diff --git a/html_outputs/new_pages/ggplot_tips.html b/html_outputs/new_pages/ggplot_tips.html
index f97d62f4..54208990 100644
--- a/html_outputs/new_pages/ggplot_tips.html
+++ b/html_outputs/new_pages/ggplot_tips.html
@@ -848,8 +848,8 @@ <h3 class="unnumbered anchored" data-anchor-id="import-data">Import data</h3>
 <p>The first 50 rows of the linelist are displayed below.</p>
 <div class="cell">
 <div class="cell-output-display">
-<div class="datatables html-widget html-fill-item" id="htmlwidget-ff7f77ca063b6f3d6f02" style="width:100%;height:auto;"></div>
-<script type="application/json" data-for="htmlwidget-ff7f77ca063b6f3d6f02">{"x":{"filter":"top","vertical":false,"filterHTML":"<tr>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"2\" data-max=\"13\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1399075200000\" data-max=\"1406419200000\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1399939200000\" data-max=\"1.407024e+12\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1400025600000\" data-max=\"1407110400000\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1400371200000\" data-max=\"1410566400000\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"67\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\" disabled=\"\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"67\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"factor\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"width: 100%; display: none;\">\n      <select multiple=\"multiple\" style=\"width: 100%;\" data-options=\"[&quot;0-4&quot;,&quot;5-9&quot;,&quot;10-14&quot;,&quot;15-19&quot;,&quot;20-29&quot;,&quot;30-49&quot;,&quot;50-69&quot;,&quot;70+&quot;]\"><\/select>\n    <\/div>\n  <\/td>\n  <td data-type=\"factor\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"width: 100%; display: none;\">\n      <select multiple=\"multiple\" style=\"width: 100%;\" data-options=\"[&quot;0-4&quot;,&quot;5-9&quot;,&quot;10-14&quot;,&quot;15-19&quot;,&quot;20-24&quot;,&quot;25-29&quot;,&quot;30-34&quot;,&quot;35-39&quot;,&quot;40-44&quot;,&quot;45-49&quot;,&quot;50-54&quot;,&quot;55-59&quot;,&quot;60-64&quot;,&quot;65-69&quot;,&quot;70-74&quot;,&quot;75-79&quot;,&quot;80-84&quot;,&quot;85+&quot;]\"><\/select>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"-13.2697246824573\" data-max=\"-13.209391925612\" data-scale=\"13\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"8.45171855856465\" data-max=\"8.48802917129884\" data-scale=\"14\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"100\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"11\" data-max=\"241\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"20\" data-max=\"24\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"35.9\" data-max=\"38\" data-scale=\"1\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"428.994082840237\" data-scale=\"14\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"2\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n<\/tr>","data":[["5fe599","8689b7","11f8ea","b8812a","893f25","be99c8","07e3e8","369449","f393b4","1389ca","2978ac","57a565","fc15ef","2eaa9a","bbfa93","c97dd9","f50e8a","3a7673","7f5a01","ddddee","99e8fa","567136","9371a9","bc2adf","403057","8bd1e8","f327be","42e1a9","90e5fe","959170","8ebf6e","e56412","6d788e","a47529","67be4e","da8ecb","148f18","2cb9a5","f5c142","70a9fe","3ad520","062638","c76676","baacc1","497372","23e499","38cc4a","3789ee","c71dcd","6b70f0"],[4,4,2,3,3,3,4,4,4,4,4,4,6,5,6,9,10,8,7,6,7,6,8,6,10,8,6,12,5,8,7,9,11,5,8,5,6,11,7,9,7,8,9,12,13,9,8,10,8,7],["2014-05-08",null,null,"2014-05-04","2014-05-18","2014-05-03","2014-05-22","2014-05-28",null,null,"2014-05-30","2014-05-28","2014-06-14","2014-06-07","2014-06-09",null,null,null,"2014-06-23","2014-06-18","2014-06-24",null,null,"2014-07-03",null,"2014-07-10","2014-06-14",null,"2014-06-18","2014-06-29","2014-07-02","2014-07-12","2014-07-12","2014-06-13","2014-07-15","2014-06-20",null,null,"2014-07-20",null,"2014-07-12","2014-07-19","2014-07-18","2014-07-18","2014-07-27",null,"2014-07-19","2014-07-26","2014-07-24",null],["2014-05-13","2014-05-13","2014-05-16","2014-05-18","2014-05-21","2014-05-22","2014-05-27","2014-06-02","2014-06-05","2014-06-05","2014-06-06","2014-06-13","2014-06-16","2014-06-17","2014-06-18","2014-06-19","2014-06-22","2014-06-23","2014-06-25","2014-06-26","2014-06-28","2014-07-02","2014-07-08","2014-07-09","2014-07-09","2014-07-10","2014-07-12","2014-07-12","2014-07-13","2014-07-13","2014-07-14","2014-07-15","2014-07-16","2014-07-17","2014-07-17","2014-07-18","2014-07-19","2014-07-22","2014-07-22","2014-07-24","2014-07-24","2014-07-25","2014-07-25","2014-07-27","2014-07-29","2014-07-30",null,"2014-08-01","2014-08-02","2014-08-03"],["2014-05-15","2014-05-14","2014-05-18","2014-05-20","2014-05-22","2014-05-23","2014-05-29","2014-06-03","2014-06-06","2014-06-07","2014-06-08","2014-06-15","2014-06-17","2014-06-17","2014-06-20","2014-06-19","2014-06-23","2014-06-24","2014-06-27","2014-06-28","2014-06-29","2014-07-03","2014-07-09","2014-07-09","2014-07-11","2014-07-11","2014-07-13","2014-07-14","2014-07-14","2014-07-13","2014-07-14","2014-07-17","2014-07-17","2014-07-18","2014-07-19","2014-07-20","2014-07-20","2014-07-22","2014-07-24","2014-07-26","2014-07-24","2014-07-27","2014-07-25","2014-07-27","2014-07-31","2014-08-01","2014-08-03","2014-08-02","2014-08-02","2014-08-04"],[null,"2014-05-18","2014-05-30",null,"2014-05-29","2014-05-24","2014-06-01","2014-06-07","2014-06-18","2014-06-09","2014-06-15",null,"2014-07-09",null,"2014-06-30","2014-07-11","2014-07-01","2014-06-25","2014-07-06","2014-07-02","2014-07-09","2014-07-07","2014-07-20",null,"2014-07-22","2014-07-16","2014-07-14","2014-07-20","2014-07-16","2014-07-19","2014-07-27","2014-07-19",null,"2014-07-26","2014-08-14","2014-08-01","2014-07-23","2014-08-28","2014-07-28","2014-07-19",null,"2014-08-03",null,null,null,"2014-08-06","2014-08-21","2014-09-13","2014-08-04",null],[null,"Recover","Recover",null,"Recover","Recover","Recover","Death","Recover","Death","Death","Death","Recover","Recover",null,"Recover",null,null,"Death","Death","Recover",null,null,null,"Death",null,"Death","Death",null,"Death","Recover","Death","Recover","Death","Recover",null,"Death","Recover","Recover","Death",null,null,"Death","Death","Death","Death","Recover",null,"Death","Death"],["m","f","m","f","m","f","f","f","m","f","m","m","m","f","f","m","f","f","f","f","m","m","f","m","f","m","m","f","m","f","f","f","m","m","f","m","f","f","f","m","f","m","f","m","m","f","m","f","m","m"],[2,3,56,18,3,16,16,0,61,27,12,42,19,7,7,13,35,17,11,11,19,54,14,28,6,3,31,6,67,14,10,21,20,45,1,12,3,15,20,36,7,13,14,3,10,1,0,20,26,14],["years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years"],[2,3,56,18,3,16,16,0,61,27,12,42,19,7,7,13,35,17,11,11,19,54,14,28,6,3,31,6,67,14,10,21,20,45,1,12,3,15,20,36,7,13,14,3,10,1,0,20,26,14],["0-4","0-4","50-69","15-19","0-4","15-19","15-19","0-4","50-69","20-29","10-14","30-49","15-19","5-9","5-9","10-14","30-49","15-19","10-14","10-14","15-19","50-69","10-14","20-29","5-9","0-4","30-49","5-9","50-69","10-14","10-14","20-29","20-29","30-49","0-4","10-14","0-4","15-19","20-29","30-49","5-9","10-14","10-14","0-4","10-14","0-4","0-4","20-29","20-29","10-14"],["0-4","0-4","55-59","15-19","0-4","15-19","15-19","0-4","60-64","25-29","10-14","40-44","15-19","5-9","5-9","10-14","35-39","15-19","10-14","10-14","15-19","50-54","10-14","25-29","5-9","0-4","30-34","5-9","65-69","10-14","10-14","20-24","20-24","45-49","0-4","10-14","0-4","15-19","20-24","35-39","5-9","10-14","10-14","0-4","10-14","0-4","0-4","20-24","25-29","10-14"],["Other","Missing","St. Mark's Maternity Hospital (SMMH)","Port Hospital","Military Hospital","Port Hospital","Missing","Missing","Missing","Missing","Port Hospital","Military Hospital","Missing","Missing","Other","Port Hospital","Port Hospital","Port Hospital","Missing","Other","Port Hospital","Port Hospital","St. Mark's Maternity Hospital (SMMH)","Missing","Other","Missing","St. Mark's Maternity Hospital (SMMH)","Military Hospital","Port Hospital","Central Hospital","Military Hospital","Central Hospital","Missing","Military Hospital","Other","Missing","Missing","Port Hospital","Port Hospital","Port Hospital","Missing","Central Hospital","Military Hospital","Other","Other","Other","Missing","St. Mark's Maternity Hospital (SMMH)","St. Mark's Maternity Hospital (SMMH)","Missing"],[-13.2157351064963,-13.2152339775486,-13.212910703914,-13.2363711169728,-13.2228638912441,-13.222625321098,-13.2331547837254,-13.2320975453153,-13.2225511595637,-13.2572163655863,-13.2206286746001,-13.253989309478,-13.2385127873491,-13.209391925612,-13.2157278814899,-13.2243437095992,-13.2336087079551,-13.21422143145,-13.2339681355349,-13.2535640411465,-13.2250089377786,-13.2160657166043,-13.2680671272333,-13.2266742923612,-13.2160179088168,-13.2482584611565,-13.2156319199566,-13.2142410663192,-13.2614879104088,-13.2452992638476,-13.2630592726116,-13.2343341712241,-13.2199077448676,-13.2227293309912,-13.2343062806506,-13.218781651651,-13.2483677722899,-13.2097478342339,-13.2680867723786,-13.2587535457526,-13.262635786914,-13.2697246824573,-13.2209026809759,-13.2330734719715,-13.2680923666905,-13.2547212675054,-13.2573683214693,-13.2137356012883,-13.2175973322257,-13.2486407324245],[8.46897295100924,8.45171855856465,8.46481700596819,8.4754761613651,8.46082377490923,8.461830626007281,8.462729314626459,8.461443675342711,8.46191259217774,8.472923276435059,8.48401630165138,8.458371253408441,8.477617055125091,8.47570184950483,8.477799468789719,8.47145134147474,8.478048406853629,8.48528034195779,8.469575303958671,8.45957352078114,8.474048895115439,8.488029171298839,8.473437335922,8.484082637344621,8.46242233645879,8.470268221265719,8.463984474805329,8.464134789434199,8.456230946296071,8.48334624336805,8.47493999153642,8.47832062438022,8.469393389176499,8.48480589906514,8.47121232619015,8.48438437371817,8.484661585743391,8.477141599844281,8.462381270106089,8.455685978131131,8.4632880274758,8.47940722413856,8.46353857052336,8.461789681588639,8.47508713872833,8.458258081280711,8.4532568143863,8.4732571907655,8.479115866419329,8.48480340615605],["f547d6",null,null,"f90f5f","11f8ea","aec8ec","893f25","133ee7",null,null,"996f3a","133ee7","37a6f6","9f6884","4802b1",null,null,null,"a75c7f","8e104d","ab634e",null,null,"b799eb",null,"5d9e4d","a15e13",null,"ea3740","beb26e","567136","894024","36e2e7","a2086d","7baf73","eb2277",null,null,"d6584f",null,"312ecf","52ea64","cfd79c","d145b7","174288",null,"53608c","3b096b","f5c142",null],["other",null,null,"other","other","other","other","other",null,null,"other","other","other","other","other",null,null,null,"other","other","other",null,null,"other",null,"other","other",null,"other","funeral","other","funeral","other","other","other","funeral",null,null,"other",null,"other","other","other","other","other",null,"funeral","other","other",null],[27,25,91,41,36,56,47,0,86,69,67,84,68,44,34,66,78,47,53,47,71,86,53,69,38,46,68,37,100,56,50,57,65,72,29,69,37,48,54,71,47,61,47,35,53,16,13,59,69,67],[48,59,238,135,71,116,87,11,226,174,112,186,174,90,91,152,214,137,117,131,150,241,131,161,80,69,188,66,233,142,110,182,164,214,26,157,39,154,133,168,100,125,123,67,134,31,36,125,183,169],[22,22,21,23,23,21,21,22,22,22,22,22,22,21,23,22,23,21,22,23,21,23,21,24,23,22,24,23,20,24,24,20,24,21,22,21,23,22,23,23,23,22,23,22,22,22,23,22,22,22],["no",null,null,"no","no","no",null,"no","no","no","no","no","no","no","no","no","no","no",null,"no","no","no","no","no",null,"no","no","no",null,null,"no","no",null,"no","no",null,null,"no","no",null,"no","no",null,"no","no","no","no","no","no",null],["no",null,null,"no","no","no",null,"no","no","no","no","no","no","no","no","no","yes","no",null,"no","no","no","yes","no",null,"no","no","yes",null,null,"no","no",null,"no","no",null,null,"no","no",null,"no","no",null,"no","yes","no","no","no","no",null],["yes",null,null,"no","yes","yes",null,"yes","yes","yes","yes","yes","yes","yes","yes","yes","yes","yes",null,"yes","yes","yes","yes","yes",null,"yes","yes","yes",null,null,"yes","yes",null,"yes","yes",null,null,"yes","yes",null,"yes","yes",null,"yes","yes","yes","yes","yes","no",null],["no",null,null,"no","no","no",null,"no","no","no","no","no","no","no","no","yes","no","no",null,"no","no","no","no","no",null,"no","no","no",null,null,"no","no",null,"no","no",null,null,"yes","yes",null,"no","no",null,"no","no","no","no","no","no",null],["yes",null,null,"no","yes","yes",null,"yes","yes","no","yes","no","no","no","yes","no","no","no",null,"no","yes","no","no","no",null,"no","no","no",null,null,"no","yes",null,"yes","yes",null,null,"yes","yes",null,"yes","yes",null,"yes","yes","no","yes","yes","yes",null],[36.8,36.9,36.9,36.8,36.9,37.6,37.3,37,36.4,35.9,36.5,36.9,36.5,37.1,36.5,37.3,37,38,38,36,37,36.7,36.9,36.5,37,36.5,37.6,36.6,36.6,36.2,36.4,37.1,37.5,37.5,37.4,36.9,36.4,37.3,37,37.8,36.5,37.5,36.7,37,37.3,36.6,36.5,36.6,37.6,36.8],[null,"09:36","16:48","11:22","12:60","14:13","14:33","09:25","11:16","10:55","16:03","11:14","12:42","11:06","09:10","08:45",null,"15:41","13:34","18:58","12:43","16:33","14:29","07:18","08:11","16:32","16:17","07:32","17:45",null,"13:24","14:43","02:33","11:36","17:28","16:27",null,"20:49",null,"11:38","14:25","13:42","21:22","13:33","19:06","17:14","20:09",null,"10:23","09:09"],[117.1875,71.81844297615629,16.06524962926347,22.49657064471879,71.41440190438405,41.61712247324614,62.09538908706566,0,16.83765369253662,22.79032897344431,53.41198979591836,24.28026361429067,22.46003435064077,54.32098765432099,41.05784325564545,28.56648199445983,17.03205520132763,25.04129149128882,38.7172182043977,27.3876813705495,31.55555555555556,14.80690759456621,30.88398111998135,26.61934338952972,59.37499999999999,96.61835748792272,19.23947487550928,84.94031221303948,18.41993774061044,27.77226740726046,41.32231404958677,17.20806665861611,24.16716240333135,15.72189710891781,428.9940828402366,27.99302202929125,243.2610124917817,20.23950075898128,30.52744643563797,25.15589569160998,47,39.04,31.06616432017979,77.96836711962574,29.51659612385831,166.4932362122789,100.3086419753086,37.76,20.60378034578518,23.45856237526698],[2,1,2,2,1,1,2,1,1,2,2,2,1,0,2,0,1,1,2,2,1,1,1,0,2,1,1,2,1,0,0,2,1,1,2,2,1,0,2,2,0,2,0,0,2,2,null,1,0,1]],"container":"<table class=\"white-space: nowrap\">\n  <thead>\n    <tr>\n      <th>case_id<\/th>\n      <th>generation<\/th>\n      <th>date_infection<\/th>\n      <th>date_onset<\/th>\n      <th>date_hospitalisation<\/th>\n      <th>date_outcome<\/th>\n      <th>outcome<\/th>\n      <th>gender<\/th>\n      <th>age<\/th>\n      <th>age_unit<\/th>\n      <th>age_years<\/th>\n      <th>age_cat<\/th>\n      <th>age_cat5<\/th>\n      <th>hospital<\/th>\n      <th>lon<\/th>\n      <th>lat<\/th>\n      <th>infector<\/th>\n      <th>source<\/th>\n      <th>wt_kg<\/th>\n      <th>ht_cm<\/th>\n      <th>ct_blood<\/th>\n      <th>fever<\/th>\n      <th>chills<\/th>\n      <th>cough<\/th>\n      <th>aches<\/th>\n      <th>vomit<\/th>\n      <th>temp<\/th>\n      <th>time_admission<\/th>\n      <th>bmi<\/th>\n      <th>days_onset_hosp<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":5,"scrollX":true,"columnDefs":[{"className":"dt-right","targets":[1,8,10,14,15,18,19,20,26,28,29]},{"name":"case_id","targets":0},{"name":"generation","targets":1},{"name":"date_infection","targets":2},{"name":"date_onset","targets":3},{"name":"date_hospitalisation","targets":4},{"name":"date_outcome","targets":5},{"name":"outcome","targets":6},{"name":"gender","targets":7},{"name":"age","targets":8},{"name":"age_unit","targets":9},{"name":"age_years","targets":10},{"name":"age_cat","targets":11},{"name":"age_cat5","targets":12},{"name":"hospital","targets":13},{"name":"lon","targets":14},{"name":"lat","targets":15},{"name":"infector","targets":16},{"name":"source","targets":17},{"name":"wt_kg","targets":18},{"name":"ht_cm","targets":19},{"name":"ct_blood","targets":20},{"name":"fever","targets":21},{"name":"chills","targets":22},{"name":"cough","targets":23},{"name":"aches","targets":24},{"name":"vomit","targets":25},{"name":"temp","targets":26},{"name":"time_admission","targets":27},{"name":"bmi","targets":28},{"name":"days_onset_hosp","targets":29}],"order":[],"autoWidth":false,"orderClasses":false,"orderCellsTop":true,"lengthMenu":[5,10,25,50,100]}},"evals":[],"jsHooks":[]}</script>
+<div class="datatables html-widget html-fill-item" id="htmlwidget-6b04cb4d9780ecc0121f" style="width:100%;height:auto;"></div>
+<script type="application/json" data-for="htmlwidget-6b04cb4d9780ecc0121f">{"x":{"filter":"top","vertical":false,"filterHTML":"<tr>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"2\" data-max=\"13\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1399075200000\" data-max=\"1406419200000\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1399939200000\" data-max=\"1.407024e+12\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1400025600000\" data-max=\"1407110400000\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"date\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"1400371200000\" data-max=\"1410566400000\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"67\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\" disabled=\"\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"67\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"factor\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"width: 100%; display: none;\">\n      <select multiple=\"multiple\" style=\"width: 100%;\" data-options=\"[&quot;0-4&quot;,&quot;5-9&quot;,&quot;10-14&quot;,&quot;15-19&quot;,&quot;20-29&quot;,&quot;30-49&quot;,&quot;50-69&quot;,&quot;70+&quot;]\"><\/select>\n    <\/div>\n  <\/td>\n  <td data-type=\"factor\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"width: 100%; display: none;\">\n      <select multiple=\"multiple\" style=\"width: 100%;\" data-options=\"[&quot;0-4&quot;,&quot;5-9&quot;,&quot;10-14&quot;,&quot;15-19&quot;,&quot;20-24&quot;,&quot;25-29&quot;,&quot;30-34&quot;,&quot;35-39&quot;,&quot;40-44&quot;,&quot;45-49&quot;,&quot;50-54&quot;,&quot;55-59&quot;,&quot;60-64&quot;,&quot;65-69&quot;,&quot;70-74&quot;,&quot;75-79&quot;,&quot;80-84&quot;,&quot;85+&quot;]\"><\/select>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"-13.2697246824573\" data-max=\"-13.209391925612\" data-scale=\"13\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"8.45171855856465\" data-max=\"8.48802917129884\" data-scale=\"14\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"100\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"11\" data-max=\"241\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"20\" data-max=\"24\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"35.9\" data-max=\"38\" data-scale=\"1\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"428.994082840237\" data-scale=\"14\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"number\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"display: none;position: absolute;width: 200px;opacity: 1\">\n      <div data-min=\"0\" data-max=\"2\"><\/div>\n      <span style=\"float: left;\"><\/span>\n      <span style=\"float: right;\"><\/span>\n    <\/div>\n  <\/td>\n<\/tr>","data":[["5fe599","8689b7","11f8ea","b8812a","893f25","be99c8","07e3e8","369449","f393b4","1389ca","2978ac","57a565","fc15ef","2eaa9a","bbfa93","c97dd9","f50e8a","3a7673","7f5a01","ddddee","99e8fa","567136","9371a9","bc2adf","403057","8bd1e8","f327be","42e1a9","90e5fe","959170","8ebf6e","e56412","6d788e","a47529","67be4e","da8ecb","148f18","2cb9a5","f5c142","70a9fe","3ad520","062638","c76676","baacc1","497372","23e499","38cc4a","3789ee","c71dcd","6b70f0"],[4,4,2,3,3,3,4,4,4,4,4,4,6,5,6,9,10,8,7,6,7,6,8,6,10,8,6,12,5,8,7,9,11,5,8,5,6,11,7,9,7,8,9,12,13,9,8,10,8,7],["2014-05-08",null,null,"2014-05-04","2014-05-18","2014-05-03","2014-05-22","2014-05-28",null,null,"2014-05-30","2014-05-28","2014-06-14","2014-06-07","2014-06-09",null,null,null,"2014-06-23","2014-06-18","2014-06-24",null,null,"2014-07-03",null,"2014-07-10","2014-06-14",null,"2014-06-18","2014-06-29","2014-07-02","2014-07-12","2014-07-12","2014-06-13","2014-07-15","2014-06-20",null,null,"2014-07-20",null,"2014-07-12","2014-07-19","2014-07-18","2014-07-18","2014-07-27",null,"2014-07-19","2014-07-26","2014-07-24",null],["2014-05-13","2014-05-13","2014-05-16","2014-05-18","2014-05-21","2014-05-22","2014-05-27","2014-06-02","2014-06-05","2014-06-05","2014-06-06","2014-06-13","2014-06-16","2014-06-17","2014-06-18","2014-06-19","2014-06-22","2014-06-23","2014-06-25","2014-06-26","2014-06-28","2014-07-02","2014-07-08","2014-07-09","2014-07-09","2014-07-10","2014-07-12","2014-07-12","2014-07-13","2014-07-13","2014-07-14","2014-07-15","2014-07-16","2014-07-17","2014-07-17","2014-07-18","2014-07-19","2014-07-22","2014-07-22","2014-07-24","2014-07-24","2014-07-25","2014-07-25","2014-07-27","2014-07-29","2014-07-30",null,"2014-08-01","2014-08-02","2014-08-03"],["2014-05-15","2014-05-14","2014-05-18","2014-05-20","2014-05-22","2014-05-23","2014-05-29","2014-06-03","2014-06-06","2014-06-07","2014-06-08","2014-06-15","2014-06-17","2014-06-17","2014-06-20","2014-06-19","2014-06-23","2014-06-24","2014-06-27","2014-06-28","2014-06-29","2014-07-03","2014-07-09","2014-07-09","2014-07-11","2014-07-11","2014-07-13","2014-07-14","2014-07-14","2014-07-13","2014-07-14","2014-07-17","2014-07-17","2014-07-18","2014-07-19","2014-07-20","2014-07-20","2014-07-22","2014-07-24","2014-07-26","2014-07-24","2014-07-27","2014-07-25","2014-07-27","2014-07-31","2014-08-01","2014-08-03","2014-08-02","2014-08-02","2014-08-04"],[null,"2014-05-18","2014-05-30",null,"2014-05-29","2014-05-24","2014-06-01","2014-06-07","2014-06-18","2014-06-09","2014-06-15",null,"2014-07-09",null,"2014-06-30","2014-07-11","2014-07-01","2014-06-25","2014-07-06","2014-07-02","2014-07-09","2014-07-07","2014-07-20",null,"2014-07-22","2014-07-16","2014-07-14","2014-07-20","2014-07-16","2014-07-19","2014-07-27","2014-07-19",null,"2014-07-26","2014-08-14","2014-08-01","2014-07-23","2014-08-28","2014-07-28","2014-07-19",null,"2014-08-03",null,null,null,"2014-08-06","2014-08-21","2014-09-13","2014-08-04",null],[null,"Recover","Recover",null,"Recover","Recover","Recover","Death","Recover","Death","Death","Death","Recover","Recover",null,"Recover",null,null,"Death","Death","Recover",null,null,null,"Death",null,"Death","Death",null,"Death","Recover","Death","Recover","Death","Recover",null,"Death","Recover","Recover","Death",null,null,"Death","Death","Death","Death","Recover",null,"Death","Death"],["m","f","m","f","m","f","f","f","m","f","m","m","m","f","f","m","f","f","f","f","m","m","f","m","f","m","m","f","m","f","f","f","m","m","f","m","f","f","f","m","f","m","f","m","m","f","m","f","m","m"],[2,3,56,18,3,16,16,0,61,27,12,42,19,7,7,13,35,17,11,11,19,54,14,28,6,3,31,6,67,14,10,21,20,45,1,12,3,15,20,36,7,13,14,3,10,1,0,20,26,14],["years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years","years"],[2,3,56,18,3,16,16,0,61,27,12,42,19,7,7,13,35,17,11,11,19,54,14,28,6,3,31,6,67,14,10,21,20,45,1,12,3,15,20,36,7,13,14,3,10,1,0,20,26,14],["0-4","0-4","50-69","15-19","0-4","15-19","15-19","0-4","50-69","20-29","10-14","30-49","15-19","5-9","5-9","10-14","30-49","15-19","10-14","10-14","15-19","50-69","10-14","20-29","5-9","0-4","30-49","5-9","50-69","10-14","10-14","20-29","20-29","30-49","0-4","10-14","0-4","15-19","20-29","30-49","5-9","10-14","10-14","0-4","10-14","0-4","0-4","20-29","20-29","10-14"],["0-4","0-4","55-59","15-19","0-4","15-19","15-19","0-4","60-64","25-29","10-14","40-44","15-19","5-9","5-9","10-14","35-39","15-19","10-14","10-14","15-19","50-54","10-14","25-29","5-9","0-4","30-34","5-9","65-69","10-14","10-14","20-24","20-24","45-49","0-4","10-14","0-4","15-19","20-24","35-39","5-9","10-14","10-14","0-4","10-14","0-4","0-4","20-24","25-29","10-14"],["Other","Missing","St. Mark's Maternity Hospital (SMMH)","Port Hospital","Military Hospital","Port Hospital","Missing","Missing","Missing","Missing","Port Hospital","Military Hospital","Missing","Missing","Other","Port Hospital","Port Hospital","Port Hospital","Missing","Other","Port Hospital","Port Hospital","St. Mark's Maternity Hospital (SMMH)","Missing","Other","Missing","St. Mark's Maternity Hospital (SMMH)","Military Hospital","Port Hospital","Central Hospital","Military Hospital","Central Hospital","Missing","Military Hospital","Other","Missing","Missing","Port Hospital","Port Hospital","Port Hospital","Missing","Central Hospital","Military Hospital","Other","Other","Other","Missing","St. Mark's Maternity Hospital (SMMH)","St. Mark's Maternity Hospital (SMMH)","Missing"],[-13.2157351064963,-13.2152339775486,-13.212910703914,-13.2363711169728,-13.2228638912441,-13.222625321098,-13.2331547837254,-13.2320975453153,-13.2225511595637,-13.2572163655863,-13.2206286746001,-13.253989309478,-13.2385127873491,-13.209391925612,-13.2157278814899,-13.2243437095992,-13.2336087079551,-13.21422143145,-13.2339681355349,-13.2535640411465,-13.2250089377786,-13.2160657166043,-13.2680671272333,-13.2266742923612,-13.2160179088168,-13.2482584611565,-13.2156319199566,-13.2142410663192,-13.2614879104088,-13.2452992638476,-13.2630592726116,-13.2343341712241,-13.2199077448676,-13.2227293309912,-13.2343062806506,-13.218781651651,-13.2483677722899,-13.2097478342339,-13.2680867723786,-13.2587535457526,-13.262635786914,-13.2697246824573,-13.2209026809759,-13.2330734719715,-13.2680923666905,-13.2547212675054,-13.2573683214693,-13.2137356012883,-13.2175973322257,-13.2486407324245],[8.46897295100924,8.45171855856465,8.46481700596819,8.4754761613651,8.46082377490923,8.461830626007281,8.462729314626459,8.461443675342711,8.46191259217774,8.472923276435059,8.48401630165138,8.458371253408441,8.477617055125091,8.47570184950483,8.477799468789719,8.47145134147474,8.478048406853629,8.48528034195779,8.469575303958671,8.45957352078114,8.474048895115439,8.488029171298839,8.473437335922,8.484082637344621,8.46242233645879,8.470268221265719,8.463984474805329,8.464134789434199,8.456230946296071,8.48334624336805,8.47493999153642,8.47832062438022,8.469393389176499,8.48480589906514,8.47121232619015,8.48438437371817,8.484661585743391,8.477141599844281,8.462381270106089,8.455685978131131,8.4632880274758,8.47940722413856,8.46353857052336,8.461789681588639,8.47508713872833,8.458258081280711,8.4532568143863,8.4732571907655,8.479115866419329,8.48480340615605],["f547d6",null,null,"f90f5f","11f8ea","aec8ec","893f25","133ee7",null,null,"996f3a","133ee7","37a6f6","9f6884","4802b1",null,null,null,"a75c7f","8e104d","ab634e",null,null,"b799eb",null,"5d9e4d","a15e13",null,"ea3740","beb26e","567136","894024","36e2e7","a2086d","7baf73","eb2277",null,null,"d6584f",null,"312ecf","52ea64","cfd79c","d145b7","174288",null,"53608c","3b096b","f5c142",null],["other",null,null,"other","other","other","other","other",null,null,"other","other","other","other","other",null,null,null,"other","other","other",null,null,"other",null,"other","other",null,"other","funeral","other","funeral","other","other","other","funeral",null,null,"other",null,"other","other","other","other","other",null,"funeral","other","other",null],[27,25,91,41,36,56,47,0,86,69,67,84,68,44,34,66,78,47,53,47,71,86,53,69,38,46,68,37,100,56,50,57,65,72,29,69,37,48,54,71,47,61,47,35,53,16,13,59,69,67],[48,59,238,135,71,116,87,11,226,174,112,186,174,90,91,152,214,137,117,131,150,241,131,161,80,69,188,66,233,142,110,182,164,214,26,157,39,154,133,168,100,125,123,67,134,31,36,125,183,169],[22,22,21,23,23,21,21,22,22,22,22,22,22,21,23,22,23,21,22,23,21,23,21,24,23,22,24,23,20,24,24,20,24,21,22,21,23,22,23,23,23,22,23,22,22,22,23,22,22,22],["no",null,null,"no","no","no",null,"no","no","no","no","no","no","no","no","no","no","no",null,"no","no","no","no","no",null,"no","no","no",null,null,"no","no",null,"no","no",null,null,"no","no",null,"no","no",null,"no","no","no","no","no","no",null],["no",null,null,"no","no","no",null,"no","no","no","no","no","no","no","no","no","yes","no",null,"no","no","no","yes","no",null,"no","no","yes",null,null,"no","no",null,"no","no",null,null,"no","no",null,"no","no",null,"no","yes","no","no","no","no",null],["yes",null,null,"no","yes","yes",null,"yes","yes","yes","yes","yes","yes","yes","yes","yes","yes","yes",null,"yes","yes","yes","yes","yes",null,"yes","yes","yes",null,null,"yes","yes",null,"yes","yes",null,null,"yes","yes",null,"yes","yes",null,"yes","yes","yes","yes","yes","no",null],["no",null,null,"no","no","no",null,"no","no","no","no","no","no","no","no","yes","no","no",null,"no","no","no","no","no",null,"no","no","no",null,null,"no","no",null,"no","no",null,null,"yes","yes",null,"no","no",null,"no","no","no","no","no","no",null],["yes",null,null,"no","yes","yes",null,"yes","yes","no","yes","no","no","no","yes","no","no","no",null,"no","yes","no","no","no",null,"no","no","no",null,null,"no","yes",null,"yes","yes",null,null,"yes","yes",null,"yes","yes",null,"yes","yes","no","yes","yes","yes",null],[36.8,36.9,36.9,36.8,36.9,37.6,37.3,37,36.4,35.9,36.5,36.9,36.5,37.1,36.5,37.3,37,38,38,36,37,36.7,36.9,36.5,37,36.5,37.6,36.6,36.6,36.2,36.4,37.1,37.5,37.5,37.4,36.9,36.4,37.3,37,37.8,36.5,37.5,36.7,37,37.3,36.6,36.5,36.6,37.6,36.8],[null,"09:36","16:48","11:22","12:60","14:13","14:33","09:25","11:16","10:55","16:03","11:14","12:42","11:06","09:10","08:45",null,"15:41","13:34","18:58","12:43","16:33","14:29","07:18","08:11","16:32","16:17","07:32","17:45",null,"13:24","14:43","02:33","11:36","17:28","16:27",null,"20:49",null,"11:38","14:25","13:42","21:22","13:33","19:06","17:14","20:09",null,"10:23","09:09"],[117.1875,71.81844297615629,16.06524962926347,22.49657064471879,71.41440190438405,41.61712247324614,62.09538908706566,0,16.83765369253662,22.79032897344431,53.41198979591836,24.28026361429067,22.46003435064077,54.32098765432099,41.05784325564545,28.56648199445983,17.03205520132763,25.04129149128882,38.7172182043977,27.3876813705495,31.55555555555556,14.80690759456621,30.88398111998135,26.61934338952972,59.37499999999999,96.61835748792272,19.23947487550928,84.94031221303948,18.41993774061044,27.77226740726046,41.32231404958677,17.20806665861611,24.16716240333135,15.72189710891781,428.9940828402366,27.99302202929125,243.2610124917817,20.23950075898128,30.52744643563797,25.15589569160998,47,39.04,31.06616432017979,77.96836711962574,29.51659612385831,166.4932362122789,100.3086419753086,37.76,20.60378034578518,23.45856237526698],[2,1,2,2,1,1,2,1,1,2,2,2,1,0,2,0,1,1,2,2,1,1,1,0,2,1,1,2,1,0,0,2,1,1,2,2,1,0,2,2,0,2,0,0,2,2,null,1,0,1]],"container":"<table class=\"white-space: nowrap\">\n  <thead>\n    <tr>\n      <th>case_id<\/th>\n      <th>generation<\/th>\n      <th>date_infection<\/th>\n      <th>date_onset<\/th>\n      <th>date_hospitalisation<\/th>\n      <th>date_outcome<\/th>\n      <th>outcome<\/th>\n      <th>gender<\/th>\n      <th>age<\/th>\n      <th>age_unit<\/th>\n      <th>age_years<\/th>\n      <th>age_cat<\/th>\n      <th>age_cat5<\/th>\n      <th>hospital<\/th>\n      <th>lon<\/th>\n      <th>lat<\/th>\n      <th>infector<\/th>\n      <th>source<\/th>\n      <th>wt_kg<\/th>\n      <th>ht_cm<\/th>\n      <th>ct_blood<\/th>\n      <th>fever<\/th>\n      <th>chills<\/th>\n      <th>cough<\/th>\n      <th>aches<\/th>\n      <th>vomit<\/th>\n      <th>temp<\/th>\n      <th>time_admission<\/th>\n      <th>bmi<\/th>\n      <th>days_onset_hosp<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":5,"scrollX":true,"columnDefs":[{"className":"dt-right","targets":[1,8,10,14,15,18,19,20,26,28,29]},{"name":"case_id","targets":0},{"name":"generation","targets":1},{"name":"date_infection","targets":2},{"name":"date_onset","targets":3},{"name":"date_hospitalisation","targets":4},{"name":"date_outcome","targets":5},{"name":"outcome","targets":6},{"name":"gender","targets":7},{"name":"age","targets":8},{"name":"age_unit","targets":9},{"name":"age_years","targets":10},{"name":"age_cat","targets":11},{"name":"age_cat5","targets":12},{"name":"hospital","targets":13},{"name":"lon","targets":14},{"name":"lat","targets":15},{"name":"infector","targets":16},{"name":"source","targets":17},{"name":"wt_kg","targets":18},{"name":"ht_cm","targets":19},{"name":"ct_blood","targets":20},{"name":"fever","targets":21},{"name":"chills","targets":22},{"name":"cough","targets":23},{"name":"aches","targets":24},{"name":"vomit","targets":25},{"name":"temp","targets":26},{"name":"time_admission","targets":27},{"name":"bmi","targets":28},{"name":"days_onset_hosp","targets":29}],"order":[],"autoWidth":false,"orderClasses":false,"orderCellsTop":true,"lengthMenu":[5,10,25,50,100]}},"evals":[],"jsHooks":[]}</script>
 </div>
 </div>
 <!-- ======================================================= -->
@@ -1661,7 +1661,7 @@ <h2 data-number="31.8" class="anchored" data-anchor-id="highlighting"><span clas
 </div>
 <p>This also works well with faceting functions - it allows the user to produce facet plots with the background data highlighted that doesn’t apply to the facet! Below we count cases by week and plot the epidemic curves by hospital (<code>color =</code> and <code>facet_wrap()</code> set to <code>hospital</code> column).</p>
 <div class="cell">
-<div class="sourceCode cell-code" id="cb29"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb29-1"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a><span class="co"># produce a histogram of all cases by age</span></span>
+<div class="sourceCode cell-code" id="cb29"><pre class="sourceCode r code-with-copy"><code class="sourceCode r"><span id="cb29-1"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a><span class="co"># produce a linegraph of all cases by age</span></span>
 <span id="cb29-2"><a href="#cb29-2" aria-hidden="true" tabindex="-1"></a>linelist <span class="sc">%&gt;%</span> </span>
 <span id="cb29-3"><a href="#cb29-3" aria-hidden="true" tabindex="-1"></a>  <span class="fu">count</span>(<span class="at">week =</span> lubridate<span class="sc">::</span><span class="fu">floor_date</span>(date_hospitalisation, <span class="st">"week"</span>),</span>
 <span id="cb29-4"><a href="#cb29-4" aria-hidden="true" tabindex="-1"></a>        hospital) <span class="sc">%&gt;%</span> </span>
@@ -1671,7 +1671,8 @@ <h2 data-number="31.8" class="anchored" data-anchor-id="highlighting"><span clas
 <span id="cb29-8"><a href="#cb29-8" aria-hidden="true" tabindex="-1"></a>                          <span class="at">color =</span> hospital)) <span class="sc">+</span></span>
 <span id="cb29-9"><a href="#cb29-9" aria-hidden="true" tabindex="-1"></a>  <span class="fu">theme_minimal</span>() <span class="sc">+</span></span>
 <span id="cb29-10"><a href="#cb29-10" aria-hidden="true" tabindex="-1"></a>  gghighlight<span class="sc">::</span><span class="fu">gghighlight</span>() <span class="sc">+</span>                      <span class="co"># highlight instances where the patient has died</span></span>
-<span id="cb29-11"><a href="#cb29-11" aria-hidden="true" tabindex="-1"></a>  <span class="fu">facet_wrap</span>(<span class="sc">~</span>hospital)                              <span class="co"># make facets by outcome</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
+<span id="cb29-11"><a href="#cb29-11" aria-hidden="true" tabindex="-1"></a>  <span class="fu">facet_wrap</span>(<span class="sc">~</span>hospital) <span class="sc">+</span>                        <span class="co"># make facets by outcome</span></span>
+<span id="cb29-12"><a href="#cb29-12" aria-hidden="true" tabindex="-1"></a>     <span class="fu">scale_x_date</span>(<span class="at">labels =</span> <span class="fu">date_format</span>(<span class="st">"%m/%y"</span>))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
 <div class="cell-output-display">
 <div>
 <figure class="figure">
@@ -1860,7 +1861,7 @@ <h2 data-number="31.11" class="anchored" data-anchor-id="dual-axes"><span class=
 <ul>
 <li>The epicurve and the line are aggregated into weeks prior to plotting <em>and</em> the <code>date_breaks</code> and <code>date_labels</code> are identical - we do this so that the x-axes of the two plots are the same when they are overlaid.<br>
 </li>
-<li>The y-axis is created to the right-side for plot 2 with the <code>sex_axis =</code> argument of <code>scale_y_continuous()</code>.</li>
+<li>The y-axis is created to the right-side for plot 2 with the <code>sec_axis =</code> argument of <code>scale_y_continuous()</code>.</li>
 </ul>
 <p>Note there is another example of this technique in the <a href="../new_pages/epicurves.html">Epidemic curves</a> page - overlaying cumulative incidence on top of the epicurve.</p>
 <p><strong>Make the datasets for the plot</strong><br>
@@ -2653,7 +2654,7 @@ <h2 data-number="31.14" class="anchored" data-anchor-id="resources"><span class=
     </div>
   </div>
 </footer>
-<script>var lightboxQuarto = GLightbox({"loop":false,"openEffect":"zoom","selector":".lightbox","descPosition":"bottom","closeEffect":"zoom"});
+<script>var lightboxQuarto = GLightbox({"openEffect":"zoom","loop":false,"selector":".lightbox","descPosition":"bottom","closeEffect":"zoom"});
 window.onload = () => {
   lightboxQuarto.on('slide_before_load', (data) => {
     const { slideIndex, slideNode, slideConfig, player, trigger } = data;
diff --git a/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-23-1.png b/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-23-1.png
index d8e92d6b..c283d04c 100644
Binary files a/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-23-1.png and b/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-23-1.png differ
diff --git a/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-24-1.png b/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-24-1.png
index c777ecc8..d462d9bd 100644
Binary files a/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-24-1.png and b/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-24-1.png differ
diff --git a/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-28-1.png b/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-28-1.png
index 620252af..34bde4b2 100644
Binary files a/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-28-1.png and b/html_outputs/new_pages/ggplot_tips_files/figure-html/unnamed-chunk-28-1.png differ
diff --git a/html_outputs/search.json b/html_outputs/search.json
index 16f3cea3..7446e8c1 100644
--- a/html_outputs/search.json
+++ b/html_outputs/search.json
@@ -2892,7 +2892,7 @@
     "href": "new_pages/ggplot_tips.html#highlighting",
     "title": "31  ggplot tips",
     "section": "31.8 Highlighting",
-    "text": "31.8 Highlighting\nHighlighting specific elements in a chart is a useful way to draw attention to a specific instance of a variable while also providing information on the dispersion of the full dataset. While this is not easily done in base ggplot2, there is an external package that can help to do this known as gghighlight. This is easy to use within the ggplot syntax.\nThe gghighlight package uses the gghighlight() function to achieve this effect. To use this function, supply a logical statement to the function - this can have quite flexible outcomes, but here we’ll show an example of the age distribution of cases in our linelist, highlighting them by outcome.\n\n# load gghighlight\npacman::p_load(gghighlight)\n\n# replace NA values with unknown in the outcome variable\nlinelist &lt;- linelist %&gt;%\n  mutate(outcome = replace_na(outcome, \"Unknown\"))\n\n# produce a histogram of all cases by age\nggplot(\n  data = linelist,\n  mapping = aes(x = age_years, fill = outcome)) +\n  geom_histogram() + \n  gghighlight::gghighlight(outcome == \"Death\")     # highlight instances where the patient has died.\n\n\n\n\n\n\n\n\nThis also works well with faceting functions - it allows the user to produce facet plots with the background data highlighted that doesn’t apply to the facet! Below we count cases by week and plot the epidemic curves by hospital (color = and facet_wrap() set to hospital column).\n\n# produce a histogram of all cases by age\nlinelist %&gt;% \n  count(week = lubridate::floor_date(date_hospitalisation, \"week\"),\n        hospital) %&gt;% \n  ggplot() +\n  geom_line(mapping = aes(x = week, \n                          y = n, \n                          color = hospital)) +\n  theme_minimal() +\n  gghighlight::gghighlight() +                      # highlight instances where the patient has died\n  facet_wrap(~hospital)                              # make facets by outcome",
+    "text": "31.8 Highlighting\nHighlighting specific elements in a chart is a useful way to draw attention to a specific instance of a variable while also providing information on the dispersion of the full dataset. While this is not easily done in base ggplot2, there is an external package that can help to do this known as gghighlight. This is easy to use within the ggplot syntax.\nThe gghighlight package uses the gghighlight() function to achieve this effect. To use this function, supply a logical statement to the function - this can have quite flexible outcomes, but here we’ll show an example of the age distribution of cases in our linelist, highlighting them by outcome.\n\n# load gghighlight\npacman::p_load(gghighlight)\n\n# replace NA values with unknown in the outcome variable\nlinelist &lt;- linelist %&gt;%\n  mutate(outcome = replace_na(outcome, \"Unknown\"))\n\n# produce a histogram of all cases by age\nggplot(\n  data = linelist,\n  mapping = aes(x = age_years, fill = outcome)) +\n  geom_histogram() + \n  gghighlight::gghighlight(outcome == \"Death\")     # highlight instances where the patient has died.\n\n\n\n\n\n\n\n\nThis also works well with faceting functions - it allows the user to produce facet plots with the background data highlighted that doesn’t apply to the facet! Below we count cases by week and plot the epidemic curves by hospital (color = and facet_wrap() set to hospital column).\n\n# produce a linegraph of all cases by age\nlinelist %&gt;% \n  count(week = lubridate::floor_date(date_hospitalisation, \"week\"),\n        hospital) %&gt;% \n  ggplot() +\n  geom_line(mapping = aes(x = week, \n                          y = n, \n                          color = hospital)) +\n  theme_minimal() +\n  gghighlight::gghighlight() +                      # highlight instances where the patient has died\n  facet_wrap(~hospital) +                        # make facets by outcome\n     scale_x_date(labels = date_format(\"%m/%y\"))",
     "crumbs": [
       "Data Visualization",
       "<span class='chapter-number'>31</span>  <span class='chapter-title'>ggplot tips</span>"
@@ -2925,7 +2925,7 @@
     "href": "new_pages/ggplot_tips.html#dual-axes",
     "title": "31  ggplot tips",
     "section": "31.11 Dual axes",
-    "text": "31.11 Dual axes\nA secondary y-axis is often a requested addition to a ggplot2 graph. While there is a robust debate about the validity of such graphs in the data visualization community, and they are often not recommended, your manager may still want them. Below, we present one method to achieve them.\nThis approach involves creating two separate datasets, one for each of the different plots we want to achieve, and then calculating a “scaling factor” required to transform the values onto the same scale.\nThis is because the function we are going to use to add a second y-axis, sec_axis() requires the second axis be directly proportional to the first axis.\nTo demonstrate this technique we will overlay the epidemic curve with a line of the weekly percent of patients who died. We use this example because the alignment of dates on the x-axis is more complex than say, aligning a bar chart with another plot. Some things to note:\n\nThe epicurve and the line are aggregated into weeks prior to plotting and the date_breaks and date_labels are identical - we do this so that the x-axes of the two plots are the same when they are overlaid.\n\nThe y-axis is created to the right-side for plot 2 with the sex_axis = argument of scale_y_continuous().\n\nNote there is another example of this technique in the Epidemic curves page - overlaying cumulative incidence on top of the epicurve.\nMake the datasets for the plot\nHere we will transform linelist into two different datasets linelist_primary_axis and linelist_secondary_axis in order to then create the scaling factor that will allow us to attach a second axis at the correct scale.\n\n#Set up linelist for primary axis - the weekly cases epicurve\nlinelist_primary_axis &lt;- linelist %&gt;%                \n     count(epiweek = lubridate::floor_date(date_onset, \"week\"))\n\n#Set up linelist for secondary axis - the line graph of the weekly percent of deaths\nlinelist_secondary_axis &lt;- linelist %&gt;%         \n     group_by(\n          epiweek = lubridate::floor_date(date_onset, \"week\")) %&gt;% \n     summarise(\n          n = n(),\n          pct_death = 100*sum(outcome == \"Death\", na.rm = T) / n)\n\nCalculate the scaling factor\nNow that we have created the datasets with our variables of interest, we want to extract the columns and calculate the maximum value in each in order to set our scale. We will then divide the secondary axis value by the first axis value in order to create our scaling factor\n\n#Set up scaling factor to transform secondary axis\nlinelist_primary_axis_max &lt;- linelist_primary_axis %&gt;%\n     pull(n) %&gt;%\n     max()\n\nlinelist_secondary_axis_max &lt;- linelist_secondary_axis %&gt;%\n     pull(pct_death) %&gt;%\n     max()\n\n#Create our scaling factor, how much the secondary axis value must be divided by to create values on the same scale as the primary axis\nscaling_factor &lt;- linelist_secondary_axis_max/linelist_primary_axis_max\n\nAnd now we are ready to plot! We will be using the argument to create our epicurve, and to create our line graph. Note that we are not specifying a data = argument in our first ggplot(), this is because we are using two separate datasets to create this plot.\n\nggplot() +\n     #First create the epicurve\n     geom_area(data = linelist_primary_axis,\n               mapping = aes(x = epiweek, \n                             y = n), \n               fill = \"grey\"\n               ) +\n     #Now create the linegraph\n     geom_line(data = linelist_secondary_axis,\n               mapping = aes(x = epiweek, \n                             y = pct_death / scaling_factor)\n               )  +\n     #Now we specify the second axis, and note that we are going to be multiplying the values of the second axis by the scaling factor in order to get the axis to display the correct values\n     scale_y_continuous(\n          sec.axis = sec_axis(~.*scaling_factor, \n                              name = \"Weekly percent of deaths\")\n     ) +\n     scale_x_date(\n          date_breaks = \"month\",\n          date_labels = \"%b\"\n          ) +\n     labs(\n          x = \"Epiweek of symptom onset\",\n          y = \"Weekly cases\",\n          title = \"Weekly case incidence and percent deaths\"\n     ) +\n     theme_bw()",
+    "text": "31.11 Dual axes\nA secondary y-axis is often a requested addition to a ggplot2 graph. While there is a robust debate about the validity of such graphs in the data visualization community, and they are often not recommended, your manager may still want them. Below, we present one method to achieve them.\nThis approach involves creating two separate datasets, one for each of the different plots we want to achieve, and then calculating a “scaling factor” required to transform the values onto the same scale.\nThis is because the function we are going to use to add a second y-axis, sec_axis() requires the second axis be directly proportional to the first axis.\nTo demonstrate this technique we will overlay the epidemic curve with a line of the weekly percent of patients who died. We use this example because the alignment of dates on the x-axis is more complex than say, aligning a bar chart with another plot. Some things to note:\n\nThe epicurve and the line are aggregated into weeks prior to plotting and the date_breaks and date_labels are identical - we do this so that the x-axes of the two plots are the same when they are overlaid.\n\nThe y-axis is created to the right-side for plot 2 with the sec_axis = argument of scale_y_continuous().\n\nNote there is another example of this technique in the Epidemic curves page - overlaying cumulative incidence on top of the epicurve.\nMake the datasets for the plot\nHere we will transform linelist into two different datasets linelist_primary_axis and linelist_secondary_axis in order to then create the scaling factor that will allow us to attach a second axis at the correct scale.\n\n#Set up linelist for primary axis - the weekly cases epicurve\nlinelist_primary_axis &lt;- linelist %&gt;%                \n     count(epiweek = lubridate::floor_date(date_onset, \"week\"))\n\n#Set up linelist for secondary axis - the line graph of the weekly percent of deaths\nlinelist_secondary_axis &lt;- linelist %&gt;%         \n     group_by(\n          epiweek = lubridate::floor_date(date_onset, \"week\")) %&gt;% \n     summarise(\n          n = n(),\n          pct_death = 100*sum(outcome == \"Death\", na.rm = T) / n)\n\nCalculate the scaling factor\nNow that we have created the datasets with our variables of interest, we want to extract the columns and calculate the maximum value in each in order to set our scale. We will then divide the secondary axis value by the first axis value in order to create our scaling factor\n\n#Set up scaling factor to transform secondary axis\nlinelist_primary_axis_max &lt;- linelist_primary_axis %&gt;%\n     pull(n) %&gt;%\n     max()\n\nlinelist_secondary_axis_max &lt;- linelist_secondary_axis %&gt;%\n     pull(pct_death) %&gt;%\n     max()\n\n#Create our scaling factor, how much the secondary axis value must be divided by to create values on the same scale as the primary axis\nscaling_factor &lt;- linelist_secondary_axis_max/linelist_primary_axis_max\n\nAnd now we are ready to plot! We will be using the argument to create our epicurve, and to create our line graph. Note that we are not specifying a data = argument in our first ggplot(), this is because we are using two separate datasets to create this plot.\n\nggplot() +\n     #First create the epicurve\n     geom_area(data = linelist_primary_axis,\n               mapping = aes(x = epiweek, \n                             y = n), \n               fill = \"grey\"\n               ) +\n     #Now create the linegraph\n     geom_line(data = linelist_secondary_axis,\n               mapping = aes(x = epiweek, \n                             y = pct_death / scaling_factor)\n               )  +\n     #Now we specify the second axis, and note that we are going to be multiplying the values of the second axis by the scaling factor in order to get the axis to display the correct values\n     scale_y_continuous(\n          sec.axis = sec_axis(~.*scaling_factor, \n                              name = \"Weekly percent of deaths\")\n     ) +\n     scale_x_date(\n          date_breaks = \"month\",\n          date_labels = \"%b\"\n          ) +\n     labs(\n          x = \"Epiweek of symptom onset\",\n          y = \"Weekly cases\",\n          title = \"Weekly case incidence and percent deaths\"\n     ) +\n     theme_bw()",
     "crumbs": [
       "Data Visualization",
       "<span class='chapter-number'>31</span>  <span class='chapter-title'>ggplot tips</span>"
diff --git a/new_pages/basics.qmd b/new_pages/basics.qmd
index fcba3676..87d99403 100644
--- a/new_pages/basics.qmd
+++ b/new_pages/basics.qmd
@@ -1503,6 +1503,13 @@ options(scipen = 999)
 round(c(2.5, 3.5))
 
