skimr

<!DOCTYPE html> <html> <head> <meta charset="utf-8" /> <meta name="generator" content="pandoc" /> <meta http-equiv="X-UA-Compatible" content="IE=EDGE" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <title>Rectangling</title> <script>// Pandoc 2.9 adds attributes on both header and div. We remove the former (to // be compatible with the behavior of Pandoc < 2.8). document.addEventListener('DOMContentLoaded', function(e) { var hs = document.querySelectorAll("div.section[class*='level'] > :first-child"); var i, h, a; for (i = 0; i < hs.length; i++) { h = hs[i]; if (!/^h[1-6]$/i.test(h.tagName)) continue; // it should be a header h1-h6 a = h.attributes; while (a.length > 0) h.removeAttribute(a[0].name); } }); </script> <style type="text/css"> code{white-space: pre-wrap;} span.smallcaps{font-variant: small-caps;} span.underline{text-decoration: underline;} div.column{display: inline-block; vertical-align: top; width: 50%;} div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;} ul.task-list{list-style: none;} </style> <style type="text/css"> code { white-space: pre; } .sourceCode { overflow: visible; } </style> <style type="text/css" data-origin="pandoc"> pre > code.sourceCode { white-space: pre; position: relative; } pre > code.sourceCode > span { display: inline-block; line-height: 1.25; } pre > code.sourceCode > span:empty { height: 1.2em; } .sourceCode { overflow: visible; } code.sourceCode > span { color: inherit; text-decoration: inherit; } div.sourceCode { margin: 1em 0; } pre.sourceCode { margin: 0; } @media screen { div.sourceCode { overflow: auto; } } @media print { pre > code.sourceCode { white-space: pre-wrap; } pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; } } pre.numberSource code { counter-reset: source-line 0; } pre.numberSource code > span { position: relative; left: -4em; counter-increment: source-line; } pre.numberSource code > span > a:first-child::before { content: counter(source-line); position: relative; left: -1em; text-align: right; vertical-align: baseline; border: none; display: inline-block; -webkit-touch-callout: none; -webkit-user-select: none; -khtml-user-select: none; -moz-user-select: none; -ms-user-select: none; user-select: none; padding: 0 4px; width: 4em; color: #aaaaaa; } pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; } div.sourceCode { } @media screen { pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; } } code span.al { color: #ff0000; font-weight: bold; } code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } code span.at { color: #7d9029; } code span.bn { color: #40a070; } code span.bu { color: #008000; } code span.cf { color: #007020; font-weight: bold; } code span.ch { color: #4070a0; } code span.cn { color: #880000; } code span.co { color: #60a0b0; font-style: italic; } code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } code span.do { color: #ba2121; font-style: italic; } code span.dt { color: #902000; } code span.dv { color: #40a070; } code span.er { color: #ff0000; font-weight: bold; } code span.ex { } code span.fl { color: #40a070; } code span.fu { color: #06287e; } code span.im { color: #008000; font-weight: bold; } code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } code span.kw { color: #007020; font-weight: bold; } code span.op { color: #666666; } code span.ot { color: #007020; } code span.pp { color: #bc7a00; } code span.sc { color: #4070a0; } code span.ss { color: #bb6688; } code span.st { color: #4070a0; } code span.va { color: #19177c; } code span.vs { color: #4070a0; } code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } </style> <script> // apply pandoc div.sourceCode style to pre.sourceCode instead (function() { var sheets = document.styleSheets; for (var i = 0; i < sheets.length; i++) { if (sheets[i].ownerNode.dataset["origin"] !