple feature</em></a> standard) which are easier to manipulate. Particular attention has been paid to the compatibility of the package with the <em>pipe</em> syntax and the operators of the <code>tidyverse</code>.</p>
+<h2 data-number="1.3"><span class="header-section-number">1.3</span> The package <code>sf</code></h2>
+<p><img src="img/sf.gif" align="right" width="150"/> The package <code>sf</code> was released in late 2016 by Edzer Pebesma (also author of <code>sp</code>). Its goal is to combine the feature of <code>sp</code>, <code>rgeos</code> and <code>rgdal</code> in a single, more ergonomic package. This package offers simple objects (following the <a href="https://en.wikipedia.org/wiki/Simple_Features"><em>simple feature</em></a> standard) which are easier to manipulate. Particular attention has been paid to the compatibility of the package with the <em>pipe</em> syntax and the operators of the <code>tidyverse</code>.</p>
<p><code>sf</code> directly uses the GDAL, GEOS and PROJ libraries.</p>
<div class="quarto-figure quarto-figure-center">
-<figure class="figure">
-<p><img src="img/sf_deps.png" class="img-fluid figure-img" width="600"></p>
+<figure>
+<p><img src="img/sf_deps.png" class="img-fluid" width="600" /></p>
</figure>
</div>
<p><a href="https://r-spatial.org/r/2020/03/17/wkt.html">From r-spatial.org</a></p>
<div class="callout-note callout callout-style-simple no-icon">
<div class="callout-body d-flex">
<div class="callout-icon-container">
-<i class="callout-icon no-icon"></i>
+<i class='callout-icon no-icon'></i>
</div>
<div class="callout-body-container">
<p>Website of package <code>sf</code> : <a href="https://r-spatial.github.io/sf/">Simple Features for R</a></p>
@@ -401,15 +411,15 @@ Note
</div>
<p>Many of the spatial data available on the internet are in shapefile format, which can be opened in the following way</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb9"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(sf)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb9"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(sf)</span></code></pre></div>
<div class="cell-output cell-output-stderr">
-<pre><code>Linking to GEOS 3.10.2, GDAL 3.4.3, PROJ 8.2.1; sf_use_s2() is TRUE</code></pre>
+<pre><code>Linking to GEOS 3.9.3, GDAL 3.5.2, PROJ 8.2.1; sf_use_s2() is TRUE</code></pre>
</div>
-<div class="sourceCode cell-code" id="cb11"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>district <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/district.shp"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb11"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>district <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/district.shp"</span>)</span></code></pre></div>
<div class="cell-output cell-output-stdout">
-<pre class="code-out"><code>Reading layer `district' from data source
- `/home/lucas/Documents/ForgeIRD/rspatial-for-onehealth/data_cambodia/district.shp'
- using driver `ESRI Shapefile'
+<pre class="code-out"><code>Reading layer `district' from data source
+ `C:\Users\UNiK\Documents\R_works\IRD\Rspatial\rspatial-for-onehealth\data_cambodia\district.shp'
+ using driver `ESRI Shapefile'
Simple feature collection with 197 features and 10 fields
Geometry type: MULTIPOLYGON
Dimension: XY
@@ -420,7 +430,7 @@ Projected CRS: WGS 84 / UTM zone 48N</code></pre>
<div class="callout-important callout callout-style-default callout-captioned">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
-<i class="callout-icon"></i>
+<i class='callout-icon'></i>
</div>
<div class="callout-caption-container flex-fill">
Shapefile format limitations
@@ -432,7 +442,7 @@ Shapefile format limitations
</div>
<p>A geopackage is a database, to load a layer, you must know its name</p>
<div class="cell">
-<div class="sourceCode cell-code" id="cb13"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">st_layers</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb13"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="fu">st_layers</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>)</span></code></pre></div>
<div class="cell-output cell-output-stdout">
<pre class="code-out"><code>Driver: GPKG
Available layers:
@@ -446,11 +456,11 @@ Available layers:
</div>
</div>
<div class="cell">
-<div class="sourceCode cell-code" id="cb15"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a>road <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"road"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<div class="sourceCode" id="cb15"><pre class="sourceCode r cell-code"><code class="sourceCode r"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a>road <span class="ot"><-</span> <span class="fu">st_read</span>(<span class="st">"data_cambodia/cambodia.gpkg"</span>, <span class="at">layer =</span> <span class="st">"road"</span>)</span></code></pre></div>
<div class="cell-output cell-output-stdout">
-<pre class="code-out"><code>Reading layer `road' from data source
- `/home/lucas/Documents/ForgeIRD/rspatial-for-onehealth/data_cambodia/cambodia.gpkg'
- using driver `GPKG'
+<pre class="code-out"><code>Reading layer `road' from data source
+ `C:\Users\UNiK\Documents\R_works\IRD\Rspatial\rspatial-for-onehealth\data_cambodia\cambodia.gpkg'
+ using driver `GPKG'
Simple feature collection with 6 features and 9 fields
Geometry type: MULTILINESTRING
Dimension: XY
@@ -459,17 +469,17 @@ Projected CRS: WGS 84 / UTM zone 48N</code></pre>
</div>
</div>
<section id="format-of-spatial-objects-sf" class="level3" data-number="1.3.1">
-<h3 data-number="1.3.1" class="anchored" data-anchor-id="format-of-spatial-objects-sf"><span class="header-section-number">1.3.1</span> Format of spatial objects <code>sf</code></h3>
+<h3 data-number="1.3.1"><span class="header-section-number">1.3.1</span> Format of spatial objects <code>sf</code></h3>
<div class="quarto-figure quarto-figure-center">
-<figure class="figure">
-<p><img src="img/sf.png" class="img-fluid figure-img" width="600"></p>
+<figure>
+<p><img src="img/sf.png" class="img-fluid" width="600" /></p>
</figure>
</div>
<p>Objects<code>sf</code> are objects in <code>data.frame</code> which one of the columns contains geometries. This column is the class of sfc (<em>simple feature column</em>) and each individual of the column is a sfg <em>(simple feature geometry)</em>. This format is very practical insofa as the data and the geometries are intrinsically linked in the same object.</p>
<div class="callout-note callout callout-style-simple no-icon">
<div class="callout-body d-flex">
<div class="callout-icon-container">
-<i class="callout-icon no-icon"></i>
+<i class='callout-icon no-icon'></i>
</div>
<div class="callout-body-container">
<p>Thumbnail describing the simple feature format: <a href="https://r-spatial.github.io/sf/articles/sf1.html">Simple Features for R</a></p>
@@ -479,7 +489,7 @@ Projected CRS: WGS 84 / UTM zone 48N</code></pre>
<div class="callout-tip callout callout-style-default callout-captioned">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
-<i class="callout-icon"></i>
+<i class='callout-icon'></i>
</div>
<div class="callout-caption-container flex-fill">
Tip
@@ -492,21 +502,21 @@ Tip
</section>
</section>
<section id="package-mapsf" class="level2" data-number="1.4">
-<h2 data-number="1.4" class="anchored" data-anchor-id="package-mapsf"><span class="header-section-number">1.4</span> Package <code>mapsf</code></h2>
-<p>The free R software spatial ecosystem is rich, dynamic and mature and several packages allow to import, process and represent spatial data. The package <a href="https://CRAN.R-project.org/package=maps"><code>mapsf</code></a> <span class="citation" data-cites="mapsf">(<a href="references.html#ref-mapsf" role="doc-biblioref">Giraud 2022</a>)</span> relies on this ecosystem to integrate the creation of quality thematic maps into processing chains with R.</p>
-<p>Other packages can be used to make thematic maps. The package <code>ggplot2</code> <span class="citation" data-cites="ggplot2">(<a href="references.html#ref-ggplot2" role="doc-biblioref">Wickham 2016</a>)</span>, in association with the package <code>ggspatial</code> <span class="citation" data-cites="ggspatial">(<a href="references.html#ref-ggspatial" role="doc-biblioref">Dunnington 2021</a>)</span>, allows for example to display spatial objects and to make simple thematic maps. The package <code>tmap</code> <span class="citation" data-cites="tmap">(<a href="references.html#ref-tmap" role="doc-biblioref">Tennekes 2018</a>)</span> is dedicated to the creation of thematic maps, it uses a syntax close to that of <code>ggplot2</code> (sequence of instructions combined with the ‘+’ sign). Documentation and tutorials for using these two packages are readily available on the web.</p>
+<h2 data-number="1.4"><span class="header-section-number">1.4</span> Package <code>mapsf</code></h2>
+<p>The free R software spatial ecosystem is rich, dynamic and mature and several packages allow to import, process and represent spatial data. The package <a href="https://CRAN.R-project.org/package=maps"><code>mapsf</code></a> <span class="citation" data-cites="mapsf">(<a href="#ref-mapsf" role="doc-biblioref">Giraud 2022</a>)</span> relies on this ecosystem to integrate the creation of quality thematic maps into processing chains with R.</p>
+<p>Other packages can be used to make thematic maps. The package <code>ggplot2</code> <span class="citation" data-cites="ggplot2">(<a href="#ref-ggplot2" role="doc-biblioref">Wickham 2016</a>)</span>, in association with the package <code>ggspatial</code> <span class="citation" data-cites="ggspatial">(<a href="#ref-ggspatial" role="doc-biblioref">Dunnington 2021</a>)</span>, allows for example to display spatial objects and to make simple thematic maps. The package <code>tmap</code> <span class="citation" data-cites="tmap">(<a href="#ref-tmap" role="doc-biblioref">Tennekes 2018</a>)</span> is dedicated to the creation of thematic maps, it uses a syntax close to that of <code>ggplot2</code> (sequence of instructions combined with the ‘+’ sign). Documentation and tutorials for using these two packages are readily available on the web.</p>
<p>Here, we will mainly use the package <code>mapsf</code> whose functionalities are quite complete and the handling rather simple. In addition, the package is relatively light.</p>
-<p><img src="img/logo_mapsf.png" align="right" width="120"></p>
-<p><code>mapsf</code> allows you to create most of the types of map usually used in statistical cartography (choropleth maps, typologies, proportional or graduated symbols, etc.). For each type of map, several parameters are used to customize the cartographic representation. These parameters are the same as those found in the usual GIS or cartography software (for example, the choice of discretizations and color palettes, the modification of the size of the symbols or the customization of the legends). Associated with the data representation functions, other functions are dedicated to cartographic dressing (themes or graphic charters, legends, scales, orientation arrows, title, credits, annotations, etc.), the creation of boxes or the exporting maps.<br>
-<code>mapsf</code> is the successor of <a href="http://riatelab.github.io/cartography/docs/"><code>cartography</code></a> <span class="citation" data-cites="cartography">(<a href="references.html#ref-cartography" role="doc-biblioref">Giraud and Lambert 2016</a>)</span>, it offers the same main functionalities while being lighter and more ergonomic.</p>
+<p><img src="img/logo_mapsf.png" align="right" width="120"/></p>
+<p><code>mapsf</code> allows you to create most of the types of map usually used in statistical cartography (choropleth maps, typologies, proportional or graduated symbols, etc.). For each type of map, several parameters are used to customize the cartographic representation. These parameters are the same as those found in the usual GIS or cartography software (for example, the choice of discretizations and color palettes, the modification of the size of the symbols or the customization of the legends). Associated with the data representation functions, other functions are dedicated to cartographic dressing (themes or graphic charters, legends, scales, orientation arrows, title, credits, annotations, etc.), the creation of boxes or the exporting maps.<br />
+<code>mapsf</code> is the successor of <a href="http://riatelab.github.io/cartography/docs/"><code>cartography</code></a> <span class="citation" data-cites="cartography">(<a href="#ref-cartography" role="doc-biblioref">Giraud and Lambert 2016</a>)</span>, it offers the same main functionalities while being lighter and more ergonomic.</p>
<p>To use this package several sources can be consulted:</p>
<ul>
<li><p>The package documentation accessible <a href="http://riatelab.github.io/mapsf/">on the internet</a> or directly in R (<code>?mapsf</code>),</p></li>
<li><p>A <a href="https://raw.githubusercontent.com/riatelab/mapsf/master/vignettes/web_only/img/mapsf_cheatsheet.pdf"><em>cheat sheet</em></a>,</p></li>
</ul>
<div class="quarto-figure quarto-figure-center">
-<figure class="figure">
-<p><img src="img/mapsf_cheatsheet.png" class="img-fluid figure-img" width="600"></p>
+<figure>
+<p><img src="img/mapsf_cheatsheet.png" class="img-fluid" width="600" /></p>
</figure>
</div>
<ul>
@@ -515,12 +525,12 @@ Tip
</ul>
</section>
<section id="the-package-terra" class="level2" data-number="1.5">
-<h2 data-number="1.5" class="anchored" data-anchor-id="the-package-terra"><span class="header-section-number">1.5</span> The package <code>terra</code></h2>
-<p><img src="img/logo_terra.png" align="right" width="150"> The package <code>terra</code> was release in early 2020 by Robert J. Hijmans (also author of <code>raster</code>). Its objective is to propose methods of treatment and analysis of raster data. This package is very similar to the package <code>raster</code>; but it has more features, it’s easier to use, and it’s faster.</p>
+<h2 data-number="1.5"><span class="header-section-number">1.5</span> The package <code>terra</code></h2>
+<p><img src="img/logo_terra.png" align="right" width="150"/> The package <code>terra</code> was release in early 2020 by Robert J. Hijmans (also author of <code>raster</code>). Its objective is to propose methods of treatment and analysis of raster data. This package is very similar to the package <code>raster</code>; but it has more features, it’s easier to use, and it’s faster.</p>
<div class="callout-note callout callout-style-simple no-icon">
<div class="callout-body d-flex">
<div class="callout-icon-container">
-<i class="callout-icon no-icon"></i>
+<i class='callout-icon no-icon'></i>
</div>
<div class="callout-body-container">
<p>Website of package <code>terra</code> : <a href="https://rspatial.org/terra/">Spatial Data Science with R and “terraâ€</a></p>
@@ -530,7 +540,7 @@ Tip
<div class="callout-tip callout callout-style-default callout-captioned">
<div class="callout-header d-flex align-content-center">
<div class="callout-icon-container">
-<i class="callout-icon"></i>
+<i class='callout-icon'></i>
</div>
<div class="callout-caption-container flex-fill">
Tip
@@ -540,9 +550,13 @@ Tip
<p>A benchmark of raster processing libraries is available <a href="https://github.com/kadyb/raster-benchmark">here</a>.</p>
</div>
</div>
-
-
-<div id="refs" class="references csl-bib-body hanging-indent" role="doc-bibliography" style="display: none">
+<div id="quarto-navigation-envelope" class="hidden">
+<p><span class="hidden" data-render-id="quarto-int-sidebar-title">Mapping and spatial analyses in R for One Health studies</span> <span class="hidden" data-render-id="quarto-int-navbar-title">Mapping and spatial analyses in R for One Health studies</span> <span class="hidden" data-render-id="quarto-int-next"><span class="chapter-number">2</span>Â <span class="chapter-title">Data Acquisition</span></span> <span class="hidden" data-render-id="quarto-int-prev">Preface</span> <span class="hidden" data-render-id="quarto-int-sidebar:/index.html">Preface</span> <span class="hidden" data-render-id="quarto-int-sidebar:/01-introduction.html"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/02-data_acquisition.html"><span class="chapter-number">2</span>Â <span class="chapter-title">Data Acquisition</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/03-vector_data.html"><span class="chapter-number">3</span>Â <span class="chapter-title">Using vector data</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/04-raster_data.html"><span class="chapter-number">4</span>Â <span class="chapter-title">Using raster data</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/05-mapping_with_r.html"><span class="chapter-number">5</span>Â <span class="chapter-title">Mapping With R</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/07-basic_statistics.html"><span class="chapter-number">6</span>Â <span class="chapter-title">Basic statistics for spatial analysis</span></span> <span class="hidden" data-render-id="quarto-int-sidebar:/references.html">References</span> <span class="hidden" data-render-id="footer-left">UMR 228 ESPACE-DEV</span> <span class="hidden" data-render-id="footer-right"><img src="img/ird_footer.png" height="50" /></span></p>
+</div>
+<div id="quarto-meta-markdown" class="hidden">
+<p><span class="hidden" data-render-id="quarto-metatitle">Mapping and spatial analyses in R for One Health studies - <span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></span> <span class="hidden" data-render-id="quarto-twittercardtitle">Mapping and spatial analyses in R for One Health studies - <span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></span> <span class="hidden" data-render-id="quarto-ogcardtitle">Mapping and spatial analyses in R for One Health studies - <span id="introductionx" class="quarto-section-identifier"><span class="chapter-number">1</span>Â <span class="chapter-title">Introduction</span></span></span> <span class="hidden" data-render-id="quarto-metasitename">Mapping and spatial analyses in R for One Health studies</span></p>
+</div>
+<div id="refs" class="references csl-bib-body hanging-indent" role="doc-bibliography">
<div id="ref-rgdal" class="csl-entry" role="doc-biblioentry">
Bivand, Roger, Tim Keitt, and Barry Rowlingson. 2022. <span>“Rgdal: Bindings for the ’Geospatial’ Data Abstraction Library.â€</span> <a href="https://CRAN.R-project.org/package=rgdal">https://CRAN.R-project.org/package=rgdal</a>.
</div>
@@ -592,7 +606,7 @@ Wickham, Hadley. 2016. <span>“Ggplot2: Elegant Graphics for Data Analysis.â€<
</section>
</main> <!-- /main -->
-<script id="quarto-html-after-body" type="application/javascript">
+<script id = "quarto-html-after-body" type="application/javascript">
window.document.addEventListener("DOMContentLoaded", function (event) {
const toggleBodyColorMode = (bsSheetEl) => {
const mode = bsSheetEl.getAttribute("data-mode");
@@ -706,25 +720,29 @@ window.document.addEventListener("DOMContentLoaded", function (event) {
</script>
<nav class="page-navigation">
<div class="nav-page nav-page-previous">
- <a href="./index.html" class="pagination-link">
+ <a href="/index.html" class="pagination-link">
<i class="bi bi-arrow-left-short"></i> <span class="nav-page-text">Preface</span>
</a>
</div>
<div class="nav-page nav-page-next">
- <a href="./02-data_acquisition.html" class="pagination-link">
- <span class="nav-page-text"><span class="chapter-number">2</span> <span class="chapter-title">Data Acquisition</span></span> <i class="bi bi-arrow-right-short"></i>
+ <a href="/02-data_acquisition.html" class="pagination-link">
+ <span class="nav-page-text"><span class='chapter-number'>2</span>Â <span class='chapter-title'>Data Acquisition</span></span> <i class="bi bi-arrow-right-short"></i>
</a>
</div>
</nav>
</div> <!-- /content -->
<footer class="footer">
<div class="nav-footer">
- <div class="nav-footer-left">UMR 228 ESPACE-DEV</div>
- <div class="nav-footer-right"><img src="img/ird_footer.png" height="50"></div>
+ <div class="nav-footer-left">
+ <div class='footer-contents'>UMR 228 ESPACE-DEV</div>
+ </div>
+ <div class="nav-footer-right">
+ <div class='footer-contents'>{height="50"}
+</div>
+ </div>
</div>
</footer>
+</body>
-
-<script src="site_libs/quarto-html/zenscroll-min.js"></script>
-</body></html>
\ No newline at end of file
+</html>
\ No newline at end of file
diff --git a/public/07-basic_statistics.html b/public/07-basic_statistics.html
index 406cef8..be4b78e 100644
--- a/public/07-basic_statistics.html
+++ b/public/07-basic_statistics.html
@@ -490,18 +490,20 @@ Moran’s I test
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(spdep) <span class="co"># Functions for creating spatial weight, spatial analysis</span></span>
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(DCluster) <span class="co"># Package with functions for spatial cluster analysis</span></span>
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a>queen_nb <span class="ot"><-</span> <span class="fu">poly2nb</span>(district) <span class="co"># Neighbors according to queen case</span></span>
-<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a>q_listw <span class="ot"><-</span> <span class="fu">nb2listw</span>(queen_nb, <span class="at">style =</span> <span class="st">'W'</span>) <span class="co"># row-standardized weights</span></span>
-<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a></span>
-<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a><span class="co"># Moran's I test</span></span>
-<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a>m_test <span class="ot"><-</span> <span class="fu">moranI.test</span>(cases <span class="sc">~</span> <span class="fu">offset</span>(<span class="fu">log</span>(expected)), </span>
-<span id="cb9-11"><a href="#cb9-11" aria-hidden="true" tabindex="-1"></a> <span class="at">data =</span> district,</span>
-<span id="cb9-12"><a href="#cb9-12" aria-hidden="true" tabindex="-1"></a> <span class="at">model =</span> <span class="st">'poisson'</span>,</span>
-<span id="cb9-13"><a href="#cb9-13" aria-hidden="true" tabindex="-1"></a> <span class="at">R =</span> <span class="dv">499</span>,</span>
-<span id="cb9-14"><a href="#cb9-14" aria-hidden="true" tabindex="-1"></a> <span class="at">listw =</span> q_listw,</span>
-<span id="cb9-15"><a href="#cb9-15" aria-hidden="true" tabindex="-1"></a> <span class="at">n =</span> <span class="fu">length</span>(district<span class="sc">$</span>cases), <span class="co"># number of regions</span></span>
-<span id="cb9-16"><a href="#cb9-16" aria-hidden="true" tabindex="-1"></a> <span class="at">S0 =</span> <span class="fu">Szero</span>(q_listw)) <span class="co"># Global sum of weights</span></span>
-<span id="cb9-17"><a href="#cb9-17" aria-hidden="true" tabindex="-1"></a><span class="fu">print</span>(m_test)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a><span class="fu">set.seed</span>(<span class="dv">345</span>) <span class="co"># remove random sampling for reproducibility</span></span>
+<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a>queen_nb <span class="ot"><-</span> <span class="fu">poly2nb</span>(district) <span class="co"># Neighbors according to queen case</span></span>
+<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a>q_listw <span class="ot"><-</span> <span class="fu">nb2listw</span>(queen_nb, <span class="at">style =</span> <span class="st">'W'</span>) <span class="co"># row-standardized weights</span></span>
+<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a></span>
+<span id="cb9-11"><a href="#cb9-11" aria-hidden="true" tabindex="-1"></a><span class="co"># Moran's I test</span></span>
+<span id="cb9-12"><a href="#cb9-12" aria-hidden="true" tabindex="-1"></a>m_test <span class="ot"><-</span> <span class="fu">moranI.test</span>(cases <span class="sc">~</span> <span class="fu">offset</span>(<span class="fu">log</span>(expected)), </span>
+<span id="cb9-13"><a href="#cb9-13" aria-hidden="true" tabindex="-1"></a> <span class="at">data =</span> district,</span>
+<span id="cb9-14"><a href="#cb9-14" aria-hidden="true" tabindex="-1"></a> <span class="at">model =</span> <span class="st">'poisson'</span>,</span>
+<span id="cb9-15"><a href="#cb9-15" aria-hidden="true" tabindex="-1"></a> <span class="at">R =</span> <span class="dv">499</span>,</span>
+<span id="cb9-16"><a href="#cb9-16" aria-hidden="true" tabindex="-1"></a> <span class="at">listw =</span> q_listw,</span>
+<span id="cb9-17"><a href="#cb9-17" aria-hidden="true" tabindex="-1"></a> <span class="at">n =</span> <span class="fu">length</span>(district<span class="sc">$</span>cases), <span class="co"># number of regions</span></span>
+<span id="cb9-18"><a href="#cb9-18" aria-hidden="true" tabindex="-1"></a> <span class="at">S0 =</span> <span class="fu">Szero</span>(q_listw)) <span class="co"># Global sum of weights</span></span>
+<span id="cb9-19"><a href="#cb9-19" aria-hidden="true" tabindex="-1"></a><span class="fu">print</span>(m_test)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output cell-output-stdout">
<pre class="code-out"><code>Moran's I test of spatial autocorrelation
@@ -509,14 +511,14 @@ Moran’s I test
Model used when sampling: Poisson
Number of simulations: 499
Statistic: 0.1566449
- p-value : 0.012 </code></pre>
+ p-value : 0.006 </code></pre>
</div>
<div class="sourceCode cell-code" id="cb11"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="fu">plot</span>(m_test)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output-display">
<p><img src="07-basic_statistics_files/figure-html/MoransI-1.png" class="img-fluid" width="768"></p>
</div>
</div>
-<p>The Moran’s statistics is here <span class="math inline">\(I =\)</span> 0.16. When comparing its value to the H0 distribution (built under 499 simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is <span class="math inline">\(p_{value} =\)</span> 0.012. We therefore reject H0 with error risk of <span class="math inline">\(\alpha = 5\%\)</span>. The distribution of cases is therefore autocorrelated across districts in Cambodia.</p>
+<p>The Moran’s statistics is here <span class="math inline">\(I =\)</span> 0.16. When comparing its value to the H0 distribution (built under 499 simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is <span class="math inline">\(p_{value} =\)</span> 0.006. We therefore reject H0 with error risk of <span class="math inline">\(\alpha = 5\%\)</span>. The distribution of cases is therefore autocorrelated across districts in Cambodia.</p>
</section>
<section id="the-local-morans-i-lisa-test" class="level4" data-number="6.2.2.2">
<h4 data-number="6.2.2.2" class="anchored" data-anchor-id="the-local-morans-i-lisa-test"><span class="header-section-number">6.2.2.2</span> The Local Moran’s I LISA test</h4>
@@ -731,7 +733,7 @@ Kulldorf test
<span id="cb30-7"><a href="#cb30-7" aria-hidden="true" tabindex="-1"></a><span class="fu">print</span>(df_secondary_clusters)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<div class="cell-output cell-output-stdout">
<pre class="code-out"><code> SMR number.of.cases expected.cases p.value
-1 3.767698 16 4.246625 0.016</code></pre>
+1 3.767698 16 4.246625 0.008</code></pre>
</div>
</div>
<p>We only have one secondary cluster composed of one district.</p>
@@ -811,6 +813,19 @@ To go further …
</div>
</div>
<p>Both methods identified significant clusters. The two methods could identify a cluster around Phnom Penh after standardization for population counts. However, the identified clusters does not rely on the same assumption. While the Moran’s test wonder whether their is any autocorrelation between clusters (i.e. second order effects of infection), the Kulldorff scan statistics wonder whether their is any heterogeneity in the case distribution. None of these test can inform on the infection processes (first or second order) for the studied disease and previous knowledge on the disease will help selecting the most accurate test.</p>
+<div class="callout-tip callout callout-style-default callout-captioned">
+<div class="callout-header d-flex align-content-center">
+<div class="callout-icon-container">
+<i class="callout-icon"></i>
+</div>
+<div class="callout-caption-container flex-fill">
+Tip
+</div>
+</div>
+<div class="callout-body-container callout-body">
+<p>In this example, Cambodia is treated as an island, i.e. there is no data outside of its borders. In reality, some clusters can occurs across country’s borders. You should be aware that such district will likely not be detected by these analysis. This border effect is still a hot topic in spatial studies and there is no conventional ways to deal with it. You can find in the literature some suggestion on how to deals with these border effect as assigning weights, or extrapolating data.</p>
+</div>
+</div>
<div id="refs" class="references csl-bib-body hanging-indent" role="doc-bibliography" style="display: none">
diff --git a/public/07-basic_statistics_files/figure-html/LocalMoransI_plt-1.png b/public/07-basic_statistics_files/figure-html/LocalMoransI_plt-1.png
index 76ae8864b9449bba6e98e23a670c17810e981a62..50d87dcb927ba7e92be21f09f7d6a15ac65728f9 100644
GIT binary patch
literal 44241
zcmcF~c{r3^`0$xA!yx+}F|zMOqAa73ec$&rTlPI<>`RFvTVjgrTe1^VlI)6#D6*66
zS+dOcc;EN;`}@1T>-xqx&ok%T+qv)ioO7QoNl)h{1=)Er004!$nz8`^#Lz1d9z_H_
z-pyRsfF1-rEh81^A$j&Omy`^XG&h$thtfRBFzDL`WkJ8qCBx3L&pyygo_Sc9c^H(o
zndd>@2~WTq24VgK6lR_m7AARC9+nrD2YuVZ@+QLC+QQnPbU)8rG7rKJlg#@E?yNko
z4f@M#gVKq-iMG56DBW)hlWYq!Zwm{9klXUi+w#Kx18IXk6A)nA1eET#?YFh<Pqgjt
zPvn_T<b_S-K?K6iXh1*^83^R;vk(1E?C(QF_uKLy&@+s)j59nan?NAg^PMI`svz}I
zGxrDJLc-ZUEOlYa82~g;S5`6#$y<Bv@k*rS;f0_P?N3czpJHWKHTx)Yq@R#kQ0gLN
zlX1uP%(wcB<R#Y`IU@E51QCU>ujCjW?11vDeppR+PKS#rjMRwHz3Td`zV{V~*9^~=
zbSoTs!82o^6xh&HLn)RCiGUt6Dli!I2+_wt>Hm+S3?Kve3&Sjt5PNEXNm}=00KgIA
z#?#tl48VPeea7++6BrODMgYC%|GxmOU<b1$gx&8)M@OB<>(jSM?(Up66-boL_H;Hr
zWAlB(s_?oq(!+Y~E5~{Wp(=9z$^KslMoDua+tZ&X!?p~!i{v}<)UUk^IK}KYk^!tl
z2z;|!Y<;bBCYAhfGxXq|t;NW!y%#U+;K#L1rGa!5=G)w4P6nOkQbd4v1pv%3Jb)u$
z#@?Pofr_=(+bAa#fmhsJiC~1O*{%oiF1-5`%JF?t5P<hHD0~cou>C7+b7|w$E$sIN
zUT|KD78^<GfSI0(v{eT4vcv!B>n4aE-<z&^=#9c39Yr1v-GfCOCUBevrwg5&hwP1E
z5=YGNO(QEe|Ii|$L3<~mFmi45sDSWeUPDpEv0nlWS$rJJ32Zw_Vt3vsMjjpNBytdr
zH!Bw2CFoUl5k(TjIKIbriqgd^RB@4X$`2jy)R_8DhdUjtblzn<IP`k$IxKYHt#~xc
z#L*IYFq(hTvyb|$NH|u0NM94NH5$47%TJ6~YOm0C>fXuEg2>-Ytj!Bewj5R`zNeFg
z*&jlDp2dEjxq5f|`)t%^T?{KVIixiu`<|Q=cUsxhij>!WxPRTj8P=Q%5Z*<EFB}M7
z)Dhp&{b$}>SHBG(FD$W&{ovAQL-y1zk>d#mPhF;}=IS^OI$7YGbJGcdzKZ5l$J8vA
z3#s(j0yYU;LHK@C!SC*O?@!2i*5bczEpV_SRk9*xgn?UXLflhQg~$G#-^PX5|8-4$
zMl96>oP)eNEMy>FPUb^lVT`BAz3FzsAK&F8{Ouq4rkhbb{d^m0>OihS)A|9?y_Yre
zj?=BNAcUmzv^lvdJKcBVI%(Th;5&x<7q9cd)WYNh*OWJV^CsiEZMHtXu7U%*`*k2Z
zc_P5Y-2y16Er}6M=ay0<U)|bu+Y;;SAYtgRlqD#%9xoO2+#=r#haLRn=xo)swj~Q0
zC)5UAv8BhRK94;3ZrTq|s1j8?p4(nOJ#k-4O%2uU)V&`n_f|3N-16M6_r3%F+^;x;
zpu%6{g9%<!zO>lNo|w0@ZuyWXpH*#0NB$AzTo~-&{oFf}q}xS)%zx3vH;cW8iu?EE
zU}h|bzv7<my-W_%Ekpwj^)C)zIvWK&Bg4P3c>jidgxB_9*J*J7R#%|yW1z51i*JuQ
z@MEVUzelQ&v$M>J_+K8GAkXI1s)K~O<1@!b_qBw|ghZAN=dgSb&dPoKo`akph3#pW
zzWwpx#=fD_hXsY@r}Ws9WqEi#ga0KRo!^RUs$YGrh$OaGm)XJZEkk={D(p~8zHV5z
z64aUft=)jh!Fv^t6$vXs!}ul|?<%pO={)lnx5bP%-}{O>7!-UB3gHn8<V3AM;5eZo
z^aO9Pz{a=bFJkhm<K7Q5ogbIi4zs9WYxO0$+>^9>&>|i^vyzv9DRL<a`nMflMhVkm
zZ{m-XgnuF4-vHsl8*3%a*C%XLLE|09lBhd5U#FJJD<`Ktxmrje#huc?Ebhs&QdJiG
zegyaNn|rV$jEn6Vj?<U8dufUN;?>lX^?zHlsyWd4IW1Nv$F|1Sr1Jdhhh`mcF{~_F
z{_i{rKeVVhYiNADdJAFa(zo%H4?OgpzG|Pvh#gNkrAR`ce{T8PL+-T@3w82Bn3t3@
zG2Exw)~LlPUBVm3$2Y)iK0+6w7I6n?MlRG4jw4UK2@ziB>`s>Y73KUS?|=+z3*d0&
zukp3uUjEbq@<Qn_F8}M0LK)Dur0ow}Zy{%h6#r5YHao-=EpA}8?!X(t!Cqw#P<U<V
z2y8d*HP^-9J<cr~iYIM5O||Luc^Lrsm31{wr0@1YOYJ+af~7oWB7il;hKu2J?bWzv
z8e<CNzZ?csh9r;2-gzVZO_LPs(&^4P67y01S3w;oF6^}PWbFwWdwmdYQS~rL04CGs
zds7(5rrwNGK@<#x<|B90H+1~p{M%CBOi=84D5AFZr{jbiJ11mjdm_i-N0zgRMhXMR
zzn9v&u}t#xznzx~?lu(D)ey;0%Jp5VoUVAtfTfxw98w(_%#U5grh|~6UUqzM%C*u!
zPz2eC<`-BFYsgP+r~PkOT7$f6kKA%khJ5dROGOt)r$y%e`l$5&Ldma@Wv-s5SsR)*
z-&5}%vTr$js0a<4kmp~gNiEPYg?sy_tb5pO{PHz*Z=bXvR^LGKAZKV?ZIcU4;5F}?
zS`C8IM=?ZK*3l(VkJuF%8Vk0HqaMi?KE^*Wh5t8x{86bDYkED%e$XF7I@H#EyrdXA
zD&3UB*Kb7cU6B)EmQIU({(5)jMvxe8e?;S!7|zbNo}>;w6Cuj^iYblhp6tY+E>T2k
z%N2PFsl9`;+7m4~3aO#cj<%)8xBne^?C#PXWRd8<n?{`0>u?_jaTSa0{T@8s7HT4#
ze$i}wNh;f0<Rm8fH*b<+tgG-x$#={?k>>YCq0^tiom)#`?BmFp(GEk4TUSO-piVEz
z4fl{Wn0gdr$ev0*IlMNCp_ARONNJz_FBXu4HE#$J%=CA~j>?N-s3Uj#H`Xnu!`|%%
z6MS^rHsT505f6GfI3iCjj?d=jJDb&JJ-J(dmug1JK^=wfa3&}f?myi~^`?{4A^Zup
zt>Sv-29sH35yo$)95LN#e3FZ#Z}BC%OwPZsRa$#8;Cne>XfAx7f$G0OmJI&_qh$^o
z_^%J<qs2P@jaYfLibekGP+L~;%`W-HZ7%mdGP?)=#w>CV!2#<uj%bAaUm_tFVP*<Q
z;?s?||H{)rGsnrS?TNZ7#_(UO&6Od*^8a1PlL6Y#Lgis33QF<!;Aa8b=5s8Rf_8rN
z*+Y!%|EVbX4$P<8*7GdNlQcsCdgwV5UCIbZ&T^W$wGe;|dhwATBg4i(FTjdU8V-<W
zWo&{-Jk+ZKAWFss!=4FbMG**}L7!!r#ytj@GYX>df-s+d0?PikS^#%e_Vs!SkoiZ}
zKzlx*2jyTjpIrxR|HPYb#pwY*l!bqcW5UuAZk!=hBQ*b`k8+2h4>-<P`EX{Foe7I2
zg?VXUga9|8s}}$*R4|eJ!&(N=%nYzAGYb6Y)|8b50O@JMJs8NQ2tMtM%HwAy2YKfJ
z-pLFB=9MvgK>ai!^{jLmUSuZ%d@cdt4?8Z1)c}`{sl<qYI1?0kV<46x?s5=s%yp(S
z<u?;g_1WtI_*vERnY`vAQQ#lb43h_^G1JeSJFA~A*-{`t19~*{F2|K=F2D}eX9x@Z
z+Pv=ri-|f_A4B2yha$F~9C1XR_Ce8E#~)}~^Z`8|`7YAchzxraKp=v6;jJ(v*cc0#
z&vg5lKC&s54mgf=3oXFi?F*37uq!?&u&kKm4)d`+D`$?SZ#kmF;tA?w<am-lP}a<$
z#AJ}|FDczt)l+J`oN+$oWBBIu$?6XzBn*DEYp|g#x2cE7m<I*Op^}xDqs{{gh;sgg
zSHH^)ndc~YVcG@@r20Z&qtn_5Kq3v_pO7~8=j<vFjAIAnpW&NIr|XgN5HZ89LFtm>
z`XO?8z*vr)Ihpk2hfJ{)`y@@LFwW-fC_efQ>|k;j4e4OOhpw)yltldIV;AMuK=_ps
zCzP3&xEx7)HAQHluEeEuD?^+b%W)S816Y^t974}%nLi)wpfqF0B<>jzJ|+sty^lIW
z%8=P1_$a)tIlbr}NSNk@Q3G~i#Eb$1JtV1ak}MLP^1@G&(sDTQJnSE3OfzFlfY(+Q
z{{7cr2MmBz?$D?N9E>hfp)j;(7Ns@2v6?P`%^+|Bx3h9JeAUrf-lCO_I#@JokrO~e
zc_U^`gaF?GXYm&rNIO?&K9V#4Jugrk_{-)v-I$yV{cnak%<M0sE77<Z%n;6<;c@F_
zdrOwn0hl<^nepf~j3(2qIF$JK@{wex!!Sr>F|zmM$3}2W)mAhZ`!~asyXWH9ASctU
zHOSG3AQ40Ko8QLjyl<06%*<jTz2BRCS$2z;@*U0!h3|$YP1vu>TS6ObeZOzkP-7X-
zAUvLPgUXLz?$SYe76E4v?>GVM=BEN9^_>dNH@CEvfCYA&`ONGbLx!M<W0KF(k2F}@
z)3C6fWiygaPc#OiLXMvsBiTtV85cAE?J6zLT~(25J($m!(T@iB2hLaQ)=H1=Z^{~X
z;00&R@9{nwqmB4J;<JMbCx(TX%P~$~BkV5?ub&nS4;R9Q{dpdjUJOt6_)gnhgF?Na
z$JiQA{gUG^P=Y3!<fBJck&3lHb5jkpR5jDW^qh;Ye`i%3Y@F<ItS6fpDtg_X{-L7o
z#N%f<AMwI96kf<7^rLOd-NM0{nHjQG>QAq^m=}%hhY3_)TXQ8~8o;adVbWzfuR!*U
z4KxrVS(1#v>}SyfZ<Bkv@SE93*S~%`=ZUcMuYKROUNoHgkn}02?2Eegl;n)I$IpRN
z*6&9yqV%$g`A0K>QrWw8`#!{<edTh=u<;?o+g3C$?r2$uME;!YNBj@MJ$P*0h<CS3
zL)7Fc@tyE7>HPURvZ-3{-1|2jVbpD(Z8P<(yG&n~Ip__=fObY#*g;+*>E#;jg|4=a
z-D`x6g@SC(J@GA%Iu%P8^|T68z{vUr>~i5)O{gXVE{_BjBEpTpCX+VQ+!Ok(ZzWah
z`#~O_W}lemV^hO5Vn?gDY-b-hJ6TA6BBU8<ea1shF}n9uax3!l&aaCW!v@O7N8K`o
z5(IMZXD``ae;XW&*=9$~O#Ga3@y4ZmhMC=rvozJ}W)EAx%4q&ou9G;pelharOtM>`
z%{*f+cAEn+)BCb|<NK)-8QxJN?WAzQP_#jQ;+k!cySWp^`PYa@sSWVq*wy@LR&%5Y
zjtvD1@oIJs4>oTYULf2cE?@c*7p5)8KJhz?K+jQ!|3%HLOw$;;EQaB{fWVBTzWNQM
z0wzbJ{LqM*oUM@5=@zRGgw)&mS1?*xL#zRROiuH7-CO52A1VB}i2l~Y&gQo+bm-A~
zVpNrY^{%VVu=ljVw2LUUP{TI|%sxc&_{$Q!Pe8%jxSuwWEhSf667FQao}>9$5X^?5
zj~YL8{i845RPGl|F&fpxYIxIQpEE^MI%p+5#*Y&*lSJ*kbZj<R!E?8hwU&Zhv!K-{
z&-7rqK$U!IqLx%tgG)4{+VMhOu=ZdtL7#ClrCQ2b)54FgM?r+2={m><lS~Q<HAk{F
zV!t2PoIWI56Z76>eKomC!)8@r=pHIMw`Fq;ep>#~bML{3QAgh5l~U5#LGLeZui92$
z-`M2ie`M-B`e-s_&-|=5J`rn22Yk(w*8w99x}fdx)b~(uC1m`uZU^~5v#W6yX|+1n
z&@{5E<-pUHr$vMC^2Ajbd~Nrg!yH1$p&7UKvq|wwXypy<DRZj7&s>7pmy8wWe<z5W
zD|q>DxYv3{yrhl@5(sc4@ggujbrJ$}Khj&2WNF|&vaxHH`BQFU05*|Ob4bGZl-=~V
zWA#8!qiu23O%j)@tx3}dtVaSVh30w<_um=?ea_o>FhJRNj~ZKH|8qx#ZRnY28?)Xq
zLNtbIV9EF({OjTzlb)Z9n0fGh$77T%%%`dJl`B7xe|kcXYe&JFY1>zh`|ZS1o2uw%
zjyK6>2VRk3wp3{0dU*YZuTmRjKA)1q#VIqGH~|y9V25kgix)gvYVcRM3*)KTc@)?a
z3!kZ2sZ;R~$7sb9|LN8VzIlseK?Q{moDuu=h^FZwT&@uK#DmOOd9RlUqQX;}aO8O5
zspuMqSNbDylpJLS9Yi@gw<m?(E*5Bsleikd#BHgb#oONdJ=tECYtNPFi_3%LJm+r4
z22T^kF~f6>!4KVZ0tsiea<$F)J4ZHtj_Y9YW^J{p`giI6sEYhA)f3!2^KRTPk3DI%
z1i^~CJ<q0$o+w0~igjID!r)JB&;XAxR}Ytcc-Yke0gy97e+T?yIq@s*wkKCs<H0;x
z?{{ERr=M*ADnDhWqy!NfFpyh_Utas-lfztg$L!kTBgRK9um@RQ^u^4?@xY2GgPao>
zcHJiKOnF?M(BLTQ#+k#4*Sd1fln$&BU!goJmh8F>S45y~HMWVBR~8-f`bn`1)havR
zAC#T>oVeuTEMbWO%blM0!ToAq4ks~pB^+T#edgV~@12gRVA*MYyfXxQxcK+MY_<$4
zPO$S<(8tkX!M<$O?RU1OKIKV{q{C6$k1BL3%YiK$(Iugv`h79tz65HlxxFM|XXi80
z?l#km)v;3%5e$su!cnknhM*``u4}`sv>^h#flSS$B=+%~SbGT^Y0rEK@xl!hz8(vV
zoamU+n@Okvr8vrm^dC)<x-h|_L2dFg@2*`(P{T%aodkpGOQOaKybL$_8sDH@DO_C6
z{<V5yejzP5D$9$%SPv@!7ytIhlxRU2g^wMVMmO4f(h1!wEAMIWkXBLRQ+ReSKPBiE
zHLypM!NrNs{DRJ58ap1_AacL*jMjse02C=t%Zml4cF8V&Y(1H@asHa>0M!}Sq*|}z
zPDOU!BkcL{aZh9U>I?n?KP5G8-I%lg%@wsphGqmYf{qBxxxN%?Y$)cw%=xsS*GXL_
zpNS?VvS{xeXLdBmT-dt5L6j(Dr?;@;)pd-Uf|Nr-jg{#~xeGB~<=C;(1?TAPIwr;C
z`L93*iQ=-oR<Sbqh;XzI;w4#=R!Ut$m@r)H4Jr?U{vwqQY2f1IANZbUb`CPq34bZi
zH`C7lIH2lyb(`gr@%DvJoHuXV)enoI`ckQ}>S-adzfe;dr#J7z2FifsBi*}G&l_%B
zolmSA4xxgY6ExRiQ<JBDOz%|zh80i)?~B$XwGem6v0(+flmirfkEyY;Y2oNwt8lqL
z*TqQ}UleezugbT_u;8xhb;N>!sQC&@hB#XVgp?b#s}1}-7kEk%wG>F0!iAH<vJu*?
zKo<@C_h3_%N{JP**byRT(3f>4mw9M8-|ZXQk>eF1u0jYqRb+FEthsAiO{*Y2FTWG;
zyFiLi%3ZXv2Dct#pQI;Z_}(<9fzq3mZwMNCLr{Z@CWhO!p=NeuVA;kngw?Ju(wcte
zDjYYAgy}_Z^CIjho%nUcK;}F_y!4J;Q-5i%+yVxlqOJO?fBi&Kv1;-o|IOWg<muOc
zfXSR}eH)Zdwcz4a@Y?nD{PCo>s=4t}eN^&(^7*s@U<?;d2Fr#Y@+q<Ohw{R*FQeY!
zxFRDr;@-wzF3Nl`GXK!o@2x!(8opqJ!k^=pM+qXup{WKc@p^t*>9e6sL$w4_=bdi5
zNtf;1mi0rW76!ODQL=7y{6G~G%xGOwFYE9*9J8_c)em!^VGYzXx$YCYDjl9d_31`m
zhY2h2&OGQ`ujdJ|8#Wc^_x5-CAgAyB^-+%~)bL!cK6f2t+dsy!k;AfKc}p`oZwj&q
zl28c9<r|_n7hR$klN+aKNRGJ<Ba<)gN$62+c){z+g1Gw0{v3v??-ezc1%H=vN}4w4
z;_v4mHgsw((PcuHS<XLI%c~TO(N7Z5^D!v*zZRpFs20h&ait_Zt5260ITGzBg0O@0
zFO6&=(8r&SPlfI(T6agC3Y!;^wyu^-LfSv7UH{=JNcC%aqxG7N>+kv*i!QttEb$Uc
z%j#!L3nN^dZIxk51%^|U%#qGkizrQ~ejb>!R6@`;;RyCy5tJYfluik$%~>eLKUN^a
z{fyj&)#Jj+VayLqj%}}aqzn6D7KJtmWIrqS3UwR#6YTkLZ@PV})$(k52+KtLO0rCF
z@$;)!<{*zF-|Fm0-RVfFHA})@ZUx&kGjr7R7+7BmHTGk(4hev#seTqrvXlCu3R6AM
zZhd(}<?3c9aYisFD1^a2+{%qanOz-wTkA4XUTg}yDCoKj{)pa@*UOIu_f;ifA<@($
zw5&A(4f5xgE4ABJ*JXY(t7%_4qreAI_^1O07;sHst*hwrLgV{N_(&%c`WFyS|9Am#
zQN3p7H@yy2Z!n#=7a{3r2F;@!bkCK(uPs+q%-sosrrhWCs$;=9)j}0JT^_Kr3!8O~
zOixw<8fAEb;91fA_-Yb7Eq3*S+?>JDt)TgWx!U!`jh1@thPBMt%Vjp@Unm}xScoAo
z$g}qRaYSFr6s8phn?u+UBgefn_M@_-kvW&Ect2|zwJL271lLtr?Hb_ZNMXz=nG)zZ
z89iH=D~HF!pJSYE#w9|cD8{4chYDQ;YCv%&czmHV)r=d$E?N{b&MEPr8i`D~ZT9Wz
z<dPa6ApF7{(n40I20HOA2%Kl&{e!B){$2m@%S&$v|MVdD6Bbw0NrCU%2PCRw_z>i>
zDXikL-S^cBtA(nDBz7!ih8U#4XJkCwhXpeJ`Y@Rn992Nxwp9C@aY1?c4f~1PJb~gq
zBfp~jco25nW4gL$>kv4Wze8n}_A<W)lj{Cd^7HLKuoeEg#uCnXX0LNMy4ws}i7>8R
zuTc1z983gx4K4O=L!}2znfYnu#tLxIdjRP)`gB5_5?uRR&%(J&4+Ia%Nip5myl$R)
zKP)(UtVZC<yG6C&AG6Jcu%ll?;y*6cOc1H1b%|3f+txn%a;KU9c&Przxg)ze+J4(c
z-Nn)9?TgTW>+VnzdaC#|GM61c*G#dWD1iy3Z~yW|^2w5=G{5o5Ga#&29RtoOeRk9!
z$7=G12*SpP_l=`C<*6iUE>|x!f>yTzgDWrUyKnprz{!!on6cmZ5)D9>T;xY;YQ6|X
z3T7@~VB=xgPdpS4b`cA*C`|B};!PeHiq6Uq9N3;)c{>>Mo;~*67c+2w@ZnRLh39qB
zsjKNx+mO<(2(uT?Iz{p^0v*?;8h}zIiYs1VzOpC$ys<G~JUm_Iz4vg55wWFwl`gW+
zpBnqa^&)tw@5?m9Y!RpuYfe`7fVSxCIDZw{951eqSJvhkIdwfn;lf>LaOWRZ0#~~h
zc|?-8>FyOPA9oJ_wnG|)?D#lv&X_oIcnFv5`)e5VO9Ua|oxYc=)rf>jOqrez#_O)_
zV9!L8yq~WhoTfO~eG!RLP181i=gjMMwW$Zbw-RS_Q`u}p<vB<Br-|dBD0U26rIY{>
z91lCIyY0Ak?{T}I^V{c6^yt4sRr(aBqc@q*cmDWKKD&Wv*V?vdeobUAO6+)Oiv!dE
zO>tJO2jWkateyVcPUNpO3gPug%g8i%nlTFdN~z53qC=(SGbp%|6IB7e(qZ{=rQg|J
z{*F1~KC{I#$zF&+%^(xqW-Bm}+@k$L*Qwz==E1Y_!=%HDioN?XBOuy|yD*c%g8?%C
zAS5`=nUE@(1GW+p%u^3hu%OwnCj2m7MIiy)Zg6$uWcnza>v_DUfaLE{0)L+k+<DGB
ztTt;x^FduVP-WX#=4;}W(NfNp`1EucR}%*5sVBAtH$D86tz7TG(kO0{t~qFqTslK-
zjZz7V<{j2ryab=2y_HLfH{kNr;Yw7$)eL0z8E15Yy$-*sPnub)<Su<p9X)raQVh}O
zNsaY_oT<fo&v^(X_(&`QqvPK%k3dfng<k9OB*_0oZ2S^8?6+tfrh>T={|n9ya<a;;
z<V^I^Z%=#+7yAsu$>zt1ObfzOy_CA{1bz5l$Xc%xI1){DYnq`774kMIYbOwl?QRI*
z1>yajzumvdHMJs87@CYpH25yA1*ETsRJL0Oh4T;BNqnn&?%%;%JV}ntClDbwi*Ux;
zmM+yOmIrq`mPi()Q5dn>+@LOYtmP?Rc7kClsi{qG#TX~thzr!i>&xBZel|kEE`N+4
zD+0$fu+))w2W-DlqJxbr<t<)l?720{L<^oe@12W0$^N*!bOgt-L3Ty%)oY8I?jSLL
zrYPyL@&4w#=fLL_*zSGU_g`g~)^c@EkpxMMEG2w|9Nw{bm+GOLZci~65|48g8Z8b~
z|DHrlW@qkM^XTenO<oONf1&*tfPc>de31UT(t$W@9Cwt)>O;x!mtRD9RK#DhvD2%2
z?AhNcd`?5RxBMqz5AGwZ>iQ!iL;Ke5XauQVehdh>PPF)Q55)3(b(XA^&?mv?5r`<|
zuOf`$7><U@(8uQH1j7rL*-o&wAY%><p5mCpwOnXC4I~Xf{2%$-T375p&T*m0pSAW;
z>s<$xtL&l%9t!c%f#5f$g#tc85@a7zurHE8W)>GLacS^6Z`U1V;njAA_JDH<!-S+M
z>Bovy`d+UeoF|8Ui`qVqz>y0(aQ2IBeQkTM)6H@D__qB-HM<LA)wAOdCacXV4Wx4^
z3_u<mgqtFUEk~_p`7~)Q%DG+FgfWjHU0a^yoM7ZeA6=OCKkU3poH144IwT5+VSTvc
zGw7=@AECpWQy<ufMuxk;I#-HBWXfVPw+c+w3Vuc+4M~i3Sl360_%C<tm~Sc)We9PC
z3wkVZoE#+5isWQeoly?kFubUFKw~#|p=iTX;H2#moGpsBEnVAQDBGz@y~B<toI49C
z>k||zS&r!xhzz*y$NKisz(<1Ski*SFYxe?9D6uPQH=N9ZPM*Izx}ffS4SC&rCX$`s
z`#Sh`<AS!Y(Ntsv@quc#%IC)h#?78Na&r&lz7_EnB4(;Kd27UsLryea<HkZ|quH@!
z8BLsEP{}}M#~e4U$J&n7Pa;NPnkX?NEUs2r_Hev9PN06JBl@B5Hq&Q5_LFSLfNc<l
zJ|`eWA+cNSj|7C>zq^nnPKB&)h{t?18Ykv%_kF2E7W!<B6!nBi`A2djhjXY<$s8G$
zz=E5ifVon%_FEvsOr9!(-0jHR-BB_-!)kew4XfLalr5I;m|M|MuPn>9M^3u%DL089
zNc@%Pg!4z<02YqTz{lW9G7u>LCW@M$huh5)`I9L$kE7$-^@d-lFr>Y|$8GqkooB1C
zU|SQr&5yuIG`e|amL`>LQ#_yscLpYj-G;n{!EbsyH4-#Ck&d)@la2#*OSw<338;kI
zMg4<PEeQIwi&!#QooFWIea&tS*+;zDV{6xks-*q$+(wnAdS&6`5}N4Cv`C~K)(_%x
zSv3J0a09P;T$8+9ua7;x7Acr15q!>-61M5E+Y|L<_J`!|tekQ?LE^7c0Y}CSNP7|?
zjA_M0b}bYSE~Xm)bSn&?LBIw@fXZF(dP?*{$BfwFcGjg67lSDV*WE$|S^g#^kQ<%d
zZU=hL$*CaJUi)a9{*}$rUy0H-86kvEaU-O(K&}W<$J%vXYLchx{wa(bP15H~jV&H0
zDN9bV1vG?vzf+0{mUPIO0Ko4(C{L_sMLJbJKL6tVGpPxBy<U3s)!t>2yY71IF+eKz
zD^7$5znOEDRqFofvVX1+W~%2WcV7`b<B!Dn>16mwxzWeZqmDvjXu~oRyrAdq4Mhq5
z1SRn8=k6^LOU0bqbBn!Qn~B;?xS`~ih}wfrV-mZmTRwvtkF8Hvfb5OZvGrzcIBgnY
zK@^1%;=b7@7>EydO3AhOc}#FGx4gFbF<^|F?v1N{3g>i8P68plhN;q?MU1QM-N)3^
zN?aZi<{ItbZ>))R@UoUAecXSjTVX_8ezU`p3^OEcC=mOCN*^l#$CRu)&uYE&O`6Rw
z<RGXk9g@LEKs&xI**dYqzbxAio8XaZyZt5Dj+bxe$wd{piGZvhQ~@2Su)O1zPLm9I
z5#azSq5;xAV`|{PX@2QQ<q>-D)L*ernCs5cx0tK;=c^^8E83QA1)zY7HPwajc<YDP
z3qaHg(%T7HC9&IoGpPZQUUf8d8Yk}u&TH!0Ls}1!(6xEjRn3k2@1X@UTOmNv2I3yR
zcXTUD-uM*HO5>Nj%KDfu>)q%q))1b_VE?Sp%}zrvKN@5^xcxSXwP06EOWAz?2KR?!
zj^W9Jlh&t_pEO|2VozA3Y^2DfdQr7Y!*4?~Y3}9}CjE=Ye39*vv!RFJ!(O%Pw?y9B
zDE+a#5OK-07<bO|eV%-y1H1Q{Di=)mA~<g=muqfJg88_?JcyKx_M=DO&&}s2R=&?o
ze&Ba0s}+`H9-JJV&0-azG>QU>u0i*>q#4O&{*vL9FJS*{dmu0`B{>mTumByXpjl=d
za$?K1LlC`Y@eAJKU_g4l_(KgGku#}-GM5}8wah-6;8^&A>9J%Nv~E3)lbGmE;f*C#
zIwXbLMVDtCTvof2&(qUurP0T7OfPSHc!4G7o|idt<yF2G>2+(NVZMW5<90;TMdw9{
zd(Yk1)w?C(Fmc!d9}0_f|KWA4+*9vrKE`>Zx_%t_ZX!;_I5E43JBcOo7L_9^#6L@(
zLi*d2oX~;irLC6FBh&)6uJGeYGoGLU@dt!V+)jX3U6b)QcwilUgMAiv``Al3&TPxa
zRYjF3<K97T+NC4A2>r*w+^=bI8T!WGTurj6&T#+mk9t2VqfJ;lD3JJQIQChlF#*+I
zT7Ub={zF@dYFaJ3!H=cxkwv_f19G?Y9vwu_{n8ETbY+Iy5%p<PW8IC?f5|4@ZFzm%
z&Oa6qo8IoDt7=C~hS7M${Il-FC7*iX7oWw5UkRsOOmD5IukIwYuR4S1)1<~)jCESm
z!S#mT=?*^S736oD>li!cxiuIPw{ofEhH;LZeo3)f(RGUDF{HTIdppK8PhU9^pnV-f
zjiuukQv&Y#DxI3N?`d>s%6p40o~F`eeL<scPcAaHFLIFZ)DU2@epx5hhTuM<bK4JS
zn>JBNmK3g+<VP_6(e=28anE-yJ3hHh9o3gcX6$*c<YGm=1H_-gn6a<Hd9h(+HcIf9
zD*3b5ymu6g2P%a9q^=AQ_o-83HN<V8<7_g?#2dqSzDBBrED;TvGLXm;#}@yU_Exc(
zruz>~VfNBm&l{)t_ZF;;Op=v5KF*7?@N*~u!8dMspPGEWS0*eEMqVfrSuikPa;`3T
zKPp_%fBdb=)m+lB^1_v{1%|s{vomECer*-O$1i^}{9k<cXJp$;x~%fSK}VIpctcHW
z<NY>MAAit%`~k=NX`qPzn%7=(|7oS9NI=B<X*ZWbk`eNZR5bWpdN;<62bc_J20dCD
zfY0!~V#GE%trf+9@drRHqGn4P3gOP=JEzC$>JnRIY&Tw}VL*%hrUb0{wQ|LC-e|xc
zNaPU1XRh}(i9AaJA1tpS@Wf}NiE9}Fw302Wu1)re=GN7wH+pIcZkts0We?<Htm7_S
z8~B__do0yh-9jX5Ye<;@cHs+LC@f6Fe_{TWfs<`U8GmybxNnBy?Omv2S?wJ=yw_`W
z*PGOnM&ud@f>TqpO1_^_AvHKurR#FSg(G0KO1`Pb;hM%v0~XH0+R5ljj3LsM6<8P)
zln}%cWc#rT0pIXWdoHg-2Sv~qo*t3HmJxk7se#ZKKSl_~U!2B4owvYUJ0v)$Qsrgo
zD7_a>0YgVJO&g+t^gr}(6m$NvY(8ai+Kdd<`O%HQ<R|&O(TQ9PcfVb8nXpfX?YosZ
zAd^eG2w%7ewb{&UB~_S#B*oVS3vC33A(WOB)5atBt&$8T6LAU0^0bi=OU&?Pis*}H
z(k=A`6>!#QRG_YPEzFTONx@%+CPCC`0VgA^9p8z3VH<&(dB|neyzu&uEgC@|(fVVm
zeUZ^;BYFR6<0y^JU7Oy*GJ8QicBogz&rv<6;0?{b++Ffh3jMc*p8kgp$QUi4&zaK5
z|8>h*AqiSC`uZCn5+V*?lyKw7?cjYksIhkrUQhVb4b<z{u-<xMFs~E;qMiP-JT_Uq
za@873ZywZmjp7K37qzp1oYv|(e5Wz*4p2^Z2q-n%b@j_8&4__|iw~rjh=39=c0JzO
z+{pDWJvu+)?4Al^MA(vrSxzPS#^M*x4@h{5fQeW3mrg3){STgb^S&Q>-?~tyN3%Qv
z_pSOboEU`_AxsV<Jl(2#UC@C|QDK%}OwXAJpx`XnZ7Kvh;U+<{;Nms++|*~xdOj*P
z)#kq$cA0>7HQf8Ep+m#>(yFH`UFE9^sC9D1))-NYJU;;gF8Nq;1$I!%Y+&xXR9xS!
zO8{fTRiid<{ZZH#@a#Rli>C$9eBB5^rbp2yPmSfixYsefLltzwx$^x<=L{L09E)RV
zLl}HQtNP2!@X!7=vwp@(*Ndy38%k<EJ&5FmVVH328DVH3kk^uaqsykm{-h#f&kEIj
zaFw*y+zw~>u!IIk1~nWTWf6jf{x;EI-}|exu-ugFmBO_X!PMTYcB_2IUulsof2%!E
zW^!ql5jb<Ge`qugaChPp|NP)&S_^?shPK-O`~!}=(Iub4G4CkfXbo~Mf74mu9WM@T
zpi7XEa#bl&4GK3DS&0;cmDUm=&6H$G;AxmJ*ru+}+v8kxnlTl|@wwNg#ns)92GA0W
zu!t(%d2-C}o8QquGRlt<frd%K)O2I^PUi>X8p-b`YPmJJN+h8rA7fqzW%tJN2DsbL
zizNT8H^$C?O*y2j?)P#aA*;o1Qy|cBf3pgz4taE&H>b%A-?G(tIPzyJ3B+AI|E|X?
z{Im&YE?MsNnn>9wcj(pQEAPjs5q7WzR_HXr(`XEBt`sd`J#{hak;B?uRlW;F))c+x
z^#gY<+|yZDv9b(x(V|d-vE!^DU3FEj+;ZT*B+6*2E<Kv)9qm$*c`Y%gxsk_O7w9~F
zSUielM=o1ghIt78#(;lNKHwVQGS@^i=c)VDQotAm;+072r;Zn87qjVICCP3(%-wd{
z76o^}DAo_EM$8wYH{0rrZ+A&sr3BL*Z*IJu{}i)RTieXn;4<$w^VGQ_sqtZAJqJ=e
zYwJfQ8c^v~M}hefGuZsG_nYsx%16zB#?n*5O~cbjOKx1I8%1{RrH@vioF2bUQ|_i&
znB+wH4~88-VBDCMmItqFNHjscsFPRQ%inE9LNU5g`-BuGP)GI~iF0ShorJrq4t-R<
zM8f|S1N>^kBPN0rQ?D}_NPg~Jc%D9mx^7Nn^Q=<&K|yw(7!E`Jw^|zGp_d?v9qOdw
z`1R^rPBf6iv=GD7V(fpt{=O$Rbs<tnYmCR#Tc}T=RExodcEV);k}|iMZsF%cH*!gG
z>;hd;s<P65n!{%jI7GHg=w5ZGb42e*X*j>UgB<zo@J+lSOIJ0zizG^n4-j8dM=b8j
zLe9)~W}pvt-oB4g-1?p{l{W3$N|Jxdf3SS-1*N+rqvU1HwI#YyyBEYpw1IaneyZHT
z-nYe#5S1bp&Z98I5?R+MA1vnP_LO?QcOY7dZHx$wZ}@c6_aJV9d#^6Zyta`}uOKV~
z@V9|4@~$Y%g)@a*Ds{(m?@R<Fx2SG&RAw;tT~&VJ+TP&uiv`0<^5s2N@KBKpys9S7
zSA~{&sr2%rfRmm8C}H$y;g7$f&3j~M#=T?4tEBR^TW~91T_-1ggOL29d)<lKxt%mX
z=ZjO{52?VRk4Be}{KIF=__U^@R}!=50(obL&;RP@im|>9n+dj7HcsdMvAt|o8?SWI
z$?z+A2R?FF5fzs{hy)VQKF%3eyUq7&6r^L!g=?=6=)UJ-zjsLUPJ%P6)69|BJKmA)
zgB#DYze&%w$8}ax%?#a|bypkc{do71sb&l{_S!$pYpJm!WHye1=E?$fUVlz?w+Jpn
zDgsC~1H;dLWS1#g5BBFUn@Kjhl;P$wPtwNTst^o}X|mG`y8>+D<^MeD{NGxLC*_!G
z|DDfBf4TlhG1i&-m>?@A|BjL3m=h=&w`~(F@vqh}r}-msZz4Zx%rDypKR^CLhTeY_
z!Gt-IQUdEZImpWR@R54bOXQT<E6F^1#{?8yKj}3L{sJUj1=01EnHs#|13eEZ=GNt-
zHcRpN(;AnuxA|=6Z}z{Esw0Cn$84WNpovg;jirmQaZSH(+fRbPIg{PwrOl#CYC(mC
zbpa{xUb*kpa}}#QDaDTjFrjB2yw!flI}^!o`e!v`=ClapaVgHuR(!dd<zLU;%N=MU
z`cuO>l>uwbLvcQMV7&MvQZL#MViO~@3+gO&lshjkUWTXff4IwnJx(UxB+yc6=FNRm
zV>O)^Rr(}JH=Wbi$O$&6fkd?^h?|z%=>;Q>?0WS`)u7;0qr;CH_NP{yNWv8!wdhO1
zJ>0`PYfc(7FJ9rft)aCljzJzt>=`p6E|{wfIX|mg12xw2869<*QX?)z$MwTeMZv+d
zxznyrgN|KMo}L+Jnh!j+EAZOb(m!if9loItK3ZKO;_rcc3^FrG*JnkFAFGpiGq1}g
zE--#ZqkKAU7TK}QNK=^4+H*}>v`mHd&-XMpf11o2QV?Ol4^H5~jKVgZ$Gy#9Vo!2d
zGjAhy1XpgrHiJJ`n<{IwGhAEsIgb@68p;zhwrs7RY0vh2eeH!q(Yn|84ucEx|41L>
z4nx^~alSaC-jif`<CPm7@eW1=iLWpgxuP{hShBQs^6kzkl(JcMMn-Y?C!aS}dhw3Z
z`vq8rm11Ne3#ooLS{w@+VN17ZPS9Zw55lq{+y#NXm7vG4L-N5C9P|CqA#<KZHMAn>
zI3)Ut4hL1|TEoDvgz>piet?*{07rN46(v4d`ZRwjD$PLc!}nyB9p1r=u65_^eGu>&
z<*6kH$4obFW4z1nwwDfdT$O29yid#1r>=seIkd`)@h}^Qqt9$8u<dV=tSuTWsyH3@
zwb>e_$`fGf@PkP2^F=8MZxVDUU!N@9{2(oeym#>`%(x`hU$TO-NP(%?`xbQXffAPX
z{3%#-E7fV<7U1f}*#N6s7x4VBk-)xh<e2pz5=%#P^A$&anDDep!%v+8qYed{lJ#}x
zU?B+r^)mHsU+%Xb^Vz*RTn)s!IfcKflb&qOD*pU}8$@CrmmOX)+<qg|k#m5pXP;Nf
z;Yj!8E*p(od14+9prebi%Uq!8<h!*s^F$j}=Hfa@cX7+HZ8gmXca2H8)^+yB&u6T<
zhYHH3->&s5J>y9E3m9L^e|t#{WY2u((Kr%AYECX+e46+$<oZ<T+mr*O=+RK*aUiAB
z!hJF!dndcKeFLYkn?0S#w)poSjCFrFuCNnnP-c>vzDVIs|F@YbJ5L(xvVY>gx#)98
z4QnrZ^r=9<^$>ykt<&2rNU8|R9%DzxYS;SJIto>p(0;8cAnkUlI>zs;n=8`0mSFzW
zniF&*yk2?;ftLH_hEo=9+iC}<WM4u$2WD5U+=LftOGlFTvZ&X=>*xO1oX!;NkXGk>
zy!~$<`>E8U?b}pt6{W2DgDXLAmX(QMAsyD}5Rao+-ok=&r=|fH$V+1QKN-Z=C$`G#
zQNj{$N!l@Bi8DN)6<?!{_EIEHJCi3{P)O-m0+^(zqVSuP*k<BwZ;~sPrN6w{I7Mbn
zLObasCBzYxu(NUJJhbJfbZ0&0SXdsrbu3mB-Bfq)8bI&g`w%f$()IM!qn(^yo!gDt
zH~wcxod2$pTNMLp?}a{+z>*%=>L-XK1c2r!t}H<*CM>@~PA*<`=<0_QpC|&8UI*0m
zi(^3R!kr7S>^Z{~GMJg$*XE0NpE~Iny;nZGME4@7BwZlpmvDj+G>b%Lc%uP}+$*q2
zOqq`X=XWBn!NwcC7kRyYeK=D1v`xz#_s%|FK0<E2jhB}RIo}@*gmK|eZw%l#M(jYb
z%xtbnPWFOO%OKOm{_p%IpLiYdPbMNryMnT7=Sn4Q8kXzu1R?$<4EV$>ftoS|eN^=p
z;8NhK(Af%)B6I-GFMC+Z!r_WSQc1Dk#?7t~JvRR2Ym^+!+T5?O+tB%!6c~KO|9PBH
zWJPlnU=HWv_U1HO^RdwP&}^mUxg^q3%xiV?+q^*W*V42S#uERZPX=$;s?zle<MK#h
zYR?~)6*B?V_l$5{Ip3&q{Sn1Wi3dDX_soJb_2~OkC#>G$_3v3YIVh|*{*Df`B#@s@
zV_In8Y473?I8~U{U)GcfU6^?5Uh!q;?8L0$M@F)Vfd#6d$g$^-z$4=i-cLK?ps5J!
z*)qT*W;Ce!F)zvT{j^%SUEBGf6AeU2qSC*;Jqnp+{&b;(2|1m*a6kH4s`O_wB-)mS
z<do`cB_Qpc3IfyoT6aj#DDJoiFb}gwly^K2NSgX%U{WbmS+D<+*tqxaM`<Cxr*->p
zJ$I?G7tZ2-_3_(|pD(2{{0ZwmdhK2X<~@vU9s96$J;xG7lX_r`-LnQ%I(g2S{s+%u
z<oozyjd1DhzLWexNBajlpf6psq9RnZt_dX8JbMb3zngz<51sm<1Iq>k4%{(h<7YJ>
z@fL%0xND<8hWV*38K%YIb0F2uy)XUe2N9o3!wPvwFTiClx5!>$g|-(mBGEurO9+T?
z<V;@8xjIY`fZ18aI#b#45IQb^s_4u5*rC@(ZtHL0;B+4&i-M=!aDlnHTE-sD_O8*7
z<bjM7Q`6yB4KL9JVilxKv+(o$nAD~NC$B;Y8x)2^k1`rKeS8%uGDG-s0lR<XKev4z
zM-O7kH~hhCk)4TfbM>ajbVO?mc16If`{>(cm(5P9v$>{lF+KLn2BGJ3+kMnX!!n-G
zG@3xxMv7J1cu^i+uJQO!+3S42)S4S2pW;dUdctvX2-t_&I=CKPNut%};i)1QO#EkL
zGBL!UtAX)#R`T|WhVhq@)8ti6*RO?f;NTyG!X>tAZEg(x;?=Y-0ry|nd6;<Uh!6tD
zi*W2R80G^nh$kFPFrPM=KV>sy+(U!V0D91s^tqomu}|cpn_`~R%p<s-QoXeB<tJc#
zw|CnmEEY+ZdF@sAJkAOM<Ht>3((J!1sbijCx%bSs;~YQ2PKxjgi5FJmw5(679`Y(w
zNc5H#uDM1ITPB7k_E_3Gq=4|*CQV~2fQcj57(NdlS-;Tw8e|)tH2%fi6<k$#_TiS^
z>mRXyx#!x?&k(537EyStEWo^XNZtmY^IpLd3oy3vBZ$5Mh4JLGYjF4?;r2?=@Q_|I
zijf-oFL(egFu#5Cky<&>Y8siQgSI=R0=H3ta)b?q(t8L`A<nh(&w8+UQgEOMU*Lwe
z|4KGAwm99Y;(KS6>w2CXO*IG4p63K{t4ER7JYTE{ym|^BucRM=4)90$(IRk(q8_kj
zfyZ3k&m$IN*GaXS7_jqU{)VtxZhj^~e0<d9=Yqxcm|XsG&zEJt-CHOwSTSd0p@E7P
z4_K`-Mi@U-kUiy^G60w4dJ9KL5ollk*vlSoa-_R@U9O4^(sZLRSM+S60log{b#2?V
z90583gvtl&0J)yag;5h43+j({F3J-T_%<FC`FYBW-p0tDkG`0GyG$He&&7X52_%=!
ziF6rN)~}cf?)7J`e-u#sXspq9@qOQp^|Evsh`ylh>5);B{r=JPm{q{B?@$%rc`pwX
zOeV^Y4uQMBXAK?#r$XVpVJ9Zd(k(-B*vunGI#_LSX_0&*Lh7RST>b+~)ZGHAmmD$%
zQs2Ko2SwovyeJIIU>kTFnww*|z`|7d*Y(0eE($xL<6TaA<vRj<f#g!S@pPYvTT@>M
zW-oyIL*u)VRsj+@<e9vEr5?rK^ewgB8QUaPX?CmK#ZkBSUoypk`h!isg%`P>T|-6o
zZ9Z3>8wQ&MmW%>4a5hq4{<4FUlt2_m&5B=VwYAm*7HJL&v0q<m=&Bq@pn;3t-Dn^_
z(nyY8Ak2%NGcimm&%ba)O&wOqK^%HX`}a!VWl<~L@1Ju?u=%tzk?@Q{G&pC}5%Aci
zdEtxBMYK(DUIayzze(ewUu}Y_?1~eaxKpF{OV-hfi&@0~u7m?}3I>e(Hza{SWuEI}
zO85(Uz-!K0Y%$uH>uLA`B!ZU!hQ`Q}!SQdU;I*C031Ke<R<rCM^@(EqIHTJirQVJo
z5T(Y(ADgkosGIiHnhXnrnMksX5;PF5XC-0u;#m@@^_{oBXK{HIE=3P^sNnTapP8{S
zY8dy`nNVY)BZvaf6$}a_Cg|<QrG}q>-fc<$aOVR-ba7Wl2q}_O6_<~u(V&K;&k(xe
zkSl;!gQ-dA|Cuu^Z!1mCJRUwTxGurjAq>;kZmYi8EC*dZ;n!6H*)#H@Ny{nbRCuZ*
z(+4moKO0TpWa-9e7;Hh+ZT4Wv4YTnF#YA#YfLIVj0Xi+%L3_B^m2Z3UPgMNmpg{j_
zGnO=xuE|-y^v#Z8d3(`ap0}AJkrEM|3$=OCjHIshYE1A=cbpXxHWR(o7i6iBbsG8^
zn_^Bb6p84W8&0CHc=vWYuqUEl)btgt%u*FE9BuRc$!~abW_si-`P>Wl#+yWl8R$S4
zq*o-DYuE_E8m#LwFP+GhffBmt50B1m)zv|I-~_q9BkD?S(P5WFIxpY}Qv9|`pqc;U
z!4mV@rj`Ya?Edua7Y3}sgBL-WoM!urPodG|zf3+=GPpuFb13>use!bg5qrmpHyJ+s
zeO=JWMQ&TW8f*&46S|TFinfIlY}Ej7sS+KQKzFufMUCEXsFEZ^-o0OXiM=kmj{6#I
z)xq>4X|5?)*826vlorcUJ_4w*2!0nO;G|aNd+{JrAG^8%<1R6hW@EcOigZPTPc>zH
zNV_XipM`OY+0SXeU;#HqmK=^IlJ9)D7+DO@P?#(2HHx~~`68)e4T<R?#KPG~(7=@B
zKoQwzNewtZtcZ}FF7abRZL{BfyamJcM2g5cOS%atdKe~6(qut*$NxPGpeK85Tf+m=
z$KKLYW9j+5l|U@cVapA65MEhxakBi*1HD%y!3<bNx+q>+EZU`r_%Y?YjY)w+a`p@M
zAS@`tghEmwC7R7?v14^MCv4Ax$W5BaEJOMnJ{jCaVMM^qFN<O8+|?C^vOEI@RFYUi
zI&KOHOS?Xb#N|uwF@;Z%h}5!r)v`g6Q)Q_hR%WMy6fegh0Y{)o`>dgPCqGh+9A6ET
zq~9=${)xjbUcmMge95n4!lw1VAj7!#+*84NiLj2Mu!K?EF{J$){NM?^sAJ)+_qVdw
zI1zgxAnFXAPzi#kT{2n1?8W^Nh>r_0?E6auPa|FsLt&Zgl(08|R|!+7@7$iSo2Spc
z=80e!ec)nTFd8&uS4cAef(u6W930&f8XaZ=6fBjmH%6~EMT%xnGq|h>q<~GCqiDD|
z(~^#H&Ut96ien>&rNu16osf7PSmTA_Cvr8rCAU}Q7*>;>>ri7AAd+|f1Jj$CLN0Ry
z%{}P?5_PjGBP>4SxruH+Azgp{)qVK?0!h8G<^{&XcPn`Cy$$Yx`Lpy7D;Q#4iX3(>
zk-!$8PZdXX-^Bu_Ga+%;r356037PPbqa(e{LLh>`w4l(=x9`O?TyQn7sd^b9@kOjF
zrCOB%3aRxdV?gOkN#!JhE?iHM%#PBp%`GPNh6x$=kSS{Ced8U`AFf()beF2y!iAww
z2(}=O!cv}+JLtk(-?H`&Q;h2%Jkg+Wt03Kyo`KQoTanQ<kJlksc#+Z}IUE<ANbp4B
zdF8fh(+Z6Ls_FkO{eY{_RQcq^4+a@<Wq-)5%%N$io8D<O_&_63d>xb*M4VXEJ>Aw6
ztQ(T43Nq1tA?t|$eb9NCPDkt2*T(>wm1IBxt6wv<$|*D>upo-QZHbxkqBpa0`66g1
ziNuwE^&I>jklhvp-M#vB<_u{uN{2i!=22u?ZO)b6vLW-ntFM9&?+5RU4Uuc;#5@|a
z@QX@Wv-tTO8eKb_wu;Vh^f2WBS^!^*+DmF1GB3Y6ZJwt-ztv>T=6@ot3vy}xAP@e)
zjqiiM!%@(sCk)Xuc-ot|zD&^}bU1<XuJNIUu?uNJ7{_j)cNPtHr40mIJ$s;lC&->{
zxVzeMg2&dk&2PDx+i#!3(a$$Uwzv*nX?g!2qTV}@>i7L0zt3@wy+=mILH16{cBpKT
zkx?Q$k-f4GvNMxCP8k^)C3_u3WE0AYG7Fj6oZnNg_vicj|Gw_~y03d(<8fctJ9>;a
zscXo!H8R6tA_NrDw}w!T<cPW9dqTB)DV+wt-}o>BQ>Ne_r!Vjfhdc1Ogb0(3&L_wx
zEh=n2kOLGef4=7=w<3AK-LkR7n5R00wcM*-Aw~&Ghn-{%Qwj&O)^1ub>5X<r^=M<u
zuR^14$o~x^BWwrD$*M?v-SBHwj>%37Rxg#**0!OH{TSgJjxO>R-6P&nF=2e<P{vT9
z*M+3Uu<|D;g9QkLx83!OPe>*I#;4yI3|V*F7_>C;M3KiYy!|`u!tQ|72jO#39WTOr
zYb3`g(?|#&T+pLT=|TZgrbtZuxX`0DUJWKcirmrzHd*6}Ogx#K%p)W&M{UhQ2UKvw
zs4?W{Km&S*OW=dFo<zySmHb?|UUgO7mGM{fm}(A+$dG>Fnom-Wq_A#`JG2h4U;M6F
z%yJV?$Evkwm|(?|-(DJ`$9>(XzbSpFr@c_IZ57z0X+%TN^RIPS1RTXAq?22mTf(F!
zPcENYR%J2z6z*D4Ps4aW%)sZ~t6DwG75-plaK%9oOcTXv+g;W<-TkaZkWeVd`oi!d
zez8(!sqZe~tnAdUr&=ov2TBw@7Sw>jhIGg(i0Va;L)^$=xKGn>(#RwR-U=)aK8pk`
zq^28xRK?{l`_yqOrju_impSDN3JCV`fe0bPL3ow?9VuPoNOrXC(-NKRik76@Vh5{7
zJ2s}i0Tn9uKO~Q>kOZsh-G`1W>LTHVYj)oQGUmm6a!c>SUOn1seX}yAWZrx<<_Ua9
z_0trVxhX1&KqkZL)*kasy2($?#F!b$vjA)}Axw|+zO^ByLL%+U)1`})I)64?dWfD~
zBP(_T-HCV$BXEhW-{y;$wuRg~venuX>tn1E!#OU+P;aB$C4KSa>8>SD4k87KZ8oec
z1n+<4OZ45dvh?cGH#H_7wwZn6p2lkTB>)HA7lez~h%u!7^T=ne(K^aj+>Ly1hRQ1O
zRos!nm)Ss4<o4Ig-Fj4OF9Mz3yUD@jli6L4)&%UYT$FL1S|z-w^lK0S;UWRUB+;|j
zB>l3`0#(lk*lb|fb|NVtZ?2ieWbUH1?w09eY1t{6CS5ypb{4bI+%{k;L7Gjt=mm}Z
zoD@TnB~JLulTxd-*$6TWfaB%ffGeL2ADMKPB^&Cp-S2v89<Uj7k{CJn=5*(b70XHv
z8^U&_&=@H-MuOtT2@=RcI;>p6zl6JTA|1Z24{MS!(}hA$u^%-YtDGjl-Ea@Ogyl`u
z-d+-xc<k`;Oq*0UCN4clJMyuGKDc*e+_H5c;RN!5UO=G3*x}eYd=FoWoc-V7!&F7v
zN0ADmm9N3{s|T1x_t~gShJNBN`;z1IsUc!&cxRjD&j!JMdaa?LSlpW&rSS3A?V(g7
z=>k4uU={wB;grluIufyVJ$mw{nyRk`Y?F_ELJq*uq3#R_G|}xcDai35FMCtD=gqeL
zTC-DoJpQK7$D6N)9bSGXzN_<~ceEm;f5tnE?~LSJeZt<bhOPABGkMNN`a^C#ms&fp
zxVMjbzP`@vP%80^`)@-=``=G5VfN<;6@CeAU^s#m6U|u+^y@j$HM<17Pbz)Ge2n0h
zhu@zt!>STS>+TU!z@)>r=@97X+wjDi!XWGw)|JPryl#Sd6pQ$~S4ag0-Uz&HD5<R<
zFJgdxL!Uz{G}D7x(sBw7OZPa9ZeZB)fnP~+I6&?8dEO3Y9${4Z37<~tNeI~&7?#is
zzRW!>Hf!x+L;B8YZH5K*YB?#<i;y!m_F?ABhL@k}S@E+&M35Oni$GKDNj~5P&Gvdt
zO0kb0ezZo3E#~e-TmOt>#%DqJ3M^zvNMg33h6xpLTrlDVDM}|e@$gSVw?YS9{a{O5
zBS@#&=PCY6>LpJ=`p@b^$K`TjmwG7$`CYk>(l<Te;>`H{3t-u~BpBx2@>HD$1AlrR
zAlJ*!1D@afD+C8s{?hz-Zt%8_Dpuzc-uvV3iTF%ye_`{&_j)t~^jN9rDTacTVFARY
z+0r+q(i*(F@O#<^yFtoie>1k)G60hoY&-9U>DVCj;@f{ce3TApM~HK90Q*U0z9Y-V
zk#1ff>FCtfQ84o9#>(>G#CDrI4f>CYpnFFsQ&juA@cXVxv3Ym0fiVSs8U`a)J|u=?
z)utXyESj4>AAUR$B0gIyjBBtxUgo(>f7q9TfBhR?;8dk(`;ERYK`MEI#i#^QE;-L(
z54#Q`pw?o#*G_^K)U_@>UhRm&B}(A$lAyg9aR<jy5mB;ieekh<7q0&|Efe6R-k?Jn
zG_W&`Wk#ZFa;WigD>9Ok&+Z+s#cQUlZ0}ORqW-a@I%SFu-2eN~c>EV<wgI4*c^2V%
zmsX@)o4n--;ZY>$IG5^>%4U?FhE`?V?|pncH;AFcHPyhM{eqdaqOQ$P-s9N`S0sY|
z%X6K}v>3IzOV{FBcbfICASd;UGbO(mhZLQs3XHlDm%?!|$+`cy(_<6z;QfPIkiO!(
zbOzr${9<xLyy3}xyH)Ks0i*l#TJX6`v!suu2-n_;3#N!pc00B^-C@hMLSWW{TCbc7
z<x1jK+boxd?)bP+l*g|g$J|(En5;s$jQ6Y^g_{)iHmXR&RrFyca^lX7!#b~?S_T%_
zW-#$N)`H>^Rb(A?lpMieiK5|I_oM`)5d4NHq1Kn+L?^s&rN5TVL;C0qogj*sc?XZP
zO-c3htN`a|3c^tP>&#d6f|fL&mprUJzIfU|hTc4U*oixyG&W%zV(|jW*SJ<*NB7@(
zK#YIAcbP@t=@JGY&OJ4HA;&g`+Er`PIj<jHjhUFIrg~wcv0p1JaBGc2khRe(V<loI
zIr`1G^)oQ!Z(4tV(eP4*!KpFsG?2P;6~8)FA?We(m;9vmCA`=z`NXYV_9Q6pgU?Y|
zaIJtU36PM9)ATZ@0Qks%tA*(elq#>w2k*(RDYP<|1k<)K?kK{=F&k^KHnqC<6)MUg
zTj-y!hNX%<x@XyLI`{D>zo=+5T$kg$xg24@1&p)95>o-QiuWW9{=IUmbhW#=5$u24
zk$%Xls&IuL==7HU0t-sq!mM!V)5XW%Df@4^>lC?;hg>)-Cy5B4AiqV(j|S&(5{jOL
zvQBR9+LvPQUjoC5PoK%*>XDfFQZ+H$ycOH8mk+~5CRqM*`+0|x($6uY{h*Vg@*||m
z&r+5Y{ZZt`qrCP4u*uLJ?qid%S8wo6;v2#3F>k@25fj<e7<;hD38}~vUwQJo7EKY@
z3M$uU1A;_gT$jE>%7<=v@{BgOf+lRbX8jLwi0#OVHWd*)j$jc5Jys>l?cR(p(i=2C
z`$u39ZcAOZqfN4gASiC|t{59b7V`T|UfKmBQb8Yn!AkkOE~Cqqaww{EjEP{j{gBi*
z9w)!w$j|vb#8>mEjdc=j{o3BU)_mCvcCVdJfhQ({G`WZ9!9c<qLU6JX;!X|y$ze=#
zZn_|BJIPN_>DZ6NF5MJHb=6$d`y!T^h$q|c<7ne`bav$=CzEW5r6R@<^(a#Vw(;nT
z3hbmoRpHu$eziPfG|PVVr6XglGF{K`d^LVDvJ83QFQSFmsqUyT+Pd;+2ahw3GS3Bb
zq(nlu`>sDLA}q&d`>Ko2M+C0G*t&JE^a4qarh|#}>yqbS+Hl=Q7zGshsg%KclOwR6
z7u`b%{Cn9SOK3R;Ju#LcL>(V|xb5^~&Bib_+bB_bjg;hB3?FH3pPL^V1e^nXihqn(
z=JZJ+u)jcePZG~}o01QM$(e3t(ih{R>&U*^3Z)zHtkaVi!QgXY+tdgg(3w(_gQuv^
zph1V{ZApq<DFoW=Wq&1src&JJE89gH4!wUkgW>-$L|A7=bjMr<CHi}!LwksH$uB0%
zO}0u=@aZn2(JubyFY1U_HsVd6*O-F|&)cV4hN2SlzdTm^c}o4hvpe}up>cifXC|EI
zgV>jFlxIX+$WTz^KHakUHBYa1^@_xpb1yKUdtX4OOdge~MSGI9)B=GZHd^$Kg#{Jv
z_IbO(EZ=;0HaQqiJ~=DoBm2&2<Td_`Q0{l8;-WFp`KF_p)WAf88@j(`OrI;yp>nn#
zIPn4x0ZdF7(S_W_{X#yh<Y~8`V~rUaCV%dxHhIaAw|Py0J1<S@hW}+2wnvgA-Dof>
zm;GX3uoFUB%>R8$_iZ}0uv@K8WVzl-?7z)s=RkjFsahoCGM(mMAz?Z&T)%s!wQQu(
znQTk9%n6pf9pmzv=vUw-p%5quM@w-9P3@vf3|6%`KHNqdT^_6cCJ6UDlmNE5sou2X
zUTmK_Xxx5{4<3Xo9}>YW$yXyaB<5JyL<S(OnOhyQEz7ykgE;&h#^Gs(CrI&P7J5sf
zMRsD0#IwAjk%iNr<Acv`eU`B5s(2xo!Nm^cxw~RcTx_cLIxQ)HMB62wY>56m3{kt%
zgU{{?J6xz?LMXNkYH)m7V|+LAMNisTazX_Y0w3z4$`*JjQrk%QUreDYeEo}|<5~U^
z>_Wa~NnCpPK;I_*4vG7%vi6&vpT3ac@-OLlR2VuE<6u2X5Zu+I)%1eS1PR873Wa}V
z|AjzW=YfKbdwFvdY^cJgHl5$p`9o3FZfR&KZI=AvSHvO*F-GC2CGDbPoW{?0RvP9S
z<(AkU3Wg9b8YtG-b#I(kTT|%9@n~QHZ^D7pKfxpfRqv2<+>b6XG#eNy`<5}>8}!a;
zqXT&zJ#U51nMr)oE2eX2To4Ktga3MW9{DaY*}<P?{UQ1q(n_+)3HHk-4EON~m}#Lt
z2%LD8SYw}fhw~+nJBNX>;2fURp1jnn&UC#{EO#bU^Y+&F;reP;OZT<RzEAi{Zjhu;
z<}G_Wb^NzL8$16#8kpg1oNmc>c~HD?EY>+VYiq3z&*<Pi_-<pITnU~J<Hcc2`C;%v
z#qHu=#{;Yd+4(By4E^dCUeV#mbi=E?W2~&I75ZBy3+^99=B>Pz93d*LPceGup<@2g
zMo(gkM-C)drHxN012mrKoW)F>C7;LbSDS$W^FgO@?OWSY0a+P)7UI<%p;3IhoR&$F
z6Ufa`D_NM{*vdP2Rf>qCB!srrI|~8t(UlW^{+{xG#kX=L3c=GR;u4}?0|_fd_XqZQ
z+mt>|O#T!=;JAiNoL`k5s6K4Dmy>r=q6|fTh7jidz%SLf94E&3B(}7eayU2i{hyig
zyXlIu#HDeIy&v`wq(iGx`OLDrkS~p$pGX<7yxbm6?s(ku+?w=m&)XisOO*}x8J`iY
z-7f53I|@X<9lk-CwkF1)`LHi_o2+@}apOu>qxRkIC5mEA4DdY<(l~@S+Q*83Hv*%b
zwpT-CYfP%}QF~5bu5;hNJMc?oL2bGHkchzNz&+6;CCxdbrJ`7`wKisV3b`lv<pL?}
z8!uMkE9EoZkOs)>10NzaB5$7_OqNUH(sjz7UbXhoVl<grY>4!y%ryTLX&h4K+dK0*
zi`6`4jw^uAu8XqywwKG?U752SQRT$xrsEh?Mya-SH)1Yikje>9zw`h4C1;>w^jWxb
zS&COv040X^GG&y1&|ZEQ?<C(s4w}W(a=z!tX?!ZX^vd`sMeSo^(uSmQjfV28+>?bQ
zQ2blM5M~44JVbmd>vf<_Cq0ietz!daQr=zewL1vyj=lIfrqmeJ$*d1wG~re$;}dE$
zRP=k^rC_F1y>cj;EBMYU{x_<6F7oA`W#TI`aede&Te=f`#;_mT;fXHMc{D9zsHJvW
z<+6VM{f_kg(JmO_tq3z=+NxWKNjZT?B`;5&)#~h(T!YY?OzQj~DD`?PeP{f0j3bPH
znPq=dm-xJkB8Opt$_L8I-ABYxuD#Wk$*9XUUHB~ND{Ou4Z*1hP1G<krYk2?2OlOTT
zMX;_TfijBY{594YhAz?kmyJ)d)u=RO1eHxl=+R#fAEYkWyC#3TwO-SEOsxvv^zK3-
zsYx()<Z}^<(ABR*jY%EqaMWD(qAJU^JYbG<cxqGIT~@P4$`_xZmQ!I)(_Tl9spHH6
zKmKwN8j?Y8F(%b@`!;6n#%_#W7^ZKJ{B>KsOsO6{#^?5+;QWy11=F?F3!g9fAx#%n
zpYtb4^S;~c-m102z`Jc&;Sib=>R>!kal8R@^Je`WL4Z^gvMB)%ZF5isTaL1YBFp94
zt!HWm>F;B`H7i*NzB6E(5S}YAOJdylTZ6XlwrHXw=YMxS%WhJdg1(voXTy}Pc*O2Z
z+b>#bN0Lq6kmh%%-puU2?HSLPsVROEhgkxECpy<X9mt0bUS#&!Z#lfPW?A4DZhNMA
zDaOp3Y@7X|voEjo%VLYxOO<_9gm0$3eyA+2Rb8VBWWcIXS<XFI;y70g%&xyfKlcqB
zt>EQ$E<>XARC$tVsyfr^ToYCV^L6TW1Sm-tswE});a+c}>(DT#OcsMpo2w9PH;D@J
zew;HvIWg*wpS>I8&%#Wb6Klh>9oe0|&V@ea$L*ylQ(=`mKGv<IP2NH;+TJ+44io={
zkp4tFQ|Q!AE*W}81E&pzv|ucm4IF)Po8piD@F@9($0RlCYHJ)po_G1sm%zK^(J0|R
z_vaIg4e3kBK<A0eFo|n3^O2UypI)R02%nzAgYzwKj$<L%^<kYlvs{=D>Am^u+NQp0
zR-;{n6Qizd1&YV1;<=aErjpFAQ0W_a;)21WZqJ{=1SGChj!Vs#tL)q#3oM!g&;JZZ
zPuP6FoUfJRRUeIS31=dO&$AyeFL4=!biUXw{wBjd8;bum?D0eWb+g`#V5pR2Cw|Ng
zRo9x6W^pzBSMrI49{A4|!6@>#q4N?<DDZ^H6(n|3bm~4hxrG@inn~2GNXg~hGa`zi
zS)j)&$-)@4Zp9PpyfSi`8(7pJMZY8xKX{o(aUPz{NpvXvVK!7W$B%x?wa$PwY<n-}
zF>!TDL}A9ATt2HEe+3F6B%d*o=tYLgH&TW#oC!tE?Qk8g0H%NOR7QR7B(~yUky2K{
zp*Wgq$sN6CtG|6r99LIw!%<T;4uk27_{?@p;=+EMdCqaR?+dZ%!7EUXk^hUwGOqlR
zYKU-&dj+o|{A2hU!B2$vZj=u)(`-zcc~w1sh{W-xBGEDzsHtoHhy3F|*4;-xIZ(=y
zFpnG7J@LdgBcOkmj!{)7;-;^}h2B1ypJ$iA@`TVy7K&<e30p-m@Mw4(;C1%PF_I4$
z4}*<Ka~0wN2Cs{qJ|}cRy|enR%HS>;LVh*yDoF_OI3WoS*6n@y-zz57<O$lsN5&B$
z(w=#i9*wp=JM!CcK|fy;Eb>6VN7vSxT3RWmgSHIc*_1ZsUFjZ|BNU||kn(DH@lXq<
z?!ldfmudkmKu>Jf_E8D@`U+o=?0H<+Q{{baS#NV5as0vRmR8#v&FXob@!Ce-=242A
z$2_2C%XxeBu2pD;I{02-4Ksqf23;F2{=_}MqV_*}j1nRvh|GmDvrLGIkJY5S4O?4Q
zREk91Rj8gSsV^NB_{k7-Xcm%)mm|ex^qbBT*{nG1S}U;?XF-3nC>WcM_g|l~*{rG3
z{iN8L6v&hwMd?<se3`bp-0I8`!1+t{vGnb1)9tY3v?pR(Z40}zrXc$RlY+PS(QqEc
zXn!bpuX+$89}5gAt|R*LE}CA*bk6!NK;ZJ&FWQ^zc@eRjBg{mw;$=`Ae3S%dzfmn)
zAr98;xqeIhAN>_odM9Rn;I`0a_qJ`8>f2fQ2JDJXTU4r5u7XC?Tec=nHc8mfms1m%
z@8;qBozL&GC5|TkH}p;UX+gilH#8o1;sli5G@sQS{hTDj1n@doePpeRudHPneyb0(
zVAKMbaG?Gx@7*~i<vG(=I!!($3>RJYmoFY^KAE|f{v;36J7~aln;00m#(c3op@3Bp
zdR0TOfdm7-juw-1vbsj*?sD84)z^Ei-v-ft@y)NY-^6}_v|4AC3>Yu=dm^u|gHrU2
zFfrPoITWyF36JW$qt7lk(Gp2wR+OY<z*y7U{hEIx&H$p}*}g%uVF<W5{XbTa2(%TC
z&$v=cgu7vrL+lZ=w$*#{vDf6`IT3|Kq?o#?HYNQL10aqF_>ZG47P#Iw+xUkCu2)&S
zzkl~G?Ck#Cf%>#)?mx|hz9O_Q?I;AekS2}{iFhc8nGm#XkMOEIpGg|HlK0f?fl^bm
z;BU(t29Iub5(|xC*qzJj7p1rGXqfsvbtM>XRf*&`FLX^?RcJt;OG&XJnB1ESwKa7i
ze|>LeIbifnL==@W1IKkb-@n!#KXF01dBgRp5J#_-XXwx8o(UYt)Stec_sfcYN%;7s
zb8Dv6=cI(oi!xEGml-izq*YYH3w$Y7NE6agg%D^RJmKQD)cg`r=wTMWbP+HTL&7aU
z;18Cq2gi`#F6>nZ1xQ+u5T5cW&(J~L_wfSBc=)BSUq-^<881Wim6Ofb8Zv|AI}0*x
z;z^nSgGG#tf=S7k9e3__8K#jBQUfr6K3R^dqdG@(K`*tGBX>nTDPh~m{R%baHYs{U
zwqg3sF+q@kUL68H1jSDSeoL<mir>h#l%PA9MZ+8`_3{CUnbJNCjYsPFoVTgu1GMqd
zL_6k3_r}S&Ys>(G6J<-I{BYYAyr{Y0h+bd(j70r)>MTNm|4~3#a$3^-?~7DIp|mn-
zg>9R;aO~Tma)K%i^b6um25fyvb?g_PfGRPP-$9UOZq?`oN{zMsn19<$ac)hY=^w?!