 janitor::round_half_up(c(2.5, 3.5))
+
+```
+
+For rounding from proportion to percentages, you can use the function `percent()` from the **scales** package.
+
+```{r}
+scales::percent(c(0.25, 0.35), accuracy = 0.1)
 ```
 
 #### Statistical functions {.unnumbered}
@@ -1647,4 +1654,4 @@ A few things to remember when writing commands in R, to avoid errors and warning
 
 ### Code assists {.unnumbered}
 
-Any script (RMarkdown or otherwise) will give clues when you have made a mistake. For example, if you forgot to write a comma where it is needed, or to close a parentheses, RStudio will raise a flag on that line, on the right side of the script, to warn you.
+Any script (RMarkdown or otherwise) will give clues when you have made a mistake. For example, if you forgot to write a comma where it is needed, or to close a parentheses, RStudio will raise a flag on that line, on the left hand side of the script, to warn you.
diff --git a/new_pages/basics.rmarkdown b/new_pages/basics.rmarkdown
new file mode 100644
index 00000000..495eef44
--- /dev/null
+++ b/new_pages/basics.rmarkdown
@@ -0,0 +1,1791 @@
+# R Basics {#rbasics}
+
+
+```{r out.width = "100%", fig.align = "center", echo=F}
+knitr::include_graphics(here::here("images", "basics_header_close.png"))
+```
+
+
+Welcome!
+
+This page reviews the essentials of R. It is not intended to be a comprehensive tutorial, but it provides the basics and can be useful for refreshing your memory. The section on [Resources for learning](#learning) links to more comprehensive tutorials.
+
+Parts of this page have been adapted with permission from the [R4Epis project](https://r4epis.netlify.app/).
+
+See the page on [Transition to R](transition_to_R.qmd) for tips on switching to R from STATA, SAS, or Excel.
+
+
+```{r, echo=F}
+# import the cleaned ebola linelist
+linelist <- rio::import(here::here("data", "case_linelists", "linelist_cleaned.rds"))
+pacman::p_load(apyramid)
+```
+
+
+<!-- ======================================================= -->
+
+## Why use R?
+
+As stated on the [R project website](https://www.r-project.org/about.html), R is a programming language and environment for statistical computing and graphics. It is highly versatile, extendable, and community-driven.
+
+**Cost**
+
+R is free to use! There is a strong ethic in the community of free and open-source material.
+
+**Reproducibility**
+
+Conducting your data management and analysis through a programming language (compared to Excel or another primarily point-click/manual tool) enhances **reproducibility**, makes **error-detection** easier, and eases your workload.
+
+**Community**
+
+The R community of users is enormous and collaborative. New packages and tools to address real-life problems are developed daily, and vetted by the community of users. As one example, [R-Ladies](https://rladies.org/) is a worldwide organization whose mission is to promote gender diversity in the R community, and is one of the largest organizations of R users. It likely has a chapter near you!
+
+## Key terms
+
+**RStudio** - RStudio is a Graphical User Interface (GUI) for easier use of **R**. Read more [in the RStudio section](#rstudio).
+
+**Objects** - Everything you store in R - datasets, variables, a list of village names, a total population number, even outputs such as graphs - are *objects* which are *assigned a name* and *can be referenced* in later commands. Read more in the [Objects section](#objects).
+
+**Functions** - A function is a code operation that accept inputs and returns a transformed output. Read more [in the Functions section](#functions).
+
+**Packages** - An R package is a shareable bundle of functions. Read more [in the Packages section](#packages).
+
+**Scripts** - A script is the document file that hold your commands. Read more [in the Scripts section](#scripts)
+
+## Resources for learning {#learning}
+
+### Resources within RStudio {.unnumbered}
+
+**Help documentation**
+
+Search the RStudio "Help" tab for documentation on R packages and specific functions. This is within the pane that also contains Files, Plots, and Packages (typically in the lower-right pane). As a shortcut, you can also type the name of a package or function into the R console after a question-mark to open the relevant Help page. Do not include parentheses.
+
+For example: `?filter` or `?diagrammeR`.
+
+**Interactive tutorials**
+
+There are several ways to learn R interactively *within* RStudio.
+
+RStudio itself offers a Tutorial pane that is powered by the [**learnr**](https://blog.rstudio.com/2020/02/25/rstudio-1-3-integrated-tutorials/) R package. Simply install this package and open a tutorial via the new "Tutorial" tab in the upper-right RStudio pane (which also contains Environment and History tabs).
+
+The R package [**swirl**](https://swirlstats.com/) offers interactive courses in the R Console. Install and load this package, then run the command `swirl()` (empty parentheses) in the R console. You will see prompts appear in the Console. Respond by typing in the Console. It will guide you through a course of your choice.
+
+### Cheatsheets {.unnumbered}
+
+There are many PDF "cheatsheets" available on the [RStudio website](https://rstudio.com/resources/cheatsheets/), for example:
+
+-   Factors with **forcats** package.\
+-   Dates and times with **lubridate** package.\
+-   Strings with **stringr** package.\
+-   iterative opertaions with **purrr** package.\
+-   Data import.\
+-   Data transformation cheatsheet with **dplyr** package.\
+-   R Markdown (to create documents like PDF, Word, Powerpoint...).\
+-   Shiny (to build interactive web apps).\
+-   Data visualization with **ggplot2** package.\
+-   Cartography (GIS).\
+-   **leaflet** package (interactive maps).\
+-   Python with R (**reticulate** package).
+
+This is an online R resource specifically for [Excel users](https://jules32.github.io/r-for-excel-users/).
+
+### Twitter {.unnumbered}
+
+-   Follow us! [\@epiRhandbook](https://twitter.com/epirhandbook)
+
+Also:
+
+**\#epitwitter** and **\#rstats**
+
+### Free online resources {.unnumbered}
+
+A definitive text is the [R for Data Science](https://r4ds.hadley.nz/) book by Garrett Grolemund and Hadley Wickham.
+
+The [R4Epis](https://r4epis.netlify.app/) project website aims to "develop standardised data cleaning, analysis and reporting tools to cover common types of outbreaks and population-based surveys that would be conducted in an MSF emergency response setting". You can find R basics training materials, templates for RMarkdown reports on outbreaks and surveys, and tutorials to help you set them up.
+
+### Languages other than English {.unnumbered}
+
+[Materiales de RStudio en Español](https://www.rstudio.com/collections/espanol/)
+
+[Introduction à R et au tidyverse (Francais)](https://juba.github.io/tidyverse/index.html)
+
+<!-- ======================================================= -->
+
+## Installation
+
+### R and RStudio {.unnumbered}
+
+**How to install R**
+
+Visit this website <https://www.r-project.org/> and download the latest version of R suitable for your computer.
+
+**How to install RStudio**
+
+Visit this website <https://rstudio.com/products/rstudio/download/> and download the latest free Desktop version of RStudio suitable for your computer.
+
+**Permissions**\
+Note that you should install R and RStudio to a drive where you have read and write permissions. Otherwise, your ability to install R packages (a frequent occurrence) will be impacted. If you encounter problems, try opening RStudio by right-clicking the icon and selecting "Run as administrator". Other tips can be found in the page [R on network drives](network_drives.qmd).
+
+**How to update R and RStudio**
+
+Your version of R is printed to the R Console at start-up. You can also run `sessionInfo()`.
+
+To update R, go to the website mentioned above and re-install R. Alternatively, you can use the **installr** package (on Windows) by running `installr::updateR()`. This will open dialog boxes to help you download the latest R version and update your packages to the new R version. More details can be found in the **installr** [documentation](https://talgalili.github.io/installr/).
+
+Be aware that the old R version will still exist in your computer. You can temporarily run an older version of R by clicking "Tools" -\> "Global Options" in RStudio and choosing an R version. This can be useful if you want to use a package that has not been updated to work on the newest version of R.
+
+To update RStudio, you can go to the website above and re-download RStudio. Another option is to click "Help" -\> "Check for Updates" within RStudio, but this may not show the very latest updates.
+
+To see which versions of R, RStudio, or packages were used when this Handbook as made, see the page on [Editorial and technical notes](editorial_style.qmd).
+
+### Other software you *may* need to install {.unnumbered}
+
+-   TinyTeX (for compiling an RMarkdown document to PDF).\
+-   Pandoc (for compiling RMarkdown documents).\
+-   RTools (for building packages for R).\
+-   phantomjs (for saving still images of animated networks, such as transmission chains).
+
+#### TinyTex {.unnumbered}
+
+TinyTex is a custom LaTeX distribution, useful when trying to produce PDFs from R.\
+See <https://yihui.org/tinytex/> for more informaton.
+
+To install TinyTex from R:
+
+
+```{r, eval=F}
+install.packages('tinytex')
+tinytex::install_tinytex()
+# to uninstall TinyTeX, run tinytex::uninstall_tinytex()
+```
+
+
+#### Pandoc {.unnumbered}
+
+Pandoc is a document converter, a separate software from R. **It comes bundled with RStudio and should not need to be downloaded.** It helps the process of converting Rmarkdown documents to formats like .pdf and adding complex functionality.
+
+#### RTools {.unnumbered}
+
+RTools is a collection of software for building packages for R
+
+Install from this website: <https://cran.r-project.org/bin/windows/Rtools/>
+
+#### phantomjs {.unnumbered}
+
+This is often used to take "screenshots" of webpages. For example when you make a transmission chain with **epicontacts** package, an HTML file is produced that is interactive and dynamic. If you want a static image, it can be useful to use the [**webshot**](https://wch.github.io/webshot/articles/intro.html) package to automate this process. This will require the external program "phantomjs". You can install phantomjs via the **webshot** package with the command `webshot::install_phantomjs()`.
+
+<!-- ======================================================= -->
+
+## RStudio {#rstudio}
+
+### RStudio orientation {.unnumbered}
+
+**First, open RStudio.** 
+
+As their icons can look very similar, be sure you are opening *RStudio* and not R.
+
+For RStudio to work you must also have R installed on the computer (see above for installation instructions).
+
+**RStudio** is an interface (GUI) for easier use of **R**. You can think of R as being the engine of a vehicle, doing the crucial work, and RStudio as the body of the vehicle (with seats, accessories, etc.) that helps you actually use the engine to move forward! You can see the complete RStudio user-interface cheatsheet (PDF) [here](https://rstudio.github.io/cheatsheets/html/rstudio-ide.html).
+
+By default RStudio displays four rectangle panes.
+
+
+```{r out.width = "100%", fig.align = "center", echo=F}
+knitr::include_graphics(here::here("images", "RStudio_overview.png"))
+```
+
+
+[***TIP:*** If your RStudio displays only one left pane it is because you have no scripts open yet.]{style="color: black;"}
+
+**The Source Pane**\
+This pane, by default in the upper-left, is a space to edit, run, and save your [scripts](#scripts). Scripts contain the commands you want to run. This pane can also display datasets (data frames) for viewing.
+
+For Stata users, this pane is similar to your Do-file and Data Editor windows.
+
+**The R Console Pane**
+
+The R Console, by default the left or lower-left pane in R Studio, is the home of the R "engine". This is where the commands are actually run and non-graphic outputs and error/warning messages appear. You can directly enter and run commands in the R Console, but realize that these commands are not saved as they are when running commands from a script.
+
+If you are familiar with Stata, the R Console is like the Command Window and also the Results Window.
+
+**The Environment Pane**\
+This pane, by default in the upper-right, is most often used to see brief summaries of [objects](#objects) in the R Environment in the current session. These objects could include imported, modified, or created datasets, parameters you have defined (e.g. a specific epi week for the analysis), or vectors or lists you have defined during analysis (e.g. names of regions). You can click on the arrow next to a data frame name to see its variables.
+
+In Stata, this is most similar to the Variables Manager window.
+
+This pane also contains *History* where you can see commands that you can previously. It also has a "Tutorial" tab where you can complete interactive R tutorials if you have the **learnr** package installed. It also has a "Connections" pane for external connections, and can have a "Git" pane if you choose to interface with Github.
+
+**Plots, Viewer, Packages, and Help Pane**\
+The lower-right pane includes several important tabs. Typical plot graphics including maps will display in the Plot pane. Interactive or HTML outputs will display in the Viewer pane. The Help pane can display documentation and help files. The Files pane is a browser which can be used to open or delete files. The Packages pane allows you to see, install, update, delete, load/unload R packages, and see which version of the package you have. To learn more about packages see the [packages section](#packages) below.
+
+This pane contains the Stata equivalents of the Plots Manager and Project Manager windows.
+
+### RStudio settings {.unnumbered}
+
+Change RStudio settings and appearance in the *Tools* drop-down menu, by selecting *Global Options*. There you can change the default settings, including appearance/background color.
+
+
+```{r out.width = c('50%'), fig.show='hold', echo=F}
+knitr::include_graphics(here::here("images", "RStudio_tools_options_1.png"))
+
+knitr::include_graphics(here::here("images", "RStudio_tools_options.png"))
+```
+
+
+**Restart**
+
+If your R freezes, you can re-start R by going to the Session menu and clicking "Restart R". This avoids the hassle of closing and opening RStudio. 
+
+
+<span style="color: orange;">**_CAUTION:_** Everything in your R environment will be removed when you do this.
+
+### Keyboard shortcuts {.unnumbered}
+
+Some very useful keyboard shortcuts are below. See all the keyboard shortcuts for Windows, Max, and Linux [Rstudio user interface cheatsheet](https://rstudio.github.io/cheatsheets/html/rstudio-ide.html#keyboard-shortcuts).
+
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Windows/Linux                    | Mac                    | Action                                                                                                                         |
++==================================+========================+================================================================================================================================+
+| Esc                              | Esc                    | Interrupt current command (useful if you accidentally ran an incomplete command and cannot escape seeing "+" in the R console). |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl+s                           | Cmd+s                  | Save (script).                                                                                                                  |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Tab                              | Tab                    | Auto-complete.                                                                                                                  |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Enter                     | Cmd + Enter            | Run current line(s)/selection of code.                                                                                          |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Shift + C                 | Cmd + Shift + c        | Comment/uncomment the highlighted lines.                                                                                        |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Alt + -                          | Option + -             | Insert `<-`.                                                                                                                    |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Shift + m                 | Cmd + Shift + m        | Insert `%>%`.                                                                                                                   |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + l                         | Cmd + l                | Clear the R console.                                                                                                            |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Alt + b                   | Cmd + Option + b       | Run from start to current. line                                                                                                 |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Alt + t                   | Cmd + Option + t       | Run the current code section (R Markdown).                                                                                      |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Alt + i                   | Cmd + Shift + r        | Insert code chunk (into R Markdown).                                                                                            |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Alt + c                   | Cmd + Option + c       | Run current code chunk (R Markdown).                                                                                            |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| up/down arrows in R console      | Same                   | Toggle through recently run commands.                                                                                           |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Shift + up/down arrows in script | Same                   | Select multiple code lines.                                                                                                     |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + f                         | Cmd + f                | Find and replace in current script.                                                                                             |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Ctrl + Shift + f                 | Cmd + Shift + f        | Find in files (search/replace across many scripts).                                                                             |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Alt + l                          | Cmd + Option + l       | Fold selected code.                                                                                                             |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+| Shift + Alt + l                  | Cmd + Shift + Option+l | Unfold selected code.                                                                                                           |
++----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+
+
+[***TIP:*** Use your Tab key when typing to engage RStudio's auto-complete functionality. This can prevent spelling errors. Press Tab while typing to produce a drop-down menu of likely functions and objects, based on what you have typed so far.]{style="color: darkgreen;"}
+
+<!-- ======================================================= -->
+
+## Functions {#functions}
+
+Functions are at the core of using R. Functions are how you perform tasks and operations. Many functions come installed with R, many more are available for download in *packages* (explained in the [packages](#packages) section), and you can even write your own custom functions!
+
+This basics section on functions explains:
+
+-   What a function is and how they work.\
+-   What function *arguments* are.\
+-   How to get help understanding a function.
+
+*A quick note on syntax:* In this handbook, functions are written in code-text with open parentheses, like this: `filter()`. As explained in the [packages](#packages) section, functions are downloaded within *packages*. In this handbook, package names are written in **bold**, like **dplyr**. Sometimes in example code you may see the function name linked explicitly to the name of its package with two colons (`::`) like this: `dplyr::filter()`. The purpose of this linkage is explained in the packages section.
+
+<!-- ======================================================= -->
+
+### Simple functions {.unnumbered}
+
+**A function is like a machine that receives inputs, carries out an action with those inputs, and produces an output.** What the output is depends on the function.
+
+**Functions typically operate upon some object placed within the function's parentheses**. For example, the function `sqrt()` calculates the square root of a number:
+
+
+```{r basics_function_sqrt}
+sqrt(49)
+```
+
+
+The object provided to a function also can be a column in a dataset (see the [Objects](#objects) section for detail on all the kinds of objects). Because R can store multiple datasets, you will need to specify both the dataset and the column. One way to do this is using the `$` notation to link the name of the dataset and the name of the column (`dataset$column`). In the example below, the function `summary()` is applied to the numeric column `age` in the dataset `linelist`, and the output is a summary of the column's numeric and missing values.
+
+
+```{r basics_functions_summary}
+# Print summary statistics of column 'age' in the dataset 'linelist'
+summary(linelist$age)
+```
+
+
+[***NOTE:*** Behind the scenes, a function represents complex additional code that has been wrapped up for the user into one easy command.]{style="color: black;"}
+
+<!-- ======================================================= -->
+
+### Functions with multiple arguments {.unnumbered}
+
+Functions often ask for several inputs, called ***arguments***, located within the parentheses of the function, usually separated by commas.
+
+-   Some arguments are required for the function to work correctly, others are optional.\
+-   Optional arguments have default settings.\
+-   Arguments can take character, numeric, logical (TRUE/FALSE), and other inputs.
+
+Here is a fun fictional function, called `oven_bake()`, as an example of a typical function. It takes an input object (e.g. a dataset, or in this example "dough") and performs operations on it as specified by additional arguments (`minutes =` and `temperature =`). The output can be printed to the console, or saved as an object using the assignment operator `<-`.
+
+
+```{r basics_functions_image, echo=F, out.width = "75%", fig.align = "center"}
+knitr::include_graphics(here::here("images", "Function_Bread_Example.png"))
+```
+
+
+**In a more realistic example**, the `age_pyramid()` command below produces an age pyramid plot based on defined age groups and a binary split column, such as `gender`. The function is given three arguments within the parentheses, separated by commas. The values supplied to the arguments establish `linelist` as the data frame to use, `age_cat5` as the column to count, and `gender` as the binary column to use for splitting the pyramid by color.
+
+
+```{r basics_functions_arguments, include=FALSE, results='hide', message=FALSE, warning=FALSE,}
+## create an age group variable by specifying categorical breaks
+linelist$age_group <- cut(linelist$age, breaks = c(0, 5, 10, 15, 20, 30, 45, 60))
+```
+
+```{r message=FALSE, warning=FALSE,  out.width = "75%", out.height="75%"}
+# Create an age pyramid
+age_pyramid(data = linelist, age_group = "age_cat5", split_by = "gender")
+```
+
+
+The above command can be equivalently written as below, in a longer style with a new line for each argument. This style can be easier to read, and easier to write "comments" with `#` to explain each part (commenting extensively is good practice!). To run this longer command you can highlight the entire command and click "Run", or just place your cursor in the first line and then press the Ctrl and Enter keys simultaneously.
+
+
+```{r message=FALSE, warning=FALSE,  out.width = "75%", out.height="75%"}
+# Create an age pyramid
+age_pyramid(
+  data = linelist,        # use case linelist
+  age_group = "age_cat5", # provide age group column
+  split_by = "gender"     # use gender column for two sides of pyramid
+  )
+```
+
+
+The first half of an argument assignment (e.g. `data =`) does not need to be specified if the arguments are written in a specific order (specified in the function's documentation). The below code produces the exact same pyramid as above, because the function expects the argument order: data frame, `age_group` variable, `split_by` variable.
+
+
+```{r, basics_functions_pyramid2, eval = FALSE, warning=FALSE, message=FALSE, , out.width = "75%", out.height="75%", eval=F}
+# This command will produce the exact same graphic as above
+age_pyramid(linelist, "age_cat5", "gender")
+```
+
+
+**A more complex `age_pyramid()` command might include the *optional* arguments to:**
+
+-   Show proportions instead of counts (set `proportional = TRUE` when the default is `FALSE`)\
+-   Specify the two colors to use (`pal =` is short for "palette" and is supplied with a vector of two color names. See the [objects](https://epirhandbook.com/new_pages/basics.html#objects) page for how the function `c()` makes a vector)
+
+[***NOTE:*** For arguments that you specify with both parts of the argument (e.g. `proportional = TRUE`), their order among all the arguments does not matter.]{style="color: black;"}
+
+
+```{r message=FALSE, warning=FALSE, out.width = "75%", out.height="75%"}
+age_pyramid(
+  linelist,                    # use case linelist
+  "age_cat5",                  # age group column
+  "gender",                    # split by gender
+  proportional = TRUE,         # percents instead of counts
+  pal = c("orange", "purple")  # colors
+  )
+```
+
+***TIP:*** Remember that you can put `?` before a function to see what arguments the function can take, and which arguments are needed and which arguments have default values. For example `?age_pyramid'.
+
+<!-- ======================================================= -->
+
+### Writing Functions {.unnumbered}
+
+R is a language that is oriented around functions, so you should feel empowered to write your own functions. Creating functions brings several advantages:
+
+-   To facilitate modular programming - the separation of code in to independent and manageable pieces.\
+-   Replace repetitive copy-and-paste, which can be error prone.\
+-   Give pieces of code memorable names.
+
+How to write a function is covered in-depth in the [Writing functions](writing_functions.qmd) page.
+
+<!-- A function is given a name and defined with the assignment operator `<-` to a special **base** R function called `function()`. Within the parentheses, the arguments that the function will accept are defined. This is followed by curly brackets `{ }`, within which the actual code of the function is written.     -->
+
+
+```{r, eval=F, echo=F}
+my_function <- function( ARGUMENTS HERE ){ CODE HERE }
+```
+
+
+<!-- The arguments should be provided in the syntax `argument = default`, separated by commas.   -->
+
+<!-- Here is an example where we create a function `staff_calc()` to serve as a staffing calculator for COVID-19 case investigation and contact tracing calls.   -->
+
+<!-- The arguments (inputs) and their default values will be:   -->
+
+<!-- * `daily_cases = NULL` The number of new COVID-19 cases per day   -->
+
+<!-- * `contacts_each = 5` The number contacts enumerated for each case   -->
+
+<!-- * `time_case = 0.5`  Number of hours to complete a case investigaton by phone   -->
+
+<!-- * `time_contact = 0.25`  Number of hours to complete a contact follow-up by phone   -->
+
+<!-- * `time_day = 8` The number of hours one staff works per day   -->
+
+<!-- Below, the function is created. The code ends with the special function `return()`, which is what the function produces.    -->
+
+<!-- ```{r message=FALSE, warning=FALSE, out.width = "75%", out.height="75%"} -->
+
+<!-- staff_calc <- function(daily_cases = NULL, contacts_each = 5, -->
+
+<!--                        time_case = 0.5, time_contact = 0.25, time_day = 8){ -->
+
+<!--   # Define total daily hours for calling cases -->
+
+<!--   case_hours <- daily_cases * time_case  -->
+
+<!--   # Define total daily hours for calling contacts -->
+
+<!--   contact_hours <- daily_cases * contacts_each * time_contact -->
+
+<!--   # Calculate number of staff required -->
+
+<!--   staff_required <- (case_hours + contact_hours)/time_day -->
+
+<!--   return(staff_required) -->
+
+<!-- } -->
+
+<!-- ``` -->
+
+<!-- Once this code is run, the function will be defined and will appear in the R Environment. We can run the function. Below all the default values are used and the `daily_cases = ` is set to 150.   -->
+
+
+```{r eval=F, echo=F, message=FALSE, warning=FALSE, out.width = "75%", out.height="75%"}
+staff_calc(daily_cases = 150)
+```
+
+```{r, eval=F, echo=F}
+case_incidence <- tibble(
+  dates = seq.Date(from = as.Date("2020-05-01"), to = as.Date("2020-05-21"), by = 1),
+  projected_incidence = c(102,110,50,37,106,190,146,138,135,111,60,43,189,184,185,80,44,97,254,291,288),
+  staff_needed = staff_calc(projected_incidence)
+)
+
+ggplot(case_incidence, aes(x = dates))+
+  geom_line(aes(y = projected_incidence))+
+  geom_line(aes(y = staff_needed))
+```
+
+
+<!-- There are many other nuances to understand when writing functions, as discussed in the page [Writing functions].   -->
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+## Packages {#packages}
+
+**Packages contain functions.**
+
+An R package is a shareable bundle of code and documentation that contains pre-defined functions. Users in the R community develop packages all the time catered to specific problems, it is likely that one can help with your work! You will install and use hundreds of packages in your use of R.
+
+On installation, R contains **"base"** packages and functions that perform common elementary tasks. But many R users create specialized functions, which are verified by the R community and which you can download as a **package** for your own use. In this handbook, package names are written in **bold**. One of the more challenging aspects of R is that there are often many functions or packages to choose from to complete a given task.
+
+### Install and load {.unnumbered}
+
+*Functions* are contained within **packages** which can be downloaded ("installed") to your computer from the internet. Once a package is downloaded, it is stored in your "library". You can then access the functions it contains during your current R session by "loading" the package.
+
+*Think of R as your personal library*: When you download a package, your library gains a new book of functions, but each time you want to use a function in that book, you must borrow,"load", that book from your library.
+
+In summary: to use the functions available in an R package, 2 steps must be implemented:
+
+1)  The package must be **installed** (once), *and*\
+2)  The package must be **loaded** (each R session)
+
+#### Your library {.unnumbered}
+
+Your "library" is actually a folder on your computer, containing a folder for each package that has been installed. Find out where R is installed in your computer, and look for a folder called "win-library". For example: `R\win-library\4.4.1` (the 4.4.1 is the R version - you'll have a different library for each R version you've downloaded).
+
+You can print the file path to your library by entering `.libPaths()` (empty parentheses). This becomes especially important if working with [R on network drives](network_drives.qmd).
+
+#### Install from CRAN {.unnumbered}
+
+Most often, R users download packages from CRAN. CRAN (Comprehensive R Archive Network) is an online public warehouse of R packages that have been published by R community members.
+
+Are you worried about viruses and security when downloading a package from CRAN? Read [this article](https://support.rstudio.com/hc/en-us/articles/360042593974-R-and-R-Package-Security) on the topic.
+
+#### How to install and load {.unnumbered}
+
+In this handbook, we suggest using the **pacman** package (short for "package manager"). It offers a convenient function `p_load()` which will install a package if necessary *and* load it for use in the current R session.
+
+The syntax quite simple. Just list the names of the packages within the `p_load()` parentheses, separated by commas. This command will install the **rio**, **tidyverse**, and **here** packages if they are not yet installed, and will load them for use. This makes the `p_load()` approach convenient and concise if sharing scripts with others. 
+
+Note that package names are case-sensitive.
+
+
+```{r}
+# Install (if necessary) and load packages for use
+pacman::p_load(rio, tidyverse, here)
+```
+
+
+Here we have used the syntax `pacman::p_load()` which explicitly writes the package name (**pacman**) prior to the function name (`p_load()`), connected by two colons `::`. This syntax is useful because it also loads the **pacman** package (assuming it is already installed).
+
+There are alternative **base** R functions that you will see often. The **base** R function for installing a package is `install.packages()`. The name of the package to install must be provided in the parentheses *in quotes*. If you want to install multiple packages in one command, they must be listed within a character vector `c()`.
+
+Note: this command *installs* a package, but does *not* load it for use in the current session.
+
+
+```{r, eval=F}
+# install a single package with base R
+install.packages("tidyverse")
+
+# install multiple packages with base R
+install.packages(c("tidyverse", "rio", "here"))
+```
+
+
+Installation can also be accomplished point-and-click by going to the RStudio "Packages" pane and clicking "Install" and searching for the desired package name.
+
+The **base** R function to **load** a package for use (after it has been installed) is `library()`. It can load only one package at a time (another reason to use `p_load()`). You can provide the package name with or without quotes.
+
+
+```{r, eval=F}
+# load packages for use, with base R
+library(tidyverse)
+library(rio)
+library(here)
+```
+
+
+To check whether a package in installed or loaded, you can view the Packages pane in RStudio. If the package is installed, it is shown there with version number. If its box is checked, it is loaded for the current session.
+
+**Install from Github**
+
+Sometimes, you need to install a package that is not yet available from CRAN. Or perhaps the package is available on CRAN but you want the *development version* with new features not yet offered in the more stable published CRAN version. These are often hosted on the website [github.com](https://github.com/) in a free, public-facing code "repository". Read more about Github in the handbook page on [Version control and collaboration with Git and Github](https://epirhandbook.com/new_pages/collaboration.html).
+
+To download R packages from Github, you can use the function `p_load_gh()` from **pacman**, which will install the package if necessary, and load it for use in your current R session. Alternatives to install include using the **remotes** or **devtools** packages. Read more about all the **pacman** functions in the [package documentation](https://cran.r-project.org/web/packages/pacman/pacman.pdf).
+
+To install from Github, you have to provide more information. You must provide:
+
+1)  The Github ID of the repository owner
+2)  The name of the repository that contains the package\
+3)  Optional: *The name of the "branch" (specific development version) you want to download*
+
+In the examples below, the first word in the quotation marks is the Github ID of the repository owner, after the slash is the name of the repository (the name of the package).
+
+
+```{r, eval=F}
+# install/load the epicontacts package from its Github repository
+p_load_gh("reconhub/epicontacts")
+```
+
+
+If you want to install from a "branch" (version) other than the main branch, add the branch name after an "\@", after the repository name.
+
+
+```{r, eval=F}
+# install the "timeline" branch of the epicontacts package from Github
+p_load_gh("reconhub/epicontacts@timeline")
+```
+
+
+If there is no difference between the Github version and the version on your computer, no action will be taken. You can "force" a re-install by instead using `p_load_current_gh()` with the argument `update = TRUE`. Read more about **pacman** in this [online vignette](http://trinker.github.io/pacman/vignettes/Introduction_to_pacman.html)
+
+**Install from ZIP or TAR**
+
+You could install the package from a URL:
+
+
+```{r, eval=F}
+packageurl <- "https://cran.r-project.org/src/contrib/Archive/dsr/dsr_0.2.2.tar.gz"
+install.packages(packageurl, repos=NULL, type="source")
+```
+
+
+Or, download it to your computer in a zipped file:
+
+Option 1: using `install_local()` from the **remotes** package
+
+
+```{r, eval=F}
+remotes::install_local("~/Downloads/dplyr-master.zip")
+```
+
+
+Option 2: using `install.packages()` from **base** R, providing the file path to the ZIP file and setting `type = "source` and `repos = NULL`.
+
+
+```{r, eval=F}
+install.packages("~/Downloads/dplyr-master.zip", repos=NULL, type="source")
+```
+
+
+### Code syntax {.unnumbered}
+
+For clarity in this handbook, functions are sometimes preceded by the name of their package using the `::` symbol in the following way: `package_name::function_name()`
+
+Once a package is loaded for a session, this explicit style is not necessary. One can just use `function_name()`. However writing the package name is useful when a function name is common and may exist in multiple packages (e.g. `plot()`). Writing the package name will also load the package if it is not already loaded.
+
+
+```{r eval=FALSE}
+# This command uses the package "rio" and its function "import()" to import a dataset
+linelist <- rio::import("linelist.xlsx", which = "Sheet1")
+```
+
+
+### Function help {.unnumbered}
+
+To read more about a function, you can search for it in the Help tab of the lower-right RStudio. You can also run a command like `?thefunctionname` (for example, to get help for the function `p_load` you would write `?p_load`) and the Help page will appear in the Help pane. Finally, try searching online for resources.
+
+### Update packages {.unnumbered}
+
+You can update packages by re-installing them. You can also click the green "Update" button in your RStudio Packages pane to see which packages have new versions to install. Be aware that your old code may need to be updated if there is a major revision to how a function works!
+
+### Delete packages {.unnumbered}
+
+Use `p_delete()` from **pacman**, or `remove.packages()` from **base** R.
+
+### Dependencies {.unnumbered}
+
+Packages often depend on other packages to work. These are called dependencies. If a dependency fails to install, then the package depending on it may also fail to install.
+
+See the dependencies of a package with `p_depends()`, and see which packages depend on it with `p_depends_reverse()`
+
+### Masked functions {.unnumbered}
+
+It is not uncommon that two or more packages contain the same function name. For example, the package **dplyr** has a `filter()` function, but so does the package **stats**. The default `filter()` function depends on the order these packages are first loaded in the R session - the later one will be the default for the command `filter()`.
+
+You can check the order in your Environment pane of R Studio - click the drop-down for "Global Environment" and see the order of the packages. Functions from packages *lower* on that drop-down list will mask functions of the same name in packages that appear higher in the drop-down list. When first loading a package, R will warn you in the console if masking is occurring, but this can be easy to miss.
+
+
+```{r out.width = "50%", fig.align = "center", echo=F}
+knitr::include_graphics(here::here("images", "masking_functions.png"))
+```
+
+
+Here are ways you can fix masking:
+
+1)  Specify the package name in the command. For example, use `dplyr::filter()`\