== "pandoc") continue; try { var rules = sheets[i].cssRules; } catch (e) { continue; } var j = 0; while (j < rules.length) { var rule = rules[j]; // check if there is a div.sourceCode rule if (rule.type !== rule.STYLE_RULE || rule.selectorText !== "div.sourceCode") { j++; continue; } var style = rule.style.cssText; // check if color or background-color is set if (rule.style.color === '' && rule.style.backgroundColor === '') { j++; continue; } // replace div.sourceCode by a pre.sourceCode rule sheets[i].deleteRule(j); sheets[i].insertRule('pre.sourceCode{' + style + '}', j); } } })(); </script> <style type="text/css">body { background-color: #fff; margin: 1em auto; max-width: 700px; overflow: visible; padding-left: 2em; padding-right: 2em; font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif; font-size: 14px; line-height: 1.35; } #TOC { clear: both; margin: 0 0 10px 10px; padding: 4px; width: 400px; border: 1px solid #CCCCCC; border-radius: 5px; background-color: #f6f6f6; font-size: 13px; line-height: 1.3; } #TOC .toctitle { font-weight: bold; font-size: 15px; margin-left: 5px; } #TOC ul { padding-left: 40px; margin-left: -1.5em; margin-top: 5px; margin-bottom: 5px; } #TOC ul ul { margin-left: -2em; } #TOC li { line-height: 16px; } table { margin: 1em auto; border-width: 1px; border-color: #DDDDDD; border-style: outset; border-collapse: collapse; } table th { border-width: 2px; padding: 5px; border-style: inset; } table td { border-width: 1px; border-style: inset; line-height: 18px; padding: 5px 5px; } table, table th, table td { border-left-style: none; border-right-style: none; } table thead, table tr.even { background-color: #f7f7f7; } p { margin: 0.5em 0; } blockquote { background-color: #f6f6f6; padding: 0.25em 0.75em; } hr { border-style: solid; border: none; border-top: 1px solid #777; margin: 28px 0; } dl { margin-left: 0; } dl dd { margin-bottom: 13px; margin-left: 13px; } dl dt { font-weight: bold; } ul { margin-top: 0; } ul li { list-style: circle outside; } ul ul { margin-bottom: 0; } pre, code { background-color: #f7f7f7; border-radius: 3px; color: #333; white-space: pre-wrap; } pre { border-radius: 3px; margin: 5px 0px 10px 0px; padding: 10px; } pre:not([class]) { background-color: #f7f7f7; } code { font-family: Consolas, Monaco, 'Courier New', monospace; font-size: 85%; } p > code, li > code { padding: 2px 0px; } div.figure { text-align: center; } img { background-color: #FFFFFF; padding: 2px; border: 1px solid #DDDDDD; border-radius: 3px; border: 1px solid #CCCCCC; margin: 0 5px; } h1 { margin-top: 0; font-size: 35px; line-height: 40px; } h2 { border-bottom: 4px solid #f7f7f7; padding-top: 10px; padding-bottom: 2px; font-size: 145%; } h3 { border-bottom: 2px solid #f7f7f7; padding-top: 10px; font-size: 120%; } h4 { border-bottom: 1px solid #f7f7f7; margin-left: 8px; font-size: 105%; } h5, h6 { border-bottom: 1px solid #ccc; font-size: 105%; } a { color: #0033dd; text-decoration: none; } a:hover { color: #6666ff; } a:visited { color: #800080; } a:visited:hover { color: #BB00BB; } a[href^="http:"] { text-decoration: underline; } a[href^="https:"] { text-decoration: underline; } code > span.kw { color: #555; font-weight: bold; } code > span.dt { color: #902000; } code > span.dv { color: #40a070; } code > span.bn { color: #d14; } code > span.fl { color: #d14; } code > span.ch { color: #d14; } code > span.st { color: #d14; } code > span.co { color: #888888; font-style: italic; } code > span.ot { color: #007020; } code > span.al { color: #ff0000; font-weight: bold; } code > span.fu { color: #900; font-weight: bold; } code > span.er { color: #a61717; background-color: #e3d2d2; } </style> </head> <body> <h1 class="title toc-ignore">Rectangling</h1> <div id="introduction" class="section level2"> <h2>Introduction</h2> Rectangling is the art and craft of taking a deeply nested list (often sourced from wild caught JSON or XML) and taming it into a tidy data set of rows and columns. There are three functions from tidyr that are particularly useful for rectangling: <ul> <li><code>unnest_longer()</code> takes each element of a list-column and makes a new row.