zLLX~(*@k8^2jH7`8kRyzK=y>ZsQT;=zgFquDHzNl`tSfh{y>m_HC(=K+xTs*P}a-G
zNf*+zWNtcLR3j#=kL4{BERXzN690BgGIl^g1a>Nko*^ejYeA`|!eYB6B0b#i3y@&u
zcd6a?GM;u<Ed&>)okYES<$Wp#&Tf`nDw`&;Y#qD~ZeSl1BCtG5^q9A#dcyb36w>-@
z0tumi2(AbCj@)76PD2afapMU@W3iFq-bc#idTxU+%Lf|h8B${Ob!};cYnL93|G2{t
z&_3$3LAut3-^rZV+cGv1ahpz_Cu6KA^|9Tw_s0#v5;2W*kQ(S~dNxRczWM#$_6`0U
zkEAXe6t%yLdqcB$;3Ar0r@F=CP*h>J=bk8UsRu}k<sd;s$sjF@;oo$>4Gyp_z7e)&
z(Eo`O<+X}6{kdKOBSlut;rCmpz}YgUkp}8M-2faRigtJIy@!qzPkb^_s}SkEo)s`!
zRm}ZBuZW@Jf!uRS-0^oJ3~)uykU(>2eg{(Scat$I#0ZUj4eq64Qkt~y=5U(fPib=~
zPlcJz6AOq7l?aX!j%3``IAb(uuo*h&RQ^W_iP~HRZ6l$bD$TzkA#HZD=VC<=Elnk3
zg4?}0b}Tmt9;O(}ty&owF^r7~!gqaprsWVA<nLRMefP5lIoG#;^zaYTn<utFQOx6N
z=V*Z$DJu`~P$h^g(fdCvK*)$S4!a$JeT+n4IUz(^u7|<LSB`h)FAqj2vxTne=8(w2
zy4|rcQ51g+2M@8yj>>@WKS@KPXuNQTDZ+N@L9W+p3uW7GH<DX5pNKJ?f80ymvy89u
zfT*Q9gclzQP{3eSnNg-p2x7cu;Da~yCc*|PB1D47Ih8Q*YVxQ5eeQp<lIv@ruJ<X_
zcM^V|Oi`s)5`Qi5KDl61ilst(KF)@sCOfmikzF<(PE3zsL4eab!t=h@#rg0)l?<ny
zK5t(HkZgH=?uc@6^a`D-E!OI9V&w-RnV)mM)llIo84lW%iZ4Pd9to|uNya(?Q{e9&
zoO9)R-uCxUXDu~SoJge(k9G-I-jE5!XN8@ww>LCN!coUX1A>c%H-40gx62#)oGrpH
zHtT6#ep<j|=<_C)?x4NE$tdu!CZ=s!>gZu0Om81ThEjTv;?niay*>-WqKZOt5vU!W
zPy>}Z*Jaga7b*YHQjPRtSNVb4D!MQ|9~chLhMplJM$4f=vz5@*D<&eFT0M(D1`uYl
zFqh-*rAQ#2K57D1DvQcj^QFqtr(CGJTA{C{f3SZDpae8U3;5e`Jq~|bn?Z&bEQCc=
zl?A`<2v}}fd`e`?icv(l@&&r=bDQgwmIai)fO7g%W7z*kNRM$dFc8v8T^v9he>ULx
z?)~S$B?LS?W)T#5yq_&|v9P=>x_EqAaON!;IA|j(J_ay{2pQyDDGyn-N2EWQnr?O<
z3hn+bKHI04@l6)p=pEP%h7WfJ0+nY7h|!X0psiJ_4~{4llJ>M+rvqQkdy(iA8$xlB
zB2p|h;75z;?E^?wl7cuitT-0-*<OkFe&VAiz=a1HrI}K}O>I!}sc?rM^O4xq_<v1F
zacE@mMWo(hIRi+p^N@Tv@I3mxb!GGFnBPq^#^WcI45mboX^=KvBYdGBKp07t6t
z!;|ko4)P@fkkmb^7Seup`v12WmtgbfL_Y~J30-!uRljp%prB7k+d`lBdHvP#vHPnb
zE4u%UPE99>8xqVQ#w@TsAH+YT(<tRujas}jGM-_)QV=HO{53S18=apwYz+6JgEqZH
z9(XqMa#96k<H&2u?7tr!-iTj2So`WgY{_gz?cAZ%D~nOHh0KC~($do2zlnMKw}b)H
z<?uUB#5&+iSCmSq|L}*q#YNb+UPfZfdoCTpRwKfbS%y&s4D=A%z{O1xOA(e+w0_4%
z1E^x<P<*dv*Mg$hjD`{GOUVx#hNP_>T(3QuAvaKd-r!fb7ZnOPOQgZ?nSg>%v>Us$
zceCR-(nps+u!>%V^7x;0=9G1Lt!vX@FCMgs75hVr9ovAI`@o6%V3z7eL0P>QyyP~U
z+2@?4c`UZ!@@n|$N1OUydztImuSuYf;=@$SWg(3u)R@|IRd8=}a7Z>iqnEsKj}{Zw
zB*TW8&xikL6NC|uNFvca%lasAMY6aF8seD-z2%g`Sq1`CH=Do@zhp`juq02o-}ye+
z#{Eo*mdk5|ypEj>v=co*<7br5kBK!oSyQBck~1Dp3!l?pPA2oBi=0r#j*Ry|Vi7ZD
zI!e$I^!qIzf3Lgh>nn+G)-?Hfy~YSHZpgDJ5#>S9xL-8zECtNJlVk%g!6iybnM&3W
zw~oml4%>qgnz*^!{poILlmKCAr*{nwA7Z`E?~{Kr-*%kwJ3;ae_KQ5W!}0AKD{8fd
zg0A%Bo}Al_@wD9t%S_HW_x`%lXF>cHw4*r~@V-kLRzIA@r4$XKuA|ElnA-;N%yq>W
z>l>J#*^4ZYVfX!nha8Z@yd+V8O&sGo^NZ@YjSo2k#wj60*0I}9{`yoJUpRd8(-ArV
zI<w(MPf&O_>>nZomPl0)__=@U_Vj;rZ1o`MN6qXO!{Ee^p<>+R-f&1jkthtce`a}5
za3$=ND72BA8Y8-LtDc9Hxd7BI+7UfLhEz6Ef{mRP6|VlfS_^(oFH#z`P1)$b9R|+U
zb7#jA9&wPC-iCns*lV+wUlE)CreU1C2jbyBU(t$v{%mXyv!Cj+Foa$|=J#EK7;Jyj
z-@ML`QK#fYV}j6D9!h)cSN$QfqmYFZ6Pp^`;9<rkoU){)xb9XeXgzz<|9R?iJr_?h
zeZqrT0kjnK#xr_e03Qug)%ynCysg7GI5X(vOb17QLLM}Cm6j!H{r!}@<zq^*06yzd
zmKvRNB{cEwb-2$T#HFwHM$DdXWR&7%)5{VtqV{w^jm+5}#&ntj^V8EIfe#@Akyzy(
zSzlr2GVo^z^F`)2(Oq!K=`*dq!0DY1%=izCM@20yILl)*G=R*i_A*l3ha0OG=$GJ$
zd9JrkrES%j65SR9;OL7EM>3WOOcBvo3Usp!8Nd*>QWWs=uy=Qv2h70sb<$m5absXJ
z-Bnyx0;*b#t`GRpj;rYZ7*1f)gO4Sj(-;BX+nDrFeS)`+$1;!FfrQr;H%kTK`Bp==
z?1B5^{IjUHMCx)dG?8VH9tFfZ(F_7D`+iCvurQ{t-)2?L+Z`S9^p=E~F#d96k_ujz
z*N-pFFD7hi%+C|Y5|?s9Nt>`=o?W~t(ZYax)2sp++WqVViAfeC>J*E2;^2C`n`ii+
zSQZGqOf~K7&+NqFdE3^}sBo0_uF#I(qupPcFxSzGfv5UEJs*57n>W>4xP8ZKmw+%u
zSqj2Ob0FNJh)W{x#gJ<0&|~Ry-d5#uAQk0|1p&<jM+i^ei38n*fJcIWf&rWaBmd)H
zW~6!~G-lcyi7Ohs&92XTHFquo^LVQ6Nm>u>vqlc>;Wm<)aZ<E2W34$kG2HckRN5cP
ztUkq1qAg(cM)!;D6*!>St;QbkR=$5@PP@BId}y9EL7TTPv-#?S$8TVu*c&pz5m#q_
zWo&WLpz<%9Zzc#EG|&$B4VPc1PAKK|?CX7Apv}&090!*+b(g~7zk;!6ki!C%nI)Fh
zUGhq0<f%X-F=i-61&q%MynB5_|L7}cZ-z^=fJ%b|<!!q&qWHz=e^fE&Q~?GIUQFYM
zORs3HgqB$J&Qy#F12@|GSUYYOaUBHU^DaN`OhL|}FPl~@T-H4{9+><4H}-zEjp%{Y
z(GR!@)(r9@F+P3TrT)h`#0mGk7EbLl;ADZNo9sqBvdZT&(!h7?J1nL7$Xj?Oy-rB!
z3%AzNnhEChoZlMmvVJu>M?^Lk>UaZ6mX%1$zMOwQbz_}P@hiW!vi;QkD%-32`7Oip
z%#OdQXT^huUhsfIMZ=__gq{@r#;&f8@ra}1<LzFy<(4x|U&m=~WE5J83&NRqlT=bi
zi&IT!X#k<8ulxqT^DeCovsTdDstTS^v-tfK4QewRK3o}+j=J?);Ke<gzvWPZb(11V
zp0?$cP=h8zVL{kY8)dO7v<yTPEh7X81F>i6AMAuN_9~lue<&Rl@=AsK@|_rp8;UxW
zEz?dLScTH=(Sy307vhc_o!;YZ8HQ&}yx$gH{`dk<4?CY+(2xYVl&e5oa4+ea4JPXi
zu224_XuSF=-)!#2;G|3mEx5&4iUK|tk59&OmS(opOk}^EOemkvMyYsKBA@@d+#d_g
z6)Wu8v-SSzf@W{-kzaHAaiFTA<Pzxc555w}Ck;pXy6eS3&T=}l%q_yX)LBir<`0b~
zmi@H0t?6GM-Pj6f<kdl7d?s$f__?Mb=f^zkJ#s7xy51giOp74VS4ooVq+_5A5I{pj
zb6JQ^SnTs<WcMIEX0S6<uXw`@%20o!Gd@TjQ-o!K)?7#w1t!GG=@?$B+Q~4JW%u%D
z=hU-0_vH0gyIZ9z%KbgN1a^z^!_B5fl%S;A|K?)+P29)etZn^$Yk$2q?-X3$jrKdM
zUXwsYO-}R&rzsO~k0~j?h?j<yL*MzV8wHg-kiYhC8Dbt0<5Yj0C6_sgERdolUw6Qj
z+{}r7FmY2*B7_QRC0Cn!5nadHccn)jk)tX)R+b4INJ?p-#BCq!N{l>UmM@l*gC*_%
z?EZ!ulAs+~bPhh9nWVlIe*KF1R75jK@xqyvc}?g~GH5)>f8)izW&}%csk^XZ$rtO<
zL&D}Zn<_+emte1zVFNcMnaqiaagzTQwza+h3?XH=iK-tn(qKk;6>NED&U6L{V;ZTq
zOb2c<KH?;zpNsxCd5e37Am+J(IWOnKx9KJq2uhiByBBo+jC{5nsS_DBxByC(+8ckn
zOBG;%yhQO;X!FHBB1KzOSZ{K_HPs!sFWRun@})3g1qes)g;>dk?0m@`aIeTPpyI@W
zL9$W`=(7A7jlljPyTU`qGVfWSsiao?ihw$Pcf<|lf;(uY|0Y4t00-*m8cry&-#sHR
zAgQn_=+>7ld})YDfl~Ylk27NKO1IX=LH0Y}KH>g5E%&Hout4{JUB81<Z}_{|=`hy|
z*gom&JqhSyf?3*Xdc#bhgm92SJV^~@85HjJj{=A_N5?nvUFy&$<|VveNYEP@jj9t<
zbog~qx5rqhCPwZB!;8?%6an)~_z`?)sGC}z(qIO`v{4srd%Wzl{lS7dS{cAIF16kb
z6NR+iu}_?!<-yV3G(+=O{fzRiS!;UBiEchRuAiPjf9GioUGRss5~$XS#50{Y_ZAxA
z8L>Z5=MqV}4xY?!!!4DbJ-9}iNR3(8#j0iVPh5x0`Xe>R492>Rs=!JKMHb^x9>kaX
zU^Am@89CO?31)8VV4=YN1OrDoCqFMumdGBMR@BaBiMW-#F!18L*kzIpUw2Zy5vA{U
z3V2l0V7vG}teFe~D@SfW<f-a-Y#mq9Eq?n>&J0wzighqDYUB!Y$4<1dZwAPwB@rDr
z1FA}_=<9mU&{5^6AssRWCvIxSEnrSO<)nt*?9ta3NL(yUC&zSO(2&sgx%Qk_$5L=y
z+qOSP1XOP0-^PQ&I<Wc_C>^C;n$w<MRp#MMw#19xqC#L<BGhX?w~H)r&p+NJK7D9M
zIyrm%@QyS)6Rml9IUEggnGMN80XeP)VR=~TRK`(cbj0X|egJu#j@Njv>hO;LWq*rm
z0mPN^m4;UTniGVAXPEY@vNJ<P^>%RAH7%CQ0XAFG>&=P;X}n~wN7#rNgN!0HIh)O_
z&(EtwF(CrR6!s)yHJlT!R|p2~5;l`y$d-?MTL=!{KlxF2|3kH!plspp2MJ=}s$9cC
zd|q^KJG@v+VGoc-_%gD6i}a%-=(qq!%}?!2TK@VQ(<AiNem4yEo?t8p1*`!q@idh=
zo_>xxbZ|9ha+I9&){V|Y{Ff|1B5Gn{)he5xM~3ArULt@o5u9QiH;e!j=a#r0{p2GR
zgC)tKja}4b)rUGr^p1q@!#Ly%=2H_OqAUfm!SBF>J-#gdu|X+!_ylH`F%Z^f$;k;4
zUReA9?GK$yRKIQSWb8IxfJ#fGV>77`mQ1B-vVT<=VNtbBG-lC$@|+-VkPkjCvK{;&
z1YHu0w)K^Zc*;X5|65pC{O;lKAYzEta3=(ie>8dmau6sza3@KlM|)cdqHBppkL^|x
z!vtoJTVff~(kni%sKFgbOApb2P-Sf1c%kG5A1qM-$Gwmz%SQ*6G^@JwXSpJK9vZJT
ztyp#P@IJbH<Oe209TllDNkh*LKUa^w{7jAB;ue1+b{K<1$y}|9XS4q`%!cphdH(Lt
z6*z_xR~`1RwVwRxpae<r2?-{kVF3CRz=%YBJCW4NR~aea6U(>w@TPa=H5BYRXC=bw
z3Cv;VERP-(!57-J6QQIe0O22OCW`oSAnM-PmF54ypTy2wRf!yJt+!4DId-k!zR8s6
zqs734b$iWQI%gB{F>(M2i`suOaJ&3j<mxP5VY1>mxPi%KH$2~H;l7J)+1$T}YKW?G
zg#vs(Eh5pfh?53!!o;%_{}_!ly!-v$RV2zu=Uy#enZgPUcoO0WWrlhS<@h^#gHUA5
z%4X&W%8QVODt<`ueU4quFMNQR>jj6Hqyhi$ovQuOTKk6PpX6cCUo;A0xcG%HWa!uB
zDE-d^EP5<_>N~;i<fv;DS88^GbF~t7Rtbknp1Kc)Gx|H~y4^fT1~6Z5J&|*=N&%4k
zxbtCk#BRf)i5Vd61&?jMMO<Xm9R5AfVW{4H4}71w-C!G#E(Y{4d_-fR(7u&u0q==n
z(b}s1QV74BP##e>U}a32ckqS#;~T0I+6hW|1opSqqo;7;>d@M2Pds55ivL8iIUF2A
ziMh8s-8g37k@Aib!+pkeh_6L#8AlBEQIyZf?mDm1uP~rACcBR1@mgttneyVK|45Mt
z%=7l)i+Fw{E^x1vIn_K-Fa49jA4C<wO|xr~>RD234@+(w?@^K?#xUm`Hi6wqqV7IQ
zEzpd=Kvwd=SL5X7FM>PV{wI+V0yWNei3r2~N!#}(toUl9GhR36=M4-clE2N*xMiNq
z&i3~a(C>+WH(xHk0Nnwx6G+R0ODMtP{v?{0T{1C8=9j?n1J#>F7l7MP(G}j|f;a*w
zR;>apU!ua^>0xlKC{B^OZ<eULT<rLDD|oaQrwV926d!({O>KTikG}P71>P)P%nNl*
zK9Qm>qh^>N2Uq_Ue>f~0gP%FVFPl(XBQRSeOjd=i83%PKL8g}zrs>%*KMVB!@6vpm
zNb`dl=J1}r{^o2XIq+-2_=;mq_#c(xA9^unoyEqoY>#~zl4=ld$J>7I2r)fZCvhgk
zUvFs0d_Y{k7DipTM2xW}!^{u-jOI`2$9u8g*7wp=+OPWgl>@%njLoD$SPEaFIz^r3
zslZI4KkBs&?ni=y<ybhb>x|u8V#nayMZ;?i<)6-u&))jw=rj@XBF<HJYff4~qGa-u
z3qDu8&b}v;=Zv&ufK4m|M|x~%al(4(X;_x1;kAdBcl6ew{l|1-AH;;;KM{7-vD(jA
zfv<Te4#M?V;nbv<gRISt$tA;_sDdNjebvsRx*V}mGf8pD;s_*+>6s8Q4&k9JLwB{V
zvqiD1iF>#0M1%=`fedqnsD|S9E5YRnxRg1j<3M>@2;`C(et}*J!YsnbI52G&1#?4K
zE+6G=p295Z*qs=_NI+K37}9l0-PzOEvlm%GSekJi5Qd3?>8E>4yGG&<%<|Ss%JX#d
z36LJ!l)!Juwv|%jv7K8f(U{?85oMIJlm{`+@}3I#H1&c67kv_)|Lmsa*a=6)rh;y}
z{k@X>DbfQD>M+O0(Ei|Wjo|ftDU|u5f5U8)3`1s2!sJAdLI>P`xH~0sf?>5;Ha{jP
zCvfIPgr)e0PAsRr{9f}Vzn6a`^;ND2f7Sz<CmSEUtS&U6FC8c~*dtfN5^sk^ne|#R
zolx<krLIAYbj(W62Dw~%hgTeaD(Bt(P>7Hs&O^u82aG4+SdW#5JT?<rmO8G3uCCx~
zG^pR*)R;LllA<ncHZ)0TjWST>j^9SS=U}JM;F?QM6?6@RnWPcS#+Rtrp9OcUDzr0f
z<Fow9_Qu>6F6lz`9RN@9I3bKFLA+=F)#fdIus!-9Y735=tdoK268(B^0l#bLbG%%X
zK|sG=x~KYhi-U(>76}L6LL8l_F<Vgx+|37bQFOO1-Ih0t{c#<{Ck^EsC_-=5El~1$
z^;u3~K6Wnn=TJ%N4|TWCB6GnwYQwu>KpV*RZB#2?k-EhE=V1Zp|Ea}V*8Iu?PAvqW
z8jPfqfg;PnN4?_9ju!?Z$3g&zz-F>Q>FJ}8sP>D821X7AKo~Y>D!9}38qzZ?H+1!3
z_jbi}0V!!BJ&3Fe#<3b2oDWh2>N}ocJ={I`l}x)Y-_vZbzCPR%o51=JFvGA`=<jxe
z0!VB^UKpAcW}=#}c1>&UGrHyqG0u0v@03`}DJ;cL(`m2hyJOVE!V_YcYu=z7<{e^A
zxlN);iQe)UFS+`fkRnPH)0?A^4L>7#ru>ig(!ng1MkS)}$k&(bRgv1Oa_!fVSANoL
zy=Tw_Q7)if#O<-!i&zF+-cJn@wA~nxqV6+kg<kSLWvTO_ogO7{sk*N^Y^cx=Y#<gM
z=#JV@IFoM}c+eKQ^O5Ed2Fz?-7X+_G(Z3_D0}!h7?<2>C`)Pfz>giBG1qKGhzKO;k
zX!&+z7w<=xj;FF6zJ4Wa0h)Q*>|w6G@<Zxi`j@>b*lSVvil;9kClR&TU~c}=D~ypT
z<|Tp(4s<kC?3fs{hFn|vMXqDa;$6b=<9)V!N&EdF#o4Ztwvw=&UitOOrN3Y$F1zIi
z=4Z<7_EaC`eJjs0L@v4Eb4chRbe)m@%29j|#&_Nu+o*pTOFg}O%a%QyFuKPhTxEcY
zX%_D{)yBH9cfdkZG>b&hP1}<JNm6<tsK!|pa_lz>7~p32J@T<(O!RNl%yPXSFI%VS
z7dh&=;SD63x9okI=Yr#1FJQX5xc8G+Vx0XO3r)>YpiENISlLrjoSghysG~1b>7q*9
zd2>?ttY4Ku_jotUU#AjTqbDd^-RaQG4wJFet_mC?`L-YCf6|P%sI{t7_>{MRUl+C>
z+q@dW|0|*cvgm7}1i0`)c<H(_SVFVLRwOiz4!!5Q5zT1BO%12+OO)??8ej7EcEx+}
z#_i=_t#&H+;9`~9`%`*O@uNNhb6mG=iqhU%d9EUI;fC|)g8Aa49$VGK#X+;fX^`<3
zK4N$45jb%T{Ko0p^|dw11$I0#Cm$}L3DU-=NN}kxo;&}e?1SYU%-`0P`WjOd|5&@H
z(3_j2oA6WhA)M9+Hn@zm?0rxGoM7szm>wCmYq}7;T1pYB1hTmlkgIMo_&zjyH=Bcd
ze!brpp7;!&!@zC!h-PX*5G`}xPypxw9Qel^d@<G)cEY?u;p`(mAG|6-gPb%bZbDt>
z<?0Bo37)4w^8FqVwDLSgR8W=vRR(s-yetDRaXrnYTk!K@IVySzB49O*lg|9<5Wg|-
zX3!%B)mbnYQ*`jzUt^BA`Hiy&hkxtxpz3-m5p5@}emV5mNe+Z1%cYE}$EvR%l-?74
z$tvw$e>YAYtPFnOAVquA-kP8FdAyW>WMse=5daudRNG0wD)-qz`|8c}(z-L(%pIX8
z>jVXMP|7b~kbmx}5Vp=M6EJ_X6z>8h6$j<uhaF9av2|@Ga;%w$S@!TV6EV)?$Dl<6
z$LY3(lEbNwMFY_eBXZ6K%0>cMhLqtjn&iV?!cjV%ux|~PgBSPhAn<37LFCl{-VZl+
zS(?jhm*X*VOV2Muz!+DJfT}~?*1KmXz1w^U;1I^E0ODc!(M8(GZ>gP)UkrmUOIVL7
z?}g(%-=M&9uXG>>3hR*z3dCSxID`2*Iec4N@W!7$N*IK1jDyqfWR<V|HKz7&BDopu
ztr_t2+YX_h1=k!ghU^a6G6EwidZx<crm}Ai&XF-{oTwd+v-#kIQ(iFJB!-{kIr!m&
zx4X!9wm$!2@r(DSTHC>6jr~RZ--LnFgKI$}tynWi*t}24jLJhVog#2kz3a|X!asIp
z*)HEz2JuSnX18fEBAfF$G1WH$nO{9C{@K9*Rl{V%l)T+)Cej2!2V+NlLEDHqm(`W6
z1pKBt)c5Yzep>M6^F8GG5=e61hZRi{r_81QMx4A#4R_+~I!=2*S-2pSN_HVh4mZ3o
zNDthz8X=UwH}aLsC6`o4J)v*?%Y_!=haHRux&`Os=dIIySLsiB0=Igh>g)T<tKA_U
z_&-e?X9C)j42H+h2@1b@*TtJ2Gu5B8@xF^!Q4=P8q<W+D9ubC#f|4PW9yne?nYwhH
zUG6J6S{wV6e|M?uXWcTRmnI0cDFXp*`X}2v^KE(h7vw^oe1Iz1v?s?<rIy@62`AXK
zUHt4b@y@!jVD-t9EGk7(RT4~H;5|)ni<bJ&KJ_ieMH1Yh`=Q)G+~f30(pnI3=r7jJ
z!eCY%bR0!=+85YjcH%yCS>iVd#AL(;Qt@ygPZ;2lLtxh_4Nn{jo&P4o*us267)`>v
zOonD%n1|BaSW>6MH(Qz#_RdyQEdv)VA`{x$x-ffr$|DunTybKYlLHpCAW@$ml}H(d
z#w5{sI>4ln_>Xm`9&I62tSwc1j%*b~-CGA23t68%%fGwW8!AJ%d1kSZb+cZKy`z;3
z7oSiN$$p^G6nZ|_>IWEL613zd(Y;U;#$-@dP~4MiG5U)V{lwlu@ZxJi0hs0e9X~UA
zgr)b>YRuV`nEn^^Z190tf{aoZ%2gkn6qqa5K&8t)tBf%Zp8%PddE;jSP_0fS??CA%
zq#0gj(PZ2|Zx$Bfnkdy3!ik5(pT;%@H6c8pBG@~|YN1M}lWfDe4l*XY9y-uk?nD6X
zNGOJDPmR6dZbKenV5$O=f8@>C&iZ-W@N1z?SQun}mq#7M-AMo!mpfq^BAN&e+y$xE
zd@aBo({Dr}ZF_6ksYG-_<Sb#1Gt`)0n-DUMdgk+p-`$9vmtlVrZuu<DC%RE#sS&cy
zG{0FN#og`3$FrmDf<5d!%K}Ub_TZCI_`3adPVaa7h`H;scOuTKl~X?VMvm2Uf-es;
zUL~WrDVS=7)nFzcUkbcxa;{t~iAl<b3+=mz;mHo|6{(tSwf~aeLOzxHwnrF~#>Z!`
z)ZlwEwOBoLNA+4CW9Pnw2tjQyg%82$yR-S1|Az%Y?TQ5l&mK;cleGsOzN82?Ya*tK
z#~&=WF0AHuBoHH^)pDGI<}-Kaf=*QuD=SP~NE?6DmbCaGH5&Rd#`)4=JYoNBr3xcT
zF`J!O+DGU6ULi%K+3?pJ7RBG7gg?p$J6j4EuLobR6SZ2zpH}|3L%lEhVZMuR<2t;I
zRTxfvX`Qsx_Bycp`0n(h|Mm`W-;D!C&3Lt^brWPuclCLWSlKVjiV(#2WUNBE7(AP!
z%Iqc@1s>U}El}~}P$!$OgLMOG)^s^epzG(`Uf{ueTg%`Eelhu{QiZ1L?B058UPWHg
z#3vA1pr9<}1Z|jlGTc!bg+!WtNG2hsLp$$MbAFJPA^+`R5ybAH{N8G4<;S&;1pc>b
zfgUM!IgNS+=9YP$A^3DvYi=7mDTT1)5>7Z^U-!B*-!3EBz?@k6st<u9OK~yMx&L8#
z@p^)m`lk&t;g9Y9P7cP=&ee{!Ae%9~Gd@2<5i%=zp(Ns1O2e`U&=*Fu(`5aAFvANr
zlArZyS1hosUy{9gXiDJLjXnZ*ni&HQLQ(G*A1vM!S{{nLLJj~t!3*r<6@(>wfa}O*
zxGSr~Z-Pr)d;`8`_J8OaNr@4dqxkv5Q^f;iXWEWNbR}j**pFsHh+f*-@*^Ub!0`F`
znA}l6I3!_@6kh0XMudT6s}efC2;Eg!EdKNZlpn+;GD@ra$@MwGO(i{wQswKQD5Ord
zTkhK}*c-;+MZW7j?d5rQz`*QN8h#*gNoUQofBItR4>Do^wN`*y!$bi2t)FvFU8(rM
zt5@_ff8dD|lw6|m(=|Uk4tUfyjYHxdy}<2Y90#Z|59hklO2UlzH{R;mw>G2h#5Ypw
z*$G7zfT~7VNz!vKyClpkvKK>Ct2Jket}!FV$zvNq+?_CH7f^oOqmi_i9{xp5Yd3FN
z^!-AX;k6%E5LSF(1r7+YW+IS`eBnd&WUeG<Vq}<nKA=FEdZ^T3;n^<tS*GT0;kT1`
zYU&|6!?JMDN1)~nduP+3`aZufZn*#6$=%)qiS-v^pJ_V9mYGg0riDe#A5W4wtDp()
z@@!tgW<s5Fy{E&Zo+xR9alGFA+w6V3HkS^g<<xfy1z@SK*AEq*qMFnpkX<*kCb0@l
zO5Nt3>`nbW0@v%s7b<X$jLB5wRu2*ohJ@r|StKD=q1rhsBuRwb-iF>E3L|XFekx5J
z29n8sVxW7Dl~%;5SYr8#iAbPM)nQe77~f9Emd<7gZdiAkf3sWOt+Acp#P<Q8w@~%-
z>pO%n@Fes}JPOeLn7e|<=I`au{P>JO{k3b&*_)8-{Oxqc_d&Vvrq`NC5(=Po^>oRg
z*(AcNHfS?#n&HxwRgQWzv}H3G(j5^4`xYM`AGy7NsXgLyM(}D-c`VE=B*2*5F$pIb
z^5h;gMo2uYbNQ)5BMIU&o*|p#9eYzB_TZGRy*<SCL-F0e?YBU(77ddu@js^SLvM2X
zeOR}I{tKQFS+6%SyMZIU19gLA-T0NS+fx=+Z&yN+Kz-jeC}joC5X&L}sRs)PG?Y}+
zg<nwkZTZC@D$F%xq;yU~nvAgkxX<%W@<j||x6e&{EwMaXu_{zRjbt32_(V#|%v_bD
zoa;3GAU%A0;7>_$WxEX$#o|NR2r}F?jk~<B<BN#pIf}2IQ)s~S;^AelR-ER!5x7u%
zT0sEp+uxr<AWIZ{HG*tIxZy=;k34-3R(L}jZ=|R`j&|uZ1V6<gv#_H~!2;ZJ1Tatm
zeH4KT%7t>6O6Mhhshw&~U=ME6bc(LZ$u2PMJ(N((U7EHL<SA~u1yZ?NflZHaIT57b
zDJa+6CdS=RC&tzGGv&=Zeog+0@nOl<=2O@@5vxYmciR_S$-fVk?y=n)Dflq9)hzx-
z1FnlG4O9Vka0a;S&w&wsz04iR<5x}n6|+aR)O2@;6<bc9RI3UU$q=YxBj1XPgtZ!T
z579Nc&^Rc6;J7pp9$3nNVmuH>oy8rD$BnVuDFxlr1MmKH=ic2s@UhGaaFb?JHO?X&
zgFLo$KQ4jSn+kb9Ngv?N&NG;>Gm8d02zhDtEaF2!iob26D9&zQ;%9Shc#_VJ5vS?p
zKT-+9V@1kR=i_a9*FOu|=rUbXEs!Tc&+NJ9AaQc9-i!*A!~xgrVrtCh(wmP5Us_ER
zAv^?H>Bfofn^P-;d!uffvnF+qZ-&Dc>VDU8;t>jVS{Lr2bAS^mPB5t)>}Hp@q-Z=`
zEP)KvqxOp%Gx6C`v7OSp&ANf|8ir&aXXd)YGLjFCQNHPtaNIrLzQ!A>X-@k0{p`>H
zlN<H@FR`YjI<8?B-DXmH48qj|?!vkQ1fI<*CCm3Q!z^7Cl<!AOi6t>7W~CVCGDEjD
zp9)M*blxa|zPfsGuy!$c-3K0;qN)HMCq0Eb%^u2dxsyv;UtAV~%6@xx9C6ie1&0#$
z+_=3&dvipg*YeCbh##f>|Mm9WUrlXKygMP05_%T|0w|ye1f|!2C@3w8bft+DrFRib
zsB#5Cih>0Q(tA)8X%d<sNKvXt2kE`{ymRmO{ReNY_sdzZvg?_%r|p@~JU9njkc076
zGzJ51E{j1|p{0~~wA9ok!IQ2u>m!K{qt)@?EV~U9LKwWf{#ExbJQ9c?5MYkp{d0Qk
ztd=KV1n^k^_DDieBR6dP>grVct>-IxZQ@-}C2<V>#>i3f{^U7+S}z^e%U(Vc_&3->
zF8E_l9*Ws3%A@9kfds3cr(h{e%)o~I*P*LJZhb2|_994C0?qkaz2fCdN}WfBIvUP`
zW@W>eHS6;rk+q$T3Jzj4<jP4!sO;9rMqv%k>yuuQZbyc};@4Q=7Ao9opZ<BOC=CAg
zfmxL2`IFh0l{mMTQq*j)y`AVWm6PL5)AUjNUZ3IDO@piI_noteZy;sv))$wcM|ay6
z4cAPUm(d+Y!*M-Pl+)Kc@9UP_JJvoABuR;@Ff*uhJ5e5D189{~Vf*5EU!#NP`(rxb
z_L0=k>I!#bA1zs=>Z#?e5=9iDFr^u~45aslMZMr4+_E^I$BBfc@P;<)FD1#o4%`Ah
zNBE%=x9G(CJy7i7=Yo}++!VI&vT%Yep_2f>m3nLECS5Maj~&t<s61E+E$yF`zY39@
z>V;6+7VgugO_Xr)xi5@2_uoXg;0Ps7?C^v3uGGVI{K3NFVHai9bS0W{^`!}2fvN@&
zq4v&T5r290>(Mph&zNMBBSSBzts5)m$~#7ChKbwN;Oy^BBw@|Ljtd>}a94;V?qgWa
zLQuzlDsNWKhg7b1>u2S+a12llQDudq?l{Wn#criFipGLx<$5H_{9CZSxQD9m#d9Dx
zWUtqcl3$f18Y=mHrNhprI*4JAhOB0JPjFk{$={O^|5a#t8Vf6;b$CkYN}@<H`|apZ
z@Pm;CD_JIwdZ64OI;<@hH}D8f+EnM;SdYEo|54oV!%$C#Xg9S!!shuZo`T*!<fV)~
z`K-Nr?*9_bj}&?8v~$rV0|<JCe>K}$1W+$}KLriviCN$83f}574&0TQ11wI@MFfef
zBl7KCr2`m>*BZ-+ZMLx$eIFF)+!H3R7#<(>!znd8kRJQiy2iKr*2r?a{t|PrmDG>*
zu(5L)3z<HWvTM>+zG{jP^_|v4o_esd{Dy$9zK@*|GMzo7{81Jd{o=V5Bem?ZP?<B}
z*7^DjZrF<LUeBb*fL{0AEsLzE=(}5PT~v>k*LNuwInF(MpO-wX`z#^v=Oz_vmk#@N
z=cZjj>yvvlghH{$2y(Sp;;M#+gBZq81LWLih0Rs^Ud-fYljB^-hS2!B*ry0Zul3>w
zP8n2G-@RWkH9xSgx6SK+JSGlCMJMp!x;_YeOw1nZyzB_|^<6rJAag-|i=n=TYOuNf
zSf^R2PUB;}Qlt2>7oyg)9}72}6{0^Ff||bV^5MNI&elxbx>U!`twt;rd>qA#+J-~m
zc%pBabhh5>-Bk-MLx(eROTqJ9pW4H4iuY02Qrhu<q!s1s>#rWOp}wZ@+O+*+gC`yx
zNZa1a7!{zw?oYFVd#yTNxzbV+-eUGeSFJSx!Wt&x4&yH4(LJf8lG?L#Bb-kTd&O6M
z$F4!?f1TDGq9Vh#Ch4F0e`9-_s=y#th{WK4g8-Qu=9K%G)<78Y<DE~WAy1twc71Rt
zy>R%uA(9A9N2Y5<gD{q<9s@q^ShG0HU!yHPM7m)p*fVYBe))EXB~m~RI`TQrurovX
zR`hlar~cQ=CM6_5S$h6Qhz9zrvEh;`|8MvjyF>D^K$)b~-t4VO);}bw*RQXEv?qhK
z>yv!q)Y7(8xKij+5!tji{M*6K3P#h(giCzHyO>S{`HfiPl>`L35;<<ppu^PTrJ}u%
zfVBEvOpp+)-|)~L3D9JYH;_TJ#tUC#xa+iPC~+!u@P@oGEHruvgCq(-MPwB|BY5TB
z9sPEbdP{jZOvem4q23uZI<duzf&7dHwRp+!2S^{?BOO(4sASz8tjX+W`L+Ng+P)`!
zSyJ?4T>>u*4(JGqE|_0xdKiYm#B-&N>CA*3qe6H_T8JV7YtIfASjrfG=64)jbA!O<
z#0Z}7@j$*rgpC#^_qxktmE&(JL@*UOa(0j+T}vM31o+}uP1nw$5I}%)p95|bYz>?w
zp5=3`W=H)jc!EsHV;i)kL_B7*;X5mM<+~cuQH(5ug`x*y*ug9|-VABue@1zUx9m!l
z^uYPEVD#$DwQZO(l2A_3f7KXU;dGcjgenT%!4I9bYG*+IGE@2^(`!iuGlRhn1=xY(
zHpT!5^)q_$d`UAd7paOwk~3j?OfT-a6&r!3?h|in&E`LNp_QmI3)M!W5)OE@My)I}
zfn$7E)>|)J7rbXji;ylCnHzpETrW~oHI5Mnv5X5gR0LHjmjL-DhBbjZNua#W`(sph
zkd&Ai^53b&_*h63l|SP#sh^vLe?4Oyy4%Q3D2-euke4P(HVhmkmSB^T@Eaq~wd11N
z;bW--`3(F9sYO>{Sf+*A5WsHGs`PPzVrxY9de9{XCjO$U@*8WN?@dSi1GiBkykC`Y
z)^4?3im}cfh_jPhBm#1HU@#hFU-o0=?qT$>fJrkt`{_*a^nBTT6*kv*WO*IksQQpn
z$KyT3W3Zo|30sR~2OJy}w@Cy!ur1?6z*6eRE_COhmnTmH$0=Q=1^4PR_AS7bDgKaq
ztRbCG#%7J*ZgRtzRrw}H^}>M})6j8mzCcrz-=sfV5#7Q$NPX(e6C_HT*wp;u4!KN2
zHZ4{cHK3X6ej;yi8%3-Y+i@6#+qCHa*_TeG*d*fIX%Ix8J69I2R+qU;3S-<z&JWBs
zFEyn6dDtM0Ap8oKIkb)fgI$*$6eQV!Q=U8mT2+bQwu^H67Wn&-a{VOT@fO&6<1vLm
zzi>+c;We9z2(pLey3tCD%=#Z%6U25X7CdYDiD-49`qm|@({^XIK;dJWE-*vY$A4_O
zwHmQ5wl$bmG8Ovz1K-akcTqE@UKAWAmeveifMh0Sf!7Fvlg?hEz6&gi4m&;NLM?$z
z@bjgEK1$T~6KH71Ea0(7NUIka&bsx%(Q4|`q6-qkl{lm4t?LHcbMs1~c1qD%<!`n0
zsze9^Vnkpq8Z=)v0pGF{E#4YdetX!L`T3=L?o(-(68G8`D2;mMQYH{ne}VbR_H9)5
z5)`{*kvD*X<J8JNb!kzJueipF_F%fxMy63@j7tKXrbW-D(^bTfig(Ye>Ek(YS3y~n
z8H|SojzBmomkVe~;Xq6O^kvED@`XecVgI+M>rw6AjBmcIN<{FW-VJ)g`OIFk?D<h$
z(xto#MrfKsX2QvB%TZZB_8wY7>1<yQoQ96DIsau>!s9ObOkERk#@*WSOjb^e{+ec}
zuVyV2g1>QE7_j`sCjlQ>T&EIktit<_KrNlP3I{C|xprNn=-B_5z2QV_MRy+eRHMnJ
z9Vf+)AO_hTchzF=B~Fyc7oS8K(7u0t8w}?R+^0N(SjdB$a2txA8Vt=D!`X=aHeVwp
zY$nxPNDUK9XKD1dyFp2@KSjOa4{xDIv<ZWfzr^E;l{&7fEBLj`r#XWM5!`o{JD3na
zEYF__+R`Qsp~vBAV#b}Wi5iB|>t%~a1Os=5dqRX<YQYVYJi()0L&->vC;n_if8~k6
zdby0z+mOUb8if-@(arMk9A@z8-8;NeiV@Y;gbs{m$<V>v<)DQ-cGq9&VEN{i;|$H$
zqnf0^JW~!h4%0!zLiJ9L+F`lAaE03Om?d*lEp9(IjBP+{jph0;o)^7vnyP|8Va3$C
z2om02we7+SYTZ>LAch3u1pzX%i0W>A&XW#}yw<Hboulh9PU(ZDdcq)U;@rO&$Mr|~
z9t}O(hQ-?*8?gB>B^h?miz}r?5N&RMKc}+vyM>^{>h&hs!=Mc!qoZ}26O369M*KE{
zL69FFEsljI9nVm3Y~z(>2h08UA$f46_A5lcb*95L=DQp71zDmYVvXECR(jztFoI@c
zd~0`|@Jw+IlY{oApVHc*z1MQbvypPJ?Q0r<E?d09FJ17@2a%*8|4)eq^~p-|Z$~(c
zP=p1O?BYCAQ1kn9U3$%;#Yct@58Hq+s%z~iOtAM5LRw~b6%7@ySAJ~);JgwWmxrwW
zjoB(B3?=LIl)@Q|a)Z_BVWcPM`Jnx0LoIqueJ#R~H*IO7@|m44rn>ShK(~}hv8qjB
zt{ftqgcrdUH-Lqau9eV`mI|DBgEUS@sEs(xm*(A0Puq?=k=}Dvox~l*F-0~lYZv2}
zvOnrysa0Yoyl3%7f%f`40utt+iYd$@;Lty%iW91j_6vdC63Au#DT|--+DQ~<JeNg%
z3Jb`gQ4kPVJ}vfHD6>19l@tSL7LA$`=!MKdVAyu?>?58jCY#+Iwx_?0kbKO5bf&R+
zV!mOe9ChBA@!siJC3>dVJJ&#<8rLdErvdm`L4h2OtFqod9T|7eG0k**zXnOfzvvlQ
ziv$T%MT=gFK&B~gTE7SMYT8BZQaqdPbU=4LE%%*I^P^`ZN)KcrqV6%k?^_aXi+682
z(mV3gcFLU})vGL};VO#Se4rAkyo7$Vd>rpu+DT!1164I#LNuy#$FaaM|E><B8s?I`
zLB8ZDj3nm`E-)R}CzOQ$Qxkbw0(fS>3`iNdg4;>|gTVdypod#igcBqQ-wA*aA)UPK
zm9*jD#&(}4;n$+5XiQwceSXT%c=~Ilr+Cf-zumx6WH;l;P1g{c(e&IhihVBq)OD^0
zp(fM_a53Cmz*Ut#P1B%@S^vhD+Ap6DG)+Cm-X(&;_Dgl1+-reNMhcrozwf+9JxSTa
zbj!T{4VAwpu}@~Dvi4q!rt-e}CG;19m~N&zYV>09oOVp?G^YQn_be@MN`9TEx&%ua
zWEKJX#2GPce&Wr6Q_zgsj<>~N=mtk=s<z>Zn<<TgnFutL)A4Y8+e)gf+<U2Rdqi(U
z7)&>Q@=jmNd#&DzKKIQ>RSe6C1~$@qbstpEv`ByIeIR_cQ(d;2y~c9pfZomz#$8mD
z$@ED3FyOt7Yloc*_v&OWt>GI=^q{i_%t0s`oN0b+^<atMj9Zm}(5il%LtKP;ymIS#
zKhJ=)>yhn<YB{Mc7IaMrolyNY^m)BOtwTJeQP@*>FSW5GN2VglF|JG$Kov)zvxx{K
zR?@J$Wj@DTDi(Q_jll9AbxyzOd>rYTODE!)r?0X=`<n;j?E6+`IVJ;(BdkL*i8ke{
zz&Df7DU&P-4UkkX+VA4Q{{01|RZ(1zsf=em$-x)o_nzvC2q3b}JP`g@vy!<Y?W?N5
zTz+y{M7AgLq8RAfB5;{zppve4<%^8YwIpSfHQ#VtLo99a8A2vp+7f(i%~rHYKHbnz
zUTSsv^<v@yHwT8Hpj!i&XpBf$Chy}iI&ETpJV8_(GnK|M=Y!gp!z%TY5<%lW-on?T
z9S!ARgF5zWDG1+ZL3TJo*)%8N@a_nE?U7ei?OuQqUsK=w)|a|ihLls=&#<6B)Plz+
z@=^yoA?4~Nb8b3JArO0N^eeMK)vFRuc*5Gh+%r2z4MkNz(pDjAz&|(F@TFohb-LS0
z#)ma+=ZPtJjz+BzGr?E7Wn8TUgj<4qy7B7H+ON5FdIw!<xfbm=Yb9zB2Nj0t-YU{!
zWSvVW^3+$qNtKa1PaX|h8}}WJ9WPAH<9_e7LNtZ66)@;=7t1fcEU%k}(s~#>qLJVd
z<dI-rPc{4aN^H1q8-=J_o89-q9IW_1XVb3oWt3WVlcG3Mta$b^eRl6$hR22mUV)52
z5laDV0({RzzW9os5cmYYcsxErGaH1oiw#(HmPj1?XsZcRuzI3+Cza83w|e&p3_}I=
z)PQ<MF2g4;#=qi=1A9t=zA1qUV$x@QUah=jDQ|E>kv&?{MtdwoJ~}q~ND|w=QQA)q
zd=57bJIfjwp*IRCLnhz0V(A)74i5?KM!+zBsRPYs&Eh3pDUVl~Mlek*KRkbu*5*)U
zVDr1|u&^KyzrJum&4#D<5C${jusdale9X+8%Zsi9dvg05oNXR+FL`uJ8B4d)ZU`m<
zvC)c5<;4k=3a=NlQ={C6UH{GrX-Os#m1@J`*PSeRnF&XU^+)l26#}+XwW7$fhVCpw
zKP44bQorSe@L{+|;2zF=dqBOtaksiE&^>0^o?0&~P#p~x?WQj<z1w4$V);PHH-fR=
z*Ff|i$8Z2!0qfFFT2gB=Hi}N9a|eZ}m<mdH@$TbdRnLgF)ZMcan*#5|%BL@RsQ%m@
zy~zT7@sIQ>c5l0ThLC_qV90saKVS+$4*r%BqVh8_mFjRn*J=Xp12uEjn?-yu;cEX0
zJcc&1qBZ|YZfB{PI(`3Z=j3v{eHxBor2&KVJ0kOnJix#*&F3a*{9Ia(WwgXGn|)+i
z0D27$1Ajs)8GRy85q5A*ciArntVDz!J&v4zWT#6(RG!DXUHJ_O7C(#w!E=dX#>HF=
zqeX?h@l&&zpvpx_R0=E9DZk->CShDUPd@zy1V40l3aNG_|K3Zcn;fQh3E;T!g9vff
zq#HY(Ha#?5XF*q>#AWZhx=#@vbeYUKr=m#9?hP-keCjo!?Re%1@_#~h@|1oq*V|0D
zeN);^$$#{9dEIvUqORm}9dpjS<M&7wjf@Dci*RVn$QL=Ly)U=k_21C?Ln-@Kcm2oO
z!ETLuU>o-E^%&Adj>_!Z-o^efz=k!rNBhy|vonNKA7Y#C{nhE)v&~I9f_j<>^38oh
zz`aL-M%9x@V)rD9tdO?>C0y|31a}sIw#khjcs1ns)t)VeITP^vce@HF9TEl{X^l&u
z2$Opju<?G%M_S-*km8n}XQ5P982u1|D}wkH*<AA_6wx*`cY5wjPQmlc`MAG-C@ygF
zvs_V7Y$SFOSntczg#p4c_P=J#?)1W{->i$dV)9Q4tV~$$QM_qEDQ)-S`4xF;IGpT3
zr2)vNh;1AQ8&@6g)NCZWif=G;1j_AwzZ5k1S(`c(Kqu}36tBpUa22%P=N5v%3@RJ5
zP*}VhKmfpWn>G{_y+}iexek`yD_Itz!)SsZas)@gFFH_UG{HOk0u-vsVK+4IplP<W
zy~2lpER|?@3=6>kcB|r9I3PU7zJxpuJY^l_QI^|39X+RbV9_Y>@SAB7u(`mkpq&Rt
zz#t$Y3F@DHO_`iem^x}xD;db|Ak+>14(Sa~IE1F($yQ(nvES=cdjmNZjPz|HU{fA0
zBtpd$>s-ipvvD`|=|1%=opBy?y_oY5uC+~tSY96PslO(Ub*jbBJi(aJv%izR4HcCu
zdfjy1cIM87r}?QBwB0%cb;DSd=)ntLS7m;vE8NSogXkygAcY+^K8YRYMz($t3U^o5
zY0(0&LYS6lN=@U_mi*y1kN#V+tfo2T%K^UCW!L0wiY`c_(g$$>!x^-x$E`eeOn_lB
z=$H{UBYEaPdWQm4exB^7Y7+<Rvq|#eb{|%4PT#yush1=E*CuLidpz9vGj;5?(`FqB
zlsh)Ui5WZy3}yT%;|3!%h!z9IMY7wWdc^dXOxDjC^<22#c@VpU-8?-b-~tM!Au*y~
z1X3C!!|#*X9#9sYVF3uxhbPhIB|y#r`Lh0Yb}%({x#tL#A)l2FWiDqDj<|AA;D`Dk
z&F$|Hu=_hLCY&{F6eCX2q>Ux@3A1hf_aptkKf2IVFLajezXEf4IZoh*C|Dl0Nx_r&
z{vCUe`Bk%_$9}Z!ZF(4ufl5Ct(Lhy{2HUfXI%JYV7<)mdMx#5aFZOMSVi$x6**?lc
zDWhYyAWLe%Y)<NPh;)pI@ryJlth@MxJ*@j9;}<yklz?Wv@lzjv9gh-27Q%Nt2e=V>
zL4ldzjYXUz^H(Ka096b&ae}^<TRT)OEN82N7ph-{(OhKPqCaF3(ab7?&gy@=R{xPK
z`4Qx)I){qfed}i;PUOn6{3P=w&{?@T*`0!t$RdjUid0}faJy+90gBT7u70Wa)aCf_
zg%C41{XS#jgU!)%4#FtywOcGa;E+iHVlngO(TDUdLqu~-N&|;Gg#k9cGVSz)mfEp-
ziXK7D+)9T4>~ZLhI$;<0gMp}1pw5N<!23}MwWGo^^&tKQ#OlQOZOvz}PWJ@9n;}U&
z>_2{?_2hA47*T$IW(5M)1PzD*P2F<TVe+~MO(jR}Elm<k{npoT2lgdp#0X9t4$>HL
zDpg3bFO_U*+?X%`D3$A48n^o>PLXA(P6cA8#~)kjfm4twBD194ih}rD9PUp8=@6EH
zAaf`~)fg00+xf3H@f$5DF~GnhNGIpO#eJV$Wi*MK=;{U-A^PNhX7CU7aJ#8JDXqQK
zIHz?465{jX*t`(zFqhQVL;2qCWZBUjVz=8y)|-n<&xKPUjlmvrsF)C-OLtF=@?*y$
zxoHWuW$O&C2y`F<Zq)vP2Ah%1mISpc3LPqB<5KBlXo`CG3j9n7+C0oZZ)Q)8wfRoH
zYEA=M^*CW)I0m-I4o5ho`f}eU`=_zRxkm)d(%G#=Z>P3hK#c1}u>o1HR%zxW3;Ed7
z%S02YAC2GMTy5~1BO%b^XD4aElKOb!bs(wMRtM!nqnn!Ro+8KbloMSFcxg;Su4JxI
z4JzbfgmFvqHa)Kx>-ZzVCojhJ`FNI={Lz$(8%|KPL5J$W(GMPWZ~}Eh`DE*cj0>rx
zuz$ajceL@*-3u&NlHl|ej8V_t+~F`i2r2R~$(TQ;WyffX#R9Ei+Ch~^i1Eqv=0l@v
zFq+5svyijmo7KRW8$8M$=8-d(u5(8E?qELT>B8DlH0WO=#tk1k$MC`e_DF1#Z@WGT
zQtB!uCwG;GdvX_kl&V*VoJ<rmTT}k54AF=gp1D6?vk-bT<@jhht~C71-cAYX&__6I
zdqd+s2b|>FDngixd^Pida{E`U=2XRU*rgoxt!oJlCt>gGSqX94znSi!$j2p5OvN?w
z^nIFrc~@}w+Py&t-BhgPIpGzM(a8Ed%-Em_2vqH|SL9&^9dZd}D2A&uO=6e7joQYr
z_UrRr-ryYOIJG0t6t4>mo-SBR0P6Lsf?Rxoi}(Har7IVDMl9xAYKwX)c}qdQJM#Xy
z>3+{|n!+A_ETt62nu^wOtrqG^75b5nzpC|LqvK*m&!fP7ivC*x#Tqe5QHKmcwSC<|
zQf7wYoD79TK_|GtJ?b7m5=9crHhi_+dR`YYzMIaCc0W1VobL??y#2JkjFTW|V-5Is
zuQ5<c@h1bOnvvb{ngINRe~ZcF#riOW{NwdYTy`XPEy>!ws6pnyCtU`d`9O;`K984j
zJvd&eQtkh;{>gN<YJEyf`-!jK4)4H3H6a-0G^OO+l0f$p0UZ+zBg`q4!e*)ei+bxv
z%En?Ghn&E)U^-A)k)kN0L2g~pTv0$0^l!6z@S!#S_Z0wmjq3z@4_;F1%!L`v)Z1>h
z&;szfRTSiA2G~{;%8OU_{^nLZm)W|5EeDV$drg905D>I`YQ@8)C#?sPuYN4j^0#XX
zQgC_Vq_!4r4krp{f>sSR6HyOqa3PVhIltx6LxU}4OW`D3XstHlm@Z%?6e=r<luH5q
z4}7;x1c9Yi`IJh81!IHPtGNkvBXMj3AeT|i2tk<Ut6K8(<$O!dpTQejVzEq0Bi0#)
z(<sQ}-_>N0lohIN#^A<@=JJ{hYZ<#NDV50X=Zi(vR6%bW4O0X_;50jso!p$ba{r?>
zC5VTP+{5%z1HWD(&$7gnrUp2)3=oL|RyE2gd?>GuFDFU1G{8yvEf5{bdUhI#WsqMe
zCkq2M2Wo;^v=p^#%+_frTsI}p_R{nprH29pE5W2eIeIwYv{!@$47V2?H(LIQSBKMp
zxhcO~8tG_IE|gV=<N*9=j4<jm@QK69p#dSfQnM*W#8m8X)qMTY*B^jH1atf$E?5B4
zU%vr<1zpD{HZ;I2q4^MaK@5%MqA<vCh0#e^j;lcA?GPHGwfiVi@a)CI_GHa=P6b2A
zM6Ql{T}aV?ulWTDb_9Mv%-w~HrJ~E@tG)AP+@}%pFr?eQV)>f!e*f0#6;8z@V1~y)
zXrm-g2dFH~`&N3S&B7gk!Tu+Z&;ZSEdy!q~CY}A(NEI`Q0_*`Cyl2^DLb@8cE#A`4
zT{}7r#)}{)gi{l*^m-0v;v!B`2w)+G&m5PM$*b@JDFXmE^rEsz0lBZRRDkdkl1Qw&
zD8ju)i243V9Olk3U(_!-^jj|;<;tnk^-zPP3C?Ds{u{1Zp}$a7AP}W~1(5rpDV}>W
zOR2YaOpK))Xjc|bHCpc9gkA|Cc+YrRTkhw+Ef~e;`5#w}<%<AF0R)||TY~ScFg?ii
zZ(NaAu3D8+Hx;GqXxusax*{2%YQ>I*+TcJH(qsSX!}`C;2c_(UmRc8%GgePTm8nNZ
zS}85=j8HBmAh0U5DjoNTYS59#+#u+s5yQ0}gA+<7_bL~pgF>eL@T&c%lSz*AV61Pa
zZvM=R=iw@RRKf^i+cM@jmy&nM?~nb<maygaz=H|nZRW50XYiK+AX)K05pODm&<9~o
zd}>cSx1=rt>ipaNWg@yy>pkT=x(6N}V$Z=?gx~<ohRD2cG#HOoU*_e)orim{4?GQt
zFNr8Lmg3a*^xY-NyG@(aob3A?{53j7;RK*4GG`_zY1`J0d#)^v)8rY@k?M6-*4OZ^
zt2Uu{#;*u%UgKHq&ku%%CNa1b4z11Srj`daX_0by_lwzKFE07Id>H86yYJ=}!JKSe
z(5SvLjq6L?T3bzurtEA)7xhuZ_>RWjaGdOR^j5s;UsFH+<o_sHhu0{0<*hQujb>+U
zCIA+(m36$<6p!;!hj+KFq3lD`USs3BpD^c)`#IV4H4jqv^eg<9I}~e<zE*w8oEu55
zS+W~&ig;h8<qvq1{r|~Jsq$XvF;3+W4+OxB*2`}I^@)3Ux3PJg@ueI)WSOVmP&|CA
zq2BU2_|~V}lB2TX7Pp_77>^0q_hc(sd~$wsaNKCM%i1oD#Shd)7mNshJ;^+>zvFiH
zSJUm(!;X>p`ReGn1tZlP{jvNIk)yR>P9oW|mj{v<ucL|&2oEhK>c-@XPyc@DSyx!R
zQT$=~+2Kg@>JF7--R+3dzaGC<yoBRLax7K7be>l6Ye5?(Uw;pV3sP6I&&$<pLY{%D
z*($5<_xaD-nYHhe@ImJ!w@8$h;QO<2UXy>^5B(0WEA4l*Ki67F@v-*2tZ7o+8TgY5
z0FOiwuxu9mbIVkBHOO@*Ze+Lff&9sPH!m~eI`_M#`rQRXC!bXxKMcZ1$+K22^9a<|
zh($=hrv_kLL>~;Tr&px<pWv9RiXUI-rRiUE^UPe(8S&5Hp$^>3<GJR;9LSCPgL6U<
ztB3Wnoc&}Z1=mMYd~N<E7+F67%q{Ge$+jAQs^;&)XICR)xBY*s9<G^`KM!fC9bR3U
z$SIx~Ta`R9TMf?PJ20mCy?MM9ybS-9%==GyCwjev)|l3SV^&IispQoE_Hq_fJsXK>
zbK$}i)JnTPztgu@o$+R%<7MC-NBzr#+l!Q8=eNN!?{sI-w^F0{AKwW7kVy>)SDBmb
zW-eU?3;Q&(9dbxWlRB0+-&YSVxaf6{XsnEtblaLt<^QIhl4m?{Vm+1`Tk5;CeN@7w
z&m3GCufyA8*cb26KsY0R0N*47&`c_Sxoc~GIUfm~R&vWPlhNm|b!ni#UD*F$o+Z!-
jU=T3>`xN{C`J^zBlVT^cc6~noyMpUi4YW!$Z9@MKTYx_O
literal 44374
zcmcG#bzD@>7ce|`*@dOMTWUcNBt;Y!R2m6skP;A-MhOwPlqg+N5-T7j3erd|7OA94
zh#(Rof`kf4?0fP1d!End{r`QJ<=(q<V$L~pX6DS9x%Z4NYSB`0Q2_vGb+pf$06>mB
zk`b|F$nDjvhAwg=8R?r|KyGqJA1gVz5IHL=IV<FvCl`WzTahB<x0PJTQSs3SdC0R0
z39$-6uB}#i$algMh=w4P|Byng@<Kx7j^H7AA$iERH6(8$q_s7q6}fKbS;^%g^dWM2
z|L~6Bd9BD_UMq5)$eU=*n?SDHts!!)Ay%y+Aqa76o>gmJ$p27Uk<SEz*gAn+w_CSc
zTel}#x3?$qtS0h8Ch`ylAxAtAB!mrua`f3o{wB7!5vJR%c?jwe#Zkc#9a2mpksQSi
z;}BC&`e<AE1Hc=5^baL3Y`6d*0Cdi)n+E0mXun=3)#57>Fk~<?{e?5;(Xw6=@0Cf9
zi$h;)j%gc2zu|u+6QVzn_UUZN_|iUUX0COGlE8#_J+@Ka{;_Cm`-eoE1hpl#_L=Xi
zN5&7*X-hnT+<^=^19FAgF=*sAdjW!wTaYmxxdJ<u|Gz*YfDZJ1v$KGZ>e0ZcDC9B*
z5IGnC{@&V6RsgOb)r&m;Xa+z6B2UKuZ-^G4V`n9N=kVa*ppbMp^MgHX?=Y)Su41mN
z^Vvfl-#029x57#9PEUEOKKObNczEA?W~I(5y|;98f&Vk<*G<91`qv*-+=VjN3jZgf
zA;NGW>cC>(SA<`cK78Xiwe^|w2Ra~Z{lsn2MIE$&=f=UszPpe1RR7biiwPdQG3)4p
zAamDvn`Q^2iJiaR?@6Lk!an`K5gFka5^4WI?AB8Cq2td#bj*O3i;}2Dp-S-P@AN(f
zHnS~mR6hoQBT5KFc<*^D4l1E%4-PtS|J;Q;_FpEGT6@#O$dJY*P;;Qx>wc1%@3`JX
zse{imq<5Wv-tQG2zM0qQj9bh+vOTDQ&Vi0#dhC)MX@7y8LNM%bsoTC<NtODw;@Nd2
z(tdFEdi6@=!|KMIsG0o0!(}BKznQS4^^c^@-51hHWAV$uoTP;%`~6M-AN-_^yN9E(
zvEK{Bd>?AZeLS-GdjDpRsQwSJ&fCs=U)2uY3@Xa>|Ljn1`MY)S^PNZ0t0)SQ5!!;U
zS7)l(u>2}P&@)gX#pfLGS-C)zaqITvxP;h$<}+r4yJ_%4LI+KU!ZPaPYAWV5q3pxM
zzDt9h<G~wWj8B{RB>cJ!?eKSQGX+ky{kXb6Lj&zB|9n~7T<FOjmcTSMpUeUm=BpA4
zLrGbM{1dP4?a}L&aI1D_g<HzT@$J1b10!toa;;3aB^Ed8pP8Nc&&I`)pint-^S3a@
z!HPE6FGWjBY|29%ah~e_NBoh_TZsCFmc_RhE{jvbS>LTQw_fCqE7>{Cv_yj-_RigX
zmJr3PSM7+BiG@NZ9OfCHWAT%7#;)v<hHpOcOE$(O|JMsLFtd-d4d_ctF|%^Z`@1vY
zhr6RQUW}pE`&-_87h`@Zy$c^WL0V?_t&KU-a^q)5nB--9Im;1J-lWiO5xD*CZ+9o@
z*7R&m)<Sou&EA@t$GrnztL<NVukyO*4wY}?3%yBeJ$H0(hZspre^XAHKPSi6jKzPL
zQ+M5v9dsTza2I-v{?E1Vw1e9#zH=JKR4Vc)Lq$tPMw&jB^e+daYEEt{9arJ?XH8Dk
zR0paQ6SWhElkxSWjrUzaQ`oy~@Jotc>tJ=lmT8+WLs#im5-a<^O5V*mx}NM3yHX$&
zO_YHCZ+FmJ8eGr<j@5@h*!g*CFCQ~+%NpH6&$bH8HXYjH)xnvk2Lanj`#ztjY)>TX
z{44=H7W{mKvk&y<=0^_Y5GCGS6>zoVJ&Phph4m(IKtm^+_S_$z!UFJ#|Bn#-I(7dm
zX{)f~57W+xxhGG)?yufA>sx*#`&s$j1^w?^laTaMgCx4^?0P!s3u))@tPlukdrdaK
zY@NOHTRrNAbbmqPu~^qL_$R){q{7}N2n3y86lYjwt(abs0N{;-0V*Et;2R|Us#eP3
z42IY}d9`zgwQt!4?I3;Cm$RHbI6hRWFJOOKHT?ktocM*Eekk*;!iK=_>(5Jo?Lg4%
zb1IzU#&y?><idpD=DSb*J1PFJqsQ-U$4k;vh;^?Pe0wYRlo`ggo4(--^+V4(Y$>ci
z!iD+Dp?qW(=-(j_U$vXZE?Wa9xxdoFOmOt;>YU4H0aj)d0M+2NDm*B>(fvbHX6f*+
z_gQmgi~yg`I$A)tdJyZtTfM)chKz+%;e`*##t(Nl>GeF`U}4=XHh4TCZ20Lp*}l1t
z1LZG2_hcheLlCAX5alhGYX$8j6z<1%hN?C4d!8T!sX;bi|5w!#=(tt32s)G%eO<&N
zl=z1%x{mef&3%qCSr)|z$b5|$GiG3qx0ln)`xBgaPx&9eLDXM~8~4zk0ygWqPuu6K
z6dY50csl#_FB8=4Bl`v_H^&>&zpHCc5VZC?_xGoW5gJcWlO{r=kI=K%-jF>5^OAfn
zY>c;M7jLo-4R&-^VOIW|W0vHHyl;!Wnz_xtmT(ZTbhq%(G4RLF2qBZ*yaD?#-x7}X
zqFAR}6Ti#sy}!KL1MjHy!mfT#c5=qd`cIN}>ATJ6$5i2X5VV{o1jlpI8|?vYL~x-$
z(9q9ot^8IZ=eM6z0r=$j44LISYMa4R)bHK|m%rriv}@Yt>sL%(Et?wq#`LwTKUu1J
zO|0`)a?r{7_qT6N$l>_-k~=fk(4RkYo&D3M`sb_H*pBw~eBn^%3>NtHaEGhbD*7|i
zOuz1<2e#x~*&CpRCZm2wr0#1{6HP_}CjxxJMEGy=tdfolZ7K9@oE@ZQwl$339Sp~2
zd9EEd{O}0(*;uZ-UQ`6U{xy<LKT!vNerYOu6~ZhPN%c^{+bz)pR`>$x#Wb%l&Tk<D
z?aMBNXRoDmcmwBL2)+X=Q|)Wc|Fh!O17hdtd&dq%*Da<rUi=Jj`a5^(^N+#KfbO3^
z+XyNTQsVV>mt9;7{mUY5S@wl0)Bb9%$@C1L<0l<99o`ybjs>@G=4E6e<v~WrreDbp
z^(0W-bs>nycO$hWxe)GUcaLhCZw$9TMF9tz0&wQteft2GgRN)BmxW&y?tkCw9^U3V
zdGLNl^#xzqm+%eCE1TU5)%N6CpGF_kP%kfJ@_WvZH4j)ap?r8I!biS+o!{G<LiewR
zAM8~(<qXw>yagIXhh1chzh$7*K!ub2N_UObs1F%=yYsi)zhy5S^hogiZzN)cZ6Yjd
zQQ5`+S=Ue)EN$+MTzwBw|2GAEZ9&g=#||!tjis>?dH(DELC2tV`i?F@IQt)yjq|9Q
zFe;k;8S4MRMIj%x-G$Db_yoB0zhU*wB}y>F{2v$wK=(i9WGI09pB1ox@IU9mK|vJA
z)LcOQ|9MdM8#Qa&If9H1z_o?};E+3!)>sPA9hLa#Wn%#g@-Q1#&I%}y00K0Nd7uH+
z5lqFD3XVb^z$X?>6u=z8xWA)`>PJOuRL3Fsh{GouGt{iWQBhM&4!|FASc~C;eEzAi
z_u?WT{DW!4fTK|w5EC77zzBJORn(;c`ymnwBRnWG|Hq$k4254;`xmQf%CP<umKpUa
z12zZRhq0*;$Yxk0`*r?>IdE_SpfqYv-_b#gN*B^zSJS5fM310#5=GCw$Y+4q1AzV=
zGl0K{zJW@a4<F|M@B}P~r}}^bLS#UOok-FtM+>|p)yM+i51~@fNS$!mn-?Soz;v1&
z5uSK<R*^0W#Q-Dnt+)B8kj?=d9(fM3YfgVf02cqAO-^|O01*J9^(^PJr@9+E{3xHJ
zP#eA)P0c~`%dkijg!!z+&!`^mjDB3}SNkQU1OT2~ko1ytuGj>8vPf1FK$s3-Xuv6?
z0k&6Fj)<2Tnn_(G`AW>})tPe$IGe5vz=!GOY+#%A2(GT3+S&=Q`-SI`X}dHGvFjN%
zSCzHvHj6r0J%y<3vYye0Cg8BuUhNJ*R0+D(+(Kuz^)84IhlU&wNXOrS1N(h8r1=Ju
zCf<#S4{VUf!=mDw(dDf0_RJFrL?8I-8;{t^mXt5jF)y%i%r$67|8On*4q}%}FW)wn
zmevna3jsDn!h_aO3B<Td(GOBC7AM-hm?FmAf_C}`1rf6i_%PR2xS?gVQm-PCRy|ff
zD$Kk4Eu86eBK1OT(^cF?h71GDA5MEz;p_XP?$HW=c4)^Ix3o(262KH>kmX{;5m83-
zCdo%N^vB^b-QPPiCm;sECyAbY#=?T=V0aIi<PsZv<SyC_-sL)KirtelJa}`UIwu{G
zDE;#ljF>RxwMRO5Rdt?^0TvcOehb&MjEP+W;z+ZO{DZ?&?<QKRTH4aVz%&0~6Fh=L
zc*aXwb}H<5(7jJZ9C~q)?#O}VP4rh9>vqJBv$5d+D@a4tBvIaBe5?-<Nt{P?+Ju_V
zu44iK<v@N!A)Zm*DAsb~qL`Q+hU#z-LPVCP(xeEJfCztr)WP>7YqQ53PrH(OU8VMM
z&~G&~3?X!FI9o?`vEpi4s99M6F+q_f-TQ%^2#yTu{}tro!WQz+wH$n7MGc{jn%N)&
z4J%AddJE#v1k4dh?kSAGtoGk@3HLAs;c*WW2AGW?Nsd&v6uZSj<o%fRI@9*Ww8m5h
zE}v$nlM<J%ju;O!>-+sh+nmUs>!vEX28KE-ajq7%Wf&J(EbwtSOUohlT~+Az#rxhh
zaX}x7;)EN{+bf!WI)i(l4(!<aT|<^ghrfEy9wI@q{A_SR36oj0q3;u$_8nHbhZ(4E
z@o|Cq6fSaDV!V^ft-=+4_JB`y;;)_SPq$F8x=M`w-f?f7R^ux+1A!u|4Ti_0`wpvP
zDhfC<Rs}%y-G<^$--C+}x?Xo-#so`3v}6VzzbGKFk3P>;hIE1I4LN2T;kNH*a8rmV
zbnmYIh1a~r!RJc0Li9zY?ZkpdoRe6hmqTLA^o7E#9Ljv)(HEhFNTY%!UjNc}s4~45
z=rymbHWfO=OUu^IBb2A^!joKzA_#tde8wWEBJ&aTPwD+zIRp<1C`ih7BHRo%V*9(g
zQ+09n>$ivk{)R;M77vutj|ZY(hb_S?*WXPdrdjJ|_LUqN8;JB6YoID}TjQ<XrHP=X
zi=A5}JJLPQIUnXuQJZ>Juwiqf3#<;)m*+eRduve%T+Sdu2?~M?!}3ro+vS8gCzML;
znKOX%4wiE1H#v%y4T>RWV-pKId-`Li?Dj{@5y6&_<qtJxl0}0(`|z#IV{<doZ#WZo
z?RTgW7rwo>E9J}hEdU1TmQ;h8J*yz1;_*+<9VGsoa{BnJr*Ualp}AOrL@j2aAHQ|1
zdI+6yAOH-LJi~t;BE2M2ME#FJf0^y~pxVHWA7iyWi}JT958YHjP)PdtaP2ASjl(KD
zCj)Bzlh4Zj+Vks${iHG))9NSGgSnQuKMwo7UzbU)lcUM)qC<KAQX6R_2K;I>8~}!f
zJPaxNU<PEc8A(=aw(TM5)w^*Bl<F-RJinz9eu7$IIyjh?pP!K-{|Y@_OVa)Qv(sVa
zA1)CegPON)mbvT<-g-u&(cp}n`Q}WI?K{%mDPoz=!`6>8Ys*h29!}N<o;|j|a*u5N
z7=swUry|t{bF&jQj$G@BD(LdFvGVUG#!C$8`l1<NF^$`KTeVFVdi#em4ux!)jn91w
zEXIFH*J0LjYbd>Rg-&EV_2<vq)_>a@-n+7zSONN-BV67Y(CpO{^s!J7>WBT#PJRAT
z+s(=2t%s>pJo!q`yMO%gL$fyp=z0#i$p7>dnElB$ZSfPE-nTTmk5N#+z4P`@0Nthb
zK%c{^;CpDI{E}j3sQHmLpZL3#4=L9g8DKMXPe4;@YwN{X^2Ey%o0n4(;sb8x%ofPc
z?O&3~ix1h8=rx=CnfMsILHP`_E74`p3W6pr_nXN%;5L=*ug@>?SBrk$3iudo=OW~-
z7Smhn`ykLF>fl@a{cm+P54pL0*x{m74~)Z$Kv^Z6kOuIIO$qIfS6Rgf2<+872xl63
z)N<`Xi!7hYfvl$#S>EzD(X|bw#!FnSAmtqF_B-<-7}(ZyrEs}`B~I6D?yk`-4K?P|
z<GdnP=E>^Xsip!w&xDbSL~TXh>^}7-IfWS>O!ygSA*lsM+f$a+tr$^0VnO}8AA9Zi
zylupZ4I5PZ19epRXF`+^Zk7RPKp$9(y4@I2GE5n)f<OsXxFs~_B?{91Oe*uKMWwwD
z?s|Sj16nVGJ_uPyQ94~cj_^&L_{W!jXX?50E6)-zhy!`zu!2Lfg=81LIvi~e(N&Xb
z7iaR<9<EY|Ms!EW9z)M+8f`VFq7oQj$`8Om0xa$cj;*6-J(m|cy*v0(r?5^u|Ev?m
z#TE-n<Z#bnS7e^-pChT??fv{{cP4<J82!`P)krZK3?w_)SEoJqY$UU2`0#XCSb5%E
z_}PIclfDGdIqbeT8*$_=*?fwhJkzwzuB>wCWospA?R)l2+bQ$=Q^6}jfCK8mPcWcl
zl&-ZNs@yyW{Bq{)fb=*{UmPeqpk?SXC<Vc#mtOQ)I>*cs8?H#Yi{`M;27S?VjB|Iu
z63^mu5L$%+^Yy6`llPV?Z_-@Tf}sJQmp)1m(cS0kKd{^Y+xj`M*&=L@XYo>f(~=J?
z!x$YpKAu#-F>3(VH@5qvHdKmp8nu;yma^Oq?2Lj(1vDdM1<?*p`fo^xnZ&Q64*5k9
zb0_qw9|<d6#iJxzAt`Rw@FD3L%kEI2vQSdz%4O=!><H3pRe?GWEgO<6!2?m9RdGd4
zZTd2JLkB&bFw{KF0ASj_I}EUu<5KfU-6g9)RP{v3XOz;cz<>-!W`IKeOWyw2KT0+R
zIL>X(gXt$g5g}2?3p(n!;$ME8!7~7J#b4L6!{}!3hvGQ^R-F^^8Iccz-zRGtbtJBv
zn7wVdE+4EqZ!;Ui9VgD>kN^@C52o=)Sb~4Z?s{5I3Ex+!s9c;>$URm}T{vVlsHq}{
z#V@WaVTor535e7T-Owx1D$mrOOj9#|q}5_mjMD6FauNbvvoQ?sAP#Y&v$Ru~k!Cc|
zk6xW66$fYMkzGr9lWP7Co3hY&gwwEF<tr;*5|CebLj!YUa0-GgINMiVVD+!?yZTBl
zk8Vrds!f}}ALeenk_)2|U<K5e>@|e}`aZ-hg8_86IDydURJwI?@BmH3LyIA_qfxR#
zXa}ZKwNq9GGnxA{;b@t>32l9?voB+TA5>mIp1mgW31sjJf;!lPv0>k{F~`B+N#*Nn
za|y1BT%)OjDG$@UQ`Yv?W>lIXoQehzRWG9a$k;4?kep4HeF<_EF5GXsa6Rf58&FzM
z$>z-v5d{7M?*$~pKbb=Xp-kC{Iulp3u?Toub(uSxJ45^kJ|W=Bg*x+FQ-*T!QK8_X
zi9Td14$R^2_z5PI3`N@ICJCy}c4{{hv7t7!ye2qph#I_p*rI*}rOc&)3h-c&hpgEu
zpCQl}azx933@Jg7E>O2+YB+vpzO%$)*zGvlK@+p%<6k=@U~|(9R+b7UGkSv<K2rW|
z`*ScL0r6ivhRR2O)kF~ro{^J|t8+3Vyt%OOswiyu742Y-VelDV68lyJwiy93Ba#6r
z+;t7Gh`%%U3+145s25pD-m0c)FfT5KQXO}$zZt+^xa)p7S(CG<5CxMO2vw9&HfrL;
z)6AYi9Z+fpK1`iOsiaP6UrN=Sco+*LpP<Qr0`7qZD8+Y(;6jxLg+blv2#y=`g+JR(
z#%tonMi{sbv+jSOEV~S2GmHg+9AS*Xl*&OB1K1g2&IlS`%9qMYp=0h_e9-l0a9%-f
zdMip6(VCpaCi2d}6D7#BK+cGLw-kjhT>t2&v2*bp(6KU9;v!&NEU-ixToXD5WqDhl
zm>+)DO>fAd+E51P<?q~c=C^Tg=9z%Uf}pjgjQvT@mjeC_N2GFil#Y*O-~B*M4&y_?
zl$ES<!Yzht%ws>t8Zc2Aah#Om=i@fZ$|XEv{zen449?>Ekud_a@-~Nx{?M4b0Aas2
zFT`cl^2@mS>j^8Ff@`&_P+U4y(ZXkodmI*70}rjSua0{<=;L6v40l1mjBgRVBL==?
zEhgLhl5Q|l{H=3N75x_XIO$Y7;2C}1T~l%92`Ol0?Z?ohdslmDL=KAKFcSR@pTmZd
z;rY(HaRDNz$>m&>Vf<@Ke_4Iy*q|Y)wd#boAFsqo(VGE@mg56{=Chjom{~e7H)CFU
z>!eX*44~0EepqeOpyR46u*tg<9_3@Urz~o7|D_MZ(Cn8}hQbTsrLXUv6c@&m^))lV
z!$#W)_Q-VjiuCv7yFJyHP9msn4ph%ocu>y>U~peGfaX_KGJwT%nY9W>P6TmdI2@H8
z0@HQ1JiLU_hZvARjuzl{KNNRZHl-Fi8)dD~jzU)2*_o9}!z&TB!e|HiTuLHyGi*K+
zWbkx#7=P9CyIJ7NUQM8|pUenT9d)(h;fr8^mC%IPq(ou2@l6$KD4a!r8_0~7PykIf
zM6J?jkZ|Xn!i!0|+y0PGmYV4KsM?8P8;h5}d60FuJVBol;z-bZKrGM&i=1SyJ|Bu=
zqClRz=!pkb-yY#}kRHeNoDt}OO2hR8|5fgZ)bOO20lA%5M-*SzPBDEb392xO-zgLW
z6_eDEQG~1rBJ~ZHw`O3}n0N}xR)><<7eZ$r8ECqiJ=WP^idpL+83A6L9%7v0NAx}8
z^kWuaa?jeinMT|C{&Es`<mIT#4xGq>-|b)BJW^V~PzW&7Krf(s&jO`-+?-#JWLou*
zXfWCofVA>&z~Es37o%Iy1W(_DohQY;T({{Y{rUH+$z1fX#2`2Go-#Dt?AT2vgmGv?
z{W=c6zgXk7;JGdi+b*9(4Mo%*iER2bTA0Kf=p_NN){9vQS7Rqj?0$<^jt+;b1KsZq
z4up?nF1lEvb~$e^C6cv(UB9)K*53J2MK9Kud8zjhgTeicB>*a;%xFLp)p5U+7tbH9
zcqSgu*inutZAn1iEc&Sa8uC+gyCYcx4DKAFzWR)QIx{h;!&4J`76VfqYM_jUyH|Ti
z3cm`uP(GbZ%i+<ZRmQ4HM}w|rmmS~<B^3z4Xl0sF_>l9s`;*vve+>DR7=f|ihfWWh
z#nH&xV`v8kiCp(<D1n<KcTLcL^W*UA)ukzwbF9@34Fg`g)^mg6aOJ)cV8e~7gFA%E
zoDtM)8icfb(q5>ULr>4Sf$NESEllB|gKE{FGOfX_1PQ$T7+|Q}<%BL|yLo7E8K1X)
zAdk$A+QCme#cA*HqhwGS3j$!;*w9)8!jgTu1e(97xDyF26oStb*ua%dF$&+lI>ssa
z_hMu&%2>R&rToa8Q@9u#=oV<{KnY~ivWQA`H@946Y-nhRez>%h*V(RGQ|b1^dgW3?
zEf1QYl#9jZl?P#cE<SmF>;*2y=qlaFRSy>P7+-25mw29^GHC4gJHr8LSU_<kNWSB!
zPJG+`t5R`BQuTF}KWZEgIpu1eG5Ewki)ERp_$}b@gAN_GaLty18^VqzYz^J7a*Pk<
zGs=ttH|`j7-xS*&wUso19mpp#F4($$DfRER=4;YRQDR_p9s961EW6>i<`LG~g%t=e
ze-r#o_d{*3DlM*G9sGUarL$O;c$`^W*A*)I`HAbkkKSJ%)cMP5P4=fR5aWfVV^qi)
z7M)}=Nf;_*Ek8n#q=3F*`&o~>u<L)gz*1uBmad?!t5>1lw*XIpW549e#6+8WCBEiF
zJO<m$aL>c?vpml{UxqRriTaByq$9&(DIN+s2Oi%Kx;Mt$sT(|YUBvyfd7~FS-|M%X
zj07K4-X<gfc>dv^tMz*vO^^ghawx)@0z14}Y)zNh6MaE37W{Z5!w+`ut=NWN|MbRl
zTO7|xhZ>@9T=|jHe{&OYI5MtVl}|<Hp2%O*e*R@nm@bz!hIV@~>uQBT(mJ()G^kz1
zsdxDZyK!cGLHvMNbXNWTRdRn$$mgCjGJIJd^VAo*tK-@XUUg(qOt<{D7khH$CdPe$
z#CoWO#WQA1AVe~nKvnka_yDiE`eqCLUH1Y%dZ;G}kCT`tg(OjaZgMZpeB^NgT)T1(
z#1RI_p>KE8Q7Ox&3;WL^)10?Hya}m*z}pQ;&1ur*3&ag=^ULr4?9)ST6n!2Huvg8~
z0~AI;+I26^9DU}?i~e15V8;L9_u;1-C69tG_9KC+EUr!+Ja^0nKcZ`Xv|Tp5jjOIb
zdAhd9zfDx9i5-?OfAq9L!tb(<GUvB=#pj`e^hbQ{9L!el2!W<U!y39WKIXNyH1>)p
zit;<=?ie?-k=$ogVh3?WiC(kFtjvujun&CfxT^^^d)1ktp>7XN$2lwms4mgP1ig~`
z3B_Qzr#rksA2P7mIY>{<`zhE1)2T{wD*Vd^N#@h=_rLGYhT@YGp9U2J@ZVVgzsk7p
zxzdLilH9-cqDFNrhS8_y6eJmFQNijT%yk}Qiu@Mk!oe=j+BLrKbo#ZUgeJdz2&Mk#
z4w2>8wpic?8I@*<%y2371b6IU=|Y;br4aa~2)*?4K3A)7*^E-eYMJWP^P4mOdU*a2
z9Na7f9N*m>rWwh00}k&<5N`olqy$thI_=b}m$T3>w(=JjkEO&#$s+xhnI%1W8CP`f
znkE&o=2@)4h=Jv=ee8?A(WfJr3<gm5<hJ^kdCaPdAMQUV2z6MxvmHF+R|($_&N^@H
z<$R6fbfGD+Xlc+TSbv%Zf2`5qi*$e3tC-c&79*Gm_ZVq1;tTfLL#FWd>px8PjYkLB
z#Ha2T=U(tfUq9D&<JrAe+{b|?SjFeiqK3%c=le9BSZs6C(1SSS(Qd)HIS1#@$cczQ
zrv9c7TwJ@;D?;+8gJdX;$X%4Mc=|C)c&bNjPIHk54wLFQ;pDkiR|VDnB4NcZy?7ch
zz|E$d?-R?2uh_i&Gm^x4G>LwLb){)0c*gf7d(P~W$Hky<Y2QSFQ=0M8<V8@cbJZ~W
z1U_G!(blzURc%*<;p6q<sU2QC5_Jyo-D+}OHykG~xhI2qBZzd0sVMfgSC_xomh903
z{i|HpnAlE#{-cx@7vLKm29tu1LQ6OL2Bp`=VWcOt>&%X>W?6b>i;cmXOo8+7MMXG8
zfcIp2$ag=HI6=9O8x#-Ut*|BlQ$iIj<VKhFBF8gg?V+Njg*t`{>3Za#%Yoo)b%zp&
z!J?Nco{kN)r+1d0-1z1iMrO2l2gqy10AT?ZK%Sl|D5*Q`$=WQlF*f6fE`C%)s~uEk
z9>uV!ucoRyiq68Ku3xr$VI0w(KkD0!-5&%lUReC~p>rQ3#_PTdqlPj_qa}sr;KA)x
z<sE`~y1<BjQ}<jPtgThOc94AKrp7O-DE{IHyS(@bZqyLhOANl%{033hsJKDv-m3+a
zgEN^wm1@g-f#@@r21_omrd)(|GF^jh=CqnNZQxoYmwED!i)Uu}M#UyGk0AJ!*F-y#
zH)9DV#fd2p{>QM61o75D%#dl!R6WXp9Z+Xn5Cn<77LXC&vA5bS>MXv`+3EVLl&c2E
z3!(z!6tE9_|2UmJHt>h{^uvl0=u;y<6BQA-7$F)Z1VGEBaN>^r!mxWW*i{X`c8>T-
zm7t8CT^|k+G#_jqySTvdQGD)e@-S^^m=Splknf%~!{<Wq!pT!{r_6K8m><;%VBNeR
z+-68|C=lPmK=V`feZLARH;f3w2BCgNu2Dc9^DL+fM9y12Nm*q`)yOiThGuz-Znb;O
zp}0iB+eXw9|F66U3YVV}Ir#A?KY~6v<Q8`&t<rKA!?4kLs(ttuY4|*JiVXBw`wv1a
zfvBcF#oh8}#|;|MrnTt1bh6L83~BqE7~nhW67`SJ9E}y%Bkz3X57qa_-0eP<htElQ
zF~B{%Zet9r7bI@oy5$v<>nxE7EL#%2elbVMa-a#kC(f?S_g*<>DP47UNz3yNxLLuW
z2jWRKwBQXd`A12MiLdr2QjSOK{!X$H5rA}z79&BuhF@uw3B|zG59N<o-;t_In;V$<
z4Xzr<@+Gjn=GZ)&9lWD9(e7Z-AH+DJoaFVlE>e~aO`wc>ZzcuBHQZbfFqK?tGOwU9
z9lYJd0^3gNKVn!^Jr9-ofXjEX?y0=)6WI(&@;Xe9tYt+LprE8c)>eiqOD2jg6!c1G
z!`|(UM{wpPc*n79IKQ0!duAwrpDg9<tv3Z)O+_B=j-|z%4i}9|BSCi5VA_Oq8rm_b
zu-nX)&$w{K=X<nc^Sx(Q(-%m(j?&=s?K5&$UaONYf8u_&VUzYvY?)L@ZZMIi)EEso
zU|Ci)kz;<7{N{q{-CxI8KOHs{S4fA-atZZr9#}(er_i_o`2rg~v)fr0n;8Ym$~%n1
z{B+K=-R%WcrqMY`r4i!lR#Yg5xQ0d>#%saH)D>THt3)-1Cj@$&4hU4q(msxv4Nwe3
zwO6parExk87R2mTo!<#g5{>+i?ygT?hQX5xyr>*yPCHf$df$Hfuj>gzb-u~FEx*R&
zmiezcn52m@f<&pzYvu~TC_zQjzbk=2gMnno%=B{Xa$nuNI6opI@a+4=R7SZ-YJN8^
zXjbK|s#9{}Yx1NHl*}-22-)X?jPj5ql>nX-5f%OXjvQyKC`Z?M?>nC^?`vJq4DmXP
zCR#!}{&Gpb#tW&<>oIO`dU-Jf4T^MQ7cc#QfMQBV4Wj_W)`UvtPGz0y$MdIB_0*Nq
z3yc2TS4&N8S<bwls`_0-JmT^7ue)ecOWZ}D<0h_lbv>1f`KI-ZSeO#0q7EdDMq4+?