+2)  Re-arrange the order in which the packages are loaded (e.g. within `p_load()`), and **start a new R session**
+
+### Detach / unload {.unnumbered}
+
+To detach (unload) a package, use this command, with the correct package name and only one colon. Note that this may not resolve masking.
+
+
+```{r, eval=F}
+detach(package:PACKAGE_NAME_HERE, unload=TRUE)
+```
+
+
+### Install older version {.unnumbered}
+
+See this [guide](https://support.rstudio.com/hc/en-us/articles/219949047-Installing-older-versions-of-packages) to install an older version of a particular package.
+
+### Suggested packages {.unnumbered}
+
+See the page on [Suggested packages](packages_suggested.qmd) for a listing of packages we recommend for everyday epidemiology.
+
+<!-- ======================================================= -->
+
+## Scripts {#scripts}
+
+Scripts are a fundamental part of programming. They are documents that hold your commands (e.g. functions to create and modify datasets, print visualizations, etc). You can save a script and run it again later. There are many advantages to storing and running your commands from a script (vs. typing commands one-by-one into the R console "command line"):
+
+-   Portability - you can share your work with others by sending them your scripts.\
+-   Reproducibility - so that you and others know exactly what you did.\
+-   Version control - so you can track changes made by yourself or colleagues.\
+-   Commenting/annotation - to explain to your colleagues what you have done.
+
+### Commenting {.unnumbered}
+
+In a script you can also annotate ("comment") around your R code. Commenting is helpful to explain to yourself and other readers what you are doing. You can add a comment by typing the hash symbol (\#) and writing your comment after it. The commented text will appear in a different color than the R code.
+
+Any code written after the \# will not be run. Therefore, placing a \# before code is also a useful way to temporarily block a line of code ("comment out") if you do not want to delete it. You can comment out/in multiple lines at once by highlighting them and pressing Ctrl+Shift+c (Cmd+Shift+c in Mac).
+
+
+```{r, eval = F}
+# A comment can be on a line by itself
+# import data
+linelist <- import("linelist_raw.xlsx") %>%   # a comment can also come after code
+# filter(age > 50)                          # It can also be used to deactivate / remove a line of code
+  count()
+
+```
+
+
+There are a few general ideas to follow when writing your scripts in order to make them accessible.
+-   Add comments on *what* you are doing *and on **why** you are doing it*.\
+-   Break your code into logical sections.\
+-   Accompany your code with a text step-by-step description of what you are doing (e.g. numbered steps).
+
+### Style {.unnumbered}
+
+It is important to be conscious of your coding style - especially if working on a team. We advocate for the **tidyverse** [style guide](https://style.tidyverse.org/). There are also packages such as **styler** and **lintr** which help you conform to this style.
+
+A few very basic points to make your code readable to others:\
+\* When naming objects, use only lowercase letters, numbers, and underscores `_`, e.g. `my_data`\
+\* Use frequent spaces, including around operators, e.g. `n = 1` and `age_new <- age_old + 3`
+
+### Example Script {.unnumbered}
+
+Below is an example of a short R script. Remember, the better you succinctly explain your code in comments, the more your colleagues will like you!
+
+
+```{r out.width = "100%", fig.align = "center", echo=F}
+knitr::include_graphics(here::here("images", "example_script.png"))
+```
+
+
+<!-- ======================================================= -->
+
+### R markdown and Quarto {.unnumbered}
+
+An [R Markdown](https://rmarkdown.rstudio.com/) or [Quarto](https://quarto.org/docs/computations/r.html) script are types of R script in which the script itself *becomes* an output document (PDF, Word, HTML, Powerpoint, etc.). These are incredibly useful and versatile tools often used to create dynamic and automated reports. 
+
+Even this website and handbook is produced with Quarto scripts!
+
+It is worth noting that beginner R users can also use R Markdown - do not be intimidated! To learn more, see the handbook page on [Reports with R Markdown](rmarkdown.qmd) documents.
+
+<!-- ======================================================= -->
+
+### R notebooks {.unnumbered}
+
+There is no difference between writing in a Rmarkdown vs an R notebook. However the execution of the document differs slightly. See this [site](http://uc-r.github.io/r_notebook) for more details.
+
+<!-- ======================================================= -->
+
+### Shiny {.unnumbered}
+
+Shiny apps/websites are contained within one script, which must be named `app.R`. This file has three components:
+
+1)  A user interface (ui).\
+2)  A server function.\
+3)  A call to the `shinyApp` function.
+
+See the handbook page on [Dashboards with Shiny](shiny_basics.qmd), or this online tutorial: [Shiny tutorial](https://shiny.rstudio.com/tutorial/written-tutorial/lesson1/)
+
+*In previous versions, the above file was split into two files (`ui.R` and `server.R`)*
+
+### Code folding {.unnumbered}
+
+You can collapse portions of code to make your script easier to read.
+
+To do this, create a text header with \#, write your header, and follow it with at least 4 of either dashes (-), hashes (\#) or equals (=). When you have done this, a small arrow will appear in the "gutter" to the left (by the row number). You can click this arrow and the code below until the next header will collapse and a dual-arrow icon will appear in its place.
+
+To expand the code, either click the arrow in the gutter again, or the dual-arrow icon. There are also keyboard shortcuts as explained in the [RStudio section](#rstudio) of this page.
+
+By creating headers with \#, you will also activate the Table of Contents at the bottom of your script (see below) that you can use to navigate your script. You can create sub-headers by adding more \# symbols, for example \# for primary, \#\# for secondary, and \#\#\# for tertiary headers.
+
+Below are two versions of an example script. On the left is the original with commented headers. On the right, four dashes have been written after each header, making them collapsible. Two of them have been collapsed, and you can see that the Table of Contents at the bottom now shows each section.
+
+
+```{r, out.width = c('50%'), fig.show='hold', echo=F}
+knitr::include_graphics(here::here("images", "code_folding1.png"))
+knitr::include_graphics(here::here("images", "code_folding2.png"))
+```
+
+
+Other areas of code that are automatically eligible for folding include "braced" regions with brackets `{ }` such as function definitions or conditional blocks (if else statements). You can read more about code folding at the RStudio [site](https://support.rstudio.com/hc/en-us/articles/200484568-Code-Folding-and-Sections).
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+## Working directory
+
+The working directory is the root folder location used by R for your work - where R looks for and saves files by default. By default, it will save new files and outputs to this location, and will look for files to import (e.g. datasets) here as well.
+
+The working directory appears in grey text at the top of the RStudio Console pane. You can also print the current working directory by running `getwd()` (leave the parentheses empty).
+
+
+```{r out.width = "100%", fig.align = "center", echo=F}
+knitr::include_graphics(here::here("images", "working_directory_1.png"))
+```
+
+
+### Recommended approach {.unnumbered}
+
+**See the page on [R projects](r_projects.qmd) for details on our recommended approach to managing your working directory.**\
+
+A common, efficient, and trouble-free way to manage your working directory and file paths is to combine these 3 elements in an [R project](r_projects.qmd)-oriented workflow:
+
+1)  An R Project to store all your files (see page on [R projects](r_projects.qmd))\
+2)  The **here** package to locate files (see page on [Import and export](importing.qmd))\
+3)  The **rio** package to import/export files (see page on [Import and export](importing.qmd))
+
+<!-- ======================================================= -->
+
+### Set by command {.unnumbered}
+
+Until recently, many people learning R were taught to begin their scripts with a `setwd()` command. 
+
+Please instead consider using an [R project](r_projects.qmd)-oriented workflow and read the [reasons for not using `setwd()`](https://www.tidyverse.org/blog/2017/12/workflow-vs-script/). 
+
+In brief, your work becomes specific to your computer. This means that file paths used to import and export files need to be changed if used on a different computer, or by different collaborators.
+
+As noted above, although we do not recommend this approach in most circumstances, you can use the command `setwd()` with the desired folder file path in quotations, for example:
+
+
+```{r, eval=F}
+setwd("C:/Documents/R Files/My analysis")
+```
+
+
+[***DANGER:*** Setting a working directory with `setwd()` *can* be "brittle" if the file path is specific to one computer. Instead, use file paths relative to an R Project root directory, such as with the [**here** package]. ]{style="color: red;"}
+
+<!-- ======================================================= -->
+
+### Set manually {.unnumbered}
+
+To set the working directory manually (the point-and-click equivalent of `setwd()`), click the Session drop-down menu and go to "Set Working Directory" and then "Choose Directory". This will set the working directory for that specific R session. Note: if using this approach, you will have to do this manually each time you open RStudio.
+
+<!-- ======================================================= -->
+
+### Within an R project {.unnumbered}
+
+If using an R project, the working directory will default to the R project root folder that contains the ".rproj" file. This will apply if you open RStudio by clicking open the R Project (the file with ".rproj" extension).
+
+<!-- ======================================================= -->
+
+### Working directory in an R markdown {.unnumbered}
+
+In an R markdown script, the default working directory is the folder the Rmarkdown file (`.Rmd`) is saved within. If using an R project and **here** package, this does not apply and the working directory will be `here()` as explained in the [R projects](r_projects.qmd) page.
+
+If you want to change the working directory of a stand-alone R markdown (not in an R project), if you use `setwd()` this will only apply to that specific code chunk. To make the change for all code chunks in an R markdown, edit the setup chunk to add the `root.dir =` parameter, such as below:
+
+
+```{r, eval=F}
+knitr::opts_knit$set(root.dir = 'desired/directorypath')
+```
+
+
+It is much easier to just use the R markdown within an R project and use the **here** package.
+
+<!-- ======================================================= -->
+
+### Providing file paths {.unnumbered}
+
+Perhaps the most common source of frustration for an R beginner (at least on a Windows machine) is typing in a file path to import or export data. There is a thorough explanation of how to best input file paths in the [Import and export](importing.qmd) page, but here are a few key points:
+
+**Broken paths**
+
+Below is an example of an "absolute" or "full address" file path. These will likely break if used by another computer. One exception is if you are using a shared/network drive.
+
+    C:/Users/Name/Document/Analytic Software/R/Projects/Analysis2019/data/March2019.csv  
+
+**Slash direction**
+
+*If typing in a file path, be aware the direction of the slashes.* 
+
+Use *forward slashes* (`/`) to separate the components ("data/provincial.csv"). For Windows users, the default way that file paths are displayed is with *back slashes* (\\) - so you will need to change the direction of each slash. If you use the **here** package as described in the [R projects](r_projects.qmd) page the slash direction is not an issue.
+
+**Relative file paths**
+
+We generally recommend providing "relative" filepaths instead - that is, the path *relative to* the root of your R Project. You can do this using the **here** package as explained in the [R projects](r_projects.qmd) page. A relativel filepath might look like this:
+
+
+```{r, eval=F}
+# Import csv linelist from the data/linelist/clean/ sub-folders of an R project
+linelist <- import(here("data", "clean", "linelists", "marin_country.csv"))
+```
+
+
+Even if using relative file paths within an R project, you can still use absolute paths to import and export data outside your R project.
+
+<!-- ======================================================= -->
+
+## Objects {#objects}
+
+Everything in R is an object, and R is an "object-oriented" language. These sections will explain:
+
+-   How to create objects (`<-`).
+-   Types of objects (e.g. data frames, vectors..).\
+-   How to access subparts of objects (e.g. variables in a dataset).\
+-   Classes of objects (e.g. numeric, logical, integer, double, character, factor).
+
+<!-- ======================================================= -->
+
+### Everything is an object {.unnumbered}
+
+*This section is adapted from the [R4Epis project](https://r4epis.netlify.app/training/r_basics/objects/).*\
+
+Everything you store in R - datasets, variables, a list of village names, a total population number, even outputs such as graphs - are **objects** which are **assigned a name** and **can be referenced** in later commands.
+
+An object exists when you have assigned it a value (see the assignment section below). When it is assigned a value, the object appears in the Environment (see the upper right pane of RStudio). It can then be operated upon, manipulated, changed, and re-defined.
+
+<!-- ======================================================= -->
+
+### Defining objects (`<-`) {.unnumbered}
+
+**Create objects *by assigning them a value* with the \<- operator.**\
+You can think of the assignment operator `<-` as the words "is defined as". Assignment commands generally follow a standard order:
+
+**object_name** \<- **value** (or process/calculation that produce a value)
+
+For example, you may want to record the current epidemiological reporting week as an object for reference in later code. In this example, the object `current_week` is created when it is assigned the value `"2018-W10"` (the quote marks make this a character value). The object `current_week` will then appear in the RStudio Environment pane (upper-right) and can be referenced in later commands.
+
+See the R commands and their output in the boxes below.
+
+
+```{r basics_objects_assignment}
+current_week <- "2018-W10"   # this command creates the object current_week by assigning it a value
+current_week                 # this command prints the current value of current_week object in the console
+```
+
+
+[***NOTE:*** Note the `[1]` in the R console output is simply indicating that you are viewing the first item of the output]{style="color: black;"}
+
+[***CAUTION:*** **An object's value can be over-written** at any time by running an assignment command to re-define its value. Thus, the **order of the commands run is very important**.]{style="color: orange;"}
+
+The following command will re-define the value of `current_week`:
+
+
+```{r basics_objects_reassignment}
+current_week <- "2018-W51"   # assigns a NEW value to the object current_week
+current_week                 # prints the current value of current_week in the console
+```
+
+
+**Equals signs `=`**
+
+You will also see equals signs in R code:
+
+-   A double equals sign `==` between two objects or values asks a logical *question*: "is this equal to that?".\
+-   You will also see equals signs within functions used to specify values of function arguments (read about these in sections below), for example `max(age, na.rm = TRUE)`.\
+-   You *can* use a single equals sign `=` in place of `<-` to create and define objects, but this is discouraged. You can read about why this is discouraged [here](https://renkun.me/2014/01/28/difference-between-assignment-operators-in-r/).
+
+**Datasets**
+
+Datasets are also objects (typically "data frames") and must be assigned names when they are imported. In the code below, the object `linelist` is created and assigned the value of a CSV file imported with the **rio** package and its `import()` function.
+
+
+```{r basics_objects_data frames, eval=FALSE}
+# linelist is created and assigned the value of the imported CSV file
+linelist <- import("my_linelist.csv")
+```
+
+
+You can read more about importing and exporting datasets with the section on [Import and export](importing.qmd).
+
+[***CAUTION:*** A quick note on naming of objects:]{style="color: orange;"}
+
+-   Object names must not contain spaces, but you should use underscore (\_) or a period (.) instead of a space.\
+-   Object names are case-sensitive (meaning that Dataset_A is different from dataset_A).
+-   Object names must begin with a letter (they cannot begin with a number like 1, 2 or 3).
+
+**Outputs**
+
+Outputs like tables and plots provide an example of how outputs can be saved as objects, or just be printed without being saved. A cross-tabulation of gender and outcome using the **base** R function `table()` can be printed directly to the R console (*without* being saved).
+
+
+```{r}
+# printed to R console only
+table(linelist$gender, linelist$outcome)
+```
+
+
+But the same table can be saved as a named object. Then, optionally, it can be printed.
+
+
+```{r}
+# save
+gen_out_table <- table(linelist$gender, linelist$outcome)
+
+# print
+gen_out_table
+```
+
+
+**Columns**
+
+Columns in a dataset are also objects and can be defined, over-written, and created as described below in the section on [Columns](https://epirhandbook.com/new_pages/basics.html#columnsvariables).
+
+You can use the assignment operator from **base** R to create a new column. Below, the new column `bmi` (Body Mass Index) is created, and for each row the new value is result of a mathematical operation on the row's value in the `wt_kg` and `ht_cm` columns.
+
+
+```{r, eval=F}
+# create new "bmi" column using base R syntax
+linelist$bmi <- linelist$wt_kg / (linelist$ht_cm/100)^2
+```
+
+
+However, in this handbook, we emphasize a different approach to defining columns, which uses the function `mutate()` from the **dplyr** package and *piping* with the pipe operator (`%>%`). The syntax is easier to read and there are other advantages explained in the page on [Cleaning data and core functions](cleaning.qmd). You can read more about *piping* in the Piping section below.
+
+
+```{r, eval=F}
+# create new "bmi" column using dplyr syntax
+linelist <- linelist %>% 
+  mutate(bmi = wt_kg / (ht_cm/100)^2)
+```
+
+
+<!-- ======================================================= -->
+
+### Object structure {.unnumbered}
+
+**Objects can be a single piece of data (e.g. `my_number <- 24`), or they can consist of structured data.**
+
+The graphic below is borrowed from [this online R tutorial](http://venus.ifca.unican.es/Rintro/dataStruct.html). It shows some common data structures and their names. Not included in this image is spatial data, which is discussed in the [GIS basics](gis.qmd) page.
+
+
+```{r basics_objects_structures, echo=F, out.width = "75%", out.height="50%", fig.align = "center"}
+knitr::include_graphics(here::here("images", "R_data_structures.png"))
+```
+
+
+In epidemiology (and particularly field epidemiology), you will *most commonly* encounter data frames and vectors:
+
++------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+
+| Common structure | Explanation                                                                                      | Example                                                                             |
++------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+
+
+| Vectors          | A container for a sequence of singular objects, all of the same class (e.g. numeric, character). | **"Variables" (columns) in data frames are vectors** (e.g. the column `age_years`). |
++------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+
+| Data Frames      | Vectors (e.g. columns) that are bound together that all have the same number of rows.            | `linelist` is a data frame.                                                         |
++------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+
+
+Note that to create a vector that "stands alone" (is not part of a data frame) the function `c()` is used to combine the different elements. For example, if creating a vector of colors plot's color scale: `vector_of_colors <- c("blue", "red2", "orange", "grey")`
+
+<!-- ======================================================= -->
+
+### Object classes {.unnumbered}
+
+All the objects stored in R have a *class* which tells R how to handle the object. There are many possible classes, but common ones include:
+
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| Class      | Explanation                                                                                                                                                                             | Examples                                                                                              |
++============+=========================================================================================================================================================================================+=======================================================================================================+
+| Character  | These are text/words/sentences **"within quotation marks"**. Math cannot be done on these objects.                                                                                      | "Character objects are in quotation marks"                                                            |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| Integer    | Numbers that are **whole only** (no decimals)                                                                                                                                           | -5, 14, or 2000                                                                                       |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| Numeric    | These are numbers and **can include decimals**. If within quotation marks they will be considered character class.                                                                      | 23.1 or 14                                                                                            |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| Factor     | These are vectors that have a **specified order** or hierarchy of values                                                                                                                | An variable of economic status with ordered values                                                    |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| Date       | **Once R is told that certain data are Dates**, these data can be manipulated and displayed in special ways. See the page on [Working with dates](dates.qmd) for more information.      | 2018-04-12 or 15/3/1954 or Wed 4 Jan 1980                                                           
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| Logical    | Values must be one of the two special values TRUE or FALSE (note these are **not** "TRUE" and "FALSE" in quotation marks)                                                               | TRUE or FALSE                                                                                         |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| data.frame | A data frame is how R stores a **typical dataset**. It consists of vectors (columns) of data bound together, that all have the same number of observations (rows).                      | The example AJS dataset named `linelist_raw` contains 68 variables with 300 observations (rows) each. |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| tibble     | tibbles are a variation on data frame, the main operational difference being that they print more nicely to the console (display first 10 rows and only columns that fit on the screen) | Any data frame, list, or matrix can be converted to a tibble with `as_tibble()`                       |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+| list       | A list is like vector, but holds other objects that can be other different classes                                                                                                      | A list could hold a single number, and a data frame, and a vector, and even another list within it!    |
++------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+
+
+**You can test the class of an object by providing its name to the function `class()`**. Note: you can reference a specific column within a dataset using the `$` notation to separate the name of the dataset and the name of the column.
+
+
+```{r, echo=TRUE,}
+class(linelist)         # class should be a data frame or tibble
+
+class(linelist$age)     # class should be numeric
+
+class(linelist$gender)  # class should be character
+```
+
+
+Sometimes, a column will be converted to a different class automatically by R. Watch out for this! For example, if you have a vector or column of numbers, but a character value is inserted... the entire column will change to class character.
+
+
+```{r}
+num_vector <- c(1, 2 , 3, 4, 5) # define vector as all numbers
+class(num_vector)          # vector is numeric class
+num_vector[3] <- "three"   # convert the third element to a character
+class(num_vector)          # vector is now character class
+```
+
+
+One common example of this is when manipulating a data frame in order to print a table - if you make a total row and try to paste/glue together percents in the same cell as numbers (e.g. `23 (40%)`), the entire numeric column above will convert to character and can no longer be used for mathematical calculations.**Sometimes, you will need to convert objects or columns to another class.**
+
++------------------+---------------------------------------------------------------------------------------+
+| Function         | Action                                                                                |
++==================+=======================================================================================+
+| `as.character()` | Converts to character class                                                           |
++------------------+---------------------------------------------------------------------------------------+
+| `as.numeric()`   | Converts to numeric class                                                             |
++------------------+---------------------------------------------------------------------------------------+
+| `as.integer()`   | Converts to integer class                                                             |
++------------------+---------------------------------------------------------------------------------------+
+| `as.Date()`      | Converts to Date class - Note: see section on [dates](dates.qmd) for details          |
++------------------+---------------------------------------------------------------------------------------+
+| `factor()`       | Converts to factor - Note: re-defining order of value levels requires extra arguments |
++------------------+---------------------------------------------------------------------------------------+
+
+Likewise, there are **base** R functions to check whether an object IS of a specific class, such as `is.numeric()`, `is.character()`, `is.double()`, `is.factor()`, `is.integer()`
+
+Here is [more online material on classes and data structures in R](https://swcarpentry.github.io/r-novice-inflammation/13-supp-data-structures.html).
+
+<!-- ======================================================= -->
+
+### Columns/Variables (`$`) {.unnumbered}
+
+**A column in a data frame is technically a "vector" (see table above)** - a series of values that must all be the same class (either character, numeric, logical, etc).
+
+A vector can exist independent of a data frame, for example a vector of column names that you want to include as explanatory variables in a model. To create a "stand alone" vector, use the `c()` function as below:
+
+
+```{r, warning=F, message=F}
+# define the stand-alone vector of character values
+explanatory_vars <- c("gender", "fever", "chills", "cough", "aches", "vomit")
+
+# print the values in this named vector
+explanatory_vars
+```
+
+
+**Columns in a data frame are also vectors and can be called, referenced, extracted, or created using the `$` symbol.** The `$` symbol connects the name of the column to the name of its data frame. In this handbook, we try to use the word "column" instead of "variable".
+
+
+```{r basics_objects_call, eval=F}
+# Retrieve the length of the vector age_years
+length(linelist$age) # (age is a column in the linelist data frame)
+
+```
+
+
+By typing the name of the data frame followed by `$` you will also see a drop-down menu of all columns in the data frame. You can scroll through them using your arrow key, select one with your Enter key, and avoid spelling mistakes!
+
+
+```{r echo=F, out.width = "100%", fig.align = "center"}
+knitr::include_graphics(here::here("images", "Calling_Names.gif"))
+```
+
+
+[***ADVANCED TIP:*** Some more complex objects (e.g. a list, or an `epicontacts` object) may have multiple levels which can be accessed through multiple dollar signs. For example `epicontacts$linelist$date_onset`]{style="color: darkgreen;"}
+
+<!-- ======================================================= -->
+
+### Access/index with brackets (`[ ]`) {.unnumbered}
+
+You may need to view parts of objects, also called "indexing", which is often done using the square brackets `[ ]`. Using `$` on a data frame to access a column is also a type of indexing.
+
+
+```{r}
+my_vector <- c("a", "b", "c", "d", "e", "f")  # define the vector
+my_vector[5]                                  # print the 5th element
+```
+
+
+Square brackets also work to return specific parts of an returned output, such as the output of a `summary()` function:
+
+
+```{r}
+# All of the summary
+summary(linelist$age)
+
+# Just the second element of the summary, with name (using only single brackets)
+summary(linelist$age)[2]
+
+# Just the second element, without name (using double brackets)
+summary(linelist$age)[[2]]
+
+# Extract an element by name, without showing the name
+summary(linelist$age)[["Median"]]
+
+```
+
+
+Brackets also work on data frames to view specific rows and columns. You can do this using the syntax `data frame[rows, columns]`:
+
+
+```{r basics_objects_access, eval=F}
+# View a specific row (2) from dataset, with all columns (don't forget the comma!)
+linelist[2,]
+
+# View all rows, but just one column
+linelist[, "date_onset"]
+
+# View values from row 2 and columns 5 through 10
+linelist[2, 5:10] 
+
+# View values from row 2 and columns 5 through 10 and 18
+linelist[2, c(5:10, 18)] 
+
+# View rows 2 through 20, and specific columns
+linelist[2:20, c("date_onset", "outcome", "age")]
+
+# View rows and columns based on criteria
+# *** Note the data frame must still be named in the criteria!
+linelist[linelist$age > 25 , c("date_onset", "outcome", "age")]
+
+# Use View() to see the outputs in the RStudio Viewer pane (easier to read) 
+# *** Note the capital "V" in View() function
+View(linelist[2:20, "date_onset"])
+
+# Save as a new object
+new_table <- linelist[2:20, c("date_onset")] 
+```
+
+
+Note that you can also achieve the above row/column indexing on data frames and tibbles using **dplyr** syntax (functions `filter()` for rows, and `select()` for columns). Read more about these core functions in the [Cleaning data and core functions](cleaning.qmd) page.
+
+To filter based on "row number", you can use the **dplyr** function `row_number()` with open parentheses as part of a logical filtering statement. Often you will use the `%in%` operator and a range of numbers as part of that logical statement, as shown below. To see the *first* N rows, you can also use the special **dplyr** function `head()`. Note, there is a function `head()` from **base** R, but this is overwritten by the **dplyr** function when you load **tidyverse**.
+
+
+```{r, eval=F}
+# View first 100 rows
+linelist %>% head(100)
+
+# Show row 5 only
+linelist %>% filter(row_number() == 5)
+
+# View rows 2 through 20, and three specific columns (note no quotes necessary on column names)
+linelist %>% 
+     filter(row_number() %in% 2:20) %>% 
+     select(date_onset, outcome, age)
+```
+
+
+When indexing an object of class **list**, single brackets always return with class list, even if only a single object is returned. Double brackets, however, can be used to access a single element and return a different class than list. Brackets can also be written after one another, as demonstrated below.
+
+This [visual explanation of lists indexing, with pepper shakers](https://r4ds.had.co.nz/vectors.html#lists-of-condiments) is humorous and helpful.
+
+
+```{r}
+# define demo list
+my_list <- list(
+  # First element in the list is a character vector
+  hospitals = c("Central", "Empire", "Santa Anna"),
+  
+  # second element in the list is a data frame of addresses
+  addresses   = data.frame(
+    street = c("145 Medical Way", "1048 Brown Ave", "999 El Camino"),
+    city   = c("Andover", "Hamilton", "El Paso")
+    )
+  )
+```
+
+
+Here is how the list looks when printed to the console. See how there are two named elements:
+
+-   `hospitals`, a character vector\
+-   `addresses`, a data frame of addresses
+
+
+```{r}
+my_list
+```
+
+
+Now we extract, using various methods:
+
+
+```{r}
+my_list[1] # this returns the element in class "list" - the element name is still displayed
+
+my_list[[1]] # this returns only the (unnamed) character vector
+
+my_list[["hospitals"]] # you can also index by name of the list element
+
+my_list[[1]][3] # this returns the third element of the "hospitals" character vector
+
+my_list[[2]][1] # This returns the first column ("street") of the address data frame
+
+```
+
+
+<!-- ======================================================= -->
+
+### Remove objects {.unnumbered}
+
+You can remove individual objects from your R environment by putting the name in the `rm()` function (no quote marks):
+
+
+```{r, eval=F}
+rm(object_name)
+```
+
+
+You can remove all objects (clear your workspace) by running:
+
+
+```{r, eval=F}
+rm(list = ls(all = TRUE))
+```
+
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+## Piping (`%>%`)
+
+**Two general approaches to working with objects are:**
+
+1)  **Pipes/tidyverse** - pipes send an object from function to function - emphasis is on the *action*, not the object.\
+2)  **Define intermediate objects** - an object is re-defined again and again - emphasis is on the object.
+
+<!-- ======================================================= -->
+
+### **Pipes** {.unnumbered}
+
+**Simply explained, the pipe operator passes an intermediate output from one function to the next.**\
+You can think of it as saying "and then". Many functions can be linked together with `%>%`.
+
+-   **Piping emphasizes a sequence of actions, not the object the actions are being performed on**.\
+-   Pipes are best when a sequence of actions must be performed on one object.\
+-   Pipes can make code more clean and easier to read, more intuitive.
+
+Pipe operators were first introduced through the [magrittr package](https://magrittr.tidyverse.org/), which is part of tidyverse, and were specified as `%>%`. In R 4.1.0, they introduced a **base** R pipe which is specified through `|>`. The behaviour of the two pipes is the same, and they can be used somewhat interchangeably. However, there are a few key differences.
+
+* The `%>%` pipe allows you to pass multiple arguments.
+* The `%>%` pipe lets you drop parenthesis when calling a function with no other arguments (i.e. drop vs drop()).
+* The `%>%` pipe allows you to start a pipe with `.` to create a function in your linking of code.
+
+For these reasons, we recommend the **magrittr** pipe, `%>%`, over the **base** R pipe, `|>`.
+
+To read more about the differences between base R and tidyverse (magrittr) pipes, see this [blog post](https://www.tidyverse.org/blog/2023/04/base-vs-magrittr-pipe/). For more information on the tidyverse approach, please see this [style guide](https://style.tidyverse.org/pipes.html).
+
+Here is a fake example for comparison, using fictional functions to "bake a cake". First, the pipe method:
+
+
+```{r piping_example_pipe, eval=F}
+# A fake example of how to bake a cake using piping syntax
+
+cake <- flour %>%       # to define cake, start with flour, and then...
+  add(eggs) %>%   # add eggs
+  add(oil) %>%    # add oil
+  add(water) %>%  # add water
+  mix_together(         # mix together
+    utensil = spoon,
+    minutes = 2) %>%    
+  bake(degrees = 350,   # bake
+       system = "fahrenheit",
+       minutes = 35) %>%  
+  let_cool()            # let it cool down
+```
+
+
+Note that just like other R commands, pipes can be used to just display the result, or to save/re-save an object, depending on whether the assignment operator `<-` is involved. See both below:
+
+
+```{r, eval=F}
+# Create or overwrite object, defining as aggregate counts by age category (not printed)
+linelist_summary <- linelist %>% 
+  count(age_cat)
+```
+
+```{r}
+# Print the table of counts in the console, but don't save it
+linelist %>% 
+  count(age_cat)
+```
+
+
+**`%<>%`**\
+This is an "assignment pipe" from the **magrittr** package, which *pipes an object forward and also re-defines the object*. It must be the first pipe operator in the chain. It is shorthand. The below two commands are equivalent:
+
+
+```{r, eval=F}
+linelist <- linelist %>%
+  filter(age > 50)
+
+linelist %<>% filter(age > 50)
+```
+
+
+<!-- ======================================================= -->
+
+### Define intermediate objects {.unnumbered}
+
+This approach to changing objects/data frames may be better if:
+
+-   You need to manipulate multiple objects\
+-   There are intermediate steps that are meaningful and deserve separate object names
+
+**Risks:**
+
+-   Creating new objects for each step means creating lots of objects. If you use the wrong one you might not realize it!\
+-   Naming all the objects can be confusing.\
+-   Errors may not be easily detectable.
+
+Either name each intermediate object, or overwrite the original, or combine all the functions together. All come with their own risks.
+
+Below is the same fake "cake" example as above, but using this style:
+
+
+```{r piping_example_redefine, eval=F}
+# a fake example of how to bake a cake using this method (defining intermediate objects)
+batter_1 <- left_join(flour, eggs)
+batter_2 <- left_join(batter_1, oil)
+batter_3 <- left_join(batter_2, water)
+
+batter_4 <- mix_together(object = batter_3, utensil = spoon, minutes = 2)
+
+cake <- bake(batter_4, degrees = 350, system = "fahrenheit", minutes = 35)
+
+cake <- let_cool(cake)
+```
+
+
+Combine all functions together - this is difficult to read:
+
+
+```{r eval=F}
+# an example of combining/nesting mutliple functions together - difficult to read
+cake <- let_cool(bake(mix_together(batter_3, utensil = spoon, minutes = 2), degrees = 350, system = "fahrenheit", minutes = 35))
+```
+
+
+<!-- ======================================================= -->
+
+## Key operators and functions {#operators}
+
+This section details operators in R, such as:
+
+-   Definitional operators.\
+-   Relational operators (less than, equal too..).\
+-   Logical operators (and, or...).\
+-   Handling missing values.\
+-   Mathematical operators and functions (+/-, \>, sum(), median(), ...).\
+-   The `%in%` operator.
+
+<!-- ======================================================= -->
+
+### Assignment operators {.unnumbered}
+
+**`<-`**
+
+The basic assignment operator in R is `<-`. Such that `object_name <- value`.\
+This assignment operator can also be written as `=`. We advise use of `<-` for general R use. We also advise surrounding such operators with spaces, for readability.
+
+**`<<-`**
+
+If [Writing functions](writing_functions.qmd), or using R in an interactive way with sourced scripts, then you may need to use this assignment operator `<<-` (from **base** R). This operator is used to define an object in a higher 'parent' R Environment. See this [online reference](https://stat.ethz.ch/R-manual/R-devel/library/base/html/assignOps.html).