</li> <li><code>unnest_wider()</code> takes each element of a list-column and makes a new column.</li> <li><code>hoist()</code> is similar to <code>unnest_wider()</code> but only plucks out selected components, and can reach down multiple levels.</li> </ul> (Alternative, for complex inputs where you need to rectangle a nested list according to a specification, see the <a href="https://github.com/mgirlich/tibblify">tibblify</a> package.) A very large number of data rectangling problems can be solved by combining <code>jsonlite::read_json()</code> with these functions and a splash of dplyr (largely eliminating prior approaches that combined <code>mutate()</code> with multiple <code>purrr::map()</code>s). Note that jsonlite has another important function called <code>fromJSON()</code>. We don’t recommend it here because it performs its own automatic simplification (<code>simplifyVector = TRUE</code>). This often works well, particularly in simple cases, but we think you’re better off doing the rectangling yourself so you know exactly what’s happening and can more easily handle the most complicated nested structures. To illustrate these techniques, we’ll use the repurrrsive package, which provides a number deeply nested lists originally mostly captured from web APIs. <div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>library(tidyr) <a href="#cb1-2" aria-hidden="true" tabindex="-1"></a>library(dplyr) <a href="#cb1-3" aria-hidden="true" tabindex="-1"></a>library(repurrrsive)</code></pre></div> </div> <div id="github-users" class="section level2"> <h2>GitHub users</h2> We’ll start with <code>gh_users</code>, a list which contains information about six GitHub users. To begin, we put the <code>gh_users</code> list into a data frame: <div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>users <- tibble(user = gh_users)</code></pre></div> This seems a bit counter-intuitive: why is the first step in making a list simpler to make it more complicated? But a data frame has a big advantage: it bundles together multiple vectors so that everything is tracked together in a single object. Each <code>user</code> is a named list, where each element represents a column. <div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>names(users$user[[1]]) <a href="#cb3-2" aria-hidden="true" tabindex="-1"></a>#> [1] "login" "id" "avatar_url" <a href="#cb3-3" aria-hidden="true" tabindex="-1"></a>#> [4] "gravatar_id" "url" "html_url" <a href="#cb3-4" aria-hidden="true" tabindex="-1"></a>#> [7] "followers_url" "following_url" "gists_url" <a href="#cb3-5" aria-hidden="true" tabindex="-1"></a>#> [10] "starred_url" "subscriptions_url" "organizations_url" <a href="#cb3-6" aria-hidden="true" tabindex="-1"></a>#> [13] "repos_url" "events_url" "received_events_url" <a href="#cb3-7" aria-hidden="true" tabindex="-1"></a>#> [16] "type" "site_admin" "name" <a href="#cb3-8" aria-hidden="true" tabindex="-1"></a>#> [19] "company" "blog" "location" <a href="#cb3-9" aria-hidden="true" tabindex="-1"></a>#> [22] "email" "hireable" "bio" <a href="#cb3-10" aria-hidden="true" tabindex="-1"></a>#> [25] "public_repos" "public_gists" "followers" <a href="#cb3-11" aria-hidden="true" tabindex="-1"></a>#> [28] "following" "created_at" "updated_at"</code></pre></div> There are two ways to turn the list components into columns. <code>unnest_wider()</code> takes every component and makes a new column: <div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>users %>% unnest_wider(user) <a href="#cb4-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 6 × 30 <a href="#cb4-3" aria-hidden="true" tabindex="-1"></a>#> login id