z^81Ti>|#BVKkbt47E{+%GMv=8nC85H|7?Qz?6mD4`SEWau8RusRp0IIHKu;s_cns5
zadPT_CdJo>>f`e5o?DM^P>sD!`*<fmecia53U=y#S;5LlYveU|U8C<u{BJ9>j?`Zl
zVUzP_Ud2|9sz$DnV60fbGp174w)SiI8x6x@qpxT9jtvycx=c0e-G1GsTLUX-6<2Ph
z=GMq=<*Hwtqev=Lb3AZ*!2r0As7;G=ZL8IPO|33$UwB$Nnm^wXB8!qU0w!s%e6o1e
zwxV$}YQvG4Dh3d@<ei)M0w*<*{ZV!!bEMv)jz9w}UYSWvJ}{?Tpe%pSWF;$G<f}_*
zd|rT=%iQ^>++(R!3WQMx;u-EJvl{-#U)&+LIaDOD#amILjN&E!UXGG^>QieZCCa)H
z&eL2^p`Oy{>7lMfYQrrbQq1>E{|PjNWF|9KZ&3pl0df~%EMBDVtHmzXV$J5%V&WAp
zi2_l<o^ukW4XSx@<s*^CD_QcURy`jxbDH$y*(*(yCb6q#!z)jmY+W*oTO1XQG!cCx
zhr8GVeOOpO+eaAk@b?Ycu=toj402S;wACU5`i+@mx92U}j8YqEcSA%o>5Z)fnKm@j
zUpf;!&`>$L%uhGu%X2e&<H7I;6;iKF9=(gV?Mx`MI+L|~v!ux7t$t&`rymOzJD1bz
z2iC3P#aM|?)9mIFMPqyM6IhfH_5F0U@Tv0YiTt{!HuF{o9DTiN<^s~D$0BpJ<>HHe
zG*9%O*sD9?{%~3D&qZ!-A=vI;wVF5SOYZ~A2C3C!gE<%?y{i=P)|t_vfNJuglu5fQ
zo>;uJkzyp^Abc2p=cDtOs9h$Ztpl!!K{uYtxD%bx$1$gtoRNeQwfKx;tSCyLdiALF
zk0^-N;KyzJf`EeHfNS>hIQb>PT|$@IdEJ}yoOu!%%8pMJvu4YDzvn8Y)G4_5{NH-&
z%`bLHT=;V#CobUu74dGOLz?9Y?uP~X`JFif3xk<MuET!7K@1F+s9d45V-aBWmOrUa
z-lvJw$}-q9_|f#{fJbG*6CK8Aj9Vq}<i%hAwz5h3Eqj%_ChsD*aL$2MVcQ~W%AI!y
z(clKkMF<PCUSlEL2Q24$q_Jy$C`+yTZ;Aq%JXN_vI_`j!&iDfsEKG~zRtG;)Dti8M
zJ@t;FIh3yMZOs8aLX4uPz76IXCXQZzOFBRkYI8+|l1ign@HtqNL&W>5DaP=a?n}>B
zb7sgWxZpf$$cs8zu~Gw^D5P=IEPH|>s7EOLgnwHXnVAGL!eAVhWkeG}_e8c%(V*?c
zorl!M%D8t1>1*EVYk`F*OQ&e=rZzhgtu21IY~^kG$2QcO%|^#)K+B7JgZ;ts3i_Bn
z4F*6Kw68waB}`wJxg&2&e!fXheQ_0yZ`s#j?Dd>);Wb}O|Mm;zGXvp$CbH~r>7eca
zQGz7mfU#=1?dDzjtMl(2&2blgl-Tr98_S`}EniitVze0-99sM9fBrxX-Jm9>m8?n0
z*!R1j@zJ<jv2j+(qOm!6PQ(Y3^T1e0;P(%Z3(w=-fF=c%U53b;b)dlqSLD1im}kT-
z`q3fL{W{e1nKo*<m8rPbQPhY$5;%YP+^>KOd20D|?hga}{l<HG89eaVoe2|h>mSR#
zO>VNy)m-he;#A`o!Q2BfLIr@b<k!L5cYjp5e~xv+cd`1m^j<3@bOJXg)}YZGrpK%5
zo~vo9m(1EJx<bB$1j?YxDO~umcyh1ml6N1WrOQ2q9%k!yNL_y$Zcb_i(Lpt)V07dB
zD-ts`oEnFRD%Eo+P$}nMeNMi4*j1q>+#a&RZtEB!c7?9tkG{Zz*Y8hfR$tqeIAP%;
z>^v!PT0yUZnS>-ZIZ$I!vh-+ynB#$dZsXkY9^v<2*vUQQuor_AxoK`lY|5h?-aO4L
z{Ju%@x<FDy4FySw3(dKS=8$LH6aeCuH*KST<k&qZ?)xOH{Qlyd&nN<q5amQ;+{MHZ
z%Cu|Uhu)$nhu6qL?v~Mq2p~N4aL#U#ezSvbN)VP*IGx{juEyZ&HFi2*x1l47jr40e
zq)U|e3#W}>+6-R-Kv~ZYNaWpbt9?;ci9lXw%)m~sOx2nSPECLG+C$?CRDMv-jdl<<
zdV?@`5CzLFL!S%V8ioRr7>!LPg{<|@^yrHi{p59(eMp&aExgGV96Bk1-&}cfo9yES
zB^?T?n#fvOMESq(2JH^glx%mrFPOaGsJ(gxm#uyxMv`l%TXkpOTfNTJbowv)E>0=m
z<+y!<y9NWyn&F8o_HOv0blgU?fyYjvF^@k*<TA@Hg$3}?{&2VQL80Z1Uc;-CeM(ny
z8CV=37cL~(7+|LK^<1j&vu5qu`<na0LCa%)6wjDGDwge05?y3QZg38zMZBwTsD2~M
zizTA^<QZTZ>*H|US0^2shY4d?{PcMll?xW9o8<3f(ovqS5e6g8qO!XTKnQln=a8dP
z)K~5~>>i_b+(BRFTIki$@_sS@A!?<*CP?_^`FX$DD3`~`EPJ=U5F?Yd@mX9Quo;y`
zfcYUyXnx<jYudGP)Dq}!=aaN99fsS85Hj6qvvYNeT7aoIe3`kjLa+FqGu=N52OMAv
z^?kqyPn1WA0BdI1<mvIj%OeY2WyEgM8){$`{Rd^FKsyw6RzYad?N|<3hCAZ_mI3yE
zMhAsH#>nS<pY<Eo;X^-^grqN-3v|=#zh*ZgU_vd#@YjuE1>tuc@rl2USJNVaBtf4H
z>glTa6Ly=&zFCE2E^N$h8(M|iE0Q(k(aC7Ml_7Yn>lW9OB*QY9I$+r-&@M)Ws)1#Z
zMkTX3w7)i|l{onK+$8pCKkoj-cUF90ocqfmyEB}WbcN`Se87<>%qU!ztemT}2##8a
zTq`l1NB@#)8$Ps+#Ae0t$L~U+)J<dVXB-t)4r&G2<i`~VY2~BTsjinPoIgdpz!I2_
zRO5VQyLRf-<LlRWiyOJ(nVZS$dHdx|j)$_u7Umc@Nato_u2Vq2pJ`FTeprXIk$1pY
z#F2zil~nq&g>MPj53~=X?vLnOWtB4|CjaqhN4YH#t@({aNLSGgAEt?;$O$jRgE$fS
z?xTDvo@G983hH;RRg1Bbt#(0~(p;`W@u$vbxQ~-8Jfs4$&YRp*ig?$Pt38obnxveo
zTMGV>{*GQQb2u%u7!-AHr|!+)eeJ7RMquY0yYaAa#P+GvY*mg%B=6T9b8Vnrjb6ji
z*&l-G%jq&)5cN2IWw(n*<i0BZWrbq6Fue3<8TD>grBAS@3WfhYmGyaFFs|Z?&{M6Q
z{x@JPSKpRK$Iq|ce&D^VI+jTGkAo$axQ40Lk;u8wTj%wjRJKE6UP6wO2#Z%-Q;EqX
zzq}vP!f?CjV>+2V+fyBF-7iJq6-C&z^x~I(cAB@oONAF#I3pR{2;l56Cs%F#tG8Dy
z{kh&D!=m~+sjTf6gO>by89-lH?IU?ZgSEW7T6p%;qzfvk#o^O2n>NScPw)Pm1D@9-
z!5O?2(oZ6GOWc{A6?tS{vicKt!hKQ5(wGwU2;3tFku@P1x}vrpzV?**Ca2<q%u<LO
z)mbJNZuz;<NF|Tp%>Iu?c%XQiosyWEKDsz_131(aTeRH~V^#O#;$?mGm|fd-Ie^Um
zeYUs!eSN4;mI3BT`1n={BAsige0nKzFCFFcd;e}-_2i0e(r}t^`j}Nq%yHJU<{%(d
z-tCOc6|qD?m?^^%G5se;bjn%3V}GCM*a?Aq2|t>ko<cW3sy?iFb=He(`IXu7vH)k!
zy&3(fdO`4$0i0Yr0b*v_=F{m2F1$uJ(3*d49GV^uUvxaQ7Q~R0M6@Gi>0b)}+#2bf
zCsJRH(76LD+0}COT!9M*;$E7lAs<$w52M!v0e_4-zJz=tVNT(p;7{*>xz?mTLz3?9
zNJs`xRMrIncA_hm$W-*<vH$M9{woQKX`Fb@Bg@7BNg9h8uD0nWb*GkT%X|zW+c?-D
z#d*=_CFwGT_^j@P4m|rbAeLK;Cq^sPP=OXeL9yU2qUvWaIIiT(w)Xs$!P4t86zj+_
z!^4Wn-*M&lik-B0PcX~G4CU-Sa?)#JvsJ3|^e)Rt9Q#D8)iH-HZgD0zx`X(JkrZ&e
zdRY`zaKpA)L0>UHy6d!&9<;7&)=!(hMfz>VZe{DcG?2)CYg&DFFR!T2%t-uMmyI}*
ziIO;?FEMV)P`=3{FQzj%eU5@&RfTvHrN9agN#8dZbh@|m359Rpb;_9M)eN&?+TBHa
z7pNA5DeLBZq<{9h%ot#aDrkIM`=h&$m#i0LlTy<3dO}(17Nv5<Tc`VF_@QrcjHM?x
zXu!c_A9H)f=0@A;?zP#m0y*6boDeJPd1rrL8m|{Gxc-?#JJo*Fq{^=)WcT-pw!T#j
z8LEdNOk0d_C5t1|79B|QF5;0>|11fuC*z99j9hd%l<HRS*ZduKT*c3U&w{|Do*5RR
zQNUU>%9_x8#}HlqKnYA>no!ja=0EfLx2vglJeQ_;#oj9`vid;R+QZ*H+WbFC4W7E1
z+R6Y^W!IX1{U_?j{clVtgfSP8#LjTlw}A3v3M5zE&z#+cq8$QK6v4>B+!B7BYd8LH
z#TvgD;pF0<Pv0f*OjFqSC&$l~wCvlTVEidsZCa_V!FRvN!S;1;Va3dgZz~rb@+Q6k
zY{h3MkwdM@xR-d4b_$KBw4yzmb$B<`O>ph`tmdbP{y)2eolldhY>QrKaEQqK2@$WY
zEB-nYdFkAh`8YBDXE(MX5wZU0))CG0UKWBR8KhlQyH?3g@17y#uY6X7sI5G;JcygV
zjT-t>GVhcc&5uO4L>G6<M!7Wp@?p-q30^`#c<Ksc3eV9vB|i4l(Ok;{i$4k5j5e^s
zw&&kVc~!{!3hy7sT<@^YoLf-RLY0^)lBjxFb!utqw|?90&laxGddU_~{5L?A7+VB3
zJX6r(^^43q8_@ORJQ)<!aY-O3WG`ArQ;l=Kn&UK^7lmDk0=+xi&8vhw6vGo&;t4>D
z8%6Xl|It>CAsA%5&yna?-#-b=?`dL*>k!<G-t?wWnkrx6=Mj86SG*Z2X71!bWl44v
zA;=?pM3L*C?(9nn!5jP1(veMd@hXr&Q+&_uw^=VQ7pJY{^s0L_B74mLW_xFck-${V
z6#?+WqrjQY0d;7R;g~F#54;?D8nACM0-J`VY&EHm>HOquXG#B}98MY}Q~%6P3oP!K
zKGy(>lL{y9+Kc8e-d8p57&!lMdcjqq%k%y@2{9~@s!tIKSqiK`5Hp3L07%^J%m+WZ
zmHf$?6z0G3xChfE=sPJ5GO8AAPovTwpf-cmfw@s5(sKc1M2%lG;_=maoR+<CyydOZ
zvHrI>^AS;hVn}T_+nod1)TH9Ipw~rPD3UiJ0cqtcuY`RJA)Jz1190v`HY!DzNor9*
z^5lR8*OLzJ!dI8{?k7KfcpVqO@|rAmki$T@4z5*03nW6QA^(Rl$HN~tM*xo7Lc)a_
zH4|TIi$7%E5Yctc^*7LIzEgki5>2(SprO=>?H2`ai=>gThwbQqg0OL~=_oZ2azb`f
z@2BUSzwwvWS0+h>KHf5r&4Q&rX~I&Y+c@6D`L^oX6*bJtl|AX5a0+B=63?W>1ao10
zmc8X&)i6Yk$p@Jksps25GfVo^tM=qk0{JRW=~E>&4!`}H=0!u}>PR*q<rRS3-lq?q
zzoBJ+@0)?kPNx8n5{pQme6bfa$1%bi#)g?mTDTiok*xT794%naKygT~&Ur*<fW`;4
z8J>7pj@?a0k_CLBk2?rAl0F@nm{%Q_tT%2XztB55tSBLt=lAQylV1!lSw=7t$&T|}
zc`uv9`a5J|ulU*%Ft2B3?<4_r-P^sQ-SiNYOHJBAmR*y7s|5fBZVL}&%jYC6*ydcC
z$k=O_A52s}4dJ9uJUOwb(Ek}F5Oya3MNqnG_IuGcL<Qr3+7FMcMOGNG$d;nD*?7(H
z4?SGnejy9&*Hzii_lA8nOTn75(s*0bhUxSvziUqZc8X{MJ#G&V{Ibn~wPH@P=gFG|
zq)RAb5VoI@sCgJl0jx3Ci$K0s#mIOR2JHWgkYzylze5elcrx-m5UbO}`=g95wmlEB
zvsR(r+^x;^InGCjK>hmmTI>q<+YJry7e1nhFZg;LA~o@WHnqvb{_C&_pot5sf_^0p
zT-|aJnKnN`Q)2<Aq8t`}Ubo2aBB|o2)j@5x39#NK4VDFRG7|KLBS>l|_$7Xb0`lUl
z%KeICW|?Jwg8PIz=pJc{ok>wyBy$nO;@O&5VJ@``&XI=6Bu+}0l5|PFXR)8_X#+>Q
z>AWF(W$l^YhNgw*S{bF#M2aH<zOx_4C!`)*migYlixD_UH-v?C&Q&wOT<i(7dS?qk
zhJ<sn8Ppryo${uNppS-nii-iqi7GpKbyGe@ovAO!$dD8)RZ)Xu#RQt@s-M|8^-?NZ
zyG71MpRVsb1C09XSy%r_?rVn2PLCqjQa_CBVsCZYfq^`hS_A6kIUe^hm5sNh3pWD=
z!SqpHz(_+HnhjjVJY;#&I_{=OnL>?kRlN}c$%y~$c8&V`sJuJ!*aMy4e}%`CIJe&e
zQtVNh2KVIyO5o=g-;Tlz<#4ZSkkNMgD()I9JgH91jGG{qyxrAbuo(c>c%X5VddV2l
z0nQz~Isz3anYS9@hE*+KXslOgY-2xsobZmh{%3T}ar1K+4pA^m!e*ojfD5)A$6v>m
zG;)#0llA5*HBC1M&LM}gV&?Y3RXiX55U<NejsIX70w{(EStc~$?uihnS@6Ex>mvWf
z=tasjuj8OM%>NQpBaCC0ASOkK6j7DxN9Y%&c*URdY|5A#>PkH7h(@nWQ3O@%3q~yN
z{TmN_^q`(~;baXl2KZG!V`dfR>ZHDy{c>BqCW{<msw4dK2DA#R<8tRjHL$fQ559SH
zE7V0yXe{WYjiwevkkY-iOqvz*+!Y`47^tVJ|1q*eO)_TWAli&=WIE!^$8TiCO;3y{
z<om@xH8Ej3Y5w`AMw1SPA<ylaP0{TxdGTGdw--KUg?P0NuUnqO5-~@#F7^DVyJ&$G
zmoK+PTeHt4=38Sy7S97LtZ+eO^okx{XhfcGx%vKV@^6Oj7`gMKSCCVt>_^GYjN#i@
z0o$^i7Bf5FE{Wt1Mo;g7?EGJ));^;KU_4CV<<q|f-a4&j_b8kVLn1x=X)Y-(z-7Qi
z6pQD)`QB9J`eVwsPJwSEBR`wcibkxe{wYEZsPo%By=_{@^kmwv`mxvjbs9jjSD!!(
zqv`Up#*QL?Lr{hpcTuSR*?U?H0VBS6Ifys@muWOV8S>tRix?J=dBy^hL&Jg>4h<RQ
zm8;{e@HoYROiy~w7^9uV+>5QTvrk&czKKJJVn_LHBHpF!@z|HlvH(VCqvNZGQvEy2
ziM0N%0<MMVbYy?&z2a*}{p!e1Tnqq}@lXIr%9{fBkrO*wIoh9@r+dtGA&0aE$8sr;
z$L|%*r~o|!^7hVui26c6OH1ucyn%5CO}Z%^l*Y|CA7fj@Dcgz%T$@*X=|nH%UYeY(
z129S4C^Hh&40-Wc24&<mb-hW=lG1(eh8;2j18UfzfEXuVYn&Ob-vl|;PMh)QNC*}%
zL8~?M@%cyQk5iV9^TD_j%Xd79KkugHlL-<TYW)^L5(CXX%t0lvz%0yWN`)p97cSJ#
zhkr2jO~!1vP~O#@ys7qL6@mzOWIuw4u5J--Q*spoGpqK>6e;(DrJ)qwM^-e`?rJPo
zR0_(V_HCh0JhS0U85IIRUj{Qf`nUblxAAQcmfqiZpt?DV(cg(}e)2$rcG9q7J#F(o
z)<%Q$di|jBrJt;|2w_<CGM4x_0@*x)sWr1!uN>I^Ei)hsaFzP8&uE*hCT1eZM7{En
zH(99F_U*;lyoOvX92DpsfSt8Iad?kEfxU8qla>LtAajwx0(P3RRUHyN6jU#Bk#wd4
zWO1Vg(`YstYZX5ri;mo{p|wq}%<$6NPF^BO9%rKtnsLKBWgH&c`qmIt!i-0m3Ag{-
zW1!;H<IYDTL6H<InWI%0Hw+fg_L(yPML$!%KZk)BhsI|f&%@Z#q-!jQn&4^7gY&?|
z_d~z5FksFgP!dU$MsFekHf3+}!+nyPlw4(krnyn(JidsPG*wRs#=uGSmv4(e*$=VE
z@<ba(HoEY4#`we{Nfwy$Lq5Epj?2s5F2!>&IZEIl_m&AriY~RrjPYDzdBMd1qapsK
z_5X7g0Cz<lI1@f9jqDGa!XsCC6jCK>5^Qp_`|QAteM1~E7()33!lX-tDh$LBY5O^C
zHarQHF&Lv`>$wQ553f6lKe(W`YxY1ly6+3=mK2m-!cq!@61){PN&vkOZ%9on^ABgW
zvUq<zI#=P70kD=t=W2t<>{KpOu9Q8?&{}b)OuupD^(d5!6c%QAHSekeOr~!Az8*d4
zX*o^p;V2%D@D~RSAkX+gVM}_@(~G+qGJ47b;LtEqmK}|!ddmP`yZS?Vr&ii}R=c??
zV3r(J^H2kt>!}t6TP&}z$m=*be|7MRz#<?8Vo~T}w14v$J1UnRWU4)pa*+mtS$eGS
zSQ7gd2(7O|dexy}R4u}o<{|h&mGU=}y7OAuyU51qC!pDMa(@$9xtKcLBzIP`EcCE+
zYbvQiUaxXD`V$H63O+!e!pwdhNoBY2k{0pg`Xs6PBNoKTZhcZ=fUO72a;adF9D#-$
zO8NSnc=k9blsqFCqWQa9jot5VZC!naCJ4$4JqKmS`<F@R(;`c2Bl0NFqfP_Wq8!S=
z9_6UP<naUX2dDL7ZWZB}kq~52A`yAnhz1v>4p^G$pwpB@uJ*S}>P!{p68MyiB2&YD
zQo8Y4-2e)ShmPtsnyn>X76oRWo$uLZ=j|F!>-pC9+>h%TN6z+cMFD?fuS?xdYX1jW
z&^jY$DO?Zwb`Xl|w}RPFgiq)cU61XkhJ3e)f+xOzojmOCa9>W4_&)?+9quxb?9qfU
zHX_fw?<hHcY!wUGl142tPxZH07oTLk*i*mur$Yc)#%FX1fYUp?uL@8@(MoBB+%=c6
zlSp>@K#jc)M<p3luTv55!EXa#wEwjPhLJQy1t*3$=?HdK-k>!0EXS$4i^rEt8-d*8
z_|dWBK36FbpHrVed`|0CHWgIvwfDE(nPMT!)Y-<@+OsNG!+#N;+6cccnwRbR^EiYo
zN^l|SVBSYCZhr<3>M5~Bt8~7tRt~;7R;}<`7Ffcr>1^Pr<J!n02>MS3I`V}qw8H=c
z{)Ox3V`ZnWi1!buF373Az0`UF*FvLfa;=w4QTHR2(q*=5n<DXI7#C?Qj55Jwp99Xc
zlVWS9uT=EyJNSyGcFzR(4jjBZ1G#CADb0T5W;u!arbdBmrUTk&D*S17iR;f#Mb?mb
z_bY4fR}L`IZL5A;`HU<9N9iHH=5w5(Fv<Vu1*;*V29Ssyuk9IWdog=}`G0u&?m())
z|NnEZd%3Q4?UhjWo@Kj6_8uWbAu>XdNL-<kon7IUj6@;X;}Y4M%9fo`GP2#@OYhJ3
z_y2jmUeEJ<o^zh(JjdgS)%<aPrgi_Ln0FZi?k?IV{On(<r^_Vp1QHiX6pj?y5f<N`
z<|w<IB-aerQsBB{8#hnB5TEV^!Zutriu$hClhjYWiXnr1pe9VvnrpJz`%H(c|LU%D
zsX1@3JZE_I%)7Ipn;)5PSK97PJNfFvs<N8gb)o_szbPjBk|4PLO+a4cGR*$n`-J@J
zAFE_6H*8^5yotNhH2nP;kM2Fj=J|<LptjVkX*|*|3s1a?5&plQ4QPV-o)~`NX3eN4
zBf`RWi)V#WlTVDPcPZAX<9n!!LD3Mpi7`r$BHkm-LUG~?RfHw>ADaS>Yj6dR4@G4!
z5Z78{-7I}M71BODhboNZJ&*)@*EI)2@asIJ>;E>08xK%dHIXbBmCDJ2n|v&-l==3W
z0r!rBDnG2p%suvgG6OsT<{|-UZO~@sg7Dok*gLC?8cDc`e~E@*xaVxEt|JjWr)yoM
z-*zx3b}5oZfTYtA(i$5Y=lEVGFefPY`r03f66^PbkjwOF!lxN6yL&W7%0AJ9>aaol
z8WPrze+zur*;u=sGY%G#(ny)~8Ra_PJ|cEG-09}^{u#Xb(ujXT{R4sc?=&gkGRHBk
z-Y+oGx}W@>W9s;=Fr^k#`n`v#N8Ws(m{M7OW%B9T0;aG>m?^vD{tXkYa8MwT4Oo7e
z)T0SwMebLupcJFr$8Te^-#<8~Y--wCvC^S;ZQm|Z>9K5~DMhH3$z_Ow>jf#3)s3m3
zj4km1`@*ZR>u!G<el3qwie24zCk0CGZ=<t5CXxo2gPypZy}g+0bYq=$Xq-KJsLDTb
z%x_5{tW`$WwdQ$tBg3=D7hOo^is9~SKx&?7#RxjE(l$F3UEg|_o6Cxc-!E+E!(A?*
zaOjnfJ5)J#wmLMI2X(PFpwrgh7L9!&$#y=&)}ZLDHO1;vvFDy2_;=f{$@GxLoF1=t
zAzu3@90)#X-<^4kG`}^Ya}Ew@6mPemlLi<Y0isAa-AY(aNtYTsXMVW0)U4rjeM`*c
z^Z7%6A2oduJ<h<|P{Z-+_aFNXn7gMW%Ft%A3-E)H%uv3_{5v=2a#l0V?%RFkV0kmk
zn^sjZcrwr$Fy-*AARTEGUZ#M+M(QF75r!;DehT5diryn@eGItg?NaQqx`nbuN0z#U
z`C{I8n#CISszN$7e7-f*tC9(jXaJezQfE!sxL@3$@Y-E<V4y%8Ia0L%x88vDN6J@j
zazB8gGzb9-b!cFjGY|7SUSb;asz5~q?;@4g_iWuCx}~&3@jr*x_0c$eVxe)}rKC{O
z(_4XCzXo79au`*w_PCtZR9T+lMe<j!F$=yyYe-TQf2fsQlpZ4y+}QHGdGOD|a$_u=
z_uz^*&FSTX@k=l4jn#KSsj(b%{`Nc?yCzZbIy8)CDH-P^WLo>P9VIRZP9C1SPl5$H
zr^zhKT!o*$z!Pk=^V@Y;EvLS`A7@(IbJ)IM$HNwTVI@}QouFsNn5@p0POVyWDEyQ{
z04hvW*lN5H-MH<8@48N<c*2~f{KWY%h?H-H<xAGVMCZ&w%PW}G>4j84(g0Wt;`_un
z79M!H9Hlam<2Z=IK^yP&fXHESB`vsb{GiLLAA=J<P1i_f;RU1R!&G{o!+tp_@))^%
ze04;m?NNVv-s84smWA!aYCl>4z&Z^ufY+dLsw>W{({fyg@hpC!@%I%N%Q853HgG}+
zKVGsjxyPv=_8#AjfSG8NY-*Z^zV(RVeg3rQo}f8vwTplL7w6CW!~+S#^D@Q-lDFE3
zoGc`ESjcsOC#yC5jshR3-1}Syyu7UWHq92Rr{tKY(*HC@LHY1#KvX3W5LN@*%R=CY
zuK>Ep?<IB9+}B*>zA{t#_v9DcQEQ?S|5Y*h4_W|==+wag*`ONSb8p20JRx)0skx7w
z;CwV~3tk4iIiYIbVLEpSpfL~2Xc5@h5P1KOwdz7S;Suc!W3kpLRgnv<#Bsx+tx3N_
z$+XRv_vc72y@A0{YNIGPUYnme;i#ajaE&KXiQGr>$Iue8c-Zv|@dn&c2GJf$=VGq9
zM9j*zUlPBD#^5l?v0NZ%qcN`VZQZ!)gI+-s&bCz|Bc>r|Jp1E9=mH;ZBHW_o2~rXh
zzJsctdBCJvEC>6wauNtVT>mi_UolkX;b22QaBDnFVyZ!uP`$IaG$PF~+MP_yXM?{P
zbbQcRBACwU!IL8^WJdG9=k)Tx72w%el@@!Q2i#g+{B_uZYD<tL+LB{;FoeCsCy$<x
za&%LUjCh~>{{+@h<g(h3GNgNT49|+h`oF{w6_=}>%W12Bek2nz#g7j`4m8r!>;pD0
zE7*?mw|x7nX<BmmK;Sxy;g1TQD_1gDf_5mkX<$$O$te;aWum4(spU^>oTJ2D2OGDF
zfs+<U<(R)=_d?iNWoT(86a^^?N`qi@4iCA`@au1=x!}#T1wUJo&S>poM5YOd;FDNr
z({i>QYP?4cRUT-bIu=aShSg`q9UW9-FUcjn`{q&+*YZ^RfocN}Fxo7hxqOEpMv-Ii
zvnbX~l;?%z<NS0O*W+w)s?*<4IUoK0)^67|rj7I!vA^2mB&m!|yPWQ{`(OlPMZzY3
z{kh!Iv!9>1#?j)$2IJ8REOc9?`8SuaH@^4S!>WWgUan{?=nu!0TA$^*Ep7e$B;2vB
z?f#_gIlc47!QPu52^`ulw$ifI;1HyM0KFQJ!IV?wj$`*Tgbm;14V+azSjFIGwz}fN
zcD;&9yzsJYfX6{o!ib*VHj?`&TcOMC4dyus9Ljr!RweRQSAn(TsIR>7kQ>9tHnFop
z?QFliCe2>TsanYSuS!i(Eg|W1uf$72bwn;dW-0huS&=9#fIK{a>if}$54DBuRB2mo
z=M#?_+5TvL8GNk$`U;p>pgEb$gEo81tc=j`16gpy`EQkxi0zIHPsPFe2PeyerOl@4
z>f-`AVJw7zzcx~<{2$KjT0+$_sDDDVHhf(+8KXGVBS&3|(Q*8lRN=9N`v5O7?s=Ic
zqtR}pIG1gdAl_SK9q|8YkbWedf(mHtP#t9V_WMv2`9LhRn&x-J4gNqrb2$%f3gQUD
zyn&S5h!nzT_&0;jo{`rbPlozk$4r1wz??H5?2S3WcOZv)L(V}v$o)!Us%QKGt5U57
z61_ornhav{s-Me~%|ILGb}z!si`@VX9K!7Ow5Yw~YZ2_>pJ^>KjUuNd*y-W_4e#e3
zx0iAk>pKVhop5*VUY3WIJb29|R{i41*EpklHJX&SzkRJ8LZ*`E=m*K+!C3(kHDICh
ziEP~5;`*Wx^7l_T-CjmoTfs&D0&qm<5PwyH;sQn8V*^CHF@r^xiN#c)O8i@Af-m+z
z%BuHx4<EhnV=Ks}oMsetHip>{<Ff8>C4KDXo@(`&F9d<1gX@}<!7r&KT_FJ{yQj%1
z_=nN$74}rAQeF&UR^^LulObA)c3*bV;h1Q?d1A971U43B#;$}qADPkJN`@eixNxCx
z)Z@*uXJa4!_T>J2XRP9l+^k&mTOq@B{-yL2;+qQ}tnz0+mPq(E&2_9SzoN{FxY>6Q
zqd;=>JG=~oz($4is7Z|Kl6nu-vhxAH9JZ}`t4})17V4jyWeqbCGa8o0U*PbWe`BNl
zDf=4?EvUhF?Y}-BZ8Ww%*LKQ-(KhB@Pl^EkoU-}Chb>S&n`5$a;veTnT_pb_qpEzc
z?)+X5^Z;yXyvT-_KI7fg<QUtQQ8$BNyDG6O-13(FMp-6|T;QL-m9oG5<fAe+s-Fsh
zHDH$Q!a8VxH^{Md1+Lw$mj>rOo>x_@vF+32AnpkOavhx`?V|*n<WU#SJPCi^3$srC
z1KEXOKhxGd@vGF=1oTMXz33j>lm0gzK`$3}hU0D{UG`&qj~3H*dwp}c;UdVpV@t^h
zUP&I2M8sVTo~X*Ic_p0Gx}^q!O_)xzB6%}W!Pwy|&t|4&et%+x-8)wIvbDHU!Lq&x
zCw#9Tm)NT3+n>`nW~$RKob{xoG8&fkS_nAx>*8p~ba7EYQ*?)|sDsA`V>HV0f}CK7
z#?Q`#Ww`D?;2>XqcJ=yI_hKd!K$9HC1una_@*ipRwf`-vb`y`%`Zgv4m%@M@a@X9$
zJAXpwdhR_KBp;lp%x!nA6#Z5;E5h}U>W16=<;9PptWtA&I}{@HV4!aMkG`v=Zqu_s
z`dx0Y_;Z*qgu~1c<w)MCf&uz6{UEGSnHv;|KR~&{ESoI6N>j*||K0(ea-u`JZ{D*@
z@V$R>r}Ea^MN%js2`5>^o^-ugw&sc*&G{}Z4D_zN5{QF5o5g2eR|{^V9Zh5e2(V5i
z3~*wp%p06No*n3mQR|R*Y7<KlN^j;I?}W)@QWT70^R3S9pGp7v1%nqnjVO2yq!8tM
z!bdl+7{DD4?+kuPKUTjS#EM?J$v2LYFaZbO!#?tqx0-&NA<~~_Q&p6B8Ro92x^p-V
zyh~PiV&m3LN&Fqj^{t#uNz+xS9*D@_EWDFzrU8sh{z8$S&t<MQ2AxKrNDJ)8W%ZzD
z$|82k+COb_lVWS9N3Xwf_NTj$ksH8hvGDy(%JjcK{9XPgesP#BiQv-u?D?~?ChP*c
z5PX%J&m0$5T9hQwQ9QG59-sJJ=Fk1p@CM=R@#Q7f3s-f`-j=+4YgH<l(;Fh?{rd}*
zJ$5b_o7t1FvXI6k?7;}&KK~m|ee?IS*Y)`>-R3A7<aOy<Pm-U`NrcZ@V6qtV{ekl9
z1pgZem$_d-0T(C~!bWfltf(_BuraJc4`&in@=8Ug2GT#SIo@7-*8PR};XFt*qcBo1
zUHn>@GEH+D(h+r(y2x)oS6!_qJIuF6^nOqw@l1}qL3T89UYOv#t!e<iEaS0n`{Y*Y
z*e-0}4}+4x@Z<_R-46%0-?GMs^0@v%>(`n#x`UZWhc(U0ULDSYHM6(R!s%C7`NE$@
zdCLRqGJ6kK2yy5*8^1;ZbAyK`bzcf=KH2L%KA=i}IrHN1!pF77gzgoJb61wnIVMVu
zvTh7tSAb$?%N6jFMbScO$g^~+oO0}kk-*0RN+ap_yr3faAA;&Dx-}m3lOtXGU+3dp
z<+N>;B7wCW+q<NK&IVI!@yko8s<NlY@pJqtimPw4kYjJbK=t*xLi=)N{^I)q<Ft8Q
zK+V4-*k&&a3k&j>e*Wq+3czPhqeOUGp%<ww0p?fFn9G^PrC4#_>)EPtR3TJX4(0m=
zg|^(G?1;_n_+!SM_Qg{$ln_4||5eo3w*4zr!EGG4cWP$bB5NvInZQ@NmDvmIY8h8N
zzdO_^A8wlL{#_I#+%;Z0r%FcC+sKmsIW7F<t2(#U75__No4J+|)0`z%SrsNILIa4c
z4setq??#@+VlEe4M=b`XPDC;UUY~23dOoSG@Og~8@AKrxg-?Qn!wN&4^4C9~uT{iv
zvzQ@hey~d_2F&yn-lw1L-2d%I{cvV#+)A#)B9Kjk4^XIxekTfkVKs!`34`trcvc}c
z=77b^WiotdK`!ye+M+vIB{LN{p=XbX6;)wVmE29?zB`LbI#N@-wEjQMnW*fw8hY$T
zxRFt}H^a5zc%e2EWCA%MpMu3cZGcCD@$^13rZz60TqY&lQxe|3#okd?Xay?S*PD*L
zUue61bZ$-P<oDjJ(O$J;s&8o3SNq#!%Hb@ycdOtt>l+q$j0Mo0LJ&i*Q(o1sApXSK
zpy2(Onp?tsyyp#vw^+8WJXmv_(JW{cf~~6KADknswhCs7mPvL+{*srst_q8Q&uGgp
z=qIkrkry!GZWsB+hN_<)$TF9r)dHy~&~{(*H6mVQBa_Z#y{+^=HzS%1^uzNqZQ>YX
z(pWe*CGEZF;#s02TL(P*uYwuGrW#~m`xzj!qRd_>+~)rm&yYh$vGW+kfW5fK?LB{9
zF3LOq@92UP>O9PvN+iw|o(S9)fr<p_hT13@yq}KE!SH9p`_dKiN1Ovsv{1-<cM>fx
z{p|35DIBk$d|0!o%hdXY;Z~ZpZ+8$Xn^^^a<uq-yJR+$N?#%q!s)`Nad{?vTs5RC!
z@-?W7*1F6Zo|n@e?7*35@ND8`<ZDhN<+Ll{5hdJNiW*ix3R!lnht3QC-fN~m-lw3k
zVSQ**A?zRGcm-C+X~a**ws$<wYC^%+x86|s@^-=?rMQ($tBPUK6Z=T&^S}VM_iyb|
z23Ed^F`ZW0NBd+5+z`ff$VeE*{T|>RSSxa`Aao?Gc1!O$OpwQaUS%TN6MCnMjsJTd
zY=oZP$Z%gUS=TC#F8bC}duEd^T$#~(j8}TgGYBvF#W1xlq$@@H{pE(;Lj!smMpdWG
zT9aypBCUrj{Z0spl7&7pD9IQ1HNmsrZz^<GpU<OPRS1bq(B?I>U=_wSDfxuY1qWXU
znBOUaKiM*uTN%9c)y?F!_1M!?eRF9z%jm`uiOV?@_D*~1)FClsK0ZH@Te3=r>0D@3
z%xEu(UpG8>jm|_B?l$wsM=gvaaMA+CV7_B|ROQCR*8BZ+?V_mlHLZSCJFL11-$URR
zW&ob37B)=^J-^b_-1CY__x(g%%oLQMw~8CvY!rvto%|LD5#F7S6;YMyp;YbbcKvXZ
zCsZdir=ie(<V*KorA6B;XN^|65lPVro%NzNVP+jX9ll;Y@8A||i0@3R<ugS6(aBU!
zE5KmHH7l;`H#YeEO`RsQ`=TGKwXpnd!X`H$1>C0z+BLX=E$S-<JwL>vwsS)DfA9oY
zlix|a(Pa;7nSWsaX8IxVr*e1jrWH9s@X>QJy@PRvn}Kg{)o<N)4QCbWAR>|fi?%L@
z-zGZ<YIQ%j*p3wkk#Pa{VH;$yW|?@^=Mu!Mswb;G2;BN)ZA-VCSI>SPnZ5ZA?|0%C
z`>rGgTr<kiCnuZg^qrcSP*A9CD<JzY$cF)Mo$wc(kZa1nL-f9Rwr^^1kQ9#Jg6(IM
zmI#T}XU3-a%)HrMYPRoBQ$^sv3pN1);xsH<pYS|t4SQ^R*~KdCR$Mwq#$!53%a<j?
zU%%!cuy@@P@#SN8^5M^>zwqlnRvkzYuj`W`E<tATzbGy9@`7yjQ}5W<@DjdX7L^DA
zx}nWdurGqkOA_h&j3Y9>yuaZQKKqq|z+c&aKkoCcDOT#E=e&W}*~!^_5*J=5BOfFC
zN%;6ME@5rmOz5fNxn#zfo~R77CEi4rYXqX@Do(TXUan<e_xlL@d7_5ky`R1aa1;tV
zjcJPCqfca9y-=87OYZEm{IPWl#bl_*i!ZG-teWEAx0nsKj9f_5mK5*7A0l21$(o;a
zjk;LV3e{ojLB*kR-@kczDsJqx>i0e@i|DfKm>1@{X8M-B;B80j-n0c6oDdL7+|#FX
zhv5~r7lzHwj}3^1D4Z6K_^FpyzU!*VM#b%U?B`Bj_P4+0K*k!YSC2I$v%d_-znspC
zPPTUB6Mfg;FAMisf8l1~6eU;F@!yZBH}biL>Nghg)in=&o1;b!$lPl^3a@~&RH@m}
z5p%|;3@`P{MY=t0^VncjW%3>;I6scqTYrbbf^48I>7zE?sJhO{_242Kvp35(qk%Uq
zZ)ic!%f*Igf4qn@6uKA9%w&TLhl`~RD?=A=+ssT?8Kl5x7@`L5kmbBM@x)(+ioj%>
z#WqDw6MktWLT}x$N%y={I4tUJ!{WElv)#s?&xHFl!#Kns#d$3S1S|0Voe=4MqM7XE
zH<V2^+y$NATJxT)0-$uM@y5qSRqF4=VosP$Zl`5A!|GZ`(VSn=B9014DAF8Mw?q?~
zm%83PyHtJMZ~Q;v@=HpSLN}p=Yx#G4g44xy$CU>^#wc*Xyl&Sm3&$6&jEQNmuEMjz
zA45Ce>y)Y6pm512Z)LP9kAGt8MNnAt7?&d!FZ7+gaG@k`W!XS6!a|#13OO9>@^aRX
zHB<u>sr?&f&`K;u%y1EFwviE^6z5%98PXDed>gGFalgU)ELq9&NYn5OPqRAhaD8$3
zy9GZKma!lW303`BVQ^asku{f61L5e<Tz)6k$WMZ%gcuFv%*)8p#?(0kd*Qmi|BwAS
zN;(w5#6+9|vPc*ZA{2N+o?2d%d1pj$jPBfAR@#lOip`rV#pMH*pU-vZEvN+MA0JBd
zDkFh8!RkM%4^ZZV`C@vM^H2Wo4fB5uMwZlVlW&TT(z#EZA-Jf12^o2>Ie6WR;yrwm
zxZF+5u|0{wPeGM<f{S#x#b^`Z!TkFJz5JZoK8brT*{;3%zHMz-;%ZjLe}H$LDYnO2
zau!X8?B;}Ss3KQ*)xeeO?=N9FIT)}nnwqa!4f>7;bt&(xyQk;6Jv6fxQBi$fJ!xrh
zKgzj>m@-X%^{KP=M&x+T`0*S3RW$U=tA?PQb?w&LlRLBiFQVQ$+{*K6cs`pFfEhCD
za}fh`j5F!h?cxHh)FliB0dPo+KM{_4{QaY?G^~&FWM>KOcO&U{R><PO3VN!*E=_7A
zkvNF|sw(9`PI}C*R!<M<wVMw}_riI0ho04GIe1xC(9kB0CA=T#%p-pc7#*Hg%M=aY
z`bb-RB!-_NhdAN_kuz~Ve?0v(_%Cs`c691pmMJsgeR}5e$9jZgGCZN&=+?#6DS|h0
zB?Swf!{G@unOAGG44zaqUFX{feK4>Rf4}T?s5>P%5XS|b$KdkrDZ>(cT1GNB-|sB(
ze?}EEfiMa;RNLUuv^oT6rww~9J!MuGqKk%`fE_I^VEE@YoGTF&ihtl{O9jiEb@{+e
z4?@i^VJy9MhG2!8ebp;QJzaWjnr`?I2g+Og4uOn5H)CKyc&39S!woC6!^capeX(|=
zhEt{~AKv$)-!we^A}qGW?m(#$pteW7zQ2gSN`}DmF3u6-srA)tI5sC9Gcw+<Eu$?&
zMfc=B3qQY%FI4AS?97P#s^M+XCbyDtX(=leg0sM1B|W8Mz%|*-r+=20|B#Fz_-di5
zw=*Kze{|ziqQKL^9ZrBSek17?h#{=?X+U1O|D!2In{;2Tv%SdfL8QcbAZIp+k;<R%
zys%VWF(tv}^b18VK2Y@xh*LZ->(yoqU$KN9I@g;8ab%Cs*ipVb_>5R+dy^tl&6#uS
z2M#oqml;KU?KNjD`%`KM_di~gpaeYlDFgz~eKnN`C4A9dWLElt9>`<kHP2HcHGMwh
zcExaA6_q4f8~oFKQG`sFBpj}TttUreHM#|X1|uP)>14Dm|1#s-q}V}0U#@UI{oRGg
zPC9R6DiZ-5lGw=U1U6L3hNE#nrsXBPzfF=?u04z~iB>68?@V=gdZtyFzSkqv&k5aO
zrZLR*%FGThbIbxc_vQY_l?~7v(Q%mlzgz&0O?A!qS-pjw`}?pt?IlWi;+IsF(4i|)
zuxN&kR|5>`kql{L)PpIux+l!$)y{)^t!n?rti2u9`GP^JoS^qU7uLNGq<FsXGB#rJ
z*)5V}kqEWbepfd*l01%<LY8a-(c<oU4PgC09&Ew;;13RqS@F8}!^HS|5_KhIqb`M2
zzfidB!YF3-OTHfaQ{K@eP{ZT{9J-C0qp^LT-d?*bTkD$<ppj4Aw3F5pkqMk_u3l;(
z^)6frGSMxC0GIy15bdRf4L+9*U7PYxb5Oh19!PFf3c*pgYFAn8Ul8}y12a9|<ST}d
zR^f2RPneGq<d~BM!(G0v=BhJ@Yq#;UMi=VY4dGApqJIa*f*n3Cur9HrH8T}i_C4Cx
z1b0uEFgmofk1w+&uV7a~GfWHcTFV%abGX6~XsjU|cVZhJM32GUO-~}$rma{Hny2Zh
zJib@$eErMCPl`?J+QYeD?Wq}X*dB)Q)?^!x=q?e)y++jnW*E%vu{_ezI%^$)dvlo5
zTm805e<FV7`(Pq`Bk@}vU7iJQb@xmYu}7^Qg~BRAi-kn*)1S9$Y`NGU?<JZPECP-f
z9?IN%pFAJveMQ}WsX;D`qxrGvVzH2Tqs5=yI<3mD%wXs2>1^^rOvi}jQa2sWjdl4F
zka9Rzh42#&_|?)i-X&aj)kwm>0U0XNZw`hvpnEo%$!{n>l^O%Y$Dfi=RWR(yFU<N_
z!HdIjl}<N?{xt0I)?L+$6Dl76tL<@DvQm{R?)W(b6rfg5hQdl4bP#h8_^Dl<Cs|!W
zvQ!2RQ#wNroK@yoHXUZ2;wwB?+R5YmX10=FEzZFrL9iHPxXB83p)}J+f=I`S!QsxA
zE~V1FA)A+t0MnH_OQ949oks)xx32Z`u$t}PlDwp=nY+mJGfV>zh|1W1e}n`R&||}r
zsW@p{74*ZI6!zYJeeX62-$*gJ`#bO&{zG7?0Y3$UUZPwePaaCNSBC3E)YF~Wtrbf|
zmt(+WL18gm0KzKnrx;d*j<wG*XvovE5{%s(iI1Yb4S8t{_gvb{NybpP760BGKrKzM
zSF0yERfzx~VZ`5J!ZKDuz{2r?w|IN}B?lHUbV*{r1N|>2rnWXr*s4{KLq2Ox69{ka
zRHmQnY$<S9*kBG0s+K1OTY@;9dCrdnM`Fl79yz$cqrlblxO!TydNq-zJLOV56z5#c
z7U}ai1?hF|*jBH5FW`3bg$n{8kv$=2baYEJKwt;k=C?u>qIgDVrCT;F2H#3&_v`Xo
zjr~H>-^XcH4p_l==(qrtWHyLVel?~JUUIRnKn3zE-`M5L<~};)2;#ho6P>jQB8MQg
z84GG229aTKsp-F>fm4^cFz7P+N>dT@XJ55ixu|^can}Pc#EhL&3wg1yPSV5QkuYKa
za)%nS9+DY=lIe{Q?0dZCRA|b1lwQINQEF1Mx^J2m^A26@9rK9-%cLZx!`{vprd`?h
z4Sq`HC7A}Fum*3Ucn`Lpl}9{obm{X#IaSF;MT2?HUssg=l2b}4Fl$`kkgV}<VEH%g
z=xW5w7cs7LpG4-^?3l8M-58vc25veql)i`WrS7Br;MDUizR$5TfMrt7fofPE(rK#<
zeCA>3qtqsm>h3ol;xM`D7t%oPVnigd5W$7&V*rBL`Y^KoZu}G+!inHB#T{?&xzgb#
z0#(n^Bsg<!q-?QF1ju7%t7eWuc{Eqv(5eJc0t9CS>^Okzbc@AGcCVieIsbr2Ov8Y*
znzV_67ggPN;VE&qrkd}Ss(%Z8Y2IP>EpT2vB8MTiDJz;~Qp|z&^hhuN!qrQ)JY}mO
zZ3d6o>ZJq`@Pw-F`MNT)FSPd`|D03b<yMnaMy}sw0a$Q@bmtrw=#h-L9nh&tyg%{w
zM9vARP)wq?#?&Q5>YJh;6vO*=f-!eo1bSTNWx&PKg2g+Rwf3L=JB5|MkQ2xr2y7;y
zaNm)`dVqy@foJYAqYovG$(fIK4~>rcY#SrUaoqpRCJ8C#eeIFj<XYS-cmju{i4~Q6
zd|Lm>g6=C&SE_=UeoVB#mUgy1^i07n47MDWh{jHxxgb5M^2zC=gz8qyGj5gD6n&w5
zQ#JQPvgxhF8adp=Ve^LWP0~Xe#OYPTzCY7PpFv6o=DF2lw2eOF;7<akmhMMtJ~tMn
zb(I$q+)6K#67bnL^!3rMVxrnsWw6M_0Y5eG2A6xZHOc3Dp*oP4tSvUY3LPEqKjJ>F
zABzjY1YS~(IWc2RmL~u9xnJ80c@$pAh{1_1>sQuU{?IrwgD&uw#v3POMSd{pZSiLR
zmAjNu>V2{>KO}YU9PcxR_?y#$SW7et%k0MlKAWWK6!jMA{@%NzD)hW2@QAL5Vk0o#
z@-lbY3cdcpv<q(n36H9L!4+uw58pd?U1gdI#3W2)Tc+ThiuZkoTkQf7e)2DX+!eQR
z3c~Vb(s?yY=v~OX&4?rAUY#i|FNRl{L*cFhPES}u39r6R?zZg@lCeCJ_oZWcU@!Ep
zi6uGo%>N(+gz3GsP0}f_Ax-i-b9CH^xESFjdY}-Nmre4B#4YIGI5K5MY=V_JfByx+
z+NB>wNG{b}Y#-SjB=*aLn6l?+uxcwi|D6AtAP@5FWDAb2;5h=e9R40I5e08yNPhmr
zGCx~iG@UE&J)f9on#)9*Q20=8nqhJ_moKS~B8&hWLrfSUZpbDPScOmHW`NB#ox}8{
zQTFy=zn`Bp?E8hE?kuvzH6^pSr#S+owN*K`EG7s`=o$W?|7L6KxffGt$5e-FShcAe
zeX#a+@eCcRh08r~6J0!!IExp8(xPc5+NM}NSNu#bxm&&&X0m-Zzx8&YQW!}vRX#W<
zZu!~$%(zWojaJ)ccz_DZ^eNQA;8ajY7+SMfyQfc+p9^3+6rB=-LYVg4?cM@S=TL>z
z;LV(*k{Mfbm|Fpqs;!9oN79~{mBM7v@=FL@aEjYZmh#;|d_!)RhQ13B6=^DHYh^fo
z(eG6ZB0R2*@8h^Y0Qfft0#BXLjUpBRsV=^gY{#rmv9rqxYVn|vU`1O+x5-Djt<*->
z5n+?m#}^Z;41i@k<ia2<Dk@7)wU9U`=Tn>{UJ_zHcSXL21~qFl5)l{Z`z*P`X}-_~
z@Kd}e-6NjG7ebCwdQFcl7Ycbx3mv{|PsQL|1`q(v_-}?$bEl_X%O<loQh{^UC58-Q
zm{TCv24wt3AYT+e>VDyC*yoBVyJU@*Ppe6j8%-=T8g?CSP|k9jpABv}7N_0y?1cNA
zV;0G{laYVS@49jD_ma4g1oIKwWEEg4xB@K%B=--=hxfI)*h?ylLCa(5ao6RDo6av~
zeP5rm)FnFl-nrn`z;!841&OQVzDA7b(%mX&6XATI#H>ek%Nj6S@Iuam@Z=3S&YiNg
z%78t)90>%6*KfzJL7kqzTC2_lxf(|i`$_LbU;?qPo<@W)<uMG3a?+0rt(g7YNmKlN
ze=cR?YZV{z3Dy#t(ZzQ14>M5`0TWO^q^`)<KV5%Q+@bcSzDOJQF;rRG!94;C{ywX2
zmg>KEA%pf&dv*KD{e7s`R?Jl|q;CLON&VK^622YEX_5jt$!OSua{13@E*(oo_SgY&
za<$)+nZrT#mKhn^qe2*$0|6s=TUP#UjL_0+P*wjv;_6|0<;UZmH=8cc9n&5^Dn?3>
zSw?YzW4sfK`>fdtG1cX}AnaBNTzczCt=#$I5cieto}FwV*bL<>G<-v6&bl$EzfO_(
zJ-l8Q0jfj`^dRAq`EyEdN|n!@$UYV$PmV3!?Ka%>xOhJEuGk0)tY+xJvD=3^3yMvQ
z0)(XSLde0H)jt?>5mtF}Iq!2<kv_V}@^yDyV7(T@?|l71O>i&Xo&i^;j!@OQNQ3|H
z59srYw**1irG&a3Q;URWKu6EC#(~vwou`X|s}U^_H@8_y&-#r5o4mff2$Mmc&dA;u
zDrXM4nJIvhmF|kNp0U$fTqC%6o1fguN}(Ux9?jilhT&;AM3dRzK<A%YtiDSGn4b{k
z+#WdiW>8irzM18!lf~cFxAP#Qj~uBe1y%j$wM7ksgo7y_J&_KB5@oX3|1FGGWrSnC
zUuc(Q1;cG5KEwPOT-9e1{CIhuN(`a+=C9&-jlL@O;mx5@o?lCPH%L(g^M6u!Uoz@G
zVh61EtLLY?QxxkT0ZVwo6)pO|-_yKUSML_iU3ugxSZTxZdapfAfDZ>(lKv;{=zM0d
zNGfX!E6^8Gq$A(|^JYUh;6|v{#Sd3M$|06sMXvP%#7u_T=}L2$Fayh!9Q)xm6)#ZO
zm4qy*q+dinE0V}XC{G&?`X~$OAk@CuJh+M7+D|E12Saq2iwgefeuTlqykI6J--Gep
zYbi(^n{i3jbN$s|EXZQ9;CKkOTa}SqrC%lY66K2c)2@nDZL<zl$FqQ<u(+t}3b?L?
zaBkp8RY-mM?I;BP7llkNk4)51me4WVtEVvRJxY>wG6ns+^&G#Bm{LEGVsJ}H%g4}3
z3PDj-z27bpZmGUqhQTH+2Zl)s-8>H@bNL&Jo^}4Tvw1EWRDI?)BzUI(*ziJfsq9XP
z$mY)FG2FCC+y5CR2`4;FJ_9d-x=Vm3*b%72$JIJv7Xw3mACW2DWIG>N7@tMVXFRB0
z+|Cc`lIg6Sr<12*00M-ehlLs#T(1PzZ^<KZ2Pnr-IK{3Q@}ec~NG*^`=bZ<)`S4sI
z%z$pXxCsL=xWYLMZc1WZIRN>=R!HAt|9%X-h-}~4PV*%U>z--i{=+ypthe(H)qb0A
zRaYC=T3>iLP!ccDqlPWVj#J={Wgbn6VAa91u5cz*)7udV*E-hYhcAf#`refJSO;M>
z_pm0yaf||}Z0*(Ih2#-<#X@qwbRbu|mZOYl<(hSlJ`Vy6==1YlCGiCM<nBgOHrHm^
z!IR750~l^b4Y&XZq_*G+^fT(uj53*t3MbY{7ReHcR`xY6u)SdA-{<s(oM-w}8!Oo(
zbXuKDN@lJVBOU$b0NXz?oD^8%df_vDiZv@#z*W7&!6Wa}&zdrDPv!Mq_={1RpjI-a
zs_1}5EwE>N!tz;yjsd_oy74O*gd@1c3r^BTc^@k?nDrdJ7Hg-!D<%xS$v<4*&dSxu
zKF*qZah_>g#47HcrER;WvBx_|mae3h;m~8(M;vBN6joe$oFQ}^U4z$27X@!WrL)H6
zJ=o6|*AWNJ{C&bHEdPc>A^Y==J~2iY%RAm@fR{_p9#L}U-ka*pY)^XK0ae?9=17N>
zSL&$juh!5yH>NCvtAQ{0tRF$wo}7X#Y*oO1!)Ka5sZ1?n8;TnCiqj@0r5QNP4rbD!
zQw_gDgK(te0{aHT)mg3pX<qk^`pi&W6ggCnnDEEzwztG#;HCYPF6o+U5VGC~CyKy=
z1<s8w<l1N-bW^^UwwHS(rY+}sJF(>~*e9X5)6MMaS9>a26%0<Y-?-rK6jGudycA9@
zI2%#`-gWVRR8N-F_YeZ6h{#e=sLqZ!j4y<EU?`{Sf54vpV~kUL;0Spmt2eyy8aFrS
z>iyvJa7OB)$a&BGV}pD4u{fxMi^&KXT!M1MHZ$l|G|+6DM43kgDshAC_ZQ(`MK?pQ
zg=239V=vuP%#YwDRq7JymayF$@PfOM7am~2qaR}DaYk^A01)otapBv~#^8*n)bZ{I
zR#mv<<B;FiTIKWfrD}A6p_(N$TWo>W(NnpUWgZ}fw6;5WdtVCX_zPiMalj;RVN`p4
z{1T0DucXbhfpwT0#p&m@)TNjB<INuPnS<7NLP^8CFcWTmf^Z?=Wv+I>$wg*^&Kd}K
zffQ=E@ZacxgKQ^SlYM%yADjtoK_N8OXU{cNEAox4m&2E;2%FS_VwfA{KgO>I!Q6(3
z#%N#;+jQX58LGPi9)466z4-8^Cv(Q^oxXaXI>bkj9Cng^7K`IBKpB}1vYbJ}uR6|#
zV}stet*VEXe*m<v|Jd}&7pDC2c|e@bSyv#(kuCpJv*bb%te*s&bjiP_w$}#Z_05l6
z?XChSIVu}{2ekN7A^GfyT|ZMHyJP*L%F~$Xz6m`D3M<57aHZ)E;9w2WaN~s?D`!ad
zqbjJRP?WDD`rEtQo4A=S5coK;H)!g!)<~58u7%B)a)4(qKqFu*(La&+Aydp-M=L6U
z9{M-?s!)xQE$MTGebv6)rQ>z5Y=Ny_XntHjoL|KitcwFmiUn+^WZxJ-N6GAMYmI}c
zAW=~e=><67j6Ygs)*D!9YDv~_w*ym?HdX#1>Egfy$4_>;+nglpLAehs>RC*$J8JeR
zg1}1(THZ3K{K<EHWW%|~`#RGafnU-0h=3Qpd-(UP@*_Z?{<n+Nzi($>2VBg`l^i>)
zlDVE>=1HT@3DG)pkNvaj*GFH^avW69ptsQpJnJ7-`-p=s*+Miia7$>%I>BHwnm*f2
zs(LV=>^kp9E*E(iQvW2A!92ASzjjj&-VoKkLNU<LKtl4L?7PK4eJ@N(|1mF^3XRSf
zmZ)nXzAlHodnQV}CZgwM`z@>qF9aPqB3Dg8A^l`LG5?mY5;h;6e1FRFL2y%{!6XY-
zZ`1^5_3wCblB@-k4hYRlM4va>Zq?eRjnRmis&0YyVK~>_vE)Ub=fl2^bS9Q4xCB$#
zjp=NnD?9uQebdn$+{D+>#u%jaJ8v0yg7uc})=9&HVGg+6`~@=;sb<NIA~?3EYIe%M
zX7gge>IHPi-!MJ;T|sO-c*r6RVvGqG#mKIf#>d-R&ur#3B!Pe!IudHbQJ?@Rj)Ikz
znii*J8)h5xK!+^hBKiqG$<vIo)B}gR0i{11tKM=uC{fubvC|(pELxsPN1k3cVj_Kv
zlatRINNh`>Ox@yuTm_K(C6x6<ee}q|m6q3%Y~hZ+P{=+v=%XlPgHAp5!DX^PL<Teg
zeWvE%K?775-RQsoRN_MXT04z@xS7~5{G~fQKHl0;co9TpfclSy2hfF-Ko!me(>CQZ
z9xCH#0w27r4>l}-MVdl*fQQTh_66?;2}Sr7T7;v-o>vG9ara2X$Ix*%iUkf4e1Mxk
z1@~y&-iwWvsYQ#7C-?)QU9J6t-6ZiscWDXff~QCbaT{tUgYZz3r?{}&Q?JriJG9ey
zBAO0oqQJ?J`cs;|7Wg&-m({?v9H}V@LEXMAMjir6(ifzUdq8ma49P5t(6mGL<B-1L
zR_*sr*qi+eiXNz$zZql8o6FBBCa5fAA49_(Kox9Va`~NObBW5Rxwfjq4Kj2`2N{^Z
zl(w(H6PVtbd&a_2&6oodUbu+CHB~`?<i=KffO(Vuz0`#;%dOC=&$~5<>_2bf-V4u!
zVkrx2Ad$ZQPGz{EZY9(8Lbber88H8%laM17;0N<x7Ua|(0Zq;a0rM_k23L3s`XuUN
z_@kGlF9UTq)hAuwM7X6Vy#mR5(~*ZQB1U048=;%s=&xklIcVCERM~4As(4^I$pyk`
zL+65t^-1l24%O*@DRJi)v&a~{eBrkP91l_5foBo*q(mhTBPFCy$WZ_@>~#z!43(AQ
z7*sS2OUAoHKut2&#f`CtKSmOG;BhzK!grZ*UWyxS)fUU0#OTH;dOL1nV|C?>9f!8q
zrVIuElZS;~7~CIJy^`4N-#kbzV~$5G;-Kixiy=5BL1mw}#L|B^R7J)E_u719s{Q;)
z4!D$q1whdxg$gclHW5^{Q=Rc`j^uf2<sli2CP>0-D5m)lj;x4;pqk?EHe_h@3BQ=V
z9&0Z{S~vWJj8bhx7ScU_@<@eUQ(xoRuPiNee|KYxZc3WJ5x9=zQo?#@JuY52G7e>3
zywcr#Tq1`71dN4cI4}UEfal)%(0Axq1{^P_OYS`SElBXE{(hKb0ho`w=y4C>JV?T;
zU7GapLU*VE2Y~^kS=0Ja-J)LLr?4SUQ{NbTwLH~o)q4{c158x#TO~{LGq{Ejf4DEg
zF*Ek8y=WLeiRBO%m`hyR84@iuHd_=dwK1+AVffgwg@Mng*c$^Ea)NrJWV|@qhn4+|
zs#y|g3x==&O#((F`GR+6LpUnY9sRC-a}j>yfl?jPbVz#OvTlC9%q;64KcQrRnFc=h
zXC}&on1u-k)D^pGDC~`IK$f=qdjkvxy45UYAjtN$`|;<rZnOU^()@9xhCTaN(=fH4
z?}yV(qjOfj)L(T)d{7M4LC#1aPz&5=SdvxXIg(?~R+in#mDmdkNnz=*Z`2jh$|rPZ
zCHYsB)wTkG_Q~7!E@t4}_1h9m)KJUNfq?xCTHKsxpJ6hE{v!m<?HJ0b4Hu~7%_1cn
zbc5F)R+YXo-k*sLRL~eoA+H^d_pvdO|28Aymi^o5WO}4&Kk%xN*Ve&4xp9vQFII$Q
zP#CwB|LhgOi53WvL2VzHpVIU_#E3T+E!`CFO2~U>{&%ZtKJW$`Lg)h{T3*#Ln7GvT
zXW?GJ-Z#|6W3|<rpA{>BL_PM8(RCDXq$vEV2J&#Bzm|;D_$38`#Xl*nPc*fO<r<9O
zk51A&?``${TAK-d>cfazm`l_)@@x7lJvk_kMmS2}SQJEQ)8&Q1Y)u$xphg-OyvvN$
z=BGU^{*)UxR^JK|Er>N6$eh%ki$%4QJ3U+vS0nhIo!H#^6FU0v!5NhkizjnpPTw{{
zG~EU%qvE5y{GB{U5LrlzNk}ST-<j=y`@em4)A$J;hx2(198;7~w-?cyTWVTV4m?9%
zt?M^YRErlTh+6G$N1MOygqKJMoy&dcBj-sDVz8DfC;~%O(W7#oTH#q*6;7$-Q30;G
z>(wuxF1fH%qbBx0iO<>+8f4^*uRWzBJczgpFKJ`9R}RYumit`b4uSvV-dFRUPtTqx
z@|Q*R>A=fwrFz!kTI>m1fw1pREP}umJUffO-90cue~;88<#hJF9eu*&s~MLuNmsX=
zlJ6ZlE5USv!rninUH|lC$XWkd9j@&PbVG*F?K>f*Av)uHU~2_z0f|a_ADxf9mHFzh
zZPeG8HQVn+XnuhpIXn<BBq&rHfhHo-e(!U&rUk8)tb^m{NxmqI1ym#Z*QLD$^Xj#8
z=Q`*%?t`v=v)LhAJ4>B^tU_x~4!Zgp_q@29vqPur4A3S!5Pww9g3T*m4@p>vrJ7Km
zk)JHq;sM*PKa7!FWaMf4zrFTVYAM-HmW;Tu;L8uFmvP$@Rr`DO0zma7^RPm{BLZK@
ziEup2Q<e9O+h!mo@QjCS?u(I${T>K10nf;#B=T_2z58kzKK&>Bs<IXam*0}za94GI
zq%k;er;#`&+U>xAYdkswhZ-#?lDo}1hTnM>r*L!H``off?L~7K*YeAn@;Uk+e47<2
zcKZ61h>23_pTQw00{yJ?3*y@04%8wbR2|?hxJkihcpS_7liz~F3hMxy6=TvHYYOdm
z_r$-U;XV&yy3{y0PrS2$GY#WI&>cO^aYQ^h3BNA^wJ>yxxPUf^@h;Eecf7Qe$;W_H
z5bzycd2XDr%L|VKRgRTDMqqi(ZY6&=?K&XPgAJkp!uez_^oXW$8aYF@yTDloN#nS2
zbSWyd($A)0O#Ea%ZTiEHhNH%l-s<d=uQX%K7VFU3jqu4SOi6l^4eq&C*RN;m*7;>-
zaLkoB?{m2G!oG8;P8G}P`NB+sqA+(*2||kDL~ii8WUG!$4}=`;e7(`QiI@=|U;ATB
zEQvVW3_Up7O$*%!|BJLd<^s~(Q?NV*RPs#v3OFkI8tcj3b{NmN#bFLqZug$sM94iq
z%77=x=lwc}4iv&1p9}25LR~vHGM8XuSaL$ZuW0S~llU%~KPm!ypAKiOe*Y%^7O%)4
zSvr~ARXx#QDHkp{fEFj(D{g8{0B~}~%{OgfICH^Er}O75ZUJmJ>0`7S8pzTo2#y{Y
zCw}?R>UxU=2ajp~{hq@g!t8N;0gg&cj}ErBLL2pRzmr=~K;l5^3#r)TDc~ejpC7B}
zG;}Q*%1yDtF@F2Hu#LEQeR9IcPx_LJe^Sm|bx_euYJ-3kO&uu+X^p#Z&#SLQR|29{
zmzRFM5N#DF^P<nW!h&#=DmTFiA{;X|dZ?(=k#i`lIz_L?H|y<dn2rpG74NT}x8~>P
zHdUea6zTAd@cZ3=PrA-Ju5Nk{wW%rvW83<;+^kGQDd7_AYywzsn9k;v*`P1AeM0UK
zAZRbKq%xG_B1X`4@lp5>0?C=P@mWkHxY4GUB=?9P;y<68V5TUA+G)<*={Ki2!rQBT
zl0XqWS-3!IcAy=-^X8at%v*aii)$Y^{DVM(3hVQyUj)@|6$_+6I<8c&LN7NSOMRl;
zK5iqH746GI;5YCYvUPM}hz8U*v>t9C4R1F+)97dbF+~hq`7CeNzBZ(H#C3Ejx0vvl
zT1ON~(=QS6q9&wL;SSV%d+3`hF7zl?v0i!LZprcz6QsQrDp)!-2?F28gN>Tk;iSwj
zfiQk1Rn=Ul13feYb1<Q5tNxiLsYms--Stk8$(}jHsU#g=TtYdnHyy%DI+`WPk7Cn$
zUG7Vie#T1{jGcZ?9EutY*qhZPh&0vmPiBYz>Tctnqs2Cn`^j^XyA%@u_^(I6t>eb{
zcOz1qyALQHk(oh_SYtF+MDUq=p}TTtXSwbh0~P(YFB{YQNrY?t@9{zx5snH86J{h@
zS5iNMqM!W?0}s|FH!YglZNg#?cYBF?CmDStziG|ShwGDGBmes`Y<9h)W5if2i+Fcm
zz)vVgcrkkR@rQ5Z<Dpc>B*zBJ4kstRn;*w7JUm|cc;RU7f~K|H$(Cxos6#wggSG%_
zjL~B95ilUDEOmPrJ3oWM+1xnzMKnqkw&hd#s#6p3+ER6@tpTlp+q)ffZbm_7^uvMs
zB~|)k{B>J3K>EXYX%|$)+DB6#m0Ue^_?*LaRwH7e&1&i~;)1+2lI!&IJ&!>5qn*9S
zyYox1`Q=qu;WAM>qB1{iEX3b#TVBc8?+WP|M(K+PuDb|1;us$s4*O23c<w$HM*5>I
z^k{dOx#{GObR%)wd-o3K$(}do>S5@oM|<%v=#=6f9L|2I>}y}U1JwGn@In_L(J2+U
z9CkfQ?|O$d<iK9fGp3ueX&4bs7FhlTKk&;u^l$ohE$(O7c|KbpfUH`h)!E)L@8f60
zm5$I=DHjAmdPRBAtJc-`x~s^g8Qem?5fYY$ZJb%SZ<-Xpar3x;ZspmZHu$RF#t(J{
zi|eXI&qcvE!)v8K-17R0DW660B0vF&CDgWQ%kf%BK<{7qkKEXxyF=+Gx%Fd8bCS}>
zReMoS{IO!M@2`9&w7xRij{e9f5~^8FV3`TU(^+Ifq6+VeDeDC<tzy0a^1dkPtHcc7
z2oEj{xNZA2H<a@TPfdPZ8K0)+mj(gM(xYP}ORmHFV1;@bV6o|E%f^Qc+^6hLKKjqP
zK(}Hzmf~~%4z86Law8&$jwWk&6J>xrAuCj~bVCtjHtv!IGLH-5b{0PzUDuJXS{OnT
zc3w!pkz9FiqLSWcxN1mvLbpN4*1AHY@km^g?istG(uL4$s#pemEpUztfAaCXadDMI
zNC)P~-f_;IcS8wZD2;Gr+dFYtxz32<tTyfZHmpDcd*%_2J~GZ`vZ~N`Uv!>qUd-Mz
z55`vT;sI8<;0gsSoopC`AGjqkM}qfvkQW?0D}Cp{J?bQ>Ei%<JiH)x+_TBzboFKsS
z|2H@b$ee{wJS29(v78+hQ$kyzn{~?%{hxWbSDJD5dCS3BtcAn!VU`|{9tepVI1$!T
z+HAL*QF5P*&f~UpF07mlCq_SR&E3isbI{>{0|R6s6tL%0SA@BB5I-Xv4{2mMyM7W~
z;Wr<FTLDmOGtf<bI$}|+)&-kp?jfQkB4PIDI0dTJsVN7;o1s4qP&IPg#dmrG2|N=0
z^cF6sdc2PY^<0BsG^|sSUf;0e@_y*w!!}yK7=G%;zs-CBo(R&Qhwe~}Ef9;wMZ#MY
zFRz++^WWfsd`^AJ)oHdnN1O;z)!Q3{TSQWWeRAX%mdmG;8j0fq^grfhh_7>cGiiTx
zAh<@Pr@ar?GOznzAkzQBKkM`04n+Y8_JXf)XfeM5XYwQXSU&(G=F3!_8rS{VOm5e^
zG-zI(o(yztSa*&1N&zGn`%4x7!ho`xEHjFriGP6oqs;yMEL?3<HG7t#sI6DJed<ti
z!{~^8p>}Rn0=g3#T{6!VXNSYVHe%!|WPO{i!rJA{EcKjMhGogyTy@1uC!`!+r)-I9
zt3IBCC&HbnmjCv#c<e#4hA13Q?KM9TLh1x-m?qLG`hWfn+en>>sJ!^BPpak}1NeX$
z9m<NPX}@@hSc6jHC?F+)rIUY!C#-0)uZ!h;D6@&x2<|qBuT|2^Zy-%##JNq$v%sD8
z9D)=oSP!f&&Fo`8v7iVBI%wQ&ChLVuuKX(MKx8j8*FU6PL)?g}gca^%2<-zAtSsy4
zFbdo)?gIULH|GWam`gI^zEic_1~wFgOAv4ffkW+djOK<i#W(ibV|NdC2j;x3qRh_?
z8i@@$m$4-sHk%TBVAdb@;0b|KgCP<qsD-#iQW(@)Famhm3FobE!+ieMM%S~$gIs+a
zO4tf4elfwZNJ<rIhhVT^s5((1M6N_zz;`;sWQyf&Mg4m0&E5~pxNa>wzPEqUy+<u-
z^X-l-D6)yGh?yiTDEvyk{)6<Z?#xZ>r&G?jw1N9#Z}o#hMy@2>EBKnWh<HcHiLVB%
z{aNtesizCmVg8$~Km1tiJ=rW?obnY7>?U@DXT_?HJs9yx;GT2UNusy~$%!}$8`${a
z7OJFi*X2v#JBst~7T>84=5G|XEngqPk5M8V&)ws<(`sa`dqD%Cf!E9}C{W-6cx?sL
z=!+==gK}kPOzW5%UV5>Gj>RoVLv7QyKQBl?ZQ?XZ$Qs*fXoQ6rxI!&d<0n|T;=gw+
zbbG%_ftLt_Rhv;X_QR;c)WMtb&0!n>$1^><zpQw=S0m4HV1q)R6)-%?Z%SmAmbWUa
z;aa|7dhBHPOY)I((q`wse`pSW%ZYm>IP}+l0vjMQ;)Hw1-%t#Ji!ofjSSpMbW`*?+
zf!;$;FvNZF|Mm9WUrlvEyE`F)5L)OUEeg_m??glq1w@o0y+~7}HΜC?FvC$_rSi
zf>Z&KjzA~^Dgx4*NKrZh(gY;A$M;*`{Ri$^_m{I)a%T4Ia?YIDGkcy9E7w%O1H$EK
z7=ER*BvZ^)|I;_Kf#ZKqT^+s3z0Fhj1p^(GMkCk09jIyf(KjZ&eo>Brmy_9A-)E76
zVn~V0?K%B0TR)}sPZrsPAXP#a`4dSphp38TX6V;DM|v&bvgAwH;IgAjVuW$CscYb2
zqi@MmqFZ;5l=`BTIVb90NvhE87;t1is!w7gMZ<&5n0>uBNDFnBzr;btR8T2McHt5P
z1AQ$bDvAy)A-V(rIVNW<w3KnmY+b;eWl3j#Nk<t(Sv4__Z4dq)?Ow{1i?&7#XiVV2
zHUbF}bPwNs-jPrLL3#cNs55|%Jf3my&fVT&QO`R*OZyO+OkC*SqL_<-CoG>>;T1|a
z6XZD4Ad^zpV`Dsb?lDSQf2or)RO=)Zo-rIbTdimEE7v>WPn>p|#EscI8&0N9cbw8O
zq+t6$K?nPn?TNeO`Euf3Q?SIL7@Y*#3`V<p(&mzMYpmwiA>AJ{H;oJPY<=@X{^a{Y
zbZ5%$T(S~nK8FX3ohx%^pJM@AwhH`u;U%B6{>f-*IDOpt$6E-9lUp!^vh_^=y7!w!
z<H){yz4={|76>0&I3L^)<By0<W`|5I#R^ZL5$QaUMz(9oN{>SmV0a|~I#PT4lYlvm
zQ~&s&aIrt<t~hBMCIW{O+3=E+Onfx<jP`aOIw$Y~8<fMcr;f10*VgY|PgfWoT$=7F
zkEPIF?bqjIP8-trqn!;hzI3B^7VTB{2Pr$dDoI(CZ{=S(De>Z^Y}djffgvORISHoS
zH`CO(@(_>r6rmXERh1+sNt&O$i(>X^9}drgf7T9=1X02q8~(n>zN{*Hg9Kd6I;+`k
zbuMa%co@Gca}FK@79Im1ulZ6JWjz=f&uCHiokyT9*=6dqRm5u1EipvhJ$_*&nPl-x
zcTO&ySi2&1e)Q8Qln8iBl*~;jTcba}g;B^!_A+@t!}pH%DJ#tb(f>vkU%^4+2t+q}
z&-~1~#qa1wz3q?;5kNy3ymUwUc{uuqm~^Fjo1;)ajS<RWdxKJueE719l9nYf9cExD
zMyBlb#;ADlYR%_l7-@~}Ong>*LiKR+mZzr`@6Ttn4e@sIY`%}rZR~lD-AZbqxD^SR
zvYl%ZvNui9OUx8V4mqED;i6zO)4?x+-HUL&zL;U9Zp@R_wp>(pQ)l5$7cDfam>d6V
z^TN`ZrBc-<$L2pF0_(D;V@XwpbI1l(i(jkxe%qg-5`$ydmA70AgW&_yn(taqCJ?^g
zub1KeN|PKKwli=>zVY_sKtn;EUd{zgn%O=RX+%h8U4KyofbwS<7-vzZq(8}kxV`7j
z-A~G$F;I!<T@<NN^y(j{SFHt?7{ja%*EM~GnW0SUF8LKXN9P<naSUP0P>!+t*$1{e
zw`T$xC(VL1GQ%_auC)Y?Qksx6VJu{t<RMgcEzSS(+I4vmz&)6E`Y-QyR>*4|Q=Qtc
zI2g05&VImf=U1S1qm>SW+m$_9LO&f_7LWZX@=m~V?RLl0a4z@%VYP#Eybf+`BjW5*
ziazPfazytd=Fj1)*OMiIc!4KkNeQ7TC%o7xSJ%xR+REuqWvIry#*|{OBkU<TbVP*^
z&9Xr{&~qF7R9wh+LB)<hr%{AWc86aa5Oc|!?^zm~kunR^>3(WU4bEwo3@t_e;}Mvq
z|KgKu_hNRlH^k{JYXQQg8c<_NYgDk#Sr3qD^~gH|gk4w=AydTd`m*tokKr{HCkyv!
zkQGRIIK<HLyXq><1HlnN!vnT3n%2c9ctAFjJOATVSoCZRY&fTQSb><JV$P`a3dH|#
zak=8BjSbcP9dNPU!>o6c^lO0T{c#tHerY@>xjv<?LwSwh`idDU5D3<Ncdzf`8N)F!
zv`U4rM966e*E~(P0Fm2NLpSU^j#=68fn0?jZT|s6wLr53vFvE|Xz_w=B}t;5z2dZx
zCI8Ptp39h1191<4nqNm@PCVz=Q`noQ-O3`E&=~2;b~Y$naTz%?#^O2V^UJNV$&+m1
zCqaM@Q23}byfo6w1$hs!M|usoV)lNit@*6$JRFdXG`_@tlE>v85?8t07nJs7-2Ou%
zKmas}SDDL0KscRx?ZZE#Z!cpAM@424CVeDcBwij1c4IALmWEuz1#6Kgzy=rJ^l5rz
zfRsIzJ}6Y9l^O2LZvy$Yd$Fuh((N3)=%5yJ{TyYt^}k(#VVi4-css-xyQ#XM-H`wb
zXh9kd(XLfc{F0k>K1S1@K7ulHz~J9L$eMx|ROg)7p|8Gc72ZRcabIl;l0gXPQ=Va(
zH8wCn{v;X0=lx|*r<&6ey-ul8c$dmU$a@n|<55@(Ls%h^dpe?^cg67q&@1KpuIQsx
z;%*ecKnLklrSs#vrmPA;Y|il_WAwvXiry5nb9Ly00vibwM^xx7Jdhx5+*(M-qyarK
zf}w+(<=e~~S##I@LyNgA059KAD>b-FJ+|o;%QK@>CyH<<y4A<_-;)uwL=RcR4=x{b
z1x0gmCLyEdz2Lw@#tB<^Z8+P52o8Hb7IzBXa_j+LPDK9C&X@WfE)g5Ot3%XGUB)9h
zAe&})ngFmOH!`m8QYyq8)T-UspiMvA*P+?zD!E^6dI(uQ!k7KjD#7ovL7n9TtNL=!
z15JQ~ZWA2x9^lrXP4J*meGPHNC~D;SCVEWW`E+LICi%5c@@!@`#XeE(HiO%7)=St9
zWdrQ&6t6iHDfD9wS-@JRXCDpk5DHabXjF9tTHxH8b6^F|&htk&vqbcUe_I?*-{wN#
zwD@MH4Wof2)5P&mkw8a7&|ENUDRu>pmZkI-p3IgrcX&6z6`_D3#gAmMil74ATX>|3
z(fxL8cNIJl74xsw|D^X4D+~%%P_US?le@WJ$5hgoxm3m!l}hh$JNB$A&2k|L9=gwt
zW%R(>BDVrBCl)9U@gU(D9Ze3c$#4mUevMOvD18cIAk?VN7m2%|VgPif4|tIdb+3Pm
z?K?mFy^fNI3_XJf@8{i-H);^`izkF!%7V>aT<<##O7G8fk2@Fbw}r5UdR`v&Z8aQ!
z<UUu+T1vBmjsR?ZbI9bGF9xQNA(Egd^yh<c4KRffq<w3mQjrFY>S#R3z8?zX_q|sz
z1$BXhJ_lAWQ?YS{@~w%$8f1FBf&Z)e)3xB9irPmiMZ>&crtebqHjy~cuiIpYgXXv;
z!2E#0>(2!?^VKU?CO_5=wsR?u)=oPUfM)R1D<DPS0@pWM=ZzCju?QeFw2Fom;Mjy)
zF2ZMDx$B7smwTVrFSG-fvH>F6Sy*;a`AI<p!#%aRaTZAWMFuMdY@TU?17W|ohf$Wg
zAoo=QciK6t-4AHepS3z=vfaJyhM^OgZQ7o~rymsTT)9~~5U_FDl6%OS1{Pz6ArOnD
zHcn{3nMtJ4?G+CM3Qal)m^$L9lg2%=cQV<oEmvSPz1k@pa<WxDXIcZ+>j}(I>@S^*
zpy7n5TLwy>_lv96sk|<0g<SN^^l$tKxiK8;NIbQlA5hqicdBqH<YYpcXulyZ+GW4_
z;4}K%oTyiT`eG;!yarb*DVhi$t!hz31yMK);ONfBJL2a9rqh^9Iah|GKuTZiteRXt
z(NI2$>OdpHnHu?n8I1b%ldbo^(S6O)`TdkWUfUB%U$(bEg9L0tjem!92SxID+y23%
zY|&@>!D!xCU^t<m_JJHTX)p?RM`8#Uz9Pcej%{hA?QhKRS#x-9;w_HKzIV|Z(a)MZ
z$Ah?vfvk*sb@+OU5Qjc_0JSIbR#N%cnZD~tgYS5+Fo$fCW9WU-QfsILixA~f6YZB{
z!c+W69vQ$`Mpf|c2s`tG3?4(SOu-HFcU9Cv)gZF0c>03zqW8%)f$K??*zc_a8loWC
zWJ3m(?T`|fEipD!u7+WM%Fh?46UV&Hdi2l(1u4GMTRA}C({<R5Lk^dUs++HC<HJm1
z9v~s=6(#t2O%Sh-j?p^eGSSyH-e&1F;70aS);_UHfm1?YsE+3W2uUPvTPIh_P?(eu
znfb%swbD@l=H0yyQj&;cF)>U3T(&r^MXSf%=@0~`HAd66>MlbYx<_|I6j{538;f_Z
z*}aI;LCZ*0&=#t|ri!R-ef1Ijc&bv)_r{Wp0BrM6{rFm0x)r!qD}MVNY)5>qIX+&p
z9es8?+4d?m*Y%JGivsjH(;^r`j=Ki44ej)YAtY|h{c+Zpy@$NWerxnlbDr|Cc)x7m
z#C|&ttkM)`$jB6i_2}7zX*zMSr$Xu2$DIS?uX618Fofl?vzlY(j!p>7ctJj#q*?v_
zbgof{ASg!Bm4PwqI)VIgck)gtaVM$OdzCq6j(AU2$V=zuv9nCZ?Gr1*@O&kvTLVkR
zg$4Hy$o?>{p|;7E_MvJ}sQ*|P<Wf}c$Ce%Nq`l4J^%Xs-B@2*%Loa~^GBg6FY|$Y+
z$&d?*V3~C)^#%^+<|*~o>YL{xg2vh`)s#%}B?v%2xTF~`a|RXIUNG?I`s6d@7~=C?
z9@)QLA5!iUgp6%IUc^9m%Adw-``5|bk@YrK#-e~EjU1DzSH%4<M!-=<a&zh_g$3=f
zspe!Ge)4mR7?8}ro9Q>ez9`m4zDxsCCn#Z3ZX--z6Z*2`UfdB<oy-eS_|bgIrs7m@
z$rjhoim30^`vqQi1Ibzanqb~lgp1r7l7NGj;ojX}=DyLGLX)b-1J{RmZ%$ldf)U~k
zzbo~)BVr|9ceJnZM^;j%grSL4m&nLIW)Ofdr2Z?hzBKJ+%BOmx6psrR%d=j{YFj<Y
zcRH^x&((CoJr9h1U2WnZXawk2qa*JSGdsyoGUO9PYzt|v_;8>C=NeYED;t7U(>kjt
zHoG@BvO;Iu8g}<0(n03apAkpWbLPvlJ(pel<D`E(&b1Q;Z@Bss0Le7=Wza<v9x28i
z_F3#jRw&%*bI9d0Wof)}>i@J`9`$C3csjfyj~rL&g_w@qK*}0EdkON5&)f3A5_vPO
z<e(r-)_ZzU|8M6V8DroTToNXfMvUHV5*_S)Lm3HH2uuRWOryPFZ7*HP_^1@F!QE_d
z9iE~0vd16ye0aNtOiL1zRVhPjrkh?*R~2H%(GC@rkF>w@t<T3rRx8DCIlPO{64vw}
z%QzLF(dluLNFR~1kfJwKug)~p;vhe{G+YIWbiKhS{*?+_tkI~VApg-u&4Vff?1O!-
zTa%r1M~dYRj7c4dGr^3F&jzMUGqpN10gO8d+egex5euhG>JpXPx~pzTUZRDRe`kD9
z%Gjr$G-fxPGkG2|#9FE3FtDQRF~NN{A{)%ZTLKo@Fr9?gsIJ!+tYMJ6sLQ3}Got^T
zq&)UFPv>`1niKoH0!)h-GU>JmB0a<B;ejHP&&maAsp6^*6oi!qA4rOVz8#3uB8M);
zpihk3d&l`>|Cm$0LI^VG@R107faG!zBII`k>)d2tSHY@9?e5c0FAurcWf_Y5;c^FO
z2Bjub4oq@-9TIxNQMJcR<w>|A(Dd(=X6u~Py_u?akMrKY6?qOkh2%pFBh}Ao%ZZXK
z{pd)?WgZVRiE7g?!Zi7r=H^1~P1$!+8%Bk~yXRYHq!`rCK6S+sdQLr+q(`Tlfs}T!
z<ts}3^;0?o9op5sW&a(jD3AbuY<WALPtFe(e0(uVlT}8^soV^%zMn*wPQCk(07l;P
zMjh25abAc#acDz*|1gs*zpQig;--}TZp|jk(l_m}-mQ*oAoxKNBpr3eZ3l#rfA|uw
zz{gScOOm?Ix=afGUDJ~|;Lsk3xKmp7P4bR3?zLJFjX~vBtAQ(;>BR<v8q0_nB}#fX
z)%>h0qVAi4i1GS}+Pj7(HA>d8+3lH)o53&~$c*S;n+JGS?jnT5An(9I;SM2WzbI*d
zX*$uT*8;x~yPr8Cf1t%J%my`X%f!Ub&(4Jh|KJ1)Fem3<&M|3xFN??c76vMRX%XY`
zAd2OzuG_L5_Zf+V8bBYswygEqMgFe5;Ucow^H0l~Op;1@_!6(i8suRjgF!jC7;Y5G
zt~InU)oG$P**;9u%Wp*{$A4%#m_I2Jg7LP$w6%Xtc`y(;%GcOZT)gjAE;ILc=mI#%
z?4;}FwF(-9Zv)~N9pwE)#yf{T#;)ki&dTP+jUqOAT4=7A@9Q}IVto<K9qpfqZzz9d
zZqT3{%+goejnboQs^Pu54tI~hb^jw~<>|YoI0<^A!y5(df{0s9`MTXwpeu&yUo+yi
zf7tKv(Q6xtZ!-S31=|Fh9}%oAj+(lAI)UPZT*+8cL)IH4er<lWI&}%1Ni9jkP@_i-
zjM&=Cs@V-MuNEmYso%~Nx<`&;y`O4BT_(~nts#!Y0MVr7z04IUX&eXqd6qrr#N+S+
z)b(*GB#VSr`a4iUKS<a>j4)Z^@(aSqij&$2U~HWkaHVi6KXYgi3tMsYiMN}z&w}$v
z1bE&$Eu^JSMe_LcL>kNSuERg{)|-4{WRENd6AE?{J7~y`M)dZBe*TAb@sa4hCX-}h
zpRCqp&*dz<%8$O=qC6Nd#@I<O`{-C;6`8AqcRXn_*h?dMZzdq;bTFzQSpO|7WHLev
zt$LO<+k2fs%BPk=m4{+_=Ed^}hH~Be+&l0qZ2AFCayc>k6g6|b+{Lx*)^aj1c4TWC
z0?akX@;1xoI3-~}9b3$axi6M8rCT>IeNv=wzdFDkXFXe-<QF*KTlu~En6pjsSaMwU
zlxWpv<T<#_0bKPmyU}T_f@+p8d&JVMv^Z`%O6I=)Wo~z!?MBe!3QAB}9icb}WVeT;
zV`{H518PP{cFn(+^RuOIxE*4%Yp@uyp^jBaEl{bJumf1BW{?miZjXb89VZq`vDuQ+
zeSa3O0z1V@Z$d4yyVq{vjfp4*s2UXdp%IpRgIKu2d6p4K_iqb0(i<L#v$eGmgq+X-
z3yfKcZO(v^^L>OxS+m=`l{%^3l()1%A~O?I8Rt}hcbnd9)PHA990n+;J~@5jd}u<8
zl?>O_W3#5xQ=Q~R7GTGkJ$iM@n-PVAW~n0q#6b900z;Z8{2Z9d0WAeNBn43<cH=6y
z9VhwuFh~G+iZQTuyTF0Kr#Z%61CM?%K9L5;^$7SBm!`>S46;HuR64uLvFlNNO}r=x
zgOHsBnfGT-{nuOOVgU2TdKCPKt{7YWs)6aGC2*i&2Sf%k&x@TF0eB+Bb#Rc9({m5z
z+Lf1mbDc^^4o)zVP;QAJU6b{BXo7|XoR79*%q@x2m-@s1?5>7C52VHn*=as={yvWa
z3j!~Muf2%`r7X+8M_)DYbEO!81#gs|AvHhmpt(lwgAEO)Z6;&(ViS1U3`bG1D>Rsi
z$@+q*M02P=l+ttTP{Adt>R2cbPrO3h)wZ7cYm8SlyjcksA)U*QG~>s_n>Q4DbYKc6
zm_o@_hA?GDel){{?yfr(?X7X4OAn+*Fs)(AEgomC1tT5q6e3YDo$hr?-665tbKm@V
z`X!J_WdxFdEXTcVLoSW4#}Gm`2MeDg{aSb($n8;H+k?3gs*e(2YcWMd!l`n@f&0oe
zN~?1Ae>Aa6yED-qH8hWQ-M3pRK$TlNGCSu4N|rLSlXH;~ZbXlPlEUf!_Ulgxj}rs#
z+gVo;uh@Y8T|)SS0~#JkTnz^WvPyu3ij$7qo6!@LP%FTXAnXcwB8$JnUk0PnU3oO=
z_wOD>itZA_vIq`rh~g>tmyuwbNf~M82Ri^nzEBNWK(##|TTCJaJ$Ji1{`_~7>hDdS
zwz39)&*sxWy;$r7*rp|DsBkR^c+&iBTRGZgi`9k<o3Cd<Bx_P2Der0@EfRke?nr5U
zkPY{JMhNq)veQ>Vc99!}zcFq-uVaqTr5igf3RhPcW4qQG0bZaS5lgpEzmNo>BM1x7
zF>_Y5ZYB9ABW>@l7*h7297!-RLDL|8u(8>wv9rOZXhJPwO)k$XemZ<cHBztka@eRJ
zF2W@;6Bel#tN8a-{oCu+n1cZq4p1#()Sq{2u=gf<Co-TUmD)n)cERso>%^S<Y;5Ny
za51{yq{K^b(C%OvMn%=DNSA{%nc2F@-Mvndi|CBb4vu_$Et;A{rh-$DP1M)tw5gse
zyL0^1rjG`IuGK*A%r*K~KJO=CtdTkmwP*Hit=G3ysag@JN?5JE7rd~&fth?xR?0<?