+
+**`%<>%`**
+
+This is an "assignment pipe" from the **magrittr** package, which pipes an object forward and *also re-defines the object*. It must be the first pipe operator in the chain. It is shorthand, as shown below in two equivalent examples:
+
+
+```{r, eval=F}
+linelist <- linelist %>% 
+  mutate(age_months = age_years * 12)
+```
+
+
+The above is equivalent to the below:
+
+
+```{r, eval=F}
+linelist %<>% mutate(age_months = age_years * 12)
+```
+
+
+**`%<+%`**
+
+This is used to add data to phylogenetic trees with the **ggtree** package. See the page on [Phylogenetic trees](phylogenetic_trees.qmd) or this online [resource book](https://yulab-smu.top/treedata-book/).
+
+<!-- ======================================================= -->
+
+### Relational and logical operators {.unnumbered}
+
+Relational operators compare values and are often used when defining new variables and subsets of datasets. Here are the common relational operators in R:
+
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Meaning                  | Operator   | Example      | Example Result                                                                                                                                         |
++==========================+============+==============+========================================================================================================================================================+
+| Equal to                 | `==`       | `"A" == "a"` | `FALSE` (because R is case sensitive) *Note that == (double equals) is different from = (single equals), which acts like the assignment operator `<-`* |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Not equal to             | `!=`       | `2 != 0`     | `TRUE`                                                                                                                                                 |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Greater than             | `>`        | `4 > 2`      | `TRUE`                                                                                                                                                 |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Less than                | `<`        | `4 < 2`      | `FALSE`                                                                                                                                                |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Greater than or equal to | `>=`       | `6 >= 4`     | `TRUE`                                                                                                                                                 |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Less than or equal to    | `<=`       | `6 <= 4`     | `FALSE`                                                                                                                                                |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Value is missing         | `is.na()`  | `is.na(7)`   | `FALSE` (see page on [Missing data](missing_data.qmd))                                                                                                 |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+| Value is not missing     | `!is.na()` | `!is.na(7)`  | `TRUE`                                                                                                                                                 |
++--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+
+
+Logical operators, such as AND and OR, are often used to connect relational operators and create more complicated criteria. Complex statements might require parentheses `( )` for grouping and order of application.
+
++---------------------+-----------------------------------------------------------------------+
+| Meaning             | Operator                                                              |
++=====================+=======================================================================+
+| AND                 | `&`                                                                   |
++---------------------+-----------------------------------------------------------------------+
+| OR                  | `|` (vertical bar)                                                    |
++---------------------+-----------------------------------------------------------------------+
+| Parentheses         | `( )` Used to group criteria together and clarify order of operations |
++---------------------+-----------------------------------------------------------------------+
+
+For example, below, we have a linelist with two variables we want to use to create our case definition, `hep_e_rdt`, a test result and `other_cases_in_hh`, which will tell us if there are other cases in the household. The command below uses the function `case_when()` to create the new variable `case_def` such that:
+
+
+```{r eval=FALSE}
+linelist_cleaned <- linelist %>%
+  mutate(case_def = case_when(
+    is.na(rdt_result) & is.na(other_case_in_home)            ~ NA_character_,
+    rdt_result == "Positive"                                 ~ "Confirmed",
+    rdt_result != "Positive" & other_cases_in_home == "Yes"  ~ "Probable",
+    TRUE                                                     ~ "Suspected"
+  ))
+```
+
+
++------------------------------------------------------------------------------------------------+--------------------------------------------+
+| Criteria in example above                                                                      | Resulting value in new variable "case_def" |
++================================================================================================+============================================+
+| If the value for variables `rdt_result` and `other_cases_in_home` are missing                  | `NA` (missing)                             |
++------------------------------------------------------------------------------------------------+--------------------------------------------+
+| If the value in `rdt_result` is "Positive"                                                     | "Confirmed"                                |
++------------------------------------------------------------------------------------------------+--------------------------------------------+
+| If the value in `rdt_result` is NOT "Positive" AND the value in `other_cases_in_home` is "Yes" | "Probable"                                 |
++------------------------------------------------------------------------------------------------+--------------------------------------------+
+| If one of the above criteria are not met                                                       | "Suspected"                                |
++------------------------------------------------------------------------------------------------+--------------------------------------------+
+
+*Note that R is case-sensitive, so "Positive" is different than "positive".*
+
+<!-- ======================================================= -->
+
+### Missing values {.unnumbered}
+
+In R, missing values are represented by the special value `NA` (a "reserved" value) (capital letters N and A - not in quotation marks). If you import data that records missing data in another way (e.g. 99, "Missing"), you may want to re-code those values to `NA`. How to do this is addressed in the [Import and export](importing.qmd) page.
+
+**To test whether a value is `NA`, use the special function `is.na()`**, which returns `TRUE` or `FALSE`.
+
+
+```{r basics_operators_missing}
+rdt_result <- c("Positive", "Suspected", "Positive", NA)   # two positive cases, one suspected, and one unknown
+is.na(rdt_result)  # Tests whether the value of rdt_result is NA
+```
+
+
+Read more about missing, infinite, `NULL`, and impossible values in the page on [Missing data](missing_data.qmd). Learn how to convert missing values when importing data in the page on [Import and export](importing.qmd).
+
+<!-- ======================================================= -->
+
+### Mathematics and statistics {.unnumbered}
+
+All the operators and functions in this page are automatically available using **base** R.
+
+#### Mathematical operators {.unnumbered}
+
+These are often used to perform addition, division, to create new columns, etc. Below are common mathematical operators in R. Whether you put spaces around the operators is not important.
+
+| Purpose             | Example in R |
+|---------------------|--------------|
+| addition            | 2 + 3        |
+| subtraction         | 2 - 3        |
+| multiplication      | 2 \* 3       |
+| division            | 30 / 5       |
+| exponent            | 2\^3         |
+| order of operations | ( )          |
+
+#### Mathematical functions {.unnumbered}
+
+| Purpose            | Function                              |
+|--------------------|---------------------------------------|
+| rounding           | round(x, digits = n)                  |
+| rounding           | janitor::round_half_up(x, digits = n) |
+| ceiling (round up) | ceiling(x)                            |
+| floor (round down) | floor(x)                              |
+| absolute value     | abs(x)                                |
+| square root        | sqrt(x)                               |
+| exponent           | exponent(x)                           |
+| natural logarithm  | log(x)                                |
+| log base 10        | log10(x)                              |
+| log base 2         | log2(x)                               |
+
+Note: for `round()` the `digits =` specifies the number of decimal placed. Use `signif()` to round to a number of significant figures.
+
+#### Scientific notation {.unnumbered}
+
+The likelihood of scientific notation being used depends on the value of the `scipen` option.
+
+From the documentation of `?options`: scipen is a penalty to be applied when deciding to print numeric values in fixed or exponential notation. Positive values bias towards fixed and negative towards scientific notation: fixed notation will be preferred unless it is more than 'scipen' digits wider.
+
+If it is set to a low number (e.g. 0) it will be "turned on" always. To "turn off" scientific notation in your R session, set it to a very high number, for example:
+
+
+```{r, eval=F}
+# turn off scientific notation
+options(scipen = 999)
+```
+
+
+#### Rounding {.unnumbered}
+
+[***DANGER:*** `round()` uses "banker's rounding" which rounds up from a .5 only if the upper number is even. Use `round_half_up()` from **janitor** to consistently round halves up to the nearest whole number. See [this explanation](https://cran.r-project.org/web/packages/janitor/vignettes/janitor.html#explore-records-with-duplicated-values-for-specific-combinations-of-variables-with-get_dupes) ]{style="color: red;"}
+
+
+```{r}
+# use the appropriate rounding function for your work
+round(c(2.5, 3.5))
+
+janitor::round_half_up(c(2.5, 3.5))
+```
+
+
+#### Statistical functions {.unnumbered}
+
+[***CAUTION:*** The functions below will by default include missing values in calculations. Missing values will result in an output of `NA`, unless the argument `na.rm = TRUE` is specified. This can be written shorthand as `na.rm = T`.]{style="color: orange;"}
+
+| Objective               | Function             |
+|-------------------------|----------------------|
+| mean (average)          | mean(x, na.rm = T)   |
+| median                  | median(x, na.rm=  T) |
+| standard deviation      | sd(x, na.rm = T)     |
+| quantiles\*             | quantile(x, probs)   |
+| sum                     | sum(x, na.rm = T)    |
+| minimum value           | min(x, na.rm = T)    |
+| maximum value           | max(x, na.rm = T)    |
+| range of numeric values | range(x, na.rm = T)  |
+| summary\*\*             | summary(x)           |
+
+Notes:
+
+-   `*quantile()`: `x` is the numeric vector to examine, and `probs =` is a numeric vector with probabilities within 0 and 1.0, e.g `c(0.5, 0.8, 0.85)`.
+-   `**summary()`: gives a summary on a numeric vector including mean, median, and common percentiles.
+
+[***DANGER:*** If providing a vector of numbers to one of the above functions, be sure to wrap the numbers within `c()` .]{style="color: red;"}
+
+
+```{r}
+# If supplying raw numbers to a function, wrap them in c()
+mean(1, 6, 12, 10, 5, 0)    # !!! INCORRECT !!!  
+
+mean(c(1, 6, 12, 10, 5, 0)) # CORRECT
+```
+
+
+#### Other useful functions {.unnumbered}
+
++----------------------------+-------------------+-------------------------------------------------+
+| Objective                  | Function          | Example                                         |
++============================+===================+=================================================+
+| create a sequence          | seq(from, to, by) | `seq(1, 10, 2)`                                 |
++----------------------------+-------------------+-------------------------------------------------+
+| repeat x, n times          | rep(x, ntimes)    | `rep(1:3, 2)` or `rep(c("a", "b", "c"), 3)`     |
++----------------------------+-------------------+-------------------------------------------------+
+| subdivide a numeric vector | cut(x, n)         | `cut(linelist$age, 5)`                          |
++----------------------------+-------------------+-------------------------------------------------+
+| take a random sample       | sample(x, size)   | `sample(linelist$id, size = 5, replace = TRUE)` |
++----------------------------+-------------------+-------------------------------------------------+
+
+<!-- ======================================================= -->
+
+### `%in%` {.unnumbered}
+
+A very useful operator for matching values, and for quickly assessing if a value is within a vector or data frame.
+
+
+```{r}
+my_vector <- c("a", "b", "c", "d")
+```
+
+```{r}
+"a" %in% my_vector
+"h" %in% my_vector
+```
+
+
+To ask if a value is **not** `%in%` a vector, put an exclamation mark (!) **in front** of the logic statement:
+
+
+```{r}
+# to negate, put an exclamation in front
+!"a" %in% my_vector
+!"h" %in% my_vector
+```
+
+
+`%in%` is very useful when using the **dplyr** function `case_when()`. You can define a vector previously, and then reference it later. For example:
+
+
+```{r eval=F}
+affirmative <- c("1", "Yes", "YES", "yes", "y", "Y", "oui", "Oui", "Si")
+
+linelist <- linelist %>% 
+  mutate(child_hospitaled = case_when(
+    hospitalized %in% affirmative & age < 18 ~ "Hospitalized Child",
+    TRUE                                      ~ "Not"))
+```
+
+
+Note: If you want to detect a partial string, perhaps using `str_detect()` from **stringr**, it will not accept a character vector like `c("1", "Yes", "yes", "y")`. Instead, it must be given a *regular expression* - one condensed string with OR bars, such as "1\|Yes\|yes\|y". For example, `str_detect(hospitalized, "1|Yes|yes|y")`. See the page on [Characters and strings](characters_strings.qmd) for more information.
+
+You can convert a character vector to a named regular expression with this command:
+
+
+```{r}
+affirmative <- c("1", "Yes", "YES", "yes", "y", "Y", "oui", "Oui", "Si")
+affirmative
+
+# condense to 
+affirmative_str_search <- paste0(affirmative, collapse = "|")  # option with base R
+affirmative_str_search <- str_c(affirmative, collapse = "|")   # option with stringr package
+
+affirmative_str_search
+```
+
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+<!-- ======================================================= -->
+
+## Errors & warnings
+
+This section explains:
+
+-   The difference between errors and warnings.\
+-   General syntax tips for writing R code.\
+-   Code assists.
+
+Common errors and warnings and troubleshooting tips can be found in the page on [Errors and help](errors.qmd).
+
+<!-- ======================================================= -->
+
+### Error versus Warning {.unnumbered}
+
+When a command is run, the R Console may show you warning or error messages in red text.
+
+-   A **warning** means that R has completed your command, but had to take additional steps or produced unusual output that you should be aware of.
+
+-   An **error** means that R was not able to complete your command.
+
+Look for clues:
+
+-   The error/warning message will often include a line number for the problem.
+
+-   If an object "is unknown" or "not found", perhaps you spelled it incorrectly, forgot to call a package with library(), or forgot to re-run your script after making changes.
+
+If all else fails, copy the error message into Google along with some key terms - chances are that someone else has worked through this already!
+
+<!-- ======================================================= -->
+
+### General syntax tips {.unnumbered}
+
+A few things to remember when writing commands in R, to avoid errors and warnings:
+
+-   Always close parentheses - tip: count the number of opening "(" and closing parentheses ")" for each code chunk.
+-   Avoid spaces in column and object names. Use underscore ( \_ ) or periods ( . ) instead.
+-   Keep track of and remember to separate a function's arguments with commas.
+-   R is case-sensitive, meaning `Variable_A` is *different* from `variable_A`.
+
+<!-- ======================================================= -->
+
+### Code assists {.unnumbered}
+
+Any script (RMarkdown or otherwise) will give clues when you have made a mistake. For example, if you forgot to write a comma where it is needed, or to close a parentheses, RStudio will raise a flag on that line, on the left hand side of the script, to warn you.
+
diff --git a/new_pages/basics_files/execute-results/html.json b/new_pages/basics_files/execute-results/html.json
new file mode 100644
index 00000000..d1967d84
--- /dev/null
+++ b/new_pages/basics_files/execute-results/html.json
@@ -0,0 +1,17 @@
+{
+  "hash": "0f445c9bd187b8df9c852d072f545106",
+  "result": {
+    "engine": "knitr",
+    "markdown": "# R Basics {#rbasics}\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/basics_header_close.png){fig-align='center' width=100%}\n:::\n:::\n\n\nWelcome!\n\nThis page reviews the essentials of R. It is not intended to be a comprehensive tutorial, but it provides the basics and can be useful for refreshing your memory. The section on [Resources for learning](#learning) links to more comprehensive tutorials.\n\nParts of this page have been adapted with permission from the [R4Epis project](https://r4epis.netlify.app/).\n\nSee the page on [Transition to R](transition_to_R.qmd) for tips on switching to R from STATA, SAS, or Excel.\n\n\n::: {.cell}\n::: {.cell-output .cell-output-stderr}\n\n```\nWarning: The `trust` argument of `import()` should be explicit for serialization formats\nas of rio 1.0.3.\nℹ Missing `trust` will be set to FALSE by default for RDS in 2.0.0.\nℹ The deprecated feature was likely used in the rio package.\n  Please report the issue at <https://github.com/gesistsa/rio/issues>.\n```\n\n\n:::\n:::\n\n\n<!-- ======================================================= -->\n\n## Why use R?\n\nAs stated on the [R project website](https://www.r-project.org/about.html), R is a programming language and environment for statistical computing and graphics. It is highly versatile, extendable, and community-driven.\n\n**Cost**\n\nR is free to use! There is a strong ethic in the community of free and open-source material.\n\n**Reproducibility**\n\nConducting your data management and analysis through a programming language (compared to Excel or another primarily point-click/manual tool) enhances **reproducibility**, makes **error-detection** easier, and eases your workload.\n\n**Community**\n\nThe R community of users is enormous and collaborative. New packages and tools to address real-life problems are developed daily, and vetted by the community of users. As one example, [R-Ladies](https://rladies.org/) is a worldwide organization whose mission is to promote gender diversity in the R community, and is one of the largest organizations of R users. It likely has a chapter near you!\n\n## Key terms\n\n**RStudio** - RStudio is a Graphical User Interface (GUI) for easier use of **R**. Read more [in the RStudio section](#rstudio).\n\n**Objects** - Everything you store in R - datasets, variables, a list of village names, a total population number, even outputs such as graphs - are *objects* which are *assigned a name* and *can be referenced* in later commands. Read more in the [Objects section](#objects).\n\n**Functions** - A function is a code operation that accept inputs and returns a transformed output. Read more [in the Functions section](#functions).\n\n**Packages** - An R package is a shareable bundle of functions. Read more [in the Packages section](#packages).\n\n**Scripts** - A script is the document file that hold your commands. Read more [in the Scripts section](#scripts)\n\n## Resources for learning {#learning}\n\n### Resources within RStudio {.unnumbered}\n\n**Help documentation**\n\nSearch the RStudio \"Help\" tab for documentation on R packages and specific functions. This is within the pane that also contains Files, Plots, and Packages (typically in the lower-right pane). As a shortcut, you can also type the name of a package or function into the R console after a question-mark to open the relevant Help page. Do not include parentheses.\n\nFor example: `?filter` or `?diagrammeR`.\n\n**Interactive tutorials**\n\nThere are several ways to learn R interactively *within* RStudio.\n\nRStudio itself offers a Tutorial pane that is powered by the [**learnr**](https://blog.rstudio.com/2020/02/25/rstudio-1-3-integrated-tutorials/) R package. Simply install this package and open a tutorial via the new \"Tutorial\" tab in the upper-right RStudio pane (which also contains Environment and History tabs).\n\nThe R package [**swirl**](https://swirlstats.com/) offers interactive courses in the R Console. Install and load this package, then run the command `swirl()` (empty parentheses) in the R console. You will see prompts appear in the Console. Respond by typing in the Console. It will guide you through a course of your choice.\n\n### Cheatsheets {.unnumbered}\n\nThere are many PDF \"cheatsheets\" available on the [RStudio website](https://rstudio.com/resources/cheatsheets/), for example:\n\n-   Factors with **forcats** package.\\\n-   Dates and times with **lubridate** package.\\\n-   Strings with **stringr** package.\\\n-   iterative opertaions with **purrr** package.\\\n-   Data import.\\\n-   Data transformation cheatsheet with **dplyr** package.\\\n-   R Markdown (to create documents like PDF, Word, Powerpoint...).\\\n-   Shiny (to build interactive web apps).\\\n-   Data visualization with **ggplot2** package.\\\n-   Cartography (GIS).\\\n-   **leaflet** package (interactive maps).\\\n-   Python with R (**reticulate** package).\n\nThis is an online R resource specifically for [Excel users](https://jules32.github.io/r-for-excel-users/).\n\n### Twitter {.unnumbered}\n\n-   Follow us! [\\@epiRhandbook](https://twitter.com/epirhandbook)\n\nAlso:\n\n**\\#epitwitter** and **\\#rstats**\n\n### Free online resources {.unnumbered}\n\nA definitive text is the [R for Data Science](https://r4ds.hadley.nz/) book by Garrett Grolemund and Hadley Wickham.\n\nThe [R4Epis](https://r4epis.netlify.app/) project website aims to \"develop standardised data cleaning, analysis and reporting tools to cover common types of outbreaks and population-based surveys that would be conducted in an MSF emergency response setting\". You can find R basics training materials, templates for RMarkdown reports on outbreaks and surveys, and tutorials to help you set them up.\n\n### Languages other than English {.unnumbered}\n\n[Materiales de RStudio en Español](https://www.rstudio.com/collections/espanol/)\n\n[Introduction à R et au tidyverse (Francais)](https://juba.github.io/tidyverse/index.html)\n\n<!-- ======================================================= -->\n\n## Installation\n\n### R and RStudio {.unnumbered}\n\n**How to install R**\n\nVisit this website <https://www.r-project.org/> and download the latest version of R suitable for your computer.\n\n**How to install RStudio**\n\nVisit this website <https://rstudio.com/products/rstudio/download/> and download the latest free Desktop version of RStudio suitable for your computer.\n\n**Permissions**\\\nNote that you should install R and RStudio to a drive where you have read and write permissions. Otherwise, your ability to install R packages (a frequent occurrence) will be impacted. If you encounter problems, try opening RStudio by right-clicking the icon and selecting \"Run as administrator\". Other tips can be found in the page [R on network drives](network_drives.qmd).\n\n**How to update R and RStudio**\n\nYour version of R is printed to the R Console at start-up. You can also run `sessionInfo()`.\n\nTo update R, go to the website mentioned above and re-install R. Alternatively, you can use the **installr** package (on Windows) by running `installr::updateR()`. This will open dialog boxes to help you download the latest R version and update your packages to the new R version. More details can be found in the **installr** [documentation](https://talgalili.github.io/installr/).\n\nBe aware that the old R version will still exist in your computer. You can temporarily run an older version of R by clicking \"Tools\" -\\> \"Global Options\" in RStudio and choosing an R version. This can be useful if you want to use a package that has not been updated to work on the newest version of R.\n\nTo update RStudio, you can go to the website above and re-download RStudio. Another option is to click \"Help\" -\\> \"Check for Updates\" within RStudio, but this may not show the very latest updates.\n\nTo see which versions of R, RStudio, or packages were used when this Handbook as made, see the page on [Editorial and technical notes](editorial_style.qmd).\n\n### Other software you *may* need to install {.unnumbered}\n\n-   TinyTeX (for compiling an RMarkdown document to PDF).\\\n-   Pandoc (for compiling RMarkdown documents).\\\n-   RTools (for building packages for R).\\\n-   phantomjs (for saving still images of animated networks, such as transmission chains).\n\n#### TinyTex {.unnumbered}\n\nTinyTex is a custom LaTeX distribution, useful when trying to produce PDFs from R.\\\nSee <https://yihui.org/tinytex/> for more informaton.\n\nTo install TinyTex from R:\n\n\n::: {.cell}\n\n```{.r .cell-code}\ninstall.packages('tinytex')\ntinytex::install_tinytex()\n# to uninstall TinyTeX, run tinytex::uninstall_tinytex()\n```\n:::\n\n\n#### Pandoc {.unnumbered}\n\nPandoc is a document converter, a separate software from R. **It comes bundled with RStudio and should not need to be downloaded.** It helps the process of converting Rmarkdown documents to formats like .pdf and adding complex functionality.\n\n#### RTools {.unnumbered}\n\nRTools is a collection of software for building packages for R\n\nInstall from this website: <https://cran.r-project.org/bin/windows/Rtools/>\n\n#### phantomjs {.unnumbered}\n\nThis is often used to take \"screenshots\" of webpages. For example when you make a transmission chain with **epicontacts** package, an HTML file is produced that is interactive and dynamic. If you want a static image, it can be useful to use the [**webshot**](https://wch.github.io/webshot/articles/intro.html) package to automate this process. This will require the external program \"phantomjs\". You can install phantomjs via the **webshot** package with the command `webshot::install_phantomjs()`.\n\n<!-- ======================================================= -->\n\n## RStudio {#rstudio}\n\n### RStudio orientation {.unnumbered}\n\n**First, open RStudio.** \n\nAs their icons can look very similar, be sure you are opening *RStudio* and not R.\n\nFor RStudio to work you must also have R installed on the computer (see above for installation instructions).\n\n**RStudio** is an interface (GUI) for easier use of **R**. You can think of R as being the engine of a vehicle, doing the crucial work, and RStudio as the body of the vehicle (with seats, accessories, etc.) that helps you actually use the engine to move forward! You can see the complete RStudio user-interface cheatsheet (PDF) [here](https://rstudio.github.io/cheatsheets/html/rstudio-ide.html).\n\nBy default RStudio displays four rectangle panes.\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/RStudio_overview.png){fig-align='center' width=100%}\n:::\n:::\n\n\n[***TIP:*** If your RStudio displays only one left pane it is because you have no scripts open yet.]{style=\"color: black;\"}\n\n**The Source Pane**\\\nThis pane, by default in the upper-left, is a space to edit, run, and save your [scripts](#scripts). Scripts contain the commands you want to run. This pane can also display datasets (data frames) for viewing.\n\nFor Stata users, this pane is similar to your Do-file and Data Editor windows.\n\n**The R Console Pane**\n\nThe R Console, by default the left or lower-left pane in R Studio, is the home of the R \"engine\". This is where the commands are actually run and non-graphic outputs and error/warning messages appear. You can directly enter and run commands in the R Console, but realize that these commands are not saved as they are when running commands from a script.\n\nIf you are familiar with Stata, the R Console is like the Command Window and also the Results Window.\n\n**The Environment Pane**\\\nThis pane, by default in the upper-right, is most often used to see brief summaries of [objects](#objects) in the R Environment in the current session. These objects could include imported, modified, or created datasets, parameters you have defined (e.g. a specific epi week for the analysis), or vectors or lists you have defined during analysis (e.g. names of regions). You can click on the arrow next to a data frame name to see its variables.\n\nIn Stata, this is most similar to the Variables Manager window.\n\nThis pane also contains *History* where you can see commands that you can previously. It also has a \"Tutorial\" tab where you can complete interactive R tutorials if you have the **learnr** package installed. It also has a \"Connections\" pane for external connections, and can have a \"Git\" pane if you choose to interface with Github.\n\n**Plots, Viewer, Packages, and Help Pane**\\\nThe lower-right pane includes several important tabs. Typical plot graphics including maps will display in the Plot pane. Interactive or HTML outputs will display in the Viewer pane. The Help pane can display documentation and help files. The Files pane is a browser which can be used to open or delete files. The Packages pane allows you to see, install, update, delete, load/unload R packages, and see which version of the package you have. To learn more about packages see the [packages section](#packages) below.\n\nThis pane contains the Stata equivalents of the Plots Manager and Project Manager windows.\n\n### RStudio settings {.unnumbered}\n\nChange RStudio settings and appearance in the *Tools* drop-down menu, by selecting *Global Options*. There you can change the default settings, including appearance/background color.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![](../images/RStudio_tools_options_1.png){width=50%}\n:::\n\n::: {.cell-output-display}\n![](../images/RStudio_tools_options.png){width=50%}\n:::\n:::\n\n\n**Restart**\n\nIf your R freezes, you can re-start R by going to the Session menu and clicking \"Restart R\". This avoids the hassle of closing and opening RStudio. \n\n\n<span style=\"color: orange;\">**_CAUTION:_** Everything in your R environment will be removed when you do this.\n\n### Keyboard shortcuts {.unnumbered}\n\nSome very useful keyboard shortcuts are below. See all the keyboard shortcuts for Windows, Max, and Linux [Rstudio user interface cheatsheet](https://rstudio.github.io/cheatsheets/html/rstudio-ide.html#keyboard-shortcuts).\n\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Windows/Linux                    | Mac                    | Action                                                                                                                         |\n+==================================+========================+================================================================================================================================+\n| Esc                              | Esc                    | Interrupt current command (useful if you accidentally ran an incomplete command and cannot escape seeing \"+\" in the R console). |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl+s                           | Cmd+s                  | Save (script).                                                                                                                  |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Tab                              | Tab                    | Auto-complete.                                                                                                                  |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Enter                     | Cmd + Enter            | Run current line(s)/selection of code.                                                                                          |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Shift + C                 | Cmd + Shift + c        | Comment/uncomment the highlighted lines.                                                                                        |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Alt + -                          | Option + -             | Insert `<-`.                                                                                                                    |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Shift + m                 | Cmd + Shift + m        | Insert `%>%`.                                                                                                                   |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + l                         | Cmd + l                | Clear the R console.                                                                                                            |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Alt + b                   | Cmd + Option + b       | Run from start to current. line                                                                                                 |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Alt + t                   | Cmd + Option + t       | Run the current code section (R Markdown).                                                                                      |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Alt + i                   | Cmd + Shift + r        | Insert code chunk (into R Markdown).                                                                                            |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Alt + c                   | Cmd + Option + c       | Run current code chunk (R Markdown).                                                                                            |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| up/down arrows in R console      | Same                   | Toggle through recently run commands.                                                                                           |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Shift + up/down arrows in script | Same                   | Select multiple code lines.                                                                                                     |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + f                         | Cmd + f                | Find and replace in current script.                                                                                             |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Ctrl + Shift + f                 | Cmd + Shift + f        | Find in files (search/replace across many scripts).                                                                             |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Alt + l                          | Cmd + Option + l       | Fold selected code.                                                                                                             |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n| Shift + Alt + l                  | Cmd + Shift + Option+l | Unfold selected code.                                                                                                           |\n+----------------------------------+------------------------+--------------------------------------------------------------------------------------------------------------------------------+\n\n[***TIP:*** Use your Tab key when typing to engage RStudio's auto-complete functionality. This can prevent spelling errors. Press Tab while typing to produce a drop-down menu of likely functions and objects, based on what you have typed so far.]{style=\"color: darkgreen;\"}\n\n<!-- ======================================================= -->\n\n## Functions {#functions}\n\nFunctions are at the core of using R. Functions are how you perform tasks and operations. Many functions come installed with R, many more are available for download in *packages* (explained in the [packages](#packages) section), and you can even write your own custom functions!\n\nThis basics section on functions explains:\n\n-   What a function is and how they work.\\\n-   What function *arguments* are.\\\n-   How to get help understanding a function.\n\n*A quick note on syntax:* In this handbook, functions are written in code-text with open parentheses, like this: `filter()`. As explained in the [packages](#packages) section, functions are downloaded within *packages*. In this handbook, package names are written in **bold**, like **dplyr**. Sometimes in example code you may see the function name linked explicitly to the name of its package with two colons (`::`) like this: `dplyr::filter()`. The purpose of this linkage is explained in the packages section.\n\n<!-- ======================================================= -->\n\n### Simple functions {.unnumbered}\n\n**A function is like a machine that receives inputs, carries out an action with those inputs, and produces an output.** What the output is depends on the function.\n\n**Functions typically operate upon some object placed within the function's parentheses**. For example, the function `sqrt()` calculates the square root of a number:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nsqrt(49)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 7\n```\n\n\n:::\n:::\n\n\nThe object provided to a function also can be a column in a dataset (see the [Objects](#objects) section for detail on all the kinds of objects). Because R can store multiple datasets, you will need to specify both the dataset and the column. One way to do this is using the `$` notation to link the name of the dataset and the name of the column (`dataset$column`). In the example below, the function `summary()` is applied to the numeric column `age` in the dataset `linelist`, and the output is a summary of the column's numeric and missing values.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Print summary statistics of column 'age' in the dataset 'linelist'\nsummary(linelist$age)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's \n   0.00    6.00   13.00   16.07   23.00   84.00      86 \n```\n\n\n:::\n:::\n\n\n[***NOTE:*** Behind the scenes, a function represents complex additional code that has been wrapped up for the user into one easy command.]{style=\"color: black;\"}\n\n<!-- ======================================================= -->\n\n### Functions with multiple arguments {.unnumbered}\n\nFunctions often ask for several inputs, called ***arguments***, located within the parentheses of the function, usually separated by commas.\n\n-   Some arguments are required for the function to work correctly, others are optional.\\\n-   Optional arguments have default settings.\\\n-   Arguments can take character, numeric, logical (TRUE/FALSE), and other inputs.\n\nHere is a fun fictional function, called `oven_bake()`, as an example of a typical function. It takes an input object (e.g. a dataset, or in this example \"dough\") and performs operations on it as specified by additional arguments (`minutes =` and `temperature =`). The output can be printed to the console, or saved as an object using the assignment operator `<-`.