avata…¹ grava…² url html_…³ follo…⁴ follo…⁵ gists…⁶ starr…⁷ <a href="#cb4-4" aria-hidden="true" tabindex="-1"></a>#> <chr> <int> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <a href="#cb4-5" aria-hidden="true" tabindex="-1"></a>#> 1 gaborcsa… 6.60e5 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb4-6" aria-hidden="true" tabindex="-1"></a>#> 2 jennybc 5.99e5 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb4-7" aria-hidden="true" tabindex="-1"></a>#> 3 jtleek 1.57e6 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb4-8" aria-hidden="true" tabindex="-1"></a>#> 4 juliasil… 1.25e7 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb4-9" aria-hidden="true" tabindex="-1"></a>#> 5 leeper 3.51e6 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb4-10" aria-hidden="true" tabindex="-1"></a>#> 6 masalmon 8.36e6 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb4-11" aria-hidden="true" tabindex="-1"></a>#> # … with 20 more variables: subscriptions_url <chr>, organizations_url <chr>, <a href="#cb4-12" aria-hidden="true" tabindex="-1"></a>#> # repos_url <chr>, events_url <chr>, received_events_url <chr>, type <chr>, <a href="#cb4-13" aria-hidden="true" tabindex="-1"></a>#> # site_admin <lgl>, name <chr>, company <chr>, blog <chr>, location <chr>, <a href="#cb4-14" aria-hidden="true" tabindex="-1"></a>#> # email <chr>, hireable <lgl>, bio <chr>, public_repos <int>, <a href="#cb4-15" aria-hidden="true" tabindex="-1"></a>#> # public_gists <int>, followers <int>, following <int>, created_at <chr>, <a href="#cb4-16" aria-hidden="true" tabindex="-1"></a>#> # updated_at <chr>, and abbreviated variable names ¹avatar_url, ²gravatar_id, <a href="#cb4-17" aria-hidden="true" tabindex="-1"></a>#> # ³html_url, ⁴followers_url, ⁵following_url, ⁶gists_url, ⁷starred_url</code></pre></div> But in this case, there are many components and we don’t need most of them so we can instead use <code>hoist()</code>. <code>hoist()</code> allows us to pull out selected components using the same syntax as <code>purrr::pluck()</code>: <div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a>users %>% hoist(user, <a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> followers = "followers", <a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> login = "login", <a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> url = "html_url" <a href="#cb5-5" aria-hidden="true" tabindex="-1"></a>) <a href="#cb5-6" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 6 × 4 <a href="#cb5-7" aria-hidden="true" tabindex="-1"></a>#> followers login url user <a href="#cb5-8" aria-hidden="true" tabindex="-1"></a>#> <int> <chr> <chr> <list> <a href="#cb5-9" aria-hidden="true" tabindex="-1"></a>#> 1 303 gaborcsardi https://github.com/gaborcsardi <named list [27]> <a href="#cb5-10" aria-hidden="true" tabindex="-1"></a>#> 2 780 jennybc https://github.com/jennybc <named list [27]> <a href="#cb5-11" aria-hidden="true" tabindex="-1"></a>#> 3 3958 jtleek https://github.com/jtleek <named list [27]> <a href="#cb5-12" aria-hidden="true" tabindex="-1"></a>#> 4 115 juliasilge https://github.com/juliasilge <named list [27]> <a href="#cb5-13" aria-hidden="true" tabindex="-1"></a>#> 5 213 leeper https://github.com/leeper <named list [27]> <a href="#cb5-14" aria-hidden="true" tabindex="-1"></a>#> 6 34 masalmon https://github.com/masalmon <named list [27]></code></pre></div> <code>hoist()</code> removes the named components from the <code>user</code> list-column, so you can think of it as moving components out of the inner list into the top-level data frame. </div> <div id="github-repos" class="section level2"> <h2>GitHub repos</h2> We start off <code>gh_repos</code> similarly, by putting it in a tibble: <div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>repos <- tibble(repo = gh_repos) <a href="#cb6-2" aria-hidden="true" tabindex="-1"></a>repos <a href="#cb6-3" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 6 × 1 <a href="#cb6-4" aria-hidden="true" tabindex="-1"></a>#> repo <a href="#cb6-5" aria-hidden="true" tabindex="-1"></a>#> <list> <a href="#cb6-6" aria-hidden="true" tabindex="-1"></a>#> 1 <list [30]> <a href="#cb6-7" aria-hidden="true" tabindex="-1"></a>#> 2 <list [30]> <a href="#cb6-8" aria-hidden="true" tabindex="-1"></a>#> 3 <list [30]> <a href="#cb6-9" aria-hidden="true" tabindex="-1"></a>#> 4 <list [26]> <a href="#cb6-10" aria-hidden="true" tabindex="-1"></a>#> 5 <list [30]> <a href="#cb6-11" aria-hidden="true" tabindex="-1"></a>#> 6 <list [30]></code></pre></div> This time the elements of <code>repos</code> are a list of repositories that belong to that user. These are observations, so should become new rows, so we use <code>unnest_longer()</code> rather than <code>unnest_wider()</code>: <div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>repos <- repos %>% unnest_longer(repo) <a href="#cb7-2" aria-hidden="true" tabindex="-1"></a>repos <a href="#cb7-3" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 176 × 1 <a href="#cb7-4" aria-hidden="true" tabindex="-1"></a>#> repo <a href="#cb7-5" aria-hidden="true" tabindex="-1"></a>#> <list> <a href="#cb7-6" aria-hidden="true" tabindex="-1"></a>#> 1 <named list [68]> <a href="#cb7-7" aria-hidden="true" tabindex="-1"></a>#> 2 <named list [68]> <a href="#cb7-8" aria-hidden="true" tabindex="-1"></a>#> 3 <named list [68]> <a href="#cb7-9" aria-hidden="true" tabindex="-1"></a>#> 4 <named list [68]> <a href="#cb7-10" aria-hidden="true" tabindex="-1"></a>#> 5 <named list [68]> <a href="#cb7-11" aria-hidden="true" tabindex="-1"></a>#> 6 <named list [68]> <a href="#cb7-12" aria-hidden="true" tabindex="-1"></a>#> # … with 170 more rows</code></pre></div> Then we can use <code>unnest_wider()</code> or <code>hoist()</code>: <div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>repos %>% hoist(repo, <a href="#cb8-2" aria-hidden="true" tabindex="-1"></a> login = c("owner", "login"), <a href="#cb8-3" aria-hidden="true" tabindex="-1"></a> name = "name", <a href="#cb8-4" aria-hidden="true" tabindex="-1"></a> homepage = "homepage", <a href="#cb8-5" aria-hidden="true" tabindex="-1"></a> watchers = "watchers_count" <a href="#cb8-6" aria-hidden="true" tabindex="-1"></a>) <a href="#cb8-7" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 176 × 5 <a href="#cb8-8" aria-hidden="true" tabindex="-1"></a>#> login name homepage watchers repo <a href="#cb8-9" aria-hidden="true" tabindex="-1"></a>#> <chr> <chr> <chr> <int> <list> <a href="#cb8-10" aria-hidden="true" tabindex="-1"></a>#> 1 gaborcsardi after <NA> 5 <named list [65]> <a href="#cb8-11" aria-hidden="true" tabindex="-1"></a>#> 2 gaborcsardi argufy <NA> 19 <named list [65]> <a href="#cb8-12" aria-hidden="true" tabindex="-1"></a>#> 3 gaborcsardi ask <NA> 5 <named list [65]> <a href="#cb8-13" aria-hidden="true" tabindex="-1"></a>#> 4 gaborcsardi baseimports <NA> 0 <named list [65]> <a href="#cb8-14" aria-hidden="true" tabindex="-1"></a>#> 5 gaborcsardi citest <NA> 0 <named list [65]> <a href="#cb8-15" aria-hidden="true" tabindex="-1"></a>#> 6 gaborcsardi clisymbols "" 18 <named list [65]> <a href="#cb8-16" aria-hidden="true" tabindex="-1"></a>#> # … with 170 more rows</code></pre></div> Note the use of <code>c("owner", "login")</code>: this allows us to reach two levels deep inside of a list. An alternative approach would be to pull out just <code>owner</code> and then put each element of it in a column: <div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>repos %>% <a href="#cb9-2" aria-hidden="true" tabindex="-1"></a> hoist(repo, owner = "owner") %>% <a href="#cb9-3" aria-hidden="true" tabindex="-1"></a> unnest_wider(owner) <a href="#cb9-4" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 176 × 18 <a