zWO$;;Hg+?u+{Q<UJ%Jmr1LC2+WvUu(VoYD&98pS*eyfNXWMISg#C7qZ81c#Mu!827
ztNPqJ<7bdH_Ag~Uz3xZr;U~<+tR5wfs(vK)A?)pcs9y`}yztkLlU%tPXA-DZ=xh0c
zd~Wx*(HOUrqu#+L)&ZtkioQ_*ZvbrG_$v~U2kY0a=&i}+mkr`TGA9ODB0i_zBmZ>x
z%tfYW0D^5kPm?Lu&XElpFFN&JX+yg4BBHpzRJshPx#p0quPr&o)MZ;WH1~s^hz#Fw
z^yY2V!vnkoY>XnKO`%x2+;tu2>XY72-6_~6QPdYfT)I^%4Ad)?kqy&1uq)bS)Xn&M
z;m?1sLSa09ecsT&UeV16k^W(tehYW#DQsN|N<VMeZ=|y;zC2p)r6t1ujdp9Ay<>)R
zRpVc{dS4t)1l;_d?2H$!_Tp8TIP=;rJtk2pK6<_1k(NL*=wJq8M3Tr8@FJ{~0%M~@
z;oK<v91!LBNamR8n)yjkpgXm<`Pxnu<xuB|Q<)A|@vaS+%C;HX%Mt;7b_@;}umDA1
z;P1S9sggDLqiLH(q>U*KXk$F@!Vaec>PhRC=+j@p%1)`{#c%qVO-(S}xc?Swv~f8b
zQq%QC;pdD=3m*i58%4705jPsYb_~0*fy!P3If#`YL<cFHqv*}WF1Hz@F)}pRBPOSA
zAwZlM?X<*_+G8?s-@?7<4=7EnZY`s;nc8M<;m7q#TQJV*?}cwcY3E6Y9k#aWG7Wgj
z@A~Gw)mtZfn;X~Lv~5RQLt&H!EMiRk1}h=p>?QwkqWH31&er7K8SX)WP(cGn${AyM
zT2fbIgFqcKbY#0-W**s}zVz^u@>I@2=-w49gcX%egi=8_zPe_Lz70NoM)gVQtP0|h
zAJ2!e`wvd}JEd?tZ^)jfU450veTVKRmg<OUuKP6TI=frW3`K=p9Ujy%tErd&!dd(8
zve)aK`R1}AqFGS0`VnleUe@p!G9z`atx}5Thd&5(m<2B18D^~erqVTWVHSxL3PWVC
zwRmg`#&Ev>(IKhWAws0(2~zBiGTvr7VmkFf80<G%)K-HF65j&8f9$mhoUtUTAMN$&
z2qX;*zEr3Gc>>{1wTGVZ^&Z-!94->Wq*ie1rWk<V@@91npo%R!DSO2@H2>8RTjsCT
zM6>ksSwEjpLuZu{h2lRfs*PH{+17OB@z~!Dl+G8>SNm1s9N6N^+Dtdb2`QJo43aFu
z$zxC;+80Au{gX9z^B?VOx6TxMVrj(zp6LKJ<4YueLm*ViKhC<ne+mDTAul&l4nOfD
z!C2wparQ{LCP7!=g*+4Ea~)#<y7jaXs?%|4HFOsyS034ihl=FqEFyE!+5QNF>JV6^
z@K@foz&Llbl*!Q5m+A#OeY~gY8SbvV8GRj@E%*`)Mcpeko@oZxgei;jTeDVhoRu}5
z0}}5(a%TUY%L2tuh8nutgBz86f1h=0y{dW5`&Nu?eyK~dI#(qK{{Ye(s)bVpU}{58
zg}#b!&7%f<m+dz{(c_q11>@bDT}!%~L!EZw@w5Y%s1JTL(S+*WQW(nB3lT7{{`@ES
zwy?>%Km+lsp$Un<@BKCzUsKT$h(T`dIJ@-QH*XlBj-m>f2<Re_$YBAyW}S3Cy4`2K
z$6~Orqu)sx@u<pxT>%T7@EY=n&<Dajj3A7|o^gU}S>XhHxZz6sjqcjO5pB?<EBfX(
z7rYto_Cs#gm6z->ZFuUFF|ao>X)@zfha|H9VKSNH8VG?%36f*Tel6rU9Cnpnz%na5
zv&mU&aeKdbAWub#L}uSbRl<i|?z!GXjumO|A4S3Wg9aQMRNb^FpjVLqqHEBiRh|)p
z@P<P<-d!a2^Rq&6-7+bAtd#YPBD~XFKjm6R{-k%`hYqaiq{I4nO!|~p*6h6x0}BGT
z8YAjq5-GuZXU}ct%TG!9!R|b=LpZGC=6m|FIK9W*Skh2EaDXm2FMAHcideJFQZyi!
zt$V34@T3C;(GB2E2rdX<CtgjB<liXR{KE}q@?g8vy~A2=>y_-Rq>1z?K;VV50+Z5T
z@~9@G6#?L4K!Lo9kb+bK6@b3Ljj~*#gPhxuz`W;blU#z$>TA3G^)-zq8AD>)44ha=
z$RV{wCFTVAdYa$W-r)#;0HD|KjPT6k?ZV1bVp`PsH&$-*2}}<Qz%c*-d_HRa<dL8R
z*bW~teJ-=#*BC}Y@ZTh{?YguDa&}Ot%3AZ(moOr^Uj3k!X>M)bD7f|cRxTX8fOpyb
zQqZ=H6<u$OBJma+ZW?_Z*<P}-+8ePyx=Wc?iHU(5BGB@#s2>lCoWYX5mGP9D3|`(G
zEF)7&xHdQ=|GPc4v2ycx{FW(b_FijQ<1OT&y`xTj9z*zd((&*z<%-MNdDnltqSil!
z9&QEh;+l_ni3$Kz*zt!;bd>7|z<~)q?U>#j8A%XhRaEK>=lHbxs`xFf=7(kf17VmE
z02<6z&TTiId8@OYPglr>sAElwiFoW4U1BD~5j;1y=jc7vofxvcz4iN30X<m?0856-
zg?kpGF>#LB!Jn%tOi|f;x?igX*%bF1FYOAXP1xR;j@|L%n-qb&KRNTNm_dLzF`Sx|
zj@b*aB}$wFH=i~<8GoWgR##Ecjop?Ro-J<-EnIoCx4DrLPg(eL$+m=IrSZE(LE?{v
z--`96Tfei&6OHdK<s}xW?XSPa=Fe5VqybQ1_SCn5Q5_rXT)4%tMJ!Nc4>TK2Q#Y|*
zQXj0Qf9I9)yVAOGYk}A9*yQU(#?n`du<>!@oA+}Y^nw9TT5w!pdV~MU;JGL45~1*r
zXm{7j(r(Jt2|S2z<rBXxss~Q!{Oh;(>5NYB?W4S#MK7AtB&@DIG&lPuu=46sVAajR
z?!)7DyM2~XXNX)z<TPv4zqj3W_{6vVacn}7`u<;!#J-!raDi(|DIc804>;qHc#-@M
zPj6j}xk>l>5aO}6CAK_%{j@=1K77>j2an4n`+nowZ|gL@WGnXOqL?Q^X*_Y=>0UeC
zC;3+VaDST+i9`Cl3~DGhdNZ2=E9m9SRo63g*V)U@PKiYw?^df0wvz?+|IKJA5otcI
z@vhCfDbjMM{_zFYCqE@p1#eWZmU8}WMa2Wz|7e)AvZZ0KSH+c5b~Jtc_Oi^1aE#gR
z(MaIwDD&aH;Pr8y`6!sT+i3Ln(vNdu3C#bOlk#r)-FA%Y=FP#YIp-_vg5r71^q)1;
z4XgII>krH3M)kKt6AvQUpr3vU%;Rgx(kFdgdekf61p_m}1|VSfs7$Hbth$lAkC@Yl
z`uS`laDS~`<BKvi|Nd^c8`J1*B}#bkUYF~J!g_zX?vU2E%Q}kE_%L`FtMn`zE`=9;
zidBgRzQJ;_{P6qrTnN!`=BXzB)|OPb)mf$FXEwj_;HKS2iQT$hYPGT5=aear=V5ND
zX+3B1)S0#RQZO$1OaR2=AHMH#c?cA@nNNIIMsGxiY}YpYBL2B{{f0-jnMStV)Y6Z;
zS_wqiD<wt8E%jQ{O<&%qY&Y6{#2@+zK30B}RV?V&M$q!wIlT~p01q8KBsSW+T}|oW
z*@cqwU%%r~fN@&@7!&<}x!S-A1XLjKf3H{me_qJ~Q<YU*#pQ=PuxMa#&RDNZ*CF!%
E0G!A=ivR!s
diff --git a/public/07-basic_statistics_files/figure-html/MoransI-1.png b/public/07-basic_statistics_files/figure-html/MoransI-1.png
index 0478ef26de09ec4f3dd1cc5ffd02b139739a77ef..98094aa161f6e397c26a7ec8d8edf1c4d5869519 100644
GIT binary patch
literal 17179
zcmeHv2V9fM*7rOKC5qA%QIV$D6|jMVB%mnjs<7)?5y3^lf`AI5K#F2-VZ{{`At)}W
zRK=x3f(2F)0tP_{As`|pgisP7jeHZ7s`q~Py}y0$z3=zE7)dho%sFRH`JXfM%)=#z
z&35C*P8|yX7{7j<?N0zG!H;Mf1`Xd{)~?zB-x?h@{=5dh17HDw8?dkd7Vvj4a7%^X
z;TL&>{Kw704ZeacV0$pr4PI&iU;V9aK;9$&33dyHuT(d9K`MO7f-OL>8+=&=!#;T@
z{7DTCX3Br1rUs|N53*n;Gngq$bpxqx7OBDT<tFch-TnVlQ<?BzDii*erOIRs27?)F
z!3=g|rovaSya)C{0{w4HrVL&Me=%h;NKwWNmN8TNzrmsMw#}y}OoS61<GpU@aR78L
z$p0hchK~IJ7=ZP*Hb0-d%Vh<)ZYj7G(~)qtcFdT%#mDb{Hd-2+<-W=<>h|>|!5ydH
z0;|bEy?qpSpNd;Q|MXjYRY1<+q{bfmGe<tXdc0LomC60A0t_DHX97SPj{@M#bVz*8
z|9<$s5)8t~?wc4_37e$CE@_ed%$&Z%u?<^I2_0NMyMslPB};Gb=WY+7o3mR3MQbnL
z+19Z3jit;(#LHqGSvFY-We~<d)fNSP-cz6$d8k`$Lqt2L%1Vj0C}K8nxC}6#Z-R8f
zVj-#ngh^-IVNFPO%A$hhiCqd{g9gaEs|iwq)~p1Hw;E;J?s2Q6inOBx1FgZnQy5aA
zTL*877a=<iJUjzP8jzhj61=>649Wk!%W@3K1p`pEWrs|sDOj7nA|u(tLVo4VqKGW}
zM&cfJM$J;3N$zKENOMJCj^suIJ8*eMQIbABjNRR8ka<_%g(y4Gcj=P7N!#1Dcwt*<
zrvbrC)>dCRJ2xOR{n5cO<nD;~Og7cYRSc>h<EMZM`<Qcm?S%SCbT{@B>632Uk+``!
zo96c_KdV0|Ir;ugQL$IrtWx2=+bKMOz+V3+Bw2W`yNBs?vE03<EGy|OtJ``SqP}r2
zh>zU3;^^V-do0(c`XE7Qyq`pJH;nb}1X$@T<5H8nh|f+E#1e@lfV1;%h1xdr-z2fE
zfwE{+t;~u&ueLChQxIn&Hq@}l+O%GQmPfQ+4_cqO#df`3yq(P{kFy1DH^^GZCYJk+
zCfzpzKh1nlg+2=Pvmfz(UsZU8%$>G6lxwn+g?mDn>b69rAC7pt_tiBox+%&^>FO#L
zMYAPrUyZovxS2<F>=bD@PicUeeez2u+e<O6O0+tnwGC+POG&k)EJzXLm8LOeeF=;#
z!G*F_6BVo<pWPQ=a2;S`=73$Xy@#%N>95`%?)-H5%6xJfwt6f{pzV2AzmU;U+0Cxb
z5u}#&;AVkT8QxOX!nG{jvZ-<m=`GGcA6zQ;*h*P&+@4)g#XcqFSRXU&M1toTvh*&_
z0B0(zI*&6EQ_EwyqO{jCynpUWzg!RO#1(8_bhB<j61_Za5iZ_S$`l!2;({;&tM$BR
z&Mrb}zEJo=Y*J5j4&)|;7CN$5Z0-(}bt<23Ov~LuYl>BK&gT;O8#3o+A>K{;!D^&^
zhs_?_-&*0-&W}uPh*;u?BzOIg&&^>k)CZ3=yWfs`2K{%UB5l7oTPP}Uo}|X->a9-5
zvT<vCDG3gf8D#X{d!`GnWL@zi)H+e-C1eGesTM_uN$=RQFc3y8%_Q+PGH!Xk*$k#h
zl=q<xSa(hcUN2_iodbDXXP0vGMdFWW_Cg)-dVtqWW!izpN7I-EB`w!)$2DAgrk3zZ
ze;1N$5n4d(;}&zvx$)>IytDA*iA3mmjbi-?pv#e>e>hG|_Du66Z~|h&pX!1OGDOG*
zHxdqRhx&D9JC@V&5qQEL+s>^0XoH>4BX6HJgE4j=>>!j@;QDH?8`8-4-jB(!SYwV|
zDLXJ9X!?!yP^NuMJ}4`r1pfX!l1H=!3p|fXw=<oe^ckK?J08BNQkC>VM!Fw+x-B)v
z$?@r1Jl<<3F{_*2@`!h9JZayU05_#77`d1A6g+VcmS>6&3I9mAM)fT=rkqR{)(IFI
z+r3JX_e#1cxlXfJi(g;iq8Cm90l6{_BzdKADCGlwvhV!lcVF3j1Rp$#x~1lp``b9;
z&4r#Oo_o8}!i#vfR7gGpoZdt#iG(%*0qk8Kja;yUvZxT}sb|YEsmjrpiC(=B@TNC|
z1334YQ$QA5rj(?BRR@l^nX|)>%>gH5$QmS>dFKV<?L}lWZ_%Y0Rg%^=zbqS2&8+Bm
z$GL%qA9~k_6YsMc?^hdvT?L(-BFp=M3f52OzDFCpzcUXprT$6@l~q#J&Bu}WZ>@D8
z1_+rpME?%%A#=KY$OIm07g6|eS-KxVBE_ZYp_k7Cn=@7B=z@$MX63;*MQ8(jQoz$?
zmPoSG=g(O>+*2k|LULaU?+?klPkzh^AkJUS=a8RU)HMjV=^P|mOi^<W&k+2SAXP)j
z?w(RV>1$o2e-@u9iZsWNtk|-%U=H!cAJ<}jRwely?zY0*^|TY&)HX~wL9k>VdRgpO
zsAwItC433`h#WN3P*i+JJ5`d|r6`O&ovM})5qsLR?`&0WL_NBe4~?uq%cW-A^n7y^
zDZxH;v|sDQUYEH{nb0G8+Vw|3q*A6N&TkiMBQdSp@r)5?)2(FpenDf5z~>8j+;Z(!
ziBj-M!}4yG8z=T)Qdcgn@-uuEsqg<YXchLwD$pd=yCr9qi26zki*za(H+5hOCF=nF
z^RHR4%eXBea;wL13up3#o=hZpi`V0`_%Cv=p&|?R6j<P=7lbQwCe&AcjP_!isGUZ8
zDR!J_OfWD*yYLw;o6w$`a?h#*JIW$eNw27)3lIi~_Bm49%((@MwEHcwobCrGm)K=G
z?`Ie8=1ZH)9lamiNzN?AvyU_i@+<{08$K*qQnD5(9FH~+a=be^&X1o_(f1-hbejK?
z^dk31&l2ct=%QWH9wqCnZYv~NIyEDqBH{P&W4l3Xsyk=xyM)Sz*qv_OMYZKyk5Cu#
zi~SB$jaN9qiC7I9z>C`+kdWjgT_HYE;w(*jZ}aTbf;9SN%eb_w*u?;%7#=A}#M=Xp
zoO>O`(RW|ROw$HjzwT+${k|JxqWxHRii&3!df-%KVu5q@vvdK|kys=0<jzJvfc6NE
zoN@qy>fFFdC4!LhV%b6AtHK{1zO@fFPf&Rp?`3*w?~Mf4Q@(RUOYJ#+tQBV99h=Bo
zosm%0qe#o_?#B5qe1CHW+C}<O>`2{{s9JV{AG0gvJxqf2TaWf&+f+yq+xN|;GV@dN
zZU|z2SVtfCK#rTZ@q7`*t-?$w%8E^3_z>Rb@j|_XzS1<|%qh;EfmbTEH<?^YmsJYu
zD;PQyC*5OR2g3>!tUJX#qA@+QI|oV5{`1p;dVN;kdCN^usN6vRKJG^yBeX%~9TR4R
z{Vm~%?wRBoVx>Mv=s7KZ+LLvp*yeE!ex{MT(i;r$iRry902|f8!vm7uVxdV~qrD~|
znW2Ez!pI#T{Qa>e$|xTV@bKW#gU_2&@*3&W8XK%h#wf6iyW8u000}rLfX7w-M>I^7
z70<%!4%h2`Ce})n<)67l&Te!ieSA+-j_+KcYWSaAd_F8jyGYvTSFT)Pv++$L9Ryr|
zcLZeP-^H`=mCZdUFzxq3SihBcWC{*nV2=mhH&xNKEgt?&>=hL83DJd8Ity<JXg_AE
zkmx<LmHQaw$~7BNb#XWgF#(XGeY8QSWr1|5W}9!f6ac&C1t6as?j}~H#Kj2DyQ2}(
z`C^nyXMJC>)anr#0UqiAsQ(=5hg?gg2wpo`gQ(~%<<k`I-EPJOMNhvkG>ic@a+7B5
zRt~x%q>I=XiUOoxRh=;>Rs=Lx2u-xNP>Y<$<fm98)@wpxu!}r62?lF%zP&6te|}MI
zzDbpassBqf4HD<11?f?9P97x?`kFq@jKzU<b!SY0`a}c(o1<$?0p{}jGl;drZjEu^
z%*V?vuxGmhniQ2jeKJsZrIiN@>U%2Bmu6+oQw0Wkzz6`JwW7-|3h>>o|DB{$+cd`r
zzs7W%25r2z&%_(K(<jGaYL%8-j9u@nadoSLH+q`xxd%y@{CTK!<ofkh@3t$rY9ZCY
z&d#tI`{Xk4Bt=ID`%reQ0p_&QAJ=8t$4~F4S=JFmQ{x57OgNS@HLBK2<82xslhL3d
z?ny~-mq9JUxoMv%TENyk16NzRtX!>^39-ByD@vaqp>=}1n=$`P5wVl9M~4szpukN{
z^_N{3vWWc%Vv2dBV*c<+n?~&_6YaA*bJdn2rl8y|U<$_=G3Fm%ll-cob_@wQa7VU~
zoOkK^m^o#PnTEK?O(u%gU>raIexvn0tR6Zn^U$57JsJRQ4XpJiI6P#yBdi)p{dU<E
z&`t&<?5rq<v?O%8m>_L*Pf>2f03HT3xuVAUN;cGXpOW1LlTj!j3L~x3b=EvqpH0~_
z{RU{i{&gTvN%Xnk8i#a^LeT&<8la>=Vd9Op32}2S_FvGiG8+Y8I{BUDIsAf)aMiuq
zKQ@`Hr~zm$>v$8ppBSLP<Z;ar&#{wi0SGe8+47;_3<kKEKJXhW-l2|wap(D)_v))m
z2T|lPbBtKCxBUnk;mrEY0<V-yy1wVq)`_<Lvy)rqKBOs^_Z|KhEy(C^h{RunoO>XC
zIdAMp(u4d+dBHVvTV4MN;s0upzCYW)tE_)e_<veU-xo>lUf(gmf7R085nk@41HSY(
z4EJ9W>2LVN|GMeliyVhW{8XyA>*L3dJ%0M0?S4Dgz~GQuBa_Qu&MvBAg%<Sr4#ej@
zW3i7ks?vv3QSV6_h|Y&Euuc)1)TEY;$Jv`@rXt}(N0)&RZArAJ@a$D3u?cF~w-ugm
zCr&#)p+A%-Uu`?_rlI&K?%LUaf@*~?sIb=Ea=#?~U@EUY<Io+i>!-}rhuR0ynC@3l
zu>rNq<q+glqqww+P(Ira84uBM+*&`&hRWiDIQ)*<?nUN#UjV3-wOM%5Y&~gvg4%BT
zVp)XqSk+$!(5GxK#n|0MY9VX*r6o-`KkvH#q&aa9zW|*>DBd5RD%hqTO}U<h3@Tx>
zcqyUuI;k|;m924ePzxOFHTItD<v1MCr=wGer(84|ghu(YfDzk4(WX*yeMwI)f5klC
zidcKzExW#O;kmtQaqR}}K)oO7TKaNG`Sc1p+M><hH2(f{2(MS$(6yEPPqIFVq;4rH
zeR^1cTpJO}wD+GrP}n_7@bfW=n9q80l{6yl9#SQ5hItUoLJ-brE<U<IM_Z|$8>LKw
z;2q5YAJUcH*1=>u#%b#Xof&|XX8^pX$+_t1p?5f=YwM?kp7r^fS7H%UD`C<uHA&}W
z+JJnE!K~cA3!$=fk(P_dFjDc8?w3q;9qr<If=ch@xo4}ofUha&Lu?0ATa8|hm~J{-
zZ#?Ghym?>Hx=gCLch=nGaU{p2r_R*VgPNscugU8Ftfy?f`H!T7e>fTWpPGNsjpJl^
z`HHJP$8gx3p=S!vD3^<0#TB}F7wkb3ln2ru^opu<1Iec3L9128zNi4ju7ggWYQH^}
zHD)jil^vnvlkG)XLlIMt#jnK4D#B$)2At~ulKK9zZ2BFH9n!|%K*zrrc!&7?^9kZF
z7U^%KnZK*7e^B^QA^lgDEW=2Dr*0zUePGS4XODlg&Q%U%{a-0Ob9T<sheoHrlw>oe
zfC+wDi%DO<J=s#TGHjOhl1%Yq*)g*xUy3y&zc;<F(z?c-<mdAI&H5`ixtml~#O_xL
zls2tS5_k+kxkX8=y-Bg#6mQO>txAKwuiM6$j$XT#I;^FY5k9-<c~eF1*h7OMQN@lm
zSJU<bIrv|G126&TBekam8&s#T7Cwu$ze15}_eihmn-_7hal85%{;?zJQ*bG3)gx?<
zQ*~Dg!H`yv@;MIYAAbnK!lxM^e*T}X=~=dZD%^mX-p4u3p9?VHZSV5k2?OoFqg})Y
zaUo>9YrCz%wjYDZFWzUKS$SRu^%D|&QthH2zU*m`)$~6L>JB;C=)D+^yxa1pp2nwo
z?>`a^$aUvI^W1%8Oy|+`UE6~TyjRmA=T4JRnw|P6G7fce?gVwj;Pv3h*K@N8%Zcyk
zjpCxFBrEN*{9$xRWfS*AEQ<pN?gZdNpN;5wIgxPpt}I&Ltw$Q@?<p{|Uec;zgH_$m
z8QVFz%@|Jo64vVQE_)Htt!tM0ak<Ja#Q7?o8s`_<<av*Uy{4Z=Y@$dkTskz9R}9TB
z>j$4ShtA(<32As!{|OgI^{6AH`r%5N$wM6??2$G<t}`}xCLE@{nIfM`|Ic*(6q^%t
z^nNYHk$p=8x@9c5-pLUk_umV$oWYJYYlchy2%_6zr_?{&_d`=pA1*iF(I(zliCz6i
z;F1wW>CTx_O(9z1aI%g^%>j8D;Bw%!#B!}qi>lQPtj-N7#uF19xvKl(fG*4x*4Y~d
z*bW)@-InD63NFoddobshedTMeu#cit)xJ&rK-Z8tIfy#=@ZzfpSu-;o=Sa7y7x_`M
z9Z#`|TUADBn;)K6>4bJe$ITh=m;NEb6D7C2WF`6Y#tt}&-=(%mZ=BR<6GvTnN*iiE
zXJATB_p{EugIkB$;?nTJ(#!nRB4pGkycKB|6$N(-{4JWlR$&7(m7BRFQv1v`y&Owv
zYLdQ3Zd6o;@28-`QIdZOqWSK@oLClMQyK9}XG5T6R_5EIJquyIF(8b3i4)l9<<5U5
zIBo7;P%~+`HZ_s<_Tm_x=cKRO4A(QCuN>ZQ5&pbc<#HOV)+{<TyM|k-$z$vm`b>*%
z;hN#C@|t4MDy`wq?X|V3#NNfZLd(<F^?A9!tHT<OG#IGww)Bda!W1HwO%=4nq)9v)
zpW#IKwUsjlWtS`R2E0KLC~BO`8)uP|_|}};n;v;rR=}D%N|*0ro3-|OO1mnJKnyNL
z-#50XyJ%^2m$PvUA)Kn&`q2IK)60WCC#T!JTeCCvwVI4kaCnRT=LOyVoT?i|O|dhs
zxM~STgpi2ual&4@62y?1HIh!3dTlOdvXw=*-<Z)s=?@qIE!v2w(6=_f2PyL8a$jBP
z>gux7Hu3VFKgw=7+Z7xYNX>%09cxBlf&#c+{}rR!G+7JF1WwkwH9QUs81t)Vu^km@
z4Rh5{a5DiJaLv`$zl=?ql!SyU(LTw%`j$E*V$5v62CXM%-Nrh8hAcXk0Vc}=jz3q)
zOP~J1U?AuX4VInLsZhx3aJ2DWle~9`;<2%@RP+Mg9~m9tc}Iu$K)lQ*EY2x(^O4l2
z&W9344M?bN;A0au>t0-ox9cGDVQ$e6ZpJ2K=~{W`N5opkhFWTbm#D*yj&8W@V*aaW
z*}7|j(%X&EYdJf07Q^@z?y(N{?A-&^(Ry-Lqp&odT)a|$*)DsgJd3at!FC19NODji
z%mIU~m#}#MG(I!LjnByHG0!=Yh&i!9UpW+lEcVc|$W+7VtaFR;qLby*P8~>t)0-h&
zo(|Ja*N@SHXX9bwy2)WQ6tPu)IY0l5?u&xF{Z2NK<f#d<NB)HPyqhwMin`l=qGa~i
zw98mkV+iVjWe2Q|tX}J<(ja=Nl_&aCU;8xCfNpoKoS}46qGS#D`9n0u&pA1+_T>+&
zBBxjDbsY8Hxjk4u(SvAJWm+$bf7x`UQi;xxq-IgI=Uif~RGN(Hx-SmRQ3u{+b9K(%
zx+UG};~=xKyTw=Gj%oi{0EW^7RBc_vA3Qx4-<M{|n{za%=Qm86UEs9c5PF3VOZ}@z
zo0F8S!L-65(fX&?Ci0Pz!17x|%=*==+kH^fEi1?oH>P^WH4XA)nC*i}DHOlKNxN@O
z-L}$E#Gp3%veyZvN+!yd0=&`lg!`k&Dr%oyQTNnTUQ$o=)WQ!*cm8VIq!u%{=Lu_T
zgX(#rQTEAJIpD7w$|Gi^_r|^^@*=&pOF~Wb>2#Uk?8p1xaCrn5vCD7^u8Rv}g!d}^
z&CWWm8B%e-GibuHU+Hbi1j?VsZ;Y6qT#q}&QueHaG^S0@a67KUVXFOWZ_Pg=cs(@h
z@dn^Q?~ts>BX{ITHlYV@h6?^1cGWs7CGSfAcQS!=3!C0JaindN8+Te4H8t~P`APHz
zM8p70{Lxjn?!3<B8%gLeYIjeuM2nW>pLB5M2nXtql*(9h_c%XNZ+^Rk{Ec&Rn;GHM
zjZ11dS+@#^w5|Lh=aY|x+d$vg4=!BJeWR*wK{KOOiYwp+EOc{BA5CTsE4G4NoCMm1
zeGByz+I}5n@7Gu>=RK&;UD9ry7XssN?b^a<_{66Q=<XpPEO()Ti2{c_ibBAiF%rh7
z3$kXhjYsYx2lfb`(h1Jhqw&v}cEQo}db`^~`9>p@gnq|UvdCc*HNbB582e$tOY7qx
z3s58u!v8zQtX4F7HOz<~x(wQLwu0TA2Hxc1arHCUy>JiOY&@y?cjV;M175@W<X*jj
ze^68{D`gx6S7kYM=UnieBMmX<eJs5vd|A!d`*y<wl%vZ`@lvU-%W3l<PRMAbz@XhH
zBEUU=6LEsu58qhjd&a$IONnIrR}ppBe`EK1IVK8Q)W3<xD)Bb;u_N@|4-K!`aPdE5
zn5@<<ivYuq_(9#1JUkX&yCXT+!=BR4#Gao{oMVn0VH`z`ko|rTZd(M@521_F1APTg
z4A2=)d>+uNspRV-CE7zVY)0CS`e8VlV!+&CW8}(P-!u0ccQazejtKUCFw3%E<%L?L
z{q5{007^}c`CRuc->4VfZ=Oz7`4&|$VCE<(G{A;Y?l2wP9Hu0B^05VT{`OP=VldnX
zN5PE(Y2t9DfZ(C*z)*sR51K-+JYpB$l9_jil~X?6=V}bQ+Qkz5ly0<dw7Y&QUs)TY
zmwshp8>;2nC^vkE|28H5qk4y%#oxNtKTA+a9sD#*&j4k8c}P?pYq0JwQE-3ecp&~Z
zaouS9)<?b<g5Sm0|8|1^P1-Ocjc_-4Ed8Z6{g)8@%Y4HuN(?3s-+O;CBG{tp!AbFh
zomt|}4^+JoFeyiXvi+1q{iWfaQvd4l-=c~|E8~47zl3@m+r#CnMN`O`=e|WTKfEZA
zc&rw81YcWZq@F9P4-3b9QxU)|>B5M5!qhQ6*E24COT!&M73X<}YZ;h$=X1Dg<oItL
zy(Qj0M8C(cjkg}(8vG3bbtLNLP`>Q1E{%DpsYh^}kSx;TVe#2t>?PXMPiz)9zd)st
zM+u|kGa2a9XN_rpEI7@1Eu?n+kY_WpWGZP;$@^xfABnm+m4h*_b|`C@n2Tll&%an|
zU%;{+UNSS3e8g_v1M50nn^8vU8h(?zVSJ66#mH*nrZI+Lw4<VI$pDP<Y5sOmuB+z1
zm1uz9dLNdeIl4!;5a#oC;_y>tr#i&qdfBdl>|u8e-dQKfJE5)ko~J%hZ#z$R<D=D3
z?!C(=!qrH0zJ<ion)+K$ytoH773VC)p86zk`3S4q)p>BOb141=Pl@k%ik_)Pa%Y6d
z#9dt%7?|42F3Q4D!@EHGooV7OF(JlFF;6Q`we#ql9ovJ4_>Z`UaA7oa`3(fq$zIA4
zb@dL(a0hKFr#%aiZmUU2M7z{aHQlW~>qWsm7r4{5th~+-ElS9CS0HKXUpNETT4g)z
z(#KD>S0f|wNl1IgRj~ZeflD<!(fP0h+GyVwSB|ExR0<xXj!8r6n@8Vs@VPiJ=^52Z
zS7YlzSU8Kfq)$903H@jLz;w<sNgY1v&+F4n^db|`E_W~mPMTrB!4@hSE_k3}SkCHh
zH&F0chG3ppp!2+lGJ+^oOHWqtYXJ^1xCG}2mx9;R=R)mo{8AW?oZ{ESqzD&(51*(~
zbxOP%tU|t^{s`UP{*u*38tf~=kA*8SSlJWIqu6f(W_>9|Mre4+m-73oD&ZlLrnJt;
zulaO@gNzhWuG$$n&+9(Zhb#ME)$-K`{*x8-JrS>a>zL{_YpI$Ov8rFJ`mb#H5A&e!
zDd@W*$|G)Fl6ShWYj_O)t6ILm=f5Mw{$T}uPeeI_+4-M)F%o|Mik9f3dHxldvsgLa
zhdBdaos6w2+`-#b@gPgv^9X+0SJ1&8+Q@s5+mpEEOPreB?MLei<f#nHN4y-)%`dPu
z-u(-#N9Xf5w*>GkX7+=W>kGJPCC?rY7v+SAYO*$efus-KU-0bTK{~-N;qW__N?Iy*
zXeR%zw*Q$L{Jzv{IZm8AK0VJ963BzT@b7B-Cw=g7_T_8na^_rEw?ySzU`QeBdLFgR
z+ojLlAD^}b)+{#HeAU71U)#1cfMmV*u&N4@Cx6#QyMkbN%NMA_>cPQPSAn+vf!G#c
z?&n*;e2=O%dWWA56kzr)+o6njYc^vwz!}&9M@RP=y<^Q7-q$wR2bN#*>A?USI0!NZ
zcWpBR6i5dBEDgZs=`1Uhwfc}mdWZomV806OM;;I*TlMd7mvf+u;9x(3!|V|pCJg8B
zcP1Orb8zseYkD4g=D_Uir0X-eHG?OKhS6?*8c?BjXHy!%s!eH_I1gU5jXq9fFhC6P
zzR{N1BkcP`BUXuM;p+_o1qF-DOUw3KJ%)uOR9IbfzQa7qJ6$E(;MpSEhMJw^Ltm^2
z;ppaLcYdfUJeNECoRP!(j;=*-zhDzANRy`?jx0@ClG;7qcoU(Tok5)~c(QFSAfXRY
z81OXb@*l-_+d7S-O1o3A<Qx?YJV)B7qy>*U4J=M9;qhEkJ1`M8ja-u;plmH{PPPwa
zWW}#-r0(7*H6zaa@FN|iND4OqV|^=QE8HE`T&@yYU;#~=hQNcJ*lW(uX1MS#Dw7aC
z3Ct<;rQ~~=?72&!;4)9XZdQxZSFkn|DF7P{@bzfzcR!pzUx7@#Zx7C&2XkyGVBC1b
z;UX59JQWqCjz^g;?Wf^#07F{EA44lq2j`kXZYj}fcTnaBG;f>qs~`;31oyC?hI;PT
z7^8N1KL3fTXvYO_ec$<4)}3_NeUI#0Qebgb{Lpcy?en0IWAX7p*mA>aJJy@&ntBtr
zH@WJ<0d?3GNU1$4eU&~ZitLN&`7!P3#k0z<v_w0U@$swE$(g^cF<Ln%5mJH!p5x0B
z7EG_RIeHFTZlljpZ;SpP#2SEzf73&eZ=G-}4&NzdZ4baog?-zJ{9R<6vPIZI<EpTi
z7TrBZB_B64mO85x%|KkZf_*z;))F@n{3YponYt&Uf^L7le{FrdD^Wj`a`2A+g0Vjs
zf~!u;=Hq5#tqA4GTvf}Gyp6|8^Nq@%P{|4OrD;blGi|^JQ6Tl8=O%(-px7WIXBN))
z$;b;+=-HCRva+V_(V|p!kZK(MIb4k)yX~1Az@*@ph=2R_h~J;5RrNfL%}g)(w({!V
zw>0)O$J!DU4Zy}tv-S$3;mMCzweh>{2@VI^ur5s9V^KlM;a4_o{6$w;)a!w#1Q)N=
z1TnLyTE@!vmaR|;q0C&1>nLIFRkk>poblnMQTdN%J_$*S*8+HCS~{=SLu?aWSgNLf
zvTaR1<m+K<w&;@Y&GEVj>2_Q>>ue~qzVo2PbdRhTsy^*5$DdqUA0O?}lz4I+*uvGw
z*no9-ood-?t=v`gYHY|3yV8<P1jHf3?glV@m1?PlI4Hx$*Cm^re=_V;0f@_$BYyKx
zQL3|^Tt9O!#DBdm;&OSg<v#XJHDU`Uhvgc0_w6yHKILv+3(E40%75k7|4~v%qN)R>
zDkPX#447@Ek%~XdNhgvSJwaJB%hsZz{2Y<sQ{|?xZ;x_6+Zb{v!w>cTq#}e3mwB>G
zn^e}`Y|V5z^B4HQnujc{^&spG)oDB&Qls)v-X4U{zL_Z|o(IXl;a_Y>byDIf?SgCy
zPGk2hE81>RfeN1iJQlKN1o9lqQ@D#&eN36V<Dt4*dC?^tVg&}cT2`o4O`VYHRD4?X
z7`#O)HzBuvKV#MnMFr9yR4*r+n@9ZO(Yn=r6IER_IUg7WmCN2^fJYW#@szMqRzpOP
zM^?0MQ*C*yHwI2GlN=XIgy-i0Jj)0a)&OAb@c+pNgF7AJ7vO`!fztXoK|vy=P23`M
zhYxck^`)0KB6}6UnNwC)(#G7KwzS?;$4#WK3hAwuwZ|#S@Nu7u4UZ4*oK_V==8hpX
zxOeNeXVB5_FyL&bkie++7wzpN^7d>bX!W{@h>A$EeOni4DGJ=%ZLB7}L=I8tJte|H
z^3#F(n-n)br$sGfX}Xov1R+I15>GWih%@4uq^}hwUEJRMD&n>5dTzK?n!EJ&d%Ofb
zJVYl-o1~F+``lXQYc^GUNUVc~M_JDv%Mi~9umr{xbahd%MJ+Bda+MG7hs6Mk4I>`l
zA7{%J*Pc`Wt8Pcu;<DMj4)Z~IqpbBTdqr)mnxQ$zggqWU$@+{?3Vw#O+kYaToGbfX
z7gZS08C%e^K(_|FW97DN!BYBb=Ul<D&H_$BGo5(KEQ3p#MIk1i^g)8x0)w#kDtYiZ
z<3Nj&&dJnWy37#giEhfGazy6Qu`aKL#uiD8Y(C?JNqx!=@M@@i<-)9kdPOr_dNNjq
zpjZ0RoD-d`B>U^VjIq?s!G-&O2G23Tmf!vA#rxGcmPmUuof@(1HQY2~6Zs~E&bpdN
z-V-%Dc!{s{!A`ay1w(qJ^D3cc*7T$LvX6cjgsvD%KaHaWYAX$adPTRDG{OB;+Za;E
zm1~WsH9`9|U~NP<<3;b3JdrMlih+-9=@W%?zAM<`73q<yNdhEi1u#9MI?(@fgB#dL
zX;?wL>PHWvsZa<3PYI7ElM$K;3jDf&$G;sujhRCEpk2`0N$w&Wp`x_VSI&MAFNhLm
zZ3I<NzQrpZhT=XEZ%b(fUb?LSAkXE07oZ0FxdQRV<D`>mDet3SHG{Be;wz3PQ@h^&
zWUYpf9Ng5pYVg9n!egX{)fp*`LD=xv7m{CV8hA=6^k?uXME^(aTo&ELdCW>e%`+kc
z*vj3~mtjT?ckBB^p_nI4GE;%hnMzU047^p+-RS5w>7@xMv4e(c5c_VX_fm^-OLJTg
zocIOjY*i%dkknN-xNoyZ<Fh4MX$0wwUP-GHX}PRU5g~ckU~f|!Wg^9#`sNgWLYRae
z-mG$#O5pDmc(;9A!nr_XV^<uel1qvk-7C-sa_jv;I|=@+0_e~1iKG7qKlI^fhga>h
US==W7+ZSN{n$5O}t6a|fADeOn2><{9
literal 18621
zcmeHv2Ut_fw*SN^0Ts}LibqjUQ52Eb=>$DCP(e|o6I6<#(xkV<UJyYML8&SVN(n`Z
zlq9Htfb=HPO9(wc2qA<d{~bgm=sWM8_wIT3z3+eXZAxbLtXb=~>dc<x&N0n{g7a6*
z2LK4FAKIr403Y-(oX8J{{(NlNs{#G#ICkXZe&{a%iU3#uMMa<p{q_SEsnC1q4Yz^&
zvQV^uE<Z)6-LKvPx>XUnCR;54w}<=kv+#qiR14^aROsUPDFQzW=u-59`na9YE7i}h
zp8G2`)h`wLhvQdY?^n-BwE(FWim86kWx?%)x+i~9Q|nXfp^KBs;Z#;u*83^e`&rbd
zLYH6tw?1ez_ZH~If$oBS)pIxyIZnMFr#^M^9W<2NCcxfM2T3Vldr1E>0IP0se_+0(
zA#(sEfcm~YCtX7N8!=}^@*hXpDXek%Lw1cBU9m`Vp|ge4ha;a7E(^RX60E!N`OKlu
zOblwX{=@3HfyalBRXeV(r81;)mer(b>4sjTy-0CEs#{e&cLM6#tAv2M)g!pt!xbdp
z7kNMdNWMP)@1{RP0-KkmVl1;v3U!ag@WqWcub>s7miPqb<W`pI<`3m^T#`AVmqw{1
zx@fo{p0(%U-N&R`k-F@Ho-ymdqc4JUU}ZtRD*=*%99SwemMANHF7^W@Nd!UM7T^pv
z2EZe>iSGbSDh5pwV<27mc5VXPDVfSgw42c@yYlcL%og9zao>|!=L&C0FH{1L3L(01
zc#FYx*x;E&g)nb+?O{Qzj2L+H5$f2$M?7@d8FU<e5&QvGwj6<lx16o)>a+zrH!u{i
zff$qQr}lQ_fp%KBvv53eS@R`pYEOC3?r>|HBvvpQiRp|IZi>Z>ny+(9v^K?XJXk(2
zo5P#lc_egtBkB)Kn0Zn}1DnU%hB^<%tyK={sb<ofi@#jLy4R(_TN+>Jlp!&_tdEsN
z?tNZy?&sY1cQ4)23NqTe+gf!tF$0>B#fL}-&zdyVMm6JqUkO-9M~aQhTE*tjPfANq
z>#d$g2Ir2nfpoWRq>8vAq+oqnJu@@7&uJn<%ZMGxf(^D0*l;}QRIS}O8#KL?;B1o1
z7+_cXu26ZD!xG;G*v-D~uqFbAKG<V{zP~W^^zj3H#2omc-@&zth0>@M)E>MwOL;qx
zeSsNHqhDLTPHL?=xVL}#X5XuqA%HG{5a-e1&I{Lek34txkI9#ELVhp`nJ8t0^knw%
z8$lmdV-efcl3rcPrpSKO>Frt0`2C<D7So^<=7m`4diz}D#t$&tG4LB7aWG+YGipUL
zHP^qC?u)^>JF~Yst%ch4u9pvQlt-wYeaNR4<&C~H#M<r9L@0RWYNXu2w6_F()?a$X
z>j%cnI5t8Ux7sf($V5hcZEUNU!q0t|nr{X13fNu*@zD9v3g5htXr?AT%$Xo`FYGqd
zsCRwn8|~55iLVgP7Zt)M>W4XA9J_kwCVKc?BMRNW8lF!G8Su)>&~F@1Yy9IkCfw99
zvq;>bm)!5;#-bKAH=!q(ovCSIHkk2<&?60)aercOxGKNxaDOmewDB5#yUC+gAnyQb
zg|X!oBM=itqAs*UUq*ADWW%<Ot#2Rg$TmiSytPMSf6wiNv{?aM%KPQQy{N3tJNVNp
zdz2U2*GbhJJ;M?%C`M^y!cD2RLoMQ2nei2_^3k<B5xy{=X3jRaspku0?9j4zJ4_zs
z0C^WsD})`YaH#an>#Om++{`2p`@BAqe1se7Q{bjM-+z31{Gt#xFH#umpL1AYw7#qw
zzJpvZUUA7F80El6)IsCNXh>&kXRi`#;2^%ac_M_G2-|AM$zO=2X`$0nV)A{V&WR?^
z`=aI;Af}4##lV+uIV#6G_xW{(bDs&*jlpufUGARg1nwOO(%W&j81l48SVDGrRP#jD
zrI*Z0U2py{aV&2NtVQ=P#6CdG8$}Rb)j4pgQRA97?l4hjz(udN0i2UfBJ<#If<5bb
zpD^|V!f#}I+3E8cbqCIBR%f4ec5cMP_%`xLB&j0M;HfdxF;H4x@3fn365fa(OyH0j
zix%T#%gQbf^@OW7AH6x?Et)BK$pIW`;4Frl*2|_fFIV-+kW0w(PC@}8akXL46==a3
z3f==rBdp=%P8As^G>%aEGhka+pFUH(aW`a-6()S+`K*Cad`evjWE8b$Q!#yV&l`Pi
z`nD6?$7uu34~Af6p2dY-V0jY<ktH%l1YelC!{?3*31VAel7iUN=Y@o^?v;*|ulP}N
z7N@Z_+mi^=<#eW;dS#Amn3K5l3j8wCACT#9;Z$HG?rsAIydQdkdjT7YfF8$>lFE6a
zx>#Hu<kj9g!*xiOeHj78ny`|?WfmM%o%=SE(W#Q|jAwMC=wWbqE8tP}hgv(lC8M{0
z;oad@xaq`kdU?e{KBCuWcD2uj_<3*HQ5=%zB^yOI8xeSmH06qh;5W*h>7{TN76FfM
z_#B#MbrdBq(YQ-%4tiHK%|F2xH$a8+5kImpAHg9)ive!q69m!a{Hw6JtC9I*{=|CG
zz6qKGZqYUOOlx3t;x&89_*4WYdb(>lq+2<H@tEJwrJWZv;rq%FwW5>7P(YP!9&rt}
zl_r;#=WX8rx_0-JcprC0nPu%nc+uTZ>HQyz)Y33C&8VmC^qOqRPv@G-`9&@qNK^nT
z{I`Re;ua?|-?e6Npy_rB=VoNi%AC|KFPMw=l4;MN0Cb1R34$dI1P7ySHQ6IAuAEy(
zmXIJ3#%<+D-DwSXCLJf_je9dYf4x>iJsT|VSmnJn#bQY?l!Md>u!~Lk8E$Lxi<p`B
zhs>zex`a!?#4CsQWUVlo{~QH0@!1*Yh_@C()1Z{W?z(&gu``<BL1nj5&IX1rM;6+_
zP5sA*;+4<BO^-b_87~hC&OkL~&dt|b9Piatl`YsLuKY=9*>^)z?K)!{eBaJ-f4F-i
zYQ)+eddt#%?a)7NGYo>#IR&t?V%2S6w0T_`9iKAvTuct!B-Jt3w7=|rDemLipWEW}
zdK9@pB|U9``7ob)fB$!Pd@FT@?lhKNatX)w=qE*>7&f{-(an!Dv)f9l*T3);10r<P
zE|5_t#Yb$K=YuG<zrT!>4lBz}A{T_?zIKdtH3qywGs=S+bz3>->7vZtDAs6GIDH_F
zc?LU_^<wdNn;g<nqpWsxVyD%wv_b7PZ`@<zr0Qo*haW@*nc=peJs%Ynq-Dkoh$(?Q
z3TF6qgXZXKSVB>gN>^y&b1?<rgv=t)K6uC6{JJXp?8~~CiF2R5V{GY7nu6FIrKE$D
zIJ#9rc~(1jy1iT%V3<cx*xkd)M^#yEc2U9cD91sq`omt?%%bsizeDV`4IhZ{-528J
z$j(K^h<h=*{aAsgSMLA^D46jS<;*^RxG8guzf|_Mfu`1ojrl@YI)O9B=oC7DAf7wl
zMA7xy*%?z5tUT7w8UbBKhyhkdHmx>Cujw`aiwg%HD1ehkhBx=F*J%aE4u}d<LOe0F
zadiY1vK+PFFPZ3ladpMpARe~agN;$e2Swsd1o2*^^zSV><l-@Yza@ciHU0kVv`=Z*
zG_ELsN4k{xRP<NQOQIMk>?egI(SlyXx!0Pl4nA<W{eP@F)$ssES!`NevL!0p>%{nd
zN%e!9lz@qfL0^NX$q1hNRsl3MqDLCXpS5JGKfJGP3qr!<pRz-fQ%ZF)@{IU~MsBM$
zm>8-~YDEorw36&4JciTG(52KBHQqr5UfF=|x>l1!roZH>mtR1-OS)bks^v0X&!aQu
zisYu7XW*ucQdUm8%2~9(WOXaIun+Ly?=s`)gsaY#RJVKN{@YkVL_IESS-No_o6C?K
zXbO{+B9?|CvkXT$ImmerBQ@sZ7x(3o3<)K8OzLngO)1A?X|&}2<HOpEpkl#zep^TV
zRr&^qp>ppWW99z)Sbu~nOa>y37aPfqvD7LpDOs)TZcPu2JT{@Wd}@)gs}!V<(dx7a
z#r9ecBlnT`h!kAf77l6r+G$Pv$a$cC_r*jCR@SQ_Tj*2iwFi+~3x%;#F(sU+<Yb)g
zI--Dt`tc>=fLxSH@anU4+{BOMlb&qRauUTF8ZRulu;-BWqL&CY%C(#<vA2@B$KAk)
zD!g+L@m}Vp#tnbTdE!75sIMBmo@L=8WJ>=X*l78>FZ<%Z<#kb*pKduUp=W{|D&^(t
zDMXxVD}W`8bYn1VUtPkSSiD133|6`BVMd>T>(bTWLZC0xXo5BJg${E`TJKmVGAylE
z;;pMiP;C^%R_~J^UUx<1+sy$SwII@xFG5&D6xyA+S}QeD)_t!DHGtZNx_^-qc2V6E
zVrg$+<<z8I_HIe*Ux$=!sewtTldfAQLQ67fDF<&ya7bI>nPDvC5rqPcXI6nrD>GFu
z9!ojA-qTNCc3ydFwOYWr&Sh*nE78N_5<*~Jir$3He9@kZGL9ysLdF0dt|p!Xi&%3w
zRJXu8$8*Gz=$>TQ3CjFlmc*DTxQp|1)+pC)xeU&I(kAP?4Y`GakGX~QJyrla&0bTb
z4NIuL?u$P8H*QB@Z$cE!i(H2WUwF+MG)w#ZjcBVqUPXynE6k~%9yQ-sQ_HDH46I11
za=jrNC6#F|1YW-_+g$5e4Usu%&=t^&w|W9slio5?=!j1F43h|0=0?iE8FT_ajRo2E
zjk*v&hhE+=c{dOPF%ns^7iUD*nMF`gzh@G?@0>j=>MpQ`i2m_d5m!bUndXm+>y*5k
z9TZf)i@G!;<bN-}hxJUW26_vOqLUN9A*e+7dX%+1h3U5an_{`bmiShlQczz7sNe5F
zX&RCw9l_^(ZStga6Y`e={HtIRZ@9<@h)2cQKU4(!mU59EZhxzzsg1x!Pa^9Tl3J+V
z0~YCU6;n7x_W69SA{cgGrKMiO)lNRsjb}<v&2U?qt2a{q`IwMMAuL1hn<7G|X6QWo
znmTC#Q)GjDUzSWFKSj$_bxK3zzl*>>T}E(x(iW!x-6{_G64$J#-%uoaK#uWOH1ba;
z@XydAuZ+A#^RHLwY!3cww)$r>@)*s(UZp>A@Q?cAKP)4!(frSQ>1>tG=HO3a&VNxx
zUZeTX;^sfyOMg=7Yz}zh>OVzB9;5kt0`J{GY8wq#8m7YRrUeU+Wrp?543l;Cc(=D-
z-Z3Y>5C(WMR)7pSlj)5&M2XSi%5^hS!&Q<p%6Jz`$?`%tj%_>KcpR1E|2?<t)3GM8
zc`M|zUe|vlrZ)|Rp4-mRV;<O2g2Y>Y<TB}0d*o`_WlZ6*5ahD(Ra7epy3TagOAN@I
zAhTPB!V+<-+J20&2Rm<m%dpR-8H>sa*fFY}{L!l4lI(5nOxwFgW1{9+i&NJfVp?4}
zo@w~1Z7Toj#D~~u1&XwgOGKNtFgY!OSFg!SWjdWe9q6}yau-U<lg5=}kJoby_D`mS
z$4xl0G!tH!%$u)R7h+*vF-LyE(o(1%OA3MNZdN_DqrTk>kj*YX4NzauB6Ct1N<iiI
zCf_RXe3QkGE+;7z7e>yrT_zm{m30mZND~!zHz%jjmO83%`s$s$BfISFHFrnpKY0sE
z_U0yY3k)fq8v?`mAJ3c7&$wf%Z#y;f>wK-bMOQ0hj~D>UXBsMAYxR~*@vGA_B$AWV
zvU9WlGNOL8w(krg0d5of5@h7RarmZ6qzisJFWyLB+Sqz}tQ|1RIe%)y7HsmdAt;;9
zpv%R9Bz4vNZ|jC?r4aw(8IwONDp2^Y1)Uy&Y<mUf-D!!R>B?H7?Y^TSHBw0G+pL+q
z{X8t>hBWQE$-5BG+$mBo!^$=XCgY~XJ~3=xcJ}`GkwYc;wrP~$5(}nA-?fCwZQT-Q
z`YHgMR?Siwa?da)-<Wk-oJU2v1@`wnWhaiyO9fAH)&`ZscOO#+Edkn>*BUM=l%fXq
zNR$+GPR;59)n7@ZESIt4ggLf6matToT%VkbVGR<BrxD=d|KEYgGTk2O^=8pou^F&I
zZJaTyp<L>G^#it}OQ&otzzy1qsA%Nhft`WcjwE|@JhI)@o=#@8kJ!z;S$6<>{!+W6
zCCBD6xw~~*4O}3fN|T-VJjPp!V_n^NF%o)2rAI{t?r5oLH`syYL8{kQL2gG&WCae!
zYY&Jb#&G$lznGR+(B@;JJbI{gP(XWSyMnIj7X~7{)Gj;^3C1vORx|ZIQ``F$PF&)J
z+9!Zo-T5HAaV4xN%&Wmt$!nH^UOUf0TB{6Tiea|=GknoU7|RM|$q+{MZ-~yZn^s<c
zTOJ?r(=G{<(g)@<(Gzha+0TFss`h6XU+Krf>@if#tqIN;j-x%Kp(cd=ZOX4-Y^FEX
z_KLEg-H5ghaSNfU+&bN9U;W+i9XZN729}`L5Uf-oG*ho;B)st`#~+ClXEIp%27$1Q
zkJAIWhO|q&M9RCwn;l;Dj{oBdUMLenM1?asU1+xAvGy&d7kG8>f--l&X!Kddeu)}h
zeTsqU*aStz+O9v;yeaW)2mIigh`BQ&DKxQYs4hF!WbsLgV+1elb)+m08mBQIhbFKc
zX*q!A1p}cMXSn5x&E)#ZT+Q4x7<L+QZs7Dm&u{Db&?4%5!DQj>X;XSrwZm~+I+|k-
z#oyxgH?`0cr6s1^i2m1N$vs>{ktImQ5BZqZPREPV6eQf(Wz+5NqUrQJ8B+!bqTN)K
z;fDVU6WWWsk$8+JDUI=y)u9*0H(3%#X4#^NP(~+7JcAe6c&0M;4R6x{@j3QD%zH-2
z$qS#$wjQfq!FyjGN?76(4)DS(Vl!9Cb<k~e;~%{3FSO<`4<wwOj;Z-Dzwg-xiU@qf
zTIX@REin2%tA@&73Bj)em`v`boGa!yMI&PK%;-E6z$_y7>T)0(j|;b)Y2uTXYEUAc
zhUCP0m>=VfoQd}Fs*5{oP~ox&Vox$mHD>eyF@h(5h=>a?`iI3iF>=_r4Qkn&Km731
zNvnB8Er1eQ9D>NCJ{1?v<B7Dp#$7>7K1&YT&FfXm&c{Ny?meN?`TZ=w4CFVU7GK-}
z-k7X>I&FDe?HBz(k2@J-(XsCddQvL3<Y0CTZ1BC*l@rq`-O`K{X43>uT>*+Xbn^&-
z>5K)%UR@ju<(jnuh;s0QKBnqFx>D`k!v#8DN@)Ke<3Nh{LVOuKV>{!vMEhnH17qQl
zjsdD`W#5k={inH-D+jb=pum&d4m1f&1SaEcJfsFwW?K7*ftshuf-bii&Q1cKzLzN6
zw0NM9!R(DAs2YTLFvoxP3F8wbX;I!bWP$BBd64YQu*XNcZsF%ue{bQtiKWD%J!sz<
zx`^K#1(iG3r&=^r1PCyB5T8F?2=s=-2iL6;nTCqoQkd<MJ-%;wI6QszboPtKtP8@;
z(I8F_yMQ3xp}-IQXm|h{q=kkeS68`<C%_}-eyg;!x&n%Lg6yAW>tCkxb>aM@y~*29
zIxb4fd4jU;d&K)HrrvTM43G#l9-A6pR90D;+osiwav#+y;xy4_h2B#o)XLnzU?<L*
z#4-CCWfflcUq|Zm<ooQO+m`t|l;5Z0E9Cm82K)zT&5tW*qOG9<g$w7fL7GU;!)Z8q
zBZkSmkpyM}=N+Vx?^d9pvTiedKY2fgf;W&EC|(imJ+s1KOGo4uv{!SCC+rQVq5z==
zo2)}$hLzJ{vCT|(OO{YexMiusjp;#?VfJkZQVSOkhV*mU!aP;`uHz-p@rq)s7NzDQ
zC-PfpFdga9-&5TrEiQloIoGEP?&!uU-{bBv9+DHVxgtO6P?3P-mm6AyC4yetv%Oqd
zrQXdJg2_->r@kt}>FUXl$cX5WExTY4rF((Yz*5mb8@{pj7(-QokgHWNE2%@d>htdw
z)@h3jA{Ko<r+~@wNEoyS4#<UaN+ksw9I;;owCx^VeQuvxH5Zz8$Egz0q5({AxK<!^
z1VEp^ng22NCn_J6t`Lmb?HEUu+w2=xI-!^qDRfL}kF=)tv6Cf_D`XC!giUEzw)Vmj
z+;j)~TaQ}2*N>ZZ2aYeptpT$GOsEA(@^)>221D)2*jepRYWGuA>!15tUVYDT1w)Nw
zD5uLDngPK}{d*_@4~iAY8dPst!b|i(%?Iciu_;ugjGqH&J~tI@M0BXcQmIWFr7aI1
zC5o$UT}Lv?9_4flSplO7=6kuT>(~4O8Wg_ANTufRo=AzGIt@yyDPX0^LRo>=@G4Ee
zyZ%d-d{^5Yd%XMGjMZHQjb!Spx(~c)J;kE1rh5bZf2Gbx)O<r<a_P3azvw)IUo11{
zR|<69bekW_6F(`f%LWKx&pzORaJjy)4vt;+VYYhmYCa&NybYTPVJd}-EK?rx4szx1
zLRw->99$K;dS}t|{LKYA2J+iX2zGi;#wk2f4Aicj0ox;s#cnFLr#AE6Th@Ce+2AL`
zo^%oa8C+P+VS}pz#+ttXpmK|4gtuBO6gy^8p7ftPut8>T^P7*|?I9O`GJtlt#3#y}
z5dWh+AVnmyO>*9T(#6*TV{raFD2L7_wHyk1Gc9aVi?b|rl1FGIyJrT$O~vnLQQNs-
z7O4v8$kr@NxBX9vcxS_Ghgr!1gfMH4O?Q-B_50Jak%i9Tbhdkmrn|6ut!`(r{Wi^V
z%1IFlg|NE5iYW2`^~HzNzd+Dh0qNzryYrg(95-i-&7+3#)=#!UKSTD)RH0N$_b8{N
z?khP472@GsrPcBa$Vr9o+|;@|?8pm{TE3q0cYa~!k2aIN_hh1duDj<?K)Ls)cy%Hc
zS|^Blvk)F7qTZ$VUH4x31(7A2$zR+H?t5Z>C!76bMYA+Csq$AHf2c_@apNOvBF3RL
zkQ5Xo&Mza?eDL3shE~~P%M23Fne8%#aktW<iUbBPlNV4PvoM2)bM}N(Yw)Q4d5fEi
z9is-9TudU>Q06N2=tKx%=S<UIUkf>%d*D@h#%Q`YaW?(C@wdFA8W-CRw|w!QZ#P@H
z6}_!()yYwomX^X{Dje+L!k_L?>pk74U6r!q<xC%(4EZ9_AwpP%ptnF13f_}e(7B16
zi!1dS?;j(~itXQwB!Eh<t$)n1XXR{_LXS(@dO{g;I!O)J&dC_Fqbo+Vs|xcu{G6m7
zi36=up&TtsOEm5PHk|)dFtmxaZ_3wRjRARdDvNd&6?1sc*d5apXzyd1t-H{Z;LHWY
zI9Wcj)Kwh|Xb}bFfk`jhqypT;7j}{&dUrruFW=MQqtzh06gvbz-80qtQePe<%?#a-
zEVg~P3^GfBi+c}<E{3+upgj1<;<y8dRphvm@1Vos(WTR^_CUsSyg8iHUX24WNQQJo
z;k52<Ac$W{?W&>}6wMRRrkJjfnGY%L$HU-(byrq_c~d}F$P{8EKHJZ~h#<y=<FY-4
zdBg0aSWj>vq8vLjrc~(9;c9YQ>ZcI&>qPQb!sle&@ly=kFj;@k&M8MG_YP;r#-K7%
z2d}fAU-qmP&MTirGJp1J`Ivy2B%ki@qWxs|dvS;otMz|9Z@kpMZX(R<fs?NN-;-pr
zRQOjz|99iGsd(*(TTASznJMxYD*Tfi{C619-v#|YScm+=p8i3c{y|fp46Xk={r9gx
z|F`2*A@dJ~gvo;Mr%3cyB$-@N{X2C2D1`t23Y{`)R+PSz+{&gJ77<p~`)u-gU1%ux
z!P;|0P$lA~;y0=Ttw*^<z#F)l3Y6o{qpLOjetCnm7vQeo%Se*_G0=*8vO@6Se1sOB
z&x+K)>Ow0H?n9&KG4`Er%fYueXywj*@^^fQCGu^P;0N(Grqs9PPX+!>s08;R;J#eC
z*0)WANKYMTB@XQc-MLE%hgL6;($tx6pnU?aBukr7Lx@FC+I~3AxilWrHk&bKlpEw@
zKZrYmXsHo5iD}NOzKRyB9Oxgdyk4fWVMZ(WP*S~?$X?wiKiF4SzmOKb;d=b`^C>k`
z*gSk#V~sk>Z){#+6*tBH`t@;*UQZWg6h>AXOtG(_p;#_rVZB$*2x9ltg(;w=H+ApR
z3VJ8dXba(H5ceIo$Vd^D)14a}K0r?|XHKL!a{WngnV@J!$iI;A`6;C0YQAe;yW(qq
zl)$r?BQquV4xPb;Db4>kpfkv1?Ofv!pdOPlrTKtI4$q}NH(a+)hfHuLBX`2KUKYt{
zg%Z!(852vnz5jf)>*fMu&6zq1?Go4__iUvsWK#b^!vFKoy>()q-`gea|9{#F{{z4I
zo2~8_(EZ9Cer<(&tegvlMHLlidi2$*fk)!94h}!;GFQsS1=`x$yEd%PZbPvzwDGny
zd}kZ9<v#z8OH%%moha_Mq({YVgql}E0nG1)I<+0jY5&2f&rdeF`xdj{m+$h9Z2|Hv
zJO^7AYmLhLcjiNTt5y|r#J~v?l^$g`M>-=B6PnC-<f%BcwfIJTfi1Y_?u?-b+?zbv
zB7cDx$>46bK79*4rHiIk>QoXgr;ajugr%BS(L{K=gHU*b-4prHd2A!0>soB5&%Q0O
zuo*L+HCgzTWhL35)Opah2K!B@UFTs!*u^{>BD)q@3I=_{z<*f_Sf2R(aEs&fLl1>M
zHAbxh59dC})C!zB9-hxVA8y>S+2+8>_z*3=Mlaf1Vn1~5ygTnQ==kX%%N%u$PVgzl
zQ~@2kI!RH1$*wCz*M8gDcv#gA^_VGO6dK*<v`-!t|3>3&h^SWPx|WVBTHx^bav^M%
z26Sd<dh;TUd3gK~)F=}rxvLO5`|M*6op^pB1|C*zL||t%ZS@dWGkJXCx0`SYWYH#p
z4=}$#(xdCG;8T&k#(P`PVXm<Lv^*G23VFCy47lo-99i~og-#~ZL*91ekQGu*omMq~
z5*HFv`K{!)t=#OpVGCH|2>$*4Kf%NJ;mEdME94hC`a7Cz-#YthihBEJqO?4izBpBe
z;jmAUqAi)(oZ*t5KHPY3v2TIiyQjD9@8{Qj(0jhQF*4wSn?z4;rBcz6@I3w32W^2^
zZ(t>Dg)-w-xeYS#yrr}8<@O|@21bh^#zV)_d6j>n^{&OFklU5{(D3X?NAB=ZCGXt8
z+GhC`2;zehVcdIf=<LGN?9M#%Rq52$G)4529X+=!V#@$ODQkE4{IhrBk8BWJniAYQ
z>L@3a53>!aM*U&E1(WFRNXXocGh#n=qtPx{8`WG<5@*zSOCP31-_wb?vyp5TBAfS{
zako^QK_&b+l0cncjT=g##PD{?LfCd0-BwGRQ=DXjQ2Ho=IXo;!h`H=FmUjbU;en0H
z>m+U8LcJ77aLv4KtV}umTBHt_b4E3RsoR|4IhHph5AG)^zvx}VVYBKhi}mrt)(V57
z&J=W9<uy6keqyMv#|6gAC)A^JpRi9=Tdgfr_}%hW(!N{jF*PH{s-!Z}NA|{6ty6%A
zOpvVI_bNrXo>dsr!uKoNI1c8$oaAB)!NI-8<;0#>1f6f3)IF0aKV9)=*U{L@&Qp%M
zJrBgd!8#Vcb|vcqQWNh{>Dl@|XJw#MOUXfe%0z`T1#iL*?)A<;zT;HfhUX#vc1{})
zI|RM8Ix5opwtHe~yaGk}m7I%q553ri6WX}Tv%LaR-lsGZ8BKPUYu)=shL^dD^jTg3
zb|z{Dm!O?rt}cMtJ{n*si+f&;O18ie?DilAJUR@u6p`k^ls!c+wolDF3LbYIa0XSe
z=M6$16M&Iw(}}6UD-$zsHXCFcw07hKSFc<yx`QwKH9SIFA*!tpE>rHK$rbiZWsmWK
zv=cUBH{mTC<<2+@5>i-cMdQKA*<S}<31KxzA$OC76ZXlCYw6a;oYx3-q8MBT4MxzN
zt3IcU2i6$*8Z=eG%C=c5h_o5afvB?gZ&pNyGOy4gqw57oAYDH`K6u;m8~_lO-0ub0
zlcY>Ybk;pn@!_4x=QOjG%faQxJJy%X_XMBOmAx<UnQkj>`vcr05yX^?OSEyRu?zT*
zYqxc`8tss+TgjA;xI-yfJNjF{qI7o^IwarmxUMKBla}^z<t^xQ*EJ@F*`4e0yU=E#
zK_j;Dt_Wf=6nQzB$--FT;kUifk?t5fHq3ToPf{@w@8R##t_P|39s8&kHcfwZ$*y*S
zzIC6{6(tLfREv+^a|#ZxJhZ6nvoX!KN}P#1JRC}ttEB}px(N1LI&Pf0+1#TX{na&P
zf9$=83ospN^2v|~hWpUZGYuWW;-YmcKO9HPjJswnD-(3;zrh~2F}dgZIyWcnaj%2O
zcu(%<*6pY8d264A)NU|dCsUrHS&^|zWeLqAajb(}wenUwkS`hSY4#5sZ_4zlZe1DZ
z&{BeE&hQYdPqWFW-6<S6>GzQTt~h-szMrr-*5Ih{zEup*$N>$N`|y@SWTyCNavE?G
zHWacJlk9FWw9#@#KcR-p<eSAB9^I#aJL)EoxDTP;TjQYE<GsID(X%nYZ3%*y$i~y{
z!f!d%w&W!%`Z@UZ_Otc}L{1ONcs~_p6qnMTQ;*Yh;Ss|cDv;%zqpaRiI#AHq|G^94
zT+8+$J4$p*)aDjdzjQ)*4jQ)HbL57Mb7Gypc@o0kS|62q?u2^dB?qK&RqN#c{Y?&W
z?_3zPZs?%FNN~6_+MVvwQ`1W^QZ|A<N+&#yUlIgY^I@1*vuaiA?_s^gMd^7qS*((i
z*9Zel?Q=pPh2&A5c>Ze<?&v~nzw@gV6OPS+(1$OhH(@+d^cvhIEEpJExGZMr*hLyf
z0B&0Ny&IW&6w}>rKgT0&TpWRgzE<Pdi7**Wuk`T`_A44pShcVS=vy|b9yI|y_Iz7+
zdMuHIgcDHN$rH`~NLh4!GP9)m?1U&G7SHLv*1Q2v$jTuXL0?`#W+^>}4qQcVLf+(<
zQG~FfnY#Shzh4-%!I|uJps>22hZq>vOMgnI>h^9IA+XE5I)^Y3M}JuYzR);DLa1|t
zF;RY^nZd#c;s9SLdS_&`7_cfb_eC)(>5Xd=JS8#Jcx2Rv7-lf}F5RT_-9%AZ7?LwK
z&^ktMM(MNrYyz7J1Xrg$^NV2-c}Cfb`@Hk(1L2qI#~3>GChX_7b!GGw6aK|J=IIJz
zD9j>(Bz7RDnsW&HuxQm&??8H*aHX=IFShl9>tjKW*c`%_Z1*uwij6g%5G;XAeX(~w
z^a-+M*>2;s>J!=5pa-=$jDqn!AuN^Fevp&Isy=O|_GNTl8#opNeKkhk>hZdT*y0;)
z@v<V@hL>|Xoo~@D^IyAl+oR>6B&4_toCoZZ7-i@)y}6Z5y=tq#8AxsGwZ?tRFS5UQ
zE-gDV)GgZV!3l3Kg~euhRAHpBa5W=nT*rP6=?QWiZc39brCrVv(VAm3!LB`+nRb^U
zhE0dyDj3}po?>2)pAcof^0DEhvkO0gu6tLCuLpT7EgP2>(Y^>#F{_JC<9xzk7{a60
z!OenLXS5FrG1$>l*ER%8xX26+A2b^*)ZVljfqiPv*hy(5+oakczNiMcGu+Cgdb<<6
zUO6)}b4bpLNO-ne40M2ko<^CAAG0fG9sOf|AuJ+wBB{#&btKtqsMMLIwIEXr)KmHh
z3mur!&sY>^*<~F_aJLlF(M4SCyPhFV0=uH;%Cn;TtoG`n3Gw*wl149bk9mY}8irmY
zOgV_hxGt4o5;j88mBbwEy}+h4mANOn>68W*aa`ZIT^oeH`NK#hG?P&>(A})-tC?B5
zc!dXNm<pDm$6Uc$+yA&c|2s;*KVK01oinmgo?(jdX8rg+?$;2h@7LTHzt{BY{{!?V
B%##2B
diff --git a/public/07-basic_statistics_files/figure-html/conclusion-1.png b/public/07-basic_statistics_files/figure-html/conclusion-1.png
index e2980fa56673b91cf6ad01be83aa50db5bdb8802..82d84837d73e06cb686e796bce170ac50d9b607c 100644
GIT binary patch
literal 46895
zcmeFZWn5Iz*C@Pa7`i)^4rv7>l>wwxLP8o81W^G&rI`T)q$Cs!P(~C%LIfm~7($Sc
z5EZ1myK9(p&-nb`d*6@m@4feadxqhh!#-=T+H0@9);jwTYkFCqo`#1806=eOaKRh^
z3iy(&o{9`UeH+&{0ss+edeK4`07!xKu~AU4RZs|4P{1hI*eKWpE7)Wz*xD-CVias~
z3c;BQ!PPJXe8WZ|m~@}?fiE&`f`e^>;bXN;Cj1?MQP|pIY;hBJfEbJm#uEIm0}K>w
zlNlVWKmrfW49<kV)xntq!PV8l)$nl-0~5A|zqS|*4ufmJG)!O`piCQu%zrd8gB3FW
z_0P<-A$85HhJP}v;p0GN^<L&cb>_f8=D;4#))og7Z<xSMK-Iwt)xkE^!ND+@>P(yJ
z%;5j@sD?iSq<#bNaj$x>x_WP*dT*}*qtJkZ$wCbfG>~aCkQqFX2_p_B;f6cF=wWcu
zXAkZK9|rdJCUCYB4Y-MkhKUJi0)qCcgZHX4|KZCdp(KI8h~eWNbl(YTz(5l?Xrcjv
zp-DvGBgC-azXy*8wU2>~9{?v}NWX}rnGH7p1c2cMEsKE6<=UfSrM5KDZQV;Qyjp2D
zJSMD^zNS<5IJf<wI!%8D`O|=+<(zpF<4AVERjz5T4<Z+CE<YII);l-nJ@@)aalo>B
z&6zXT<py>}o^Y33*Pk9NnM|7t3F4xoh;%UuQ5!-;HaN>?lCc8#{G3e;P((J!pSlQ0
zx6Pje7_8}?JVKs}F51uq=?tHrG@|O^vse^07VdbF=6|<iGEj*O*Z2Rp+c-dfONHOv
z?-MUf{l$FOA4ipH7y7xW+YApPsj-5rBVPt--IWU`LNYrWykM4Gv(>GGCzhj?GLy<w
z|I&+r=!^H}JmoS+K1FZcJxf{LfT~Z9UA13{D&y_*Io~zwtPG2D=I5(|TAv3^JYC-h
z_?9VHfsWW$zjDqlud7W5DjAU@&PeCh3;!3G(UJsN$NR-~p%@I5fhXt>MLE?$6XK11
zgbBGt4fgvDymbK>=>Ezz{GrF=J*NZfx-dDp8>e+_4+t51W1($->+M3mL@EpULui;g
zq{V>oR+jq@PsI|Mi9!8}tmBoVqdojj)ig$7f8AEpcv;rD0sOc!t>Cl<VR=sJYje}E
z0doD7|Ag>W3T9B#T&aFl*mp0Kq%Y9vdxxmZflac%E3No2rCRa=^3(YVc3R<Sjl!NI
zy{-gdK+KUF)rY%%9Xe6S{N?C8Nn@!m9bZ9-<m2%<4xU!2vYo9Cj4X(N4QLM^a5)T`
zFFyN0QwI3<7yzQ!RkFjwg99NXuKNXP$OJ#m&m4?h1$9Bs3R(X|z!XK0Ooex#jjx-b
zIlw~{K))(SYxcIh>mcv^-`i5GSU+a#?M;HW9KcWZ{*Ht@ppffty(6RTc8ErZ9wR_(
z#P2pAtr4q?F5#Ug+fcaE*+Gt3kQm55`Zw-WD1ny~p+1w0nmebqj<aNx&m-L&P99I;
z54gmRM|_>HISANGlnx)P$XWS0VO;k&#=`9P7rb7TbNbv@4O_>o3}E&%-$1*$)OX(K
zLjy@r``(PrMUQ1l&0vnBV{gm^C$C~hvBn~17}_zr=&F$?;jEnZJ*m#YR-o{~I+(<L
zv(u1Rt}5%NXbb#()+>#SWXfjeio2oXEx*%C)pFt5EQtMyEY0qnkie^rT*v%jTMV}m
zBE#$`YkTgV^pxr|0f>N9F{XV?_ZW(d>get9w{OL7#Vf`Rj!l#~&bj}tCKvxS=eMJI
z*r%}C7dpU5$U?#honq>$_=`B}k`jt07-{O09xLJaLyuyzmYct|9LFIaGzEnaI}31m
zgOuiodOHni=|qI|oa0cHr3T3`9{#C8K*}wJ$9OcbGR7apWQacf35kjTYJc(ucI%eb
z5%L-kqA0A`uS+(*<-I$%8FF!yRsCeE=f=_=KG@+<R^E7Mi{|_%*Mr9DMry44{f(Kb
zPh3as3cI&rsIdMU1xdEIn?+h`VNRxkzA@+trci;=Ni!EiI-F`{TyxRnTavXD&eHGW
z&)iso0ug@$x8$roP9zZdn6MA4BgW&Tu1~L$If6Ru-u_RpA0Uf|zVq{A_B)i`j>!;-
zoZW%_l~QwA)wl3RH*cqx%u&|wVK!#A?yZ^EcMxOBa|5lw`8Xm`4sXv8;9VC2adsHY
zRsZ?x?KpRy$YZk=Dg!OwLi1N*$~nonoup_65*JG{7&Gqb3jx=7%BW`XiJnZmJ8!M1
zdtjf!WVJ;>aN;W4g9^dBbSgcvU|`5f6+ugfY=y^9a*?*a-!W_7bFOHFQHQ^KHEm((
zx1x79Ew)^r=oyGTvR(0e*GyHfpIZKWr?@j`B}wjqd7&`+D%e%R&C&E&UA#72AmOT<
z|2^Uzx4#GyT^?}tDj%6g*IRKaTTzlr(7xKqyACx!@2(p?#8?3qW45;l#3P4v6ekx7
zD<kah@CYUFQ(qrdZ@rN>%f-3YS>uSjT(h-X1NQGH`(VZw8m2D*jhCUdmjv)b-sJbf
zybj+W$7NoIRdPPzqD<Q5fABVl?>;!2%cntxwbM97$0gFB+J6*KP{sS*;6JqALUXA4
z>RQ`uZu(Aud?wmJPJwXlXm#M+aR<fa6>HEMbZFdNuckAyQb;ye{408H#f98k(dSgG
zd2fKIT%CaaK-l^kR5@11iu^PaTm%B|p5QT&;`w{&acH4zOlK9D+7zlHz?O@N%%@8@
zdYvqcG?84Cyz3$NpU}wB(mIQ|fdKd*`tm2W@wNXK{p?H5mY^n`(&-NVBvKt&|Glxm
zb+LI!80ozA<Q&DKo1<Uu$3iD)2PFt@Y1CL@`>vT!h41{9{c&8y?f)(po6KQC8=0=v
zka;AnHga-^w1)f}@3A-{gNz6Vwuhx@{<C<ZJ*;gppto8vPA*_0c$6^xW(%)+%dXJQ
zx@8L~P#VL&d>Xc$VDCDS%k~>1q9|waU;bUJ*w!lV6Q5}PG`;ko@C)ZydM9tX7$!KY
z<~~mO^ip{oG6uwE<zUTDD)hD38;SxTr6YA*o4metgpGR*5%PJ;I}hyFCqcuv_JzS@
z%2R0|6dZa3bl?`&!j3c{Ybbe;>?#B=Bi3FGbf7feSJOjpto)t<O?iOrRTkl^T_3KC
zkmeXP-Qe#OR^t8nY!>2ztZ@V_J@TDu;_!VOhBaUW5+oZZ)7%%w5bN-7N-l>towQ&E
zb+v=Rz^O(DKCBeiBxlqw@$_&usFr=JvNmg#Z9aa>?eAPXCoc1vgQA)0x!<B&Z{F+v
zIq1Bn6KA;5E@07{k{%!#C_Bp3kLSx08gf88Jv0{58soUk*-yFEyiuxOYVq7t{uU!G
z=nngN3TK_PY6C^sBZFq4CX+gb+2=hkV*l`Xa88B|Ca7OS;A}M{rQ;Baxs^$?l}3+9
zOaDKD?a$qH!^k;UXwaUq&Yz8gd%w9E`UoPOr@iRfD#OEO<g^JJl?~?8rwjKdl!qE;
z(^Wk8iXZz?ISJm1WC@<{xs`i7H#R>;rXpL@u3o4)B0xUgw5#c4h0WUoEQs~xh+&hL
zcPY0|g1_*{)tlYiw<+3#y}~~$`LlIM7~?9-HK3tJ36x)uA8c4dph()yKyZB-(k29h
z;$jQiI%dy-m$qc%+$Zn{zJaxOGdxas&llOfE#@;hdv0vkPjmkuxLqje(&uxEpkj{`
zQy9t`pnhv3L}vX!a<ct(Zjl@Rf(?@-Jjq&fs;0jAUklk{FO5G*Mi289K*x4_<K3s@
zuG3TzenBG{W0DBc`hCsF@ioMI{ru6)8(kN{H=suP`1%-2gU2+NM-M7u91ikYM>w*b
zP)8w0VtJfl5bIp|<lV0;S(q}-7xcw!9bUD2cleGf#MnULxsZ)Nm01r`-lR=;T&khP
zKlV#Tjz2DrXWYxxn9|o3tlmD|v-kY<{^_2o<|mE2>W*|+)nB<82`Q_*!gqD$x}jI6
zhj7ZLMA)!Ry}RYUsJ9=k<LrF3d`iBfr)Cv>t;5%q!!co>-3S?ZPKEA8VJk@r90X$b
zF!7+@vA3w9AvB=tWXX|UC~scOvoUx?S2;PxDtIu^GyHaU@X5b7p=P3+`OyX8<JE7q
z*;ofy!ruw%*z35f@!z9X{3`~XRrdz<{<GSASom{*k-uR#97`LEaz5Y?I2=N^UB{jF
zKNxRJ3g`J^r!5A$i$}w1?`<d_*%|7`>_=u{jtJR4NjEUtbKReh{9`b?!_iRZQgIf!
z6DtG%w`<GHh)<#XL8TwasOpL2bCkbcJ28ZXC?75Dj)ndR#;?1NQa%{u52IMi+lN=>
z_YY35>UUNl)W{!}2Uz?Ko6Dom+^XU)kBcGM^XGidIml%}b^ch%)Ib`n#_;P#;3>z=
z``=6{p7tLY7rKn#{=%y*37#Q86?o@8{;%-2f~y6(Mv9uNQUG5}+LtU#<=><=1CF>e
zsHZTx|86}4AyDQUA{hLmZ1JCP{D0j{0sCY0*T`_Y{|U<#TnNRFNKv;k3wC8bVgt|k
zUs3d5doE~c0*=_5UZLub$K5eY{H5}Wy8od?KZQ~HM=K3*1^pk0-VMMgeYCnZ7pr^q
zO?ky|YOISV9OB=I{=a{r_XVi*ciTn2ITJ@-zwcco?@5K##ZHvw34j(%lbe||=t9=}
zxICr7ZjAZ3!M-vcG+CPIfCMPIAlm|Dl4B>@CD_0eexf%|7;qq><Fn%c7evpg`v$1c
zf~FiZF%qJ3GeaPar0c(M0wGW2{TO=&;llx<Z@o1jA&P&S4z8lOWMhqx&IDz97G31H
zG@#?uk0l|p)>lG&qLQ~~E=Q606EZ^8+W@YQkC7xqvPnTmXJ+RrfqZHbe_Cu**fJn*
zfAZiTB7S!AdZBusbH7<h`~|ggVjn^<)g?hY5>;N@`+rnp;{E|M3?RY!7%Z#m^gmfC
zE!au2{xQAsPgX%|fF|0(grhH#2z!Np{YRK9{~z#aR~pcWfyHf37AJ{&&eZ0gxY`c?
z#EsHGpbxwe&Q%<x|Ae6Sq$MfYJWrYgoRcgHP>>9ud#3%EB(eYh9DluZIBoUUf?MhS
zSL6Q|qtJ^5A#=m-_z>bowcN<u*!Iqlb6&)MRHlvaangW3!FpnM`zJbY4syIMtP*bE
zjQZEW(@aWBV2=8AKl~d5y%JDW43EkG{QC<CF(oO>l8u(6co#OBdi;@lw_q}C5BU=R
z^gSrShLt;C1r5l-h^%#AkP!9jeE>C(XDkv{m8hA-Kj~o;<Dd42V&R_I66~arYM0=^
z?m2nexllCim`aj>(#&K5W}gI7D#1YlX_Vl^&M1<sFZDkSu)&T&FaD9|Btd+I8;V2a
z{}GZU;kXZ5?Q8uBSc+#C$p0BnJPTY7kWGTs!X?Yd3Yvbyx%dyd|GxNdCH%J~{QsT>
zCnnAd7<nL_s|4frz2TEeX0Qfa1}n=>fXf)s@l%nc(@nD$3{0UJF2p_OhX4Msk%`EF
z7d%~V=o0K@qRY6kF4x#L$58b?H>)_^;5NVPr=*TjO+}gPx>#!L#0`mAJbWq*IEg(A
zPun;if-(a3X#C4g2i_U=(FdkcB=~~Hm4vhn5*~4j2@-tv-&}kzA{oBY%WER>U|G_Q
zi6ZqKrnV$8ED;raTzrRlfzxq?*LkxPCQa{ilL#}{J`Q}X<gTAs1e|bV?&Kt?6PwnS
zkkJF~aTiJ$)j^dSiG9(YZXG|Gf#=*8u#vK<uurjQnK>X~#{Mdk&wcvpr738Q>_*j_
za`w-`ED7>{*ZN$cBOnic=i=b*_wQ1Y$oWo$^eWPVxtM{ezjqZ7@|p2=>#!Wj@s|-y
zCBKR&vtZD<Ne&VduEJa|KT8TTV69z7`<(|)2{aj2k&!qF^kG)z)dk-m37&5iSFf~S
zBH5HlS`eh|e&LbiATJ9Pzsvo-dWOjRu!@${LDh%$peCwSPwrcpumD_A#J~X{tVL;&
z;46uvk0|@mQWUVePmZkq$4b=0XRB`xu4$Vw7en$0XJd4<f)6K&cMoS&WUS3;U?1=o
zK?|aETb{z5CTB^!_MoG=s1%mS>r30)dtiBbxRgms2uIaa#4=ozqy(@d)-fJ_1(T&<
zDbDG9cq0H<!~<Bnph}&@qR9A~`u71F86<2}WaFzOoXI{7#mrymQNjw3n-JW8M~aIS
zbx#Y$!{WwNZ^1OsQ~L`yi3W{Q6FPX7MHZpTahRf3QpOf^899DxP3*V(S5_AhC$@E`
z2W)qJMQ4K^+1MLw`}xz0)mOr635E=2r;-`VIW|`DVsI$V&xVtH`o+g-?e+`u6q(Q8
zbn*Xajkf)G84SlkM@G$~2I5Ee2yO)Nc-2H`j|uBOhQEJMupPwT<>P)ZS8|-P@wo+k
z7P5Za{u;YA+d286BJ88gJ-ZQu+$PA^89Fwb!kqHzhSaIB{l{{z>V`gMHbec9f%G7A
z?^XB`qpH0mLmYBk@Le9JS6gG+_GDT98SM`4&U=!RV+m@}$t{ri@N1}&30nz>_i$F!
zJUT-^ypMg8$EC<Bn+J@-%JuJpb>>fdjKmn<GVt)df^=3~UK?QnUBr?A4RB>b%51=i
zR+2q=wf9MEZPqe%*4+6s)fefusX+1lY2%M#K>d-<LK=-caqhYg(djC9{Ps&CxpU5E
zjg`%Z&nfp0ksCjoaGB8UrkOisZsnOh53G!LzBgcM(j?hMynUuHwr1}i`5j<v5Py>h
z<0H^5C5f!-!F?V&iD&WxpA$<GwNfw?LV02idg(t47pW562UZiW$E0}$Phk*Z<B%@7
z^T2HA9eL(s=nc~7*V<CO=TL`j*7O6-1jO8&<vHEv)_m4YM}0x5wogjA4~NgPzU)>Q
zWnbdf5f9XE!KltoL2l&Zol!@%2^2MJpKojjXxg(&yLr*$$wytp_tmFdUY|rb9(cWa
zwwB^}9c&8-jUU*noqf?0@_OTAz~fi^4PkQq&Mg?!lPyRaIgaGPw|yl#ARKv-gr5Ub
z^=A%T`&jFSsH9awio!BiG9DLhoUZh5sHs67@!tmbGJ%r=&?ep*HFlsFYQa>s_-#Qf
z$WIAp(!)ZIwl3v@CG#HP<ZjV-5k+}v-KpYbrZXyi$?DE3%Alt5{+VuJ`SQ2<dCM&i
z*3K+Re$KjCd*XqwDrBAg`I0*!MqV8%767ekNmk&sP5SPTc%boxm15@r69=_&uLl=@
z1nNAgNUV<Wmg$Q56MRhhG4=sp^@|@x1wCO8?9L)L?a#dI+Gjkw`h&o41$N7I@4axU
zB4$z5Z@noj2n~KB_QZ1{@<WNiqdt81-}yXkT4J$YlY@@;PnBHGj*t1Du-UVP<Vny~
z_4y$f4Vy*T8T3xC5koU{ntWXKgxz6){;SPyc5KcG!)8r&(E8%~pZBuG2#4AkysUKZ
zosPm>N`UPZllfl3r^RSoMm}CLke<WF^W))$)2-9hACt=k$?Mzn_S}#HfnMdQDPrSd
z<9kb<N)H0rTNjHUz8Jk-znS6z|LErBd>Y!k-=7YAN`HpF02YQf3GM}zL<LERk{!5U
z!pIQydof?h(Z871pK<rGTd!BNxO!Pe?cS>J;&_*s?WHlLY0>kWz<(LcTV~~HTJxh)
zm3^Bn66oJ?pClhT{>tI4Mzwicry7##!pPv0NyGVTwf<nlxv-AkQN2?{;BSA61-
z9tA=&L-Ade*6?$%z6Aupc@E{{&OP#_gagl|J2(1ROO;ZAM>V8Q3+@(cHTCCFSXE~a
z8NB}yMAK<~$Buk^j%iH_e5<9PcY4cnbtTSA_{Ete>H!`j@O0$B0VNRn`lC1aoB(7&
zkZc60i!HgW*P`byUP#L29+6Q5tQ^6L2akaM@U7l$%SD9s<D!u0&L5utU{weApzCnr
z;&ex$>}7J%T@)H}wANz?<h8!ooMAZFSna>l)N>o<`us=X`<{?L@7Z<6SY4;{GJE&s
z^6V!<C5&$<3EDMLq4m5!cFKPQRaG*CjB|r^m(Pv2vyW2xPWN5$z~A^4_p?;FyY(8O
zII7`5GY(8|&%#c0I%SsuYxD=ZWEH^Qdbf!i{cBW1IDP}qK`{qOAbYM;I$uTL-q)W+
zB1>IiG<BXsMn7Fhjq*gPOaJs14I~_iJjP(~M>tu5wG&wphG{iS0bA&u&8G#YY7y=1
zBhkLYmqB_z5f<}p7Z6I1artwdbJ<oHH?)F~CiGWCoT-&f+Q8fXp;;qS^(~<0R(Apw
zKf8Y;$A4;YTRMbLeS2xO7cx-J#$j6GK>qij_zs0zki*F-O!-T8@khVh`&mjKd;}=X
zCLDp|Q80D=ZrKGU_Tm$W8aKBAxQ>tveYL832Io676lGG>HtLq3F|E78iR?ETED|5~
z9KPlI(B`F?@S7q6n5H@O@HDb4mP<xHf?is+5*WhsPbEUxK^v#KrXe&EXO1nTM&Cy;
zWk@xa3!|O;QRor67kDv8rJN0?>CiM0$4P>k_G}j$wyM(-nfwdtcSJ6-fmd~$wKGZC
z9O9~}qxyh_*pVUlB&Y?mc=KW##7YkKeV5~@(Zy8rTTv403a9+*j8f0tG`vF9k=OT9
zF|Lj;j0#q_ab|I<tBGv}l-mVT2it--wNN-~)OL^v{n@5`3bc(5743)LPo-&40#5>3
zFgpsT_G*n%W!%hW1mbn5vG$0~Lx@6?dO#eRxuis;CJw&kjM{<eb6T_4&k&cg3`^Eh
z7h@CIEg4D!R>geGHE-&lj{_FxskJySXdbIE_u|fGQzbuEiI)_=S7oGQlzfi7RrJ+{
z)3JeMfNXx|kKZHY=zQ?v7(<4bSEheIgYV;7$OOq1*Id}682UZ*nM-rQ7n8RAVvNX)
zS3JwBX6Vh?aJf@Jm@nFA$=l<ZeuE979)EhR{aHj5182Grc`N2cj4)h9$nvW;%C{nD
zUIF7lj+en#`f$@AZ_PI=aSX8s?-vhc@_GI7+V^OWWu$d!9zraPF)Uz8bFMPaYxr1?