\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/Function_Bread_Example.png){fig-align='center' width=75%}\n:::\n:::\n\n\n**In a more realistic example**, the `age_pyramid()` command below produces an age pyramid plot based on defined age groups and a binary split column, such as `gender`. The function is given three arguments within the parentheses, separated by commas. The values supplied to the arguments establish `linelist` as the data frame to use, `age_cat5` as the column to count, and `gender` as the binary column to use for splitting the pyramid by color.\n\n\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Create an age pyramid\nage_pyramid(data = linelist, age_group = \"age_cat5\", split_by = \"gender\")\n```\n\n::: {.cell-output-display}\n![](basics_files/figure-html/unnamed-chunk-6-1.png){width=75% height=75%}\n:::\n:::\n\n\nThe above command can be equivalently written as below, in a longer style with a new line for each argument. This style can be easier to read, and easier to write \"comments\" with `#` to explain each part (commenting extensively is good practice!). To run this longer command you can highlight the entire command and click \"Run\", or just place your cursor in the first line and then press the Ctrl and Enter keys simultaneously.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Create an age pyramid\nage_pyramid(\n  data = linelist,        # use case linelist\n  age_group = \"age_cat5\", # provide age group column\n  split_by = \"gender\"     # use gender column for two sides of pyramid\n  )\n```\n\n::: {.cell-output-display}\n![](basics_files/figure-html/unnamed-chunk-7-1.png){width=75% height=75%}\n:::\n:::\n\n\nThe first half of an argument assignment (e.g. `data =`) does not need to be specified if the arguments are written in a specific order (specified in the function's documentation). The below code produces the exact same pyramid as above, because the function expects the argument order: data frame, `age_group` variable, `split_by` variable.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# This command will produce the exact same graphic as above\nage_pyramid(linelist, \"age_cat5\", \"gender\")\n```\n:::\n\n\n**A more complex `age_pyramid()` command might include the *optional* arguments to:**\n\n-   Show proportions instead of counts (set `proportional = TRUE` when the default is `FALSE`)\\\n-   Specify the two colors to use (`pal =` is short for \"palette\" and is supplied with a vector of two color names. See the [objects](https://epirhandbook.com/new_pages/basics.html#objects) page for how the function `c()` makes a vector)\n\n[***NOTE:*** For arguments that you specify with both parts of the argument (e.g. `proportional = TRUE`), their order among all the arguments does not matter.]{style=\"color: black;\"}\n\n\n::: {.cell}\n\n```{.r .cell-code}\nage_pyramid(\n  linelist,                    # use case linelist\n  \"age_cat5\",                  # age group column\n  \"gender\",                    # split by gender\n  proportional = TRUE,         # percents instead of counts\n  pal = c(\"orange\", \"purple\")  # colors\n  )\n```\n\n::: {.cell-output-display}\n![](basics_files/figure-html/unnamed-chunk-8-1.png){width=75% height=75%}\n:::\n:::\n\n***TIP:*** Remember that you can put `?` before a function to see what arguments the function can take, and which arguments are needed and which arguments have default values. For example `?age_pyramid'.\n\n<!-- ======================================================= -->\n\n### Writing Functions {.unnumbered}\n\nR is a language that is oriented around functions, so you should feel empowered to write your own functions. Creating functions brings several advantages:\n\n-   To facilitate modular programming - the separation of code in to independent and manageable pieces.\\\n-   Replace repetitive copy-and-paste, which can be error prone.\\\n-   Give pieces of code memorable names.\n\nHow to write a function is covered in-depth in the [Writing functions](writing_functions.qmd) page.\n\n<!-- A function is given a name and defined with the assignment operator `<-` to a special **base** R function called `function()`. Within the parentheses, the arguments that the function will accept are defined. This is followed by curly brackets `{ }`, within which the actual code of the function is written.     -->\n\n\n::: {.cell}\n\n:::\n\n\n<!-- The arguments should be provided in the syntax `argument = default`, separated by commas.   -->\n\n<!-- Here is an example where we create a function `staff_calc()` to serve as a staffing calculator for COVID-19 case investigation and contact tracing calls.   -->\n\n<!-- The arguments (inputs) and their default values will be:   -->\n\n<!-- * `daily_cases = NULL` The number of new COVID-19 cases per day   -->\n\n<!-- * `contacts_each = 5` The number contacts enumerated for each case   -->\n\n<!-- * `time_case = 0.5`  Number of hours to complete a case investigaton by phone   -->\n\n<!-- * `time_contact = 0.25`  Number of hours to complete a contact follow-up by phone   -->\n\n<!-- * `time_day = 8` The number of hours one staff works per day   -->\n\n<!-- Below, the function is created. The code ends with the special function `return()`, which is what the function produces.    -->\n\n<!-- ```{r message=FALSE, warning=FALSE, out.width = \"75%\", out.height=\"75%\"} -->\n\n<!-- staff_calc <- function(daily_cases = NULL, contacts_each = 5, -->\n\n<!--                        time_case = 0.5, time_contact = 0.25, time_day = 8){ -->\n\n<!--   # Define total daily hours for calling cases -->\n\n<!--   case_hours <- daily_cases * time_case  -->\n\n<!--   # Define total daily hours for calling contacts -->\n\n<!--   contact_hours <- daily_cases * contacts_each * time_contact -->\n\n<!--   # Calculate number of staff required -->\n\n<!--   staff_required <- (case_hours + contact_hours)/time_day -->\n\n<!--   return(staff_required) -->\n\n<!-- } -->\n\n<!-- ``` -->\n\n<!-- Once this code is run, the function will be defined and will appear in the R Environment. We can run the function. Below all the default values are used and the `daily_cases = ` is set to 150.   -->\n\n\n::: {.cell}\n\n:::\n\n::: {.cell}\n\n:::\n\n\n<!-- There are many other nuances to understand when writing functions, as discussed in the page [Writing functions].   -->\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n## Packages {#packages}\n\n**Packages contain functions.**\n\nAn R package is a shareable bundle of code and documentation that contains pre-defined functions. Users in the R community develop packages all the time catered to specific problems, it is likely that one can help with your work! You will install and use hundreds of packages in your use of R.\n\nOn installation, R contains **\"base\"** packages and functions that perform common elementary tasks. But many R users create specialized functions, which are verified by the R community and which you can download as a **package** for your own use. In this handbook, package names are written in **bold**. One of the more challenging aspects of R is that there are often many functions or packages to choose from to complete a given task.\n\n### Install and load {.unnumbered}\n\n*Functions* are contained within **packages** which can be downloaded (\"installed\") to your computer from the internet. Once a package is downloaded, it is stored in your \"library\". You can then access the functions it contains during your current R session by \"loading\" the package.\n\n*Think of R as your personal library*: When you download a package, your library gains a new book of functions, but each time you want to use a function in that book, you must borrow,\"load\", that book from your library.\n\nIn summary: to use the functions available in an R package, 2 steps must be implemented:\n\n1)  The package must be **installed** (once), *and*\\\n2)  The package must be **loaded** (each R session)\n\n#### Your library {.unnumbered}\n\nYour \"library\" is actually a folder on your computer, containing a folder for each package that has been installed. Find out where R is installed in your computer, and look for a folder called \"win-library\". For example: `R\\win-library\\4.4.1` (the 4.4.1 is the R version - you'll have a different library for each R version you've downloaded).\n\nYou can print the file path to your library by entering `.libPaths()` (empty parentheses). This becomes especially important if working with [R on network drives](network_drives.qmd).\n\n#### Install from CRAN {.unnumbered}\n\nMost often, R users download packages from CRAN. CRAN (Comprehensive R Archive Network) is an online public warehouse of R packages that have been published by R community members.\n\nAre you worried about viruses and security when downloading a package from CRAN? Read [this article](https://support.rstudio.com/hc/en-us/articles/360042593974-R-and-R-Package-Security) on the topic.\n\n#### How to install and load {.unnumbered}\n\nIn this handbook, we suggest using the **pacman** package (short for \"package manager\"). It offers a convenient function `p_load()` which will install a package if necessary *and* load it for use in the current R session.\n\nThe syntax quite simple. Just list the names of the packages within the `p_load()` parentheses, separated by commas. This command will install the **rio**, **tidyverse**, and **here** packages if they are not yet installed, and will load them for use. This makes the `p_load()` approach convenient and concise if sharing scripts with others. \n\nNote that package names are case-sensitive.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Install (if necessary) and load packages for use\npacman::p_load(rio, tidyverse, here)\n```\n:::\n\n\nHere we have used the syntax `pacman::p_load()` which explicitly writes the package name (**pacman**) prior to the function name (`p_load()`), connected by two colons `::`. This syntax is useful because it also loads the **pacman** package (assuming it is already installed).\n\nThere are alternative **base** R functions that you will see often. The **base** R function for installing a package is `install.packages()`. The name of the package to install must be provided in the parentheses *in quotes*. If you want to install multiple packages in one command, they must be listed within a character vector `c()`.\n\nNote: this command *installs* a package, but does *not* load it for use in the current session.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# install a single package with base R\ninstall.packages(\"tidyverse\")\n\n# install multiple packages with base R\ninstall.packages(c(\"tidyverse\", \"rio\", \"here\"))\n```\n:::\n\n\nInstallation can also be accomplished point-and-click by going to the RStudio \"Packages\" pane and clicking \"Install\" and searching for the desired package name.\n\nThe **base** R function to **load** a package for use (after it has been installed) is `library()`. It can load only one package at a time (another reason to use `p_load()`). You can provide the package name with or without quotes.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# load packages for use, with base R\nlibrary(tidyverse)\nlibrary(rio)\nlibrary(here)\n```\n:::\n\n\nTo check whether a package in installed or loaded, you can view the Packages pane in RStudio. If the package is installed, it is shown there with version number. If its box is checked, it is loaded for the current session.\n\n**Install from Github**\n\nSometimes, you need to install a package that is not yet available from CRAN. Or perhaps the package is available on CRAN but you want the *development version* with new features not yet offered in the more stable published CRAN version. These are often hosted on the website [github.com](https://github.com/) in a free, public-facing code \"repository\". Read more about Github in the handbook page on [Version control and collaboration with Git and Github](https://epirhandbook.com/new_pages/collaboration.html).\n\nTo download R packages from Github, you can use the function `p_load_gh()` from **pacman**, which will install the package if necessary, and load it for use in your current R session. Alternatives to install include using the **remotes** or **devtools** packages. Read more about all the **pacman** functions in the [package documentation](https://cran.r-project.org/web/packages/pacman/pacman.pdf).\n\nTo install from Github, you have to provide more information. You must provide:\n\n1)  The Github ID of the repository owner\n2)  The name of the repository that contains the package\\\n3)  Optional: *The name of the \"branch\" (specific development version) you want to download*\n\nIn the examples below, the first word in the quotation marks is the Github ID of the repository owner, after the slash is the name of the repository (the name of the package).\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# install/load the epicontacts package from its Github repository\np_load_gh(\"reconhub/epicontacts\")\n```\n:::\n\n\nIf you want to install from a \"branch\" (version) other than the main branch, add the branch name after an \"\\@\", after the repository name.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# install the \"timeline\" branch of the epicontacts package from Github\np_load_gh(\"reconhub/epicontacts@timeline\")\n```\n:::\n\n\nIf there is no difference between the Github version and the version on your computer, no action will be taken. You can \"force\" a re-install by instead using `p_load_current_gh()` with the argument `update = TRUE`. Read more about **pacman** in this [online vignette](http://trinker.github.io/pacman/vignettes/Introduction_to_pacman.html)\n\n**Install from ZIP or TAR**\n\nYou could install the package from a URL:\n\n\n::: {.cell}\n\n```{.r .cell-code}\npackageurl <- \"https://cran.r-project.org/src/contrib/Archive/dsr/dsr_0.2.2.tar.gz\"\ninstall.packages(packageurl, repos=NULL, type=\"source\")\n```\n:::\n\n\nOr, download it to your computer in a zipped file:\n\nOption 1: using `install_local()` from the **remotes** package\n\n\n::: {.cell}\n\n```{.r .cell-code}\nremotes::install_local(\"~/Downloads/dplyr-master.zip\")\n```\n:::\n\n\nOption 2: using `install.packages()` from **base** R, providing the file path to the ZIP file and setting `type = \"source` and `repos = NULL`.\n\n\n::: {.cell}\n\n```{.r .cell-code}\ninstall.packages(\"~/Downloads/dplyr-master.zip\", repos=NULL, type=\"source\")\n```\n:::\n\n\n### Code syntax {.unnumbered}\n\nFor clarity in this handbook, functions are sometimes preceded by the name of their package using the `::` symbol in the following way: `package_name::function_name()`\n\nOnce a package is loaded for a session, this explicit style is not necessary. One can just use `function_name()`. However writing the package name is useful when a function name is common and may exist in multiple packages (e.g. `plot()`). Writing the package name will also load the package if it is not already loaded.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# This command uses the package \"rio\" and its function \"import()\" to import a dataset\nlinelist <- rio::import(\"linelist.xlsx\", which = \"Sheet1\")\n```\n:::\n\n\n### Function help {.unnumbered}\n\nTo read more about a function, you can search for it in the Help tab of the lower-right RStudio. You can also run a command like `?thefunctionname` (for example, to get help for the function `p_load` you would write `?p_load`) and the Help page will appear in the Help pane. Finally, try searching online for resources.\n\n### Update packages {.unnumbered}\n\nYou can update packages by re-installing them. You can also click the green \"Update\" button in your RStudio Packages pane to see which packages have new versions to install. Be aware that your old code may need to be updated if there is a major revision to how a function works!\n\n### Delete packages {.unnumbered}\n\nUse `p_delete()` from **pacman**, or `remove.packages()` from **base** R.\n\n### Dependencies {.unnumbered}\n\nPackages often depend on other packages to work. These are called dependencies. If a dependency fails to install, then the package depending on it may also fail to install.\n\nSee the dependencies of a package with `p_depends()`, and see which packages depend on it with `p_depends_reverse()`\n\n### Masked functions {.unnumbered}\n\nIt is not uncommon that two or more packages contain the same function name. For example, the package **dplyr** has a `filter()` function, but so does the package **stats**. The default `filter()` function depends on the order these packages are first loaded in the R session - the later one will be the default for the command `filter()`.\n\nYou can check the order in your Environment pane of R Studio - click the drop-down for \"Global Environment\" and see the order of the packages. Functions from packages *lower* on that drop-down list will mask functions of the same name in packages that appear higher in the drop-down list. When first loading a package, R will warn you in the console if masking is occurring, but this can be easy to miss.\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/masking_functions.png){fig-align='center' width=50%}\n:::\n:::\n\n\nHere are ways you can fix masking:\n\n1)  Specify the package name in the command. For example, use `dplyr::filter()`\\\n2)  Re-arrange the order in which the packages are loaded (e.g. within `p_load()`), and **start a new R session**\n\n### Detach / unload {.unnumbered}\n\nTo detach (unload) a package, use this command, with the correct package name and only one colon. Note that this may not resolve masking.\n\n\n::: {.cell}\n\n```{.r .cell-code}\ndetach(package:PACKAGE_NAME_HERE, unload=TRUE)\n```\n:::\n\n\n### Install older version {.unnumbered}\n\nSee this [guide](https://support.rstudio.com/hc/en-us/articles/219949047-Installing-older-versions-of-packages) to install an older version of a particular package.\n\n### Suggested packages {.unnumbered}\n\nSee the page on [Suggested packages](packages_suggested.qmd) for a listing of packages we recommend for everyday epidemiology.\n\n<!-- ======================================================= -->\n\n## Scripts {#scripts}\n\nScripts are a fundamental part of programming. They are documents that hold your commands (e.g. functions to create and modify datasets, print visualizations, etc). You can save a script and run it again later. There are many advantages to storing and running your commands from a script (vs. typing commands one-by-one into the R console \"command line\"):\n\n-   Portability - you can share your work with others by sending them your scripts.\\\n-   Reproducibility - so that you and others know exactly what you did.\\\n-   Version control - so you can track changes made by yourself or colleagues.\\\n-   Commenting/annotation - to explain to your colleagues what you have done.\n\n### Commenting {.unnumbered}\n\nIn a script you can also annotate (\"comment\") around your R code. Commenting is helpful to explain to yourself and other readers what you are doing. You can add a comment by typing the hash symbol (\\#) and writing your comment after it. The commented text will appear in a different color than the R code.\n\nAny code written after the \\# will not be run. Therefore, placing a \\# before code is also a useful way to temporarily block a line of code (\"comment out\") if you do not want to delete it. You can comment out/in multiple lines at once by highlighting them and pressing Ctrl+Shift+c (Cmd+Shift+c in Mac).\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# A comment can be on a line by itself\n# import data\nlinelist <- import(\"linelist_raw.xlsx\") %>%   # a comment can also come after code\n# filter(age > 50)                          # It can also be used to deactivate / remove a line of code\n  count()\n```\n:::\n\n\nThere are a few general ideas to follow when writing your scripts in order to make them accessible.\n-   Add comments on *what* you are doing *and on **why** you are doing it*.\\\n-   Break your code into logical sections.\\\n-   Accompany your code with a text step-by-step description of what you are doing (e.g. numbered steps).\n\n### Style {.unnumbered}\n\nIt is important to be conscious of your coding style - especially if working on a team. We advocate for the **tidyverse** [style guide](https://style.tidyverse.org/). There are also packages such as **styler** and **lintr** which help you conform to this style.\n\nA few very basic points to make your code readable to others:\\\n\\* When naming objects, use only lowercase letters, numbers, and underscores `_`, e.g. `my_data`\\\n\\* Use frequent spaces, including around operators, e.g. `n = 1` and `age_new <- age_old + 3`\n\n### Example Script {.unnumbered}\n\nBelow is an example of a short R script. Remember, the better you succinctly explain your code in comments, the more your colleagues will like you!\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/example_script.png){fig-align='center' width=100%}\n:::\n:::\n\n\n<!-- ======================================================= -->\n\n### R markdown and Quarto {.unnumbered}\n\nAn [R Markdown](https://rmarkdown.rstudio.com/) or [Quarto](https://quarto.org/docs/computations/r.html) script are types of R script in which the script itself *becomes* an output document (PDF, Word, HTML, Powerpoint, etc.). These are incredibly useful and versatile tools often used to create dynamic and automated reports. \n\nEven this website and handbook is produced with Quarto scripts!\n\nIt is worth noting that beginner R users can also use R Markdown - do not be intimidated! To learn more, see the handbook page on [Reports with R Markdown](rmarkdown.qmd) documents.\n\n<!-- ======================================================= -->\n\n### R notebooks {.unnumbered}\n\nThere is no difference between writing in a Rmarkdown vs an R notebook. However the execution of the document differs slightly. See this [site](http://uc-r.github.io/r_notebook) for more details.\n\n<!-- ======================================================= -->\n\n### Shiny {.unnumbered}\n\nShiny apps/websites are contained within one script, which must be named `app.R`. This file has three components:\n\n1)  A user interface (ui).\\\n2)  A server function.\\\n3)  A call to the `shinyApp` function.\n\nSee the handbook page on [Dashboards with Shiny](shiny_basics.qmd), or this online tutorial: [Shiny tutorial](https://shiny.rstudio.com/tutorial/written-tutorial/lesson1/)\n\n*In previous versions, the above file was split into two files (`ui.R` and `server.R`)*\n\n### Code folding {.unnumbered}\n\nYou can collapse portions of code to make your script easier to read.\n\nTo do this, create a text header with \\#, write your header, and follow it with at least 4 of either dashes (-), hashes (\\#) or equals (=). When you have done this, a small arrow will appear in the \"gutter\" to the left (by the row number). You can click this arrow and the code below until the next header will collapse and a dual-arrow icon will appear in its place.\n\nTo expand the code, either click the arrow in the gutter again, or the dual-arrow icon. There are also keyboard shortcuts as explained in the [RStudio section](#rstudio) of this page.\n\nBy creating headers with \\#, you will also activate the Table of Contents at the bottom of your script (see below) that you can use to navigate your script. You can create sub-headers by adding more \\# symbols, for example \\# for primary, \\#\\# for secondary, and \\#\\#\\# for tertiary headers.\n\nBelow are two versions of an example script. On the left is the original with commented headers. On the right, four dashes have been written after each header, making them collapsible. Two of them have been collapsed, and you can see that the Table of Contents at the bottom now shows each section.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![](../images/code_folding1.png){width=50%}\n:::\n\n::: {.cell-output-display}\n![](../images/code_folding2.png){width=50%}\n:::\n:::\n\n\nOther areas of code that are automatically eligible for folding include \"braced\" regions with brackets `{ }` such as function definitions or conditional blocks (if else statements). You can read more about code folding at the RStudio [site](https://support.rstudio.com/hc/en-us/articles/200484568-Code-Folding-and-Sections).\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n## Working directory\n\nThe working directory is the root folder location used by R for your work - where R looks for and saves files by default. By default, it will save new files and outputs to this location, and will look for files to import (e.g. datasets) here as well.\n\nThe working directory appears in grey text at the top of the RStudio Console pane. You can also print the current working directory by running `getwd()` (leave the parentheses empty).\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/working_directory_1.png){fig-align='center' width=100%}\n:::\n:::\n\n\n### Recommended approach {.unnumbered}\n\n**See the page on [R projects](r_projects.qmd) for details on our recommended approach to managing your working directory.**\\\n\nA common, efficient, and trouble-free way to manage your working directory and file paths is to combine these 3 elements in an [R project](r_projects.qmd)-oriented workflow:\n\n1)  An R Project to store all your files (see page on [R projects](r_projects.qmd))\\\n2)  The **here** package to locate files (see page on [Import and export](importing.qmd))\\\n3)  The **rio** package to import/export files (see page on [Import and export](importing.qmd))\n\n<!-- ======================================================= -->\n\n### Set by command {.unnumbered}\n\nUntil recently, many people learning R were taught to begin their scripts with a `setwd()` command. \n\nPlease instead consider using an [R project](r_projects.qmd)-oriented workflow and read the [reasons for not using `setwd()`](https://www.tidyverse.org/blog/2017/12/workflow-vs-script/). \n\nIn brief, your work becomes specific to your computer. This means that file paths used to import and export files need to be changed if used on a different computer, or by different collaborators.\n\nAs noted above, although we do not recommend this approach in most circumstances, you can use the command `setwd()` with the desired folder file path in quotations, for example:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nsetwd(\"C:/Documents/R Files/My analysis\")\n```\n:::\n\n\n[***DANGER:*** Setting a working directory with `setwd()` *can* be \"brittle\" if the file path is specific to one computer. Instead, use file paths relative to an R Project root directory, such as with the [**here** package]. ]{style=\"color: red;\"}\n\n<!-- ======================================================= -->\n\n### Set manually {.unnumbered}\n\nTo set the working directory manually (the point-and-click equivalent of `setwd()`), click the Session drop-down menu and go to \"Set Working Directory\" and then \"Choose Directory\". This will set the working directory for that specific R session. Note: if using this approach, you will have to do this manually each time you open RStudio.\n\n<!-- ======================================================= -->\n\n### Within an R project {.unnumbered}\n\nIf using an R project, the working directory will default to the R project root folder that contains the \".rproj\" file. This will apply if you open RStudio by clicking open the R Project (the file with \".rproj\" extension).\n\n<!-- ======================================================= -->\n\n### Working directory in an R markdown {.unnumbered}\n\nIn an R markdown script, the default working directory is the folder the Rmarkdown file (`.Rmd`) is saved within. If using an R project and **here** package, this does not apply and the working directory will be `here()` as explained in the [R projects](r_projects.qmd) page.\n\nIf you want to change the working directory of a stand-alone R markdown (not in an R project), if you use `setwd()` this will only apply to that specific code chunk. To make the change for all code chunks in an R markdown, edit the setup chunk to add the `root.dir =` parameter, such as below:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nknitr::opts_knit$set(root.dir = 'desired/directorypath')\n```\n:::\n\n\nIt is much easier to just use the R markdown within an R project and use the **here** package.\n\n<!-- ======================================================= -->\n\n### Providing file paths {.unnumbered}\n\nPerhaps the most common source of frustration for an R beginner (at least on a Windows machine) is typing in a file path to import or export data. There is a thorough explanation of how to best input file paths in the [Import and export](importing.qmd) page, but here are a few key points:\n\n**Broken paths**\n\nBelow is an example of an \"absolute\" or \"full address\" file path. These will likely break if used by another computer. One exception is if you are using a shared/network drive.\n\n    C:/Users/Name/Document/Analytic Software/R/Projects/Analysis2019/data/March2019.csv  \n\n**Slash direction**\n\n*If typing in a file path, be aware the direction of the slashes.* \n\nUse *forward slashes* (`/`) to separate the components (\"data/provincial.csv\"). For Windows users, the default way that file paths are displayed is with *back slashes* (\\\\) - so you will need to change the direction of each slash. If you use the **here** package as described in the [R projects](r_projects.qmd) page the slash direction is not an issue.\n\n**Relative file paths**\n\nWe generally recommend providing \"relative\" filepaths instead - that is, the path *relative to* the root of your R Project. You can do this using the **here** package as explained in the [R projects](r_projects.qmd) page. A relativel filepath might look like this:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Import csv linelist from the data/linelist/clean/ sub-folders of an R project\nlinelist <- import(here(\"data\", \"clean\", \"linelists\", \"marin_country.csv\"))\n```\n:::\n\n\nEven if using relative file paths within an R project, you can still use absolute paths to import and export data outside your R project.\n\n<!-- ======================================================= -->\n\n## Objects {#objects}\n\nEverything in R is an object, and R is an \"object-oriented\" language. These sections will explain:\n\n-   How to create objects (`<-`).\n-   Types of objects (e.g. data frames, vectors..).\\\n-   How to access subparts of objects (e.g. variables in a dataset).\\\n-   Classes of objects (e.g. numeric, logical, integer, double, character, factor).\n\n<!-- ======================================================= -->\n\n### Everything is an object {.unnumbered}\n\n*This section is adapted from the [R4Epis project](https://r4epis.netlify.app/training/r_basics/objects/).*\\\n\nEverything you store in R - datasets, variables, a list of village names, a total population number, even outputs such as graphs - are **objects** which are **assigned a name** and **can be referenced** in later commands.\n\nAn object exists when you have assigned it a value (see the assignment section below). When it is assigned a value, the object appears in the Environment (see the upper right pane of RStudio). It can then be operated upon, manipulated, changed, and re-defined.\n\n<!-- ======================================================= -->\n\n### Defining objects (`<-`) {.unnumbered}\n\n**Create objects *by assigning them a value* with the \\<- operator.**\\\nYou can think of the assignment operator `<-` as the words \"is defined as\". Assignment commands generally follow a standard order:\n\n**object_name** \\<- **value** (or process/calculation that produce a value)\n\nFor example, you may want to record the current epidemiological reporting week as an object for reference in later code. In this example, the object `current_week` is created when it is assigned the value `\"2018-W10\"` (the quote marks make this a character value). The object `current_week` will then appear in the RStudio Environment pane (upper-right) and can be referenced in later commands.\n\nSee the R commands and their output in the boxes below.\n\n\n::: {.cell}\n\n```{.r .cell-code}\ncurrent_week <- \"2018-W10\"   # this command creates the object current_week by assigning it a value\ncurrent_week                 # this command prints the current value of current_week object in the console\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"2018-W10\"\n```\n\n\n:::\n:::\n\n\n[***NOTE:*** Note the `[1]` in the R console output is simply indicating that you are viewing the first item of the output]{style=\"color: black;\"}\n\n[***CAUTION:*** **An object's value can be over-written** at any time by running an assignment command to re-define its value. Thus, the **order of the commands run is very important**.]{style=\"color: orange;\"}\n\nThe following command will re-define the value of `current_week`:\n\n\n::: {.cell}\n\n```{.r .cell-code}\ncurrent_week <- \"2018-W51\"   # assigns a NEW value to the object current_week\ncurrent_week                 # prints the current value of current_week in the console\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"2018-W51\"\n```\n\n\n:::\n:::\n\n\n**Equals signs `=`**\n\nYou will also see equals signs in R code:\n\n-   A double equals sign `==` between two objects or values asks a logical *question*: \"is this equal to that?\".\\\n-   You will also see equals signs within functions used to specify values of function arguments (read about these in sections below), for example `max(age, na.rm = TRUE)`.\\\n-   You *can* use a single equals sign `=` in place of `<-` to create and define objects, but this is discouraged. You can read about why this is discouraged [here](https://renkun.me/2014/01/28/difference-between-assignment-operators-in-r/).\n\n**Datasets**\n\nDatasets are also objects (typically \"data frames\") and must be assigned names when they are imported. In the code below, the object `linelist` is created and assigned the value of a CSV file imported with the **rio** package and its `import()` function.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# linelist is created and assigned the value of the imported CSV file\nlinelist <- import(\"my_linelist.csv\")\n```\n:::\n\n\nYou can read more about importing and exporting datasets with the section on [Import and export](importing.qmd).\n\n[***CAUTION:*** A quick note on naming of objects:]{style=\"color: orange;\"}\n\n-   Object names must not contain spaces, but you should use underscore (\\_) or a period (.) instead of a space.\\\n-   Object names are case-sensitive (meaning that Dataset_A is different from dataset_A).\n-   Object names must begin with a letter (they cannot begin with a number like 1, 2 or 3).\n\n**Outputs**\n\nOutputs like tables and plots provide an example of how outputs can be saved as objects, or just be printed without being saved. A cross-tabulation of gender and outcome using the **base** R function `table()` can be printed directly to the R console (*without* being saved).\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# printed to R console only\ntable(linelist$gender, linelist$outcome)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n   \n    Death Recover\n  f  1227     953\n  m  1228     950\n```\n\n\n:::\n:::\n\n\nBut the same table can be saved as a named object. Then, optionally, it can be printed.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# save\ngen_out_table <- table(linelist$gender, linelist$outcome)\n\n# print\ngen_out_table\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n   \n    Death Recover\n  f  1227     953\n  m  1228     950\n```\n\n\n:::\n:::\n\n\n**Columns**\n\nColumns in a dataset are also objects and can be defined, over-written, and created as described below in the section on [Columns](https://epirhandbook.com/new_pages/basics.html#columnsvariables).\n\nYou can use the assignment operator from **base** R to create a new column. Below, the new column `bmi` (Body Mass Index) is created, and for each row the new value is result of a mathematical operation on the row's value in the `wt_kg` and `ht_cm` columns.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# create new \"bmi\" column using base R syntax\nlinelist$bmi <- linelist$wt_kg / (linelist$ht_cm/100)^2\n```\n:::\n\n\nHowever, in this handbook, we emphasize a different approach to defining columns, which uses the function `mutate()` from the **dplyr** package and *piping* with the pipe operator (`%>%`). The syntax is easier to read and there are other advantages explained in the page on [Cleaning data and core functions](cleaning.qmd). You can read more about *piping* in the Piping section below.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# create new \"bmi\" column using dplyr syntax\nlinelist <- linelist %>% \n  mutate(bmi = wt_kg / (ht_cm/100)^2)\n```\n:::\n\n\n<!-- ======================================================= -->\n\n### Object structure {.unnumbered}\n\n**Objects can be a single piece of data (e.g. `my_number <- 24`), or they can consist of structured data.**\n\nThe graphic below is borrowed from [this online R tutorial](http://venus.ifca.unican.es/Rintro/dataStruct.html). It shows some common data structures and their names. Not included in this image is spatial data, which is discussed in the [GIS basics](gis.qmd) page.\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/R_data_structures.png){fig-align='center' width=75% height=50%}\n:::\n:::\n\n\nIn epidemiology (and particularly field epidemiology), you will *most commonly* encounter data frames and vectors:\n\n+------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+\n| Common structure | Explanation                                                                                      | Example                                                                             |\n+------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+\n\n| Vectors          | A container for a sequence of singular objects, all of the same class (e.g. numeric, character). | **\"Variables\" (columns) in data frames are vectors** (e.g. the column `age_years`). |\n+------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+\n| Data Frames      | Vectors (e.g. columns) that are bound together that all have the same number of rows.            | `linelist` is a data frame.                                                         |\n+------------------+--------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------+\n\nNote that to create a vector that \"stands alone\" (is not part of a data frame) the function `c()` is used to combine the different elements. For example, if creating a vector of colors plot's color scale: `vector_of_colors <- c(\"blue\", \"red2\", \"orange\", \"grey\")`\n\n<!-- ======================================================= -->\n\n### Object classes {.unnumbered}\n\nAll the objects stored in R have a *class* which tells R how to handle the object. There are many possible classes, but common ones include:\n\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| Class      | Explanation                                                                                                                                                                             | Examples                                                                                              |\n+============+=========================================================================================================================================================================================+=======================================================================================================+\n| Character  | These are text/words/sentences **\"within quotation marks\"**. Math cannot be done on these objects.                                                                                      | \"Character objects are in quotation marks\"                                                            |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| Integer    | Numbers that are **whole only** (no decimals)                                                                                                                                           | -5, 14, or 2000                                                                                       |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| Numeric    | These are numbers and **can include decimals**. If within quotation marks they will be considered character class.                                                                      | 23.1 or 14                                                                                            |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| Factor     | These are vectors that have a **specified order** or hierarchy of values                                                                                                                | An variable of economic status with ordered values                                                    |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| Date       | **Once R is told that certain data are Dates**, these data can be manipulated and displayed in special ways. See the page on [Working with dates](dates.qmd) for more information.      | 2018-04-12 or 15/3/1954 or Wed 4 Jan 1980                                                           \n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| Logical    | Values must be one of the two special values TRUE or FALSE (note these are **not** \"TRUE\" and \"FALSE\" in quotation marks)                                                               | TRUE or FALSE                                                                                         |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| data.frame | A data frame is how R stores a **typical dataset**. It consists of vectors (columns) of data bound together, that all have the same number of observations (rows).                      | The example AJS dataset named `linelist_raw` contains 68 variables with 300 observations (rows) each. |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| tibble     | tibbles are a variation on data frame, the main operational difference being that they print more nicely to the console (display first 10 rows and only columns that fit on the screen) | Any data frame, list, or matrix can be converted to a tibble with `as_tibble()`                       |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n| list       | A list is like vector, but holds other objects that can be other different classes                                                                                                      | A list could hold a single number, and a data frame, and a vector, and even another list within it!    |\n+------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------------------------------------------------+\n\n**You can test the class of an object by providing its name to the function `class()`**. Note: you can reference a specific column within a dataset using the `$` notation to separate the name of the dataset and the name of the column.\n\n\n::: {.cell}\n\n```{.r .cell-code}\nclass(linelist)         # class should be a data frame or tibble\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"data.frame\"\n```\n\n\n:::\n\n```{.r .cell-code}\nclass(linelist$age)     # class should be numeric\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"numeric\"\n```\n\n\n:::\n\n```{.r .cell-code}\nclass(linelist$gender)  # class should be character\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"character\"\n```\n\n\n:::\n:::\n\n\nSometimes, a column will be converted to a different class automatically by R. Watch out for this! For example, if you have a vector or column of numbers, but a character value is inserted... the entire column will change to class character.\n\n\n::: {.cell}\n\n```{.r .cell-code}\nnum_vector <- c(1, 2 , 3, 4, 5) # define vector as all numbers\nclass(num_vector)          # vector is numeric class\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"numeric\"\n```\n\n\n:::\n\n```{.r .cell-code}\nnum_vector[3] <- \"three\"   # convert the third element to a character\nclass(num_vector)          # vector is now character class\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"character\"\n```\n\n\n:::\n:::\n\n\nOne common example of this is when manipulating a data frame in order to print a table - if you make a total row and try to paste/glue together percents in the same cell as numbers (e.g. `23 (40%)`), the entire numeric column above will convert to character and can no longer be used for mathematical calculations.**Sometimes, you will need to convert objects or columns to another class.**\n\n+------------------+---------------------------------------------------------------------------------------+\n| Function         | Action                                                                                |\n+==================+=======================================================================================+\n| `as.character()` | Converts to character class                                                           |\n+------------------+---------------------------------------------------------------------------------------+\n| `as.numeric()`   | Converts to numeric class                                                             |\n+------------------+---------------------------------------------------------------------------------------+\n| `as.integer()`   | Converts to integer class                                                             |\n+------------------+---------------------------------------------------------------------------------------+\n| `as.Date()`      | Converts to Date class - Note: see section on [dates](dates.qmd) for details          |\n+------------------+---------------------------------------------------------------------------------------+\n| `factor()`       | Converts to factor - Note: re-defining order of value levels requires extra arguments |\n+------------------+---------------------------------------------------------------------------------------+\n\nLikewise, there are **base** R functions to check whether an object IS of a specific class, such as `is.numeric()`, `is.character()`, `is.double()`, `is.factor()`, `is.integer()`\n\nHere is [more online material on classes and data structures in R](https://swcarpentry.github.io/r-novice-inflammation/13-supp-data-structures.html).\n\n<!-- ======================================================= -->\n\n### Columns/Variables (`$`) {.unnumbered}\n\n**A column in a data frame is technically a \"vector\" (see table above)** - a series of values that must all be the same class (either character, numeric, logical, etc).\n\nA vector can exist independent of a data frame, for example a vector of column names that you want to include as explanatory variables in a model. To create a \"stand alone\" vector, use the `c()` function as below:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# define the stand-alone vector of character values\nexplanatory_vars <- c(\"gender\", \"fever\", \"chills\", \"cough\", \"aches\", \"vomit\")\n\n# print the values in this named vector\nexplanatory_vars\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"gender\" \"fever\"  \"chills\" \"cough\"  \"aches\"  \"vomit\" \n```\n\n\n:::\n:::\n\n\n**Columns in a data frame are also vectors and can be called, referenced, extracted, or created using the `$` symbol.** The `$` symbol connects the name of the column to the name of its data frame. In this handbook, we try to use the word \"column\" instead of \"variable\".\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Retrieve the length of the vector age_years\nlength(linelist$age) # (age is a column in the linelist data frame)\n```\n:::\n\n\nBy typing the name of the data frame followed by `$` you will also see a drop-down menu of all columns in the data frame. You can scroll through them using your arrow key, select one with your Enter key, and avoid spelling mistakes!\n\n\n::: {.cell layout-align=\"center\"}\n::: {.cell-output-display}\n![](../images/Calling_Names.gif){fig-align='center' width=100%}\n:::\n:::\n\n\n[***ADVANCED TIP:*** Some more complex objects (e.g. a list, or an `epicontacts` object) may have multiple levels which can be accessed through multiple dollar signs. For example `epicontacts$linelist$date_onset`]{style=\"color: darkgreen;\"}\n\n<!-- ======================================================= -->\n\n### Access/index with brackets (`[ ]`) {.unnumbered}\n\nYou may need to view parts of objects, also called \"indexing\", which is often done using the square brackets `[ ]`. Using `$` on a data frame to access a column is also a type of indexing.\n\n\n::: {.cell}\n\n```{.r .cell-code}\nmy_vector <- c(\"a\", \"b\", \"c\", \"d\", \"e\", \"f\")  # define the vector\nmy_vector[5]                                  # print the 5th element\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"e\"\n```\n\n\n:::\n:::\n\n\nSquare brackets also work to return specific parts of an returned output, such as the output of a `summary()` function:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# All of the summary\nsummary(linelist$age)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n   Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's \n   0.00    6.00   13.00   16.07   23.00   84.00      86 \n```\n\n\n:::\n\n```{.r .cell-code}\n# Just the second element of the summary, with name (using only single brackets)\nsummary(linelist$age)[2]\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n1st Qu. \n      6 \n```\n\n\n:::\n\n```{.r .cell-code}\n# Just the second element, without name (using double brackets)\nsummary(linelist$age)[[2]]\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 6\n```\n\n\n:::\n\n```{.r .cell-code}\n# Extract an element by name, without showing the name\nsummary(linelist$age)[[\"Median\"]]\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 13\n```\n\n\n:::\n:::\n\n\nBrackets also work on data frames to view specific rows and columns. You can do this using the syntax `data frame[rows, columns]`:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# View a specific row (2) from dataset, with all columns (don't forget the comma!)\nlinelist[2,]\n\n# View all rows, but just one column\nlinelist[, \"date_onset\"]\n\n# View values from row 2 and columns 5 through 10\nlinelist[2, 5:10] \n\n# View values from row 2 and columns 5 through 10 and 18\nlinelist[2, c(5:10, 18)] \n\n# View rows 2 through 20, and specific columns\nlinelist[2:20, c(\"date_onset\", \"outcome\", \"age\")]\n\n# View rows and columns based on criteria\n# *** Note the data frame must still be named in the criteria!\nlinelist[linelist$age > 25 , c(\"date_onset\", \"outcome\", \"age\")]\n\n# Use View() to see the outputs in the RStudio Viewer pane (easier to read) \n# *** Note the capital \"V\" in View() function\nView(linelist[2:20, \"date_onset\"])\n\n# Save as a new object\nnew_table <- linelist[2:20, c(\"date_onset\")] \n```\n:::\n\n\nNote that you can also achieve the above row/column indexing on data frames and tibbles using **dplyr** syntax (functions `filter()` for rows, and `select()` for columns). Read more about these core functions in the [Cleaning data and core functions](cleaning.qmd) page.\n\nTo filter based on \"row number\", you can use the **dplyr** function `row_number()` with open parentheses as part of a logical filtering statement. Often you will use the `%in%` operator and a range of numbers as part of that logical statement, as shown below. To see the *first* N rows, you can also use the special **dplyr** function `head()`. Note, there is a function `head()` from **base** R, but this is overwritten by the **dplyr** function when you load **tidyverse**.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# View first 100 rows\nlinelist %>% head(100)\n\n# Show row 5 only\nlinelist %>% filter(row_number() == 5)\n\n# View rows 2 through 20, and three specific columns (note no quotes necessary on column names)\nlinelist %>% \n     filter(row_number() %in% 2:20) %>% \n     select(date_onset, outcome, age)\n```\n:::\n\n\nWhen indexing an object of class **list**, single brackets always return with class list, even if only a single object is returned. Double brackets, however, can be used to access a single element and return a different class than list. Brackets can also be written after one another, as demonstrated below.\n\nThis [visual explanation of lists indexing, with pepper shakers](https://r4ds.had.co.nz/vectors.html#lists-of-condiments) is humorous and helpful.\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# define demo list\nmy_list <- list(\n  # First element in the list is a character vector\n  hospitals = c(\"Central\", \"Empire\", \"Santa Anna\"),\n  \n  # second element in the list is a data frame of addresses\n  addresses   = data.frame(\n    street = c(\"145 Medical Way\", \"1048 Brown Ave\", \"999 El Camino\"),\n    city   = c(\"Andover\", \"Hamilton\", \"El Paso\")\n    )\n  )\n```\n:::\n\n\nHere is how the list looks when printed to the console. See how there are two named elements:\n\n-   `hospitals`, a character vector\\\n-   `addresses`, a data frame of addresses\n\n\n::: {.cell}\n\n```{.r .cell-code}\nmy_list\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n$hospitals\n[1] \"Central\"    \"Empire\"     \"Santa Anna\"\n\n$addresses\n           street     city\n1 145 Medical Way  Andover\n2  1048 Brown Ave Hamilton\n3   999 El Camino  El Paso\n```\n\n\n:::\n:::\n\n\nNow we extract, using various methods:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nmy_list[1] # this returns the element in class \"list\" - the element name is still displayed\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n$hospitals\n[1] \"Central\"    \"Empire\"     \"Santa Anna\"\n```\n\n\n:::\n\n```{.r .cell-code}\nmy_list[[1]] # this returns only the (unnamed) character vector\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"Central\"    \"Empire\"     \"Santa Anna\"\n```\n\n\n:::\n\n```{.r .cell-code}\nmy_list[[\"hospitals\"]] # you can also index by name of the list element\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"Central\"    \"Empire\"     \"Santa Anna\"\n```\n\n\n:::\n\n```{.r .cell-code}\nmy_list[[1]][3] # this returns the third element of the \"hospitals\" character vector\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"Santa Anna\"\n```\n\n\n:::\n\n```{.r .cell-code}\nmy_list[[2]][1] # This returns the first column (\"street\") of the address data frame\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n           street\n1 145 Medical Way\n2  1048 Brown Ave\n3   999 El Camino\n```\n\n\n:::\n:::\n\n\n<!-- ======================================================= -->\n\n### Remove objects {.unnumbered}\n\nYou can remove individual objects from your R environment by putting the name in the `rm()` function (no quote marks):\n\n\n::: {.cell}\n\n```{.r .cell-code}\nrm(object_name)\n```\n:::\n\n\nYou can remove all objects (clear your workspace) by running:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nrm(list = ls(all = TRUE))\n```\n:::\n\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n## Piping (`%>%`)\n\n**Two general approaches to working with objects are:**\n\n1)  **Pipes/tidyverse** - pipes send an object from function to function - emphasis is on the *action*, not the object.\\\n2)  **Define intermediate objects** - an object is re-defined again and again - emphasis is on the object.\n\n<!-- ======================================================= -->\n\n### **Pipes** {.unnumbered}\n\n**Simply explained, the pipe operator passes an intermediate output from one function to the next.**\\\nYou can think of it as saying \"and then\". Many functions can be linked together with `%>%`.\n\n-   **Piping emphasizes a sequence of actions, not the object the actions are being performed on**.\\\n-   Pipes are best when a sequence of actions must be performed on one object.\\\n-   Pipes can make code more clean and easier to read, more intuitive.\n\nPipe operators were first introduced through the [magrittr package](https://magrittr.tidyverse.org/), which is part of tidyverse, and were specified as `%>%`. In R 4.1.0, they introduced a **base** R pipe which is specified through `|>`. The behaviour of the two pipes is the same, and they can be used somewhat interchangeably. However, there are a few key differences.\n\n* The `%>%` pipe allows you to pass multiple arguments.\n* The `%>%` pipe lets you drop parenthesis when calling a function with no other arguments (i.e. drop vs drop()).\n* The `%>%` pipe allows you to start a pipe with `.` to create a function in your linking of code.\n\nFor these reasons, we recommend the **magrittr** pipe, `%>%`, over the **base** R pipe, `|>`.\n\nTo read more about the differences between base R and tidyverse (magrittr) pipes, see this [blog post](https://www.tidyverse.org/blog/2023/04/base-vs-magrittr-pipe/). For more information on the tidyverse approach, please see this [style guide](https://style.tidyverse.org/pipes.html).\n\nHere is a fake example for comparison, using fictional functions to \"bake a cake\". First, the pipe method:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# A fake example of how to bake a cake using piping syntax\n\ncake <- flour %>%       # to define cake, start with flour, and then...\n  add(eggs) %>%   # add eggs\n  add(oil) %>%    # add oil\n  add(water) %>%  # add water\n  mix_together(         # mix together\n    utensil = spoon,\n    minutes = 2) %>%    \n  bake(degrees = 350,   # bake\n       system = \"fahrenheit\",\n       minutes = 35) %>%  \n  let_cool()            # let it cool down\n```\n:::\n\n\nNote that just like other R commands, pipes can be used to just display the result, or to save/re-save an object, depending on whether the assignment operator `<-` is involved. See both below:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# Create or overwrite object, defining as aggregate counts by age category (not printed)\nlinelist_summary <- linelist %>% \n  count(age_cat)\n```\n:::\n\n::: {.cell}\n\n```{.r .cell-code}\n# Print the table of counts in the console, but don't save it\nlinelist %>% \n  count(age_cat)\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n  age_cat    n\n1     0-4 1095\n2     5-9 1095\n3   10-14  941\n4   15-19  743\n5   20-29 1073\n6   30-49  754\n7   50-69   95\n8     70+    6\n9    <NA>   86\n```\n\n\n:::\n:::\n\n\n**`%<>%`**\\\nThis is an \"assignment pipe\" from the **magrittr** package, which *pipes an object forward and also re-defines the object*. It must be the first pipe operator in the chain. It is shorthand. The below two commands are equivalent:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nlinelist <- linelist %>%\n  filter(age > 50)\n\nlinelist %<>% filter(age > 50)\n```\n:::\n\n\n<!-- ======================================================= -->\n\n### Define intermediate objects {.unnumbered}\n\nThis approach to changing objects/data frames may be better if:\n\n-   You need to manipulate multiple objects\\\n-   There are intermediate steps that are meaningful and deserve separate object names\n\n**Risks:**\n\n-   Creating new objects for each step means creating lots of objects. If you use the wrong one you might not realize it!\\\n-   Naming all the objects can be confusing.\\\n-   Errors may not be easily detectable.\n\nEither name each intermediate object, or overwrite the original, or combine all the functions together. All come with their own risks.\n\nBelow is the same fake \"cake\" example as above, but using this style:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# a fake example of how to bake a cake using this method (defining intermediate objects)\nbatter_1 <- left_join(flour, eggs)\nbatter_2 <- left_join(batter_1, oil)\nbatter_3 <- left_join(batter_2, water)\n\nbatter_4 <- mix_together(object = batter_3, utensil = spoon, minutes = 2)\n\ncake <- bake(batter_4, degrees = 350, system = \"fahrenheit\", minutes = 35)\n\ncake <- let_cool(cake)\n```\n:::\n\n\nCombine all functions together - this is difficult to read:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# an example of combining/nesting mutliple functions together - difficult to read\ncake <- let_cool(bake(mix_together(batter_3, utensil = spoon, minutes = 2), degrees = 350, system = \"fahrenheit\", minutes = 35))\n```\n:::\n\n\n<!-- ======================================================= -->\n\n## Key operators and functions {#operators}\n\nThis section details operators in R, such as:\n\n-   Definitional operators.\\\n-   Relational operators (less than, equal too..).\\\n-   Logical operators (and, or...).\\\n-   Handling missing values.\\\n-   Mathematical operators and functions (+/-, \\>, sum(), median(), ...).\\\n-   The `%in%` operator.\n\n<!-- ======================================================= -->\n\n### Assignment operators {.unnumbered}\n\n**`<-`**\n\nThe basic assignment operator in R is `<-`. Such that `object_name <- value`.\\\nThis assignment operator can also be written as `=`. We advise use of `<-` for general R use. We also advise surrounding such operators with spaces, for readability.\n\n**`<<-`**\n\nIf [Writing functions](writing_functions.qmd), or using R in an interactive way with sourced scripts, then you may need to use this assignment operator `<<-` (from **base** R). This operator is used to define an object in a higher 'parent' R Environment. See this [online reference](https://stat.ethz.ch/R-manual/R-devel/library/base/html/assignOps.html).\n\n**`%<>%`**\n\nThis is an \"assignment pipe\" from the **magrittr** package, which pipes an object forward and *also re-defines the object*. It must be the first pipe operator in the chain. It is shorthand, as shown below in two equivalent examples:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nlinelist <- linelist %>% \n  mutate(age_months = age_years * 12)\n```\n:::\n\n\nThe above is equivalent to the below:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nlinelist %<>% mutate(age_months = age_years * 12)\n```\n:::\n\n\n**`%<+%`**\n\nThis is used to add data to phylogenetic trees with the **ggtree** package. See the page on [Phylogenetic trees](phylogenetic_trees.qmd) or this online [resource book](https://yulab-smu.top/treedata-book/).\n\n<!-- ======================================================= -->\n\n### Relational and logical operators {.unnumbered}\n\nRelational operators compare values and are often used when defining new variables and subsets of datasets. Here are the common relational operators in R:\n\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Meaning                  | Operator   | Example      | Example Result                                                                                                                                         |\n+==========================+============+==============+========================================================================================================================================================+\n| Equal to                 | `==`       | `\"A\" == \"a\"` | `FALSE` (because R is case sensitive) *Note that == (double equals) is different from = (single equals), which acts like the assignment operator `<-`* |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Not equal to             | `!=`       | `2 != 0`     | `TRUE`                                                                                                                                                 |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Greater than             | `>`        | `4 > 2`      | `TRUE`                                                                                                                                                 |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Less than                | `<`        | `4 < 2`      | `FALSE`                                                                                                                                                |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Greater than or equal to | `>=`       | `6 >= 4`     | `TRUE`                                                                                                                                                 |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Less than or equal to    | `<=`       | `6 <= 4`     | `FALSE`                                                                                                                                                |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Value is missing         | `is.na()`  | `is.na(7)`   | `FALSE` (see page on [Missing data](missing_data.qmd))                                                                                                 |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n| Value is not missing     | `!is.na()` | `!is.na(7)`  | `TRUE`                                                                                                                                                 |\n+--------------------------+------------+--------------+--------------------------------------------------------------------------------------------------------------------------------------------------------+\n\nLogical operators, such as AND and OR, are often used to connect relational operators and create more complicated criteria. Complex statements might require parentheses `( )` for grouping and order of application.\n\n+---------------------+-----------------------------------------------------------------------+\n| Meaning             | Operator                                                              |\n+=====================+=======================================================================+\n| AND                 | `&`                                                                   |\n+---------------------+-----------------------------------------------------------------------+\n| OR                  | `|` (vertical bar)                                                    |\n+---------------------+-----------------------------------------------------------------------+\n| Parentheses         | `( )` Used to group criteria together and clarify order of operations |\n+---------------------+-----------------------------------------------------------------------+\n\nFor example, below, we have a linelist with two variables we want to use to create our case definition, `hep_e_rdt`, a test result and `other_cases_in_hh`, which will tell us if there are other cases in the household. The command below uses the function `case_when()` to create the new variable `case_def` such that:\n\n\n::: {.cell}\n\n```{.r .cell-code}\nlinelist_cleaned <- linelist %>%\n  mutate(case_def = case_when(\n    is.na(rdt_result) & is.na(other_case_in_home)            ~ NA_character_,\n    rdt_result == \"Positive\"                                 ~ \"Confirmed\",\n    rdt_result != \"Positive\" & other_cases_in_home == \"Yes\"  ~ \"Probable\",\n    TRUE                                                     ~ \"Suspected\"\n  ))\n```\n:::\n\n\n+------------------------------------------------------------------------------------------------+--------------------------------------------+\n| Criteria in example above                                                                      | Resulting value in new variable \"case_def\" |\n+================================================================================================+============================================+\n| If the value for variables `rdt_result` and `other_cases_in_home` are missing                  | `NA` (missing)                             |\n+------------------------------------------------------------------------------------------------+--------------------------------------------+\n| If the value in `rdt_result` is \"Positive\"                                                     | \"Confirmed\"                                |\n+------------------------------------------------------------------------------------------------+--------------------------------------------+\n| If the value in `rdt_result` is NOT \"Positive\" AND the value in `other_cases_in_home` is \"Yes\" | \"Probable\"                                 |\n+------------------------------------------------------------------------------------------------+--------------------------------------------+\n| If one of the above criteria are not met                                                       | \"Suspected\"                                |\n+------------------------------------------------------------------------------------------------+--------------------------------------------+\n\n*Note that R is case-sensitive, so \"Positive\" is different than \"positive\".*\n\n<!-- ======================================================= -->\n\n### Missing values {.unnumbered}\n\nIn R, missing values are represented by the special value `NA` (a \"reserved\" value) (capital letters N and A - not in quotation marks). If you import data that records missing data in another way (e.g. 99, \"Missing\"), you may want to re-code those values to `NA`. How to do this is addressed in the [Import and export](importing.qmd) page.\n\n**To test whether a value is `NA`, use the special function `is.na()`**, which returns `TRUE` or `FALSE`.\n\n\n::: {.cell}\n\n```{.r .cell-code}\nrdt_result <- c(\"Positive\", \"Suspected\", \"Positive\", NA)   # two positive cases, one suspected, and one unknown\nis.na(rdt_result)  # Tests whether the value of rdt_result is NA\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] FALSE FALSE FALSE  TRUE\n```\n\n\n:::\n:::\n\n\nRead more about missing, infinite, `NULL`, and impossible values in the page on [Missing data](missing_data.qmd). Learn how to convert missing values when importing data in the page on [Import and export](importing.qmd).\n\n<!-- ======================================================= -->\n\n### Mathematics and statistics {.unnumbered}\n\nAll the operators and functions in this page are automatically available using **base** R.\n\n#### Mathematical operators {.unnumbered}\n\nThese are often used to perform addition, division, to create new columns, etc. Below are common mathematical operators in R. Whether you put spaces around the operators is not important.\n\n| Purpose             | Example in R |\n|---------------------|--------------|\n| addition            | 2 + 3        |\n| subtraction         | 2 - 3        |\n| multiplication      | 2 \\* 3       |\n| division            | 30 / 5       |\n| exponent            | 2\\^3         |\n| order of operations | ( )          |\n\n#### Mathematical functions {.unnumbered}\n\n| Purpose            | Function                              |\n|--------------------|---------------------------------------|\n| rounding           | round(x, digits = n)                  |\n| rounding           | janitor::round_half_up(x, digits = n) |\n| ceiling (round up) | ceiling(x)                            |\n| floor (round down) | floor(x)                              |\n| absolute value     | abs(x)                                |\n| square root        | sqrt(x)                               |\n| exponent           | exponent(x)                           |\n| natural logarithm  | log(x)                                |\n| log base 10        | log10(x)                              |\n| log base 2         | log2(x)                               |\n\nNote: for `round()` the `digits =` specifies the number of decimal placed. Use `signif()` to round to a number of significant figures.\n\n#### Scientific notation {.unnumbered}\n\nThe likelihood of scientific notation being used depends on the value of the `scipen` option.\n\nFrom the documentation of `?options`: scipen is a penalty to be applied when deciding to print numeric values in fixed or exponential notation. Positive values bias towards fixed and negative towards scientific notation: fixed notation will be preferred unless it is more than 'scipen' digits wider.\n\nIf it is set to a low number (e.g. 0) it will be \"turned on\" always. To \"turn off\" scientific notation in your R session, set it to a very high number, for example:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# turn off scientific notation\noptions(scipen = 999)\n```\n:::\n\n\n#### Rounding {.unnumbered}\n\n[***DANGER:*** `round()` uses \"banker's rounding\" which rounds up from a .5 only if the upper number is even. Use `round_half_up()` from **janitor** to consistently round halves up to the nearest whole number. See [this explanation](https://cran.r-project.org/web/packages/janitor/vignettes/janitor.html#explore-records-with-duplicated-values-for-specific-combinations-of-variables-with-get_dupes) ]{style=\"color: red;\"}\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# use the appropriate rounding function for your work\nround(c(2.5, 3.5))\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 2 4\n```\n\n\n:::\n\n```{.r .cell-code}\njanitor::round_half_up(c(2.5, 3.5))\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 3 4\n```\n\n\n:::\n:::\n\n\n#### Statistical functions {.unnumbered}\n\n[***CAUTION:*** The functions below will by default include missing values in calculations. Missing values will result in an output of `NA`, unless the argument `na.rm = TRUE` is specified. This can be written shorthand as `na.rm = T`.]{style=\"color: orange;\"}\n\n| Objective               | Function             |\n|-------------------------|----------------------|\n| mean (average)          | mean(x, na.rm = T)   |\n| median                  | median(x, na.rm=  T) |\n| standard deviation      | sd(x, na.rm = T)     |\n| quantiles\\*             | quantile(x, probs)   |\n| sum                     | sum(x, na.rm = T)    |\n| minimum value           | min(x, na.rm = T)    |\n| maximum value           | max(x, na.rm = T)    |\n| range of numeric values | range(x, na.rm = T)  |\n| summary\\*\\*             | summary(x)           |\n\nNotes:\n\n-   `*quantile()`: `x` is the numeric vector to examine, and `probs =` is a numeric vector with probabilities within 0 and 1.0, e.g `c(0.5, 0.8, 0.85)`.\n-   `**summary()`: gives a summary on a numeric vector including mean, median, and common percentiles.\n\n[***DANGER:*** If providing a vector of numbers to one of the above functions, be sure to wrap the numbers within `c()` .]{style=\"color: red;\"}\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# If supplying raw numbers to a function, wrap them in c()\nmean(1, 6, 12, 10, 5, 0)    # !!! INCORRECT !!!  \n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 1\n```\n\n\n:::\n\n```{.r .cell-code}\nmean(c(1, 6, 12, 10, 5, 0)) # CORRECT\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] 5.666667\n```\n\n\n:::\n:::\n\n\n#### Other useful functions {.unnumbered}\n\n+----------------------------+-------------------+-------------------------------------------------+\n| Objective                  | Function          | Example                                         |\n+============================+===================+=================================================+\n| create a sequence          | seq(from, to, by) | `seq(1, 10, 2)`                                 |\n+----------------------------+-------------------+-------------------------------------------------+\n| repeat x, n times          | rep(x, ntimes)    | `rep(1:3, 2)` or `rep(c(\"a\", \"b\", \"c\"), 3)`     |\n+----------------------------+-------------------+-------------------------------------------------+\n| subdivide a numeric vector | cut(x, n)         | `cut(linelist$age, 5)`                          |\n+----------------------------+-------------------+-------------------------------------------------+\n| take a random sample       | sample(x, size)   | `sample(linelist$id, size = 5, replace = TRUE)` |\n+----------------------------+-------------------+-------------------------------------------------+\n\n<!-- ======================================================= -->\n\n### `%in%` {.unnumbered}\n\nA very useful operator for matching values, and for quickly assessing if a value is within a vector or data frame.\n\n\n::: {.cell}\n\n```{.r .cell-code}\nmy_vector <- c(\"a\", \"b\", \"c\", \"d\")\n```\n:::\n\n::: {.cell}\n\n```{.r .cell-code}\n\"a\" %in% my_vector\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] TRUE\n```\n\n\n:::\n\n```{.r .cell-code}\n\"h\" %in% my_vector\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] FALSE\n```\n\n\n:::\n:::\n\n\nTo ask if a value is **not** `%in%` a vector, put an exclamation mark (!) **in front** of the logic statement:\n\n\n::: {.cell}\n\n```{.r .cell-code}\n# to negate, put an exclamation in front\n!\"a\" %in% my_vector\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] FALSE\n```\n\n\n:::\n\n```{.r .cell-code}\n!\"h\" %in% my_vector\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] TRUE\n```\n\n\n:::\n:::\n\n\n`%in%` is very useful when using the **dplyr** function `case_when()`. You can define a vector previously, and then reference it later. For example:\n\n\n::: {.cell}\n\n```{.r .cell-code}\naffirmative <- c(\"1\", \"Yes\", \"YES\", \"yes\", \"y\", \"Y\", \"oui\", \"Oui\", \"Si\")\n\nlinelist <- linelist %>% \n  mutate(child_hospitaled = case_when(\n    hospitalized %in% affirmative & age < 18 ~ \"Hospitalized Child\",\n    TRUE                                      ~ \"Not\"))\n```\n:::\n\n\nNote: If you want to detect a partial string, perhaps using `str_detect()` from **stringr**, it will not accept a character vector like `c(\"1\", \"Yes\", \"yes\", \"y\")`. Instead, it must be given a *regular expression* - one condensed string with OR bars, such as \"1\\|Yes\\|yes\\|y\". For example, `str_detect(hospitalized, \"1|Yes|yes|y\")`. See the page on [Characters and strings](characters_strings.qmd) for more information.\n\nYou can convert a character vector to a named regular expression with this command:\n\n\n::: {.cell}\n\n```{.r .cell-code}\naffirmative <- c(\"1\", \"Yes\", \"YES\", \"yes\", \"y\", \"Y\", \"oui\", \"Oui\", \"Si\")\naffirmative\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"1\"   \"Yes\" \"YES\" \"yes\" \"y\"   \"Y\"   \"oui\" \"Oui\" \"Si\" \n```\n\n\n:::\n\n```{.r .cell-code}\n# condense to \naffirmative_str_search <- paste0(affirmative, collapse = \"|\")  # option with base R\naffirmative_str_search <- str_c(affirmative, collapse = \"|\")   # option with stringr package\n\naffirmative_str_search\n```\n\n::: {.cell-output .cell-output-stdout}\n\n```\n[1] \"1|Yes|YES|yes|y|Y|oui|Oui|Si\"\n```\n\n\n:::\n:::\n\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n<!-- ======================================================= -->\n\n## Errors & warnings\n\nThis section explains:\n\n-   The difference between errors and warnings.\\\n-   General syntax tips for writing R code.\\\n-   Code assists.\n\nCommon errors and warnings and troubleshooting tips can be found in the page on [Errors and help](errors.qmd).\n\n<!-- ======================================================= -->\n\n### Error versus Warning {.unnumbered}\n\nWhen a command is run, the R Console may show you warning or error messages in red text.\n\n-   A **warning** means that R has completed your command, but had to take additional steps or produced unusual output that you should be aware of.\n\n-   An **error** means that R was not able to complete your command.\n\nLook for clues:\n\n-   The error/warning message will often include a line number for the problem.\n\n-   If an object \"is unknown\" or \"not found\", perhaps you spelled it incorrectly, forgot to call a package with library(), or forgot to re-run your script after making changes.\n\nIf all else fails, copy the error message into Google along with some key terms - chances are that someone else has worked through this already!\n\n<!-- ======================================================= -->\n\n### General syntax tips {.unnumbered}\n\nA few things to remember when writing commands in R, to avoid errors and warnings:\n\n-   Always close parentheses - tip: count the number of opening \"(\" and closing parentheses \")\" for each code chunk.\n-   Avoid spaces in column and object names. Use underscore ( \\_ ) or periods ( . ) instead.\n-   Keep track of and remember to separate a function's arguments with commas.\n-   R is case-sensitive, meaning `Variable_A` is *different* from `variable_A`.\n\n<!-- ======================================================= -->\n\n### Code assists {.unnumbered}\n\nAny script (RMarkdown or otherwise) will give clues when you have made a mistake. For example, if you forgot to write a comma where it is needed, or to close a parentheses, RStudio will raise a flag on that line, on the right side of the script, to warn you.\n",
+    "supporting": [
+      "basics_files"
+    ],
+    "filters": [
+      "rmarkdown/pagebreak.lua"
+    ],
+    "includes": {},
+    "engineDependencies": {},
+    "preserve": {},
+    "postProcess": true
+  }
+}
\ No newline at end of file
diff --git a/new_pages/dates.qmd b/new_pages/dates.qmd
index b0c401c4..f3cc3f55 100644
--- a/new_pages/dates.qmd
+++ b/new_pages/dates.qmd
@@ -262,8 +262,40 @@ linelist <- linelist %>%
   mutate(date_onset = parse_date(date_onset))
 ```
 