href="#cb9-5" aria-hidden="true" tabindex="-1"></a>#> login id avata…¹ grava…² url html_…³ follo…⁴ follo…⁵ gists…⁶ starr…⁷ <a href="#cb9-6" aria-hidden="true" tabindex="-1"></a>#> <chr> <int> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <a href="#cb9-7" aria-hidden="true" tabindex="-1"></a>#> 1 gaborcsa… 660288 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb9-8" aria-hidden="true" tabindex="-1"></a>#> 2 gaborcsa… 660288 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb9-9" aria-hidden="true" tabindex="-1"></a>#> 3 gaborcsa… 660288 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb9-10" aria-hidden="true" tabindex="-1"></a>#> 4 gaborcsa… 660288 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb9-11" aria-hidden="true" tabindex="-1"></a>#> 5 gaborcsa… 660288 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb9-12" aria-hidden="true" tabindex="-1"></a>#> 6 gaborcsa… 660288 https:… "" http… https:… https:… https:… https:… https:… <a href="#cb9-13" aria-hidden="true" tabindex="-1"></a>#> # … with 170 more rows, 8 more variables: subscriptions_url <chr>, <a href="#cb9-14" aria-hidden="true" tabindex="-1"></a>#> # organizations_url <chr>, repos_url <chr>, events_url <chr>, <a href="#cb9-15" aria-hidden="true" tabindex="-1"></a>#> # received_events_url <chr>, type <chr>, site_admin <lgl>, repo <list>, and <a href="#cb9-16" aria-hidden="true" tabindex="-1"></a>#> # abbreviated variable names ¹avatar_url, ²gravatar_id, ³html_url, <a href="#cb9-17" aria-hidden="true" tabindex="-1"></a>#> # ⁴followers_url, ⁵following_url, ⁶gists_url, ⁷starred_url</code></pre></div> </div> <div id="game-of-thrones-characters" class="section level2"> <h2>Game of Thrones characters</h2> <code>got_chars</code> has a similar structure to <code>gh_users</code>: it’s a list of named lists, where each element of the inner list describes some attribute of a GoT character. We start in the same way, first by creating a data frame and then by unnesting each component into a column: <div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>chars <- tibble(char = got_chars) <a href="#cb10-2" aria-hidden="true" tabindex="-1"></a>chars <a href="#cb10-3" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 30 × 1 <a href="#cb10-4" aria-hidden="true" tabindex="-1"></a>#> char <a href="#cb10-5" aria-hidden="true" tabindex="-1"></a>#> <list> <a href="#cb10-6" aria-hidden="true" tabindex="-1"></a>#> 1 <named list [18]> <a href="#cb10-7" aria-hidden="true" tabindex="-1"></a>#> 2 <named list [18]> <a href="#cb10-8" aria-hidden="true" tabindex="-1"></a>#> 3 <named list [18]> <a href="#cb10-9" aria-hidden="true" tabindex="-1"></a>#> 4 <named list [18]> <a href="#cb10-10" aria-hidden="true" tabindex="-1"></a>#> 5 <named list [18]> <a href="#cb10-11" aria-hidden="true" tabindex="-1"></a>#> 6 <named list [18]> <a href="#cb10-12" aria-hidden="true" tabindex="-1"></a>#> # … with 24 more rows <a href="#cb10-13" aria-hidden="true" tabindex="-1"></a> <a href="#cb10-14" aria-hidden="true" tabindex="-1"></a>chars2 <- chars %>% unnest_wider(char) <a href="#cb10-15" aria-hidden="true" tabindex="-1"></a>chars2 <a href="#cb10-16" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 30 × 18 <a href="#cb10-17" aria-hidden="true" tabindex="-1"></a>#> url id name gender culture born died alive titles aliases father <a href="#cb10-18" aria-hidden="true" tabindex="-1"></a>#> <chr> <int> <chr> <chr> <chr> <chr> <chr> <lgl> <list> <list> <chr> <a href="#cb10-19" aria-hidden="true" tabindex="-1"></a>#> 1 https://ww… 1022 Theo… Male "Ironb… "In … "" TRUE <chr> <chr> "" <a href="#cb10-20" aria-hidden="true" tabindex="-1"></a>#> 2 https://ww… 1052 Tyri… Male "" "In … "" TRUE <chr> <chr> "" <a href="#cb10-21" aria-hidden="true" tabindex="-1"></a>#> 3 https://ww… 1074 Vict… Male "Ironb… "In … "" TRUE <chr> <chr> "" <a href="#cb10-22" aria-hidden="true" tabindex="-1"></a>#> 