zz<&u`@WU<>@s~jBlXN8EczOMPuldVNb`UYt>=*I|pVLegzK*XcSr2J}e&m|Z-Vc2F
zfaGjM{6G$<D&OnBeYO0BG-u@g@$$&4TNL2nb|15&S@USIAV_tzJxJKyDA~|F`oN|t
zW9Y{Lb+dxcEndxKb9!HcmN#E3?C)PqpyrPnn~u2WaKK0iIQc1Mev~#^OJ?!P*TRy~
zul+1c9gwyAd(Q%4_x-y{Hwe!((m5PC#XQ@fUns15SNxYMP{pR-HB;wpeDG>%5-`~n
zMn(-T#R&{Yd(}cl&o-QSRAdYz#W(qHGtWI-<wz5ZN`_jCzW=O^Bw#LFH=4o|8WeqO
zQ)fkpS)!n^Q`R%j#64m47T&M+=+Qdn|Je($aW^4^@2yTv@Ly}Xve~BG8U_<~o_nsM
z?^uKE%pbCu6R-CtLM<32fvH?-FeFlZc&*?tdl*~We(Gq;$zr)~{-{-r$6p())8d9=
zGD0{_x$*GCKWc%vl6Q=0(7UW(bwF$7X2ruruDtUUlZ;=O_p+17N!U#zxO53;h_qK$
zRTCf+^lb4d5Sf5o*B#Uwzd;PpoB8#@UTz@yl5fWikQDLCdJ4b3@S_QOg2LUV6|h6(
zQ`CR`lRjs7ax*6E&Ph{I{3)U}AD|ZjZg${$2xsyJK7Gu66Ou+a+uknH=!M+nkbmg0
zf7&#x&m=opFx-*sD;NdyXORLMk!oB*g+>p~PC+6Bep}E(gk=04_X&VOJuIfC7>7%U
zz250LLy4Yjwm_nX;R*9&KC1@?4PwNGOexPH{?K8kLNn;}?>TyOuOp%dH3VEH2B>>^
zm6@^E$Xnk=Zs1qRSU6t4!jbX--z#e4#e;vZO9$`W>KvO#w9)i`7WF$gzlJd2<F*5F
z8b1SF2xE8Bk{Kkg&vQ1wPXgqo<tOtIrncW+kO{Q;MLa<lA8@8zp1*6xt=+nB;sE>N
z<@qd=4@>$3*S9dP2!pfXO|)|q==JQ{(I-ZZkLX`*pGmkkO(BXb9=SmwFsT{XuwN|i
zO2F_NfOkcy+fYMJI1*=u`fVTcR3Z0X-3q5<IoZ1=Jzeq|R<$dp5p*wVBWUq_UHiqS
z-3a`8;N7+fC-!8xL;@=)62j$Mp7LA#qkH|-MWctfA;Wj>uX{LaUD&@7Vg~bW58r`}
z`n9L1V>on7j+Txa|G1`tWD4_SLEgVZbLxui{O0q|O%nPcaptn`<)pwsq&BC65>cv%
z8$#UU1a}KWXwe%pbX`ic*zdc}K_~gGhNe`nIED}FQ9Y~FwR`8eO6}10rku-{*pyXU
z3)@HU>kUm^cZ6wYoC+d2WAIX+aV-3lf$R^ZWdx9r6&i{Nirk7rCgUXm6?XXP`S=aZ
zvPT6Q_+l_`OL=~43f{vYq+4|Eoum~qp6_NmnLtND!0&tg+}KoTJZ3xTV!Ru?8u(D#
zIKFCyJ|c0qPhe`ta;!g`ezZpnKrRREQw6NGX0W#oxn57C4!?%qq1Y9lae6ZId(&jz
z>?~f@<6!NWnvReNsp=&{f<ZLcx;ynVVU!NrYnmn<%u=cQLL;w5k55}szIzj@=_W7u
z$*A{z&BY?}VwW^MS!J@GEeu4qcp?F^u}XvxYBcC*l{ziO(XN<mL^9!xl%gyvpQhn#
zYt-o;F)+`havJ=mw1*P}ZUUthWsTt54bAS48)G`kh}LUlXH5m!1aMx4Dbr|U125M>
z8NYXyz?8WsbeKchk55LlJ%1M0lgsk*ZC*RHJ~sb;Bdgqg?^IMv*^{g$$Pqb?mUt;%
zl|YO26?`J;%fF0myJtb2FV!)W0I}VdOu*g~OZ~kmtBql?oxj5Tvn0Bx9V$ZL^d`z^
z;}wbS19e<bH8rp&_Y!0-I=aOH%3n+13k?>{*t)zYi0FRx-x3;OIiIxOe0_|#YnpDu
zi`34|XUX#XD@4?(OoZAS6QNuhFo=w(7SNx}X`A$STPH+WOqBK00D;fvR{}!UA6W=4
zD{?#vy=W75f;!6a&n&UPrG%$vN7#!SiV`*J-8__6g4C&jt)Lia9oo1gaDRa5k&$J~
z)8zqt>C;cu-^b4%kY&%lkueB{6I$Y}vi>Q&z{qt+Vv-E_;WD+(x<CKh<jPm#`*Ply
z;^YWr!TBR)@^vv(7LEHJ4P<m@*Z~fGbfX^Kd05SQWdpj0Xnjpqto%h+XQpY{?}Ao6
z#Dfr6ff&iJYO<&0GpHXVzRTMLz?o2-M%Ov|6}X%-=zXz|sQ?;$1FjZVRKy43dMU8d
zmJ=6Bx@q!4DArG1925kt98WJ}%fAb_-bjQ(^5fSv6&5ZMG#!AWNLR1+!r^P0Mj$aw
zl_m5&Z1`mM4#tBfnSZ2P$PJMk`b)~VLp#N03NP|UcVDjC&i>GGx_p03A5`(o6h>3?
zd&dKhI^@eX=-phpH}dyYGFx)})E74UOnT@<5}R`@^zD#HR*2I37M`BN3m@UE0tK!s
zsG6iQSXp>5TNv&Vh}a*Wcj~^!eG1}KaY8&^h<3f&{_dtCWx9<L(YoS=tM@mkAH$D;
znqR!=PMxgO=%0iHkjWKoyG&&_z8|_i=RJshv`qgac%<0w`}Tkonj1O(O!Vrr8+K^h
z+kpVc6Z;J=xOzK}E`^N*2?mo>?f>9htHB@qHuCSeH$zwx0xw;fzn0BRE?o_JV{=+^
z-rt2;)q4%K_8_)8^fS~?jTTZ0L9vaF(aJIcxEw9kh9$_gzYcmgi<jL)6V?Pl+?Pdd
zjJKL)kd;-ay%q~li*F~`p!)U>v|?V(TGPEgbH*46ZpVyITEdUUAf<zXd*kiPH^b<m
zofnjokP7mX%$UocsMIOtq_UsoWVn6Hh8X^l59NhB-P#DCt3@SW{E58h$miFET$7Kb
z)VB#S@p-L~8UuO%JFvxZIFtgNK%r~w*iXD^$LNbC2$?NxPUmdz?L%1PX9xvYvB=0M
z=1;zwbf4a-S3iP-TNg6+1E;pP<F>I~4v(M}a&*WImA)%B!r}fACZ)a2ZA;|fnrU|p
z1uNDhFoQa{ub0XI@@=cx=YbzF=+jwDV^TD)?jp&nm>^0PP{W*j<N@-2{Fbz|2b>^C
z`x#xI<{Ko|agJVXmnk~rUbRX22=Q+96=49A_A_GV?1_Lx8PdGU$hhUcL9<AlQ`AFS
zEx)l8{&-^<2eM0nPJ&3^YR}TQ-F@u-KJ10mLl1pE3LhPs{IjRrRmL_b#Q)Lo0DCP9
zR4fJHlHgf@T8Q7LK%qDE{yHmQO~OWmOhivmW!95p&aeEYA`O~sVwXtf7fHyNFJF@^
zz@8*E?hhMR?TOATNlvMYjdO{)fuf>{%-GaR<DWc7Kj>*uMxHDC)NqnpN5JJ457hBw
zJ+NRCUoWWWAO4ee178lRZrsALjC4tS*`R6-M<hQDzK_64?WwgSs}sY|Na|}f_9+tm
zZf@VWvSoRYwZ`<i+DIm{TX+*+0#s~XvD0gn>pz!q-xfY!`i%N1q>JcrWvyzxF^N}Z
znB=kX|7^>OXq;6fmMwgaPD0AFx)Hi}Vk8RN)%x$cSP+%jf%oFulawV#A`ze`Ew44D
zmU$M7$96APNG=qn?14BsUt)9?>O21ig*9Eo!_J$8IaY=iNW(jCa&Z^>xe~rVW)2!X
z->h{C?zCSTzkAV;?o#p%hQ%I)>3m^dP$<G<06OaY<Qoy}v7PcYl{Al^z3bFcAi4+Y
zxOopijLpykB=!|n$TQn$uJW4CIRn;6xCXSGBP@{Wx5#{H=M;M4Woi|Bgh72l*W<iR
zG5}|+<5?=AnMG%ztzoU&n<ej2!~9sN2!(xFinB<l=xFoQmo!R{Nfzq0W7G|4PkqDP
zaN^a<7@b-_@oW`K@Z_D3dD#~joAoThNHe;O>oN3&D6snUZ#4%rM1>vaeovkLC3%eQ
zX_~NAMR$CJ<gC+Ax0ro$@n@nsn`RTxa<GCBZt=X&FLK<mVdS$3y29q=f9~mLGGx=Y
zv`WUw4P&ySs`uRtf8pDH!{G;Z29fZP&2O&$rEt|LMWJ>B*RT;gHM8=A{CIRCxxm1l
zT7Hs<JN*qx0A~?N4+!0gPHL2S?#s4>VmUx~eAfPy^eHum=pQO2Ks-lZIG<0rG2wUQ
z`LF?FRo0KEz#V_^xV^>t+o@k70|-#RFNanj^0(b1bl;<Fcf5Z#T#PpoN+TBt^ZZRE
z;fQ>@NNLVd*I*Lva=jh2UZ+-&yyv1Rd*YYOi+Ht_Af$j7XCSA<r?e9QUQ1XMCo!qE
zKOjC#O=`i5cBv<=15cs*<mi$YrJMbB`|lQGc#?B+yeXsNzn?fXT&!p{lstD&r0fgw
z!ZGG2$ER#9+@Wx1<6t{IY2HxVZt#B@trskOn0@>Zj(+k1`iQ5nur_txhBo2NqtCB(
z+Q=84U$VSx`;p((AXQ1QM>Af<wC5IU*3)#wP8M;!L0wl#Wzx(S_4tmF@Vg)Ls8IJ9
z`m^tJ1tgD%e!H%Fg1x=fr&;FI;|7CGx|b+4pX;Z&BPUb5<X<Yug^EZM@&{~*spq9c
z{L87B4&4aPaDvdA3?xyCPrE}_;hq-JnhjL#rh;)#2}ZC=9S}+9GguT5LGE{MJ#Gj>
zW8TD5uP%qFFK=yO$kFN&2^kZEuortKo^z0Nb)s2@_hoMQV3i1Tiw4^sZ281HAyF>Y
zm~1nz<(8=7K}6%h>5=b~N7r&`u<6IQSRc)fp6Q67Vp4<CFB~^yc!dqhVK^OFwrrmc
z@7n@yYW!RgJcre8mv5v!5D~{x`7Pd)n9)6!t2xa0<yX8L@{4;wVYd@2gU<#`7qC4F
zQ+QP8zMKNhhSMyQN4N5;l;f`i@AG76@lS(16x|Zno9q=wdNuUl$iHo~-(CwlSJ_=8
z0#pZ@6FHRWH1ldnPwOWvf{3&$?+Ki4BB5=ceO-vwBV;|v`L}y>Xe%gtsz#95s+oGW
z-jgaLI_>jcmF?=CUM|Popyk!mjx3;pC*?DmDg5V<iIe%QRxeU$xA3c{O%ox}><<2q
z*NgpWfSQ>aZHOb&Uc;!(<7YXUb-_xXp|odCKX02gQF-_<!|_f5s~~|hm}$f5C8PXw
z@Y57c&5i*=G2tYbmf`@f7bn%#ue#Y}4DXaKq$`SE5mx~g=PK<?=vAM|f$t4(FS3#&
z#wo|jpJ5Xq-xv*ET`5)l>Ku1Z3#&8jyYy_XsxP2KJWWI%_W2W2$9wc_8sfM|9fOGa
zktF}w9vxh&SB=ILH4?N$<TF>g+WebGn{V`l9zoX_S?p%GO_;Dx4xElV#&P0QeK-lQ
z-@)MNG9C7qQRpi*OVoMHX3W&0SCxuW1^LZ_@SR;Gx|QwkH7k;XF}C+;geYabB6{Pt
z?n?)<5&Ma<0;Ww<w0|F3H=M7_sRC%}4u@os)W52;Ss(K_WjV1S3n>*m!)NSRRrZJI
z-}MbpF%6z3#@mx%Huj7C1m7yEIq5HOM?*4a!*ybQbq0ObjzTa!Gkz&U2e_?85aTN|
zeT%JW12q0vO*blZujonW(zDaD!tgAtRjTZNe^2my@Nu+Po|tG-6V!*qu_)@QYd?5`
z_Pc8SPWpi6o%D-ugS%w%N?#`$Z<FUfaxIFkq|?}q>?<=Y;3jFNn^VqMlogvdJ*t4+
zj8H&1a}g`|&r}Hjpu9mtB}H?EmL@i5=iL=&-Gg%ThOuLtzfas})$G7}O37!t_J6Br
z9l`bkT2N}GO~LP#49Hz~k^?4}1^Xixr7?L(+@o*{De4yEoaPRrOTX$*c#bYzb$ekn
zD$J_P*B7#_lH1E<;L*IFWmZ#Y@#c*NwZxC7V^BdE!#7MhxUIfp%q8%>t3p3-c+vc#
z|Ng79t2Y|F;uV3&&2a{$CECEv!`0H|TaI^|PQ8>9)*%&R<FCZ+GdgveVH>H@T9A_#
zSakJ}1H>l{3yb9BCS^Xqbhwa>g7mf$As@UzYXoY+Oo2^c$vDJ5EU=FIZd03`n7F<l
zjHlyD`lAbvk<;7bNBIuB2wY~i{v_TCNLDe(V8}T)g|KaD8k42Wrn}2$FF)M<aOkL#
zJLgEW+mGLDq5`Z4ZQ&LuVKQ7%NJsYzt>5jy_8?5?PvH%GEf~MpTv4?Z&3PO6gi#wi
z`jx#)8E7O&k4ViG^Q7%U?M}#BXUR^Q!!FzA!}j$}g5}#@qEmqY-1iH>3G-$DM6J9K
znb?<;)ZP(DidDaDeB<G~MR~1{9{$xUC8eC3DuK3^*UvwP?F?3iX$<r*FiLI{*&r0h
zj-FXDC0MT^=0jtm(Ft`+;?LVR7}K?^@z)Wj{najQZ^F?}V*%ys)0e6jV$haCXphEy
zxeN5fxnZGNGgp<_YlDSuIZ59z$EO5})_R<y3K*TnB%;F3$4$4gZ+=cK6*bM)xAboq
z+>XK{Su>tg+INtTR*-^2`_>suUy&Mj2xG7mT73y7qk%*%#e{(Q-VQQ!2^~-9Jz}Q$
z{><m6z#|ukw%ww_W^yTUnD;y^g7+{nzW*_;>E<-hOS)07bda?nbhTt}af3bs%`Ioa
z5NIsUxjWO-&(ETBkH7dSa1dXGcjIUyd>b#l%q@qVq1h8vLhjnEw1MH3eh!fMVD{>>
z_q=8xz2a_zxLBlQxJdS-zz?~XvMibqz36-O-_b~>jE~tMJDpYeuH$QFn1ie<>4YMc
z@RHvFTC?VqdXsS4arHZDRWP*hC3AAJc<<>aKe$rHe(ptnzL=E1gt3e@VZ$a^K8=UB
z(r6Y)&pdZb+rNO|ii6JWf?b|gr~CcOsnjP@yI#8aSzFq8oVlZXN!%*u+$C^^T9M?v
z$=&)EpfvlRq$Y|f3|t>)I(Q#+VSAhD!0shwx24-du^i-3jwc)Xnd0S<6+Y7&d5N$;
zfIJCvS0r9ugc}{S5VCDhx&n56W1)M8MVxw@4EGnI2>QZ#7G%}YPY#-P^NJ2J1|aAZ
z+6!1b0&mEtFyh3mQ#?CRGT1i9HtdgWo&$4VUj3?LU_^9hhRh`Lz0R3!rE+d(IS^hj
zpLw;mTZ~rX^Z4>>sXmgN6ztrpqJczXQ8yc(rgA5c$vl&)XD7W&@%XxnjgJRim2m9u
zz6?eJ8`(N%n&jNBRBRreKG@Iah08)!Qt=MqThi==BKs_$C&RVyUG<oFPe_t3YqQ<T
zGI?@28|QX*E`#-sR?|(%9|+l2C_NXOF8;&>vVIWo$$SuMLNX=LNpxKNkm?uKJKA@`
zK|Oh904i1+&vhxRKGvM@HhW-(&F(Ty{a6IxHMzt=<dQP6%&_92?4j_Psc!ejn41|#
z7^KyX8A)zO@UpN-mB8UKPWBm~nqp@n+650rloGSA>{JK1@TiqM6E(2=2vPylXNL4E
zze^*j>m>+D#qUmi-E>O6vG>rnG~!oJY^}7`;HLZib3|oMEDcT%-8j=y1wp3Rsz)A<
z5;)V*ksKAv;`Ust6HDJ2K^i0vloh3U7@W+2B#s8UOM8ns^q^bpXU^sAgo_DbvR2ro
z4G4)uZ#wmf-CfI~L96MD(VOpi?m^jJ)_(a<t{!_6IzSHMY!0v(*9<OFh6Y3=0k3HO
zLA=kbz&+8UkM&<gI!91gdn9`j)*M0QpPB~@%sHf!WDSj~2XNmVLXfg=ReO!=oxTuz
zEZuoyZmMaeW>BL~5Ow;yrttOdr<~V5uy0LLv#*#mjF>MOr#7I_=N1Myghw{GD>4a&
z+~l+1rv;$J<^_B`pZc|L8S;0>Ii8TEs>#npj&C-etoJxi!E+H%OlV>XgrNgP^8mv4
zHR?F)%ZPQoDn5vpw*I_p@~rI@HSfzb=k4%Ju{PykIpadUxEN1T?BP`x{fl<wj0_Fw
zt<_nLiO3l1$UE3Zs;cLJt_ef5(j?xZJM;ee1MpuE4T&qvr`zP!;i~CMFp%{)tFdHM
zE>C@*SP%(rEA?o|{{&P^*Zxr1(Hf@OHzX7-G?cw>3u-X8X}y?sR<i9}Z!nlz&%*yn
zglK}}dXtGNUlQ2Y`nHo@VPDp1%9Q}U7$bi=SLjFe>gUptkHnWWf>w2^91uF9ahIe<
z4?E7MUJOAfRc#a70)>QrfG^3?2wI-l)=oEXq9xO_X;=fikP-#8!fB|)wRh6GBwj(D
z;NB5QBdK+VIM)eEZ7RDSH5qSbUz4ai<)Hhni5#0CGE>GPTD&zRb*d!xvx{bu7>c#W
zg~AY>X4T$3dY!`O9C7RNgDHHM*ln_L%@ixE8Zy>T1pOc5T=9@C0@sJ1{&?6a#$^)4
zy3k72R`_HdlA=Ht6Zv1~rY=13dTnqb)HVP4<<t3!SHgBHkUnNaTCbf+e7neP?Yhrd
z@B4e7%;ATbT_Q@Ci^!c%U7%?1l+kJdVwoSPXYEsoP9-i6(}j)R%`cR!+TXE$3nsLg
zG=E<1OUPIJ<>H{yuen;uj%_NS-Ei_P;Djv21j(qN1r1+H`<@yWIAUiOeN=O^1JXb+
zsdeX$Pr4eX-x!J&Xl1xhxS8;P8f)ckdv}aDg_&YZd*IDc#Yh$tD_d&%_Ep5^Mpc4u
zhCuPBA441bQu}no0%>gud7{FX%sugQc0F58Q`FZUUK~n==4h~r+`By|HZvPtf46Ho
zJTfm7jcxym2?^<BSdP4W(y(bw-i5~JuQX4}`<r_Z)s~|Xc-PjxpM@zxKuR1+2R4oY
zm}{?ZY>jmXohHt$ASB=?X*9-utx9Qu0tk;jXbZ^{;_|ug(2UOBuM)!@mB&84!jt3+
z*SKjnH6hzj*gEq!<E<W~YnI+|Hsm0d&DL&*yu{T+6TFXu!F}_MGD+W8Wl6x`GyXHw
z%?XyDn$RQGHInaUWEAsbbP>sXI70<khsK*uH$G89mb+Mj=&MRvVq00mY#kruEd&&m
z^_a2gW96qlbsk$?Twq#NZOdE#k<>KTW@Uc?Q_s{4PcUqSw?-@^>4zq6c4at1&j#wZ
zI_f?JN)VNgFO7S~wto&}LU<hAIm+gLF0zM_3VDHd)!z!&8@yZpv$>7Wna}<R4x~7z
z@zQsLi3NqHXqgry{LU2oi2N>kfH|bYIfC(Eb!~)!UD*wwNGwk~kDu=lO{rCj+kjMf
zx&72t6~34}erqA(AK2|!bpmqReYxf2cJUVeZ&2E~1lYaZMlij6vY_5qdIn)&Y?ewB
zo4;eTqFJZQ*rad--Iz1pk!dVOnUdjFyyfXXrOfe1-rWWs7ZCG}m=CoTgfVlfm^PuU
z-fEUDzfEZQI*y%eyo6Qy>t93A`+F!go;LZQ$!>VL>?+t?e4b*!1QJ%9|8Dst?OYI1
zAUnCi<-tibUMU}kcGtpxw1Mvs-IE})y(vf+&O8zIUpy90n>uS<YR(rqJ=*QQ-6vgO
zqz0MXf4s)W-hD>soE9ZR5??n&ON(ZPa%LB|oH7-gg1)rLL+=RujzGYO_D7K20vckZ
z1_AGlY;NqQ%-`8LR<H}wnu81nA?t<Wo@`egfz5AI$0&HCP2;tttt^B55~&V&L+vkE
zm@DYvZ?bz|zMez5B7yQPBGV&P@3$)-1NGZcXj`+p!KTv9l+n#iRkKJREn<A!oq9~K
zdZL3_^qIvU9grV}^?8OAyW*pvO<HnX1f{<1Y)wuOg@BK+|E)k7v~9Db34XR0o&4&?
zY5<;kI12jfaHt(kDG0fpib~fdSo6^P_WNCM_7x$zQ(^7NX`eh@oY20I2brL76p*s8
zv9-Mkct;D!X>hpviSKm%ob$iQB7NW#=c4tjrdNtIgP(RgCh?DaLE{S=LpX$X1k*YK
z;kTc;xp(5L-Rp1AV!I;Uew1ToF6R)P6iVByfUfRV^uxxbsI7qLs{5$%AOh##k8POq
z#c?`m{li8Iqlu6|2ewEHdlT)-t9rjcy2}v%z-iP>>QqVrcnR{D5Q*>W#Xw4UB$Tk?
zNqFYwb!NPeyQ|AznIwS<(x?wjJ;9koT|*JuA2A6)S%(q4@TmtL*d`vX>jxtw)VQ@B
zWlkVU2*o16dPZ}?_5{(`Pm1H`XF|Vdce}p=F-sZ*`nw7;DYqJ<tOS`**h3d8Opx_?
zM9-F1?Uzhp(5}V(w?ZkMFLfABKF3=KW2I*&@QRgH$L;o}@3Njlsz`xEYy`lyFm_<b
zTM*wX&mqF-KY!XP5&+y&h}CT~+i#^VMSOqQx;yMppc}G9`rIdy?cQ2<%5)eE2_$qI
zXevM^?ARZOo=v$Ut{x7ANADFdxC1TCo0c@M_iP<lK9;?Pvd-&hG~YzRRko~c?A?UU
z(T~vBezBpZI<$pC(+$pK+I>H<+s1r}C0O}2a4n+rdaJV`bVZNbQET7>FA9r=s~2#7
z_{CltxDl*#x@9HQchH1x7OWAaphT+kUIg!tC$od!Ivn|cVU{sr{aSV1L0)&n4J0lR
zh|iz2^$!07?;F=#^XXcCk0VGtxq$JbZEIDPhv4YAaQxB7UvimSJAYqaGy_-%nNg^M
z4f`(eB{lYIB>H>CQYBaAc~l~b6j;tVEThILNC4o{)-;DuY36(Wr|=8D0>J{<S6QiD
z@6&@L^um>!6^GHmHq+4t;LJdBLeo5FDy_=1GM}&h%3al))A%RH$rNt(n|V<c2~c5h
zO~F2W%8VyL{0c9WL5uFwis`>IUN>v-XDR)ir6Y4PKRA>-etI16_ESLLtzLYMc3*8-
zP2o?P17?~Rb+;e*kxG|Y{wC%c*L1FZ5rdRI%;dmRrxWI>NvF#&gi448tXmpx*pQd<
z!h57b)X*b(&F0^DGiy&50(kS`VFt3}{()1;)1wV|UqX8fIs}OPQq>*YDU}DfLklMC
zvM3Je8$P91_*`-}2D@xXo5&4`5;xjPpJ6?>oL--8A~3biVP1o$`tUGK)ERcAsNDr%
zC&f~J$ru_a8fZ6u@|?*A)WanUKG!QZ_b9&Ywbl3rw?N`&$Z`Arr(G4sYuOrNWetv+
z5y_Vq<H@lql!Le3Ic`bheakdl&Lgamw%DI#FHzDe=2e=|yw|x8!LM61hRUzLda<(=
zW@FAHAD2RjHqSCgw1%=quZ+R<k^lO?0EGd{RNSi;^ThA;U?P&kR)I)sEE0T>c`*sj
zV{2Aj2~Ky@fjsBgQT6?^R;IUgS-~gD+bJHJm+x<Oe#PLJD+*lJvaGx4|5b<Wv%{{x
ztQbj#8Yrir=nw=>WK?(M)q7{zX>zpvQ!y|}!`=!0T82s6(MP{AetqQq$Mu<S6RCvD
z`RviVYt{!Pw-XOc#FC$Pb^hgYrvj%@G~(ssSJ)}Bhd=&2$UjIkW(8|Dh~z&|6OHML
zE4SC&!d1i5%5<b6XRA(?;%~~(I$468)NC{XUYAvnjx~0edv1Zhw7!Z_hP4lVuo2Qb
zfk>e(E!`w#Q<ATx#VB(V>9XP!P}p&ZI5)LRh&j>P=1%DTZi*a-Ryoc;Ff>u6j2Xq^
z&)|3wQOu@7;5NkQ@lfjE#_MlIp6No>*Y&X5s<fSH8=Ct*!NhnuJwx27<PA+$QGy&Z
z_UVW$aYFan>rBVH-=Fs5pVP1K?bl|3Z#UD&+}esgr!8f4KFkOTkBcC{0e?u1Ce+Ni
zpxEJRXz^||KzBF^B1f(>WS)o*3w^c!Sa{#VD=7A(8nyKqR68dasN9Ir6gW7%7Y?`-
zkX_6m8TvUlw8j5bter+WkQ-9C`x<=X)i;Bn=p{7`<;yMP@ZvyOAAAClybWoUTAumH
z1cYTH<FZP791+m<?vws=_;sFFw~O9yXfo;&;72mvr<3o<-*bCP$ZI-NU_pU>u)#j~
zBW(xL{~Fq28gF+;Rm~BVAPhd-f;aLy-HYwYKffedF^p24!n^?wnUiVidF3mGTa<oa
zjiPd<mo0l{k)M)|7)2#Mc-e2=sImc|bxw2KF6h{b!0Dj9sRr?1y4>X>s_uTZyFmqs
zy@)_c{wk*WDE_z4B>#rN?IMmL3h=v_zu5jR&3FWT<SlqhIkNz!Q9F{HVDie27;Hy;
zdq3Ir!Nkef4NY1%f*d;-U~}f*ee`@nk^*}M`Lv0dK&xr_1bd4b-N`zn<dY9t--Epw
zO@}I3Jlunf8eK|VQ$zP@j9oeNN`kNtZ*Ym~pA=om!LkmNK)Z#x18#Oj-W*80{@8O3
z0SQ8@KQJHHrIU<Z2-fTPtDunzpvG4WaCRr9Z_dn1-!B05N1Ip3o%5+wY`}igmhvp7
z<(0IbkvhBw7Al|tDr5m$tP+csn`tNR_9akBuz-P+Xeq?}X%vqbQnAVIO&gLJc`^c1
zy7LtYH8ZphceVZg&E(j4XWvN{jLOAD9FyG1E9~V2B^pq8)IASXp28%Ow=gVAJ7woR
z{6$_rr@1V+FK%6Ayw1OMt|@Q|bCQAydk!^Djg<qNI*qzh{G6c{e{`pAuKG7<eK~2z
z^mHqqQQ=mAZ9{z7GwkR&V$(?>%&+pV6wt(GSxp!hR92%BN<F`SnXL-yW&wZFZIUSu
z!_qVPTbS4$CvN+paI1H#yuR@Xpe}P_BcVr;tz#F<Wg9U2U;Ebd4Me8!?NMil&$5t{
zhY%WAB<Y>DkHhOoDW>`{XtMzW_t(PUjf+dC+4uI%rFJz{imvnI-*%uR-YxtOZ^fhy
zrztcyBt=y}bXeQ{ha9&qUFxrVo%yNMkXdm3Xuad19ya^3wAz);VJcG%yEnR`5dV+3
zbvP+Ml36{O2o2<95l+^t4{k&vO@pbvna=#pD&Pa#Lv=@$M=A^ck&F4wIA!5(KGaPP
zm4{;GggFh7^EZ7P4KGh?u2lu-j_qeT?G7N<Ke7ScTN|gE8*-`ON2K_dZ>x8vZiT%T
zOcn%ge5)p{TiVXpE9lIaiQJ5JC*R-&NOVVu=>E*U6<S5E2WaFS_&!gr?zUA$qSaB?
zxVrAoFO83xN$I`=w*{a258r;xRP_>QtTtdO>?@DuNbkKh`qCaaxig~0LHtyzxUpEW
z;=yUoKfhbMW7#_I&v&r=Y@eh<T-DZB<av8*lwMr7egKJ^f7n#eKdZS^rG6L|mF2?R
zg3&68A{2k3gkOz|-?Lv?M>U@QU6K7EpIO1{=j!rTz=QZpOt(<#%1X&)%Dn)isJ{#h
z#O~VY&*0xJkLa~xB;BUJY&e;E2twWLAl>+{L&@+B-FkIyu*q4A=3Vc&jy~mhLLu)y
z1+NJ=>ecZ{bS$uc3N@Cd?0s|POoV#1JN7Z9K%?rW>~pPOJ%7m18`*L{?ytLxgu7l;
zkpFYuUB$Phsz4e5iGyyn)?qkBDtDvZ<b}36q^BV6jQYFuihK9ewe>xB<b)>>0;^Dp
zxBo9%bc_0%LAo>_ZB%9`oduq{uu4-1VsDNw=7DJAq$mFeRbL(t)f=||%$Tt+V_(9I
zC8Ut-!i+5;yNaw8(TWhV%-BMNlC8u<qRm!HS!PI<lr2$_eOC;U!I<+qec$)}<M*GB
zIp;p-Jm-1Nb1&C*-4H<HJmrrUvC$N7Zy*VykeoKTh(Bx4^i=TW8>f12*)DwLKObw3
z0E8}Lx9Mxn7PojBzAU^uZq+MHL#ZkmI^M)po&<cPSl6MLh*NUFYKPbe<~gEI0sj+a
zQrV{lh7G?IG@@DyS>Ek|K9rU)hW2PNOSHSakk=KPSWV=?z>P11A_Gt5@9D9V&>s-?
zbu8fic*fUk=f?eJNqZX20vCslf9L4>f*ybHWDPDMsd>h{rx(c^2cSEp<$fU=>Kh#o
z)?Ki7U**2r&7z~@t7TGXy&yvCN`43Rd`COYmB-g+_x<k5!`T1aR8-ZI(;xwZbCbj?
ztA+f`n*%34ONIt&F^2>|w+(CY*B1SCf<t^PpZ%sev?h$}bhmT(%{ZV{CA5EqBX*R!
zg-w5UbiSa8?I1sNyfk$V(*}*3crm>!!K)r24)7hL)cst7v0o8H*;I&td))lbN^I4<
zVGqYzF#|lbXd@;-!d7gGph0Dd_~(fP^z0H+LrX|2e)>!{!0^OQg5JN(yCB)=+{p%<
zlln)K<8@+~8=alVgB(z(uOJd<`^3^=zms}J8zh0mRTilpM?g<%Pj>42544C=){+k|
ziAUP(NAc~>BE~22ueK6paIgFrc3Wy{_d*Bp1>2`obeQc#|8-Fsaa^3x<{V_*5zzWf
zIeTNz$}3|1QQVHX1FLcAl8^Ec+b6tYgY(?e{|dguPsH=hO<YJQ4Z2t;xaBoxF>!vy
z?D%-4620fK{nveSCr97fPS7jtEgLHYLH^l1+3nO^<HW%<NF6HOoBAMh^zDf$D4&5f
z1M*z)YXBo3VROIy+`5kI(@p3Z*VV8s`QvLsazp{Q`3fau0_@4c@h1ABM`qdANVs~r
zO0-9SVbgC%)^z4OP8=4QJ+w`9c;G<~aJbcPuzg@gcYXK%r+>Z?-<I0`6ALgm`f6uB
zqf!ne2AH&+KN#H4jw$utY|)O<UW5z-=<N32yFNRnt<%*~!NYx1L@LqsVQj<{#Nj))
zO1TMo&*Clv%x9%br}-a_Xa}sFQuY7v!RiR4<_h|^?i<euc7!WHa6AZ~O6egwq<mca
zx^N4+Gyy*z437=KcfEMHZ)9yOdE;T4>iHWOV2-*}ru^>Zsxvbct~_+oSJu58z0<Sa
z{b?h<rW-Ja_(_xdXfd)R>*ucS(}F5)r<co*2*Bxl(%0;pcXX3{5045DTz5#$+EUAB
z;ZhNYqM2NmeCg$%VX#qG4~z}cAhqku-Y$KXdCqROLCyJAliSxP6edgqe#Jk2tr#1?
zNWi{hqkd=LkAo|pi1{xH)*89t*~9CzO2i>DdE8N!30$R-HNHZxxc9_4*q_)ek^vuO
z>>Z7BZ(LY?duZ&?&Qqt-{+odj2(jCcthKn&Vz3w_?(P9D{0`X1MsS;0(g^83jsY7I
z<vx9XH$Fak_T4_tq;WFEdF~|?1fP`!9dfGng~wO-IC%OZ_QX+zXi1lvahzEW7#Krc
z+XD&v?DzF`7CP}q>=)6%_9v=I1@e9T=<!RKBoI+h$MMM^`;k<$`2FX1RL)UXLn-Gx
zwjq5tV(6jY`LQE`;O<>V!8s1<tu3`f*?IPU2bsB328eOz??o1+>)pQz_nzOmqv`v2
z<nS|KR|fkN2c<H|ua6EK#H$GjO{I~#Pa)rFK@$Q(H_JlX=tU{(IV7>|`VDMV>0qeE
z#QR0{{8^N@hx|`7+!WjBLlX~%#gSX~CE~7$B3>C+?qYOpfPZDhXXp>Jnb?}P3Q4Bz
z1H*#?zu!IQ_f_%G&F8(=Jb8J1e0GV;F!noG0hkkMCtW+VZ|LymUCG3VIRe!lB4c)G
z05kp$KAC$Tu>EFGV-_V4bjZL#4AEsz+_7_C_XU_#l+&SCsD__+>Qv1)5cVPO*R{iP
zJcZ>rsfKju8x#H_f9$z?i4hQwfEgpo(JUmRuh}%lh8KBuiJhQ@2+Yj7m*~B(=JSO3
zd#zvkrC(bjB0+*R=jJo{+X~ORh{spkAZ@WgKEfAyEek^8V|NK;$k+G#NDAQZM7H4e
z3**$EFW-A#*q&w=vjejels4-r;+_Hp(2v&WhLkNY<Ox7+hjh{7e$+yiD?10ae4Vup
z>6FhO;FbK#aY&mDi!d>5BdS2VBW+MtW;=8a-h?i1TeA|jv-_NDz3R^~$C%;8h{)nY
zW_qX+g^;>ye-F?l;bLV{nJ&lsHt4agHR#t1931Hi`jq|SuDslN<sziwMZ%+un3oMl
z2d;l2Ng2l$WiXzc&RF~f#-;D~rmuQ^Cf?3ygI;$`5@*CoM@`f>-@d=<$uUhZwHNuF
z>|^+ukK}=vmyl;Eoi)Ajv+>Ub_t)1RnPrEGz#+mEWGg)dJ<+uUgDX5eWlRSIQx!j`
zBnecuE4WFe+wKtdnvmh+w8F^F547_OQO$dx0gP@Ct2ZNTM89d3qSY+`{`!VT@RUcY
z9<yJ=d;^(7BWj{rTp_$3>AcvzzodkIRriY;z<{`7yB{nEnE^8rP-Q!GYK-;cBBh+w
z2mFFojRY;9ocWgj^eX>dL|!?Y)3@?qn(tsm1N>}(_uy(;KJv7hyla;?!*9!LX%mbr
zDek@bj5-qBH^;5<>-Uh-LsJm)kkzfNCdy&xxnE^qK^b>f!N0Gh4l_5eQ3%@4LAt@~
zEIc1cdKLHEO#pNetlcN7EeOS+gBCA!<~s3`OeX)iA3?6R{}2Lupwv&EDKM~xtcjcl
zq%A%z!NYA6SFG9zHQTasWa(gUBlGk<QSMtyFNU|D9bRU?`7OAk@gv8-fD;aMzAw=z
zufbhI=gZ*v$ztu9f^mf(skdeky=Qq3D9KLUPN@k$hL<?LU1IA-dA#=f`6lesai>8$
zr4w{7SMafo@JGQV{7d3V#<dsxpv9H8VL{Lf%3G;R9vuB<5uva4AKDJv2EEh!Tkw9B
z@(wgu&*|Eug>+(_M0YN@#i+*!eVu}O<;WF?Dsjw)@nUhEpMvID1`!s|m`&zMdk<|R
zakFT9#0Q%?9`m`?azJAW4ZOU>YH$>kZ@Iq@c)G^B<>q}H`wwzdiN6J9_s44=nIP^#
zbX=6Z+dphAd1+F`;)q_SN(?)yh>D5Sw*^X4PbPJY>{WFw4F9Wseh`PM4}VYOkpmKC
zd@B>6<KW#OZ1SOKaEaAKqYnF9j_jX&qqJgHyGC0wTS4tg@?P8&W!39~WnirqwC6Ke
z?0X#p9(6Y}*Mhx8#e<k^qYs|364K?8pA4MXK2V^`dE^^Po7paM3#xmvzBOhB&Rj{h
zR|9zlR4UrCW2j$B8%|b!Xwvq_fYA5a3#QaeOwohEfBQRh{U@DoZ<8pL#1BGB?K2g+
zWnEZ!L=Fd;j&P|@H>ZXg9djw$eNGZVWX`Z(xw52qG{?HA!RQ~(Y4dO!RMUzKR$QlK
z1AjU2q5<EQX(`hM^>P>8d!g9$K=8w<z%11_ya_BxiwatQ^I}Y#=5^uXIXv>df4gUh
z8i-zVpw9W-=@QR}1ccl2m09CejX+gi<jPGsj%nJkA+K=<r(O_i!}n=@?TMpTaPVhA
z&Gi-}a39{Se{z#A07;cs4>Y{xSk*3SP}}b0?!DypCL`^e*wuNR>uHBj{abw<OZo_E
zpyND@Y5#nN(PO2e6Db1i=?0oM=9MwA2h7X6M3&-+(_IOk>~ICiFe)#J?eeb>2}DX;
zST@hOherT6&4bWJ%r9vpJ`nv)AF~C{`~+6e*sAn8K^_yi;OVus>?u54M`4Y_E#3J+
zsp4C3rv>C)URTczivyX*jI~%_;^tqcD_Gp&rd=kt5f8x7vW`m{OqjuHjv9CKrgN_$
zUZK^;3@~H2^%umy>$12_8@SM;dZi;PBK3@>M^&}M-$?INV^TJPk>jrGZ}=LR&C=@D
zM<1%S5n)UaOca+vF}xu2FSDzZQqaIfRNx~%AI>rkJ`&GKZg?>fm1QY@=0H4|WhcZX
zXDd*XelcSo{&K<5ZU^!)+2&JMei2?b8w4U~vvNAf1Q>(9io6BQ(Y)@2*NKy8*+=DX
zC7irMj2aN*6#cvxy>iBTrR3B~JI(KzpRIXT4{u|r{FC}~Z*_RbY(3MrdtpgA?f)P+
zb|U8)0pJ#Jo*}v+Fb@*n)73iOUB1nK{-kf2Q+X9%#31h58IS1$!KbC<9BPMnW1TnA
z*?~oW1cRiN5d=Bhe~WtIkm4NW(qnRh6}Yel15tf?<0^da-o(nUE)4KvVtzdPs29I#
zST|XxSKH>+9BwHEiVDl6krD`M8Tjum)DA{O-AjX>olX=L7;r&KI0Cx5y}tV0O69e7
z7RH9@NHTBVm+;Ri=n39lsiSh@@q{TOHpGGWH7iXPe;nd@Zm}T=@eeFfXCfShW}0qU
zIha2_;*OkDZ0-yRh<JBQRZU&Xh4!YS+^3~K-6TF^Wu^U;QZ~<ceZ~0CUJ(|g^;6!X
zug<KVH~-8IE6+%ZCU%QK-{Ir3R=u)ZZt5d5-$O7KYe+@pyrK9icOQG~HIw7#=zS`4
zhTj71l62lm{;-g_k7&47{J<>eN0K7YQbg#$+9J?xnh4`$p2$=il2DWo{!{<l@x|Z5
z7v?;>i5?FZj$Mn^xxqzxM83o-)e!bvCIZ#bpobzH=D-!Iu1`NO14knHKhb-HLu{CG
zM6RnMG;C<I-QEB0q`zfL_#-)9Zq5AGjg<$vJS6F1dHRI>`^LC9nZxN95LM0wi5*fD
z=%g)DGA1S|om384eB%Bme{x_>YYQ9WxLQ<Dp2;Y~2b>J16Q2S}r0S2#*aN>H<7Gst
zdMEwR7n$CRG&x;X{<MuXzszP_LajVIh}fyO2hIZHo&jr%E9P8;Z$jR6I<dE)JT|!A
z5*8bRn#1qw`;|EK;Q(`!A5c%T8CX1GqLLBd)m(yZv5L^4=elbrTcTSLhiWyEW(!7p
zGgn+HV5DI#16lhTy9s%l6hd?V#CLik&cj3tFF~XNgT>l$Z<64-HA*UwKTB@mCk32`
z_`)r&*0x~$IS?GNIgrp`LwI-L<3QO;(lTTU9tn)UMi<nIzm9=IZ@c`k+=ib0k4azV
z*?g@S6oYR$rOf}NC`sZI-z7wr<7$Yq92kFgCo^aDz%$03Kl^3A``ANjW86m9cdFJm
zMK@z-5&Z~GY9%TCAJ9d%pdDfe#5tEU-!nvo^SWRr%{cpmt`FMf?3EMd1e;tZ`4HEG
zB4RoKb<G}TD;!1*WSL4}_;Q<lQi2d%=Czt|nJhtdtPpBd;edP-<r$*iKh6;S5Sf8y
zNtdxIZ{yA-Grtza;l8}&$H`e6bBOCvn~z>a|7Io%-~>o-!uPV@+XpxUdEjrXS03~#
zC5{8-s;Tg1b?(@|K@Z3%IRtGc*6wQbP*qMB96uqQ<xcpQU{oaDTdZSx)nMd>N%n{;
z_f_3}8vizjC%<0OApUhqomll0TzDI76DCC`H6B`jbCV6aX(ubmyD+bmt|lAn|E})U
zz2Jp{Dr+D)Mqj@fZ`ZnJ7mc6^gB~HiyZ=+^=`iGibaYNgl~=dQg^kQn<oo1`phh_L
z(DnnH;EnZYo7s&}$nvwC?MFEtY7{yC7b<tR-$~%2uBY`V8jrzV#OPmo*_zqsJEH&g
za5MP0weFByQr)wu;Qi6X*V=?Xde{Np-I6uu3F1YBu7X4DT+{uZQ);X6YZ*Tm8BY)K
z-R1r=DSCxZby~Be@Ls>IR|()mxM&gXoU`!!=OS@gb=k<w5dTykhBT}u4(%&FajpF6
zU1&FkkIVymPpZMeHYjIy(2QYs4d@iF?kqs^3j1&X58Jgw-eYW)0%_|1yq@#<0!+cj
zhgb0>LJNO)3g12U=6=W4o4g@?)5>Lb=4P$l>}&7vDY`)C)L&N?%hMqIeM$kd=suDz
zwOv#7bYTJ}3bx3u2U#$kbo5~(nAeg}1xp4))cX`dNg654My+;N+RGQ5nJz#wxbTtn
z%4mL)Hj;MgYfwO>+;Jh$$xY8e23jx$KWt7CZTCF~&l{P|P=llQa6YVH(VNL>CH~x2
zzfXOxL742vwzL+LWG)1n#xA4A`CrWb{mrxi{SEPJMen{OLE?#3-vyX+!bsQdIfw^E
zHW4=w>{~1yUXbRzzB(!0h|E$q&PJ04VlSbS-6wP+z7#e+f+$bG$ZhD)PhQ4Q4tZZW
zSxDD{1A-yuS_#hQWIZSU;FXVH?#MU>;rDzOl;`MwB}gI*eHI(joA%C}2PlbuulDHE
z7=~Iy(e0)`<>zgU%rCros$ziNKmOk>ppG7pU%JNo?z5ZFgSc}y#y41SMq#=8fpX9E
z7|+COY@v-1!4|5A!>TR2u{j&1FYSzzBBZ<t$J7_s8FnkeutE#rOmmiJNa22;%uLyz
zXo6Fe3K~;^NE8a=ZOj(@cm2*?CPS_6epcc0w8!#NP-3SEv*gWHSh9sygY$Zo#)8mD
z{+X-#=7bRFYvwjzNJIK7yk1;}I`=`3Z{9MgT<ja8+vN-7<OL*zvc7cbE!JnIatjnF
z&p|3Ea+|W!+Y9+I-W)gOGq<fO5DT;UHF{xmbuXAjo-@;}z8~MqJp_3mg!d%cewBsl
zSG`W!=HMGjxtSL^0jD#qNFB8{W=%dL=iDKMB3q%ze1<VWeTHTi?|LKkv^tnYd0u6E
zldYcDBB#%jbo)P;LJyqNElI|+w^#A+VmP5Ek-xXpI!*Jx(6E&F+aJ|A4iZXV36qpR
z36Wh<z|L_kP|DxdnCmH*g4oNArfRiI=O<g1Qo&<@YJ_J`zr*-vLG!zOQZSJ**s(kC
z&50>t*e7Ti7Fx&Fr+>L%^RQIT`Pf-RX6<qHMT6=;oR>~sOH&a~(bYY0P%ymx<6L0-
zj)J)0xIVH<SN5rL-L`4p;vppNK($cVH2%72RlWU3qERYF?@Pwe-h0qRSrw^=EjEB%
z?)y?6`1-XHI^9@BhBiY9jsloxUxf%Y2sU<Lv)>Pi8P8#;Q9P+cV{QIFdwRR}-aBEN
z$qt<BIKUNj={+A-NyXqkN(jGoOr3?f<I?nGHD6X$uJxiNaA+?*=nGM75d+p_1)#sb
zY~9PLZh7rY$~1l=pHr{0v6|t<eQ|+Z_zIGAPv*6s^v*moUtUpUGI#*Bm2M!68qYFq
zK3;PlDUYN&?dY-D!!j@g-`OZ;ylA#zv=PM7<BVDK&5Ylh)0GGE0PR|oX<c77z7lGY
zOqa!_C!94pR>iXCi=3RC<;k=h^og2W<Rc{RVNMM2K~jH+--P@pZVoJJdg|R9*qh^s
z$h3bZ0P}23Or@QyKN_*~{s^_S>bUXPRCr_X-MPhD;R0!vekV89(;t?E{TXT#`0Ff_
z_=$(A4(Ar5tj~vDUxP%D_Am3oE0lXM?jw-p<9n+OI(|H?E?PpNt?y*)UogG4tWPU|
zQzLgFv;2Flp0ZMqR*LmUErgQ!&oc%63Q`~vMP7h`$xfjAJ~9)nh!=LvAju?bRGcKQ
zQj(#YvcAiO+Gz3?R<Xi@im{)tL6b$H{kc<rA*KHIp$4f6-)12@Y=F)0Eg`A5E@0%u
zVPo{+eT3$r`UUC`J@LYfIP`|HPOnsg#oCmascAPkAHxO1@*@<K{e%L@Y_>=Qv;bWT
zG(pqghpEL&R(T<?$$s|M6PMCu>{VT*GCL>$iPNHs#lyFfh$K%_I?A8>OnhEuP~w4e
zAyUm$#0GeuH_UlEE;IFVe8%U)-<_4|p7(65k9Mn4t@cili@{N0@?K~~8Ej7ByKGhu
z3Ct+>5FZ|Q=&ZT_bBoA^@V8I%iNXcrT#@KQsJ_+k(1v04!<H7zn#?{fF55F|zWi45
zqCmO##|qR$7#OgqU4vnH3@=sw>0?_(6Xhf*^3d&w8vp#>5i9W2&W2xe-{U~eUt{M^
z9(cIQ=wG^-5qHy*1@!dv_0_9%iEx2U+qD|zm%C6S?7~t;2G^nL4JKWPq>h;DoTE?;
zPU?Gn+73`zjwOA(q6}tUD71_tfYhH-9+cP8jcc>bRI^@Fxhpqs=*&2Qid_FjCWP|p
z5xpSn$M9Ntwq-Z-v%-Sm7e&ot-|8vrRQ^ec=7cVDuvf#HO8sx2y8|PcE;ZGf0yWUz
z=M;(XuK;n^jT~MWOhM;hfro=?4zta~Zng{B&2uUzK`hWb3Cg_%Nmrj0-{su}C_?YB
zi2x?;womGx?cC+}nx#mB=;RMIkPkF#e!%bm#j8A)QIE<pp*YR_50$e$uwoS9?bk`*
zErj!6L(0aj#9HsSR|07pf4K+>;MVik<M<7JWd|H^eRDUZ=4CznZ$EZI5xbZi&|HaZ
zmm`PV))dDduF=W<1lY$q)MoC8z^Z;<{gdLZowlg$lm6WCe^>zcoh0iOLaTnWOL8B1
zH&W?6BAFhHt2^?{vGHd(3E^TsuzLH<IVwxooAkwF*4wa@PYTCa%QDdx_N?9yq8N%Q
z0}nvm@1OC{M;t%x1BPvc7dP!u)EF0T{7b?qTUN6`(M4MK!0+<~xklfPwKaM<IcXhO
zhQ1q;cp3O9i-}v1HD~{!!!pULQ%H;?x7Fx&@u#&Fmb?Gxav~(&v*dLa(r5Fc*rPp~
zXQP!ybL&mzMsA-{0GHr+gXBgOvCj%tIx5OLaG;+K^{y9H-?HO_tKRN;m^u9Y;&jj(
zcJV4N+Ij5*+FLwKQ{%zy)WU|3MkNpCe{`{!AJ7>oJ6ntsB9%a83Z1vm<SzPLIx^6X
z`9<}i`K2$JyLZe$I<sgJf89FGVQb7CoT~Z~>3^jP0L8jb>=p-rbq25AEN`@n;MOTZ
z2sP@a{w{tWh@L0@6P4UxlwFQzY+iYOhQ{v3Iz=IWQ|2*HhTOOasqEi2e+`AUYx8HG
z7uK(N%mXI5aG5{e*^SnN(MUw07`6NQ<5h{{^H3-H@zVr3Qay%zA-@gcW=^%KGj}3;
zJ!S2<#r&R_R3DZ|`v@~J?eR$M%lM|!5*v2sQz#o-F<|;=UZd~U85Z$h$E%`c0UL=7
zDekHxyy4RIdQp`v93v%Rz~I5D49Su;nDOB3#rkt_M}B|Q4El*iwH#R%LACl2+@O7<
znwA;To82TN5!(0#Ilp5Gr#oP`?BmjovbZW=1A0V?hjoU?hwv9b1nobe%CgVm!G4cY
zn-^^wK2O`tEeNhZ186UTk=aV~%!l81mK=RwJCKG|jb|KhL8q8Y(Px%=xPV@YQd<>c
z1qZU*3E$qB9_Nc4F}ELg!hn%Gir*&|%Ybv6l4wKgDPOMeiMNM)L+4+{MO|TgntPE^
z_Q}dF_KuFLSN>k|SHVoE;5?#j2AV;EQs3R!6NTmh9zi-2m0ItVB%OEh)tN1!&E6Gt
z_iqTC;3vg%RYHHHcMf2Tnit`WB})l6lsH(j<mv?cm-~(YUeyMs1}{{p2<Q*q@n=5w
z__(eDT|dSL;S^g#>^!R+`Fs-(mCC*Pb!F_O>jNh}j6tK~zdPb%deha^E8d#QgUY>(
zxdZEBdC*Bg(qO<P?2Q^0;If=5+l&bN%XQ4|rbySdmi}WY>%vX!<@%*HxTv_VU0Tc}
zVkW~ctt8Ba@+jYt8T{Cl`xDf~0U}<ul$`2Va=!vdf_^X#5(S2aPly0BL@_o)Et_P_
zN_c|-YqL`Hp1hM|WC8N<K6OZM>R2DkIwb@Axk;K-@11zk#RD#!+RqLy>n!_hWp=VK
zOV&@L%6AyOE}=(ejOpyp;0M58xel2T<BAaL<LJ@j)96D7f;xzU`W{!|Ll9RhQi1ax
z<U@<vbW|cb6PqY9e%x$jqZQUh8`1X{{PRBZjajA2-xQVbX#ngg-cyu3s9}q?-bTFb
zSA4Pl^b@;F&2sCMF9Miw?h|8~0uR)bAL#<gy#4Q<@{`H~?7pPd`_T{>PTWzs{crS(
zuF6E+_%|l_R)$@TY(2-0Uv<VoXmvVHv*zlv^?jn5VbPnQA-GC><c{w?&RAVA@Hi6$
zeyd^=0hL2uhch0X^!%;7GdZAP{G(r(ycqQ{ktTjZZHTTm2i;@(*Nh9lFo9sKRUo<?
zz7`@PY*d=0&pYj?_C|azffc7590*$PTb<s<O_cd=_^$lfOa|Ta&%*q)0wUg)WXdAM
z&LIuHNt0HI)<x4{o^RQpF9R1|d})}OS@$|=<$f;IXa;$8<&PnVSRb@i{QR_<jbeq|
zYm!zUznCggH-E&R&8WjJ`hmZrbXE<6-9B1>#)OVp61~K*6Od_(X5txx#&o`WioB_h
zXVmv~i7qdGfuA_CjEh9Rl^cBiX06frkDAXWm9NBFV$*L-{)!1~_2Vy&<dvpcP*8%S
z){Unf?|9i*v41A*LYYVm-etOJ6+4Ung;WJ``zJOGe*ev>T70>0PiENz6hT8NIpBbX
zNgE+gQ4LiU^%0P*GhA(cnn`_UJCz5XkM9s)C5@GhnnBR=9hFqmJ+Iw1zTf4U{eHRJ
zt7>&j?U4ecE;_!UC9mfxGSia^hb?E(7eoHV+0B;zy5_S;_j9T<q2<Re(5oMr7+H%X
zWHlbFio8bk3WqXOke5+Mt{APxL_JAKT@5;4$An?#2btI>nLYW8Bu50XxhQDQj_<F>
zB*?mj)#oFtbG9uKr^oT&YW!Kj^T#O0cZET_##omS&lv{8&0~w5#$~<<4kD;+`hi%=
zah~dWjYu98<cc-!i?iDDJ{4w~T6_yieqqAQGM8VnK9u|VS>FL!#*!)n7D_3`1o9<4
zd5L-YY2Xw#h-)pA-RPGA`;7Qxid+r}hoDBAux+(hS~oGjPkV3Kaph><sLFN|y3Ftj
zu)I}ONZ$FJ43su5i#{$bFdJWPfvzBNksUCs>~<KBG8$+Hk`-Q@s+oxC`ySgp97|lJ
zSPTrehfa(wEyi%&dzJV<rW7kgX+_7T#=B&T7}4&c%tlq-TC$}Z;p?xx;O5Z8W`4kF
z5culm@>IM?_(G<7#lb`c*1tKEJ+DA=%(~8c-kc2*5bne387g!;iS?m?0VH)ofq}IL
ze??B<v%XQA>e$D)#c%MPnvYO8^-5Q;Kt%GjMb@b!fZ<>;aiI{n+ar?MW=m`)+K5t6
z^I;C?{Ke4@Db?-Rx5{vV4o<*)dy_+}PQW4Wv4I-ZcVWY-)ax_V6`#K#X_h$f-D@K_
z1AyMgfm4)pD3bLqRAtT<L#Ahp$p-N;!-T+P(_A)^pHjX7teM!Aug8yTVs{(U{~j&)
z*D27~Eh%Yx#uFK6h$dsdr)wv|6buG_<m$tnVO5U%T8v%-s3-&Wd$&1A*V&y_0PZ5&
zdj>HxO&me)V7YZ>vO?tW6PA&X@y^e8uvwaja^w`H0CsFHEMr!DNs2lf_o)U~nxP03
zuDElRE%--wGvh1^?z4O$f@=q|>oT?(Ppo_e1;~J0Cop^avcL1YRj*00yO{N!7fpK?
z5QlkC<5xMs*V7UR!rYD4)2|InNskCeF8%oI`9VK~fOu_52${yZ$e3jO&Ie}y&Mpe$
zYD&nN3E%{K+eP`AX9rzJVj&F<l8%=1fezVcw**+2+(M}u%_tyD8qZU_E2k@PGs1&*
zxkxk>G|NR6J1n#j+x8D=o)C%o^aa7|ox}NKi<MDy6kNMA|9UF(nCzZN&&|IGT|lxv
zgCKkXNRs|#B<7*Rg3~(ov#hI!2^!e2u#?(Y_FbVu=}2-KX^}C;rV$ZymkTb9efy<v
z0g8Re;XF!W?Qf?fe=dDFz=@0S;hVz$vUm&IJZ!E(8aMUcr<ys9KjTSSS|_R^s7VMU
zzF7Un8Qz8v2#d^Qy=|>3fTaH7p&P#4nQqxz{B<FE?32`7{kj)=&+p+1G4`VHXOnX?
z_&al*rc}&zgaD>>ujpmZFO0H9!Z<HuWgmFQ4p(uyGUep#=xp@cAL}`&Zjz>zPmE2L
zUKQ=W`aN+6iBa8Rdor;x7R{&f1`24qtDR}EoV1EvEg?aHg`r-gg~1_Si68IxUOn<e
zoLM4_3*usK3IiMKlRTueuTRp9(&N?E^KXk&+vkaIC4#hmpMSIQpvp~DP55?YtRCIE
zbT6_uP3acyx=$PNQ$`dsph%Wk$+hn9^?Pp!!Ex1*f95$}*dCUBg(IP-GWI{gH?Qy~
zLcnDIgb+@eD*0}_afx^1mGK)2h5fm%irL}(x2z$l@EYijJ-@|wZY`vF3h(p5TrS*a
zJYDa@dQn5h>_v;a+9c&ZS0JR~p#iG&9(D6w&oh}})royTQ8oM9ying{g%~f;M9})W
zV<Wb(duT>_gWlT}m5xAH(FPzjLyV)Db-Y%Wgjq>$C%1<xM!iVfIf=<eVyA?Vid^3e
zinD>c3NoSR`9rpsYeb##b$pdsML+J`?Up-kFHrx+{Q$TbVBT|GfhTP%%dYW5$>!LJ
zou99t2&-^SJUG~(+#1@=iRc(X)tLj}ztED#;4_kBWN=T2OdOY~aBl-{$P70cr5?=B
zrq|kg^PFp>j%$zVp~f>2{%!<XQ)Srg-wzrYNH4#6C<#O2*ur{k_AuFx%|;Vhp1Va|
z&|7YXMv=JP%MCIt;4nYGZ{W^RKi8*GslwwbF2X<7_iYp3f{q`Dt--yuN9Y8*h9`W2
zYxr8R=bY*a6MqG`NdE#Q%fiP7=Mm*1aOO&%t6~p8&r1G@&8t-S#EQZd@ICJwAI0t{
z_%{*T?2ZG^`#{qF*M|^BnaZ8}Kq+=>d!DXlB|LNfQ`R==LQov&koE2b-m<{Epaktb
z%z9*-_^3?u((uy@1u|f03YM)oC<TdoCFfT6YHY{Fc(fC3Cbg_D-Wy<ZzNLX82qCh|
zsM*MIv2pJNn_Pn_CSHVOjv!;h+?!VL!5rn)z#Z<2BZkOJgVM}>%Eqg0c{9}wD5wD!
z0B;j8jIt)?Wt-LW4{#1?&4G76pxzxvgf_eNWHjtKQ41wyWZyw+`dLP^yOq4f2Co)v
zvWfu5i_T>v7ylEfuMd27b;Q~m+QPdnru+&R_|)KtHYnhJG^YrvK=^J@w>oYwG}K<)
zOR7f!(%<w?t;ARz@)h|2?!Xh8Z>DMn+lwP?N(`-^vOH}ULfS7#z6#@!I7q5IY=r{f
zSlH{&gb)GttzY`NV?eqMCVAX|8jJ}#CQI{7V05)-hIpiK2|R5lBkeWMqd#eNES<@@
zqA{qH539HF19#p#&oViuVVN?XVmNL+C<wX6_qNJB$M?5mFPc5!^jXKQBYJ|R2peL@
zK^;n8=u&K-Yes#?7CRZr_zRE{*xmj8uwYnVIcd0QuTrF8aBcH4$B3^WHzCqOVG{4n
zzr6I`(_p!W1AhXsTE_BGjed-djbzFBQK(Rh`1&42K2XM$oI4A%O;nemq3Me~T+uyz
z-yybB6CrAdM<wEKdUvik0oRLSkg%RBQ%>YIni=ZK_Cx82pX`$pnW?6kDbrie87F-u
zu=ZMyF{En@uUy&H1K-5SqJ~*as5;v2=Hxivu2yl)sp6iLJoXWJ0A7Xp$TC?La*6J=
zY(n$pOPv<K&qy)%Yuw^0mrwv3HAqv@5H{+IQ>1F^ks%E(twZhkWr^Wm3Kg?uqSAj$
z<tIUT&6jEMt6ovruH_G}NI%K@-=7g*&+sDr^-yc6mYc<Qz7p*~p%-UD{vCGen$zuY
zn5d-7F`LhgHNDW2^$}y#4!`O5(0mLI1kfEDkAf=Ej=uvN^rGC$nuJ<0C!nkrD{?t*
zwfUx+F6&O?@`hmMFej!8F+LYx|A%%7Q|nZ(TKchx^ES~lQ2cj_qiB><L+|MA2s$<@
zd>Bodp^VqW3n>OZm4-Cdd05L~0y9{5dCErUl-I?dDw#6s%EP;`n^?8#MC}Gd91&2_
ziCFpDZ^m~ZGv{~Ztl1N;ihU>Gff8XR6*Z{i+ld3BbGtTM&JUm_KHJ;D@`SJ0tE~20
zLVvn^j0b=Do5T8<hx{o9#eQSkUaS51Jxzy1R`4cU$0(N6ud<}`H+kT3ON1uMOo15l
z%P8r7yMOanIz_^5tFrSjH+eflm&Kn7<?J~<e_6C}YZE<wixWJ(IK~Qv6tk|pyrjl<
z37dOWVzq>Sey*;hQ7(&ym+absxx7VT$%p605};K2C2Z*1b}#_u*g<ehPE=jKt{f<Q
zRyZ0<T%k;J=LrMmF!_D$P^$`*^(W<RV8gmV0_!J#j#<5c`SDIO2Hr^O8B-HNOP|jv
zJ+%s5-G%cz_n(`AOMZqwul*wK9F9c$FN~r&`CYh;>H;k_AaT#jte23z^84GN==&}o
zA;+XMuv~$#y)};#fbrmGvhxGZ42@lDOY)2Ti|4n?MphNIP*FG+0gt1R4RvD^r}<bW
zrk2N3R*S|d{n&Y-JF8gaKn}}gWc_bz!@9Ym_(LUsQdoXnZwYq*w2K6$4yzt9{r6sD
z1B1bXYHyQW**i;M_;>6G45yBm+7+f@;ifHKKx?*B1K8EQdGLTx;qii`r0FOC_@Pa9
z0(&YJ`O{)^rw)I;?}jiS_HTb2op9hoO}zi_9wzZqT~D+2LFz?m5EpsSz#5FK`j0RN
zvcNYJvH|-x8?}3#1O-$M%}gPBQ`3gGw9hdp(rxbMIHkV(5>(Z9^D-gf{c^_is>9)j
zG@vmtSSj_pIj(Nmj)wrFjX7-LMl$Zdtzz(!3^);UTb5VUHa5j=zCM`%B<s(}Kwi~N
zhwlG|-VZg$$vPmuNz}EMNQt(T{d}LDzf}~)b%F|i5nb#uU@-uQqg);4Pi=<3dKt|v
zLhm1btCWg0P`e^>4}l$n7A8U9MZmrd(VXlRWWi4Ildcje5!ld&+>|YfEgHFg7^>~2
za(Xk8K<#V<5>pdRywpB(*Uk4VISzvxwP|0+A*z%JV&Doytjgm0v$=pCi#H7W5waZA
zc=lqgOw<pLsQi2=1<)Crs*zB1Yi@H!`wh<V@>T5hV`n+2+B~fyEL}&`&H2Gx>1-Pe
zqFEs(mJR+r!|*MbnHes5AJ&YwI5dWV8;L=iT<lbN##oYZb-uS-*f269X`^G!)}Q^U
zaqgV{A#%IsCxKoOOxJZ>&9tlTEtPy$7S-EJHO&I$!#50*kgdVvzcWhe!<IIg2}rPe
z!sVC3d@h>mg2WhXcGCHtBQ6sqiC1=79s;l~J4M0t221#`R!OnAFfDWOf{)8(49^gz
zZOawJ!P|}L`&bZAnMLphb>R)fkgfS4e3y2&>gETY4VkEK@DtyM0(7C+i^J$w7e$Z5
zauQmf&Le3OEFV7hWG*^j5HyBEuHLxfYy0}2a08S`Y+IyGKc0=hBJzsYs|60~v#~H<
z3FbOy6>mz#=4V6L=8p#r>dd6agLky+o0RH8!+=||01Y~gJXi?iuV&ap@6K6{u}VX0
zJxteJylO~T;2d82#Bh02#`ScUaNRdNw<aajkeR%HhF*YQb6(}!*eCji-%kH$H$N8&
zkcY6wn^^ZDyR<0lHX`ujB#9zcDJW+l&+pSn*8OXd=UVvMNf$Dbdjn~W(5Qch3UWMi
zEIy=zP{a@F=8{jOJ@!Hi8~wH&h1s7vcOY+JaRdy<j{5b-#{xYNqR2_D?<w5X<HGsT
zjH)<QMUGI7uIQChXc~DRSt$(RHmWw7fCTPyLFob@Py$>Q#rG|(rnA9|ZKk_{K`hzg
z^UByIN4fuuOWOmn6x6d-;kAzgnh@)3PM?Q^o==L*&!0wvKZ?(KZKauv*Zxh}VcUe-
z%?L8!XibD10bXSh8fws{+R>y3B@Fu!(~DyZTj^}&dbWj#)|Wc_)E7e1Z60CKPfTZd
z(m`cYm$Ltv`;OpJ9N;AFBcLWqmS(zJ8D6zu0zadpieYej*N-kCGFZ#CY=wdU6Fc@p
zr+;TVKm2^K5kJRcK?qoqr*g3u4Xy>mE1<y;KNpZ_9Dx@>y(VDv{E?r)Umy>$Nb}gA
zE!YPLsPbH$>^J>paSN|T%8P!Btq~9ywi^_gqde<D=;ZxzZh6<(<)cD=GSrz<4ADB?
z?aoK19Ir*ToJCwnb3)^GeYw$}X-~)p!0YUA)o4!;j*sMzmil;|Rkq<5vi*T|+e(uH
z4vC2*C>?EAG!RJWsVISw?suVT(GmUpVptfIty=_CUt-DNcbm#OH^$w2F};YUv!1g1
z>d)aShFy20%DFk>w52YO%arg*(x2&9Du@r5)fPHd;d(&_5z2al=MIn#7EM1ag{9e(
zB&K{2;a;00lsiiL(c+;1CBu7FMU4sHr(d%KQdM-p$ZI7|Ho{eJHHonRB#6eEEf#PP
zP%={2-)X|+sfR>|rddXYdx-s0GOzb6-L{9#K!Dt)>jAX;^`?0+$PJ{o`0VquOLDBe
zV=mm*$RozQoM7&AWQIo-4iqaKjhXl$<HgT&43TU|D&z~7XJ6?3QhJ+CncblGh+Xc1
zUMUUi`5;aBU$bstG~Tar>Pju3ojCcrJ0u0w5Xoa@_2z{)(_*Lr5M*(?DU}|N2^_Sf
zV+w#H!DoK)%Rz=6{><}ZRu|fd<Z?F8)lBH<aX5e}Pz9Yvd6F;zoIfMa>*eq`@}z(W
z*ojD@*M_rwj`hlK6c1WMLkaM%Z(b;SPYaoFY<_9rAcGID#}FNwxOj_>byGy)I#TvV
zlrHWhBq0XG6hP$bS4C#}C+p-j0cfIJ#&fZz$0B9hOP&188f7qWS{_T&#T<HA>GYn4
ze~Yn3J}~cs>;>$Z?I+7Mig_{IO0HvU2E6e2d4V-Kay20A?sssk3m0djx}o0qAQm8Y
zdXw<-nAymVkcx0VNPum<JXu03vUA9S%j|&+yDk$uc|*`l61WyaeGe{h3z7`?><4|y
zk@^?^GI`6TDH}CTqf*I@DUnyhFOJhL-LLvJXPImj0v}E2Na*&w)k3tqcat%u$SMgT
zmNGYonN_A=eu*5$kDms$Z9Hh423%XM3a#oj)6mDikqq?&QHq25=wu_)*^zhirktcV
zs;!*V{Xuhn2CVRa{ralJ5LI~g0rEdXrQr*Z!1IF>`T~sX#UF&zR6Y329^IatDrl_9
zNl!0B<kpSR*F!&ZO9H4Ef9o445`H4)fy2g4n=t`iqneFsfb0AI%$Tlb=b8kifmX)m
zm}BzE;$j}uYoj)ZWsZw_on2z=M{|+fT1f3R&$o|ui6cE%5+5Tl2Mxqo-{Pc%5Y3SX
zm$ObfZU>)sfVv0UktBjw8S4bmGaboH+H_^^s7cAcOw`0WVPO{OI(j_1Z^{ahDR?x4
zt_8A@r0S&};v4pFM%$+1hhXAe;Al}$5;n5!KRbSvZR5lvk6$zxFe_^^KM*y)7q-B(
z<N<*)qG<1qHug&v=APCp53%34))^e^DbUfrIpw{h6Yg<Cyc>Ny6%A;&{zlm{`IKNu
z5xksesC5hUXK5VQ!>i%aIbL{h;q5B1{VlTU*Ux|qQ!IiPdZg*(28xl4q0tOi_3OO)
zFPt$y`nWhV176MT7Sil7YY&S|Syu6K_vt4>nJ;4wB70Xj_|WAl-6Eu!30ACdIX@V0
zdin^;Wus2<H|;5EMM{JH>+uoS{=5(-2mh~;L&g6Y(ZF6+Yjn(l8us{vra{t2FeHmo
z&^zmS^|Dbpny@&uglvVTXTk?uG^c~wW$}L<#b&}ObBDze?#|Ek9%ZO0->)AcK@WE%
z=C%#Tn&D|wi>Bgl<kWA!-7OUc9|SNh&@|f8N0X(IWVx#e<iNTzDN|@yQX&P`IC}Z!
z6s;&Et`PAjlKSrhnuW%tk&puCDu~5<o_$AR8kAmoWUXRvf$^7eO=9=>N$0olWWe1D
z#Wgg4y}~FPc`Xi5<ytVUPskvPao%4Yy2wEaUdZRX3sHA&-;q)gBpqXS?dvOvrF-4^
zUjHovx;v}@Fyz6ySKw}%*B$rc+K9nbJAapMB3;wH2KjC)6}$Nc?%j-gWNwiGi#$0j
z|2}2GWJxtG{wM}TyGQT=y!ZhvOjLO<6kwsuh*V}`)jpB0TxSYUwvX12{(B8FD%*OR
zLXh>L716_MML#yl`_IA)qLtg5i0kHmYHK*tAaxK5*r=!WE@e;$o!1;0d#)j*IAjon
z#+8frshEU@`T4%1jG<ZSSm@5vQk}y_;}3yWn;3H3oD?pZz$cK9+y;HHCeSkd_Y4{^
zHpfE|G-^pRiohbHu76#V7wXC-`7<e66O@5Bv~%rj214)`#|=!fhv%}AveaV_Vq*HQ
zK?@mG?>)C!vUhvvhT*5dqj>2{yxvG)+>w?ped|3jItC5tI0g_;Oyegd7b5=G%1+mK
z@o{@dA|)?6aVob!Eq<ppqnWG`v?OH%E-3(Oy)x1P;QuG&ycqN1dV4;GdDe9I0xbO{
z_j7rRWPu!zILl7jJmwSZ-S;O;(_SAD9$H$!lHkVs9W{*fPV!?r<QIVKl9@hYmwRM_
zqD?H|n!sDq^kL$p^~y$6lPTiDE%h8yLz2nm-{E}f`pV?dW-Ha{ebnlAa{CqPEZGPc
zjyk>Yb$DsUWlBmJN+dy6EcJVQV(v|9LK(9D%>6#68;4f6($VmY5h2Y#9KWcr>J--1
zws_6hVq7!yF^G~a?>ufME#;ioY!Q15;Ml*zQzwXC`Eg~-*w^nwM92MDse2IlY{D0*
zq7@g?si{i{_9KMhgpAUc?_tfXDp(%B5_`dnd(GAXf%%+~ACz+pF>?JYl4NX=(KbO*
zp!g-t!g|cO{myF#<KJ+J_#HMHs|H%5-{GF-_vdwP=dpwSCpQRdpPk=9US{K=(%4a!
zlEzFn3n_$4-|8watBm1)Z&>(yyup$H&nGAfL2BIpPhf%c67BsH6}kJ_z-jz3g{zc3
z)=Go)r|g@9g|V6tl5p!KVb0@^U${tU|3OTDNr}Z2EF&S_$+AYd2M#h6)y!WiPZ3F7
z93;x-OuBVV?H3ipkQdJ2)qCaRA-b)<zX~lE5OZWZ`d4N6SP(je@B}3=M9=+QuR0RE
zLk#33N3IM7?3sd)<-c#}vM%<6%<^bPV4{3ZWr@<Z$lGI={|^fQ*-<57a41Zj6iYR5
z&D}{6+$#cfVP}IEGLLv7xev08TS60l-3-3(11~oMPtZHK@PEF;R^f}hXdyYiVsQtO
z=i0;naL+wjV4C5aL2iTGfCw-upPP7CX8oR4)YFlZO~ZQu>QI^`Gg4I?;)iX#1`Xjw
z+$3pw$=SiLo%P{&(u8sT6CN|l;$U^|gJsK)o2@+0#p{ixjR{5>EFRGkiBQy$QCoNP
z&54^%<omuHkf2T)#74dW`#m{o)a$!@3?1h81#|cCf>4OB=%s_MDQ_$W;r%AoL)KIT
zuyxD@kzbxPh3`hOLtwo~1bk4S#m`VSD_5~B0~i)|YTWd9q|>oD#GfgJ&qfzEprE;~
ztwnQEDnDD-1wQd6Jwd=RKUX~^G}b+Xzi*SbcN#AF!y$o8**<3E%pORcz@vT>5EQ=@
zt679GpJlMSD7<I=<AuJ(6w3XUfATU-hNzE&HHM>4P9qPVMP>F(QN=4Bd?Kpe|8&eJ
z<vs$%fO2JkKnWv*sm(k~k~kxYIBKEOC1}Blrk(W_#IfXx>{7hn{uNu)KvrcHMI<(-
z=*XT+18WhIy6<aYZe5ki!IFCjGe#MjG)<(xS;e9UcuUx+g7WR=lAoo(K3K>QQbTa_
z*kBMxVXuh~e9B<qYdzd2cm$ZH^Z30DlZE!Sp%<!|MAxqgO`|A&lDxALGYOjpDUr{K
zS%UJF=IkKNFb?M@z#qc8Y>pX5UHf!JswF{A|4kyh3V2wUFgm4bZ!<ZY3UZ{lY}Z%J
znAXo<et?~Z*~($H$;O8azmue@HB-3EH$}QP0kc2%mgB_5z&kCRY&HHQzMS{x&#oKq
zqC}%_N^O2_Rg2{q_Q`jq*a@Qy4twf;rU-7Sz3j<B!ommjUh$8C>f*qZBMVcbTO0}_
z{62UWkoj@Z?dp*aUgZGEU52vq#0c_7%Na#Loj9k4`nGxdN&J{wLg8j>y$Lm4u{)S%
zz)bzcB^bc4^N^)y*ufd3m#`@vcxv(>%Eb{g^`PcerX}ftJ%nWkCVwv5rKuss|7>Bq
zBPTtYv!)W)B@JLU;Z6ejwq*fC7Xj~yvB7YvhH%*39H55XDj{xp5U2A&ddcMcnl1dd
zy{GpqvPkif+Gj}s;LDpa*TrX=$es2~K|gqF;JOKusE%Sg{E?Z02&VB{#)BIF+9n%_
z&lXW&J(hw(0bV5s{`08T%1edx)<_dVx}q(duw(ko<%+O~GSngv9eaiYe0xRD%|gdf
z03Y$X@u-*8c(g;+9V9y}4OaUC$S2q>7tuQoBTLPa1q~%*p|`B^PYyEQz@0$<eIzUd
z!QHuU8@of!w^0P%ZT(8bUL=W|lDv<=gGe6TXBF`8+_;&xIQZNIC=KnZx7O16@5h5o
z3aI_$jU=s#?R_zI)x_Dm%UhoC%2}RXLvF0AgEob!rOQ&{rF#u>0{98_w*`yBExhfF
zTJlxXTcBfms`QpG^g}zGu!f#P#VTB}8lO8LmM0&UDIJq9*`dv)sR2xYJKPpEly2%A
zb0<D<zJxF6acT(-Ygt3-%5%lE5KVwT)4Jl{+dEFV0g~^!iGe%(m|`$&aMf_p?%Kvv
zLtq8UwE-GuHJ`I06r6WU<*Tb*gIw>AB;79`PSZ0Ux#ZfnY}SVdA9I8cd>*$EGX){a
zCv!zew1=Gvk8Aibb?kp6OfNOo2e+#QbP5wxKuDftPCkmIerD7Xwv_y12euSM=TrQq
z%{ds8t#9zirKlP1kxC(ZPeHupKXNf}%FNdkCu`HXC)~f0ix6({4N67h9sr!2aup`(
zfW;B&Z&OlvLxzTjWD>NnO8|Ec7vFh=1R*=HJPZ+K|3d8mSP+e%@e^*{IpY}rKt~DC
z+$d;dl@u4Jrwdzf%`PR1Jp@w69FO4hd#8(mns>-B3T*p>>SJVJ!O>I9RCwu}V_1OW
z+wWk!^fy5t-gSE&!5xd-cY+uZ(&flJLDGXEhbkFC(u-qfex4w!$6R}tSP)j;0F?yr
z)vU2~hXg4xBZ<ol3j-@Xt52K)OgTY-fY7;V&>phBmocEV7jehVj~$zoCSH~Cm}*7g
zzQW@^xpATfDr1O53!`*0co%n;cWt+R5{{3)&sXK`A&xl0-4>9T^`c*pC6mR|{s~OE
zz99fy7H1fKV@W=;q=x#(&5@gSI}_x~L@|C6{XujHlDfTjyXh?zoa=gVdg1lwR`{o#
zR5kq5bqius)b@Kjqn*9$@<eE;R@Xr=Zf>XbJkui<^6CGb*2}WWGJ)4dc<%~S7)&rA
zA~OjOBUSKp>`5lHfG2Gcy^o#YLTF8RBXLn5yF#5yzpgl0EmxdRFO(hxE1pl0J1IV*
zBoQ#zYgu&(InI}w`EXdeayeQpG@yG73b9^&FS_fBpflA*{{M@+eQ&M#)Z~7*9By8G
z3MesI65p%F>M=Kn5_PNeoigwU_C}Sf6G`{ZDIx41#FEdQXZNTRmF%p)c(1O=k0^=b
zPpVV$1d_9RwA;bcLgtKXlEmqN(Xr@-7}`2z*BkPRS@1N(?}vN$cIE}ihBw(2%#EYz
zD{jGY$N1|B%wQyG-7C<y_BL~a4l!GIhoP;c4I+FdoCJb?O|>Ke#>=~Kpt1Kg#=eVN
z1*E%w8DJ&c+8oZpj{8z{l=2ae6sk?h#&>C>_DBq>VpH+$nTA(0YzxFczt`qga`86c
z)C3Za)C2DcU^`J;8B$1Lnpfc7rluX*Ch^@m<OMz131g0#!%gGQ*QZ-uk|E!K8{!;2
zHHiT0X(h_hk=DYS%OgXq)s4aW2oego*5BqLQ9iv?tGE;Dsn|^Uu>);xu8e4aWB*+!
z!{)*{VRmRQ5~oi~5ncsb5as&fMrFZHSqgXr<L%&~lsFfHz!6Zu4D^e5{m4mPn991(
z^zadbCvCYSA>xkJ88_tWh2EDcEZs!Ni;+bcMU5Zc+|u!kTY=WFmv>qz*Ast;4u8Nh
zehu&aIR|xl>2ALF+P2(@JAa?&=kAXn1atp7dPbI!%RzeXqX*#?02E@!3}Eg+zlcOn
zBHX9>Dl`bKHvHXOKGZ6LypRc({9Q9xv8CVANTQQwlVLG@X!gJPAk`A$gJohyIx!$j
zvL#vaCZFE{m4=OVX&gL}dIlxnd`%~I@aGgZX5DIYi^y2roExKC?wHV`{$F?B9TY_n
z^*PJJg1AVK3=#~W1j#w<q9TZ>NX{TxvP6lyfC3T(M1q1O0m)H8;-cgvIZ2e9b6nWn
z8}z&H>i)UAs=KPYI;v)enw@$5>({S;@AaGB?$qUtVZ!v(7@;k4ehHT+7fsAP;8|T4
z>k(mZeMma@^@|iEtVL2Pp>Z~Yy&qhA`kP4bB?YI<^^{ukYb&PrC-<dZEILuHMe@Cy
z_U23~*6Jax`RG`t%U70?_hqW>wjLTk&bBmy`i$qM;3%nLFCrj@FE@>1s9+^z&q(h~
zMtd<KlenVovK-B`2d;&0tL;O9+oXcH0Q(lvHB>*41L<kNPSaK!uIt@v<EexE1Uy>E
zq63A|R}6N7dt`(j708f`*dGXY*4Jo?kVg1<`<xXIrG2J}#w5pRSPG+X8smXV0m?Xu
zb76t7GlOLUJL9Q|7*69q03<atqfZ}19+EW3e98*+%6r*kT;}Sy0t`~5dC@iPwKZ8T
zygv$Jvg1jtdT^q!pzF_F*?kDN1maBdlGn8!M4RlPEUB)x#E`YmkS<R%@x8oOl`x3O
zg7%WFZ;gEIBW&s2B@lLbhXv7!WHMAdp0lFpV7GPZ+_$FYXN~m91+$Yu$P}L6!;ob&
zATm6EntJ$HCs;&DDZKEk!4xW4BSe(*t6bWRySkgjBc`3Phs*mT*YzOwG!(;E$am6!
z357xdqE+zGS3_IMxo6Ym!T6Kvv}_0;ax_4#O2idf!qd5zQ=uahCz9B0M#(>gd$J|_
z1NewNWJK;AW$@J5l{?{0Hw7svMbUC|v1aUUz>u)|K&#J`*6n)jz_%*OFa(lto6nr@
zPe`&UP<Z7>E@}XHk3R`Ab%*M{DuJfESWm%B1t2MG&Nh&oP>xLE(J4sZXNV2y_LBv#
zU^LI#Xda#K=c*oNcDDIPmy)4v^$P;wro8EdjAYt*g-$bb*p)c+*+Rr8zMzve%#f8?
z>NM~bO1zArPJ4|f1c>bmuoLsbXLQ1;JvcNsyC#734tJ%?y1;7w?K8!+8VD_hV?a4*
z!P2?AX^=&-sj5qfEg!>>_1oJ@75vS35JWa`l_!mW`&j`OmBCw=ie@D9md9TfS<ZRs
zsw3=@r@B~7&`#?1>)H+GsDG18yuFqxsq-Db=RGw@Fu_Y4umVq_o&yi5{ubT}%!4oV
z#>U!go>&}gyIto@w^gWSX^7fq3Cwv<WdxW&objxT*QRKn$Jb*S)tbT49V{PlS{CPL
zJOFGCTcVGOb;oWM$%$#4<^{eDL->%)ajBG3;VOUIZ}Kv*Yuw_j28?ksJ&Qva*6oqA
z6a+aRJMq9D{7FxTq}A<pWX`FWHFSBOHuG)ddqsBxXV*@6|8IaXpM-PZjvFK=kS3bu
zmgy>9oUJ3BVkVsrdLWcmTZXym1C*tkGo#C1n-#79ltj(lQklIF6tH7mY&vo8Ieo@?
z{Rg6hBAUfBF3t>K_-~|R6V{M7yetV$`>_ou3)IyNK?>8wpO;=$o9qbz3RzcFmP$rf
zqT0swZFX3zm@?}ig9utEpVij@m>N@A)<(;3N&Bz2H=aBf_PVI3S>Xv;2}5-*b%Y5&
zdmlR?t*J2j!POG%q_aK7Kfb@o6GVaaHyqO%@l*5*fHf@lEDnof2|67Rd{6N!CS_<Z
z9VXP4>Adu3B0@l%-69!V+;1}{WW*4ZEQ_kI`d4n?ao!04<$&GQE8MJPL`$i~mj13;
zPRv@-m@+?#`;gi_cW5V7d{BxN?=?KKmN+A+!g_s3sFJAFF(Q6SyNft$XJl(ym(=;!
zB-g%#m9ye1Cmu5aS%k7pPbTCef>wfkApwDBI*rAgrBYH7bZRNyKZnkk-@SMlG>pTp
zCSb59iTUJVSZ<de>J|MTo6_h$=_fovUqt{ht?LM8mS%PleX+x0t5+Yg@Wr&iNu&G1
zU?57jK}y|D482}-CI=jxg>MJcO&oTv=5xGcQ1F$K@K;90G3!0%QBZ15tqY9NxS<<?