+Another function we can use is `fix_date_df` from the [**datefixR** package](https://docs.ropensci.org/datefixR/). This package can take in a wide variety of different, messy, date formats at the same time and set them to a standard format!
 
+```{r}
+
+pacman::p_load(
+     datefixR
+)
+
+#Set up messy dates
+messy_data_table <- data.frame(
+     case = 1:6,
+     onset_date = c("2014-01-01",
+                    "05 9 14",
+                    "2014 july",
+                    "1st Apr 2014",
+                    "15 le avril 2014",
+                    2015
+                    )
+     )
+
+messy_data_table
+
+#Fix the dates
+fix_date_df(
+     df = messy_data_table,
+     col.names = c("onset_date")
+)
+
+
+```
+
+You can see that even with this range of different formats (and languages!) it has managed to format all of our dates in the same way. Note that for dates missing a "month" it uses the default of 7 (July) and those missing a day it defaults to 1 (1st day of the month). These can be customised using the arguments `day.impute = ` and `month.impute = `.
 
+For a list of the languages that can be used, and additional functions and limitations, please see the [website](https://docs.ropensci.org/datefixR/).
 
 <!-- ======================================================= -->
 ## Working with date-time class  
diff --git a/new_pages/errors.qmd b/new_pages/errors.qmd
index 49b2f8fd..f19aa6d9 100644
--- a/new_pages/errors.qmd
+++ b/new_pages/errors.qmd
@@ -117,7 +117,7 @@ ggplot() scale_fill_manual() values = c("orange", "purple") ... insufficient for
 ```
 Can't add x object
 ```
-You probably have an extra `+` at the end of a ggplot command that you need to delete.
+This is likely a ggplot error from the use of `scale_fill_manual()`, where you have not provided enough colors for the number of unique values. If the column is class factor, consider whether `NA` is a factor level.
 