4 https://ww… 1109 Will Male "" "" "In … FALSE <chr> <chr> "" <a href="#cb10-23" aria-hidden="true" tabindex="-1"></a>#> 5 https://ww… 1166 Areo… Male "Norvo… "In … "" TRUE <chr> <chr> "" <a href="#cb10-24" aria-hidden="true" tabindex="-1"></a>#> 6 https://ww… 1267 Chett Male "" "At … "In … FALSE <chr> <chr> "" <a href="#cb10-25" aria-hidden="true" tabindex="-1"></a>#> # … with 24 more rows, and 7 more variables: mother <chr>, spouse <chr>, <a href="#cb10-26" aria-hidden="true" tabindex="-1"></a>#> # allegiances <list>, books <list>, povBooks <list>, tvSeries <list>, <a href="#cb10-27" aria-hidden="true" tabindex="-1"></a>#> # playedBy <list></code></pre></div> This is more complex than <code>gh_users</code> because some component of <code>char</code> are themselves a list, giving us a collection of list-columns: <div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>chars2 %>% select_if(is.list) <a href="#cb11-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 30 × 7 <a href="#cb11-3" aria-hidden="true" tabindex="-1"></a>#> titles aliases allegiances books povBooks tvSeries playedBy <a href="#cb11-4" aria-hidden="true" tabindex="-1"></a>#> <list> <list> <list> <list> <list> <list> <list> <a href="#cb11-5" aria-hidden="true" tabindex="-1"></a>#> 1 <chr [2]> <chr [4]> <chr [1]> <chr [3]> <chr [2]> <chr [6]> <chr [1]> <a href="#cb11-6" aria-hidden="true" tabindex="-1"></a>#> 2 <chr [2]> <chr [11]> <chr [1]> <chr [2]> <chr [4]> <chr [6]> <chr [1]> <a href="#cb11-7" aria-hidden="true" tabindex="-1"></a>#> 3 <chr [2]> <chr [1]> <chr [1]> <chr [3]> <chr [2]> <chr [1]> <chr [1]> <a href="#cb11-8" aria-hidden="true" tabindex="-1"></a>#> 4 <chr [1]> <chr [1]> <NULL> <chr [1]> <chr [1]> <chr [1]> <chr [1]> <a href="#cb11-9" aria-hidden="true" tabindex="-1"></a>#> 5 <chr [1]> <chr [1]> <chr [1]> <chr [3]> <chr [2]> <chr [2]> <chr [1]> <a href="#cb11-10" aria-hidden="true" tabindex="-1"></a>#> 6 <chr [1]> <chr [1]> <NULL> <chr [2]> <chr [1]> <chr [1]> <chr [1]> <a href="#cb11-11" aria-hidden="true" tabindex="-1"></a>#> # … with 24 more rows</code></pre></div> What you do next will depend on the purposes of the analysis. Maybe you want a row for every book and TV series that the character appears in: <div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a>chars2 %>% <a href="#cb12-2" aria-hidden="true" tabindex="-1"></a> select(name, books, tvSeries) %>% <a href="#cb12-3" aria-hidden="true" tabindex="-1"></a> pivot_longer(c(books, tvSeries), names_to = "media", values_to = "value") %>% <a href="#cb12-4" aria-hidden="true" tabindex="-1"></a> unnest_longer(value) <a href="#cb12-5" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 179 × 3 <a href="#cb12-6" aria-hidden="true" tabindex="-1"></a>#> name media value <a href="#cb12-7" aria-hidden="true" tabindex="-1"></a>#> <chr> <chr> <chr> <a href="#cb12-8" aria-hidden="true" tabindex="-1"></a>#> 1 Theon Greyjoy books A Game of Thrones <a href="#cb12-9" aria-hidden="true" tabindex="-1"></a>#> 2 Theon Greyjoy books A Storm of Swords <a href="#cb12-10" aria-hidden="true" tabindex="-1"></a>#> 3 Theon Greyjoy books A Feast for Crows <a href="#cb12-11" aria-hidden="true" tabindex="-1"></a>#> 4 Theon Greyjoy tvSeries Season 1 <a href="#cb12-12" aria-hidden="true" tabindex="-1"></a>#> 5 Theon Greyjoy tvSeries Season 2 <a href="#cb12-13" aria-hidden="true" tabindex="-1"></a>#> 6 Theon Greyjoy tvSeries Season 3 <a href="#cb12-14" aria-hidden="true" tabindex="-1"></a>#> # … with 173 more rows</code></pre></div> Or maybe you want to build a table that lets you match title to name: <div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a>chars2 %>% <a href="#cb13-2" aria-hidden="true" tabindex="-1"></a> select(name, title = titles) %>% <a href="#cb13-3" aria-hidden="true" tabindex="-1"></a> unnest_longer(title) <a