zA9t{})H3;yQpo;ua1^1$gv`N*=e|C~5|(C<0Q^3p>?bhz@M`>Z&{kxm8K7<Vn3l@{
z%~ny{)*}ai&4dFbnWhd{B$-?{WI?-5RQUdUeWEX4;WPXFP~WZfC{+VPb|^0Zi^2>>
zwPH@6v(5KCWSTA34EW>JsxPO3xb`_jg;$}q353%(a6>N`Z{Q%Vb4A9Qb)K(e5F?JJ
z-X{?7I|73Ofh$Wu(>Rh4!><bRkd!DpRFHl2&?8`6JV5tzg}bNVhPC4ugiI8eB2nY9
zD&kCYQ7Igk^O)#c9eLc>a|Lxsp8a4V5sTWUC>iaUaCFUqY~Mx?W9-Ptun3aXpG)RI
z9DTHtqKh(2t2)_oAYe>;j8c%eDFU-8QCZsak|g>Kb~@(Hr<Nk3Z^qC3f(y*g_F6#D
zZ`36|;@`l(+(V{*AM&s|yOGV=)kDZUFp(!)45h(t5xM^n5k_~tG!N-xDC%J#xrnBt
ze*d&=SMK5~daO90{p(cS&Lgi-Sd5(S3(-1^<D!OjKrr2m<N?AJ+SbyC+M}hXj{YhP
z47kgF;oTSbLd5zd5HEAr=-3dRrt78ENl_=A@sOe0Mp+PC=)OU#RiRh=E)v{js_6aR
ztcsVx%_q6vfaHGp(zkFOdCw@+@Hs^(_P6vSK1^>$a&k^w0qiVp<7()!sm`emD-X2@
zu0m+lC_vjMyk+f-wNta;>FW1=)tIWm6#9fHahPc#K~KT!QzUPO!J{~z{uTKoYO(vl
z;}cU0f4Ys@uRmu|Bv`>Szt$dQM?ywh4blh?(l!_E;ppNe8dTz#dqHp-c`$E_S-K!^
zi<T^Gh982@_Rrl!|GD}(O4S&UQuon^<h%#Qn_KmWd_UwTa=i#z#TbvDwAdFMCt(Zp
z>c;QhC79o_Y>9v)D+9u6ZE}9Hs>9!u8j5V|ebP4469LB3xaGkuKn$hP8{VPs-15YE
zg)7C#=aNbGEQ`!OHc{jevfuLW9!|1U-{+E-F}o^Cii?88F@YpR!Rt2IMJ)Gzj4O{c
z5097xEH0X?#M<oFq`>nX$<*Al$|vyg>PPol6-8S!_#yROTB=EHocrv2`_9nl1DCsm
zsmr3PuFELV9QcP%kmVb87T1)1QNC`?axK>*q}l?izwVbVvQ<K<!WCA^rfPTnUyZ3%
zWp!n%17uu}<~XoU9mkqbj(v98xEr^635;q?!VjT0s~fvNZOrz6c(4!LIndL|A9F0;
z+#NaCzu)(cyh=#nMl(yem(Wm+Cd+mC9aWL0*s6~Y1|&oAw>Sr|hZ7&oRBxH8y-Bf5
zn|p<CMR!DxF`+fR5ORWRa5PRRA4!_#HZcUukN*jD>{_X8Ue6p6A1b;PLlhl|f52%l
zzfmP|81hw`r2)E+pwSHO>IJZk&j9iC)6<5CO@L~k(ZcdcHPOZQ29z0mH5)DDcUL>E
zv637tI22%=()R!yqF0_;yic`;Xdgj7SQi2zCi_|h_jcF+4iVK3J?yJ^{=$IyvQtF$
zt|&Q@{QQy2VC54&&K6Zxq!WbFTwIG_y&)W|8o(!R$U0RgeuaI5KY>z9Jk`I>!SPXH
zTa2Z2H4Rl_tOj@NKtBF?RX@+AS|tVQcTjxGZhFV!KyhVvVE~>^L=0{Gk+}I4oh9&z
zA@Dbu2)aYVG;Tv~;@iNM)<IbIBXt7t;{0HH7j_s?s1qImbyDAJ7&b?`>bu7l;OE4E
z#dUC{J`$UPO-f-jyOw{y-6{?8{q%E<K}0~6l)G?w%7N1WU!Bx8*U)T6Qg6yJ@5Kk{
zgdgc;j@dA0tlN`Y1s<^8mqPYxZ%p@JM)d%Rcx!JcM_9xBt<|LH<Onqaefwb^q2#r~
zH;1?j3++Sk+4v<};LF><_zm`lIHy!t5zX**auiF>5VsXa<?8D%Pl4GH%%ifpRm97D
z@LF00?E!l(#I2YRq&WenwFTx`W=B=wX+KBzT&__i&S`LK^e5n-#JD?y(O-!G$H%1K
zG<^hLiWyPa%YXx%Ba?v@8*h{FwCk}``NQ5^;>F{^_H}3vF_HyJ){mO8I{(J;{2R3+
zc^7EOFoB<SMxoN6V`(OdGO`z@mcQNpVfKU>=|;SGc>ZMTHGp!;=*m938%<JN*C3D)
zRDC2OfiBAD+`qhr8ziV_sNPBxi(5ZiN!aBkDoEEHt>0qHp-CLm;2xOK#MRJErs4}*
z<HGS*u3U)IT}GMa_#jN6RPX+TyGvi;y)mSN6VNVT3cD>@h|pU@%^jgPFjQ)_W?zqz
z$W)2;yjLw$!nm`gujJob>vb*0R$gh2;Jki%D|{z!%IT_L`X<hv0@*X=!3(HAImBY>
zAn!X@BPg3yE?|WK?Gy7t!b2$X0^|FJ+7#&zfiAUKoj<g))V(*22*c(-C&{qv^s7@n
zQ-J)MAy9A;UCoGIlY6skUk0-to_@7+3GxFH%q5ur<#Be}$*(eTQXks!Dc}s75TMFU
z=AV(aPrHm#{#%>lf+R?2Y8RCQjnV=5CahLYH+yQ$p72x<12LttQ6q8%t3lqOQo8Ws
zHC`sK3P-JY5#uq{qFIWt{U<^PYN|-VR&asqYq37(=IS(_wd9Hu#Pl`wD332eKYff2
z7>>-1eRMf-0PGza;#o4Q(_a?<>^mWTVzg~!|J=I)dUGFy4zx{oxE~lKA}PEc1#x49
zl24iwjE-+GqqpSyB|KLx28b8;2is{&3bG)B`_o3h3Mp-tr#+eq;2d1%L#@*>W@L<_
zLW_ZTq6!msw?EsuSjEpLEH&~Kq$|838B}4I%aET0&U4sxd^<ip#fsb%7yutTVQH}D
zn`zP5+TF8wG5*-u0Geh@x#45_(%+~nr{jU?<0qd~Uyns^W}>1}Lcs9Rf9rJV{vb;8
zJYqW%5l5@alBDt2MTsg~3RRNsYZI*&3Y?ZbiGp+$<D>GEiLF4)gM#KaER}FF2eOIy
z!XI)l!PTC?=JOcF2Vo73Mno0z*i}l}ckEhl`@JWbzVm%I>D#w0f4V048sR&L;Qo_O
zT}0`qtU5>R(M{>?;GEtc*veoJ47r&mPU)ZW?4UER_+hqh19%=)l@H|EFyBuNUWG{J
zd%LX3exuWpy3n<l8>`1@FBGjsaFipRiWaUG#Eti?k4l$WWzcwV4A!OAK|+&vJp<Z*
zPl&(<|2zZKe-5%DzeBd|k`|VuIPzR*5}P%+%fkvD<L)9MVy@`;x>w7D^hk)Z29put
z=>>4`r$qk@=-RW=e%e!+3ftTkME1628-_k&Mq}xex$JO1FE8rjl(Zic?Y&&J(Eju7
zvkoCs7<Vxsco4JkQd>4(jZH29{}}|M8O-+s@ZF83t8=^+#{+MBQas~lR_RdA3=9ao
z7KEF&l!fIb6EE%zwio=Y9s2AoXK<G=IXHnQ(<j8weR%xw8KBX2g9o$;%eJfV29`VX
z6z01d>FU;;OcUuOwEZOUEYG1fZ(-doo0b1rFY>)&h@aX!>*nh8v{lSQN)AIpI`yMW
zLe8rzWN{Q11%YB@7<bDcyHzn>&vFZCp5|hn2I;ECMiqcfe2#=B4V5L?NLCPKsC9TL
zkI)dB-T&7{I)YDF(4?QstiNG~;mNNdU0xec9tbR0RC@E{rwV(@=MG{G%yl;GYDyd~
zbj`;85)!{}$*xw+i#vt>HYfW{OLIhPhl)5I4k@WjJ@d(Jn?n)KetKj_tqLR*<H4zb
zHylpuqxP+MHE;7Z0|j@4goQ17r)68DRab28#KbyS2o^&^FZ}6qG*vPM_8N*%QJ3uU
zM5CCr36M7*b`N@RjDWe$Y-5U062$j3wsQCG7EG;)l|1gkMIj(u-8M*$^Ag8Z^&rJe
zp3Ylh`SzWC8lBki5DsXf-yVXc0kD;%Xke(||Fvq9i!D|j2=B+py>!AJeX;CMKpdF^
z`Crtt#+B@nAoe|Qs375^n=tz7qFRouZZIU2Ve;MhICFz_7Nob3)kwS`l4DH1zc}RE
z8Kb%`rRjXlC<$W&tMdvb-AEz}0xuvmWU4A6V9tkI_ip%(o)N(WIWkhLhbWr4uXzUg
z0A>!k?pbBn5$PE1Q&S(Z*fA85z0d(c?Jn{tAwmxS$k=AL7-3jG#PI27MYHy0egy)h
zI4<eko=MU$=5yc(;V=#5seT_5#U;noFkN)Q*eg%yq?o}EeJr(>IQcS{bT+^(QDwC^
z&XFV>$C=i+xE>s0ZGSMUy*VEK6x=LY!uR_o%0q+gOF<f2Id$vF+a29PwW<<0GzW3f
z-d~9R;8;Y9eTjK)|51!sh0L(w_f^6xiWx`#@u*sLl<zHsJJ~qBT}qD;fs*nu?$phO
zN1c71ECVr0q#H#x^^D8%s<$v2Gwv+rnCja~fqW1r(N#G+u==eTxWsbXl@4#X8LLGw
z?&it)<Yg!Z&1tr8*|F(P_Osw&p*IJLCLx`uRi<VATR*xGO?cDv8Vb`_ES}OhMl_qC
z>5|H?^?~tqoWADjdi$e8ewi(r3jRac)GGXB_X2&Vbn7rmSv@<Q8~U<_uKOfh#t|?$
zOs?#84PX<m<??SG=ZWLwI3Q4tWPB)J=>OGdlAC8F8A6^CE~j&*V{7spI7sZ4^nG;g
zFOtm!PJgabGXC8j1ESxecJ@y4dcHVB1SDq%SC=#B^)x!q@d{WtA6U5GhNTeQ8jFip
zj%M}eWdz@?*xm%ly6dAwf-6+5L)JL8uG`?ar~V|Zv8^E(a;85>Q2E_zH#D*kNiZYM
zVI|LFLEczYVXc>f@UX`}1I%CzPhm~h8X#jjEK2UOw>4slQE7Cr86NI~XIF;0>tg4y
z%~UyzlNZRxcg*<4>cD{Ucz@dLg4&C&ZLDXO<?;AprU10ffG`$csd4+&eJR7A8CR|a
zFJ6GEH70sH$I|T)EiIBoJN_C8M&}8Q%sJm#XuJwXh7O%5U#}!XZHm41<Z~CyGA1sk
zXYSOlfvOe~)Jy?a4kUqd4l%bjof5CGr33geA#b;0rrSEEMbYc0I%WFVaMJ@BS8_Dv
z{==tRzozKZ3t?)JRn#FDd9Hz#$_Vs43=Gl+`bd8#iB>a~?5;3Aq%Mj3Y}o@?Lz$44
zx?i+&D=&bC<^C1G`AmJd{FNwF-dP!E5G!1TKNUtBmSAu@YX#!O*AM-DQ6IuTFcWno
zi7i=ODZb}diMJHm)?g=^Ev5aOYS|SjX{aVuN(F68T>9i3;iUr^yQiZg%BxtUWwKe;
zUcJEBJCCKbq=M$Cu6x59=qmUtR&A)Uo)RDPA9?6UTwb337|*%+l-FAXU32inUD5C{
z(b6g|+VaS^-!`AvNC<5><U8zfK$6<aPcOUYE^A91`edcP%Vjck?Hj^{y2*im@jmPA
zoMhcFa8@8WPePdZs;|%DhgN1w<QbfuchKYtFaK}FSDCrlG2KA+2<m2|0Q7(n&1-L9
zKh$@1f9v#-psj-cfsoK?Y0%2FONezEVG7Ps9Pe&t{2-3^Wj=%Owvf-P6uQR!mc!Gi
zi%++7rJ{H}SN+V;`#YAU@UK@KcEDxz=~y4!Q_u_r^$+FYjW-9E#JNXvs>ffGD7M9{
z#2c~IT>mkxaYU&BAdU~I@qZY(cCP$~_05?CeL1^dQ{Hdc?hz`Y<tCypuXF>u%qJ?8
zOQ9iUDSKklt;Ks`Cr_t>doCpu_!50*?OA%{O>HbInSIa5>&$4me)MSLqui;2ESYwA
z72A2~V7E?TS5yzbp63T}&T&A~%z5iIiLY!^Jt`ISSver2Id#{S%gdwmb$N$<!<7kI
zQXdPCJgnE02=S&4#eRU*iS)7=MX#WmS1BvhSzUfcy;HFHxt@+se~ST;ZeND}KCz&6
zw2RB=c6>K3i|xt=ZvmxUg<>Y5nk{^6T*GXu041$T$>1yODvCbUF!5Lj=!k5iKw=1E
zgmSaZWnQd@?DY>Ha5gVyEk_8@xL6m~fhS2NYy}6}_pnYk)$I=m1&K1)O{`P!hY<Xd
zH4xH$!Aa^uU`LrUJS|O%f{)lMV|A5sd|dnPW$R}Yk5$@7;Tn%SUZ^4*etMT^8a!RW
za6VX0weW{I*IM<EM#zUx0hztsVFZzHmzLf7hDgQuNz$S^6B+h+xw%aXcdzxMo-%Yo
z7!P{dUnqU~=hUtH7}1-4s~w1eo+pRzUVLlk@6=zm><qe|=Q5jn{JEEKx71%_1(T2`
zCI2_dx>?$429y;g_yMkDW!BJ}FooRGZp-{2E-*AIg|t;0A42l5TSLHX-?`tvZUt>~
zn=~1D76s#A3xBE)PF;TUC6W7STx=)>$ACNPE&<1c)Wk-qj0W6u06uur2M<Xcm;=o<
zy0!u;hT!}h5C%;-#6lbgy3xKB1Q^cH)Ig|~AN(1x{=su`<EjmWghos1%>+Oe#$En6
zD(9Fs<ZtkFff-$aW^3hUIvI|$>_)#HFl=UM8f?#g&;xWFVfUGz5&tdp`f~s~^3yv)
zZMDuAz{)@vLuo0Hm7}MTR9KU%&zX_KH7`VjuIk4TevZSQM`uEi1Y}GOWM7M@OF7Ta
zGzZ0$`5fp)L}%Ipc+VA&(59E7uw4_fH_X63CGiCoB>MmmNiuAv4Zc^G%CrOg;QdI#
zL+)o#Q@<i;e@q7|ozNT&F4GAKex63iiYbDKeiV?qA3;>Y_)ZL1X15ST2bi((nDt5s
zqB;Nla|@J-T)ha2ScWd6{xkr{e(>n{f8cDOE0O(JoB|HmoCnf^Krj8_=i6OhlN$hZ
zFiwNPif0|1-k-)V2vFS+1Q>yBC=_@~1Vuvt#Q(`lb&L%uMz25dOPWfU0?2__NG%~*
z=&(J(NZq+op7N4Ut-s5|trHuW`I6`FZ!iKj7vaFY2ME~q{km(LULmymX23Llp5L$O
zPnll)e}xOmob+yHAxu-p6{Z@)O?~dOG@ObBLC^yM5cJKJX23(G*kN@y5JE9?th2u3
zWD3l<c}t*Ab-c#s$0FbDrx+!!Ub-|&!3gw%@`qrZINla*fme671ei|8A}4NIb~Ps*
z(Q2E7My84!p2<7|wo*ER-i|EEcpQo)czKN4*!Au>FFZU5M@2d9DkJ__1_^mMChN7h
zxE@yuIKFA2g#%x+oS@$g!i5HEC(8`#ez6D|)`xT}j-w|*{XP<aMe8*5)DJq)WR334
zUUN!L5T=iF|Mhz6IFzN~v6HMZLcg3FC6I^DV5Hp{gq!kS(y!Bosio+(TvaEA0&=~T
z5c@ILDRg^thXh+O>SMl7kKM5cqy_>7KKgS7L>23nlG}93(}gYAE{I`u47;)-_9B-m
z!97dm7dWSj_o70&^``1E<J+r7qWI?Mw`?P~=5m=Eo;4!s=1AMNheRHNnkMxY2X0Lo
zezA7)LL52b!r3w6EkZ$14=4-}^^+rYK4VAW-tXM6WbQ{8r?T9Y430P<xCD_`F?@Qx
zPB}eK4GIrUN<hzU3#U{=3R3*`6xL@He@d2z-RK0RGkA-mYrfg1Z9n_85j#FPHtkUK
zz3ZrqeVy_p4Y*y;%AP_=ZH#e5qq9iwY+>8?0?g2TPHXq~MN=Yrj751$5{p1nLk#17
z0!%G=Eb#`|^lXg1z@fEM<<i*UnWNu=I3P0f0JQXMN~qd~&)83ayk~f!K`<&k++#rP
z;j#;=J*!6Dd8cfFv7=&(*Ct}XR5u!emS=J#yE(EUAi*%U*{-wD@YuP*@mxv*TZ8r^
zl?Tw9+BbEB(JIiJ!RX8x%3z3dX{y9*3@oiRx+yzqOF*YM4nk`k3_<%dInpFPS;tE{
zO%<o4R8s!4wXbl^h{g$%@Z8BE247nbek(7NUF*_c`LPWxSJ~t))Gl3aJW6Ppp)hIv
zd{KcZN;*P-p60IV68o`U6=a^E^9v3I{Q6@dH;ddnwZ0~M_y!nEU8uKZFJU>?nDr%O
z;jBeeCta#x>8|<7n>V)Af<V>IlARE-CVMTlnGWqvXkCVzY&~CmfN)jBe(ehy2prf)
zPQy4-^}KG!3x*bL@BG#sXJY*)?>Wu!Y0qBAQH(b>oU#iM8-+4j)H;Zqx@lp5>Cax|
zu7V)jc3)><%GEYoO0u<=^HWYE>tmF&3MIuSdV5n4)WQ>doumj@!bM|JiVTa2;vlwd
z_nYT5#0Z4Gt72{de|sSF0yJ5N^G^HW3uId=V8GaOmIwy?CIYEQ_z6_f*c1Ca;6GVv
zPZa$Oyte}6*7ps7DbPR(a>WHW00YkchnLn`KsOTr_B+u15yOCYFc_c?9{<0bfB&o&
zaxZ%hvg_rz66m>tN*YwkJ5)PC)%>OYLAoCRI{Z9kwEE>S7h}MA>cCx55SY1oo;<<k
z#$LG3ah{bhqJ{(CL%|G2w*RU{Aay7h0;uVLd~-X4hdUrQRr-S|@!yop|3z`jS;_08
zuaA8|*CDgEgKaM~Z~gPGG@*h6#%?za)nJdmUt-fj<Kd@c6l?ykKFhhu1;%?AKc<HG
z(jn9~OG72X%V3f!5nCb}s3;O&Vpqfbk@fOw7-&w4PZnOi`7J#POt2RB1gi8^u<;2V
z_+?UeC6~T38XxMNPyDA2>@DtmgtZPhA7q9d2YP&TT<I$cDDW`*i_2~e1w%a_{HS<1
zLav6I?!+^}{y>p>^O$RTuRXG87IZK^XGsUIsiU_>_m0X^6BPVC8l(J<-j@!Aj|;Ew
zd?d}!ye4=MG_5HpcbDAY1wqQZ2XndRz4SM(Z@Nms)mIq-=ROT7uezlH%Z%iS!e#-x
z`GxzmA;}l7IP%sP89#)oLB?KFmskP9WCDRT_jSSh1v5)-?4Dk$x6>K2;2e%gFCv2h
zhWlEN%N+2So7@J6vQA$x?VSq7tiPQ0`qS)I8iOTPr*pmKr%zWL4*mIg-RaacPn!`Z
zhrUZXUIJ$&Qk@3Io-C!0l)^YUOf8k4T_ne)u&mO46s>=I@vl{7RJyoS`nz;?zA0E}
zzE_moB}Ys0r$kTgbn$L{dkmY{%W4K#8dRHNrbI~p7<If@oGQ$g5lRaK3gEZwON)Dp
zk3SFQisfSdo49up9mOv{d^a#zc5q?DFb-8k8<~qmr#j6I*j@EyDzOEmiwc%e`BcJW
za6p$yeRQ@Mdz<;zYw0Ym&f>ZMFoWXc`76_y14iT_F29W4$r1>mI6Vo+ocM!b&oi*#
zoe@E_`X^hmoMY+R|2ho5<G~b@za~2o&+6(skleGxG=tGL(3>IXOaoR^fFqjoHUA;g
zU1XN@Yp%%uET=SiTT%YogPA<YydqfPNt1`**pp}g7ES8)VL{;~wG3v#?oK`|?Y9|8
zKrZ`Sec&4q@H+>g3x;_bHvRuuxO`{(6#=+6peb-D>I1ki<y632nQl4&Jj!fZQ~BC<
z+Y!p1x-fEk5c!)kylbCS?|;_>JuVsAzEhZvhwXcmdIP{)lO@Z=zRr#yQ;d5TB!}ay
zj|Kk+ByXwGhG`}p2MdyH|Kl2RE^FmyyvLp=9J=X`bK7^<zW+0KE|gtSY5$T1k;e4+
zNrUeP!_mvgzf_S}l*}q#`y7QDGncs~cu@C=vWtNc4Kl2us_x@3rhq9jRX-FraXAT$
z17u%@%ki;h_tPXmF>_2m3<Ds_=Uq;7;kw{~2KVI%<lnsYxq(xISz%S&U_0?ODv;0q
z+3P*6$3z+kci|sof0OdOfuKBa$kH$f=D-Ds&Xc_Vdhq|ExDrRzPxj1U_;)T1Y)X(k
zIV}I@XVW*Kl|SWbhS+rk!q}s$9FOw71%VPIYzP4dx{~L<>7u#6))&@tGQ)sbYh7F;
z(9kuu!|qp$v0~7xU|<&*i<<zgZAYX4{|qplVl8ftvSt_es!_s6tWIJLw*n#PHYQzy
zARy=z!A_zbDBvc5!uq*-#5$y&ZHE=sx4k{{{9gDPbddC|4cHI}+N<1J=bTbJKI<z;
z8T4_zBbh1rQ<$+4YqIyFFTw2lAeMI*1Skm`J_nd2cbc1c(xC|M6v<wsSp2dxWx`@>
z<ZRlr>$d<HvNQ{o{Drm7bh<BodK~sigJfpp4#CA)^KHB|>^_M21(@taf>G_|dKYk4
zpA!#Zl4lbmAvteN5SI4MH4;Gdx@AIqevKaB7UF53f}(<=@jveUeP*;MB`-F<O~ip^
ze1lc|8z)Z{rvMQ@Ikj?l%{RmS_=|;77b>um_dNng#lcaQYEuK2QUpEmx`HBx9MPXm
z+m!NYddewce`6H1=EI#xzftncx9W+@(=?qkhqI-L0Tck1R0G5x1V^X(eo2+TNwpRm
zp{U~j(sN8TRev^bq>>0(vhbPfXvA>2DM-*u;@H;a9Gx3HpTGf~X;ky^(q2(IyDlRn
z^2y1+a*<a}ME+-$_TA)~^2%DRy|<Lk^@1$2I;|2`3jIG3_;i<-UNl!?N4bqdejsus
z*ZP8PN*S(dQO$qe_FOwleRd9KK&SwJ7mgIw)YMRlhZgk~zC<*?l^Y65^jw?$L^sZD
zBIHqO9XG$*sBNdGO?$%GOq}=vluD;j^~6t_;X$q<<?Q_N{gH^Vo&3elk_xW_*&J}J
zYpMbpLWM#?y==s2Z!pNMyH{S@LKhfYW$3w%<`i|%O@H*%vN&Dz*XVk;BSuB2{`kFC
zrjZTRj$jI5;f@hnIF+yKev2`#(@t%g9r4}=zOUGTqvg=Rw_p$`CSwox`9rSdYI-OC
z?DX+%rx_7iPrLMvPyH3Mj&<1PY@yNiht1~o$wjggl5ZlO>l7s4ykjJqLE3Ov0#v2~
ztD7kL)4FY#!cB8Gb-pL+m-`LmnK+ZK%D&RC?jXIT(_FUH$Te~zAGNUUrB$gU-}ao%
zG5KDTW>?&b#OJ(kZgI=t>N(v&8j6Z^5{@j^qMu84aZ_*eH}MzH;yvwLXcY1~y&t9A
zp5|4)puRQ9#NO2y8N1%mqH}{k?-f%Ybmns`s38uTY9_QXp@LV5`{XOs>EQhqcU><J
zU1O}7${n${VGFLdOwI9hog8j=AJC(Bo%gPnjoqkeTJO+xH;Q5d*gwI+wu|X)2f`Lx
zjV}s2d4wKxEj33k8~ZK|XdERp^YUIw8tSZ#bSX@d@?0BA*d6J<9hTGl>Trj*kL30x
ziN_f-jq6$PIEL@CzoJZvdsxnKg`eZ1mu5otHAUz5-!nPReJOH<SO0omv&L<$nrJ2Z
zwco@p6l-&YvfH9H64E1!SF2~QH~*HoswwA9MOVPxC0WA=<}b2M`EaLjq^uQ3G)CUJ
zeRPlg<s7$9EU!Ab=C`0tg!Ot~rx}y$oB~}R*2_O>BbA{ve93^Voum0r%L6x6?CVjN
z$%$*Sq?hIVRxs*B(*Hz?;^y3YP2=HdsM<@+e8Hvrlu)1@fC9Hbrg{J#|HsakZ2|C)
z28`AL;0+ky1L%98R{)S14d4Zir>5X%G&no}0A*T6@bfx3nAikpNd9+kKSROa3u!&|
TSNsBs10E<ozE^a|H1NLwXB(_<
literal 47267
zcmeFYXH*kW*D!h#LI>$pfq?WbMFfFFq>2=k-cg#0(xsE2B3%%riWC893Me3*P^2qW
z1r(%%3MfUXA@fcAp7*_L-G8^Ob$`4u&V-qL_CC9wefI2$H8s{_q~oOn05BTpYhMO{
z3jRsaMneIg-py)V000qgdeKY=07#Miu~t;HQB(|7RKzJ-TPs?JDq3eN+Sn-C;1q50
z6hpHWLz`d-_=dG&DEU751OLdj4h^*qg^x|v+3<G~Mqy)vv&oyg1w>(7FqY7N17M&~
z>+H}_MKXA3c4#*IZ3@kv3~g!(ZGw-xIGC^v{I$X1@^E?Wxb`_*JCtp$nEj7NcBo?Z
zzwz1G*5sktP4K_$Cipm+-L#uM*_1swnLW9iXJeBG6K|i(n}eD{6`Mk>n?gfjGELdm
zP1&LU8PNoPCduO_;p1-8Zd23lWYg|$J5I4Z4<-w>L(pWl^<;MFWHyXAl#Cl50HcS&
z$)8<#5PX>2-JQ#`nQPCRn`@t&gXSP;w<&bDDf=J3Y%)qR2#gp$?m_{MP&*Eq%Y)|H
zAsCuW1U^E?egy8q`k?jJxAp^oFPi)xk+ihw3IG}yXrD6+%3f<(E!XHv6}eNOtFLf}
z<C;pri!XNhuiH6Gz6d<%?wzP-?BM^4{VLFyFHbX|J8kMDt$X7WpL)X3%&$=6*7?`D
zn}hFLl79x8xV?MG_vmI%oMq1TjyyL5Rj176=`V<T?N0Iuk+gXDG{r6osP46UU&#RE
z+eXevCm2p8>i^rD$>7YrNWH*{osRDhloNV9j@`LOix*^@Zuml9aQw48e}U=*qbPWA
z(SPNJT*7Uu&Y*;4Clz>x3M0?TTjU#^85d4v-J5noI`wM*{}hQCXx;0Z3E$n^++@NX
z=HBLt_`6x0OJ}>SM|iny_L0(SZ);&er8fTPpjuTkV%>3nxu7|ti{bhb^-KhDPO6*g
z+x!4uGfTrEb)#P`S6+Wk7Nma7q9FDb?YL(35m5l6*$TZHEDhsskkS$bjznS~iIQMX
zBe*ihMJO4O;a_%R#m|ItY2I^XMYP$5HQiGd3Y;NJ962n#vW&Zi*n7{>qjjFUp<GKC
ztg<=0me(5Wq-*h7e6Nn2bv)R*#))VvZ<=oBebn^3;H+h+VCj#^{TVCJYWJncP2|UD
z!qi_h3!V#t_6AlKcZW!~A0Id)lJDsvH<;RahgF7##8^Q1AUj#3J~}2tP&abpZ?wy^
z63&Dvb3qoo)2+jy@zmdnlvpXmo+Dv<xdpSga|q>MFe02raL3m_FJ8fgBKDNiU+|L$
zFyjSqTuM`AyY6&&3*?3hsa6g{+E_8aaUjBGA_@{&K5Y|;DhTH3U9w%EneiSEcKc#6
zNAHW@@8W8w_86W71pgU==KM1Lm<&Y521I)2_xi2`66`*NZ)eVlL3_b-?o9!o9ojxE
z?X^P<?$C(e15#72NKF*~5f^6v>`c1*sr=UhB%<}&F5$4q(Q{auuu}pBLn?Zw9&P45
z$4}?+V@S8JM^=4lr--@7>b03ywJ_*#TzKWu*Lw3~WHZ+OtB!$ohlaXd&fqB7Q)t?f
zNC&|cE9IT6-QS`4uS`z#=(!4X{d_<EZNgM)JAK<@rN}nOog~VQoe=mfCK|z}@%m^`
z0QdIwch!P#GG`(+a?7Emz#N~tUjq^I5HlH}=AW*kpq7nr7f(i<DToMri8$J8!W{X_
ziJtyt$zFB*^8)ouD_vY!IGO`AcXf7*a<}>Zs!g=*Iu9F$memLP4cxW&Um$vvQ|+H<
zT&uMf&(Vw)GTGab+0Mr`VamRZzRg`x%g<g3L~N{+>~fO&La+8vSj$9gZ<<sZ5}4kP
z?lj+JlD2OBQ{j!AwYCpam6h&p-AOp=7DUe46A!96ZBNDeRKnt_=YM_glD;q!Ul(L%
z#Y*8Z`0A=p`QG=zPYyKY!3a`i!sG$Y0o?gU{F-|6OaTtiU_0#3d3U9r^4&$q0mqI|
zq6Y}mOvjK0hLSJ`pRz`NbCNBwd9^8ZduX~ALzF%}FtJTBdq~*-8Qd5sG3yGAeHl}i
z0=YUksLoM_x>?1s6?*DgxPAC(!pm_*lf-Ym9WDc{-NfeB;aa#TcpRnZCKG?Ye#-RJ
zM^6a2#8XFgiOmgX+uka$pdE&z5VOTLlIX}?y$ihrg=sXp6rsR?jpi;r1F|>mQIq6P
z`Zg7Z+`Stsucn#K=MMc!{qgjplGhMDzE+PE5{y5zS@$dKqG@wasm=IX`Jre%NiOj6
z%ad3uu%n!}LN{!2@#<8$xQj|z&)q_vKw%`dHpt5A1T3clF&Y~Y?0=~X>dKI7g+*ln
zSPj_=5QrH2G!z#%3NLdq&^`u*9?{c7wT*9<EOT@H{?P1zG;ZGBX$E^n$=<lxAMK0U
zKs_tG+6av!%+P%&PW?Gg*=DPBbmVaH>IwBPxQWD{J|7Vi*}fYL;Pz&ryi+o2#qRgQ
zt9jWIC!Lk$+90lL4@tRf;P=jrST`jl3L3lrgZ9T<MDyn_tq_59SgB62$`DXjeJq<`
za6G3jnxlE7tw{KS!9r^D-rW<fhjWBI0m2~~<utHsgV>r^Q_8VWs(O0j(8~VUQy*&o
zZd%XH8hJF;Y_=Z595s;~3_ET(;Gv=CP;t`uoJe6Z7F;$|Dqu@{Cu>NSej6-(S?#B7
zWgtj~sr5^Q2I>w9pA==;_c6W>md3JJD8t8r=4E4hYXWJNRttO%3VH=zbrp6~td`nm
z9Qr8!(l<c}%H(iT$=tiEx@+y<sPXn+0DQSjxkunQ3av@D0$PR)1!Fl%zSgXE@T%1C
z^)46QC2Ea6C3+BAetGNlZF?SA)4lu_RXrzS!CK3H${C-oz;tH(vx|hl9H8ADzKZ`x
z>wro4=c8m!6MDm|sDa>BZd$VO6Hv1=5ly>e2|zf_Lze={+#pRWYX%agj2><Bx4EAs
zrP1L{h>Mji4=_kHzd;`o{bt;qs)`|t^dk`ZirXD3)xiJF6$m@*m&rh2?_Byt{o#94
z+A)Lt{}UZd@Wx?f>y(Pk(;*;~F47)Fg&57&{iQZcpl$vIB_lRs1xS{-qt}G|*T#{Z
z{AMhmwdG4FaE!phhu@XW$xqu>d56>6Rjc3CTVCpw?K&#p33RGl5hDw)izZ|H^FZMx
zjiDhZ{9~&uGIb3hoX~CkrU_<7k|u9i$#*=G)P!$kNY}pGDw8c+!L&TE;F{!8D*wsp
zGe0NDIeLBtTgg9NO%iE9{do@+=SHx-Kb5b@R<1lO`|hZQC-5EFE6l9eDLjn51U`7B
zGLsjZe*{xc4aE_8rG?q?A6eTy(sv4D2U2FWP;I@_+$mlZM_(N8?`{9SThx2aYO}zr
zF6x7f&&OYm0xQg|x}T{;c82rEjSmIF%5hAy^&67Et4RL$*zqP`AvbHp^KTUTsJ3c)
zU(EGxzTr^d6ki;L&?}mAul<%}BSOwaw9JOKx8W$7BP1cr{Es{}fttA<X4;d=Y4JAw
z=5IuE>*eeFx+ShRZ!qHB{fRr}OMkm>Jr8Kkue+Vt>Z?BaC+zFc(FT`*M7;Xxk)2^M
z@y(GKyJIxF{<3Skwr!<6Mk+MtZCZGt`?(U({8=b{{vq2;?B)l{UfB=^C68{t*;A%f
zU5`6<&i0^b27d&2MU<n+fi*@VIE3Vtus?4Z%^4MSAGz`7k6gGRs^HPJymREh#Rg6W
z+Qvk%tWkeeIoGn$ldD$Aku-J-TK;;}=NVLFb!WB3Yhj{JIUhK!&&5}^9@WG%yb^Z2
zJ#W8flzopK1cup%)nk@;Fp_kWMM;qn@BX|?itLujVShWbc@@0R)SPxn@So<6l?n+V
z{Z5#qYB3PZ2Pe|rR;HfhHsYh0PNBaWuR+DDQv9fi?mmH*7+)Z>Fr$6st8w%1aa{K6
z*(BW3&JbZU<u>E7U!8tCG1DqPzhX6-iN>vr{)DQ%x1aV72}h~8Z`*CghjP1ekH3iV
z{s<KN#X-3y)PpT>n?jtR=(16l^(0h(q8exzKYfEkfNU@ZMni+py;EQ3jqUV>!9X1t
znW4JCPm$O#K+P4w@UeHARRIwc@posnC>}R4b3sk*od9XRX@x5)ROzsq5b<J~aF!Uq
za+>Jnh&xi>%kthsb6!iL!LJ_<KQ`jSf*rXtn2a5w@5VyYq+=cQ!|&T+5oTMnYK*j@
z7^K&w^2<`GHr@wwqnmM90{yb909Kpct=a6JqY`s<a@tU6uAvGs84jKM?S<F6itxr9
zNV5_(KzidbzT()10V*yZy58Pt=F5mP9C-Wi^8x=mW1hIm4aJjFA#Xv%nPXCZnDW~t
zk-zNLqed8?(k|e1$mz75A!x-7n&N2Ie;zL*M>uEyPPdLdM;3DO&BY3!rgNU)Bme)-
z$xpL&Lvh?6+Hcn<15Z7!1Sp)m2Ev)RpEI#CdgR2~11Vbk;oJ~3f^l*7i2DyI#s!@6
zKT;O}gU0{k)E$f5aF(}Y>B!(-f6+dSg7*iuov1c%cQ^vyW@H1M&)~gFz4ArC5cq%=
zKlfQ4AwR|Q{~pj1a@G#x#rU9KoD(b%=H8VE0#3w(vFCRIH^f-1^BSC?2c5B(BtbW>
zGxL%TkVZ1N>o6kZNyi7{E+f1-!2`ttQ;+~XxKi*CSfRL$<0O$zM3rpzDCDd(U?|qj
zBqLhU6+u+d$Y-+!pxXAl&WQD++N=ThV4@Hik?}(tq!WwN84*cZ{N{}J1$J6|HIUCf
zA@UCq-zQX?P@A{zM^^Iu62w`6JHqMAS-O9SG=9?Jb?|fdOGL@@qrHR%gUB}TkVSej
zq6jl~5Dz-{O-;!2+ZJ>LtR!2QYP2Vrsw_V1A5}g{Ix?`D3q5GV!My%RmLlWgFg5?j
z>v^Mpygsl)fPF8R@Nor7n1g!MPdYMTmy&;i=}VRXG>{Bn5IdhkW_KLx`j1`u05b3y
zt}PT;B2ePz?0Ww(Aygtm7V?$+H~)mJl?IrJbuh<ts$`DsDF0i#F7S5Mn`4oNeEh#=
z4wr-gA@EncqXx9sY59wKX6Nr$r;@wKf8tKkLU=oBLRBzD4%dG&K3;^JZQUnd;EMWp
zfwv2}vG5z#--=Etd5-S7uR(n!%;10j-2lQa&%m;_VE-rUtL$`bxGl>e!DN`tm*Q+>
zT}_Fz<K-|7P*)|4$X(|@hENK^h#|2^Ske-g#L1E_y(A5C7XzVMcx0hC2YKXsaZY^F
zjHj(L6|BAgn4T=a9hAZ#HUBYGaW4FlQZ{_y$$wcc8q7ec|HyNZku;Z}L1no7KSHu(
zLcy2LgB-m%vQ=tR{*y#JD?*;zI0+UDw=om!YOlzyrg#xB)RA3nknC!_urkh){qZKO
zfL{#%1N1*4_#Z3yzvBp&_Yd!j=fiGwSA3oTpBBA;ZIT^~!xgS@z|lUJe466?&tL!T
zb?WYI@b9MQ2@rhp>zrh0^S;KuH3K{3je0IuBfzk$EdjwN_XoDBQgHzG&o0yVIQVpZ
zQytub-C63!1{vBS><w;-a0_|-SG43mf*iNqU;aZXl}|@TAl9XMlzI#gJ3p5eAL%K)
zPQ-<iq!!6jy-?BtV>~Z0wTinHuTR*xF#{f_!?->0SGHl?rc~6))ge5qrquNwNGI;N
z$Nw&(KE#Vpy5ghxV2lescgPqo<mE;$v%fi|7z3#7h2dCJk}&oU78JWX8%vypbI@e!
zTv~j-?BEcY;OU3=JZ?o}oj{4nIe7Tbc{=jU7d!R~uXBPyrs|&83vMvMctbLW$??Vr
z=GSAdsB>XvuKCcC3BF-rFtSNyp>8Xe|9!J+jXl|!xuT7Xncq%(P?rU4V&bS?%Y1&a
zIfL%f+4F+yjvaoYU#@W_(1Q<~^rzDjAS%I%f4m=?($e%2d^1A7xkl5AY8w_vpMxbM
zNZ<F(tUzVHU3oYT0WV#Pv;So4A~;tR>d~5EYW8jwa}i9iCOf14p`l<*aFRbIMTMtl
zI_reUtLn{AARWJKmksNdino`U!r83_SXo%}9KdtuU6?0xn~WbnJrZfK1ZH7*dBm2J
z<%ONEt;rl_V8Y*Efor81z;XqiOC*XIzH;VlxelHd?~Js2M#jl1yQeHv7wP2E?Q;fA
z(R5gw`a)dSWn|B5!#jX1ACD6ljSm6_K_X$_Ew${m7CFfjzx()*91Vc_()9h1!m})H
zTRI5HRgXo?@@hqNMpu+JCUD#d85RsLAS!L2_HjIjpv|N3r==~G+yjl`XuZZ1dI`36
zZttrP)Nt}AkKbreLwHM&eoJwLo@Ctlu{W@1!l{@5jWgrjX9xlN<$pp1bnB~$+Y_YT
zAR9mQQ%FkB)ub(W+ila#7BkM-`094y+y>#q1P=Fc&oORb8=^zb20(_zzu!s~>_H*&
zl?eQHtD^UjVDy!)bC-bnefGa5HZjq51J^9fbv;xIG9L($K9pRexlWYpTH43aB7&G^
zO{j0A=AEkfK>RF6P1~yAZJYgS(K3{s8VDdlp;?@`3O&|Ct#iv%+h~~#>O>ssUL+Fo
zz@Ck1Dc(Ol=i=Iti^-n)?xV@;SM&5h(5sV<zRHM+b0;oTn&CGw0*|+$cS!FOA8ttl
zsiLLp>0<BH+s3(KhWM$Li0;Q_y`IXHFWrAzZBvFhMp}4fR*DY3cN`jvQ_x9Rg053K
zVYcoCLY1HL!XB<$7ceUK=Pf%Q^qdyeA@RiIW%=`1>sFVYRLXH}QhCT{(YT%nQPv|M
z6G<>|`uELyvELyk4$~}>6}81zhtCJXb%)LjXE2pNB_wq%o+a<9(OLJ^sl0ihDzf-C
zb2uz#v%+eKTdj{xfiy6Jhc0?)WI@Fo_&}~-y9&G;ug9`R7LL5ltDZC{6FGyTpUwVG
zh*nicHg8R<$<3T>=?32uP4O#!KPFtXwu8Hy=2h=RpblH??(sk@HOtUFQ#|b+P6*+R
zNStxChbllNBZBmO&BrM-OktIF<`#<cM5_g6aK}jR^Ipc+CMO4n$Rj2Tpk|C8k_Cd0
z^6w(qd$$%ab_?Ca;u~jR76rk8__ZHBb(om|x++;p4dlL^mgGd7&AxQ70=@aeYm5yP
z4_+f?TV6d5=8r6$KAsPLy;=d^Ymils2lff9MYq%zF!z^<#bqT=Hm953H)?ecqCu}(
zk_E`IPTTn^7Hp`!Ug;EMVy{+v`_9Gp!RH^pO>Bzxk{OKt6iN&1*wQ6HLjcE@q1ywx
z*c?OMF&?PB`&K_Rj*};?&|+`f3tk(eYioTQBfCvM4zVGEG@k_2dU=hyT$TxwSLUQ0
zIoRbn&S&n?4(Wgn34EPL_DQh+N=Q1dMD=F-0_O9vgSUz#3d&C}8BAMhQb;fQyh%e6
zVCcuhXwTW7PjD4LdR<?V^c|qxADTaHY^L)6`z=MHZQE&BZT&O?yq3`$?i}?*1bM!7
zm58EJ^a&uzK>^N>j>EAXduH-`>qQ_u^vXhE6g7n+M%cgVmaRlux71+~4g-U$9J^+B
z8R93+IXF#Aoww&)3Jw(zB`KqOLl#~~Ju6ViQtiPL=Tl8($+ZTQ*oj<6EZ8{8zl|7H
zLRlcJsE;Z&p%0xK%BDcsR)v04_mWD^rhsIL477{kB<bBcoehoAf|j3be^-9q!*1zT
zWW>FWRO&2nYH}Q(H=;i05cu2S2p2QgGYiaa*~=(Bee}~FEMUycY)Oa8MgkMC7(~EU
zD{g&Q4h?1()(!(&TTtkAm@lLU({sCXpkfgB+hq2~u@&edGH;y(XWQ>us2Cj!c&*k`
zG-psCl5}D|fD&Ino;P>XjH29r<d*OiHw{7CE427GX9;njaA@o=BR-9#jTSqkW17ET
zW>k(HFtWcDvVaruM#^VFY_!-z63!R_gxXkkvy{S9L)uacDA9(93JI`&2&q!e&J*3G
za-9{cvyxv0qp*;JrS7rd<CYh@o*I1VXbRlv9Da#($$0<r#c<fC7aZqj*jyG%vPbvi
zO6=ys#SPt*1#QP@u)1CqALJ`ReZ36vsm7O9V~yE<b1u9gKgF%dr|vGNNaI@Ji2B7-
z!`a`63dm&j(QgRTQeN+AxFSvI4va##6QsK#8xJ%X&qhpHff9+0eLd`3l<>J|KKymc
z*)K%7W+vCZmtrnAk0DH(iOT7qCX<5NVyKnM210-T>jtc6v{moHn;ptjsYb@7`fMOw
zc~tuwa({-<mS*ZK>ye#ka0BUIDXjJ?Z&A92*z+&oYRfpjQTr}huqm8&0B=WzUQxCc
z1S^!O?K8))fm)>9+Q94`(#@ymG9A);_8ecib<xiMnXJA4GLZv6>(2dT2I(V%n21QD
zc|PB863+o%A?@^m7HQRH&Ial2OtREx5gn=!cDYpo?n~v~B2bk?f{#bE`G56PFF&4+
z;4WoEA@d}g@|5q3e7tE+#R4h6O5W!~nqT3CbpFm?Nmzumk$IQ#FKMv>2<E3!9WV_p
zFwH*u2ATJBOc7_)eB;6bq4!YIp!wZ?!2S1$?D+Z*=E&qRXxst$lN~&3<!V_<LRzxn
zpU=>;r(LQvx-LviS2-{GHv#%M=CN1M)@AUpaGV9q4!njRR<#J_4RJkh8!DXIZ$z4o
zvUezy)ruxQmy6ETg16tSE9JtIk3TO%!#vo_XM;^NW5J&|yhBo9yPK6cLi{F;vtVjg
zicTbOVIA75j1XOFwKRBBBwcpG#YYm6EQNJ|W@g0%54G`rEmY^Op|Ey8Ybmkc*jzM4
z7YL+G_CwjyoC&K-OX&D(Dv^&549;#@qw=;4Xd2N6KgMH|scKmy@c!?t%~bO{&3P~1
zU6a7d{z!m+>RoR4yR_u;qCys2rtDpVj?-WX*X3oP+HQTAh8nH-%jd&$yzAmxJM8FP
z2_EQgQsLCCOV2M6b8oQiJweKMI@8pV9^46LPhbUi1ZJ%}NBe2{WTkcJlA#V!j?coF
z+)YBxSM$rY^N>CQzZ$HD_<kCt^`qtJ{#z+E;pL}gtASBG_;QwMEgZe!Bjg;RL?=qQ
zZ^)fk`Ms{>_SBIs5l-f`{qSoff)VI_oQ5PGt!)I1Ue1E)b)zgoIqs9vI8UNFa0d72
zq*4|YN$#4d3Y7z6H4BhG5}ipQPTBUVh2Yj%_Q9or``vH%-@o2-f#*EHyz0DU<^AEA
z(X02d`$H-vRYK={7jS)7Bz$dB+}NQWT3~anZhq45q`k(S;31x{FzN35NgZCk=Nc=B
z)Dh}T6Z-xFl%08;e;?hVVB4STFBkN$t6~?lA`#RS-<;dXp6mIPvFW&FWfNqdQ6d6G
z(}JOFF28<$vxxud1@M8BqKDZ7;WKGlXUDq`=(kqX^tIz0=js`!L!eaIg?1%x8zoBg
z&oH9-JJtLq9anw9MU3yNkN<BpBruWz#}1r4V|H30&pYT65<Ru{{K0{L_xIMFv*X7F
zdU|_Ksl9884)2n`sj0rWiZ0Q*_weO?e=RS=xMZz<+*;!%WJX-Mk}wa+Bb=Ttnmc-$
zJ3cvHWvS|lBgMx}bA=07>n%{x00L+XukQ^+q;3xE$<<@nAVb!gB}jr2eMoCB2o`OF
zZM6az%mgS@e+5RmF655)AV+CiWW>)U2u1KfQ4+f+I`?yNgi{c_j6F`kZ|Ho{opmDx
z=`M|x+Ew12p?tXSg*2_&zCq;DeD;MnM3~8f?xFHL>Cv``GOD)5PiZR#{9DlxxA>Fm
z_lP9IJn#@gh<`<9EHvR0pjsk-AIy4N&4f*GAvENGDmxC!9|u>spa~@>zL>qVY@uy)
zMPWaB21zauWZld4grzm12tSgE4Df)U996xW%;46^Hq19mQ`7Euuia|5DAAkq7D()r
z0%`UA_uOH2<Zupj<u@YPi@2<wmxb_d_If-QGf2PAquFNqlv-Fi`v>HM(D$;_25}td
zq+{JsBa^;W(4D)-;3T@&=m(x~<66?|wdqP_TmiMPl-&j=NMWlo*HX*x6w%T5K_JAp
zv{$<N_J_nCIkdvh98#!^QEi0e&X{T{>~)rt)Y!Wu0T%FG84?<$)sU4uPs0P1(s$#c
z_>Q(E0*=IOTeG@Xn#Z5E^@(~1IeP+>+?Q32(#5EW;k<O`oRcc8P&E87_)aDdJ_cH(
zTp)A|V@dI&29@^LsL;1k3n3<1BX*D|l((!_n5|m0eT!f^nbeL);uGWOg2eor@=!bq
zp_E(^s@a>4*KROFMG`vc{ET}TEGYbA!iDFL6o1bKUJ2!unM?Tn{G>B=Bu0n5pZC?E
z&^>3^tHqh)9nqvh9eIHp3g~{9RBRJVXV|$n;|Sh8r}=d-coNJNiwc^KzerXnijqz0
zGvLBGA<*TUbV*}$*qyv#9m_=M!p-UZ$`4UtahE?Y;Q|rNbr;?McE`b4yJ`^R$@F4n
z)45h7M{$Y6H1H@H+51-i(-fP9VD#s!z57hKogD`lLFmz5?jt!Rp}zcOewU(ZP~xVO
z4SJ2%MOTZo**?Zc{=6r74zP1Q8reNhXIgan)ct^7!MDu&<w!gX^`n{_QjG6?D<1=e
zQ)0)}HZlcNVga+njdelu*Q{2H`d9dYsy$BOM&nNgY#(mp{DIz!t~XD*arO75E2*{!
z<v`rF$MJXI5Az!g^DUSh(8RBa{C0NBjdJVsq}4U8ya}%(1}EI*Rt{@x8xrkm@&~VD
zHl$D-k^;AYdpNR89Qtr72GXF!&YYh0CESxe*v&0ois3K_dvtp!g~VM>F*@AJ#B-76
zWlD{N+!ZO{&>5nuEm8_cY^~GnJm2>T5aKUvlG5d`_H&;`FhghQun*3(o>%%d82ucP
zOw5;3l4U!AF<9=6IyEc`zB6-+gP#<#?reAl5=A-1x8#w%T=zN|sCvxN4!oJbGn&y*
z(v;X<7FHc*O*x)<XW+zj4q%2d<E~rUfk^#bl$3drP$#b7X*ce(?{qOc?~t+P1E>Yn
z7HO(v;?2Vamb6687d0mkkAIY~npvjR@jwzk&A1Ui*wGTE-*mp4XwjFOYWu%*F5kl4
z1SOaD);fd|A?vpRq7SwSPeGgcEGO$oBf$+}x*EGR5Ld{rGe_k7#pK^|KCxrLl1_@f
zj1`2$42+-G({g4kW6ixWAw)V~mk9ND*lrNieN0G99H5306?pF9JHy9azx!wR=}SA@
zD>(qxBbaYv`<`AQopW&r#C3e0Zu(3EP)~qFB<_n`8r?cD&4eUp{Kp^rtFdZ{s=*6`
zpeX45x@m+Cm}HK*VBY;?ZIbZjNmY~H;oQ1-M5?7=ycl5eSvNTeS6pxHgb=w3Lq9I!
z5^F?3%GXT~YCE=~bqb#Qt6nxumq>IHL2UD_L5B6cI&*6d-;UC^pe?xkEGMb$d2;HR
z_##1liGe5}3nu+$|BBXml!Rr3KNP3gn+a6byl7M3EG5gXEGS#14&bEirpWo~I$5k0
zT}n+d6ddLD1ovD6_{u!;P$-kge(b4podTOy=KXxaozlz)Eq3wCInc}b#28=OgTAjU
zPpU38?ttDG@}Zn~NlaXLuGs1t)5g}~yYhfewWGNAwLo38#}RHdx$~Q9!Jn4iwOnxa
zCC$L-8&fOV1x)TwI4xR{kqwu-ED9!7THf5)AS3~A<$h~MHqCFGh~Y3wrN@xLkc?wu
z>1(PQx`&0PZgc0k5z0t_-^?{sl7JqEZGFn%y@_3Ad*qT64f)Z4Za3c?VZN6o!$Kt~
zYx_rt%<HSxNgU39WxZRGC&n22UZ3oaC{V4cl7yq~>Bnn{d(gq}le2^~irdzgiD`NY
zGEbwS$28b4qF>KTPfLtY;q?gvLV1)>(yzevzfodX_^Fm7r=#=?g?_vY69C;1Z*0sO
z<NMI*N?SRXN`T1SpMSQil56whSXM<gWRJoszO)K_YZu06D5oT)OL-(KEwr-!Y<61K
zr!Hv+QbXt$KClFX&ueD40B|C@r(EoXp0Aba-5{;{n!JPfk$D;AvVV48Tq$yQ{nW!D
zjL54ld7rD}6rL;ar{{V^*DP(X-FeV<hekGMi9LDK@iE~7b;bLf<?#*2++ZQn&`I!h
zi_gMdTs30*%yIj(AkL8^Y;WY5&43Lg%?`e2u{(XcjKDt?RSWk`Gjf9W%-TAnaUbz|
zQOb<E;hBfT-)JyDUG|;EoOD*fnLYMGx|m!Mp$DR7&pQ$W8GxNz+6<q1=!_Sco-}};
zD={4}>4h%vQ;uKouP{TXZ4p{P%n(CQh~!P-4dV?1i^em-Eda~#GZQWZp?`GI#&^*r
zla^9~H&x-mN!;*YAzalOC0$#2j}kFgA8hDie-$9|6t0w;`5^4TcUpS|D_m##TJ@{O
zzh7%hg#DxL_P@Gvs}48y>mv<W8`+n;C~IbMvFD4vu3>e1__eYgKp!Zv1UlN<yUVR7
zF`Vf(jZ|4%ty-wXJD&{Q6LuCFsF*75icW~4yrQq=M@KMu#=uVT2wAp;nc))(yrUCN
z>fBwKgMulsYG9NKj}B*<!2|JcG*3OLW}#s(m;1+gSUv@|=bD`Tk69Kd(z;jlL#)w1
zhrr!Noj|t*xN*%xnNrtFZ@aj^i|+A8@WOQm16m_go(tQVmtQv1Y!2RPn(_!6OgJSa
z2qsr4CqhdGd(Gzij<d{JO>G_>&{3y9(MtwYO!Ag!*C}4Ot&a3{0>Vo<_8_HyJ-xaI
zW2(C(u0N60jgw9M=6R!4658hL@Utv+-3Zntsc-_Z^6KY;B|9|LO9>J0^mY^?w+P}O
z%M-~pd6Br=ea`OW>O+g0LfDDyZrtf-pEoW6H@IrtKw^$Ew_Z_`ecungK+YP4e_TM{
z$<<~CjjSB1Z&W%?Y;bK@Pg{sQQ{LjoJ~}rzv+;O#@8q}HxO2%>s)<loN8euV3ZuE*
zGzrtF!2;RRVXb8Tw5S$3G|;L)l!(oz9esa}PYuvL`(#ro2V@R$1Re`xZ>B`e%a*JF
z-uR@{sCvNbkXOl?%pp{|H)9N{*x<sN*$<)xLk0EqtEN=SNiF^;ZC_)J=cSsI;&xY9
z>$I3@gFa2Nn8Vq!Jc*vjR(!wu(=smSY>5h7tHmF(Z4gp{=@rf=aU*wBt=IK+Vqa5U
z)(%<Ck1?@UP&!#(P<{0D+{%|3D$A=T%^x_-pM1}si0LQ0IgWE|6EiOG?ip+7$~^8k
zf?2&&sa=6<>uKa0-*^2x!Iw<Ch*FJf%!Jv+H!k{`lEmC_FI|+`H1+L9P=mR?p^zO}
zo54qBOPzNMGY~QzJ}Yz$#zc>>GS-y8Vm$dWo~KG3|0wzDuM<{&D3vH(ZJyZom7#`W
zWv3kjSV~?4;X?<#zmFDQwy%)`#mdM-D0A6x1^i8T77zWU#LtX8kctw~DIQ4X5#yXK
z{NtgWdQCgyQONMOvsW5fZ_r`C^5F~KY;ySYD;eDRC!OI0NKb(eQk;%_WBJS|uWxx4
z=Zc8Q<yA(;rMHzFL_Ue~+PLC0k)Z&#tU40t>?e{8d;ATTpBp#jfS9j3-ze!kU8w>5
zybzVRms`lWjp-4nT)gpOt6$jn^b*b<Ve0wfCGjt(X6ZpbmCN-XU(e0W`$R{iG|Kp<
zTwvns^Q-`uAjcZYmmbU|B>n2Dx4sl`RCl~<LDZ{I@urc=_rT0~5-TOaa4VJ6%}U{r
z&&X@yLa$a#eb1@6T}geMwo1*D;$lSeXGrK6`=2lG#EL|Ws^7&vy2Fy$&q&r7?Uzk~
ze!FQwp_`W=+-cG{J8%i4-L$%-7p0(J=VKUmO+H2ao+yHunrCgF#PzX~?)2RYjq9^l
zBKdR*3Ww<W>}8Pm;oXRcM=$RC3p_*@J^W^X;aM`oK?y2agh4%TKLtJ%`3+5xeMc(C
zsojpLd42~o?D+la-Lp+I#}0`^N5t?kx&^m0b#OpgGPq7UX%XZz@L>6R-f81LC<~dl
z<?w0o__YPY`BA)j*`|%b<<>m!h>N?g_gW`R5yNkAw~!-Kwr<wU2(2Et44|}txgIx9
z_$VmqmG*3Gi;x5IF0N3VH$9K5d*AnR^x-0k+1dEnv7+V@D9RG&7xL><j+ffW(C${A
zswGQyaF>QT#EqDq#{;?Q3X%p+AlLU_D89)}hd#K2?<fn~&RHH;&y4sNwplCU>~2b#
z@uca>m7RuE6k4pQeq{c^9CfWb3tU{wzA%K#pMC;8Pbiejv@m`Tm4yP{%c(|<{_Q(}
zx6T$Y*PY1F`a)40s?TG;>qft4_}G5L)45aM!<!Q>{I6biCZ?y!O`YeMlvMP+N*dRo
zD%&Jz`|o!Kto=1cV8t%DM-I`?YfhXU*nIP3EU@yy4q<CcDof@DH-gbv2v%!=(0%AC
zlMu;p8}T44NnvZno#zA8{~LjAy^5GEm2IuQXP#EuXD|2kw!syJfV&jfPkv2*KPLO_
z!*zA_ex*yyaI5OGP}<%-xxn7)OEoEeHMSuybX`RXJZG@y(%Ok$L~~|s%6HlKx1Qh3
zn^i^V*nK_*enm7ZM)M<6{TG&asA&K<eVOi5iYq1A`g@~!W6`8|4Smm4_Y-JvZ{P7~
zU^Y*T=5wAn*c&)@!+9~{A(K!eEo+n}VZYNSK*cUw?(5x}Pi-Ng2($~G=P4<27A7LA
zGzU>|shqpswXc?@P7mG0aWR+7ZBlx6lsgH`T($$~v?W=6R)e(@+a{JD>C@@4t$*}w
z8E<F4qCG)er@FlAiK1EOhIIbH1QEv@k}vT-t1S3)u@mBa+Lqt>!%f2`zXQY!h<xCr
z!Y4?jfQ=pBn*odco>6Dpym*kw{;@r{G1r7K8rTWFKCIVD*vAYx5b}?g8T4&$5NbgQ
z%4p<a^0e^qi8OWz!&an(q3G+kN8n=O?Rt6Jb_pTt@;Mobq@%pQo})K($pL1&Yv6Jp
z3N6{N%aGSR%Yevu0Lip6$kKo|qh@4BT*t?|T34@Y{9w1b6!FSzBM`^AvzXbSOAj;^
z((V}YAVAyRP`aZOhqz0TMzCAO2vYt&6oLryrEB0fbKgJD0dyD&Z4BfcBxM{dZe&sY
zGTnCQksL7F;?Jy~t6DDTQB8e-)spIl66Rft=ops_u+A@tB*$j~LZos^r>~`s9YFQY
zTMexxi}b6Foxf{*ROs*679!9F6oDnyj=hh^1Jhj{x8sf*kA(5?sF8(|efb@3@5VzU
zyD^|UfFCBAik%NdY~(T+Tgr(CWko&Z?_g#=c70fD&M<%i%PFj%l$8&x9p@Le2DU%M
z95?=^psJb$cYHYJywMi+Wk(lN&seU%VFF9+8f;K4(zHFmV_&L1nG12TVv!|15&y=$
z&PS-m<kN14s>bftOo!u>TwRbs!_0e%<j&4i$igGpZ=Z2(;L7L2)%cuPXq^(cOTO)T
zrqb+0f!{W?+RAz=lK7re7W{Nj#eFKNfh<X^R@FQkPvC9B(1jv_$19b*sXLGjWo9g#
zAOXHP=0s7CAz|7c+$EMW>fno0&bA6CwTsKvqZAL;*It%N7<KlImGN%3YvYF>Y&zao
zBZ|G33VXyw!+Gf?kn}2^CxkFzf1g!CUHxN^X*YX_t72$8;G>Ue7`y&F-AfK|IB0An
zT>oN(L6xy0wAi|Ff;ToWE1W+Pg*s1hjk(E4g^Q9_O%T_^qp76q!uJkzCH`z*64t9o
zE>3+S6UnMk)=2;Pg&dJ1V<NkG$wqeLE!^&cnb(qqs&9Yln+=_?MSQV_$t<y;tuTue
z*mMVe5a&Aly<mIgNrzl<5ej>jQry7dJXm~J@;dphsHY4ZO5|NdA&JBOG+FYE!9FN~
zt39s8GRbQK)gP4a+iR=VP$d`LN=oK_ei&4Q`mW|<X$#otlG$#Ls>Ai_y`-%7bC_@y
z_j4Dr8s7qs8pWPQrRfA@RZSwj<|!UCT45FrYUhX%|3`cKUgD>w^G~zmC;T}mnQOD_
zW4E{7!!0~e_M1hoF4}~mZhD1uHF-AZkfu#d)SKzYwNDB7`|6J#X1a985FfS*6uO3(
z*+b<Q)J=hc#U*37DF=G_=E=1X^Z7`mJO>oIhFDWhCj6|J6k$^nex^LITv7IB*yYRZ
zEaR6K&Rzrxv`X=CkfC(_`~yn08!6%w1&=o|=K*_6*cA<-kdPRn%!hj`WeQr4FGsFl
zR;J4{<SqVn=a{(S$7ML?<CIC;66{7V;ENS`pm-5Cz=Pe}`?C@f`xteAFkJ(@U=^F_
zpU#)pM|2MTXmNxQ1}*Gp6(9-Q%H2%@8??`!c!1LfArfsaM6Z2*{Pxt~b;syvyt{Gh
zmhQ2k%YH5>dDmFtBmdH^!N5byJl<n9Q$GS``~L0ol<lIR6z#i8&KLR^x+BvDIA#-w
zUeciFb(QoPC90`M+Ba6GsUzYLd+`@i{SH&LKh8X8QLTSp<v-Ok9@4s55PZfcN)_7)
zN={L8+SH3fCkH&=d?v1p6+RaC$o#OstZh5&okiz|XWJqyN#rf{EsjB{eEct;?7)3q
zsFM`^3RlV&vvX_e0`$g@xdiV(<;V7}bFbcpO!jP_*t6%AC_X8?DFup`aGqQSV~LPw
zicEeyDdzp&cIJZPmt|5e-aMS$Nr6<yg%`bf^B94WcMl~4+P$wf<oW7H1R525H#?Gb
z$arA9=1M!7CWRLUs8{!v*lX8Zkn;4<g4Ff63b+(7sga-da#qRzs+?i+TcY)|B-m;5
zkR>e1-VLXIK^P9StWXvgo%oZ$Knded<y)oZJqMc<*d+`@8zW=<gHCsLJRRJMG1XzC
z?MSLN@GoW4ILTI!8_zKtM#MydWMX=)!PH?fGI{Wk!M%?yUycYRUq5C46t;klLkigI
z`02|)awE6p^Ha!^l>?v1`iZD>#*eu%CEU`<K4tj^5-S@Sr-v;C_s<%b0bvRHG`)1;
zqG`|J1zAl*`pAhNBD0ltxbJ1viJeN%(0yH~ykk)Q&4oR=4QslI&>LONL0US8SG?;!
z9;CP^AWTg{-gfB+hCPrG!(G;mRK+TBv?0-wITcBT70QRuG*5|TG(ECXvKZ7iS5eDn
zB}Iy|;SKhNW`6eKG!xnRq0P{{^Ql)rGmCK#{F+e}6Hj5o=O=?tAKxANET?_dLIxa)
zKKdCO+kNf1ro{xym__@&^Hm~SzijI-&2HSNVl?GOh_T_XlM(jd63=zBj~$zB7o1=X
zR;hojAtcJ<<_>E!oT-iS!vlBwQcltQL0kYc{uNagwJ0xewtva%d{fXMMJnU9vPRHn
zC2Kh=N&3vvQC*P+_Yfv0e$sYb<EEpt$tB)V0kQPg^V3=UDGUiv2@f6YlG{!At?Ynf
z`HCUo0>?z^QZOEtTa;KA$GM9lh?uYR_9?M)c~t4&Fsdfn_j%A<DI!kiPO>yKtbHKR
z%|9Wocm*sFy3x*}%b2u_HblugK2#4N&tTJYA|)T7W*+S6)z3UWL9q^I3|%Tk<uU&C
zAo)>Yn8owOfQV2Lk<*V(udR&ScS5SYN7I&!Uf7=ueGdkEaNqiF6UQg--vUIj(f+tV
zCuABF!*jxK(@_e1JV>81CrqLiO1*{ng3*})tVg&m@ck3ixoxHpKKg;Jv>@ps$C!j}
zs$2iiHw$3gk86MBK(x%fZ`7N<Gxo<OWQ&-7R_LN>T1zdEj_SoWG>G(ax7}A%ZqGIx
zg``d=4Et)wvTJC3epbGIgB@*0GcWd~FY8jOo7zkIm4lw6w@B|Gcttn7{db<wFYE&5
zFwgXU;pww1J8)4apQ9eB+}h6-16nKl>~`6neWRXdSx}St4>5@&vWVfIMpD1N;^2HQ
zfArS}<gW9q{D=<cjhZXT7H6UzZ?i3Oqy?*zu2Ck<68eQ);Kk<gKrn8!no<K&&Oz(;
z*2wH*EI?sjRrIgq6?V}A3(^m*Cs$<*%swA2EZn@~B;dcL&l?d<dj;R=HWH&`)CB2e
z?3y9bMi$)=@h0P5<?E8Zp{<TXwr!=SP{e0g_g+lcxv*3-tE}@CrSIVf$JL}<F8nNg
zLG9<HtFu{6M+4&8uh3rOK~K)w0png6$>06TQziX!Hj~z*-nWq=)_X%)yQACJ?{4vK
z5&r&0d^G49D(ejx)I_33NTVc-BdEHfsf=pd#&+Mj-5NpUpv3y(ML$fzYU#sew(}D$
zCn>hl{lCfXi49RbJ@h9MV!-fJh7Pca7=O`rde`<;(fRrn;erlD%&}ZCTOXDq#Cdi|
zP8xh^^<jq0m+{1<XDTfux$4N3^l;~GGoshQ)3#5nsn@rKk;6M*cXTlF2EQPSJq29f
z!)1!Zngx78{A1O&Gxa+o4lqMF>-im`rS%m~^ysB!7mG~lq$^vvJ%&67FdKSS3!!gY
z?FN)cwW*qf?*k%_TGZk;p)<#M{LZQ>HkdptFcS_89&)HZ0lDsEZ9BSNyh)e{N!3W$
z-o(`anh$+{_-<Nfg2EzkgDCA!2QPO7W}ZjSWgg+Gw~G!q=PZ#Wh~XWT462FV?WFcI
zAwa1B_|FkOI@prDB<^>*JPQ6{AG;sAh5K^~?$+9vpyjk*69(6R-s<b3>?O|0+}^R4
z2EhUE^@ZX3;~n|6;QF2rp_EL-P!K~6Jyf(~vw=I@#V)(x7jO>@S|V3BAz>u?A(*wR
z`NJ(<mG|PRc?$RM6~&O7Y33r&AlqjPXZ5<O6ZB1nBRfy_kUN4*-{DFd4v1W0AF3Q~
zE4;^DA(_Yl<|0bBmRJ6HP&5jtUn!DSB<lZpdqB#RY02BhJ>G%L52R|u;Zn2uW{?I#
ze1%XoaX=JHxv|#o3wIpf+Q%HQGpoEF2(P%!gvbPKAF?p0tAk%Xnr?o3q<~1aFq`6M
zH{6VL-juIs0NKgV^Q*@<a{m}#vwV`DptidNP0XN{moHE<&c7vUAxdW3AEl{!mF6I5
zrh2Ds9O#oRUiXhxHYhQ>6lb2D@j?d9VeX{2CeNLN)qEk}l?6)Gy*Ksu1WQJCEX0FE
zTef!y7lqU_v;2g+UrO4c551!t<80su5*vvW_pm>CedI)j<m-5lod5}qrS2!$3deV5
zCvQ1kQ+{9O{X%OrbFY#M>@(}5zq(FZZwvh5shULQZ9DP!tvfbcDTT%pJl}9&FO4({
z=5K_|spkmZ=0ltjfGFSI+{zs)pEq4nt{Y9TT!34koo+Ha@iI^98c$2c`;Askrw4w#
zaA8prFAC=}*aC?vTCB_LEaqAhFXWo}l%YQ0LG`wMBAJ7S_!MPRt-Y>m$jWo`wRvYi
z+uEDU5C4oBJG5F9XcA!yk28LdY-y;6m4>8f+pPCZ>Mf$7(Wy8cB^fB7uX@Wq0lG(t
z{{2uIHBS{B+a`&+3rsN#b0)w0#XyK=iAuU33actk@%3$Y%K4PD@Sf2w1G4=rN=#qo
ztaHqykNcytjC%<5Pv)UP$!6!4W28^p<}DMvBZbUbm=q1RI|zR^{0Zl4Pb(=s<*w~5
z_+{R0LK?_^2H}r*iCpgKrycnr#nG8e=sYFb57ZC`G^uKIK-M32{GB66P0h^nl=`2r
zh}433?skr!Z>pX&ldDi-8crv!RoAUTDx{mEGtZ!4B${g7cktE1vBSj}(b$%!Cg9Cy
zin@{fphpq~43&9n9~qI@HYfz%gRI!ea^e+8<)iLgPo9Mck=$vqMfaH54XQ%h8J7+G
zZq2*O9m5w6i9`gwwx0?6=zdNSF|3Pc^JjWh*9O13u$dcp#{JF}(}*Vq&j}4tE{oY2
z5CtV#>df=iKlCeM8gIp}umdN{_+5ewCHi`f8#3<~dU$jBK&JZ@)47xXHkZL%XA$+0
zWB}}#dP7u<bny?dCHOt)UVa*<mEywc(xsfdOS49&7*&QHI2#06@fS}EFUTK6Eg}b(
zq_clbCvI1$@Bene6rSTrSHF=jvw&IU|1BAD-lc&T>igIYEhCcyhUWr~*H@}u{@W;W
zJ=GGmNR1~MVq7ub#HDloX8n<?Ob+-hEqAj<E8@P^3%RG$Q~yeP(~sGcCX%fx`fx@!
zf+Z~HaDIs1ZyU*etO9pqkicu#)9k-`0m95Lhgn3fb^B4GbB~$UU3$&FN#*W!QHtEx
zNqW)dYfrM2UJ4-&vE#P{nFT<fzwx6xEz%62M3V!B4y7%@+s)RqNWF;Lmq3S(YF+Eb
z#p1%=tcm1(A*L69kjGGNkylT6OErtD_e$|AG(G{a;VvBS4@Pl!Zob_b6&BUz1oCig
zih9!QOABH%T%mF*XA_FOh!7{)GfXlB$?14Mryq^*0fmnbt|HKbk*B|AcJb0lo^oeB
zD+M*dyWw0T9Z#d-Rb8V!CVNE^W{Wb<TOc9S-R-E^G3^Oe!qr7Y^2cH`;5&no`o^gB
z;4DWY6ik8L%ZvJ)0ClkTIcSQF71Tgnm1lV%OSrXTxuZLjdZwE$?v)1;?BHcs*LzBh
zTdjAQlsfJxuN`goH#m_?6Y+*0y)KTuJ-&t6b0W?p%Yi5Fno3&6*xyGrgP8bHxJf1-
z?)7NuPjW49m-p}UgI;B=U6$o0mv84;ADOL5V$xong8ERbV+}mVuiXdC=kvTT(`%ah
zfRZ7*Tg6$94N8cOM;yTV2=fwrGESSjlk+f@-LIXj-e~pvhUdeFS5`ZqH&<nQp)dsg
z<ZM^dUp>n-6~4lozO%(IpJj<${m8=HfR>V~grj@jeBV`H?=QU@rU}g8E_9fiG_Wmj
z2Q8KhH;lraXi$^w-h_z8(uorx6r_IqZ4|pMHWpMJVe(ii7M}*Q)|FYutqt-ZMpvYj
zEW4rE&ZT|1R&J5V7uas-;*$-6Hn@DJX)l^9HrO|$i|>j9boF$N-)vF@lDXJAB3*<~
z_Q<l9p(w350e=n&V2K5Vlj7w@uc!5;l<2o?#?|w~uZPc4oH@&RbfC7$r?)XO^@r6y
zfVIMf=7}75<F&wq!*2ckfkMc;qY_v^GBmORPrp&LpH4cM2U0v`4CWIHN+4WM0AJ2=
zv4y*EeTHHdej`f%076en^0?FBdD72ynOJ*N;-S~>N#)y)L5aq1Eynh8qlHN09Qa-C
z-qYNT3Kt?iI%k?oQed0*=x#0dA3!IkHLsO)y?T4%nH+MN1^=<Or)yuXQQO@-H-N+T
z_TBhRf+^^r(Wji{%lOK&!0U!B>bUH?BkAFXnCLl*W_@C&QW30ZCk?>jw!nr=ON0a|
zURE&p8I&X{=3bxjjODYRd=fxk!Q=b?NZnnfef#%u84s&%dDmM6_`BL8Wtokvcj}xy
zfsnUH_2yO$J0YMeD`}8J8sxzzoM~ULca=D##RC~qVoy^}L~97S)yE<762Ou-3hFTV
zBs^<}G~Ir8hmnB;OtQ~55{v1_msCjZ&O!+N(~;@vh@GbS2YzursN2`%P8X}a(boyR
zlL@plFO<=LZ02*L16^YrHqx`0#hKLoASABhBrj>JWe<woE^vjDCCz&(*yC!Q7E
z<^VyCnr7fO2jU(j9;1$PCb>`bDHPXSBc^W?$^c#wABc&3?jYhg$>RPY1}}t2UPsih
z;`z_#T^GVCHgjabM7|5|iP=^vZaA*t->+w1G-8|+v3mf)ug4ud7oULO2G>d2@9(S%
zKwBe}K*BxU8n<#<Ya84WiMzlp3p62Trglujjc0eEjNd$i$DwWcNU$adOh6bSS%6iR
z7pnhWP$tW3;zyuA*8g|nZeF%!c!qW77@b3c1M*;Fk0~^UXf*!w1TlJGXzRe4IJ9+j
zk9BzSnYcHUD+0=7s?kh;j-*vF34-D$j{jJp!A>uDPsga9qha8}--BZA_0C+ZHEzf4
zHGclBr!Txf=#Nq$rRO5&4<IZsOVT}M7e_cRrIg}#Op6`pyXTw)`OeNCF7@<pt@iVt
zpeQgw_#8nC9Yne9;~%aO$IqB{!==HE)`;JJ0SIyR__gT|R;Z=^J0JP0RI1WjS@KHQ
z;s>9cIF5*Om#QgQgzj0hw8}!kgs$m=O-$3D_TPxGJU)y#sEx)lm_Iyf=tp1)>rJ?(
zq{k5|B^5RdA&S0>X#MIoL8a0q%!=Tq!DBXKg=DCCVV)y=0T(e@KskF}0>piuzY=%P
zga!P$AEB%lxY{#LR6mbC5Bkqc<t8s^Io-X2&5oWcj^A+f4gCR${8c8or`z>HzmOY2
z>LvTW8OcpUHmXSMS=3eT!GQ0pvon{ZbP9o|;FG|qHBCY9(}*Cudyr?t?L)^Ga9Js8
ziF1oE$d5M$oIN5YX&2Ggx30;Sl|IU4lgL^fP8WHe+Qoycy8qBaNq4;YIF(MD2g209
zWA2mRc5c8FUpS#-sETHRkT;=4vYepkWy5!cR@@0f&T-$c9Wnb9!&B!Gc*h<j0#BS_
z8Slza@0A!q7I_;mLHoa$`to?FzW@I-W9-}5vNQIbY$asImMx*EWUUmbq^#LykPx9F
zOWCufkYvd=$QD_m2wAeH82ez%{oUT5$M^C0{X6&0x#ym9?m4gJ`Fy@Wx1{pQ8%k<&
z<2b{fRYAP&aVj&D(j0UV;ad0LCr{7q^Qe#{1O`9IT!m=XrAz+xO*Qh8#Hf}VT4Vnt
zffJ!62Sr_zSc~n37g<5n^L2a$(5=0poTfiC@Qntyo~P35M{<`8cRQ_q^qYvf5WniG
zJTn01)c0&^HCCPY+dm>GurH_9L&jd=(kcsI$nr8-GJQ+ECaDWP9bz~BdIcf60%dGp
z<Z{v(5tpv!>|46FAM)>&%Q}aABfD6;aX>O?ur6M*uS>wjzTpKMRMB^c!}zo+k*^sy
z)rTXze9g-fOqms#0Juc;5vjC8Pi8!TPPF?RiHAPE&<{7Jly5lUPNFa?N7JC)o*@B*
z^%%55i?dp~jL5Oi^tbi2xwCs(J%};pB)zXDeCV0%l^^${nB0zcLGELk=nN#m@WY|+
zM}}WZW}ILk(6%G2YiYoX>BMg-wv7r#(SnUe-oHoeelYgTAW1E@dsir_yeiF?DOOK&
zY9ibc`FDWcgtHu<qo!<GAf5SQ_=^{n0%H9IzRcunMn9p&KM^H9!!2W<mv*k5W++}g
z;7Wb@BpnAt0)FAW*0VUMkA}~G5%TkfGjp7v&yp_hTdVda&L%RP-Fnv;+Tg)-J6hTN
zr6_7va4W1ahEEdrL=#F)msqA~YB?agg1ALAe3luwP_xZIRX;Z)_<@$~dm}(mkO3i<
zeMdkB3rA`G85LLRdbfp4BFHuAz(0U^%;{x7gVHR1t3&`Qy@gcQ<kpOwyOILXtl_`F
zzz#JT#GJc+p#gJF^|OIpEg$+}w=1HS5%Rmng~XgGF|$!Pr`iWYK9HF5Y-KwHRPy0M
zx3<S{D}VDwjLr&wu%!Zu{qPrJ`WLopFG>tk<xa8MQ&GwA`;L9Ne@W>$wG;2L$xFij
z;>UH^-nHnu^QlxmWm|Bq3SV!EIWV@N(=S+YlRtH)gpKd}63g7b<SM=wf1{;|841Nh
zH?zVi<(v7Ws(?Is(gkjc`?=!Z$(ssmjz!)f7m8mwFESE(RZnvqw)f;1-0XnTps!Ec
z`?S{_OV{y|kPHXtZq3mJC^P3F>DNCfmd}45Lcb#>ob=36blbbKKOOl9bHHFD7XJx;
z;3eL<8`~m$&^1c7Eg<fotDjI<wJX0RMAgMpU2NTXsSdXJ8i{%qCr<pYi`Qi^QO7
z?eb1XsTY(_JcImDIV8(2E!OL21Q2=Lf1F1<`cEA;FS3dv<b&(%AE_oll?><%H7Y$N
zl}8}$IF(&iClRtk5kzQi&=5RMU1pABn6JM7Y~-H4g7SH_eS9|@mz-kJX2;B$QsWkg
z2Io5P*-##5%6#dNAoQbEeGi)nOee#hI~bm;op0t?G30mpdRh!TVi-MR=j%ReO^p-B
zd32N4HeJrTCOrGN)q$@j>rzKJ2*2b=Vd4afH};NmTuKg?SBp<^g2(=ZZz+$SYDHhu
zndBJ`vWaP-r1pkK!Hh0F*ke=+8NLpuw&vZ}@lW}QSB0N+eYG=vFXJ=G`})+>+uy@3
z5KMv|WAN4)OgtXe%KnqaRRfA<B1Y}0yiYmTl-fdeX$x1RT1kS+@HkAYcdoBhb$rD0
z%Z5jpKL4hw!!91mTz=`RwUXY21&8Y{ey?pWahy>B>KiU@a&0D|Y_r(N_sqDrhf4Fn
zLm?#eVP72+GRK)FMRBajIo(%N(A>KCg6<Pf-2>4gUc!kz6?GnmV^nscHKMqh?vhyg
z)?L@`h)A?O(i+b-dYf_~>1}d~jm^bDp9*N5?;~S~J+<ewnWcNtaq1>tEn}~4$}8a(
z{ughaDqSb8`!!#8+K03q@P2B4)59mcL2~k0u36M{D}^`R{B*H8AJhZea$0sfi#E#*
zJ~~O#rLQC{)8%$s<cUMeuaV$%r$n(5r)F<IGi|%BM2?LGE_DIx7-6tp)dvG6RlOKv
za+@6>goCG30Jq*7k!Lr~fbYg%Em3M=)57w@?Rd9g2F;8ob{^~7OV=60FC%fmeqPj~
zU3RL(^?2y&(IRlm!J=xV@>KE%-x)XUQQEkg@W>bCDqE=QGz~Pki>l7o#K!q1wOl`%
z8MvAwv`#|nFUrpu5>`4O)wHwVWyO8BShD0Vx4^uk$mhA#o$T6$9)LN*Sm@@#7+5cL
z*Xhx3nw+JFi?>%58|ANa6K;~AcZc*d_~dN4ALJ=IE+#^u-98-%eXTIFx6+LJ0<SJl
z<TOS`ley)r+lw~!hc`$4%uA#027?C{OuMC$PoztG@OJAR(6KaccHEGprU@>p&`|*C
z`>jn54ma$~q;T!O)sOr6zRlG$$Q#uw19oScJ1l1Lf-sGEIf8!?pCYMwIu?JG|0R;7
z?%I#234Kmcdo7SIXzP1~p6vj|{~{9J_QYnJpF?3@vk+!(z4^x-<joh<WJFTfH4VGJ
zBW3AO4K~Yzm{rVT!`4#FC|ve9i#G9J!YA<2v!k~tcOKcmA71$T1?PmTWy6J%{ATC&
zxV7wQ#6!1U%p2!@ze@Lqfr%0_XT=(9n-60lZW-uw;58v*JppK3JPt~62jYzF6N_v;
z_ob3(SoQ6zB%W?-V1Ykv&dns2<P3Ix|J|>pcYlmM;k28Sg<XSL=#0oLWX-}!*bZ*n
zEWz6nntKv8ndotGO$s!wC3+)Jw6JlaT>hf-J=Ks)+AgFHQ2`{4JDkYtd^;-$Ib2N!
z6)J5#H*r6GE=N3#Cejfa7Q*U^?Q?vV?)j2sFR$geCZ;q^mzapeh*Z(Tj^AfZYIY*@
zp@}v58{USs3yeauq0&#!wpXaz&5O&@9JOIDtgu;}?s?;MKUaA6GE8HK(vg={B<*`(
zq~4y($}X5#k&${-N}TW+Tx3!I^LIox*AV#T(m8ZghS-d}aWD6NS;W%w@}JvxoSK?;
zk_V3c5FWDG@+<`tsv`b6aDpD3h2u<}2`&$Gks^h!1mSOqC2?FIyK8^upPwoS#r49u
zT|e3!4dfCa?6GTd>2%C^nRntU_r)c0M0{NJj1vSy9QRh<j_;T1tTH?r_33K-%=i!f
zGK<gs0VnROLGnr4+u+TGykqk(r=`c@9xosUuCgi0iqAfYtqeSk6|mdSKjY9`xN&<p
z82%ew2Xy$=mjY9vu3g0haVa(|w<?6ye`f$Qie!pJ&P%P{07s*ncmCw-W~Ord+xgjN
z@jr!v`<BTrPC)OKk5Do4(F<ZpT<8a-W<Knr-|P6_9M&UXlqF^#<7YFW&Xu7`#l}N^
zKA-3oX7Hg1^d_>H@Jo8)Vcuq-EeOOj{kA_wlLcEQA!Rei?e0fYlqz2ThqD~X?tsjf
z^#$LPnjeEXO%C(rzfx?+)}Kq{znnXQMMYS-#+=NQ0m%ur>w==Pyf5>!jN#rz{ECN0
zGyk*}a)8G}(YxNjjqh_UyHUCxI7XApKase@VXa}*cJ_jgpuJ#%`7_?*?VL&LQ)HD7
zlC@(Q(Btc1+rt41&Mvy*_fAyA#cM${Ykl@Km`;vQww?;1N6rY*s^3BiLRaHD@Dsy<
z)Z-k4G(quUW+2Ue)LWl(<AZNBD;%PHSI#Pc!u_nU+(#dk{N!G={VxF3?0lSR7+c;B
z-9P~+Iqp}n?-{=1BHPbQpmz;e?vt)$vU7dEfmO&c25u)JUX1TEKArz6Q~uvr944$c
zE50L6xKe94!EIDd%5Ep0nw;C7XvWOB_uHRpeDW?bdwre%9_~GD{qt3a$dHu>Q>Mv(
zlhxcid69aY3pk<B`AH|+zgwT?tC(NCF2aqaS^R||m1#Z2u{HmkML&3x6s|t~MSA2N
zqscukIN*lw_N1ha3UxyM>V($_@2Ua+KEh+ZhBse;poR1EirYW+)UI6Z%AHzL?LnI^
znn;wdpg@~hu1W`_5x0(2_%QKDmU{dp!Xx96^C8myk#(xlcUq_`m9Y_hQD!ihe3YGi
zY;;)z$@zFqUa;5TF-V*KN7hg?c?@Z*jIB3kf?{z33kZs}xy5LP+4<VowDI$#!cO&F
zJS$57yVM8#Wzny7(^E&s7p^L=p%9q#2v3&l`UAIxEfXZur^j)3TA}FmX0?aw&AC8U
z984kG+>_XIlw$T4!pRB4X8m2`FOJi3o*(j=o}bqb{!^#TOMWZc^S-5ido(f1^i3io
z!Trk=c72~d_>-boR1+VxzVS~2=OdbgKjgK1(Fr|AlEf(Kx|DZbR&-zZS>*{E)eko<
zrLV=jV~Jq<Gj!R0p>1%w{A3}e>aO?+lW?_I)XlngG(YGziL}J}#0duU{uN3mvj#PB
zrde{`R~^hKJTVnuET5o~i&eRmGc1@U+liCzAF_CY#|@?p_gRzvO!rveE|?(vJ=O!s
z`m#qyC6OAie4gch;G1X0WfVLgq+lQc?DnS410(kt7!X<M<=|#CX7^*6TfQL>+SzfW
z3mP}XsZA}?yNvV2zHanqc=b`G_*3auZBdjpBM?CR2g9*Sz0Wcs8Zg&<t1#z*Iq=+o
z(Link5oK=4k3=Qcmxnn>3s<q|FWQmoCu@Jzp7_w=&=P1S3@i$6MiWi}k{s^89x<O5
z$@c1izE!j`GkPi_Ead=&Pd1b9^97#0Sp;=o%*!a+6gc}_(XXZPrT=Q$ff=an*AM*I
zc`5&-`B1ZF68LU0C_;RI^fsfKNcHx>_>#{GgDjxy!XtS#%~?(~mhntsaL>@Sd-r2Y
zS|XZ_Pf2k-uP(sH6@ku6vMH?7^<~pP2gYiGe@JBOt_9xI#=jh`MEao!vv~vjvsecY
z(p?5f)L`NJVzcx+Za)+z8iv#m${ZBG2C4nx&*MP;eNfn29Ou__pZ(ax(2S*W^o|Yr
zI&lV>69a5!b)s&lDk}osIsDdL09}m?{QG;;<?^L?W@Zq|`O9x5&90>8LUCsB3CJ%>
zI`r?37Yi>i)BnM8FPQhwdBclPxeZ7^9%l3TVSZ~ezb+HXwVJm@xd)mvz*E=gj!}D<
z+s`rVB~p~S?1}hcTC5ElG|mjnm=`a|MzSSz@oEY*1vno=jB-z_qa@oJBO=7uzi;vd
zLMqDzntw&_5IiP2`qu_H(A!W<x*6?s5XGu|YXN^NGAq#ZZ#P*q?Cg5>%i<(T5%$gn
zA2QY!upxN=j^K{$K$u;^*EF|~^kwd8O)`g2Btu8go_d!ny6G=NG6SLE@L3-B2k-LZ
z_qTWRXfd~#j{bZ>Or6IE6{tgoFX9V6Qx=tz5~e9KQW=e;k7@0Y9ujE%AuPrWX9HD0
z*m;RIsfsEL{j<*_cdPHq<6El|Y)MGWV_@@9@!;m_c8}1nr!G0)cV?-gr@J=sFM(q`
zlr&RD87Y9_)$kn##0Pj+v)6Opt*5C090WHOTP-9>=`Vy>Gc7xxhE(Llhz)FHw`Q!M
za8-13M$X~1Iwh#u+X(mD58qDVog|<8KczyqklrV#h9f~6&HndPp?AFkSR|Ex_tUv5
z*v@8MpsyyFl>}<1aDXnH1Ny64*0mHDX<++oowgL^`ULQ*{JAp}xn*Ct3}~k>;1)Ru
z?>9x8#uA}#Ll%44E(S?V-|%Tr9@1xT$_@zS`qYim@yuv8FcdEj8((1}CPppt0R6ha
zmb@9o;b(>dX!g_=x7fP~X5$YUFrDs!GIK}kCKG|kHuzec+QVc<R;f(sf%=e`nHaWl
zy-W9Kzn~9Gv9vZ-^OvZ0;$u{o4K+S*xdJ|?hps@1gRmPY#gHKfn7r8#wRDiw!ummI
z05Ce?Mk%u7K8@+hQ>}Z9b>Dy)7lFY-DSO#MGru}9!L3@QZ*&VGo`Gp0B>K&b6K3yj
z^)S<7Y=Pnh-7}wA{#h3CI?oztpp``e8H(9+af}~bPlD8LZo&-qHs|y`hxSN(y9@_g
zw6E{nK6D9LQJvwl{IVhr2u+bUA4MLop46lzUVt-}y4IiJa7qVWJm9X%g+9Dq&7{oS
z=MH>&e}R{f+)1hh=gEz|sg-(y=bJ-)hMmD{j+5E$YWJVJDX-E-xn0`fu7-*oi)BH-
zy560y$Q4H7fe2)qRcycUA84q{F#|W5zRHOX@C)%Ouo~{GHK>E{$;I1d$^V1WcS^qA
znFx3vOpyw+roMB?bm94~@77jDjv9|--lw|EC4bD@zru~I@FYlnN%$|<#hd*6g~4ZN
zDZdkc%;)*J&q62KWed*x7r#!14#U`USYcC5*~iBcWs3$aXa=3@lD_(D+}_2QeC|~i
z+l?r;)AZ$>@h5hHawqhQTaC(9=)geu^GC{sr47>ZvusK8WzXSQImw+;(c8mw)5np%
ztC@F&%-KD=^RzwisKgLD?v9Qc)8(FZovmw^?S|U2&w&TV3;8Ng`gp`l;{#~;@tfG>
zEQmj<VxAlz95~kuYIq30#H`-|p`Q7(8%ODvWf5H~8P{lzuk{)VA_Cw3uH9{X0xNjA
z(S?{HmU{3TS2U?y?Tdb2f~YWLj)^$7B1-93psmjAhGkD!OOjN=y@PibjXGa$o+nIx
zmpiqcaNn<cxBfBE&HFad^s|`}mvP|>ekr3y+a(qn&XiUsJowj}ADq-h9;AKWB1DVI
zG2l1gQvUPeCzWP-CGpdm2#@lrYI(-8JE9UKX<J_!uzA!}q_PaD$b-;5(c}id-5EkP
z5?ZeREwHjzuB3m?T3^mPfs>l;0z4T?dLP6+ccs`ER_$ByC$l`M4XX}n7Rr_z+M#Sj
zP|j*x4OvWz)X$?qd;GJcB}%?tuB`DC7tv3(;uyC3zUg9*bJjEVT+F#3UhP0jX(j;M
z7!VtE`zPD-pO?w{ts|~W|7)<mXNlrMTapz;sTZ5rX?q`w>{`a#A(ndalILzyhj#CC
zecn=qQ^%O=wZm6RMWCTzW0=O7bdmJxI92o1C%U?Lx%HS;_Ya3^E?I?vuO+{<q010a
z+yQKjDO~^T=kCx&_U#&r<i}U2yc1u{tj?c0_cQ@&brXXI9ZtY41==U6Tv|mE`97^$
zq&h5no&O<slLk`{@rJ1^IVXHPz~B4aTyiCUpfqT!SsXHsdcN5_T{gkrdqqF)H(5o^
z)cf^IC>2c*D9xFBeT{T^dC}wM()*Ns^D;!qzB`A6!dq~g_K_&VrX4#;FoC+pR6Hu{
z`})WpwyYc4;!Ms>gU;duE%+%ge4e`)PJJ`XHK*d*PZcM@N#zs<oM;f`S00z|>x-bP
zM1KeRq&n!ki?hA*mIpJ%e%aUtj{P@Yv-t{DA_vkT_CbMAIjAJ~)Bf2@21g*N`?5X)
z)Y*WeXHQ5Y=!%o8k=9Y^NEoO%ZDuY~M)O6^L*K7u&H;I+Th(Sz<D6q)C<l?7kh3cd
zE@?B3H^pq^=6B$)o%zha`rXs9LHKcD$;R*;rL%0d>e4xnWd@$1i@@!+UA(rHVk2@q
zMfj@4DRDM7=3dm$7n<XFeF32-^s$IC2@ofd_d22!%l-C@1Zd^7xNA(!KaQ$rUJaa*
zkAp&vh}|m`Ew|8sMvN|L8$`VT=u?#=s)*O6E)dt&=EU}ds%b~*^<t#yv1x$FxiNnl
zARV7V^CQe;l`iRsFq)t`qoL1?oCpHbaRl*gj_tEv!mOL}eyZ}7ZuZ^cUsT91y>hML
z$=Q45S*W9LX&HdY?bHvnuE?DCYA>OTR=-qU3rUEv-?r=i-^cUNm5UZ8#ok<CnC0Ec
z%~2EHF3A(`(AoLYT>*0?7;uM;_CmKglBj?a2f81!eSjvcbYXkFV^g%D_|Nj@o>gFB
zgtbbfkm5VX4iphZsF@XPeOyMlf5^Mw&5gJ#DYSVxLinOpVlRuN)4Ml3$4r>D54)}w
zO8!Mn8!H`xE)?N|IuA71%2V>~M#DXg5(~uwBqsN~6s!mI;Gu5e^W;#pP}R!Q<RsPx
zL)x;~pevVC(l);3^jIb$mP?c(D}HS=X;4#1qK$~RKhPq-Ij<G=)g+%Ul7UpjfM#6m
z;_D5TmiEJJx7Ymr!9L$zzdEQP23W%@bwaMyNrNaDxf!db8QW;2O})vPntT&!{pe%6
zR)M89*kQm8xy#}TLHrA360HoD$3BrD_F%j0Le6?~4D?9++A7-%<Nzg+Yed48p_o*N
z9DsupJ$DcA+{?2!C)q|ST^|)C))el91V+o(A{WNvb!=#L<Zvw`^~=N&a+K#hKUCAa
zNiLU#<@V&Maq*9s3im`qicdA8tY@S_Qj19xAl=b2p~Y$Fjv1P~r<3Fcy9`$!mt6FZ
z&VGLS`A`uA?*{@Qy)Ag-Ck6;>IF@I7zLIo3fa;<T<gLO}#p0wvMU_a8BPnU!o^-GB
z%E4hkh-lhg{DO~7iJK6t#aM!@nuF~A8E)=%a?Ypn9N`phmAt(DRv7-v|6u|A-|Il-
z7{L1INj$q7o1{e!?jc57B=PTJyHFWeXPrs^(#1@b+`00?T3odYce5EfK-!!W{q`A_
zKG?w586~MViTPgm0-a3n(zUNT?V&6Mz7-WRWN@F;qTRXkUg3Fn;KJ>LxA)g=tOsv`
z>Ae%$K{eNYR8B&6+D^Td)S+ak5r#xJPki5m-fdIK+yqs`V)tS*QTGCTegBTqYB=Gu
zmpqt%E8RMW0K!`ZtSFb2hyDvKM8^R`39m;FkI$b2WvL#GR0!qL&+EzKPH|Z)-Lsni
zSr$#>!x(L25z)|oyLTNL3_OGwi(MU%2Di?$5PX#tc)?ctRNK8=U}|FZmo}#k$?$v6
z=)*=l^g>k%YHKh`ub+ogi5o6SvZcOjI}Gq@O?KcZ@Li(EfL4_)dhIFKcu9v>Bh9{|
zg>pRLBYGqZ(S^!+@{Nwdj(u{|^q0iRC>Vg-tr(_>eF#fq&7Y5>A=nUng&ATPn&_3^
z;&Q>!@8c>U9cWaJML@$Q#YV6e$Ir9UpZiwFRKR02L67683GkTQO)$YNi{DTSE5y%R
zsL^0TB$|^gF2SH#+k9cBu_)nxQz5YsNbSr{FHe-!8CLm)b-?+r_x#nTG!rlAYsedk
zf?pEty#)GIFX3<L&$pl+CQh!VsGl&|8)jZQaFMdBtOJnK)dB34_bl#OA(m9>JnbHc
zgPpc3<aFAv_tY>E_14h=g<e*(!YoXGrX5_zRT$4{Dy~95P7>HCqU-sj4oHgjMtUaN
zDD^IafsIb;PN>cGy<NoTqY989GcH<nfDBxH2Hi1V)xTU6eY88jI=~R{>Nz8Lkq5)s
zzGu@8&j~SojiS+v)1YFvDDJmrhiIU02wv$=d;NvQ5@73R#!Ev)O2|FL#SY;wr`_lB
zWXdc1J!C%aY~VP0Sa<zTbHfha7Bnnb_YU~-Lyk58M!}3pRmI#EsC0oP@&}=F6q7r#
zstV8xW*oDB5c?O)BVZbp%0ClB>$*HB);W>OepB3qIfgCG%BBdCq0M1G?EFXG=*N#8
z>%y;f$kQcOT!TH~M{mCp-~V%Dt6~VD{b5c4x401L=W``)jsZ*)K$g4>-khW*O)`@{
z0srsnk4K6PAS>mgc2Yu!i6~&#qd|2ii5^c_pPGu?;k<u^sAa+P=;xs8dFpXq!ahgE
zje~V1;oAl|U&TG{wE{kI<Lp>3Zow|s@`%4&2rYm*#4aZ?0_NG~4CsMh1XQf^08~8W
z$Iqpuz)ok*zS>gtq>TNHf{JNotT2Ly5uBILn*E>}9~J#7vTUnhpm-(o2o6gJ2W6TI
zfo%C&savfs>4<lLMp`m-5|v|y`t<f<9m^{rzcSyHV;=<ilS)K*g%Q{Mnp<l67;W=%
z4x+EGm0P6zIEC=4N2OS3Qg7~+@5a8xs(?AkJU*CP771)cXf98&*_}k)<JAwh(g)ra
zS#Hs#*+^^tXD&R1yqwQRNUc5rIV%J1w0je5wkjiJtMrsCq|}|tCN&FOsSE}>F@)^x
z`KRAx-m_2hRyS_)<1epPmz%yeTE+YLD`HVA5iO2)kF!d>5eM|V&d~D79eYej#J3(z
zD*Y*bD)U>Dk@tl#{xttF5ONGWbQhs!TLF@ep9IFfK6%lBx}7FM)jt!noYml3Ao7{%
znz@O`kDpEM@3o8WVFH7!{`E+d(n4~%;^^})u3$m#w_i|&1x2L6+o@4K7MQtMF~Msb
zL9_aYH!X`>>G|IW1?ilN3LzZUe&*No$*9uQn-q2kv)9jOvQ`mhrd~i<JpDc`4JzUS
z8`q;uJ|vCQ!Dua+K4nTO11PI`s|aF{MpzLSdBigof-<ae@<oA^ty<osFNLc)cZKTH
zk)9{BfEPt9@gUl-=Cqwl6$Hao=h0xyYodEY>=`}9WU-CGdUr4P-S7C%ktB}u@C)E4
zwy3dG6qaV8g}I@$i`nhsuO#S=-^V%l7MeLnUPLjhiIeCl%*e!y!7?ckOJgQiVtHtZ
zb$$cVOVMI?Vx1lSa5<2A5g;e5r30@D-QS#9d<=>A8;$t4oy{JNa9_X|NnuEQZ<@rU
zv|VgX?*gr(7kup`fX!4^A#XtcG!2Fumvrj9m!ICe0h#6BnBZgfvfYgRxpw-mh+d}7
zcGKQ)n?JvJP8qYdzlsQ4bXBjF>N(4egpp8|Vu<OA%j}B4xxCq5#H_qw%x<T>#66;_
zKmqq{FPV8p{f%?kx=SCVc{u3SqHrmSdW{J;!(<IV3%TJnAwtk*n>(vg!@u}|4kPd5
z4L-dvzr2r`8L!;04A>7g0`6Pi>fdM7G)&l-J^`oI5m~p`;RC3^YD1@dA`-gc`QiJG
z$&HP@as?^n_uAR_5Ov2x*m08$ABN1{d;V!De~ODm&#va|=g}&E<QNNQ-#F(Ylabu{
zN)d~+%|26y*88+iD+oO^in*H&u{ZmnsgVn@ZFx8DpZ>fNRlo21nRaf{8-cD`zo%^Z
z?z@a-`gJ?UcBP}sZG+Y?f3hc#6%Bm*TWA93HvCm~9-5hjY08OdaP2_nm~a%=CkGvH
zSfGNr7BG}O7}=~EcW8axUw8|b<<AMe<Y1cK^)m3&T+V7h6F1~&2+Aj~Yx;5dxrusQ
zMpi_uL4zV;*+E=~P_#w0BHQgzuW#<>j-|QR<o=uD=A;Ztrz2rxBxx?tJ{hY5`#lLf
zZ{RvDCIBUqJHwsM?44ehJd&$cGSm5#X;0A}eP*YXxVl&I)VHU?=2bAgrO@F)+}OCN
za>ru9@;-DIMrvZuie;<su@@kz5!l&dJ3XV82q^UdYgaOBv3w>9caKwho~~2+Yg$;O
ztO7`IZ%UOD_(a~T`MAL`&HHE-A=FKKh#l*^W2aMw!vF1crfI={H?gkDIjfiU{pUcQ
z$1L_rX%ghdaW|65X{_wj`xsJrDG3(;i!mUc6e{d9C|2W&EpbSSHX>bK)R*l?TM4~G
zRY@TpZV_yJlkk*}b1T`FY|o)8SF@`O4t2(Z9nkjkVTKjPk5lmsgtJrrmoI%bL#@hF
z)}%pYbO?(S`u<4HS>Q@T@A>t$l;A3FrtngOa7b#gs4SrBl`+E#Y`YEvuaq9Vo%q+c
zyNv|MO@Q9z$ll!A>_^g?-`!$b%Q58Z>ngAm8e4OJ2r~^K-_BQ5w2EjE9e+1UPD8b#
zh8tf<i`#n9oZhLc0#n(?xV<QMTJT@fn#1ys05;wk=mD~#reZ(+6WtCh9(uj&Xvly;
zzxrTad-`<Mbj8VxVKpR)<RaVQ^o5JSB@f2v#QrrgvM$>2jFery@OWY-Pc*F*31e_B
z93h0>WE8bv5YM>}Fe`b%HGh$BE{Lp*=_&zs*bKpc>xWeda4%ZnC^~hG-<sNXM3@}@
z3mX>qNs~Nf1FBe^L_k)q+Xf$Gq2#_`L?Dab3SDvAwH&RP{#?z*zTK0Qc?9XLN1G%1
zBjH$-Af!pbPTb2q7*}R|p-CCQfxaSOEw#@`2x72R0+^fhZ4`V`JU=3*i{|l_Uu8#h
zN@(CJB0uU4Z3j>oqx`Rrp?k1>Q&MNxkc!Bf7`}tttVKa<5`e=p0h>1D&$b{c2yRHP
zvs@g7nw97^hhhmde>Bj9Avv(wbxcG4Ct2k#i+Rl6;`ynkTZBwHq_;LL;kUOS0=M|^
z)8*=u1%y|)Q@6&xI9qD_R?+*9OJcM)*3RlIy*tT8V0df}r?tIWQU@w2mWZ4=vUn@L
zS36FD1f7A!4On@YE4w`NKM}Ar?Y~YRMc`;LS_}M>W{UUgJst0++JP2{;5?h<4t$5g
zu*Uf#VZB4NkPzc<CgKln@VfOe%2g)TONXsnvhv-c-&!_-2GmL(0UE3@7<)(>a0sM?