 
 ### R Markdown errors {.unnumbered}  
diff --git a/new_pages/ggplot_basics.qmd b/new_pages/ggplot_basics.qmd
index 3dd948a7..0dae6b37 100644
--- a/new_pages/ggplot_basics.qmd
+++ b/new_pages/ggplot_basics.qmd
@@ -525,11 +525,6 @@ ggplot(malaria_data,
 
 <!-- ``` -->
 
-### Factor level order in facets {.unnumbered}  
-
-See this [post](https://juliasilge.com/blog/reorder-within/) on how to re-order factor levels *within* facets.  
-
-
 ## Storing plots  
 
 ### Saving plots {.unnumbered}
diff --git a/new_pages/ggplot_tips.qmd b/new_pages/ggplot_tips.qmd
index 1ef408a0..3b46b501 100644
--- a/new_pages/ggplot_tips.qmd
+++ b/new_pages/ggplot_tips.qmd
@@ -700,7 +700,7 @@ This also works well with faceting functions - it allows the user to produce fac
 
 ```{r, , warning=F, message=F}
 
-# produce a histogram of all cases by age
+# produce a linegraph of all cases by age
 linelist %>% 
   count(week = lubridate::floor_date(date_hospitalisation, "week"),
         hospital) %>% 
@@ -710,7 +710,8 @@ linelist %>%
                           color = hospital)) +
   theme_minimal() +
   gghighlight::gghighlight() +                      # highlight instances where the patient has died
-  facet_wrap(~hospital)                              # make facets by outcome
+  facet_wrap(~hospital) +                        # make facets by outcome
+     scale_x_date(labels = date_format("%m/%y"))
 
 ```
 
diff --git a/new_pages/regression.qmd b/new_pages/regression.qmd
index e80a8d32..cca9538c 100644
--- a/new_pages/regression.qmd
+++ b/new_pages/regression.qmd
@@ -439,6 +439,34 @@ univ_tab <- linelist %>%
 univ_tab
 ```
 
+### Cross-tabulation
+
+The **gtsummary** package also allows us to quickly and easily create tables of counts. This can be useful for quickly summarising the data, and putting it in context with the regression we have carried out.
+
+```{r kruskal_gt}
+
+#Carry out our regression
+univ_tab <- linelist %>% 
+  dplyr::select(explanatory_vars, outcome) %>% ## select variables of interest
+
+  tbl_uvregression(                         ## produce univariate table
+    method = glm,                           ## define regression want to run (generalised linear model)
+    y = outcome,                            ## define outcome variable
+    method.args = list(family = binomial),  ## define what type of glm want to run (logistic)
+    exponentiate = TRUE                     ## exponentiate to produce odds ratios (rather than log odds)
+  )
+
+#Create our cross tabulation
+cross_tab <- linelist %>%
+  dplyr::select(explanatory_vars, outcome) %>%   ## select variables of interest
+     tbl_summary(by = outcome)                   ## create summary table
+
+tbl_merge(tbls = list(cross_tab,
+                      univ_tab),
+          tab_spanner = c("Summary", "Univariate regression"))
+
+```
+
 There are many modifications you can make to this table output, such as adjusting the text labels, bolding rows by their p-value, etc. See tutorials [here](http://www.danieldsjoberg.com/gtsummary/articles/tbl_regression.html) and elsewhere online.  
 
 
@@ -456,11 +484,11 @@ To do this, you will want to split your dataset into the strata of interest. For
 ```{r}
 
 f_linelist <- linelist %>%
-     filter(gender == "f") %>%                 ## subset to only where the gender == "f"
+     filter(gender == 0) %>%                 ## subset to only where the gender == "f"
   dplyr::select(explanatory_vars, outcome)     ## select variables of interest
      
 m_linelist <- linelist %>%
-     filter(gender == "f") %>%                 ## subset to only where the gender == "f"
+     filter(gender == 1) %>%                 ## subset to only where the gender == "f"
   dplyr::select(explanatory_vars, outcome)     ## select variables of interest
 
 ```
@@ -759,6 +787,41 @@ final_mv_reg %>%
   
 ```
 
+## Model performance
+
+Once you have built your regression models, you may want to assess how well the model has fit the data. There are many different approaches to do this, and many different metrics with which to assess your model fit, and how it compares with other model formulations. How you assess your model fit will depend on your model, the data, and the context in which you are conducting your work.
+
+While there are many different functions, and many different packages, to assess model fit, one package that nicely combines several different metrics and approaches into a single source is the [**performance** package](https://easystats.github.io/performance/). This package allows you to assess model assumptions (such as linearity, homogeneity, highlight outliers, etc.) and check how well the model performs (Akaike Information Criterion values, R2, RMSE, etc) with a few simple functions.
+
+Unfortunately, we are unable to use this package with **gtsummary**, but it readily accepts objects generated by other packages such as **stats**, **lmerMod** and **tidymodels**. Here we will demonstrate its application using the function `glm()` for a multivariable regression. To do this we can use the function `performance()` to assess model fit, and `compare_perfomrance()` to compare the two models.
+
+```{r}
+
+#Load in packages
+pacman::p_load(performance)
+
+#Set up regression models
+regression_one <- linelist %>%
+     select(outcome, gender, fever, chills, cough) %>%
+     glm(formula = outcome ~ .,
+         family = binomial)
+
+regression_two <- linelist %>%
+     select(outcome, days_onset_hosp, aches, vomit, age_years) %>%
+     glm(formula = outcome ~ .,
+         family = binomial)
+
+#Assess model fit
+performance(regression_one)
+performance(regression_two)
+
+#Compare model fit
+compare_performance(regression_one,
+                    regression_two)
+
+```
+
+For further reading on the **performance** package, and the model tests you can carry out, see their [github](https://easystats.github.io/performance/index.html).
 
 <!-- ======================================================= -->
 
diff --git a/new_pages/shiny_basics.qmd b/new_pages/shiny_basics.qmd
index 78eb9512..d46e81b4 100644
--- a/new_pages/shiny_basics.qmd
+++ b/new_pages/shiny_basics.qmd
@@ -1348,7 +1348,7 @@ knitr::include_graphics(here::here("images", "shiny", "app_table_view.gif"))
 
 Now that you've developed your app, you probably want to share it with others - this is the main advantage of shiny after all! We can do this by sharing the code directly, or we could publish on a server. If we share the code, others will be able to see what you've done and build on it, but this will negate one of the main advantages of shiny - *it can eliminate the need for end-users to maintain an R installation*. For this reason, if you're sharing your app with users who are not comfortable with R, it is much easier to share an app that has been published on a server. 
 
-If you'd rather share the code, you could make a .zip file of the app, or better yet, *publish your app on github and add collaborators.* You can refer to the section on github for further information here.
+If you'd rather share the code, you could make a .zip file of the app, or better yet, *publish your app on github and add collaborators.* You can refer to the section on github for further information [here](collaboration.qmd).
 
 However, if we're publishing the app online, we need to do a little more work. Ultimately, we want your app to be able to be accessed via a web URL so others can get quick and easy access to it. Unfortunately, to publish you app on a server, you need to have access to a server to publish it on! There are a number of hosting options when it comes to this:
 
@@ -1356,9 +1356,9 @@ However, if we're publishing the app online, we need to do a little more work. U
 
 - _RStudio Connect_: this is a far more powerful version of an R server, that can perform many operations, including publishing shiny apps. It is however, harder to use, and less recommended for first-time users.
 
-For the purposes of this document, we will use _shinyapps.io_, since it is easier for first time users. You can make a free account here to start - there are also different price plans for server licesnses if needed. The more users you expect to have, the more expensive your price plan may have to be, so keep this under consideration. If you're looking to create something for a small set of individuals to use, a free license may be perfectly suitable, but a public facing app may need more licenses.
+For the purposes of this document, we will use _shinyapps.io_, since it is easier for first time users. You can make a free account [here](https://www.shinyapps.io/) to start - there are also different price plans for server licesnses if needed. The more users you expect to have, the more expensive your price plan may have to be, so keep this under consideration. If you're looking to create something for a small set of individuals to use, a free license may be perfectly suitable, but a public facing app may need more licenses.
 
-First we should make sure our app is suitable for publishing on a server. In your app, you should restart your R session, and ensure that it runs without running any extra code. This is important, as an app that requires package loading, or data reading not defined in your app code won't run on a server. Also note that you can't have any *explicit* file paths in your app - these will be invalid in the server setting - using the `here` package solves this issue very well. Finally, if you're reading data from a source that requires user-authentication, such as your organisation's servers, this will not generally work on a server. You will need to liase with your IT department to figure out how to whitelist the shiny server here.
+First we should make sure our app is suitable for publishing on a server. In your app, you should restart your R session, and ensure that it runs without running any extra code. This is important, as an app that requires package loading, or data reading not defined in your app code won't run on a server. Also note that you can't have any *explicit* file paths in your app - these will be invalid in the server setting - using the `here` package solves this issue very well. Finally, if you're reading data from a source that requires user-authentication, such as your organisation's servers, this will not generally work on a server. You will need to liase with your IT department to figure out how to whitelist the shiny server [here](https://docs.posit.co/shiny-server/).
 
 *signing up for account*
 
diff --git a/new_pages/standardization.qmd b/new_pages/standardization.qmd
index 2c5fe5a5..0aa23eca 100644
--- a/new_pages/standardization.qmd
+++ b/new_pages/standardization.qmd
@@ -1,9 +1,8 @@
 
 # Standardised rates { }  
 
-This page will show you two ways to standardize an outcome, such as hospitalizations or mortality, by characteristics such as age and sex. 
+This page will show you how to standardize an outcome, such as hospitalizations or mortality, by characteristics such as age and sex. 
 
-* Using **dsr** package 
 * Using **PHEindicatormethods** package  
 
 We begin by extensively demonstrating the processes of data preparation/cleaning/joining, as this is common when combining population data from multiple countries, standard population data, deaths, etc.  
@@ -41,39 +40,11 @@ pacman::p_load(
      rio,                 # import/export data
      here,                # locate files
      stringr,             # cleaning characters and strings
-     frailtypack,         # needed for dsr, for frailty models
-     dsr,                 # standardise rates
      PHEindicatormethods, # alternative for rate standardisation
      tidyverse            # data management and visualization
 )
 ```
 
-
-<span style="color: orange;">**_CAUTION:_** If you have a newer version of R, the **dsr** package cannot be directly downloaded from CRAN. However, it is still available from the CRAN archive. You can install and use this one. </span>
-
-For non-Mac users:  
-
-```{r, eval=F} 
-packageurl <- "https://cran.r-project.org/src/contrib/Archive/dsr/dsr_0.2.2.tar.gz"
-install.packages(packageurl, repos=NULL, type="source")
-```
-
-```{r, eval=FALSE}
-# Other solution that may work
-require(devtools)
-devtools::install_version("dsr", version="0.2.2", repos="http:/cran.us.r.project.org")
-```
-
-For Mac users:  
-
-```{r, eval=FALSE}
-require(devtools)
-devtools::install_version("dsr", version="0.2.2", repos="https://mac.R-project.org")
-```
-
-
-
-
 ### Load population data {.unnumbered}  
 
 See the [Download handbook and data](data_used.qmd) page for instructions on how to download all the example data in the handbook. You can import the Standardisation page data directly into R from our Github repository by running the following `import()` commands:  
@@ -289,8 +260,6 @@ The age category values in the `country_data` and `standard_pop_data` data frame
 
 Currently, the values of the column `age_cat5` from the `standard_pop_data` data frame contain the word "years" and "plus", while those of the `country_data` data frame do not. We will have to make the age category values match. We use `str_replace_all()` from the **stringr** package, as described in the page on [Characters and strings](characters_strings.qmd), to replace these patterns with no space `""`.  
 
-Furthermore, the package **dsr** expects that in the standard population, the column containing counts will be called `"pop"`. So we rename that column accordingly.  
-
 ```{r}
 # Remove specific string from column values
 standard_pop_clean <- standard_pop_data %>%
@@ -300,7 +269,7 @@ standard_pop_clean <- standard_pop_data %>%
           age_cat5 = str_replace_all(age_cat5, "plus", ""),    # remove "plus"
           age_cat5 = str_replace_all(age_cat5, " ", "")) %>%   # remove " " space
      
-     rename(pop = WorldStandardPopulation)   # change col name to "pop", as this is expected by dsr package
+     rename(pop = WorldStandardPopulation)   # change col name to "pop"
 ```
 
 <span style="color: orange;">**_CAUTION:_** If you try to use `str_replace_all()` to remove a plus *symbol*, it won't work because it is a special symbol. "Escape" the specialnes by putting two back slashes in front, as in `str_replace_call(column, "\\+", "")`. </span>
@@ -319,111 +288,6 @@ This complete dataset looks like this:
 DT::datatable(all_data, rownames = FALSE, options = list(pageLength = 5, scrollX=T), class = 'white-space: nowrap' )
 ```
 
-
-
-<!-- ======================================================= -->
-## **dsr** package {  }
- 
-Below we demonstrate calculating and comparing directly standardized rates using the **dsr** package. The **dsr** package allows you to calculate and compare directly standardized rates (no indirectly standardized rates!).
-  
-In the data Preparation section, we made separate datasets for country counts and standard population:  
-
-1) the `country_data` object, which is a population table with the number of population and number of deaths per stratum per country  
-2) the `standard_pop_clean` object, containing the number of population per stratum for our reference population, the World Standard Population  
-
-We will use these separate datasets for the **dsr** approach.  
-
-
-<!-- ======================================================= -->
-### Standardized rates {.unnumbered}
-
-Below, we calculate rates per country directly standardized for age and sex. We use the `dsr()` function. 
-
-Of note - `dsr()` expects one data frame for the country populations and event counts (deaths), *and a **separate** data frame with the reference population*. It also expects that in this reference population dataset the unit-time column name is "pop" (we assured this in the data Preparation section).  
-
-There are many arguments, as annotated in the code below. Notably, `event = ` is set to the column `Deaths`, and the `fu = ` ("follow-up") is set to the `Population` column. We set the subgroups of comparison as the column `Country` and we standardize based on `age_cat5` and `Sex`. These last two columns are not assigned a particular named argument. See `?dsr` for details. 
-
-```{r, warning=F, message=F}
-# Calculate rates per country directly standardized for age and sex
-mortality_rate <- dsr::dsr(
-     data = country_data,  # specify object containing number of deaths per stratum
-     event = Deaths,       # column containing number of deaths per stratum 
-     fu = Population,      # column containing number of population per stratum
-     subgroup = Country,   # units we would like to compare
-     age_cat5,             # other columns - rates will be standardized by these
-     Sex,
-     refdata = standard_pop_clean, # reference population data frame, with column called pop
-     method = "gamma",      # method to calculate 95% CI
-     sig = 0.95,            # significance level
-     mp = 100000,           # we want rates per 100.000 population
-     decimals = 2)          # number of decimals)
-
-
-# Print output as nice-looking HTML table
-knitr::kable(mortality_rate) # show mortality rate before and after direct standardization
-```
-
-Above, we see that while country A had a lower crude mortality rate than country B, it has a higher standardized rate after direct age and sex standardization.
-
-
-
-
-<!-- ======================================================= -->
-### Standardized rate ratios {.unnumbered}
-
-```{r,warning=F, message=F}
-# Calculate RR
-mortality_rr <- dsr::dsrr(
-     data = country_data, # specify object containing number of deaths per stratum
-     event = Deaths,      # column containing number of deaths per stratum 
-     fu = Population,     # column containing number of population per stratum
-     subgroup = Country,  # units we would like to compare
-     age_cat5,
-     Sex,                 # characteristics to which we would like to standardize 
-     refdata = standard_pop_clean, # reference population, with numbers in column called pop
-     refgroup = "B",      # reference for comparison
-     estimate = "ratio",  # type of estimate
-     sig = 0.95,          # significance level
-     mp = 100000,         # we want rates per 100.000 population
-     decimals = 2)        # number of decimals
-
-# Print table
-knitr::kable(mortality_rr) 
-```
-
-The standardized mortality rate is 1.22 times higher in country A compared to country B (95% CI 1.17-1.27).
-
-<!-- ======================================================= -->
-### Standardized rate difference {.unnumbered}
-
-```{r, warning=F, message=F}
-# Calculate RD
-mortality_rd <- dsr::dsrr(
-     data = country_data,       # specify object containing number of deaths per stratum
-     event = Deaths,            # column containing number of deaths per stratum 
-     fu = Population,           # column containing number of population per stratum
-     subgroup = Country,        # units we would like to compare
-     age_cat5,                  # characteristics to which we would like to standardize
-     Sex,                        
-     refdata = standard_pop_clean, # reference population, with numbers in column called pop
-     refgroup = "B",            # reference for comparison
-     estimate = "difference",   # type of estimate
-     sig = 0.95,                # significance level
-     mp = 100000,               # we want rates per 100.000 population
-     decimals = 2)              # number of decimals
-
-# Print table
-knitr::kable(mortality_rd) 
-```
-
-Country A has 4.24 additional deaths per 100.000 population (95% CI 3.24-5.24) compared to country A.
-
-
-
-
-
-
-
 <!-- ======================================================= -->
 ## **PHEindicatormethods** package {#standard_phe  }
 
@@ -432,7 +296,6 @@ Another way of calculating standardized rates is with the **PHEindicatormethods*
 This section will use the `all_data` data frame created at the end of the Preparation section. This data frame includes the country populations, death events, and the world standard reference population. You can view it [here](#standard_all).  
 
 
-
 <!-- ======================================================= -->
 ### Directly standardized rates {.unnumbered}
 
@@ -488,8 +351,6 @@ knitr::kable(mortality_is_rate_phe_A)
 <!-- ======================================================= -->
 ## Resources {  }
 
-If you would like to see another reproducible example using **dsr** please see [this vignette]( https://mran.microsoft.com/snapshot/2020-02-12/web/packages/dsr/vignettes/dsr.html).  
-
 For another example using **PHEindicatormethods**, please go to [this website](https://cran.r-project.org/web/packages/PHEindicatormethods/vignettes/Introduction_to_PHEindicatormethods.html).  
 
 See the **PHEindicatormethods** [reference pdf file](https://cran.r-project.org/web/packages/PHEindicatormethods/PHEindicatormethods.pdf).  
diff --git a/new_pages/stat_tests.qmd b/new_pages/stat_tests.qmd
index 5064793d..be99017e 100644
--- a/new_pages/stat_tests.qmd
+++ b/new_pages/stat_tests.qmd
@@ -241,7 +241,7 @@ Many many more functions and statistical tests can be run with **rstatix** funct
 
 
 
-## `gtsummary` package {#stats_gt}
+## **`gtsummary`** package {#stats_gt}
 
 Use **gtsummary** if you are looking to add the results of a statistical test to a pretty table that was created with this package (as described in the **gtsummary** section of the [Descriptive tables](tables_descriptive.qmd#tbl_gt) page).  
 
@@ -315,8 +315,6 @@ linelist %>%
 ```
 
 
-
-
 <!-- ## `dplyr` package {} -->
 
 <!-- Performing statistical tests in `dplyr` alone is very dense, again because it  -->
diff --git a/new_pages/survey_analysis.qmd b/new_pages/survey_analysis.qmd
index a4019b6b..70f7d47b 100644
--- a/new_pages/survey_analysis.qmd
+++ b/new_pages/survey_analysis.qmd
@@ -1050,7 +1050,43 @@ survey_design %>%
 
 ```
 
+## Weighted regression
 
+Another tool we can use to analyse our survey data is to use weighted regression. This allows us to carry out to account for the survey design in our regression in order to avoid biases that may be introduced from the survey process.
+
+To carry out a *univariate regression*, we can use the packages **survey** for the function `svyglm()` and the package **gtsummary** which allows us to call `svyglm()` inside the function `tbl_uvregression`. To do this we first use the `survey_design` object created above. This is then provided to the function `tbl_uvregression()` as in the [Univariate and multivariable regression chapter](regression.qmd). We then make one key change, we change `method = glm` to `method = survey::svyglm` in order to carry out our survey weighted regression.
+
+Here we will be using the previously created object `survey_design` to predict whether the value in the column `died` is `TRUE`, using the columns `malaria_treatment`, `bednet`, and `age_years`.
+
+```{r, warning=F, message=F}
+
+survey_design %>%
+     tbl_uvregression(                             #Carry out a univariate regression, if we wanted a multivariable regression we would use tbl_
+          method = survey::svyglm,                 #Set this to survey::svyglm to carry out our weighted regression on the survey data
+          y = died,                                #The column we are trying to predict
+          method.args = list(family = binomial),   #The family, we are carrying out a logistic regression so we want the family as binomial
+          include = c(malaria_treatment,           #These are the columns we want to evaluate
+                      bednet,
+                      age_years),
+          exponentiate = T                         #To transform the log odds to odds ratio for easier interpretation
+     )
+
+```
+
+If we wanted to carry out a *multivariable* regression, we would have to first use the function `svyglm()` and pipe (`%>%`) the results into the function `tbl_regression`. Note that we need to specify the formula.
+
+```{r, warning=F, message=F}
+
+survey_design %>%
+     svyglm(formula = died ~ malaria_treatment + 
+                 bednet + 
+                 age_years,
+            family = binomial) %>%                   #The family, we are carrying out a logistic regression so we want the family as binomial
+     tbl_regression( 
+          exponentiate = T                           #To transform the log odds to odds ratio for easier interpretation                            
+     )
+     
+```
 
 
 <!-- ======================================================= -->
@@ -1065,3 +1101,5 @@ survey_design %>%
 [gtsummary package](http://www.danieldsjoberg.com/gtsummary/reference/index.html) 
 
 [EPIET survey case studies](https://github.com/EPIET/RapidAssessmentSurveys)
+
+[Analyzing Complex Survey Data](https://www.bookdown.org/rwnahhas/RMPH/survey.html)
diff --git a/new_pages/writing_functions.qmd b/new_pages/writing_functions.qmd
index ad478dba..00a4aab2 100644
--- a/new_pages/writing_functions.qmd
+++ b/new_pages/writing_functions.qmd
@@ -45,9 +45,9 @@ flu_china <- rio::import(here::here("data", "case_linelists", "fluH7N9_China_201
 Functions are helpful in programming since they allow to make codes easier to understand, somehow shorter and less prone to errors (given there were no errors in the function itself).
 
 If you have come so far to this handbook, it means you have came across endless functions since in R, every operation is a function call
-`+, for, if, [, $, { …`. For example `x + y` is the same as`'+'(x, y)`
+`+, for, if, [, $, { …`. For example `x + y` is the same as`'+'(x, y)`.
 
-R is one the languages that offers the most possibility to work with functions and give enough tools to the user to easily write them. We should not think about functions as fixed at the top or at the end of the programming chain, R offers the possibility to use them as if they were vectors and even to use them inside other functions, lists...
+R is one of the programming languages that offers the most possibility to work with functions and give enough tools to the user to easily write them. We should not think about functions as fixed at the top or at the end of the programming chain, R offers the possibility to use them as if they were vectors and even to use them inside other functions.
 
 Lot of very advanced resources on functional programming exist and we will only give here an insight to help you start with functional programming with short practical examples. You are then encouraged to visit the links on references to read more about it.
 
@@ -65,17 +65,17 @@ Before answering this question, it is important to note that you have already ha
 
 - Is it possible that the code I have written is used again but with a different value at many places of the code?
 
-If the answer to one of the previous questions is "YES", then you probably need to write a function
+If the answer to one of the previous questions is "YES", then you probably need to write a function.
 
 ## How does R  build functions?
 
 Functions in R have three main components:
 
-- the `formals()` which is the list of arguments which controls how we can call the function
+- the `formals()` which is the list of arguments which controls how we can call the function.
 
-- the `body()` that is the code inside the function i.e. within the brackets or following the parenthesis depending on how we write it
+- the `body()` that is the code inside the function i.e. within the brackets or following the parenthesis depending on how we write it.
 
-and,
+And,
 
 - the `environment()` which will help locate the function's variables and determines how the function finds value.
  
@@ -84,9 +84,9 @@ Once you have created your function, you can verify each of these components by
 
 ## Basic syntax and structure
 
-- A function will need to be named properly so that its job is easily understandable as soon as we read its name. Actually this is already the case with majority of the base R architecture. Functions like  `mean()`, `print()`, `summary()` have names that are very straightforward 
+- A function will need to be named properly so that its job is easily understandable as soon as we read its name. Actually this is already the case with majority of the base R architecture. Functions like  `mean()`, `print()`, `summary()` have names that are very straightforward. 
 
-- A function will need arguments, such as the data to work on and other objects that can be static values among other options  
+- A function will need arguments, such as the data to work on and other objects that can be static values among other options.  
 
 - And finally a function will give an output based on its core task and the arguments it has been given. Usually we will use the built-in functions as `print()`, `return()`... to produce the output. The output can be a logical value, a number, a character, a data frame...in short any kind of R object.
 
@@ -109,12 +109,11 @@ We can create our first function that will be called `contain_covid19()`.
 ```{r}
 
 contain_covid19 <- function(barrier_gest, wear_mask, get_vaccine){
-  
-                            if(barrier_gest == "yes" & wear_mask == "yes" & get_vaccine == "yes" ) 
-       
+                            if(barrier_gest == "yes" & 
+                               wear_mask == "yes" & 
+                               get_vaccine == "yes" ) 
                             return("success")
-  
-  else("please make sure all are yes, this pandemic has to end!")
+  else("please make sure all are yes, we need as much help containing COVID as we can get!")
 }
 
 
@@ -466,9 +465,9 @@ Functional programming is meant to ease code and facilitates its reading. It sho
 
 ### Naming and syntax {.unnumbered}
 
-- Avoid using character that could have been easily already taken by other functions already existing in your environment
+- Avoid using character that could have been easily already taken by other functions already existing in your environment.
 
-- It is recommended for the function name to be short and straightforward to understand for another reader
+- It is recommended for the function name to be short and straightforward to understand for another reader.
 
 - It is preferred to use verbs as the function name and nouns for the argument names.
 
diff --git a/old_bookdown/new_pages/collaboration.Rmd b/old_bookdown/new_pages/collaboration.Rmd
index b764b1e8..691b21e1 100644
--- a/old_bookdown/new_pages/collaboration.Rmd
+++ b/old_bookdown/new_pages/collaboration.Rmd
@@ -671,7 +671,7 @@ you were working on.
 *PULL* - First, click the "Pull" icon (downward arrow) which fetches and
 pulls at the same time.
 
-*PUSH* - Clicking the green "Pull" icon (upward arrow). You may be asked
+*PUSH* - Clicking the green "Push" icon (upward arrow). You may be asked
 to enter your Github username and password. The first time you are
 asked, you may need to enter two Git command lines into the *Terminal*:
 
@@ -729,9 +729,9 @@ knitr::include_graphics(here::here("images", "github_desktop_push_button.png"))
 Without surprise, the commands are *fetch*, *pull* and *push*.
 
 ```{bash, eval = FALSE}
-git fetch  # are there new commits in the remote directory?
+git fetch  # Are there new commits in the remote directory?
 git pull   # Bring remote commits into your local branch
-git push   # Puch local commits of this branch to the remote branch
+git push   # Push local commits of this branch to the remote branch
 ```
 
 
diff --git a/old_bookdown/new_pages/heatmaps.Rmd b/old_bookdown/new_pages/heatmaps.Rmd
index 11b6615b..5cbea539 100644
--- a/old_bookdown/new_pages/heatmaps.Rmd
+++ b/old_bookdown/new_pages/heatmaps.Rmd
@@ -469,9 +469,16 @@ Now use a column from the above data frame (`facility_order$location_name`) to b
 pacman::p_load(forcats)
 
 # create factor and define levels manually
+numerical_order <- gsub("Facility ","",
+     facility_order$location_name) %>% 
+     as.numeric() %>%
+     sort() 
+
+facilities_in_order <- str_c("Facility ", numerical_order, sep = "")
+
 agg_weeks <- agg_weeks %>% 
   mutate(location_name = fct_relevel(
-    location_name, facility_order$location_name)
+    location_name, facilities_in_order)
     )
 ```