z-K6H*OO{#`gPa=xF%XDpr~Nnn$sE?1(1ELTf8sraDK~iG1mn}HSh&j(w6j_PFY|*#
zKgJ<VMSirA*$-@#!SvTNgDe;_`r;#I$-Trh-f0S@ITcK|fpF15K0{S{=Z}yT!Zfl=
zikA`Lx<lu9bUHwPq^X_SbY~%96Bb2^__A~R0?Pxd2D|m$dF<20ZbKqE2*HW|B*lB%
zd5BW<8#m2FS(5`F89dOSCrLuWicC*_^0}Uo7%XI1UZQWXQk5M#zT<6%2xNXvi5w>F
zuQf$KABT=#H5W7$*=-{yl5L21t^SWHMBkO0^sIkpI8Wpcvp|DPN$@luz$x;AQaYmQ
zxI&<4XG`i{Zx_q7&sMYJ<Jyd!s`33Zqi^F<A9alog(wAIIT0SGl24&es?A~-O!S}{
zD-LKR>V8%E4yQJzB(Nmr-uG-KSy-w!fCqd-7khy}Dh;+wAUDOE3C-@x=0uwGiw+vg
z8J}`Noqu^GFSFN?=A#h+9*Z#Xf&Kc1FRYsB)^02j=r)~jqJ1;FA#vfRN%Ap*{GdJH
zR&r7Y6(?Txu?M9Y%+nnY&umsU+G$y?Z!$+rzl3qUgMHx#8`xvhq4(ajY&p3U0Piyy
z0Ohe1u}`@xoIEPe0&2>(%AFdU0ly;i6KoTkV}vyGsBT^gcnK>C^uNia515C%h>LjF
zSjPhWUhycYnoEpC9`Y3Y?5Rgt+ouKiHf6Gd;!M_>-|p1kKBsW$h<I42@Sl*nK6^2c
z{sO=T2T*dVm4G7I=^+WjTH`>w7==_-;&b9GCuL0;e5|{w#C<W+Ugc=*;{Y~<mKzv5
zf^Jw_adHcGS7|1W=xjmf7>KNUqAqZmE{4+!p?I1%4k4Z=%37dFB<ApTgB%Ue;o!LD
zePHTt|2ia*XZqwtp0Q22eS9708q=`=85^%?;Z;<^etZt^sd|y;%IVg>Qb%CrRoWX*
zbuI6IMOrI;WG46?aXb!~dQU9TsJd9Du`=MaL@z#TX~gbW4unAQ*{?yvF@)B@Xx#XE
zcD1P&G6%J=l0VxlYnNQ4YW17ubvr;L853V2h(>^@Wx`CXW{uy1Os!N#tL?sN!F1hD
z$P6{@PjL?sbM7$cUt-?(6NWTnM-<=QI4f$cd5VD`i-etP1zMsiv4!D<^8JoOydsE0
z;;^f=AyfDTPV1`(Ex5{&2GU!ds($22W<;m<30wz>^6x?|6V%CoyLNc}amvNGP6g6@
zzR-C<kZYm&9Z{1ddjI$vPl#PqL5kU<@993e`jiiLwH-excoCSswaG+Y$+cG+tJH8e
z3&m~oiGv6+>z|-F{eA&cpccPrzZGyrkoIR^Ud5SH%M*=r5f|WW{a@iaE{JxL@bO85
zD$#y$BBAG!XxxJ4;~m8kwqlVQG{Jl^r}5?h0TJ>OE>A!d!Hx3dAJCAyPWotEMUr4V
z(tS<JA}jJE$0d_pdeW0%Wk`MFCB5}YY1mXZQ*bTQcjkTX`{LcHZZ`)I3#RWSIY!yS
z{M?8;XibF21D*A3O$JM$)_sXk%DYp^uW`p9RZ)`eBEmM&o|a&dW7u+pFLS##?qwp_
zhdkIZIqQSX;+ZF9QPE7be;pz!N7OF}{>dWR9cuwq0duD)^op&ap`&q~hbLw_<uO!W
z+#YQ<BXso+@$C4}t7ADqX&`yt7qR|TXcR?kKZG(u{@%}B+Y>v0a0)M1r3k(nvqyql
zZZlzSvd%V(%k<zsiB}Svl~-_r?MtU6zcJmr%b@l|H#-G-eR`ATb%zovM;IC@Fx6%D
zr&}`ae+A)hO+CxgA{*i#7r%MF<RdPP<o(|eb3ox+Jy>P3dCv5)>bZRXcWh8f`U0&j
zD;FWiK0KHCBhB=ACE}>m>PmW)K>BR&kU_(Z{%4=jdYwB76VXsw%WYERx=TokeQ~ar
zNJ&~zRNzpSObX)LFA?OxJ%%~nXRF3irBD{oZRTcBhx0G<MdIsykfj#mLOP46q38eC
z)ZifwOs*FMJpryNNq<XL*0Cz%w+No9MZne>sWgU~jpT9hX4wh;xgvw9;la4l5c}x^
zmS=uoJd6CD%u_;n#G!_1wK1*&WpZI)ZllER44yO-$_t)D5j|{YUlL1T&PVTY{v2}_
zm=f{MmYwj_%sZ^=RA=aOReS~dL2}F;^8VCDyyPXXjmf_Su_6~SO5-kHV$bqAo_pi5
z*5w4J1UEV;LXeHi%Uw7w<3~Nv(=zT$2X^?+{J8mZ11isG?ce9~@W2A5IfolDS)nWV
zb_?hh`SZmFh+$s+P#WPL2MXnm!OKAzj-m)7iKOfux(VG=%w=!}c=R*ga`FcFhVS6V
z(NJq97!2>!lX{y~z?v<vb~-plF5=P*%)S<U!u6mwc_>EoF%H`)41XewP}{o(6(9-S
zkFNEhT9TV%`gd$ngV}JbM`2|IuIjnAFP~ySU|CQQJ+%>fs_uFokncpYjW~1FP^`Yn
zEVQooS)c`u=1Zk5HsnUi9RCHaFJIg)+EXE!zE}MA2r62E<E3M6Qb<>wmF4QI(D>93
z1)RmMvULpc3aKT^B4e+gbW7cpiy&=(g1R>T=`1x>n_EzoT28p+X@Kx(gE&ijL%8ax
zP3n5O%vDfq;A?KeAvc{gXnDG1FgDwM$i^Nlz#tkxZxs)rpcE>uC@CI7=TyJ+fWde!
zzgtd1LdpCERzj{LTpe*pn7XymtlG8bb4!Ks*UY<z_dgr=8kmY~!?wWOY7f3oa1ACz
zq%qDyNSN5(4|HcH{r!=3{vVKe1Eyxch%zMs#1z9Ad_{k*%~F?)1<wPD*@{ANw8=@1
z2kiBcG9CCwP`pa%nL<iuh#FOeaLFeb)Xomp9+t=;Dxz@r(Oc|<%tZt=<x<|$Nt46N
zU$c3;myACdU-t-Sop)T5;N&}KxI}v89znVsK$`2L;N4;C>^g7w^hc~FaMGa4@JWL4
zy0H{Wm=<~S13}zaNckm_t7ag8BOGY?w;NEKuY_JZHV#FXN75SSAuBY!6HRnf9$3{!
zD+DayH<T_S;4RVh<jH?x2QoPwLQ+6<-NXHWPmxqm<70CK8|XZts6hi)y&P&sOn(RH
zEoi1F=d=;n;W(FSqN4;i6sK~00n+AS=v||XXwxVV)<u!S8M7#i+W~bnp+~Ofa|e!A
z4A<}?VNoCHYC|{*Ca93B4DZs~5OWiK@M_ia#B50CcTYodRXzEhJ5>fby*X9?=Wv(9
zg$^qsC{KX%4@;_Fq`<fa+JQw;u$|i&yiCmyJU}EhK|EQP#^csg?><k3MJ-P%f^f0Z
zAf75JgC@Kn;YI1%uSeYed7D{R<hw+VPOexnom19IFF|BT!vg1kQ(Ot}dg?x-QSBzc
zQfpM!LuZlWCAcHRgzgWo!M+@Mr$YMx2@cO+{3E@TN=tM^qIGv)tczZx8KY`ZC-y{N
zAs38ceT|$&jcyiK9l8q2GiAK=X&b|!PlT>aYfCk7Z>9S<7EHRxgcE`HvKo~-|00p>
zr(%j2V0yV4C-~ctTmirE9cuF|g}&@I??9Q8En*fse6$TUtx5MNC0p!UJ_b3xm#^$Y
zw7Qk+Uk?}P+0~2R^?HS86L;L5X!00hXWHFQpE6|DV5(q??c4owa$789EVDtC8eRDP
z>9KkaX!kL)SP=n<N`p;CocQkO@CZI@>-O}z3iK!2Z*SHhfIfhF_3DSmzYmHRW1^yc
z#s_4}*2TdMh1zSU2!|Br)jGUe)lg*Sk=CN0-7gL{pv*aF#_ygJR&_&(A40@)0~O>i
zJY%tJLuEHD%lWz8-Up%yh;JesxiizjP~%{d1BxitOuzg+b81do33&H&yyg2D#$!va
z(z);BLT!FVp)c)X0DaK()gl=kg`7e`Ss<zxytAlCc-eA5l&`(Whd8L6&!M*VyUGhv
zHZJhdjB^7<@MnKT^dcbM098&Dqw-E2QTSU+)!Chgf{#H_dSzbv9giVI$137aq9qT|
zjS8>3=6k`G&HjpMKuzL@>ZQ>Odim(Ux1qnNgH0tU@IuKqsA*H5T=8G0)?AX<bWHYg
zYoot64Q*z!Tl=tNAwIo7E~mQen_&4$l(xihK{x@FH}%MSTzRqa#kf@aBR}yc501PP
zROfS*T7D_16Q3JhOWh74zDIaI&P4*HZAN|RH;qr_tN06d7aL|6mO?X8fry!*4B^Rc
z6oAf)F$00di8^&C;6~SU^B-+z!`bHOCrDsK2)cjnzJjG>+L@lm`#%!I*tx-7SF&Kl
z@X^H-z&~nn_Gb_iCdBtAMU}d^p1twR?8B=+I}a9-!+bEo^za%B?H5u>jv}Z|2~-Ys
z27%aMj!@yxL3H8`e~_Jsq6k0a4<@ucsL4b!WILH8#zQA4(H3rc2Q}JyGwI+%y9WZ@
zbBx6IPE+s3&KJ<QP}>;Z!xww!RldmDvrXr?AA6$rIWwGR{SGl{a1{+}Cdvu=rKLee
zGL)7C<;YA#&7SF`*X7CS;8O&mD<VmRIAWx&(*kRO3D@^2r<TbNe&YzO=_5kG%Yi$J
z24E|AS=xwek*1mIh!~7`<oZ<oj7Totrs*=pWCdJLSlbFAsv|t(XOI<7ybjrS28i?}
zA5ZgNdU(RZWv%gH9JS-hMb4v4_pE`|oyp)o5wr-jroIq32yr}0i`jwsz0>KKSB6%p
z*MC77BeU46zCzH9Ij&D%E*QQ7G&?*HWQMH9g!*qtSNq?L+Cx&Dq*YB>xu4Y$d!kO8
zNDvFFhI~J2ti3a>7{!P~it&Hk*I<Q)68RLKJ^i>T`u0IT{?%(~fOyD^t7MlpX$OIy
z8h_vP7j&F9Z$-Ld*U-&J)^bje6y6_~I70{X8OdtKO{)GQ3~067@^eEZEM<=5;uu}N
zJ%_y%jp5IFy~dSAXMHsd{Q2=UjC0v>=IH<cWNOo)BA*srM2wKgQ^R0?k8OF&@4JY8
z8ZoYYZB16_8S^{I0sATnyOe$>{teUgZ@Y{)YcyH()>q?s2^0noMPLn?Cvz)1cOXb2
zElT#deJrx6=vuA|)1m)q+hWnw8jv&iqZC#-C@SuToM`Wn6Ki(?ipG3&4`D@9ta=*k
z+<F6yO8+ds`Ej6=6GZvmbLM^kW=Hz^Jy&7Utrr#6CdM`9zG1{6T-Sp>=P$7Icg7>i
zlnfm|CAwj1Ct5h;dd>fu(o~iO=^St|<F}Df(iww$b@RoW$Z4H--{o*y{Ax9#T)B?h
z-=i)f0;N_d@r#5c#>~cyC^%#Pfh=mtVoRZKcvQqR%t9pNT{#ifS$ItL-7KZcP;+R}
zy?Y``0<4X9%Ij53rU+sK&si7&zV%RGGO%45%be|X;o0^(fPr5UM*3LUM?>+jFpJ5#
z)qw7OK8PJ2rERoE(}zf`$=tH%--df;2T*PHPbNzmjBB783#^JKi;UQH-BIW7UVl}y
zJ@V_2n)x=77KAsQv22AJglH-3Yb#_c9nmkmxWxm#Su^nAQy_wTajW($m_vP)2xG++
z0M|eJn^Q{2>O`vbLl(kO<jY<6iJ8u<cmMh|@T2qutc!d@K_w9?RdibywX7~WiU4pk
zq&4LJ=)%<?PJ{Oy4Kr5S#m||*Li%RMsk=hAAiDCNqiuCLp6>u?8qAt{25~VFbt(N_
z#y_8uu!q`OUGLji&a2hRoDTA$OsSp+&l?Z^-d&O)&SWQF_hiP|5}>gIRfSXi`b8;B
z20B6dh>gcP4O3iMOa^*eJ{~Y}+>LAMbszpa`zf%0a;D_Jz2TyW7s)1E00CA@&G+&5
zfv(6*{koarG@?Qco91pZbqS$u5<I!aXhka~v428?15)1<+x@Dbxz}H>f4-Bvc9{+l
z2!|7HuS$(9L|y`~!Wxxv6f5ThlgGw}A_0mUS5=~H5_W@|p6Q#$hOvG51m#uM1+$Vx
zKbGGuo7&7|vA+4z0Z^`b)RktByIew8D<Z_;zb6@;QtvKI9a+CR#cZNIxrXSc6_bM>
z&jm4mzJA9Ju6y!LDTr?1-|xk$bpN=Tw35A!kkRq;?`biCHrMN=XR!i^^~IXmKlq1W
z;`zUkG@__<2|E5ILY=ux{BW>#S9PD;nsj=jD7T$bE(Q7u+~uvQG;1d2{#CFHl$e{b
zNuu;GyxH}&E9_Lbz)&Ul&{0C0<3@Qp_qvj?A^~sEc8}UtH1m{a;B8`O;=y>0z9IT+
zUcQO?db8}V|669Lrj%TA;Vg_>5$S87CuFlc7huq{U4m*Pc&ISEJ(2hN#pA*sX?hum
zp^L!a5<Ell)Ks@gmFmUjUHYaq{R<uNXYq)iNX5OBu+0qmd|$_vI`umsJa<Gi{B6lx
z0Xg6g64pyb5rU>hj)jXc+#ejwht(avoQ#3OZruO(f=8o4AO}W-ekKwnmKXLRkdZ-z
z^LAUtVg0+E0I_xi`qb;<?BfUmM)H(NB8)KK<FuBczBhh)-1)eU-gL=-n`w;1w4nev
z(}8Nmk<G>ri?FS1!HkXcq7>a~aqv|idyM`l+<@DE4K(XP80xb#F|V(}kKXT@&a<<I
zC4bXGqh?cIsze6QcDk;!Pu)k2porHUsRh_-Mizb3$63mjZTQ<%t#iCopKsI3<!844
zJ0BjyD!0MXl_x4Z_RR!jGeN`0vwet&Ikq1t9k1Z}%e4UG)F@07g_%1A9|beb$M7#p
z*`XVv54KgQ2WeLsyMkqhzbEXX^YfAICVXl<)8uM{TE3^Vz5w-vpc7$L?)HCJ0LDAc
zX#j_QnxAj7NpiX28W7p*(hB7>c-;Bn<EYHM(wNX6pp1K~dI{u3BO6T^u-m*!x)~Ms
zTPfWsx`;rD;%-tlBhV7Sv8o}^23-jWB466@c47VO^1+M{jn0E!V$cmFfK7-&Bs!i@
z4F{mzqaiVbE7k(M45nez3qJLp29qJmg(Ph4ko?2d5$K%%dh%@Q{ZKrV6R@!@5?Jqg
zw|aInli7Oq@e#uI52NPTPevf=j3z2#^vMvUB2LoIpjiu_r^jtQ**Yr^6twjwyD_g!
z{!MDLcyN-tQ(nmz{Aj%zEGkLErvz4{M_2AFq$7_XI>{O{*k&MJVcSIn-%5j<Z_I?u
zly7VMX$(8H;Y<_%dzZV{C9SSe4cTrsk;Nvnk5Tck7C)s?CBX6N+f1+J+?xeR!2e|)
zt3^A|xLXf7<Eor$>%OmxS<#4LwS(aOA}ak*_st-ZT4cODd9Xd+L2d?~^>PW}A2ooa
zrzqA@EcVHLH+u-8>qWSAhRh)`{_Ssj4nM_mG6SKLP8rcqUW0AIM~c;LE)gWxLt{0V
zT$b|?W<z@g3sgSq*65CsS;{Hhr((OG8X1LwPXWTS`94_|lN_GRKvegH^V0HH4a%Z=
z<u$u`tZT+ufPdUYP6VDYgGkb^P&E)Vop`49WZ~(j?~o{^29r~Aj}*>?uOe~s#E*i)
z_2HUVN1}BZ1Mf8qd@F*FQ}?;QwsTmw^m|{kS>gIiI963h@LYu$bSQYzW=YP6rJoJ>
zLG0P@86ST|<cy*wQG}m#{;@3fKxn#q-N3!Pa2lI!l~f=O<+c{{2(P)!V(E&-q|pT0
z?)S8XX(*bdPRoqY;os0~Un&~`gLI77TE29m!q$rKG?1;ByLj|d%{z+wd&c*+v)H*R
z!y=VF6b@M|b{(!@;C5+ieyI<?&4K7~8zoRna|Uy3@1)E?ZOq|rU7}%Qj?tg}2B%s-
z%yC%VKdN=_4d2X|E7j+R+jVgZc`8(o2C?rnLwOHxQ#yg>CtYMxg4c7I1Qw?0&d<^~
zI%TDOyfScJb!|@NU?iRi%b7C;Ie*nFq)zEByh9&disdL{U1%m&6XQMU(CgVpKqBOp
zzAV{7#skl2d(<@J(^>I^1vWx5EG+`1+6gbM2%{0EPghUkK60QBjpC1jRX&7}&iVLz
zcQBAt2kkO5xgSP{QO`x0{{zanN+WWb=r42(PDoi7Aaf4!u0J7ze)rA>mVjRznd4sv
zkm%trGm`@|9CksYks_$)!psl%jweB!E4Ng&Akm(Y5gUs81wzG!A^ZW%5;A6lkQk|A
z41WWCAtzYXSXkYnTUvEKHauUybnZ`W`Nj1R+^BTVtNq#Y`o#CMQJ1N#bIrYa4otoH
zrPVOj3}kKbxkQWYFW$mU>v;NMwsZf`|6c=y-jA5wWF!vum*;WzDdi|B`Xhmm*N!A1
zR5V?i+-SU1D>KQ1^w(AGYq?9|{lP0eNzVRgL=w&ZCv;&c0Nus0-ep4+^CRZ#L1oo+
zcxIJrF~p7nV*9_;AZ@j?vqwL5oLn!17gDPhJw1$!%C5ku#cqmDA&GnJM_@t(qN>dv
zg{x@X-tRX;Vgk?od8eE#z4i%*1oO0?3H@AOQ&)vx5b+7EBq-!mor;HAGW3Zb^9V}H
z<AZEovAZ2Zbj1QF$B}x*zUtCcAw*vUpNVTmNF<<7E{@Sa{<?6CUT-}MoirO8E|Rc-
z_Yb?F>fHh*@Ddu{9iFEPo#~@s<G{2`e>Ly21!IE>)A_R?7bq4~^AH}8x(~w>8zijF
zAMh>Buu%FnF=kQg&2M3r7%%QN_65k%?JQesE_@^j?hTCGXNBwUx{-}fBRm;!TW4&7
zf~O_c7@i9<(*<cULj25?_vWIWog)aqM;spEnGQQ&v#REoI_Do06Q8%35<E&wN!Rp)
z@7{&h6bKeSb=1r)0u`sk3H}l^*?}gmR(h?byzVpjLe^2C0L^8%@&pFvnZpPIV+6_P
z2+QfGI;QMv6FWKz=}1C6fdS#&j-38J!)~+pLg;~^XlTq6<-S(DWOvY3;l_1!DWCyK
zjl@HOIj^$~fzf9r7SPSWU_-bqQYW%4Qy=tA1V{l}K>`vj<=YeR=tOVFbI)O}HHNAk
zu~Q$lSfMA}E1c%!Fy1=}X6B3_#jaxV4h0MBD8op!p2m+)w#Sf2-f-uuF>eC`R>|{9
zb;x2`0-Jib+A~+znhC+JPdX9BjfrrN+VEN})ixD7rNc8~?fWdsfCZw3Q}O}0Z+cN6
zhO8op<hUU|Ni@7kI&`o`Jh~2+QGnkjJZk#t2{oj$DAH&?G~V~F2uu>CL71+_m_KC#
z1Alw|{@dd|=)D84T;^I#fTsB)Ggkje67NxOm!WbV!rzP5q*m>;XMdr2!<?1G@Z!(G
ze9OO#DD-QQNKD8IZ+#jQ@viudJ(WHf>%1<Cuw90M?>8@7C7tLs{CWD1sMGH=xH-YV
z$*+ExE3~rL)%}@#6`ozJ;qi#i&h!#n6qa9umc}FBP{N-mpJ~Uh^=CpcCUPdR_WG@O
zHza1ddHU%(p2l`jodHnE&&1G&FU%%pt(0Hge3=Gb3E&uU4U^_OQ1Vn>dBpU>pnfQ}
zVM?x9;D4RmqI4=5A8JSeSek~KJ%^p9P5Dd~y(*6&6gc<ccS232kzMsS1sVeI<Lvae
z587hDr?o%%T;RLP;O-Y%x}y$WtQIx5rRi=T)VqXj+h<}AR_2GY!}i<D(`5EKo6Fl{
zGtjzIG7t9x=%~-kYSazbKe0c6Mp1-qi`tC`n-E0JhJFq8LlnII9+V2PEI{EWVwF(C
z51ug+NOCG8HYw+ut>o(J3r_?EU8HFUE@Ap3^VA7k0xu0^S}GX{SVe<}Ucn6?6B~yc
zPeA1NO6`fxTkf>e2hDe<hJP7ZGGwiBwNZ3vpqk3qYw4kNvNnhZP!+JI&@)9lA$=$Z
zkhJ&gx@Z<MX#*m@`E&&7nNfnm`O!sW6o~oGID1R3mEHIimUVcSU?lV_FA(9Kc4t(G
zrZ{Ln)m_;0LF0XhlyWemLS27$h(AaP-ln_(l;t9yj@aovJ$QfPB2CpSpwh+t!zqg>
zu-H8P*;C?hWgVhM9VAk}6>URnc!(KJsBJGsSs}<Ha?r_M^IKv$&(kjfp}N8nR)WA<
z4L0vu*cI`L?f=)^cLqff1r5%!uml%Dat?|hL5YG&S`h>R$r*tK1QSWJq+L`L1q37t
zNK(le1j$Kq&PkF;&KVYV=LY>Q)cv@-s=KPYx~-adTeCYo-TgYfe(y~mtsSw+60<0h
zZ&F?cZqImOJ_<IgnfiSsv`k;c5S||o5GT`X)PY;@bpGvd^)PUhTMJ5t8vb6bqylG!
zJqX}Qtt+?<7L#FPF58b7pD|g)1=<j#CIg@opX+^dbj<uc_4#C+tJFh-4+w)M=B1or
zTQM&Vn)HjhS9y*=$IS;mf9`IaZmh(sD13A<H8&l<`B1tTMf2<`bK7il!L<*CPIO#X
zA4-i?b}BX7Nb0!fPL$v2uMe(x;r-5$a8O|WF#L4rm7QF64d>d^iZ-jlR-A$Fs?tGT
z23Ty@;|asUkWEB;7NJG=^BYn@YB-t6))VO_*-UVnd1GJJ8Z$0}U7$?NE`X;vbpE2O
z^Zx>95ji!_%g3MplR3vK-BlfJs~!u}VpK{H{&Ue@muSC_%THJ^PM)x1VfF+*T3jr3
z7dsadx-YY>LHGUp)X~gX2-4$V+Fbl#D~j3mfz07uajyyrhGa0hMZf!5A0`&|`t!{P
z;0w|j&7c`@i<8i0vAzBasCfh~)$ZD3&_Ng6xdtgeeS#Jyerd}=e&9th*89IqI=;%D
zEY_p=b2J0I2j_~HW=CS9f<&H@X9;(Qc^HlCA|hdI!b9|VA<oWP#Vu6RfliOWi=fXz
zGxF9o*l`E5wDIM0y_ku)Q=H=<_!UMhdDyrQ`pVu8#`}w4mB^&2SKf4X0OJz=4+Py<
z#XoZxzkZv_2{_%vE>k@ePcsH15GYDd#4woFJ8#u<QNduDk{aP;9}Mtcf&Z`-oZ5OJ
znD)*sedc3s;-fJs#-|I|!cfN#;CB{RJ))f$apx@cg?!9Y)2%DinV>CRlLgg_#hk-~
zl-6Kn8m1j!;9f&zco!SNo#Zq7Y5>plVm%Q}`pq#l_wK9g*b10L{!35jb=o-zJANY8
z_esR1_~kR$IyV30jU}calWEkWBB}+*cb*aQkqSR=&~P*RP~oLtkvQ@ke#Diz0xbS`
ze4Hc>WPb)#7Oh27!i`=--R;b$0e`I0!V$hgCfO`+SKlTuB}?`vGu56QdkxY1;|Gr2
zG6Z9D!^O2^w4Dkmi7ghqgk6!zzLT$1_M)R(oOy0cQFGw+!!6mp&6kqEAy=4m#=a8D
z44E8WfMe&60;Pw0<t-QoC9otAcLh9b9RLHH7aT(ePt%<d#l~wXO_kvCXFevB?lcGd
zF~MB#n}_{D*Jc;{!mK}{;E|8cTJ`y4le<rGo;{WAO(Uwk+T_sNrI)4yY=SSJhS4IE
zzhAns@5qAfm&Z`&H~>M^?p%5sofE*?<+=g*`Kti^h1Ze5gfy3z1h5VeGG%(GwQSf;
zzrS>pI5eJXtgdSFcLBymPHisOUEZ^ZjCd*Y*x0T!`3p^0Z9-v$jR*!`Hm<(5%Zhc!
z0(dE+l3sAS;0<B^6*>TRY9-om{&oB3Ppnw8@{Pwt=TN>w0kveVQrO>&4_TfRR3Y;|
z#d^Wt-iSGFwTAZN>6!KfzY_yoM6k+QW+Z!<#Ib09+ZIqL`fj9)&9Ji-f}P%RL-npk
zRNLwP^wZ+<P~$1;pHkrwfFGWAkzxd6-V=`lBWiVeU|V~!hyr3uQib_$A0(<KuqXO+
zNbrH80hOjQ4NVrq*Gkwas+K!YmAsE+iym0)@fZDlKiqaXI~1nRhNZVJz!eKik1bxO
zoN?DhcpiR?`uuxbSNwavz*5Fhv7v}Vs>HcIOm^2ojq|o>6iw>6nW5TUJ9B&o4AZp<
zl}g;XEyBLB3H}JSUV!MYuyB#YYG~eG8C5aXD<hFA>*UI%#1@)Ri(OS@#0p%2@rM(o
zZ8*-Qu#E#79b#IX@OHtI-6B#h)>~<?E2dW#+Pgz`r4mzl5=EGpFb5RP_akk&agN`|
zWGHX88rfZ{0Oar!Iy70B^7DEh4G%zddGb@)lS>x@o&e&Ekcq&@g~G@L*0pZEZPLIf
zP7NyrEw*-Xty3lwQkc-9UnnK8?O|8#rG}d=zqmcYs7ADzUP&#gKBr=MDlKPd5J?Vg
zRv%8GX!w59(17xm0AY<jI6i}7cLbt8%FJ!jaFFpaG)rXXVE+Zgq_WL`1cg|C3BYVS
zC?onzS6L-#;acUkA7->OuO1+N8p&d{C@$o#CI|%P$5Dv@Rw9u@D}F(+Son43?CPKo
z#&L4<vhEh2j>lviYQuL;II|q#U2YinCX2A_q?i|p-i^{jO4Lf+U}IA7?Cs7EE|>px
ziF4MCjy_DsdL&E>C%ozx0~_44aBCaJfrQX8PJA0!Q43;z+b65D0-UTSv5-<1J>o?q
z`%MkDTIi_TY@A#wAyW<t2p)c+!~FF#EF<&cao^|_LTq1FA?Es}PN99wH=va>PcWU~
zw2`Pg+$0<Juxx%4ma%B@nrdynG|A9{q`s2ucgOe<H%$NO!<(7J?DSAqL86Kl#W|LJ
zj?(wF@hbHr)3pZKY=9J;a2mt-D!3Um4L@oD!|4&p<}`&okho6vl{2Au+fhj*$+yz9
zrE47FTSr94jj$*pu8Gr&v*SR*T<JXRwa$^9!b#ee?<1+wH7Aicr2>x^qMk?Pelmph
z&|NO7#186OJ(4%I?9cWU@xj3y0=dNOv}fpO#yn&`lbi=`YYET8itBX1ao}z*D1W+M
zYfwv;mISAEgyT(1Ma~qb*9TeWgPxcmahM>s3K<`stS?C_w;|=~1w0v1nX%<>u<iWc
z9S%pID`#6sE6IDDjtR!{KDS;0r=;qv<XtMeQV?~OfC-q#&9wy5Wt>Y2h3T1~YUtaz
zne~>T%1xxUrZ)0*)YRgHis@g?a<lX(-W7~8g&RvH#h_QfK6BBB?H*PLX<pUI$2dN*
z1R9v{Z-a?X+cB|kMC8HG!<b{P*h{KQwdV!{dRhUoxe)fd7C+=H=!5_RMXkGS?T13t
zCQB25(alY@+_B8k_Q5L!2^0maSRwV#BrFElxk0d#l8aRt?9w$-MD@1=>Lc3;dA+p>
z6ix{gxJ{(ntcxhtYF_`U)ZR+qH8Y7X-1UDj&2U3@(%Yt#uooENA3EJZg7fw%GT(-Y
zoK#PK-V%Fo{7aT#JlAE`Mt6@@4SeWVDfQ;HlLwF!UcR?!vV>{yE&V2}kMC&$#AJz#
z)~~YU@45)-7T(RA>lasA(D62TAUDp0{Z4p9GVdmt7wB+Zf8$>IiQU~nCT0g0@0hnz
z9+xA&+SB3VMZ@}crs5?LXii6e0-t|He6c7{lc;uTX**KL@=|~)k0~giA&1Fun+aP+
zd=!uSRsnw#6f7t90`^B`{Rv634v`%r=Ogkhn>?$ypOjgkm;EAZap7;rm15g{2P#T@
zD0vjKxEL^r5ZFmgp>R<V<!N^As^fDrakJ?H9==LEV%xEES_Vp2xmEi!$8%bL4POa%
zVd#u0fB%F=DuWPztF(2(!*Pk_)6rVsyI!_Ed4!&AXA2;a)2l5`yQgIvpRtjN16|=^
zSAD)|ruJ=miRDyqqlTiooli_vCu!Lk``Cg?iI2n#MeQ%X?Zp)IHd3O7J1Ftqn!Oo4
zDPUi+*h6<ja!gKm2-{70I*yp`E?Yb%3np@twJFZ~*Ljo>;#-H;Zu`jv+dK2oV)3dl
zu2_kXS4*}0bGnq+UW}Gr^j8#Ujk0MKqD)>oFXd4hr1prn4^B4p$Sl{kvbv(fVq}0-
zNloBSGjSB1qtHT=-lmRy*wIh%E^5t%r@Z&)xNzyO)mJB6p1l|ShP{2+E8719Eshf|
zaL4u$pfiu(tIH7w4q9@E*s=Z34dG#qZ_ibTrcW~zN0?9ORi-IYpeS&B0e0bKi&LYV
z{VR6BVK1nn#VmFQzC`sFHu`#F6E0o>N2yaqM9D5w2x&RU1{STAvI-(I1w)<a24l(!
zS84;g;d>a(6U9+Q@pXz`@QT(U2ZEZbw?b@b=*cXi*NA&uc_OXJ{)u{(=t}#*6@Y&U
zx<wNr{=w7tl~dzy2rbz5u5uO>=SwGbm}??&!5yKKbWBOv13A4hAKZRv`StG?m7|xJ
zR8eRRjnC>D`MC6X)$AKv93)CA=Z{!B-U`HP)=o*5A#jGBgMil)8ai5oNSLcR+0#p%
zXIsSdOAnn!G-?fp1mh&{;b~(dbos<rO~DfLt77M??sdUULt$M{hVB>PLPvnuVtB73
zV{&1Id@JCmb$l;BQw`AeOTVuTLN9C{Z0qzIuDxHpw@??a7Zl{6;Qc#ah$nzR`nJ8|
z6HDFlfb6$|ac0z9Q^D=aFZ<?X<=|*s(lRBqmM$Va!%@LmOaX7oGm#A~BSs9B>hnhO
z8Jfo7lCoh5w<t_XF+%&bzAQgfjUuj`+9w+%#rprsVobaX3$y?w+YYk8ncTB$<2r+w
zuZZ4i0+r5lajgufN@}3BxG0vwx~C%qh5n%VS^b^`PF`ua9`=f|t_J(q;i;M;xO*Kt
zu%!-^h+@Ocot8{f&F+dyS9e{zolX-wr^{DNB|{6?Be_&S|M;_C%FljLm^^8vtTO@2
zoUq=L4*W^49OWbwSW&qRe2?BQJ_GtL#7>;u$rcLy^7e4+#q{2@GZ52-2cBP<>iGp!
z<h|+D%sJEr)!vDHLl5f}?WS9_Cy^Dr(Xl+K@lIAn+d_!G(%s)QaK+%tI1I1hJY0G7
ztWrS#lnuNOB}(Ou@bI#0PNbg2eyvfV?Ujn&62ik=Fk~8D3M!zs-}g;9UKAnkT+NK&
z=TD4Xam}I0z0*^@GVM+${w8cKU8p(RtM*;p>x#qT>wv8HL@uBrJGKfQAhfP!i_6go
zUS4VejOIhX6ND*&%V;g4U9Xjg6z$v5*GLVcRF}&=@TQ^U9+#FdMj77n-teQZF0cZq
z5{wm)cgWLT+{Th%jG=9oCMG6jimS^>y!Gkjf^^3?+nTnWH+*Z=0wMO9>*(Ffe%)k{
z`!6*!5e^70Ke0O{_t=Ior0}f+^e3<UV!U$wDFS;t`8IjyGDOA|!KUaIdfaBl!htf~
z)zk48th!BvjFi719#CTGuX`5o#`e}c4fv6bIdQ3TuOh+H-$iF{;hzQA8UjXAX&RFE
z(Ham}HO3-0GB8PTZwG4eWS~jP_G{WGD8|^pKcM8YHdcdcoue!HD1+#=L|$<X#e2-g
zJO*k`RHlDrM%<^39nj^|tt*N~XboUIZkEX<r(h;76pLYFU$c|BZ9aMiC^3*QJC30R
zY?eCI;uEU{_SgCSBxw*L!bC0*3kBNs4=4AgjeG1HP2YIM@nd1?=iD|I9f70*EURX9
zM^8kPy>z`jCDu!}WYd54*iH0{0H6O&SvN6y+dCBz1X(W*4Y2g6dNYYt8`LI;hIdmv
zqkz~p9X2aRwx27i=@&<@DS1X&&02??EJCCfC!gm`6Wa&j+!!1c$-ciixQoV>Ar6`9
zGUU%OMEs>Xff7ZKDb326{9VA`5%GCXo5APYY`f#|aLtK6wRjFV2VuYrVQ}s>A?l!F
zdHTyz9c!ur>FPAgI9?!7d!O?k^KvM$w53cLHxXG9^W7TRsZW@ES+YoHa#q@McLxph
z=6OWo(=}`Z3Yt&`_{x1Y&pYi)4SSCA#n!8>aqm<|{k0DL4iH?<?b9T@&s=(#wBEjj
zsgUcs0JDg?eEaAx@-H*m@1YqqKX(cg-P)&ukqmaiOb%#L!4pXY*L@pTyz*rzeq}R$
z4HM~!H&&9J_G9_c*a+Od6z|L}`2<)o<ocAee@-*@**>T7P4dpU%n0Lvkq_qhi1s~U
zVip~+bk2A?N8!aDF)s8B8RjBl_*UB;gT0DxdRZb|^3^X7-%XZwJq6Tj=^8|^%pC$*
z5Mx^)1*h0G2wmB?qr`jYx}02kj5q!8=+=`rFm>*j3`i!TxPwFhN3w9K;I^{2s-FWM
zI=yAkQeiZ5_)3|4lSQJVeEPrA)me+!GryNezxw877I;k->x6%MS0bG7g$5b|N($8h
zRYd%WOuCrZYTTo!YIul$dx$?mWOYTp2*RWZ!bBBIi29AZR3PW9KPH_)fM1GJ{VO8^
ztP73+M{s-M5Wz&;i2)(9_+9>Tb!5cqkl^;AdvW)Nm{5mcv+w!q4W*Ywf;4Znj50;}
zqN?-uHmM$mazEBp`K6nK7u_)BY?$)h+x&Vl6r3AynfN4^QTw0<2YNBZl&qh~^~UFF
zl^4*#3n-deTf=T+c9~X1zI`EA(kKnDuR?I~zE-aEXZMG7!Yc`~w{kN3Wo(V`q&&9m
zBl3sVKyWoR=Rxooa%PpYI-Ju>3VU%uD?{BV5M~sq!@5TP9Jmn9B6LyTSR>Qe#`Hs?
z$*{#QQs%m~cyJ6rXf-|oY6|S18z`#{VU*&`BMIyE-UGGrS0idp%Q@jjve5#QvZJF&
zw1+Jd_ITuL1dLAft-^f07!p;r6#Z*z7?9(q#5&9`6<OL7w;hE0$>z+rgf(~pm!_Mp
z)d34wHIQ<>f}awN#*^~e2;fAq#TY?>*~WuMB3RgkeVJ^BD{{=`w7=lg&(v}SqlRjS
z-<6D$PTYy@B+#ORGQqbjL=~0jwb}e#g$N9O<72MeDqZQ-(zwUuxZ1Mi>Bt0dyoA6`
zUqvV*#aBj%;d~{Q+W>-9V+;1+*unwu5S9v-EpL}+w^&S)t7yL-KaCiR%tXT2OCK4^
z$XI7Tl5(Cl55CA=S~1(`21aD>+^`|pj}5soJQCdUG@w1eh6#l?M(+j{W<c9wa5qMn
z(jDLD6iyZ{H0XnTc0d{HnBSi$T;sXp%sZo{M!P;6xY}BemFe_5y5Tr3WompqL!Fo6
z)_HM$+P(<b>3nqd^TQ=p2S7Ee%Cd$w$sk_{;WX;}DSPW#xuyZ$`+9b=`@-`fWHLiB
zbIU7AmxJ(3JELIO4|h@_F!NFJvv0)WAoa<sfDK9P1&3eDd)9zg9X2;AVXOs81cqb`
zj(y2qdsezZQ+oA4CaIh-*)`A5ajRt*qoR|R!Uy*(rtLc3HFW@_4<gHYUHmypt9bo7
zCIq6mx%NSinAA_jbN$_owOaa>PUq=m7`^k3ga>Q-ffdpC=SOjOAsuQ4ehJ?>RXn(0
z@+YZ`xa7(3=#)><5e~xy*P1)=*3R5b<<g(LWoNo(Ea!qh8Sk(X7?%3uY?0}z+=nsJ
z;Y|^Sk1ob_f{Tdc$QM;I-VtS6Nk04LZ^Qj5;YU#!U{pzHOjdpeE7(M)b(2m{3ai=~
zb;HMnNKa0v5%`J3enAE*W8p>lk{?z)AEaHhfYzfU>-05N8gFIAdkePg2XSkOR?yOw
z&NUeodBbqEhs(81G|9hXXZJT%JGRQY?pYwh$_T~mj_C>KLY#lRR+7Gp?4m^^zY*P^
z;T2pU8D1a@bLbv<gUu2hnR8N@Z@h>^1r8mn@RX5ZHm-m05ONdwW=>qpz|vt*30Kbr
zwa|bI7YgK_lb>6iPK>_2X$bf-qpr2oPPMmBOJLU~Vv0=Ckm!9=7YZ!Zo|?8rQZ>JV
zDP=N?OF@B<J^(O;-BY}+cj-K%-d%`5MUu@m64G2Cm8wMQiK{4jen2$(B3e+nBN5h(
z5W}_?XyocR(w1HwUU>||9af3+Jtm>{oe9I0@!B}!4{d;QG-kKa(Ab_#WevZzagkB{
zI&q}bvte8Id_~{N;}@b^x|~G63+cWj*>r~7c%TKnm;&A!yZG5D_=O>COwrI#LQpAB
z-(sVvtzw?3_YaQBh8muszUGCjqleUO<?#iahg4kleRq>!+NJ5ZXzmSdK`(LaL|3Sr
z(gO{m#TDNq8xNoUr|HCIqSyyRKEv+&%t^gh8Dw_dWS$ZSYA(z5I8Wy9k8_rj{Z3<W
zIU`y_s0pYNCW%s0Vs)#L-R-mv5##cE6H335{~?ND{h~s@-axA@Ft92gIUD2u-{5hG
z=VkiNRf~&_#gEqSIhHqy_hK9oVTK(Q*Ym%&(^n0gV?K(N-Day>Pm3(gXbH&3H@+Dv
z=&|B!h25J~Dnyn9mS1=a7Z8lL25P1iX-<r<R>of6WKk9j-fXIgOKu!dt^<gp-&XqF
z30W;8pI}g{Y5EG9$Uf_y^7_D`2$qJ){tBaA?gDmLjsrNlFHqUY&OdYgV6i~I`>KjE
ziT#?<F|pIl#Gd%Qi&dUZ>hCIcjw*Y73pZCOy>~u)Qs*$Z$et(FGk}yyM*jU*hI@J^
zfI{<a1ggcrCzI^f40oKB<w5@{czZg|`<br~p`^ed=a?a!knJpCy1Cvx97?!aKW=^k
zbndwIHnAjIChu6?M9h5ksrwdf`F@}%@8D}l8F4|X()T5DbT`-hpMv?T@s;OfZ;cxo
zaSq!Bseo>>48>*XKc|dA*I15gM-LYs10Lx$YwhqT)^Jv=A6N`NYWme@xVP@9A|`&)
z_xoo@9!M&{H-957Nzzi*Xf-!*Z(8f?=n7~o>ajPuKaCWp!uRw5=O<{VoN0)oY{HpP
zw_R9_$aWNmhB!;ha^LWFH?Sl`ek^28ONg9{^&5Y^kIpPj?Z@2t*el<5ik$ImOFYly
z%TNtdNr|Ti`JS@(E~jQwJvE^~amI)WFBocQ)S1jHe+5&oMZ-l_k|O3lX#DfbJ*lF=
z<jG(ZCM_vx?eg5y2-E2Ay&ch{_w?p}>TWBifG1Y?w0?}RzKhSlsKhF?33zBGd;%;`
zKkPwhAz$iP$9EWz-iM+qD|nb&^%`7ne>xlX^9u;Y9x9!Pu;q%{yhaX6lnld{5)C>m
zt){4EssP^wR#e(5;SJ$L9GkIs7QVe32gLS;klBtaEx>z^!a?)MAEQLnDiBy(c&i<5
zvjs>U!00uc=W&N~^+q(L_q^0+7+2~gqTqp|pmG>Bou=()4()CJ^M9i-8VSH2Ci_8C
zY$sQ+BMx>hz5Km!AQU`DB*G#$_m{6Xko|q=y?$UXKVY9JWzf4C*z+I~q2_17IustV
za_`kD_Df)MJmzez6iWoafHKN{sB9*d;D1pYzLZTI8?JX!rv-|s3;@X(u6skk>1O{r
z^}FrI$Un8zG}nP8PBI!vtXvw5<y=lv4mCxcv&sm7WBTe(h|y?3)ZreGe!Ub0Du6-U
zW^gndIe-GyE}6j}OIUaXGm)T0d7c5i@~vn9-Xx><GuaUh-1+(Uiw*=6JIDxu=q2q1
z8~kC|uh0?s|3F(>;Gq85j)e*6RfK|IG?09Cjnpjm$xVM4KzUMmty6ClT8ED^MFU)_
zXg~y*Aw>YG#0UTm`2C-}<Ryxg^}gU<I)k0W!hrjlh^-CX=27J&k9+m&w(M*Np2tgX
zrgrPyTP-K9sEGi*3`{`aM?d7ucQ55%1Lygdnt&QYA1f}fQK?v{{y)%#U`}+smm<`1
z3z*7RGu3SbOJY4(5pW<K4hOXRgJ2H?t4lLG&LJeQbHZbd7L7pN^4?j{v|HL1A$WON
zR$6L^ovnaX1V~<P0<tKhD`SFl6UhUn%tQ_%1k1JCV}qnN`E%rGS><ikmZchiDY<A;
zcHxncwKcVCyK4nQ!^v~A?J+BiAcw_bxZlqXgteW0f^oC6+tFf=Ltrx<5-9oR2>&q|
zC^}Fz>0Ip<C58UsLp8Bm3af;{fjDy{S3Wk$CvSpBwQ%+KCC7vqF@`9&?((T4ENk8O
zDbFgO0?SZ>i5^}_^vdr{<~j|w60dK_WSQb%rLSZNz$@7iK3bSw1&auZa+EPA+%P;$
z9NAhYa)%=T3A{QHr$vz!eeVZfA-ayC_Gf#-KVsFG7g<N7UIYls&2vxN?}WZxH=e4g
zo!nW0_RBPdec%}3pUY&av+R(so+oYH8WLB7q=nQ=65yYFkp9TgQ~uC>x0tg=tXcFG
z{O?12Wl5b*lQ0Ld+jq-Y`sK~@Lb%!PG@oM1ZwLGe>Q*>7$=@OK+`sm-OAYnhlUZ{T
zFwm^=5_aFZXqjN#^w9?D=5w;Fb?bK}wT=q9H~PBv$1EHyoIY*Z$d7Vv@t^_Jz~U?P
zi%Zo^Z)a_jn@q!>8)LFV6uMWgm{mV25~<4In2d!}!<DUiEm%;`ZLOn`5L3`7_-In~
zSZ?to&V9GR9<Z&8I1@NdMDqAyQGkVB<EeE9jIDGny@zl*VQ=hav1m1t>j_N)OxHxx
z`wan}QV{!a4}WkcKPZ!*PJA>HT62Ze{pCM`tM>r+r#h-Es6vH$F=9OylqfL|2}T5o
z4f34~RAzw+lhDM=RaF{Q>malem?1beKklLB3QroVUetP3IdJ}ywI|FOOmE98>2xcz
zdyWRz?so3TE%sRDW=GUDU*wP_uUe#S^k8hBp|oiEa_%;B=&fL32AVtStB0pKzknT3
z@X;F>Rt_2l&<VSG=$9nq9TSyR(VnLI);ZJx*tDdZ!1wnNvO<PF&Q0y1^L)Hn%MHMv
z<|K!o)LOn<cLU9|e_lFx-@m<;YJ_P2Bi8RW$3w&fEcw?^qU4Hq^n@&_&1UDm6_$$M
zKuewVzyQxyS<*t(CVYR7kuw%^krS+F&0Z0#)@~hTYglB3CI@9^UM)(?DuoSkP!Dgn
zR$DlZMr{6kg|^r!UZ{pj0wtY#KevURz*u#jMX}A!f>d^96^bpBuZjTFmtC%7D`_n}
zeiI>paUw`*#WdkFE=1|o8$U@P<spGg(ZfW9Q`Oqu0MUQ3QVUOjM(DrxkZrx<4})mt
zglq*36MzJc{)d-_Lm)Q;S%$c?p*IrXp+o{-k^ld+B>`^MD-Q=Ce((xdlAbZh(m%>J
z>QglBf0+IZ!Iv<AQ9CN4ZV<|Ii4gtG5WPnObxLRXmwjD6+F%sq#$Q)lWCENn=-(t)
z#}Bp<U!p$C;N(H}=7FNV29d73n^-;BnJ4+b39e7=X1VR+?@h>cxDU_Ge_?I;&`4t4
zV}BbdH&{cOCMOhv?hC%WhRdtqZTUw}pYBcL>fe|XF)X`vHfB=_n~&K`tKb&dw|qhz
zWGiGj;(lG?Chs79J%9~LY$vDv?p6T%ann4JBr4TR)(E|FqH-zrrZstGX?9AR=s$Ms
z>1r5&AFErT$#!sw3UZq{!I$lr03$KksEBEY@+}+7AKvAbYi&^(t+nOo?4I{dEhEQ?
zp?R+K7?1kVMhnO85Ufv2Vr`7C8REE&UjAU+y4j$|p}n9*jU(sdhq^&3Ki&F0B)?tL
zWO}eH{_dL2%3$1}6+83F-%it<|1*@R8S~EBx$;77PIwHfHk)&|+mFvj6<(JqQ6vu+
z@7Be^TDhvo%%vI{0PHL7fUDutoLgoi`u7?B3lNKWo{4!d$hpW`bJrcWTE+IK$<j9>
z24SYgSz4tH8Vv0oPlY-bd9WI1W@A&wg$ZqCi_*2N-m_<}W2a*Bz5Oj6Bn&2ahr(2A
z$-_QF_i_Kxt!w|-IMv>^zR*W0%vTi6NL%hKcBn=7y3u|APxhfPud>(R%(6KX_Po(`
zY~%3bS&)z|@7?Jccu|K5C=mNv&{U&P`#V%8efTTkzk<6rbp=!3@pFCQfn!ADQBy{D
z`5H^M|EUjak~!^c2UZ{6``kteGz|#54GDF7SOWuQ$fHk%e~|yWu^&6*Kdxcsc{Yy-
z0WDBzFpKE#o`Ucjc4L}J_~SBDCV<RZ#WJY&4J>j+?+&VI<oSPev!TXL_tq;MwU)MF
zjE|=WcW#Opu_7x}D}!h9HxwrMLp@a3!$c%7#4qv0=RZFubpEyQPUd|gLrN}TvCZPO
z4ILJg4Na^hR;G1Vh^irI6!#{dJeLLgG>D!!%`f<bg4b5XQq8@I$0<`I<=))t4=qDt
zIB*Ro#8*}&vINtr9vxVNwb~?)vvk@dm%uW(Ug*8ZH_5FRzgXQYriF$uSNn6A^uF8Q
zAiekNw%db$+UXlj`~COshK;#uVogsR!s%2@Sez=+kc0Rn#QHpnWHxkai;607v-2GZ
zq5H?vOM)W%jnn!fH=*9Fuk9eMr*KofA8pYR@Yf=U9-F#^M9J~d#^R>BNf$c)G$aCl
zdD`T9HV(UgQW?ZCanC<<bKM7BQwQ)sp`=xVvrZ@3-d#w2q`6}ugHMhGe#90e(1{aO
zUx>wV^pGu3AW@L1x(1Cq{4<koeL@qbLJ7@(@^hBbT}jvAW%55W*ltP?z>8;jRa|BS
z`CTr^#wnOxfZzpYB|scpdHC`|;8||=FWdeX!M*(NEapAPJMcrt|EyJ0tfJp&3nBdQ
zGC0L{+EiK$y@Fv$#4-q$0D6H<xQR$6W#4R`vJdib@{KE;2*9@cI@s4zspg(&<GsE8
zvO3Hgimm<L49O#b&iJ`+N84+Sl8%S1N!rzuIr~thzrY0leJVJx+kB*rzI>!`xRX9z
z_Q-H-qt8QlY^8Xu74vq&<O&)<KS$<Zn1EO*?}OiyB-WaFdV*IT@r^4M0c@pJ`X%0b
zf^s)-50Eh?7$pt_R357i_ZEhIQT#}rLENHz=^fG5<hLdI%~2?=Hu(lTi8elI5&;Ts
zAcp^<C2P$&{gBhV=(;}OcX>~kRC)e!rZt-G9~>$P>;&bkU<(+Tv}uyY6<mp<9@_3`
z3C{IAL;xSF*ZQ5^q|RYCwl-9ksjQ$8Q*5CBKIdbga>&}PpXNoHnRVso#!^Ye%Tj-o
zl9jlLo;<G%51MjLxz1N_P&?UvZL1Ce;9tFCG6F3TVU@jk+&Z($<B=~%i}$-GhgGJp
zd*kFf<f=-kO#KJ7DQNMgR?NT5Wf;T@U?>nRfEdPv!L}kSR@12{e&Tqn!#{FPnMn?$
zNB>ya&jqO0jxyRNFEifS=2D-c^b;*PyXV%Mp|g7|Gpc2>_b&N;d?qUX+0n0ZR!~b^
zuAyA}PQnNj{$?*+<(%=cmGm@cvxq0TcMd!{X`h|H=c;a%<jIZzzy8iqrb_+elwx>0
zEVN<TVF&Z(Y_zG~Qh=ip1^TqK@3R}9|DoXV8&5Z~R><+QYLad<XH*vVvT#>6n<s{|
zbiB1FwUvsWw=TG`BO)WV-FIccgy$QBY+%IPGc$497U4MI#_{=~-Q+Xg@H6Xy+z76P
zlp(Fi2YUr0lOL+!MP7;TY`ZM8D+Gj(hO4qKPDpu7SVaft`yZtb{hXg<KG<?0wB7i1
z<6SWS^x^h>_tT-3C>#$%?eG`Uy8Ft|5c)Qqs|0YIGiLd0^qgTv9Guo<emZ}C2O)Ro
zdF6$yDuZ!@Uk(QH6Ost&7nz=|F#}O=S^2_6%@_sw-fJy}EWx&VyP!cgH7PsgjEVd8
zCay@)Tl~>{ndHmtNx@<FFK{SaHJg7GnQb+;YZ<@llhopTRFXAuiSv&Hm6XOsD}jaf
zy?E^*lM2;6;AqJflA6F*4v6FtfuQFaH*fJjtQD?}$%?|y@65(l`F>IU`mncZ%sJ)I
zoRzb)F(l$aOh~?}i5|IlDrucE-x)DHuHry7VZDOw^Phq9RYSTpNqY~n^^ltH`N@ZF
z2t@Z}+R#ZG2)*j1ylf1#H+Ds|+QzKW6f-twt$Ljy@bC<Q*BS^d3Hbw)uouO5avqs8
z-bwY|{;a7vX-1cybHmQCXIHZQo5KRcm81>}DQV$U2HNo!VMWFtXI$Pu7B7nFna}Lp
zkoPG!mO8_W@eD5^S21krJ8r{o?`pQJw{343l&I(hr9a4WzZNPq{GI#{%kW#!M)$G1
zqibH5l55kw_uoAfGrab=1dKFepSz2m$yB`&?vNSl*@@!9_|Cj6OrPFv);zdn_?0f>
zDe0td`{=91Cb5O)R|2W~yL-G7@>i`Gd&*?OZoh~4v=qB{u5iAhoYeC?uNPEG^&7FP
z$X}3;aV@LK^+L=j(34%l2x+|x*{zQ-1fYX}TIl#c*76Pl(1!<#*8zYA3h@Ep9pnN4
ztRj?=08puQ&;>4SG;|KTA_ARN=$N2055@oP-;Y5%<fUuN3D(e7Pyo26q@kDxl_LC4
De6^xl
diff --git a/public/07-basic_statistics_files/figure-html/kd_test-1.png b/public/07-basic_statistics_files/figure-html/kd_test-1.png
index cd2936975ada7ef831ec76b61957bb70cf5d6024..9bde720265ae5777c176d45dd10512ed984b4e38 100644
GIT binary patch
literal 15703
zcmeIZcUY5M*C(1nN1A{rT|f{Kkd8s%Mo~beC<sUq1*8}0H4r;eBPd9Zjb5Znx6!L~
zh!CZBBmqJQkaGup-tU`v|2gNnzB6a$%*14e?7H?UzrEJlx6h0WbXb^pnII4di=M9b
zbqIt81%bdnF~Gr^;Ai+q2n5P(bk*b{_!9y_Kp+kf1OkEpOEkp60pb9bm0&GcMXjd3
z91sXJ!odOI0G5>qG#Y`%I#7p!RS>WZY;ZuJsqNGk_(!D!8ts4vORPg>r9&lHQqTwp
z8l1%ef<EX9HdCiL_(G#A(P%8XvJzbhmJ~D=i^fta9Uzqsh)Oj0b^x2fHtI|VUzL?u
z@LwesEGd-~N`HSp7LCB79k7+)8%=Ei+rT*vzOYyd*b6MM6bc0b0q3PuqA6JLU3pLk
zPC#w>;DRUynZbBZ_ofd7BJh;@fyT|O--SSgA$r<cCV^=y;~{of^Waxry@|$N(gDl5
z71%-FijwqA--MMwJC{M<=~m9znM)~!NiXg3<nZ{(pTUqi;ULyrB1)%cE%Ui#{Ktqu
zx&U!z2!j}-It(Hx1EUc>`oHz3e5^~gtv*+9$A2KGwQCNiroOk8$=cZ~s2RSd{L1Z|
zj?hpD{&Yz+YXfC^TSL9yzTV$uA}GAR#JN7V|AlI5rn-_RWjQ>oLhuJ(csP0c8Trtd
z7mZWJDPU9Lt%d0x%$Fp8);A<r;K{HI9M6U>F+1TDLtIGD(ubKeF4WWI>@aH{2ih5W
zT?ShS-+N{*B<RC@$uh`aJJ6I&<+9(CON+xVl$nj<UsPC<G_GW|X#!iR6OO37&C%J9
z9Ky5*OWp8TG%PSgl^TwYK~oyt&3?7*(2gkrGaH4WnJ4<Eg@noaYYM>TBb6)^L{b>Y
zAA};7&v{dz?PisiBpPLo1UOEu+LpcuK}A;7ExBd4?i5>lrYJM?B2yBL5uWF+qPW;G
zgNr|2ED82+@jl?po^csE`g`R$_cNtHdZ%j!(<xWJuF~h!-qJhhh=&LaXEwX#&jTj_
zoJCVx%iWd7-U*PIsp{D%#@^ry#{p@O>d@De@sAd~of3raLYB~)U`J((W%x{)EvY&<
zslj(+*Ld%?&!!|9>3v(d6ydPaslWVqX7zN(&-qck>W!;}JNxmm9a9^hx8w%|+O|Fv
zKyH?}HuTJRmaUXM#JgMc4`{N^$On>6?X8u$h%G~=YwIR_Cww<wM3mL$@0|}(?Yh{g
z35=68+A<M6Vb`wSRDMa{rKuk<neV6(wpVcsvuY%wjWX@v`8MpC|NdL3L+0-L=TB01
zbV;|S-Xa4n_hvr?_p<i7*C*UmZBTN)ct?&8Nz9I#3~DsNK55HQwHCM8HtZmJ%3SEv
zwHSl8TcY(#_cS(-IPWM6J#t<YdK!AHV77IF-t}ENtbA*Ebyr$Vc7p+Z21kJG*$Q+Q
zU$VD1yc;mdv#CJT7=<2wa`-r`+@j%IeX>bZHfiCWg$(bddgIoec}Jm@wdSrCEVPto
zZq)&3pdBhRkYP~_IgLXoiek;5e0yGA4!0ld3C>Jb|3b36j{4@+8derC5L%&w8p<5c
zcT5gJy?gBlMdSz}@j{ysTxI2slPiXw=AG4#<nLQN2bF~zn!+7*e*bf*9eoZGLN*Fj
zB#T|{xPd$TAvDQQ)Ox1n$Nq?*a?<f2G3j*34V|Y2MCX`$LoAZOq^crM-mI<~P3s+h
zX5*3I*FLCkBn`d95Bs=Y<Xxg-)ZWBv?FdMrDa}c8PuTjJj;3XZBmS|sz4D-@V~@b7
zrMSZlino<!ZHcE6?t7}o9#1x3rN2vnKlEm4QcA*0!j0{25f8x+iLW!ByRj9NRGYEX
zhh^^SQR4S~9pg&W_4lTXcAKL&20MaBx!~pV>TIoE{=+*C_pt^}UJX3Z;PoZj{UqBl
zqD=eeY0rAM$+8j|m1bhd(*tIkW_*9@_Wex9oFe(^P4^FMJTpT0Wl={Vt*R@w(q>zZ
zR*1``V!+UqsPm?t*Vpt*GX@mmSMC=w^$tXSnO-Mq9tr7w3}Ku)Q!%T1E5+?zEYv$~
zyrSXePcGr02E)ZST$+}i?!{@95)&ybGgAL7%7NLPS{J9Z@>eExyF@vdBHLHqe+rAO
zu<9z9w>NYybdj}$r-YM!-Nps`NCAUi1}1zLW9>t3yV5!hj6NP`L7!nAQnt3^{{fpu
z)JoNteR5~fO<UXg{GhwJnj6#oO$8rMv1<%C$sq#dzl5HOB{)z*?T{0x%pMIiH$r%p
zji1(lnpCnZS=d7^g$yE~!TsAY6$?}o`(#R+^Fw8Qn;f@w7)xEK>qNbvYZaurdo^RB
zEMqc6&`1qvvNU&9A9TzPnB)_E8P^}Sc3?$Pn%bk`1oz?%PGi~h!X8h*lY{$iZP3M4
zlpC^lh@p3PF*9SR$7R>EvTRl)8r)7k%s#HvuT)<G=u=g!l3%(xc|>@4)OsPE_7>Eo
zJ0K)%Otg>H$Z<0D>+0^!lnc+;p%#U^?A-Y$6LvZKnT+;wbN5HhF-?Pl$APEgT126T
z_39xvgihzeO?2K>j4+8h-&{I5GKsws;@hF-?+X))x!{^J=z0z|eWsS2RlT3>gQ_9a
zb7Ce}c3>tkw|z!p=6wGs#pdyL4Z-m67vbJRhm1(0cxEHwIZUeKT8H7%-0br)1h83J
z{uolx1GnhxS^jl|%^#fm;d#`f(Q%co326K*c?&Maa^gG)e~T9s%QRUxC%(SN(zw#(
z1kh&tMT^<dC3=#$vU!C<DeJ|BNT43-jip&S%Ncw}=5U}zSLEK-bRm-wi7$w=b7JaO
z31g)^km~v1838#C@e^;58ydn!956$g%$`hJhG6X3eanh2_bCewbw-)mc#Mv{cIB4D
z&7}y$x~x4)JhI>Lyu1J@Z9cmbUVnL!N0lar|3MvRupi3GF`#GTX4xl603T|j0;E4%
z8)cMcJD~d%FnA<^<U0tp2(}6gLIrE=RBR3Y4nl9Gu9X^~&ar;AR7)sK?=^EQ4kLU{
zkt1>P!v<7mf9PHAVKiP6d}4D1v%>!*X^vb2UA!79D!X|nFz7%VZ$R_9*VV0jd(KN~
z<PP0RRf5^C*=NKws8!FOrtL~_@yO#0Tq#spdOP0un;8A>JvXLDZ|~hAlDD|PG1?fl
ze1*Nhm;pBsSCbL((f7d0ub_fw$zxC#!@BzC)>n7`>SBIUnYV-yl6xU_kx_k^Zi9Bd
zExT#3c&55own1jLF?uC?81HEBdCO`SjqD}F<y2qX8+TT}e&xu1#`AK;SUa2gD`Qcv
zTRs{H!_HedySGTBPs`30+?d@O_>#*b+kpwQ;gciKQ`DoTfYk_h`W~B+V?(h3XnQ?l
zaYN9>LkC<$08Iv%W%%99FJleey$EJgbCEnpA^)PYTpEr@;-gh7Y@oUNDVbe$QRfA#
zuA7><6x)F<{(1h9o56B<$U9%~D%R>J^5Fw2%!#x)3Jsu?G=Y4Huts7rAN8ORz)XIP
zM|$(l^%}lsyMjA>?PAMrSx^A;g5A)*X>{|%*bl9s^yN}Wo2WAf%y$HtX)4cF7-X^=
zauF4~#FK;#8A9tc7CPqdW#wnv$3QkaVcC#2s+KWwdS;q$T9cmO4-C7^-*147vLw?L
z7O&>5Dh}3azqr^ok=^jnbS)sP4aaOcZt1#F(-7@;69pbbprM7!j;yFTyA?QFa9~sh
zkI8J3huM&?EXoFh`v;9d{h9uQkHvh#&XaS4htvyJKMEh{ostxg9&&F0D_5mCUA0q}
zBe-BAg15XEW@gowj1%)U$-Fb-w|T+8EdOD1y~$i=*TdPOZ2Vbd)T&4Hs;&hulvlmX
zlLH%?i4U>hv$Hbn&x0s=TBX#gAuT##YQRuxQAT_POspGL1p%#T1)|5<__1AFA^n#h
z>KpZpf-*e$-}}Qhf!jag(n`Y+_?v+pb^E{UgRaunpO>UvWrpJ4B?-YE1#$=*>fzTe
zGq6uyM4jUhzU@QP$_a%j>-_gWFf%eZb^ZA1bpmlvRAtH@x2`|ynV_RtOxbW&M%|3(
zN3dpB+KV*`oG@%)ipv%yHT#`OD(>t&OR8CZ-dP@WZsXoULjUss!GvB0v;?fYbIz-x
zGx`=!+;|Aeqj@x;0&c<@fLyTWCd}&3J!k96z6@P#sN>awl{W}j6}Zvl;C9PP2DqYD
zkn}lLoY&ZlES_c9wC172?w+ZM8}J-wG+IlLNH<%9z^0!;HWjXXnQ!vj=^r2cc&Zm1
z(TNH}_2E7ql8b3?b<@~u>F^$U)p?FmZvG?7eIfnlh8`K;;Zx?(;17Y~wNb&zO$!&R
z?d@GJj7|piK=b@j^YkavZJ)+`@O=}>Qn(>dmf2ZpEZ3ee@jR2edI2O;9X4${d?fz}
zY@o#=O}^i@r&*oe>H6$(0F`EXzd-9M!M1bpM)F4bv}BP>KQgGfGf(rdFuhu(c?AbX
zqklG0tFq_IY5CE3A9A}!r~)MvEznJ>m@8a_bd|w1dnU|0LsR$2#y1{sj7QPwLTl6%
z;JoS`acy^HQ^Lbi#6o88SC1NmrmacwT=MoJce`B+D})b(R)wadj=oX~7%vZyP7)82
z%Njar7@TpskXOIp=c}XojOd2~mIY%BMr{45v$klN7>9Mmj;*edTf&}sc6Zg6*lwUa
zY>pWIAitnw{Wwb|>I{0k@czsVGg)iz%5b}m562~5kimsC9(_Ngn<yKG9~O0u)3+nm
zq&K?o4>1^3*C@C@)(%`ey-*Z3>Uw3AfnAuVw!++x9V58#rgtpjWTjxA&F=W~dhIZ^
zJf3SopC#e;>I&hWA<*KK>!&f}kkO~{tWgq_*Zc|LxvZz^Z!(D9Y}{Up)GEihm&|))
z6mnwRnwIqCB3yQ6(t*ubp<gqkwf<k6e^$|E$25{Gc8bO+W;{#UqmhqqK9rMSOdgE!
z4H~UApKb}8u9v!t5+~iybW2t!R@6F$lMK(TVCrK;2W>Hzy$ra)uhJguK!;4NXs+v@
z`8a0a7HjWllpfHr;eK{A#r{sPb*xvlWp+Kh@Ql7iZPs#<*+U6HhQa73B#7vE7d2Mv
zMWE!T-mM+8u}e&P=EoadH&?NJaea5^rSVdF-eA1<=n_qi;9J|3&eJo4$H_YqgbR*h
zY7ZCdESrNydzkRsep^Ehp|{M|L}_w@>hkySF7b?LW*C<$Kzv8gbd>^TuD{T{ow#Cn
z1((l&-b^G(E!7v_6)I3dpV0XnSuegR`E@hidN)r!eyGwgWG>iFD0=C26-iUDF3<3}
z{8>5I8x8?g8<)~^RBZNFa*ThaYk>xj5$qU36^tvAn_}a?2ZS$bMtx*J`;|+mUA`+#
zYDyhjGD1p!B;zmCbRL18$`~i*s>hFO`ArlG%9=S4iD7cT`%2DieG$YocStk^{)f1~
ztf%Nzv*lP_iV~8T(HLu(`W<ApJR_Trs_3ZN_PU6gO)74Odw{3w(Y93#V$H$uxe}-8
z>Z4ocQnzQGfBfz$nc21Bck7nlQ%LnkVv|eQ-puaq?o>s`UBr?opq?l|Tb8(Tn$J-x
z_Ny5*Z$b{77bxP!?A&X#L%jpZ>&kf3mjcb}fwXsD=6#=f=el+lk|068sNPP~+O#KQ
zYPMF;NFhY6u%RHE=D~tS>$-bWcS!+<lRm5zKxg<=<1&$yDVsQD8#pK(*T{A+b17il
zoat$QaOJ1=q^csb@t=yn*(VPf`At|j_pBUU;AJq%JmGj=g$U(d4U^|stQ|CP6*B6H
zO@0qeF`bhQvy=d&wxA&2cHfgVgwH0X!yh0mZ__x55<i-EmA;&QIQ64{nWBZgrE&s5
zcAk1rf5u|?!OIR)Q!Xi9q#3ZuPg`bMI;6_vPzZ1>*>=DO1lwjYHEZImzRzYK^E6G!
z$#s2Uew4&1tVyggPd;&bV<PxxpT@0{6Erzyl)>LkUzD!26Ht+l?_Nah^uY7F=Wluo
z8l@ldnfSE`QPL?@&snW~*<ZIxnJf_9>)#bvY#+Z&<Z|_R>1T86ju1ME41z{@(gfj(
ziWX|;E)kC4Sfzg<))QXX<EX55InO7uiRI|R)p>8tt3mttMTOTAqy&QXgu^du4otJI
z!^4^nbb~=vwntqv8Qr}V<g?iw9QW+sBD#89GQtI!72f!zWc|h;hI)H>M%@UI%?Xvp
zIWY7dMh0jX$dt7w<>>9D;p2;EZI?r&&HDnUn&F_{@U|@uHu)8&2Usf7H;xthvHS=l
z;b%8S%iiowj3*^Aprb-83*K##Ca?v8qCkh$kPeiW_(+EJ4o`^JQfkyJJ!3F@I#?-G
z0l2}YBSE61n)1`S#@YvkFD<%kZ`E>t^)>%m6!-jvWnTJ1nZrd#Az$K5luH&n21M@&
zxPA9S_D1fnr_T))`WH<kzpt(9G7LxMk)bylPp#6M2q0a4u;qaIXeowA*5$K)t-6F)
z7SJPy0fhky;;}--yV4oMJa0OCGL*B5k72ePZqCh|g-uUtsC-6Xr`#S~%)5n<!0t1v
z-K&#Sbm5?DUAAENVEE;e(tMcaBxdIuW=GeeRkq2yMncg|j_zcw*Ms_C7Z25`z}m!@
z3`Ri0<hiKY{%;zG1zor!xP`;PF1QP45&P>uwk0(=y|9_=FfKImtm)=ceFb(W?vqwK
z{x&b5rH!x3{7yQ!G8pM*zRx#LZ+z{0#iJQ}t3C{vJcLH3`^9H|t8}M1nNz!*b8U&N
zn1!AAUUejM?TL<LALRY4*_>lbON+!D53w}(Dhk!r#D@vF1b&0g1`WfA)iN|C{48aJ
zSf9#w9QZVAd#HEZFF9>8{@r(G|MTz*Tz61;OChtH7e_4{g^odCmBO=-yH)Q=tJ@=1
z)m59K@2PWqgQnadN}Wlvy{DsnJ5YqR_gw>I&?>rJfaCt>XDUDppQyJQ>+Oh17NaRa
z`wmatMBhSwCTI<PAy&xqVRfpx{Nj(=EBiO*o|8uJ2QJCFF+(jPpcZHSY32ppG=Z5L
z`EPN>>-pWHn@Yv9l?c<EZ+w_$9&X=8*}$_fu5Uwd`|*q$+ZhjriV<-mDgi8B$x9d5
zol#eVmiZpnuEIqCEjKk_W|;VDZI7cNH<tv?G^2vIkGt0rL*{Tqb^4RnWcF`|mp#K?
zI|I&F2{%FJ-zJ`MBATV^EQWOBzDgsXM=1l<%TwnlO{COoj7IF1tmw^6nw7Q6h5bBo
z#OBM5J)54`F72bjK2n%6vnd2HYNk|MsKqJlN#eoQ$(#MGD28SDC(YL`pXtxp)<_Wn
zY*lA7yA(P+f9EPTKFTHqR5tV#@7<6bw~-Dio#J8pqV)pWZqI!RUOpGd{}K{Z)-YCV
zja=d@iaes9?`_{fjECH)y6>?knMCX4;I68lQv15L(E@J|^9={t?7m;zo$bXg?CC7I
z-)|{NAG3C>Gd#s&LDlLsGun@DXZF%qB;<x#SXMfuBCKM%tqXA{Rq#CO95~|UsZN*3
zv(K_B227d#8)WP&W6D+(eO~2`u!+*2R1@BuaC_>9E60@w$?X2>1Bvw}N?Ddj)97lW
z>h9v&O+Az<j$mE*3hD=q)3OKoFguD&Nk`nI00N^FKzs~&#(-9lQcD<$d?a~g=y~_E
zh0V<nZ&X3TWvr{j6*oyBOEZ+Pp#Dq|Ae5QW<MwhV+&}JKkCuT=cOh)Y$9?3xF7#P_
zT5H%fN|X4`BOD_1p+X|$<qC~c7#l7>>UtV<=e;VEF;eI#^tv6b2)P6y-EsQcf~Z4V
zk*O1SvNaDi%$$Ihj?%wNTzNEc8Rc=7Wk=)UF^u!v+smi{Mfk?Ft0+KHHm^8u7v6*~
zg^VjUF8Gf_+^0^y8eOVy*&42YCI`$;)e!f0cFOmc*@cy^45RSwAG~kM%A^Es?Zt&#
zH?TRiJ!>U~3ZhBjqw1mWp_k?8a%yr~3e?wL^6(xO7Pvx$CgU1%D?eooIzN{3KVQ2~
zVoJ?qM5egynWi{JoB@Uk*}LNKcape4RxNc)q;p1=HMWLT=U86THNH#RikN>%>3QcB
z(6Q+rC~dCn>reSn%mBA<$*PM^hU8Y~8gO%Yeo@pH+*^Aiz9|wOGQeuIeq@#>i`JP@
z5P1rBd(SVvtLRBjX=^?En%Ok;l;<}s)PTKObY}RXn)6w*-+I-n>D1eVGOzkL1o=kE
z+=-B=#jEq*mo}c(8YjJs$H!_QiSU~FA8hk)f;5GP!dESqp{Kf|L;;t+WBVf-<rB81
zvh6ZmW3_P|kin<pl-DCxWtoc~jI(?az9LTLuSGc7<Th81s6RUc6bjId1}lQ1VnuRC
zl?HAHTga|Q;qzTV*vA#rSooQWEq@qOI+q{&O>Kp1|Gi(TqibQ-UjCLS0UvJx^NkZZ
zgeFC-sZdDsI0kg$@(5YK<``ky54X0Y+4P<?G}a<v69sqJoWTdo@<%$Z71|j$@tCBQ
zd&-xeUy71h?#koFMSe$+pF_r@j>7Hz70y*@WG6Iq-4CN_P5t`*Fc1xGAHuIpq#YJk
zr(s}ya|nGlyy1IlPm#)FabSXho&Vc0Ow%r&+)N@6`sJW~TBx7GeGvCZNRTLS4?t<t
zwDLh8z+qw{0E+H^zLM7zHQ>}~@##EBC_^tu?pG%C7)sGW`u1@^1V-Z|{QprIp$ZU|
zWasAQgo+!3>k=VQUR##lLA9l&q70jl4Qb%-$wR#>9YZRsE695xaFEgnd7!N1S@&nJ
z)m&1`d`!O@yD)Ge8oJ~Ef^M#U^V414cRHH2b+k~J;<uw1=f3V3y}s8Smefv<zzZY&
z_$|8O(|Q>n`B_8()Ds5yi=tKE%BpuQiD1C^M{d+gj|VYhI^&}>mac$@0`G|VBdEny
zM1@@K<1Oon2UH>t^>(RB_ew0?$ChiRzkKtafgN+a8InBp+u18N{G3Wydylp+g2@mC
z;l4)av>x=MhRbeaY=wo|ts5de>*)XBl0=c&H%^eOchJjS#oaxzadC#-vgcM?v``S1
zbvh@}KXL*~b}!UN(KiItxmm6c&&=W91UQg%(<;SKPcOO%HIW^b)_^d0#+yUz0ooh<
zXd*xT?zf}Ds}b{R!gDuS+{Bw9UOL)1=-F<k+r}K!0l{po?w8<vQD=Zv6|pNc`A^PM
z-2)6QG>@))p@5$M;=yQj;i_XSZl}LcN3Z=EEqAaSYip1xJQYO79~|EUfC(S|-<)@;
z^v$6{=Tv@5c2fs5LW8>9KbgIQT7WJ>CY03acpLuTY>8?w;KrO$vyR2A4P@hbf+Oku
zQEO_QBP#4zRcsgsrUKk#71R^tpM?NQR<=zTaAj%r34=G-9zs`h*{$tuZsw9aGX!Ae
zL*UY?KP8(X`W;F_KAt;u0F6^2NW#5OW{;qys}W9Nofg`tAzn1@5PcoEJvHSSq$)$N
z1stD(Lp8R-O(tS9Acac8#Uz&PD0RRgZetz}weSQq%J@crM^G1}RP$*)L8J(k06PzO
zDhS)NCr82vnQ{9ukU|AvVi1d)7$|)LDuZG{35icn&_$WDwc0s=UFCq$<X(SI1MoHw
zj(;`$NgM>0>JzSSRWhv``7{3Lw`~{+Ii(Rng%t~R;W^SFH}L~xf$}n-!GzrZGUXF4
z45<b3_BhqDj?>O#ui=+PKD}Z9mHy6c=w)@G^AD+i>Ow878Wd?SU+U3Zh%*2)UW$iK
z0Z~o6%gz&+1e=PM?E4U?Ls`KL1j08<eHMV1?g-}MI0l6G8wYK?Pk1l`<D;ssy%S_3
z77%WqXwf-cQ*z>RQlc`8ju+Drpm%3O%k_~Ps846UL9822DSs-OczlYTx|R&kRAX4O
zq7<GgMozK2Aq<YcLpz^0g3mLgsW~PQ7iP+z52JRJ1W3uf3t46aIoLa8;h3Au=1-1b
zw(b;flt@5XA8`l+Uq8UatR8w5%E<^&7kUR_VF1Um3v>KghCs3NCxw!W!<hn49EHMs
z51j_8it!I`;lK!g?WIoZCD6{lGWEKpnLsbcUs$=8N1YM_^G(=t+z`QT)u^%f9Ww`W
zvAlHL7(Ltc4TaGSk!aFp5`jR78`e-u_`}PT#tO6GzQNZl23mD_GTFqMF2z5@cXh}p
zS2Ij)-R&!%`>3P?E(Tgs;&|usPt~OHUw#|S?$h85w{@ZN#EBd=xhtV6pG#fam!&LZ
zJ07|&#qmR7Tp$aga{Z<|_&EsYSTh^+rBuZA3_PiHKV&lU-|8U{hlhu4IyLNjxG}Sl
zCf$C1k$=c_tH_=V;YF7dTK%3LrjjECL}7R4Nj^Bc-!!cu2benY3HHJRK$3oKZ*P-X
z8aN7q5Z7Y$KY&)R{Punfiwt0SW?`V2G_gem1v^w{#yg3vdTvi#&FVF(%)ui(_G@<2
z*}u`$_Z74Tbs=eBR1nigY*2fkfz|0R<*oPUKMSKddDIl;k@D*|<$MO|<`k-dpwbB<
zFUahH#U2M7gK{H6^UClW0}y_P-cs3W1eGUyWb6f6lWv3;F#Qqk;~kMe=pWY38f;)2
zn3r}tNIG%clHi$i)ErfbSN|O_Sc$zGW>-3?(a-uvI+s;GS8`zT><Ilks;{tntzfM!
z$Z@sT0vC?w!W89Zz{qO*r5*^~R(3!Jh^0z75O+tug3zR!De0lu4y(w|0vy9f(R2Lt
zp)99>S#8Ysw#_G=R&=d9w}gB`W7I^71kpXqbjqOi-Br>4v8(+}<WB$=3o=rn_C5<W
zc-s1bkEzxE;Jv}f{-H#Rc79N+UjeqUM#CV-cO6yvZi3z<b0|<@HnG6<P^+UqoG(HV
z$U3Ls+M+<Ff+lr(5S6dTg$JxZ1tZxtT1!tLOo9KmavfwmJu`f_<`vn7(Q~b%yRvq+
z@po6w5=(1H20RS3mL5ZbTd3L?Sxn=O03rWhk&^YyWl)FU%)QRZF<r&cJ*Q0QS}Po=
zY%YK#tHrPEm9;%N8`De3Pga|yEY`_iJkU50HkX!sAHVkzDML_sZi2$+SK%SaqI17I
z;&j0-7nqFJ)7vkiKx=S!e^~tog>q`1y!qi*_mV6c{2wR$aoPy|4;eB!EV_0>u*BoE
zt;>%z3Sf$NC45I|E1=GxpCq3H>5AXw*XG0|6Od_F(y>fIKdcVmg<IHXwP(Jbv3FPY
z8Sz;JRh@4U_<pP8K$Nh*kdn<SS76gB!ac`Ww?Ut))DQDToab%L#KVS%RMR+u@!gzB
zuNDm3*tJa{PHZDssXMVkRoe9@M1ab1ybq$Z+Oh~DAk`0gf>QuJ2ykD$yHBUG)>KqE
zcV@S@d-$UN8mHxs?H6|t!2bFz$7!9s0<3oytmT7|E0nIIsR!6d+v=}iaBC?#;t`bq
zK1`Eue{s_Y4ONp>fQ3`+Ra33Cn7{bO2l@@>ep>DTZ`qL#)Mj3GX#0P(VivX<l6wWH
zL&1>E)kjBu3p!(M#D{J!pgj$8pRBDN`+)nO3OH+T1eojkhsy_gw=$~tk$_=j$JpsY
zdD+3e|GVFL^g3$Rru&2tJT3N*P<xdd`g|=#K?I|v(G@(f=If|F{SRec@u9>i5=rwt
z1=%fb{{0`xy@N;}Df7a=Y3)+fyOk4b2&d9}3Wy0o>nrd2&%}VPAZYoDCB>ThuHRNv
z@&6EboHi$jP5VDF;4hL(0)(n9kIZ8M+Nb};3NB%v>3oZYYIP8~2RTarBDaD;{Pz$-
z|1Lpwnh88>Ou$tg$~shAdr<rDGz_?@qBcbxNt#+@ik5(qFM!S=oY^P^gG-@P4-=Hv
z1Pws$BWM>Oy?>XM1p-Dl*9d6bGtem%xWL>ymrW8tH3+PfaMmn8_~XAHGe;S8SfY_?
zOr)k98U`b|0*HS9&hj2Xl?7dW`XMJr)IS^4qHRrM+(THC<c94OWe@fL0rFlkITf)E
zFqIZLv8Hj6k;*JdVBvDy=$bK21Yi7(f5ZvO*NYw_0)QE{#lK7c2^~OzjnFJD{6o%l
zRHwoG*HeJ8|M{eU#y(`~J>Ax$r3jU;qMJMuI`NOFav;e*;g{C*QM2KCsvIT%%zMlP
zm4ajKd4KdS&j8&!Iag@M2iS{3IQPe+760mDjye*B4VVqy{!U;XFL4HK`^jfor=x$+
z8!;YItSLy1Ye3>6IXRx9K-~wu6AX`yB2`vs*oz{lyTZRh4^V%owgMVZs+o;deOdQO
zZ_Rgq*)vH{9VM>^6NnASWW|-UtCoLz?tfkP<Qx4xE}VMT=6C45w2+i^(-nVfFlk0*
zU<|XIG6Om&^End0g-+FBL;k49#v*1R*#?!Rrv@ISPYn)~8Z_@jU0k-DPhBO|9|Xf(
zU&Qkz$xEO*{B@J>px#L#M*ay#M$W*>$D_`Or;oiFKW~t&dKlc$Pnd7O-cr_@Tf;BX
zGo)G>wyKC|CI)WlHLa7>()s@7fv;0SJu#Vh1&;LCFW}jC@dZ>q$yYJvmRc+oOb%k(
zPJ`b0Z<~>UAltwbAeS^q8eLysZzDZ!*;A!r(*(qwiXne|QV~}0(DD^Tx1_<8Ib5j$
zKo4qnR_Uko-vEHr?fJ?01#~htA_I=km_lWKrg1V!t2!qWE>HFh^~ZsM0R?)t$K|%d
zLq_yBA8TqP!`kX~37#5xh8kM@brR0N6e->^>sT6}#^cFcjW6FCqEInl=w^8lRY(6n
zI9&N7jejrM@1QEZ0u&C=4BrY0TI&&XF-(#TYT*O$b^3nN0W%98lqvts5I#^jw2uj|
zH*6SC8QKkT-`#rx${7rVI`uIsqYTtD%Nz_pAGwz@X@k&TLg(b=6T0h2F{4I`<<PN1
z{{n|U5b=M?|F=1y&5!xV>9$e7b>%=P^NZHkL&ARTcvDS90jQEq$f{@a@C3j{(8*R-
z{(e@qTV08AwB9S2p4vqYz{U3ctg90Ic=h4Nykk-oHR?DDSJWS?meWJ{1~F4RodM4o
zy}pT`DJR-EliuE;s>L19mr3v5O57Nc|IcUu9)8!zIcll5!Fcp<C?BPlt?W?M+wdpT
z5e=<5mQA~3uYNCeE4%D^ITxrkU{b(`UqiZkJ#Mbqkdz!@pz{knheg^U(i(A=Nw(3q
zYU`=)?f*?AIIByOZ}avAE$mUmpVYxSxiaXLKer3p`Q#3&dN)JHt&`fSJ3X%|2Y)u0
z2OUz4;`=e$M=^^v#Uy7Wf9Fb=J$PVo_@KnI&fx@v8s!;5xBz`npICT<2y5@@E`x@Z
zyE08b|8wQP?i$S4{`jhYFC3`;u2Lg3e4Q@Gi%s4`w{i$oH>>h94$MIxK$o=mkUIFZ
z1C3J*n2zwc4S!D8`ohs+CD1{Lng>W8|3n8~BQCCkR|7_cu=V=epcCu)1U~VG#YhIb
znnL-a^0r7tcrA!^8_Z<RngWi+&3>rTVi*6K6JWe$qJ0c=)%3MI5Rz%C(Ma{){$%B2
zN#MB@`;=Xn?O)>iclh`}HUBGe08Glw4%>A1^l07+-wc$dS`IHJKR|DV^mwU5$O*Nv
zy?28nT@~(2F5L{mk$-N{(L_MBF1&!I#B@3C{!}Fn?AmQKF9--ap<d8^YZe4A4#0#7
zZyIq3p5%-c+*`&Up_$KkI=!oNF%8T%Dmu?Ki!JodNHg@Rv$d@oMxI#>x7_s%XRgo>
z^L&{0-{v)m=ftWsB_DjG?1Fmf>z7?te?r|MCi3>6k>b88u*}d4rZ8WFcIeCLHlVS%
zTEj>OW>D2$OB{F<WTNspNXCDc;1q#;Zu)opfaZY7*r=YVp`xPiOCkKc5JN9ICppbB
zPDR8Wdc`x^&*@GofuXgUhK9!3MvTTMpovcy@(^_7X+Yoi|KX?3In)utUd7PJeL-hL
zlaHMqHZA!@mKc36-Zm|ZK|-=sab?>r`nMhXFR><7eGUWg8k^@=i|`k{NUs!;G%?t;
z%$GQ=M+sb0iWgP&Xj-iw2|WZyH9JS%i)TRBGHB9q7+jC;=lUhaAsoOFc1R@c-O+5x
zFM1-ts>tq9ZB;!v1LH>t+Nd8Fx8)-KuK5g79rZuaf;2zx90wo|{zrU9XCUJZd=hQ*
zr0m|Q5&>MS;GPx5buQaI%pWb*W*5TbAC@9xldOjzS!k9L5?<6Elkm(7pEu}drJwgf
zWJZ5qyAao=+=&x6Mfrz~wKM9*^Q=7e_e<$(G?If3eyLeXFxmEhA@(}UIRLJB<&>wX
zX2|?(!Z)VgZo^b1Xj|Ca>-4m&Jk3p-<sGq?;zKk}hW*`ittKI|*7|k9&a&0Dr^vo$
z2_=O7MEy@qBAE}qKV5unoss2?IN`9gq}j(981MdgWmk;b!PI>q+u0GWD6L87Fsgn?
zU74?@(=;SsbGzFRTVSy!XN=zaxYYk5*8kS^vgldOl^rqet3G*<T*Lk%x}5!Uuhg9k
z8)U+_K8$Bks`N4%3t;8se&yU@T$JPp$@y|ijZ@xD-L3&}shQ617R|(P**)j6LCE`2
z8OJ!Ke*c7<)#2_dk7Aw2+MhjhPKm6$B(Eo)-7gR9^q1#D^UUykl*Vzr{_j!6Th~6k
z$|~H|)lt-6;JO>0t12#O{r#+!3A8UWOMum=;xS@;v@vY8dsj327{=+Kr-D9st0%W}
z?dtWNk}DL-ZF=3H6n`aP>qqhmUglFgHwK*WhaF#=qJF7@{VhjL9XY*(<sM`G$bCf)
z%ze<Sncc|33!5M6e?dFHzT~E&cPPOmS_SHT<f~2N@pi~ywpp{BJ|X;E;N9+5t^Na-
z&gji(IKrk+KWGdyj)uz5#dGOgf0LZGTfkUm%JW%Fe~c0$3@k<dEXIKk8F=LPW2TbD
z-;NYlkP`-0SfLhXTu+7F)&*!4%#>DNN(AW0>sLD~%c*JVZC1bJr}a6~qIWcLz8jvB
zBK0fZ*m>$z)|Y}qy&i^riq1^(`n9|mU4sjSP5$B=&VA+&<7`td2Z5Ru{|MqGzELAm
z&7SQ*d-92Ms(4r2TDM{Uz@l@52m4pC3i!8*+pba5*QX<q7fQ!7D}4oiT_Yq0*J|i5
z;GI^CdiG6fHS{Wi1K7;I7U$Q^bQa;F-`mqW&1DzX*j=1@ot}}k`~v1fH@Q;lJ>@+t
zk!wn?i%juX2EPA@E$aPvVyVc`(q~4)^LvqD|H?IW=<^@bCAI>;sZI|0L@XcvNDA@M
z#ENs-+ARxOr<Uy8kM71<h>umE_Ls(elrjXZ<z!;9SgR7e9NWLOqRRyCH{p4>)Fl&}
zjpwdu_^(yAkU-)8vgcF(E1z}!x4F2w3~|0fyWz48i*bxk?nAVC=5TdMLScpK;zt=^
zG}46rdPBUYNAuH~w+~(m14i=U<oUS<+;}u`^iT+zfxWH^C%&h@@JeiEKXX(y==;vh
z=~3L6(;d*a3iM&>Ex+8^rK%S{q-?fh>h@S2yj+^Fg83>4B2R{;)omj*-5c*Enl!e+
z&!c{J9S0VSGr2;7W+_woBx34>#82pP;P)&$=4So(&6P$+wsIorYJ#?^4#RU%;CChX
z^r~ZJ<%fp7s-Yc&l#{0S1qER=o_^Fv=i<eJwi-^gx^Jx+;$rc6Kcca@DHJ=`B*Pt(
zEtvW_kcd1GC$D<XBtPk&#D&|?IE`7?C;JA#yo8s3foq!5owN>;oY6`-Q6XVN__$nU
zgPmYhyu-H)6**|sZ<(K7vJF%2R<nCxKlE55E((%NZ{ey^X5gOntiw4b0uFspB?72S
zd9UfO8&`b3Yj9RkGnpb-X)`u4mCz8G4zRHv^ym*JyTm_sxGr!__PXLy+K!u`^9oIh
zztH&&kh9#-ybwE6zpXAhvuf#=`?ZI9Q@5ljBcmrp0X8;p_&H!}$mB>GeuON7C5h6t
zrX>XuGE>#=GxT22M*Rf;lSTzWmD!+V%y_RBo49-ew|~VaNdX!RrZel#7D7k)tVSOn
zTj}`xw|gy{Q(^=eWuf!AJ$<+<9pI-8q4orytW(GqP>y>5UZNEcSfiwjEr;KF3mz=t
zJ`)6ppBq<rozIz5mJX=Qba9;J+&K>NNIad<y6E>Sh1aqj3a?X#AG}XSblPMT(hHb+
zHdov}puVD**7X*Pret_V?1ZdGTx6kA(UWkhLKTK9g)Z4Q+3HI$n^im53)HoI1+VlA
zLo_jqW=(sjQiZoM$@On*ERJ3NdINdmXn=MoIBNA8x3HR;$SULB84h7L>-u`7T>sPA
zk`^@&?2xW>g6yzIg$g=NokJtzxqdE&L^_~w_#VSDNa{$<aw<KupQ%C8i6@?ykQfH`
z$~D4AY-TyI$9EGKI|AJRC;aiSwk+EjDVVuC7U(->hQTJu&i8!PMq%dgKP$F>dwzSm
v4q+EQnUc9zP5v1@nE5p7{|8U%&r;wBM|z_4vXnCfeCb^@&@MWE`@#POO~dF`
literal 15730
zcmeHu2UJsAn`jD6X(Av>jer!Th%}`}LCQsnNEbvYp@Vb*1ILO=%LS!LiBc7U)X<3y
z=|vC_LQ#502nmGxPVnCU{WG)PdTZ8tZ`RD42RWOZUBCW)``eqRCPuofhj|Y}AP`o4
zJ#AA6gbsi};P08>U`^=LwPz3rl-cBp*=6t*0#SiLP!JUrhzeL@ASe_B1(tZQ7ObLG
z(|%AYDi{?MN(BX$cohsr1w%y9hJjTOunlZLsbFaBv>)&b9)-c6FkneU;qfRuSngv~
zAQ*5K6a;h76>O$WbMOa)!DBE)3?7fcgXKPkNW>8L@hAu$rGm$R9~9UOw$Wxf_=Cq2
z!CyQPEcfyI`@OxrM2rd%gCgR=4~EtPwt;gT{2>ze!CqiN+~41aK)`wT@tA!g_`x64
zffLYLirrP-fy6j;ThH1b0uhL$J<zzRRc8nU0nyjKXm%%UX(Y^%(>gVI^=NX8VzNS^
zfZmt%Rl4u5<jWFJJaV169hY=tTE45_;v(ve?I&a#*%_PHpPJ*>Uy&5hBt$^0P3;Op
z^K0YjA$0K%1)-1)9w_Vx%YW;~W(k!xdBdC?tvaVRIZawg&j{bn6Ok{EG#;yA731sr
zT1(DQGmy&4TG71FVBDo({VqK<Si{!G)5d3B;Z*1JOk4+1lPYA7W2{tb4ipO?*LXnT
zhuYu{o9wpaCz=x=b{fX9BN;a$f9A9SJ8&m{vqLr$=+Hd31W2DxO)tcp@Kcvg?*uqv
z>yE}|^<CFeeZYGxTh>++N!sX;QroWCQq1XqJr{LevS{dvcUxn}?B>?8m{e#G`ITYW
z00d`2pWkY@`;>ghgd%xe6-gRcI<00yK)z(iPiuIwQs$Hju1c7bftwlMaXid~fx*gc
z1h5mGBDL%$4W)`I+kqujszSj$2|2@Xv%)Dm7uC!C5lf-H<rje<Hyfk5y4AB#QzT$f
z;D4<s><ZC?$tW$cz}oSBrMQJ?{|^D|<qLm$$gpk;VV6Ts9dvAi2iQdLmf>EDynvuR
zxW$E%DtKBAVb9}cQf0-E3#^YI6-TgrYmfGVC*0l6X0|g%c+$_##|*lbus`p5HZ?PE
zxYhHu*O>gEqc3l9rsdDU=K16bdF2wG#9ETngDi2EsUG=`NUDK~40|slvCSk{l=!I>
z=G0h3)kq?A;Jad5E8PsQ?Vo?%_G2n)y-U1L?>n?PIHZ2QZf;(Z!zI{q`w``KYE*ax
zP(wn;YX)ZQVv|cfPsgPaQkOqlcHP}v^N>f5ywZLG!6nK*k+rupcuH;8*fJ1dRVM$r
z_TY=|_9lL-#g~i~z!F2n%WmKG=y~?hL1}BbODJk)*VKzoENeU<<?hc2`-TYr6Y)Ad
zJ!~eU_dVm6Hr`a~^;U+6Ujc!eY`dwb%Qk8)vc!e0a0#9X9t?S<3p}J|FwXKU+zwY1
z7706D%Sp)34Efc<hB^D3i323rspY<G8?}zH*u1INx4x-9DvS%KeBJXNzFQ}N2=iU`
zW|+KwQ+;8w2U*s%hSQQSjd9lF*Edi_TI?2XqzsCrX^PS7@kcI-Gm3XuhS9n14%UYz
zRx|4Hh91LaZGF{^!0Bcu=cse~M8I_77D}wh#AkG%TrzbRT5+whPoGgmF2TPyjb{yt
zU$rUPN(82A@AA%_)|{p^QL3t0T14FD=<-!moa&7|9+r9QL60`Qsy0#79Xg3*E4!Zj
zv7b2|F50=FU;2<7p|$a1q*sb9Eb{0{P#QU~i*cXE$JoR1l+H=!sb<f&5uF*TrIlCO
z-|kISg$Fr~xi@4fk8H^rDSIw`TV8~fI>{=EpP4E6m410x?WVMry2zlQm81VV-q2kQ
zYQmo4E-_vG3q^q(r?tu{-(%Ue;Czjx`}KwzqG`}>;U&Gd>Z?ZT4Z7LEcTrUPXKtFC
zR%~Js3(lOGF@e=`;onsch+VoCJ?b3w*jgiR(52P=0lG?JALAl)VVkMO?x;s~spdq_
z)%a7;(i=8hrJ)I-KJn!2j6XfuJ<Wk!3obEs!hXqje;GQx<B@L^b=P{F9{96hCKijx
z9k4t|3khw?le1Y%?x(c6g^l9|O&ZpUgC#hGkp<k)R!zZoYjN$qVRMCeS5#l#@QuTZ
zGgfVV?az!T&->p}N)@rxB%xR~oN^`1O!~@_VcxPHo)K>W=%m|yAAua2xarla_~nB%
zvZ$=KN0oWFANWl57LuCvOuG)9zj9YZma6$T*-v1{&-+liEc<8btA9)zm{bIR&<M=u
zLxgd(W%O*-$ugVZII)&7nN}~2Mt-B#isl3{yD3{jTd3Q%XQ3pB8MCmsoT9NH*)RjG
zfSc7ls_4Il4hj`-kTa#87of16x<uz%v8MHWH^nC`Co?&8&J!J8p!J60V!&n+%;>c6
z0Ivf~TSkQ1Y8I@HdAf95KHfrkZ$aNI=)B<c(g?`*b@g`cFZ=vAK6S8fX)BbSa@}kJ
zZ0Bd?$PsFV!fzp>o;+=FRg5a0%Z=T-c5Sz;1Q}JJehG-JeXy*_5Ei!gTEoheF+Wz%
zql8<hr?mfSabx8SWi~N*ah6VxH?rTPVBij2^R1u_L;qdl8A#wvm^iYLNT$!{{V-k3
z*ERPWk$J7>Xtljn(f!H76WFz~DIV-{2vXU2G%>Tkt3#wB5SVv%V}`nCGL|Q25<f``
zE`oD2K7t%7tMy5(hl_S>EP>kg$3v!W_r6G1R0RKgeWXF<p?)TlmBU60$MwIkNR6#Y
z8YyaQ?R^@v*#<)4llVjZ{$lGNZAE`orE*6uwOr@Mu8FUSCD%87a^&=M29(C=IA^wN
zXuNeS#8q<qCI;o?Ic8Mg(G04t0K#nsMc(Xz;2MTYE3^hqn>KVQs`B@Z9+H;cL5sLq
zZ`%~NllSlb`AzmVlgS0T5b^bSNOk9O##|Zd-Zfy7+TabSaE_I6+6W%NZ4SJZ79-8Q
zg_o~a{aS;N@2-0+75pS21eC^{(;*@Jk1K=3uB*O!*J-~qov!G(CVrkS-?zOw;dusU
zZofJUK?+H{z#`kV5eWa5vZ-@p{?o5D6Jc%8yTHuSC&KDxGagyoHO18{dC)bFwy5!;
zgDE9tTnff-tKS&?sHhw*j0@WTI3^#TXaQ)5lM~)<xYd<r$QeOPWiJ*RoxE$VIUg!K
z-gBVkGSK;y6%WRI^;L>aklboyz1Gtspf$VE*_w_dn`gg!E52^a*Uf{~%{*pFNStZV
z*se+5KZnn}(U$pVeTeU>7Ug1>=IiNW<lvQsKW$2XZA541`0{Vh8}{6=EhEfik(w7D
zwXVF#WN**NHHWsoQ!Osik<eN43XHigfE_oqG;W!Pfcm}x37p;@0{OF3xa$fE?Qd-1
zW{Y&K8lb~2Tv}kkmEC-F>UAi^cP3Tqr+<I2@oZ;BOjBRh_yMM!eQD%`Em<9}u6v#L
z(sOvShIquJB6|C-m8u}oWjCz>m5DQ58)SHS=s0^=L@mvX^g&N+NDYeT`LgYrZ56Le
zbC?ITYrYJw#Au+Fd>UOBaUB9L23lm8F>3M0P9mE|Hr!5;zNhLo5-jOv%fo%E>s?qw
z)`_9`A)lJiKS1g1lDd5uqc%3ciaEPVd1^lP!bgIgrr3%emb&%qRTVznTk}QpM%U^M
zw5^{nqUTjz$>B3eJM}mF>ML|)7uuQ=LBFGKAdXzyxIfbH=a(<3x!llD^Yovlgoxel
z+Bb^Vamse;rxxh+GU$z<@icjk7Yo19(LFIA%lunD%3$BB8FlLg{I|8j3%cU^M0O3d
z!<jo*o*Af+UOtSSmuIOh3UBrf3j9`;G`~|8(mhNz)5!DrIui3$K;J+FnI%q<c6hmR
zE!^0{F?zwxh8sH_W8fdWBE(bno()6JEy#1iL7tYqmqw1?wO2*<e3mULZMoudM*!hV
zv&@kDC;wYN@9Q@<2$8(!ps;0i7#-sH|FLIM`YLDWANTA|A~V+4w16YBut`b%y~?Ao
zhj%y-#&k^I`Jrpt0MPMoUR<l&l;aXaLpImF$ju$+F9h68pe{^)=vvT3r?TEm6m5$A
z^hWwbi;s9q*1L}rb9xPa0_{`G^8TF-GGU_fUV`lEH?}4NCexcl6=0K3A=0D}TWR^M
zq((<o_U?}JVWmMp>(3(D^g@Txx_Py=BC44rawN%8L=Wh%BsIE+?@o=6kAJGzd^LC+
zI<FitX662@F=zmKdO-Ud{JF*J8OGAn2>lb$%Od3K!LV=Jlln7#VTgW+U42Qom$9aI
z1cWX>)B31RS5YrvBt5PGwxoh|W>|+m-}~(R#LY|xMVfop)n@H@j<nwE;QJDv6MVl{
zT%c99tD}ZG1ovf_rGzZljz0)4u%CPkA)kxtE%R$>?tfg`=-&i=8wAWUN~AkP#uNv<
ze#VMh7bqj7c;z`f7q1u5Jmc4k4p9uHYi?xYDX_*fj?XG=Sbeu0<%iBYN*krPmAE)I
zK~tZHFdaeUnIk-o^wu3O3pE!*i-$Zb7z(h@kSm*yqig=KeC$jaUG%68yKU}8zhUF5
zqtJPIFYgmh+fwbq3DOrTWfwmwle%;Vf2P@ojlN~;R#W{&n)D)nsT?F|nw#s5)w=>*
z*jj&i?AL^yYk$_e?p@f;oO`c!R+;#eorIqHs3+q+mMq=+E)YmvNi_B+krX|OfXZO$
zB(V^=-2UUnp&3#*Uc<s4$;S;3VIGV~Tl5-v5A93(K%w)uLVImlP}G%AQbc9PuzPiH
zVqcJV{N6&$iQgDA*D{~0y6mrJ55<_uR9yn*?WzY84FA|$S@3I~3KKe(^^Lb>tubyd
z$YH6ZWE6MD+A(>7KHqjE1%F9cEif^_lCW5j<4MPaiAtBY7&(R9+w}s;ugCMqd#~eY
z^4<?2qs3EeME&|Ft;|Lz5DO{PFe3AvzUSjS!>kyz#9Y;#HKA5H>cBj<r{K}qcyiSK
ztK-_+Bgdkarw3J_trm4RxF6)_+K(PGTiN8ek+H8PpaJzODQo;=D0+FMoO0|Uu(#|n
zR~vNQekTrtvr1Mx?jMh_9??rmg8Sd?;otsqKTHCy(89js)Rq>KbI6oxL^Z&fV~l|I
zvdk1*UBP(O)qZ*TSz@8$bh=DaUyy^psOp3Hy6d?<ZEprdnS0y(qT5DP)EDM^vnxDW
z!$TDBz$WiQ=-DvA5f%*j^?b_v_9IfnzCGTux+{gfHz&u8Rv(O0$!GHVRm}@dO_dHD
zGEvuQ97?fnEzqKn$J*^xL<Uco&5WGuYzw!*M9P*`Dov0|LxoNvJ0|Rwk}MOh0Je*M
zoP{I;$IF}UD*M*gp{FBcsc_WbUio_cGl;cM3ZZm#+lKPN25#-gRk#_Eui;#EqclpW
zLbqq@Y(;R9@}8x?`nuA7UKS5o(o{?wg`1}s3Nz$$lBe4U=>ezfl!aL^)WE}h(4t7d
z5`k1t#6hiV-Poc8PGzm^4ex7eaUd34jf0-I+N?z>R}8$`vbnu66*=zey1UgmHY74A
z0D?ci>gOC3A#@Bbn||0)b~nkLaMv`N5#&s5<LT?x_<avW)f4>6UoC}^>JMLZ=vTAn
z+v-FSj9Ss<=%$~fqVH|?7Eq5QpVa|wXsUgK1bY>Z&BRf(7Nq=3^~?QNtg1OfZ{dI!
zy5l;sId_$M2SP&n1Yna6kx}MBX$}Ef6OUG}g^P_R#(m_(YP7}Pw{8ncj3IG1{Vaf(
zuOyqlw?PaXHbGa7$sv2NDk~`Ct8N{TJ{O3y%c+>2j<b@&y$#faU96xpIAv1Qi$J*`
zs%9IW@gfi^rOuvzCwp(fIiw?_>Y<kltHjv*kj=?$q5YszDzC}Rh|M*#*iSal`7fsD
z)B4NkEgI?q>*xFT3r29~;ZFNwsaylgUMHaQWs_HCr!}x2M~uZTp(}^nmf-V)a%Bq0
z-uazIp9MPCMh$Fd?F-HI!4`?eQh#Kz4|6oc%V{90Z)bjdXMKHraeTsPx#=RXm26HI
zcB{OI{!9|CP{KlCt22J~!eJE73FphzZgWqfzcCRE=i)mq296o>&mQeymVH+5=#ct|
zhe=i(8BXymaTh_>Z@qggd#uRXG=tGhO6m;kTZEuVpiWmj37B_ECb3yE=3j_k0w=(w
zO$P=OtaP`cq8`t;j{LE~<>CDz(Ei3PAxsqddZ7)I31KlD>GE+Gh@YH$N2a!;boB#`
zN~)kD>4)r=BPF}+Z=l82MI-zgti6woazovtos{z9`auR*usAM#Dil)|@jrYksNY!W
zZSP&#sU4D4G6$|#;Zaf&6NWjx(S2`fTx+bNpYJ5nV10z6q^A9}{cAC@f2%=5YE;Qe
z#ZCQ*7(VtwHWLrg0!yBO`k+y-ulzgimHmphBd6M4_PTUEql5+9-w;O11XWs%*d?`8
zw;R7ZuI?yaUevY~dpjoV5>I4tRDBh><1&fw3z?yr?7oQt-U`Ncu6d<%>wZWTu@*GN
z6+QMLT$j5NX(vnGU2A1Wxoj0$e;s5TK~rC+O47M{)e?@i*C?*`ujuLk7FF>C?oU!`
z{kWi_(d3-kx(?$A;O#clT=VoYqnQBOeV9ET+<RRYT|?Iuuzjl3SyK|w-wsFOg5||x
zaM^upm3M41rByW}hLammz|c$Q^rRWkkd81)5V==J=H5`fympnf0ESmLRK(f%E)u8j
zTyy;<%+_6KqiYxX&c~Qe0=xAYyQOE-EZgW;Bd*}d!RTtbk|nRoS0&=0)_zs4timtJ
z+v&RQM=czz1U4x<3Q?3f^dpG>YKd&q+he=y8-lLf61H0u`#Pw5+Ax0Sv6KEl>#HMJ
zjD~?_iAsdlT;gzaCA#2I*h7f)X9$j86~^_=F6di68O_`4HMZ_1tue+LXG$BKHdL?s
z*^iE?`-mHGC1f$-lkEnS1A){^gP!x4A#86lZhHn*PH@pWcmai^n=^#-5%Q;@Fa_=7
z2>&x!(s)sQUruyvlO)p-?8#P$bLrt1P!(5ur7{@U=QAI6XlIO{qy<0(Hclc1!9MpO
zPybP#?16N2+4B#MQEPWhqh(-R+6$B>;>~5T#Aua`<@ktiAx`1pqN7{P#G@`i_z526
z4k=D;fbx+7H@i`xvbD>rIj?4FPulV<aD4Q~bLd-wWXqO?0ZifUb#_c(SU-h6YeXne
zu*7GXcl_MIHsT8;rM8j3uD&7MXU}tNJ6N4g;)xey{?3*lsa|tLw$NucpQJ~PQ5zH)
z_H|TtU@;-v`AtucGfqWDL0HG|a5MDLn##|Mdtfhg7j=!8QxeF*&|Jg)n(9HVxJu``
ziRVWwcswVLdG+pI-QZX_Gq+915P13YEHcQmb-#uQle!b-btBow(IY}+vb<J%%sDbe
zr*Y#e7xd^SxqZ(J>+lE0In+~X9nz;3&g>ReE>ge7i>rpOBKWlhv1>Z~bb2x5zVM}8
zv3_M+ZfSP`8LOk%d8KY#+g2jIE6VG<VQTHGT1}fZCs?^^31jo!+r8{y7Bivq*Zwb?
z){7Hi3?zafE`VP)k-oWx6;0x)7Do2PX1a+ZaYE7|eq~1AbD7}ZHdUe*%Sb;s!GSp+
z3v-hbTx|@zDsIj!Ttbl*h(_{}DbIG#`T?bIQ=g6?s|~|#!<S=Ges$}*1{uS<trngJ
z525FTaz0IK3hk&udmLb9UWygRi0*ua^?lcd%W9R8Wa&UVn_?WKL%a~O^hY%GT-5t(
z9*ncvR{r+)AR%R?@@_c2<kDuwQwuA832-O$2V~fi(^F~s=JiM)jgdc(!=EqN6l=<@
z9Kr}LJP8c$YEfX<_lFX;*R*`Qh8rM*+W<~|u)tFsiAu;|Ew+1l4vE^(%2Lj>^Eqq?
z)LGwa-m@8bO_cgPCxU7zvT&VFlKs-(Fa@T+1{t#xmmZG(0eD|v4NV$nG1>aC*Wmjt
zU~hEky8IzbB?=Hkd(laZF%($1F21w6aSX8?!Ui4sa<#aNOji4TPY+%$37hnq<27ku
zwUAk8<dIOP?llpl#~8~ewI>BK8J+OcnZ69&%SR9#&^3I35QaKe;Lhx6lWtMvAYQ&;
z&Go3G>tT52`S4f#{2a7CC^U1>%)@cdK@BOMz%z%Zop371{)_K+4u9=`W4AE$%cj_K
zc5!b|8YU`?9QA&Cjo#<W$Iv!~kY9vnso$b@mh@GTjn|Wfl8+_(S8KfRDc)0QL0Nv9
znJF$(|M}}8piS3&9sg-_F0UaWu}p}^E_L$dO%lnsK2Bx(YRSy0u&DVfvtQfRWrJ7j
zEdFR!-C7@EpLLuGM+&{%fIIBE3@~AyKtc?dN!=RdqYf6btuh@$wQ+5bzQ~dN>m}7F
z&AwZCS7yW_1I;YPIKDQR#(0$ooJ0!4COi1IP9Jk#{Y5UnF;0@#?)ZpKT$y}RWRcE&
zNVO=4wd<|Os*&oW2)B{xL7M`%{ruhLy1MK{$kGw$Q4WO9V9CbI0Qu>kZ4H?NXLOQe
zdoFMP92^)2tkKmw>D8Ib36=dNZ^oHVcMd6^uz5wk%tJx-Jp(fZ>AQMB(0$PQV3Z>b
zPC*W6#&m@LfEhZ#58$8$M#o5}rw!C`AkHIbpvFKxKxwNY;s2hJ^$gNo0VREthAo{d
z0{QwDy`C46x9nIkZ8ey}f0a_3A4?@CMMXui57?{UFaRK|B@DCkhNfX#U&&K6kKh7$
zXNns#t_+U?5Ge0!mTpha*Zu*iVV-+(p;PN@v@VW7Lwfdy5D)d+DGYNTx@3GVg44(`
zxTco-JH`hrt{tOwx&=(XOUSPOplA@UE2H~~=1M+7atc(_m!#)Pod2i404rbK%%WTk
zR{GG-iy=lcC>^^697{0rYWIGnl~jp90*{Zw1LTdE*IPn=C@mSg<hV+L9C#v!oIZco
zCaqUUHac@no+CZ>BPRlR`8m|)u3)81<MH}{FgUH7JTi(}osRvQvcSDc1IrCCB^5-G
zzyr~;s5rrm3EKR3;N=_#Or^2*$$8{3$JY>~p#S0T+J(^Z*e4qBwU+}x<$3sL0ghdU
zNmT;W_$tE_RpC&!=CD|JxC6_PVC{7Q45^SoiPI6N5_!D>@Vh7!zhR;csArs1%DNYG
z`8Z;OFaFehbFGue_tQ+>_aWx+p@4pPtnk5T!M_m)M{oQdeVjHL%{Zx6aIfR@am4bI
zSyjZ!1-4Dl_<`{GBO6G3zqnjz%Z&kQGfF?s^gyJ+moDJ$w0!Zse}NKB>_Nm7kR%e1
z?$~biD7EasHy@CP5Pe;jz|?I6B1r@)!TlMI?R`>`(-CY1!{h}5)LxFE+4h<5FUr<d
zJypJo4Qk_oZ1Cs*#pMX(PNl|GE2D29VCDUQn#=hgXFfu#gS8bRI&8E7ke6dDjCCO1
zs!CJn^9Kv0jsb*bxY=lI1_Y;wct>U3j8aFU;?`#cpf)~8jWWLP$cIpO^qDVG`hs_b
zkshqgj^6N>PtGEzCBEMxWwP(3LvZqljSyB(QPA&`fQ&tx{jm7-1U<llz1a~3c9la8
zrgR7SjB;Yh43l#2?ip&IK=>Q<>-cEYhF?&lMK33?jXP`GU(iQpR+{Ks$w1nSd~wQw
znWt&>Z{7ZXxjb$PObfxHA4h}A{g?|2=ARPcpkK6+pa#R4P3Gs0@M?o!wGMZWuT@K$
zoD1F3j|fNwwe^+>)J6(CO(rp<@4i*nU<GyQY%xT7o<Uu0`>o3F_ZvOW<{=P%DD5sl
z9VBPDv&s4a+vsEWBOu{f&LN}TUd%!kT%?WchS)XeAI=K45pfa$74Rg(?AqlLXb@S<
z>>h2c+tAbf=x1K<s0*SOzVR2(!cLYmNXy1VOSCYU{R;V2Hg3gD>!=59?RsdWT%Q`p
zfvAAGwcETuR}QIQ56g*DKYSZ;fFn2JCvUXJ3bg$l!PeIHZWUz?yi}mTB8emhm<u#*
z)HJ*RDKXB{y+q2Md%tR>L2HyjlJ*^yQW|z=G<}L^ToThSqXSagWTg4({rE1x=p>F?
z0p9kLjP(uaqFH0x4gPp}qQ>)}6o!^1E8gF*mX&f1a!?(+f-}UHhLbD(LzO`dJZ=Vf
z_v}SyI1_IKuhh$aJnLdysa%D6O8k2FcdJ;Cm{<ePExj3;nv5>J13sA4%sb%LvkSDs
z^AJZ7E70l=*PD)7hfT_kj`G}6P)!6+S#ZBAIT-S*PbK*_<Y)Y5?ewVQz>CDx!KB^h
zhWrUi#e$$0Z530XeU<c<Ggp|8AG|{_x8B4&k+*Y2yK+MqWW+^!3DxbHIpV^?g6y=Z
z%zoPs&A97H4$(JMV)>ykE|$~CL3d+;7}n)R6-}SI1QKrP5Xc29sLgOcPl@KpFD2wZ
z8CM^gB!NOT6eFvdJ-DgyUHSghZ|?Fk(Cm>qk|fI`q}G6<0qnriJrbCb*0%G-sgb^j
zjn>Z<+Dd`EXc$|xDW-03olhq2HiOj;R?r%^48laPqz*Ussbp7hUfv)N&QJHVBEzJ7
z?LAfyM%<p~ajf+g8x@~a&GkT4xJV9>ImqgH(*$}h$wZC1S~Fg<apx*ybImJEb!#-(
zE{N$`WKcSr4e^?b`Vj^0%e<z7_(AjI5f0yb%!Tk5-(r;^6pwxZ&x%yzrZy;gbOnzu
zfmvTx@VIDG5X?fUV>?_lemLnt|4>fFAICO+w#lqH0UDmaVUk3m#LFkBDn~gH*D_Kn
zCQ{He>*f*!=L2N|U&fj^VlEM~SsNFTZ*gz)Mloo-ls`dz9vsFDn)0UG`D}g(0Se`x
zP7{80<S(!`hh@OSL9lB1`O==adeaB&IoJ}kDCQmBkpm!s{;^}*EMKE`{0ZvU{fqRo
zjaPdUr1?1wI`%u{G(i=V%Z9KrfwKC~aSMwqGMI-)s6l2r-14IjGfk4Ek(oj>x`c-G
zD#5Cu(=_?90!EV}$0`Gy>tt!K7C^f|3)|jcTD{})^u&H&J0DG<FVZ&;$CI6F)_SWm
zlM_0r(Sk0DM-j+RSlIJ1ZAErWH88S5c|zA5hP(l~G39JX&KY$S!I%RZ5ZLU`w@A4F
zUE{+HEHdn{N+SDkENy41>ST2S>lx9(lOTqOR)|+I{0;wsDw+cLibMGCJN+n{VabN1
zq<1%gr`&vK-7e3vn6oq(&43<vrx`>lBxOZ$<mMUoPkh5*tN;Sz6f_b&nhNRIkN3PI
zJl-)kN7y8!g2KoE9=}Mc**?1(bn$nL2U?#&6_a~WR|{nFS@j(IVTt$XT}!Iajzy6|
z>bv=>O478&t3Yx8*Cdrhl7x(2Hn0b2A!wk0&~7(A1k)-211(wwO&`6hZ?N6goZ-39
z5P{{Fax}p=ftHR$CnTwe2!s6|e_(KxV-1mJps_<4Id{67p>pE;fk{<Hz8t;gDMDL%
z7?R_Gq?1^=KLpUC)Dzx7?ny!lhK36-mReCQa$*};`y2L?^!aFEVcieU{;q&Bx_%Bp
zUgr76kS*r{ZNtLW$MY$ZQo|wL{|ia^Ej6GK1vNOH9crX2dVos4zgFq(%2S{OfY`+y
zSPV(zoY;5jdHsg%)$wuTxlH3hx-&IcB}9xhvlZxn8Xc63GPtW##9HM0R^4d9*hTt$
zU-nY{_&QVmbg|#u6Qhvx++wN(bVup`GV<9F#g%)_0vvy{<Jdolxi>VrBtH@R#QASz
zFfgasyXI%qE5-Hw3RNyC{hreMi~hM#k3FS*HMVLPXs5Voy0&;Oc1<3u`6lk#Bbo{2
z#x_n>)xajMzTZ27KsLUIJr|p;%)Q8-`M8}O3JU<e#3!2Dq-`!Bte=>>?Sgi<)h2@-
zz|KwGuyv|$I3ws^85bYQ)c%Dq!!hi}lyq}L`okRuGZ<Yys6DxEXtuqOG%(0Y{P6V2
zKe526^I>>O(N6M$Tq@6Fx8F+T8lTJ;KLtJKa#<)S^Yud-kX+b+oTkMMN!VxBmbZWN
z6J&4|+=K%GCcXmylHh-E%=11u;BTp>nWc4KZmgv0tG2(#UZi(ToIFsL>u}%W8vl?e
zGoZa%GpkYzNg{}*J+b<GUeMfj_(aZ_Mwc?X!+Vk|0B0*`YyZ8&w$V2K=pu!TYFy&;
zSKpbPYl>k!OW5=C^<Dir<f0WzlTRM3bakksS9|pU&0mA6x54OBNgA!}O2~yb?dt#5
zYHo31Z|_8O<(IE+%f5JB;u7Y-QG;H*X7eMz0pH+)>2zE8@My|kG+}i;11%-|ys*(h
z4$GkVC_U&<PajVYt{oMd_m?Ru-&8YV3$Gjf6_X=<VF0K4TR*2Y)AsPbi>*Enq9Gyd
z&0aciK0Z@`m&aj~QBNiLi`aJ?xZlgK@4tY6^5_~G?*!=^t5nF<K1!p=fP2bM7+AUV
zbep2!pk@3>Lr{G=ExG{HP8703%k1C2HZSWJ9g_)%GtmCEJol?Xr7}(K&%<e#G7j;k
zSKr_;rU?{Nw@d@nF+9*WJTx>kX!YwvIR9@WGh(;T>-0M)bA=w>^17)ALjE7PZSnj9
z?_}V_UiBqK`%;ztkG|@<@DSXRL?FH8dB1<Z2@_ql<pH-%4RF7-ukUmJd3z)u4e21*
z>g_0fIN0axpp<`j9fuAnftwp;#2A(J&NF%1=Eet^;m`Mr+YLAdzPKPYNGHA{>!3sb
z+Fkt?>3>^lAIEyxTIn39rXbBnfIEm0*{PFA4>s2aDQugxUBXhta8bAqO{*l}qN7Qp
zhd}EJ?hRsmqz%Dwe=;-=(}gA+c#kKF$T^+wVg*Q$_(wc|W6F7X`{VoWG?FVJU;e|8
z|2F6Uzx<D<z~d)yg}+S7RzZ^osO%?c2if}W#+o$^X`uT372N+wC-Q-&S?f78HO4R?
z*2q7uLsREn+UUIl4ehQ>P&n^{W0dJdsBaEVNz($UFA&3oAnz;jv38^P!A`;~-8+Ht
z<zU3Fzt%kEdK?rPP}Bkf^UCT^spG+G%6|n@v`S9TZyNKR|1cKdP=}s3F@w?pv%j+=
zj)3<Uw|g4a?8CXcbA?>emqDomciLb`9_9bniQ4Plt9L*j@dVsBbxri=9M4Mf_M!P3
zUoalftmITs@vj%AMb5&kChq^*N*wV4_(kvcy}Q~9gI@alJKfNeJP4ek&=m0QX5X$e
zO`IKp<)XGp+i7JnKJaK}9kgtj1MhW&Sxf>)26oVB{`RGCCz_@52gGvK#?mty&K?34
z+k>UqKNj8qo_$Dl7&R<8%QXJ@=gRB`NS|$Vs{n^3`$2^JL>U>wC*r3XTfs1?NPtGH
zGJp>LoVOmnAE=vF{t<U@cyMwQA}!Xh4pN2AH3mv;_r3`SmGHR>YUvJ2h?bm48F|kD
z=5ObJu4wGNvY{Uj`_Rw#JHx<-wZ)Gp?mzO;vGYNWlK6jd-U8ZjK&O550>s(AZ!y5Y
z^*0$)3NJYWY#O+`;j}32e{+uU&u1F{|NDOl3M{(;>#jRTOBiWMYz_o1NgKwC$bpuW
zL>>iGy;uQu{fQ)S*9j)cU7NIeHcvUQ|LbgMkeX=R*dYfl51?q&DoiaiJOF(GI<$(}
z2`_kJlm@LqkE+c2{pws|W$KQNoZNnS+3EGaNsxkbukDQp%g8az67_l0D*NF{ZWzHG
zT3Qrr^4rT1Hu@L2Qd;HC3*qRI%s;olOH3;Afi4fy2uAS~h5;}SR?W{Uf>afZC%)sl
zxTv9dl|jO8WX{t^Kh8Q!*h-Nr#-8nnDy$rVL`rZlNQ}_&Rm9cQdf$h3ADJ+k)z4Ex
zRd)aEe9ZX%S~RrgL>~Q?lltwKl)N%iIz-iRxKr$>yv7T=s~<NdH95b|NvJ`%uQIr<
zh71q&DTY>mdIhB=7>|+sRWD}A2O;5FT>m0@`i=2;{v9~o&0kDMfSdpB2csOb!U7pT
z_OsGqmTB7qK8^&`E^kg{a2T0J_j3IdrBBIK&y3*+XAw@zKAtD}QC}FjEWC4E`@FuK
z(Y1#O+Q9JTO}Qtx;~mm+nZ%z$s-u269{DNSc;1l1=qS{W=Vue*qy97BRN*vH*rd$I
zxQh=HxF!@XpVy~rwtFb_fJt2Pi`%o?@l2RnCQXLF*W^G1|7ThdGAv8SggpBn@oe*B
ziOLhAC)9VjLe=mS#Fht{3lU4Z<sDsd@uDHF#vewFd%@dj`Y!ehx|HyEKjn!@b29sg
z+t36AZ8Vc0w}qaS8+=S%_<Xo~)cE=ZsQy~vZg+#xwJpBWVptoi4RrkBF{60VZwgC3
z07`$VZ{CG{<ZiqbbZFbHObl^hQLQ|w*NmK(0iZLpdp@T^mfVJjkQ8^J?1HD3T}!8e
z?VU51-Oo|Nhe{7^RyF6{TrUcB&CGL4HF`R@wdJ7#jVr|!*JoybY=0ZGrLg1$rly<T
zOVu{LYC>rx4Z8b~na8%>UYakcqYjr6mbVphveJ{jNo7&TC?H_D7tDcgd2aS_vk1X<
z!E#;uB+anz-o5)?@p)YZkfr@{!+G+C!(mEzYEOwws{1ih`M@wu{R?HJ)wrn@gNRg$
zBGL`tHt5(<zUySMY;U9b$}tu1=irc<EBx-yEAcIJ<t&&zg(VMQ{>9Fh{mL*ml~78b
z#^GbV<u8Qhp5#iVzg|@4ZW7HoqtX<08oAY54qlPNo8*OU6T3!I_We_#&rn0HaRCaw
z3YtPZSwfAXIYPDT`;4l{*52}W(9)Ss&&*(GVj-ka!D~v8sF&*&pMH{bZaa)CL7^pF
zy)S##m=ntT1iTSr<a3(+e&bm~Ye2A}Jt*PxS^dU4oCp`W9SYxT787)+Gk>oF?WWRn
z^ixk=FS-P?Wq&bbr|{;IawB*zKt|tJ^i--_Ygg)7k3fzqJ=wcsaHx$X9bp$dVh*^T
z&LGgGaH26Bx0{*m9n92S^ZGp9t*8}=<m$JpShZ@^c(+!=vZsUF`fs~%lM=~g=Z!uV
zYX=K<f3rPgpZ*75lL9x&8K8v4=jva>xD5?JF8lGiOXKBVjfux7Zc607dCus%BCgML
z#O2bvGx5y6?iPSUGTyCcXLEU1!4Q`*y}%%M#Z(n(%Z$hC$y_e_t}II2cQY8^5LEDa
zQ@PUnTqdrcjl5`Cv65g`5WI0)ai^yBdgtPHht(fJ04P^)RV@?*hZfvgjU>;yAVwP`
zm1RJobq}OTh7X*pV`=tq%=Oac?Q%uSWzw;wZH1AHZ=6S33<b~hLuHqrRN?K%t4{j7
z3NfDD%~0B2&M^llcT=Acm7L!`2;0`sKehd&c1>Z)7jU5dao<)RxvlOsW|R$C+E6$_
zt#r^PUlywVBB^=z3<D4bMw(2I|I<GgzwYc7EI-&^8MNG$`*8LMVwSq|vU2T{Y(*0t
z{33vL-rM_;u#@m|wPZQ}rUcWG=k4~Io7F2W$`e{jpO#O-=zK^6`VrSu#PqB8UBDDj
zMfiCGwn`<N?_f4-G!3SJJL)fQ6rWwu@uGqI`mGHP=zZlR$VjyA$}@sd20ESKL%5x2
zrr8Ak2gQ$$lgPPiLfl~?)BC#x)Qy5s@gIUGk-w&oV6E%Fl9vc5_VNwtl?3hcx=dg)
z^cOxH=yAd0iyL;6`nQZyB`oeO3xVJS0^qFy(AKTtPd9r}R*c7t*4_?B6W^rnU-L*Z
z-ZG=WM!>Y`=v&B$hOysN%H!Vgv3)B#*CD(5lz?EEFJf^IT+;&d&LNUh7gJAF=-QL2
z`0@6{(L)Ni_!b3)4;l@dW)~M6!ZkWo9q&8!KhlVcf}}9ocqo?{dF4KBbBlQbhu*Ig
zMk-JEtr)IWx<6=3^K;!p?WuVa%IllN(cG%{mIXjqF9W$`N}nimN4CoA8`-Y?7s!KZ
zJwt~SmNXvDav<)UfthW5DV*m|Wi9f%etI|f1lDrNa<8Q9st#~~Y6!51dn0vzs$}Cb
zo}|lyxgfhbt*I0Y<G^k|fqVe}gTsBs_gI=kMc!6$rSzad!*1TRj0-G42%OsA241RM
zRmv<sl=R@Q?!iLcQXCu5irD)vRNuW+y?6d_5Uu9|cr(sO)l-mOeg<kiBXG<z7hj}1
zrFO6cv6Tc|xl`kE$x__JMfIL{>q`+ov30aI@WW7rv&QzPoXaKqM3+m-@8}KW1Jej<
z*V$EyMx#AG96;}3&)i?f8*aLXRtc@GQkTT{SMlzF7tMa*_xgU}61bxj)1_>uQvVG6
zCAh%|l5=?%cq_!c0dMV$Rzgu?=iQwpSS`usw}v@Z!BO8|okj))X%BO5g@Z3Op<y1T
zOIAkL$^+<|w)$CyL211168kI#S5mvt|3-a;4^naC)5&6xPPZ0HeFUYxS%(m$<nGGP
zt6v6+(V0ynd)f5!W6fJZAK9?mPa(G$mpg^>$RT$q9ur^P?C*JJYG!F}a6<2Av}GlY
ze<E-QeF4K!tZVq5><FVv;oh+Qe}uFDzrDu3P&%(jL*bdd83_2Jf7wX8=+e#m{{u<w
Bkl_FT
diff --git a/public/search.json b/public/search.json
index aa6aea2..9bf7ba5 100644
--- a/public/search.json
+++ b/public/search.json
@@ -18,7 +18,7 @@
"href": "07-basic_statistics.html#cluster-analysis",
"title": "6Â Basic statistics for spatial analysis",
"section": "6.2 Cluster analysis",
- "text": "6.2 Cluster analysis\n\n6.2.1 General introduction\nWhy studying clusters in epidemiology? Cluster analysis help identifying unusual patterns that occurs during a given period of time. The underlying ultimate goal of such analysis is to explain the observation of such patterns. In epidemiology, we can distinguish two types of process that would explain heterogeneity in case distribution:\n\nThe 1st order effects are the spatial variations of cases distribution caused by underlying properties of environment or the population structure itself. In such process individual get infected independently from the rest of the population. Such process includes the infection through an environment at risk as, for example, air pollution, contaminated waters or soils and UV exposition. This effect assume that the observed pattern is caused by a difference in risk intensity.\nThe 2nd order effects describes process of spread, contagion and diffusion of diseases caused by interactions between individuals. This includes transmission of infectious disease by proximity, but also the transmission of non-infectious disease, for example, with the diffusion of social norms within networks. This effect assume that the observed pattern is caused by correlations or co-variations.\n\n\n\n\n\n\nNo statistical methods could distinguish between these competing processes since their outcome results in similar pattern of points. The cluster analysis help describing the magnitude and the location of pattern but in no way could answer the question of why such patterns occurs. It is therefore a step that help detecting cluster for description and surveillance purpose and rising hypothesis on the underlying process that will lead further investigations.\nKnowledge about the disease and its transmission process could orientate the choice of the methods of study. We presented in this brief tutorial two methods of cluster detection, the Moran’s I test that test for spatial independence (likely related to 2nd order effects) and the scan statistics that test for homogeneous distribution (likely related 1st order effects). It relies on epidemiologist to select the tools that best serve the studied question.\n\n\n\n\n\n\nStatistic tests and distributions\n\n\n\nIn statistics, problems are usually expressed by defining two hypotheses: the null hypothesis (H0), i.e., an a priori hypothesis of the studied phenomenon (e.g., the situation is a random) and the alternative hypothesis (H1), e.g., the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nIn mathematics, a probability distribution is a mathematical expression that represents what we would expect due to random chance. The choice of the probability distribution relies on the type of data you use (continuous, count, binary). In general, three distribution a used while studying disease rates, the Binomial, the Poisson and the Poisson-gamma mixture (also known as negative binomial) distributions.\nMany the statistical tests assume by default that data are normally distributed. It implies that your variable is continuous and that all data could easily be represented by two parameters, the mean and the variance, i.e., each value have the same level of certainty. If many measure can be assessed under the normality assumption, this is usually not the case in epidemiology with strictly positives rates and count values that 1) does not fit the normal distribution and 2) does not provide with the same degree of certainty since variances likely differ between district due to different population size, i.e., some district have very sparse data (with high variance) while other have adequate data (with lower variance).\n\n# dataset statistics\nm_cases <- mean(district$incidence)\nsd_cases <- sd(district$incidence)\n\nhist(district$incidence, probability = TRUE, ylim = c(0, 0.4), xlim = c(-5, 16), xlab = \"Number of cases\", ylab = \"Probability\", main = \"Histogram of observed incidence compared\\nto Normal and Poisson distributions\")\n\ncurve(dnorm(x, m_cases, sd_cases),col = \"blue\", lwd = 1, add = TRUE)\n\npoints(0:max(district$incidence), dpois(0:max(district$incidence),m_cases),\n type = 'b', pch = 20, col = \"red\", ylim = c(0, 0.6), lty = 2)\n\nlegend(\"topright\", legend = c(\"Normal distribution\", \"Poisson distribution\", \"Observed distribution\"), col = c(\"blue\", \"red\", \"black\"),pch = c(NA, 20, NA), lty = c(1, 2, 1))\n\n\n\n\nIn this tutorial, we used the Poisson distribution in our statistical tests.\n\n\n\n\n6.2.2 Test for spatial autocorrelation (Moran’s I test)\n\n6.2.2.1 The global Moran’s I test\nA popular test for spatial autocorrelation is the Moran’s test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\n\n\n\n\n\n\nMoran’s I test\n\n\n\nThe Moran’s statistics is:\n\\[I = \\frac{N}{\\sum_{i=1}^N\\sum_{j=1}^Nw_{ij}}\\frac{\\sum_{i=1}^N\\sum_{j=1}^Nw_{ij}(Y_i-\\bar{Y})(Y_j - \\bar{Y})}{\\sum_{i=1}^N(Y_i-\\bar{Y})^2}\\] with:\n\n\\(N\\): the number of polygons,\n\\(w_{ij}\\): is a matrix of spatial weight with zeroes on the diagonal (i.e., \\(w_{ii}=0\\)). For example, if polygons are neighbors, the weight takes the value \\(1\\) otherwise it takes the value \\(0\\).\n\\(Y_i\\): the variable of interest,\n\\(\\bar{Y}\\): the mean value of \\(Y\\).\n\nUnder the Moran’s test, the statistics hypotheses are:\n\nH0: the distribution of cases is spatially independent, i.e., \\(I=0\\).\nH1: the distribution of cases is spatially autocorrelated, i.e., \\(I\\ne0\\).\n\n\n\nWe will compute the Moran’s statistics using spdep(R. Bivand et al. 2015) and Dcluster(Gómez-Rubio et al. 2015) packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. In this example, we use poly2nb() and nb2listw(). These functions respectively detect the neighboring polygons and assign weight corresponding to \\(1/\\#\\ of\\ neighbors\\). Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\n#install.packages(\"spdep\")\n#install.packages(\"DCluster\")\nlibrary(spdep) # Functions for creating spatial weight, spatial analysis\nlibrary(DCluster) # Package with functions for spatial cluster analysis\n\nqueen_nb <- poly2nb(district) # Neighbors according to queen case\nq_listw <- nb2listw(queen_nb, style = 'W') # row-standardized weights\n\n# Moran's I test\nm_test <- moranI.test(cases ~ offset(log(expected)), \n data = district,\n model = 'poisson',\n R = 499,\n listw = q_listw,\n n = length(district$cases), # number of regions\n S0 = Szero(q_listw)) # Global sum of weights\nprint(m_test)\n\nMoran's I test of spatial autocorrelation \n\n Type of boots.: parametric \n Model used when sampling: Poisson \n Number of simulations: 499 \n Statistic: 0.1566449 \n p-value : 0.012 \n\nplot(m_test)\n\n\n\n\nThe Moran’s statistics is here \\(I =\\) 0.16. When comparing its value to the H0 distribution (built under 499 simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is \\(p_{value} =\\) 0.012. We therefore reject H0 with error risk of \\(\\alpha = 5\\%\\). The distribution of cases is therefore autocorrelated across districts in Cambodia.\n\n\n6.2.2.2 The Local Moran’s I LISA test\nThe global Moran’s test provides us a global statistical value informing whether autocorrelation occurs over the territory but does not inform on where does these correlations occurs, i.e., what is the locations of the clusters. To identify such cluster, we can decompose the Moran’s I statistic to extract local information of the level of correlation of each district and its neighbors. This is called the Local Moran’s I LISA statistic. Because the Local Moran’s I LISA statistic test each district for autocorrelation independently, concern is raised about multiple testing limitations that increase the Type I error (\\(\\alpha\\)) of the statistical tests. The use of local test should therefore be study in light of explore and describes clusters once the global test has detected autocorrelation.\n\n\n\n\n\n\nStatistical test\n\n\n\nFor each district \\(i\\), the Local Moran’s I statistics is:\n\\[I_i = \\frac{(Y_i-\\bar{Y})}{\\sum_{i=1}^N(Y_i-\\bar{Y})^2}\\sum_{j=1}^Nw_{ij}(Y_j - \\bar{Y}) \\text{ with } I = \\sum_{i=1}^NI_i/N\\]\n\n\nThe localmoran()function from the package spdep treats the variable of interest as if it was normally distributed. In some cases, this assumption could be reasonable for incidence rate, especially when the areal units of analysis have sufficiently large population count suggesting that the values have similar level of variances. Unfortunately, the local Moran’s test has not been implemented for Poisson distribution (population not large enough in some districts) in spdep package. However, Bivand et al. (R. S. Bivand et al. 2008) provided some code to manually perform the analysis using Poisson distribution and this code was further implemented in the course “Spatial Epidemiologyâ€.\n\n# Step 1 - Create the standardized deviation of observed from expected\nsd_lm <- (district$cases - district$expected) / sqrt(district$expected)\n\n# Step 2 - Create a spatially lagged version of standardized deviation of neighbors\nwsd_lm <- lag.listw(q_listw, sd_lm)\n\n# Step 3 - the local Moran's I is the product of step 1 and step 2\ndistrict$I_lm <- sd_lm * wsd_lm\n\n# Step 4 - setup parameters for simulation of the null distribution\n\n# Specify number of simulations to run\nnsim <- 499\n\n# Specify dimensions of result based on number of regions\nN <- length(district$expected)\n\n# Create a matrix of zeros to hold results, with a row for each county, and a column for each simulation\nsims <- matrix(0, ncol = nsim, nrow = N)\n\n# Step 5 - Start a for-loop to iterate over simulation columns\nfor(i in 1:nsim){\n y <- rpois(N, lambda = district$expected) # generate a random event count, given expected\n sd_lmi <- (y - district$expected) / sqrt(district$expected) # standardized local measure\n wsd_lmi <- lag.listw(q_listw, sd_lmi) # standardized spatially lagged measure\n sims[, i] <- sd_lmi * wsd_lmi # this is the I(i) statistic under this iteration of null\n}\n\n# Step 6 - For each county, test where the observed value ranks with respect to the null simulations\nxrank <- apply(cbind(district$I_lm, sims), 1, function(x) rank(x)[1])\n\n# Step 7 - Calculate the difference between observed rank and total possible (nsim)\ndiff <- nsim - xrank\ndiff <- ifelse(diff > 0, diff, 0)\n\n# Step 8 - Assuming a uniform distribution of ranks, calculate p-value for observed\n# given the null distribution generate from simulations\ndistrict$pval_lm <- punif((diff + 1) / (nsim + 1))\n\nBriefly, the process consist on 1) computing the I statistics for the observed data, 2) estimating the null distribution of the I statistics by performing random sampling into a poisson distribution and 3) comparing the observed I statistic with the null distribution to determine the probability to observe such value if the number of cases were spatially independent. For each district, we obtain a p-value based on the comparison of the observed value and the null distribution.\nA conventional way of plotting these results is to classify the districts into 5 classes based on local Moran’s I output. The classification of cluster that are significantly autocorrelated to their neighbors is performed based on a comparison of the scaled incidence in the district compared to the scaled weighted averaged incidence of it neighboring districts (computed with lag.listw()):\n\nDistricts that have higher-than-average rates in both index regions and their neighbors and showing statistically significant positive values for the local \\(I_i\\) statistic are defined as High-High (hotspot of the disease)\nDistricts that have lower-than-average rates in both index regions and their neighbors and showing statistically significant positive values for the local \\(I_i\\) statistic are defined as Low-Low (cold spot of the disease).\nDistricts that have higher-than-average rates in the index regions and lower-than-average rates in their neighbors, and showing statistically significant negative values for the local \\(I_i\\) statistic are defined as High-Low(outlier with high incidence in an area with low incidence).\nDistricts that have lower-than-average rates in the index regions and higher-than-average rates in their neighbors, and showing statistically significant negative values for the local \\(I_i\\) statistic are defined as Low-High (outlier of low incidence in area with high incidence).\nDistricts with non-significant values for the \\(I_i\\) statistic are defined as Non-significant.\n\n\n# create lagged local raw_rate - in other words the average of the queen neighbors value\n# values are scaled (centered and reduced) to be compared to average\ndistrict$lag_std <- scale(lag.listw(q_listw, var = district$incidence))\ndistrict$incidence_std <- scale(district$incidence)\n\n# extract pvalues\n# district$lm_pv <- lm_test[,5]\n\n# Classify local moran's outputs\ndistrict$lm_class <- NA\ndistrict$lm_class[district$incidence_std >=0 & district$lag_std >=0] <- 'High-High'\ndistrict$lm_class[district$incidence_std <=0 & district$lag_std <=0] <- 'Low-Low'\ndistrict$lm_class[district$incidence_std <=0 & district$lag_std >=0] <- 'Low-High'\ndistrict$lm_class[district$incidence_std >=0 & district$lag_std <=0] <- 'High-Low'\ndistrict$lm_class[district$pval_lm >= 0.05] <- 'Non-significant'\n\ndistrict$lm_class <- factor(district$lm_class, levels=c(\"High-High\", \"Low-Low\", \"High-Low\", \"Low-High\", \"Non-significant\") )\n\n# create map\nmf_map(x = district,\n var = \"lm_class\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n #val_order = c(\"High-High\", \"Low-Low\", \"High-Low\", \"Low-High\", \"Non-significant\") ,\n pal = c(\"#6D0026\" , \"blue\", \"white\") , # \"#FF755F\",\"#7FABD3\" ,\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using Local Moran's I statistic\")\n\n\n\n\n\n\n\n6.2.3 Spatial scan statistics\nWhile Moran’s indices focus on testing for autocorrelation between neighboring polygons (under the null assumption of spatial independence), the spatial scan statistic aims at identifying an abnormal higher risk in a given region compared to the risk outside of this region (under the null assumption of homogeneous distribution). The conception of a cluster is therefore different between the two methods.\nThe function kulldorff from the package SpatialEpi (Kim and Wakefield 2010) is a simple tool to implement spatial-only scan statistics.\n\n\n\n\n\n\nKulldorf test\n\n\n\nUnder the kulldorff test, the statistics hypotheses are:\n\nH0: the risk is constant over the area, i.e., there is a spatial homogeneity of the incidence.\nH1: a particular window have higher incidence than the rest of the area , i.e., there is a spatial heterogeneity of incidence.\n\n\n\nBriefly, the kulldorff scan statistics scan the area for clusters using several steps:\n\nIt create a circular window of observation by defining a single location and an associated radius of the windows varying from 0 to a large number that depends on population distribution (largest radius could include 50% of the population).\nIt aggregates the count of events and the population at risk (or an expected count of events) inside and outside the window of observation.\nFinally, it computes the likelihood ratio and test whether the risk is equal inside versus outside the windows (H0) or greater inside the observed window (H1). The H0 distribution is estimated by simulating the distribution of counts under the null hypothesis (homogeneous risk).\nThese 3 steps are repeated for each location and each possible windows-radii.\n\nWhile we test the significance of a large number of observation windows, one can raise concern about multiple testing and Type I error. This approach however suggest that we are not interest in a set of signifiant cluster but only in a most-likely cluster. This a priori restriction eliminate concern for multpile comparison since the test is simplified to a statistically significance of one single most-likely cluster.\nBecause we tested all-possible locations and window-radius, we can also choose to look at secondary clusters. In this case, you should keep in mind that increasing the number of secondary cluster you select, increases the risk for Type I error.\n\n#install.packages(\"SpatialEpi\")\nlibrary(\"SpatialEpi\")\n\nThe use of R spatial object is not implements in kulldorff() function. It uses instead matrix of xy coordinates that represents the centroids of the districts. A given district is included into the observed circular window if its centroids fall into the circle.\n\ndistrict_xy <- st_centroid(district) %>% \n st_coordinates()\n\nhead(district_xy)\n\n X Y\n1 330823.3 1464560\n2 749758.3 1541787\n3 468384.0 1277007\n4 494548.2 1215261\n5 459644.2 1194615\n6 360528.3 1516339\n\n\nWe can then call kulldorff function (you are strongly encouraged to call ?kulldorff to properly call the function). The alpha.level threshold filter for the secondary clusters that will be retained. The most-likely cluster will be saved whatever its significance.\n\nkd_Wfever <- kulldorff(district_xy, \n cases = district$cases,\n population = district$T_POP,\n expected.cases = district$expected,\n pop.upper.bound = 0.5, # include maximum 50% of the population in a windows\n n.simulations = 499,\n alpha.level = 0.2)\n\n\n\n\nThe function plot the histogram of the distribution of log-likelihood ratio simulated under the null hypothesis that is estimated based on Monte Carlo simulations. The observed value of the most significant cluster identified from all possible scans is compared to the distribution to determine significance. All outputs are saved into an R object, here called kd_Wfever. Unfortunately, the package did not develop any summary and visualization of the results but we can explore the output object.\n\nnames(kd_Wfever)\n\n[1] \"most.likely.cluster\" \"secondary.clusters\" \"type\" \n[4] \"log.lkhd\" \"simulated.log.lkhd\" \n\n\nFirst, we can focus on the most likely cluster and explore its characteristics.\n\n# We can see which districts (r number) belong to this cluster\nkd_Wfever$most.likely.cluster$location.IDs.included\n\n [1] 48 93 66 180 133 29 194 118 50 144 31 141 3 117 22 43 142\n\n# standardized incidence ratio\nkd_Wfever$most.likely.cluster$SMR\n\n[1] 2.303106\n\n# number of observed and expected cases in this cluster\nkd_Wfever$most.likely.cluster$number.of.cases\n\n[1] 122\n\nkd_Wfever$most.likely.cluster$expected.cases\n\n[1] 52.97195\n\n\n17 districts belong to the cluster and its number of cases is 2.3 times higher than the expected number of cases.\nSimilarly, we could study the secondary clusters. Results are saved in a list.\n\n# We can see which districts (r number) belong to this cluster\nlength(kd_Wfever$secondary.clusters)\n\n[1] 1\n\n# retrieve data for all secondary clusters into a table\ndf_secondary_clusters <- data.frame(SMR = sapply(kd_Wfever$secondary.clusters, '[[', 5), \n number.of.cases = sapply(kd_Wfever$secondary.clusters, '[[', 3),\n expected.cases = sapply(kd_Wfever$secondary.clusters, '[[', 4),\n p.value = sapply(kd_Wfever$secondary.clusters, '[[', 8))\n\nprint(df_secondary_clusters)\n\n SMR number.of.cases expected.cases p.value\n1 3.767698 16 4.246625 0.016\n\n\nWe only have one secondary cluster composed of one district.\n\n# create empty column to store cluster informations\ndistrict$k_cluster <- NA\n\n# save cluster information from kulldorff outputs\ndistrict$k_cluster[kd_Wfever$most.likely.cluster$location.IDs.included] <- 'Most likely cluster'\n\nfor(i in 1:length(kd_Wfever$secondary.clusters)){\ndistrict$k_cluster[kd_Wfever$secondary.clusters[[i]]$location.IDs.included] <- paste(\n 'Secondary cluster', i, sep = '')\n}\n\n#district$k_cluster[is.na(district$k_cluster)] <- \"No cluster\"\n\n\n# create map\nmf_map(x = district,\n var = \"k_cluster\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n pal = mf_get_pal(palette = \"Reds\", n = 3)[1:2],\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using kulldorf scan statistic\")\n\n\n\n\n\n\n\n\n\n\nTo go further …\n\n\n\nIn this example, the expected number of cases was defined using the population count but note that standardization over other variables as age could also be implemented with the strata parameter in the kulldorff() function.\nIn addition, this cluster analysis was performed solely using the spatial scan but you should keep in mind that this method of cluster detection can be implemented for spatio-temporal data as well where the cluster definition is an abnormal number of cases in a delimited spatial area and during a given period of time. The windows of observation are therefore defined for a different center, radius and time-period. You should take a look at the function scan_ep_poisson() function in the package scanstatistic (Allévius 2018) for this analysis."
+ "text": "6.2 Cluster analysis\n\n6.2.1 General introduction\nWhy studying clusters in epidemiology? Cluster analysis help identifying unusual patterns that occurs during a given period of time. The underlying ultimate goal of such analysis is to explain the observation of such patterns. In epidemiology, we can distinguish two types of process that would explain heterogeneity in case distribution:\n\nThe 1st order effects are the spatial variations of cases distribution caused by underlying properties of environment or the population structure itself. In such process individual get infected independently from the rest of the population. Such process includes the infection through an environment at risk as, for example, air pollution, contaminated waters or soils and UV exposition. This effect assume that the observed pattern is caused by a difference in risk intensity.\nThe 2nd order effects describes process of spread, contagion and diffusion of diseases caused by interactions between individuals. This includes transmission of infectious disease by proximity, but also the transmission of non-infectious disease, for example, with the diffusion of social norms within networks. This effect assume that the observed pattern is caused by correlations or co-variations.\n\n\n\n\n\n\nNo statistical methods could distinguish between these competing processes since their outcome results in similar pattern of points. The cluster analysis help describing the magnitude and the location of pattern but in no way could answer the question of why such patterns occurs. It is therefore a step that help detecting cluster for description and surveillance purpose and rising hypothesis on the underlying process that will lead further investigations.\nKnowledge about the disease and its transmission process could orientate the choice of the methods of study. We presented in this brief tutorial two methods of cluster detection, the Moran’s I test that test for spatial independence (likely related to 2nd order effects) and the scan statistics that test for homogeneous distribution (likely related 1st order effects). It relies on epidemiologist to select the tools that best serve the studied question.\n\n\n\n\n\n\nStatistic tests and distributions\n\n\n\nIn statistics, problems are usually expressed by defining two hypotheses: the null hypothesis (H0), i.e., an a priori hypothesis of the studied phenomenon (e.g., the situation is a random) and the alternative hypothesis (H1), e.g., the situation is not random. The main principle is to measure how likely the observed situation belong to the ensemble of situation that are possible under the H0 hypothesis.\nIn mathematics, a probability distribution is a mathematical expression that represents what we would expect due to random chance. The choice of the probability distribution relies on the type of data you use (continuous, count, binary). In general, three distribution a used while studying disease rates, the Binomial, the Poisson and the Poisson-gamma mixture (also known as negative binomial) distributions.\nMany the statistical tests assume by default that data are normally distributed. It implies that your variable is continuous and that all data could easily be represented by two parameters, the mean and the variance, i.e., each value have the same level of certainty. If many measure can be assessed under the normality assumption, this is usually not the case in epidemiology with strictly positives rates and count values that 1) does not fit the normal distribution and 2) does not provide with the same degree of certainty since variances likely differ between district due to different population size, i.e., some district have very sparse data (with high variance) while other have adequate data (with lower variance).\n\n# dataset statistics\nm_cases <- mean(district$incidence)\nsd_cases <- sd(district$incidence)\n\nhist(district$incidence, probability = TRUE, ylim = c(0, 0.4), xlim = c(-5, 16), xlab = \"Number of cases\", ylab = \"Probability\", main = \"Histogram of observed incidence compared\\nto Normal and Poisson distributions\")\n\ncurve(dnorm(x, m_cases, sd_cases),col = \"blue\", lwd = 1, add = TRUE)\n\npoints(0:max(district$incidence), dpois(0:max(district$incidence),m_cases),\n type = 'b', pch = 20, col = \"red\", ylim = c(0, 0.6), lty = 2)\n\nlegend(\"topright\", legend = c(\"Normal distribution\", \"Poisson distribution\", \"Observed distribution\"), col = c(\"blue\", \"red\", \"black\"),pch = c(NA, 20, NA), lty = c(1, 2, 1))\n\n\n\n\nIn this tutorial, we used the Poisson distribution in our statistical tests.\n\n\n\n\n6.2.2 Test for spatial autocorrelation (Moran’s I test)\n\n6.2.2.1 The global Moran’s I test\nA popular test for spatial autocorrelation is the Moran’s test. This test tells us whether nearby units tend to exhibit similar incidences. It ranges from -1 to +1. A value of -1 denote that units with low rates are located near other units with high rates, while a Moran’s I value of +1 indicates a concentration of spatial units exhibiting similar rates.\n\n\n\n\n\n\nMoran’s I test\n\n\n\nThe Moran’s statistics is:\n\\[I = \\frac{N}{\\sum_{i=1}^N\\sum_{j=1}^Nw_{ij}}\\frac{\\sum_{i=1}^N\\sum_{j=1}^Nw_{ij}(Y_i-\\bar{Y})(Y_j - \\bar{Y})}{\\sum_{i=1}^N(Y_i-\\bar{Y})^2}\\] with:\n\n\\(N\\): the number of polygons,\n\\(w_{ij}\\): is a matrix of spatial weight with zeroes on the diagonal (i.e., \\(w_{ii}=0\\)). For example, if polygons are neighbors, the weight takes the value \\(1\\) otherwise it takes the value \\(0\\).\n\\(Y_i\\): the variable of interest,\n\\(\\bar{Y}\\): the mean value of \\(Y\\).\n\nUnder the Moran’s test, the statistics hypotheses are:\n\nH0: the distribution of cases is spatially independent, i.e., \\(I=0\\).\nH1: the distribution of cases is spatially autocorrelated, i.e., \\(I\\ne0\\).\n\n\n\nWe will compute the Moran’s statistics using spdep(R. Bivand et al. 2015) and Dcluster(Gómez-Rubio et al. 2015) packages. spdep package provides a collection of functions to analyze spatial correlations of polygons and works with sp objects. In this example, we use poly2nb() and nb2listw(). These functions respectively detect the neighboring polygons and assign weight corresponding to \\(1/\\#\\ of\\ neighbors\\). Dcluster package provides a set of functions for the detection of spatial clusters of disease using count data.\n\n#install.packages(\"spdep\")\n#install.packages(\"DCluster\")\nlibrary(spdep) # Functions for creating spatial weight, spatial analysis\nlibrary(DCluster) # Package with functions for spatial cluster analysis\n\nset.seed(345) # remove random sampling for reproducibility\n\nqueen_nb <- poly2nb(district) # Neighbors according to queen case\nq_listw <- nb2listw(queen_nb, style = 'W') # row-standardized weights\n\n# Moran's I test\nm_test <- moranI.test(cases ~ offset(log(expected)), \n data = district,\n model = 'poisson',\n R = 499,\n listw = q_listw,\n n = length(district$cases), # number of regions\n S0 = Szero(q_listw)) # Global sum of weights\nprint(m_test)\n\nMoran's I test of spatial autocorrelation \n\n Type of boots.: parametric \n Model used when sampling: Poisson \n Number of simulations: 499 \n Statistic: 0.1566449 \n p-value : 0.006 \n\nplot(m_test)\n\n\n\n\nThe Moran’s statistics is here \\(I =\\) 0.16. When comparing its value to the H0 distribution (built under 499 simulations), the probability of observing such a I value under the null hypothesis, i.e. the distribution of cases is spatially independent, is \\(p_{value} =\\) 0.006. We therefore reject H0 with error risk of \\(\\alpha = 5\\%\\). The distribution of cases is therefore autocorrelated across districts in Cambodia.\n\n\n6.2.2.2 The Local Moran’s I LISA test\nThe global Moran’s test provides us a global statistical value informing whether autocorrelation occurs over the territory but does not inform on where does these correlations occurs, i.e., what is the locations of the clusters. To identify such cluster, we can decompose the Moran’s I statistic to extract local information of the level of correlation of each district and its neighbors. This is called the Local Moran’s I LISA statistic. Because the Local Moran’s I LISA statistic test each district for autocorrelation independently, concern is raised about multiple testing limitations that increase the Type I error (\\(\\alpha\\)) of the statistical tests. The use of local test should therefore be study in light of explore and describes clusters once the global test has detected autocorrelation.\n\n\n\n\n\n\nStatistical test\n\n\n\nFor each district \\(i\\), the Local Moran’s I statistics is:\n\\[I_i = \\frac{(Y_i-\\bar{Y})}{\\sum_{i=1}^N(Y_i-\\bar{Y})^2}\\sum_{j=1}^Nw_{ij}(Y_j - \\bar{Y}) \\text{ with } I = \\sum_{i=1}^NI_i/N\\]\n\n\nThe localmoran()function from the package spdep treats the variable of interest as if it was normally distributed. In some cases, this assumption could be reasonable for incidence rate, especially when the areal units of analysis have sufficiently large population count suggesting that the values have similar level of variances. Unfortunately, the local Moran’s test has not been implemented for Poisson distribution (population not large enough in some districts) in spdep package. However, Bivand et al. (R. S. Bivand et al. 2008) provided some code to manually perform the analysis using Poisson distribution and this code was further implemented in the course “Spatial Epidemiologyâ€.\n\n# Step 1 - Create the standardized deviation of observed from expected\nsd_lm <- (district$cases - district$expected) / sqrt(district$expected)\n\n# Step 2 - Create a spatially lagged version of standardized deviation of neighbors\nwsd_lm <- lag.listw(q_listw, sd_lm)\n\n# Step 3 - the local Moran's I is the product of step 1 and step 2\ndistrict$I_lm <- sd_lm * wsd_lm\n\n# Step 4 - setup parameters for simulation of the null distribution\n\n# Specify number of simulations to run\nnsim <- 499\n\n# Specify dimensions of result based on number of regions\nN <- length(district$expected)\n\n# Create a matrix of zeros to hold results, with a row for each county, and a column for each simulation\nsims <- matrix(0, ncol = nsim, nrow = N)\n\n# Step 5 - Start a for-loop to iterate over simulation columns\nfor(i in 1:nsim){\n y <- rpois(N, lambda = district$expected) # generate a random event count, given expected\n sd_lmi <- (y - district$expected) / sqrt(district$expected) # standardized local measure\n wsd_lmi <- lag.listw(q_listw, sd_lmi) # standardized spatially lagged measure\n sims[, i] <- sd_lmi * wsd_lmi # this is the I(i) statistic under this iteration of null\n}\n\n# Step 6 - For each county, test where the observed value ranks with respect to the null simulations\nxrank <- apply(cbind(district$I_lm, sims), 1, function(x) rank(x)[1])\n\n# Step 7 - Calculate the difference between observed rank and total possible (nsim)\ndiff <- nsim - xrank\ndiff <- ifelse(diff > 0, diff, 0)\n\n# Step 8 - Assuming a uniform distribution of ranks, calculate p-value for observed\n# given the null distribution generate from simulations\ndistrict$pval_lm <- punif((diff + 1) / (nsim + 1))\n\nBriefly, the process consist on 1) computing the I statistics for the observed data, 2) estimating the null distribution of the I statistics by performing random sampling into a poisson distribution and 3) comparing the observed I statistic with the null distribution to determine the probability to observe such value if the number of cases were spatially independent. For each district, we obtain a p-value based on the comparison of the observed value and the null distribution.\nA conventional way of plotting these results is to classify the districts into 5 classes based on local Moran’s I output. The classification of cluster that are significantly autocorrelated to their neighbors is performed based on a comparison of the scaled incidence in the district compared to the scaled weighted averaged incidence of it neighboring districts (computed with lag.listw()):\n\nDistricts that have higher-than-average rates in both index regions and their neighbors and showing statistically significant positive values for the local \\(I_i\\) statistic are defined as High-High (hotspot of the disease)\nDistricts that have lower-than-average rates in both index regions and their neighbors and showing statistically significant positive values for the local \\(I_i\\) statistic are defined as Low-Low (cold spot of the disease).\nDistricts that have higher-than-average rates in the index regions and lower-than-average rates in their neighbors, and showing statistically significant negative values for the local \\(I_i\\) statistic are defined as High-Low(outlier with high incidence in an area with low incidence).\nDistricts that have lower-than-average rates in the index regions and higher-than-average rates in their neighbors, and showing statistically significant negative values for the local \\(I_i\\) statistic are defined as Low-High (outlier of low incidence in area with high incidence).\nDistricts with non-significant values for the \\(I_i\\) statistic are defined as Non-significant.\n\n\n# create lagged local raw_rate - in other words the average of the queen neighbors value\n# values are scaled (centered and reduced) to be compared to average\ndistrict$lag_std <- scale(lag.listw(q_listw, var = district$incidence))\ndistrict$incidence_std <- scale(district$incidence)\n\n# extract pvalues\n# district$lm_pv <- lm_test[,5]\n\n# Classify local moran's outputs\ndistrict$lm_class <- NA\ndistrict$lm_class[district$incidence_std >=0 & district$lag_std >=0] <- 'High-High'\ndistrict$lm_class[district$incidence_std <=0 & district$lag_std <=0] <- 'Low-Low'\ndistrict$lm_class[district$incidence_std <=0 & district$lag_std >=0] <- 'Low-High'\ndistrict$lm_class[district$incidence_std >=0 & district$lag_std <=0] <- 'High-Low'\ndistrict$lm_class[district$pval_lm >= 0.05] <- 'Non-significant'\n\ndistrict$lm_class <- factor(district$lm_class, levels=c(\"High-High\", \"Low-Low\", \"High-Low\", \"Low-High\", \"Non-significant\") )\n\n# create map\nmf_map(x = district,\n var = \"lm_class\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n #val_order = c(\"High-High\", \"Low-Low\", \"High-Low\", \"Low-High\", \"Non-significant\") ,\n pal = c(\"#6D0026\" , \"blue\", \"white\") , # \"#FF755F\",\"#7FABD3\" ,\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using Local Moran's I statistic\")\n\n\n\n\n\n\n\n6.2.3 Spatial scan statistics\nWhile Moran’s indices focus on testing for autocorrelation between neighboring polygons (under the null assumption of spatial independence), the spatial scan statistic aims at identifying an abnormal higher risk in a given region compared to the risk outside of this region (under the null assumption of homogeneous distribution). The conception of a cluster is therefore different between the two methods.\nThe function kulldorff from the package SpatialEpi (Kim and Wakefield 2010) is a simple tool to implement spatial-only scan statistics.\n\n\n\n\n\n\nKulldorf test\n\n\n\nUnder the kulldorff test, the statistics hypotheses are:\n\nH0: the risk is constant over the area, i.e., there is a spatial homogeneity of the incidence.\nH1: a particular window have higher incidence than the rest of the area , i.e., there is a spatial heterogeneity of incidence.\n\n\n\nBriefly, the kulldorff scan statistics scan the area for clusters using several steps:\n\nIt create a circular window of observation by defining a single location and an associated radius of the windows varying from 0 to a large number that depends on population distribution (largest radius could include 50% of the population).\nIt aggregates the count of events and the population at risk (or an expected count of events) inside and outside the window of observation.\nFinally, it computes the likelihood ratio and test whether the risk is equal inside versus outside the windows (H0) or greater inside the observed window (H1). The H0 distribution is estimated by simulating the distribution of counts under the null hypothesis (homogeneous risk).\nThese 3 steps are repeated for each location and each possible windows-radii.\n\nWhile we test the significance of a large number of observation windows, one can raise concern about multiple testing and Type I error. This approach however suggest that we are not interest in a set of signifiant cluster but only in a most-likely cluster. This a priori restriction eliminate concern for multpile comparison since the test is simplified to a statistically significance of one single most-likely cluster.\nBecause we tested all-possible locations and window-radius, we can also choose to look at secondary clusters. In this case, you should keep in mind that increasing the number of secondary cluster you select, increases the risk for Type I error.\n\n#install.packages(\"SpatialEpi\")\nlibrary(\"SpatialEpi\")\n\nThe use of R spatial object is not implements in kulldorff() function. It uses instead matrix of xy coordinates that represents the centroids of the districts. A given district is included into the observed circular window if its centroids fall into the circle.\n\ndistrict_xy <- st_centroid(district) %>% \n st_coordinates()\n\nhead(district_xy)\n\n X Y\n1 330823.3 1464560\n2 749758.3 1541787\n3 468384.0 1277007\n4 494548.2 1215261\n5 459644.2 1194615\n6 360528.3 1516339\n\n\nWe can then call kulldorff function (you are strongly encouraged to call ?kulldorff to properly call the function). The alpha.level threshold filter for the secondary clusters that will be retained. The most-likely cluster will be saved whatever its significance.\n\nkd_Wfever <- kulldorff(district_xy, \n cases = district$cases,\n population = district$T_POP,\n expected.cases = district$expected,\n pop.upper.bound = 0.5, # include maximum 50% of the population in a windows\n n.simulations = 499,\n alpha.level = 0.2)\n\n\n\n\nThe function plot the histogram of the distribution of log-likelihood ratio simulated under the null hypothesis that is estimated based on Monte Carlo simulations. The observed value of the most significant cluster identified from all possible scans is compared to the distribution to determine significance. All outputs are saved into an R object, here called kd_Wfever. Unfortunately, the package did not develop any summary and visualization of the results but we can explore the output object.\n\nnames(kd_Wfever)\n\n[1] \"most.likely.cluster\" \"secondary.clusters\" \"type\" \n[4] \"log.lkhd\" \"simulated.log.lkhd\" \n\n\nFirst, we can focus on the most likely cluster and explore its characteristics.\n\n# We can see which districts (r number) belong to this cluster\nkd_Wfever$most.likely.cluster$location.IDs.included\n\n [1] 48 93 66 180 133 29 194 118 50 144 31 141 3 117 22 43 142\n\n# standardized incidence ratio\nkd_Wfever$most.likely.cluster$SMR\n\n[1] 2.303106\n\n# number of observed and expected cases in this cluster\nkd_Wfever$most.likely.cluster$number.of.cases\n\n[1] 122\n\nkd_Wfever$most.likely.cluster$expected.cases\n\n[1] 52.97195\n\n\n17 districts belong to the cluster and its number of cases is 2.3 times higher than the expected number of cases.\nSimilarly, we could study the secondary clusters. Results are saved in a list.\n\n# We can see which districts (r number) belong to this cluster\nlength(kd_Wfever$secondary.clusters)\n\n[1] 1\n\n# retrieve data for all secondary clusters into a table\ndf_secondary_clusters <- data.frame(SMR = sapply(kd_Wfever$secondary.clusters, '[[', 5), \n number.of.cases = sapply(kd_Wfever$secondary.clusters, '[[', 3),\n expected.cases = sapply(kd_Wfever$secondary.clusters, '[[', 4),\n p.value = sapply(kd_Wfever$secondary.clusters, '[[', 8))\n\nprint(df_secondary_clusters)\n\n SMR number.of.cases expected.cases p.value\n1 3.767698 16 4.246625 0.008\n\n\nWe only have one secondary cluster composed of one district.\n\n# create empty column to store cluster informations\ndistrict$k_cluster <- NA\n\n# save cluster information from kulldorff outputs\ndistrict$k_cluster[kd_Wfever$most.likely.cluster$location.IDs.included] <- 'Most likely cluster'\n\nfor(i in 1:length(kd_Wfever$secondary.clusters)){\ndistrict$k_cluster[kd_Wfever$secondary.clusters[[i]]$location.IDs.included] <- paste(\n 'Secondary cluster', i, sep = '')\n}\n\n#district$k_cluster[is.na(district$k_cluster)] <- \"No cluster\"\n\n\n# create map\nmf_map(x = district,\n var = \"k_cluster\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n pal = mf_get_pal(palette = \"Reds\", n = 3)[1:2],\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using kulldorf scan statistic\")\n\n\n\n\n\n\n\n\n\n\nTo go further …\n\n\n\nIn this example, the expected number of cases was defined using the population count but note that standardization over other variables as age could also be implemented with the strata parameter in the kulldorff() function.\nIn addition, this cluster analysis was performed solely using the spatial scan but you should keep in mind that this method of cluster detection can be implemented for spatio-temporal data as well where the cluster definition is an abnormal number of cases in a delimited spatial area and during a given period of time. The windows of observation are therefore defined for a different center, radius and time-period. You should take a look at the function scan_ep_poisson() function in the package scanstatistic (Allévius 2018) for this analysis."
},
{
"objectID": "01-introduction.html",
@@ -249,6 +249,6 @@
"href": "07-basic_statistics.html#conclusion",
"title": "6Â Basic statistics for spatial analysis",
"section": "6.3 Conclusion",
- "text": "6.3 Conclusion\n\npar(mfrow = c(1, 2))\n\n# create map\nmf_map(x = district,\n var = \"lm_class\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n pal = c(\"#6D0026\" , \"blue\", \"white\") , # \"#FF755F\",\"#7FABD3\" ,\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using Local Moran's I statistic\")\n\n# create map\nmf_map(x = district,\n var = \"k_cluster\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n pal = mf_get_pal(palette = \"Reds\", n = 3)[1:2],\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using kulldorf scan statistic\")\n\n\n\n\nBoth methods identified significant clusters. The two methods could identify a cluster around Phnom Penh after standardization for population counts. However, the identified clusters does not rely on the same assumption. While the Moran’s test wonder whether their is any autocorrelation between clusters (i.e. second order effects of infection), the Kulldorff scan statistics wonder whether their is any heterogeneity in the case distribution. None of these test can inform on the infection processes (first or second order) for the studied disease and previous knowledge on the disease will help selecting the most accurate test.\n\n\n\n\nAllévius, Benjamin. 2018. “Scanstatistics: Space-Time Anomaly Detection Using Scan Statistics.†Journal of Open Source Software 3 (25): 515.\n\n\nBivand, Roger S, Edzer J Pebesma, Virgilio Gómez-Rubio, and Edzer Jan Pebesma. 2008. Applied Spatial Data Analysis with r. Vol. 747248717. Springer.\n\n\nBivand, Roger, Micah Altman, Luc Anselin, Renato Assunção, Olaf Berke, Andrew Bernat, and Guillaume Blanchet. 2015. “Package ‘Spdep’.†The Comprehensive R Archive Network.\n\n\nGómez-Rubio, Virgilio, Juan Ferrándiz-Ferragud, Antonio López-QuıÌlez, et al. 2015. “Package ‘DCluster’.â€\n\n\nKim, Albert Y, and Jon Wakefield. 2010. “R Data and Methods for Spatial Epidemiology: The SpatialEpi Package.†Dept of Statistics, University of Washington."
+ "text": "6.3 Conclusion\n\npar(mfrow = c(1, 2))\n\n# create map\nmf_map(x = district,\n var = \"lm_class\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n pal = c(\"#6D0026\" , \"blue\", \"white\") , # \"#FF755F\",\"#7FABD3\" ,\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using Local Moran's I statistic\")\n\n# create map\nmf_map(x = district,\n var = \"k_cluster\",\n type = \"typo\",\n cex = 2,\n col_na = \"white\",\n pal = mf_get_pal(palette = \"Reds\", n = 3)[1:2],\n leg_title = \"Clusters\")\n\nmf_layout(title = \"Cluster using kulldorf scan statistic\")\n\n\n\n\nBoth methods identified significant clusters. The two methods could identify a cluster around Phnom Penh after standardization for population counts. However, the identified clusters does not rely on the same assumption. While the Moran’s test wonder whether their is any autocorrelation between clusters (i.e. second order effects of infection), the Kulldorff scan statistics wonder whether their is any heterogeneity in the case distribution. None of these test can inform on the infection processes (first or second order) for the studied disease and previous knowledge on the disease will help selecting the most accurate test.\n\n\n\n\n\n\nTip\n\n\n\nIn this example, Cambodia is treated as an island, i.e. there is no data outside of its borders. In reality, some clusters can occurs across country’s borders. You should be aware that such district will likely not be detected by these analysis. This border effect is still a hot topic in spatial studies and there is no conventional ways to deal with it. You can find in the literature some suggestion on how to deals with these border effect as assigning weights, or extrapolating data.\n\n\n\n\n\n\nAllévius, Benjamin. 2018. “Scanstatistics: Space-Time Anomaly Detection Using Scan Statistics.†Journal of Open Source Software 3 (25): 515.\n\n\nBivand, Roger S, Edzer J Pebesma, Virgilio Gómez-Rubio, and Edzer Jan Pebesma. 2008. Applied Spatial Data Analysis with r. Vol. 747248717. Springer.\n\n\nBivand, Roger, Micah Altman, Luc Anselin, Renato Assunção, Olaf Berke, Andrew Bernat, and Guillaume Blanchet. 2015. “Package ‘Spdep’.†The Comprehensive R Archive Network.\n\n\nGómez-Rubio, Virgilio, Juan Ferrándiz-Ferragud, Antonio López-QuıÌlez, et al. 2015. “Package ‘DCluster’.â€\n\n\nKim, Albert Y, and Jon Wakefield. 2010. “R Data and Methods for Spatial Epidemiology: The SpatialEpi Package.†Dept of Statistics, University of Washington."
}
]
\ No newline at end of file
--
GitLab