href="#cb13-4" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 59 × 2 <a href="#cb13-5" aria-hidden="true" tabindex="-1"></a>#> name title <a href="#cb13-6" aria-hidden="true" tabindex="-1"></a>#> <chr> <chr> <a href="#cb13-7" aria-hidden="true" tabindex="-1"></a>#> 1 Theon Greyjoy Prince of Winterfell <a href="#cb13-8" aria-hidden="true" tabindex="-1"></a>#> 2 Theon Greyjoy Lord of the Iron Islands (by law of the green lands) <a href="#cb13-9" aria-hidden="true" tabindex="-1"></a>#> 3 Tyrion Lannister Acting Hand of the King (former) <a href="#cb13-10" aria-hidden="true" tabindex="-1"></a>#> 4 Tyrion Lannister Master of Coin (former) <a href="#cb13-11" aria-hidden="true" tabindex="-1"></a>#> 5 Victarion Greyjoy Lord Captain of the Iron Fleet <a href="#cb13-12" aria-hidden="true" tabindex="-1"></a>#> 6 Victarion Greyjoy Master of the Iron Victory <a href="#cb13-13" aria-hidden="true" tabindex="-1"></a>#> # … with 53 more rows</code></pre></div> (Note that the empty titles (<code>""</code>) are due to an infelicity in the input <code>got_chars</code>: ideally people without titles would have a title vector of length 0, not a title vector of length 1 containing an empty string.) </div> <div id="geocoding-with-google" class="section level2"> <h2>Geocoding with google</h2> Next we’ll tackle a more complex form of data that comes from Google’s geocoding service, stored in the repurssive package <div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a>repurrrsive::gmaps_cities <a href="#cb14-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 5 × 2 <a href="#cb14-3" aria-hidden="true" tabindex="-1"></a>#> city json <a href="#cb14-4" aria-hidden="true" tabindex="-1"></a>#> <chr> <list> <a href="#cb14-5" aria-hidden="true" tabindex="-1"></a>#> 1 Houston <named list [2]> <a href="#cb14-6" aria-hidden="true" tabindex="-1"></a>#> 2 Washington <named list [2]> <a href="#cb14-7" aria-hidden="true" tabindex="-1"></a>#> 3 New York <named list [2]> <a href="#cb14-8" aria-hidden="true" tabindex="-1"></a>#> 4 Chicago <named list [2]> <a href="#cb14-9" aria-hidden="true" tabindex="-1"></a>#> 5 Arlington <named list [2]></code></pre></div> <code>json</code> is a list-column of named lists, so it makes sense to start with <code>unnest_wider()</code>: <div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a>repurrrsive::gmaps_cities %>% <a href="#cb15-2" aria-hidden="true" tabindex="-1"></a> unnest_wider(json) <a href="#cb15-3" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 5 × 3 <a href="#cb15-4" aria-hidden="true" tabindex="-1"></a>#> city results status <a href="#cb15-5" aria-hidden="true" tabindex="-1"></a>#> <chr> <list> <chr> <a href="#cb15-6" aria-hidden="true" tabindex="-1"></a>#> 1 Houston <list [1]> OK <a href="#cb15-7" aria-hidden="true" tabindex="-1"></a>#> 2 Washington <list [2]> OK <a href="#cb15-8" aria-hidden="true" tabindex="-1"></a>#> 3 New York <list [1]> OK <a href="#cb15-9" aria-hidden="true" tabindex="-1"></a>#> 4 Chicago <list [1]> OK <a href="#cb15-10" aria-hidden="true" tabindex="-1"></a>#> 5 Arlington <list [2]> OK</code></pre></div> Notice that <code>results</code> is a list of lists. Most of the cities have 1 element (representing a unique match from the geocoding API), but Washington and Arlington have two. We can pull these out into separate rows with <code>unnest_longer()</code>: <div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a>repurrrsive::gmaps_cities %>% <a href="#cb16-2" aria-hidden="true" tabindex="-1"></a> unnest_wider(json) %>% <a href="#cb16-3" aria-hidden="true" tabindex="-1"></a> unnest_longer(results) <a href="#cb16-4" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 7 × 3 <a href="#cb16-5" aria-hidden="true" tabindex="-1"></a>#> city results status <a href="#cb16-6" aria-hidden="true" tabindex="-1"></a>#> <chr> <list> <chr> <a href="#cb16-7" aria-hidden="true" tabindex="-1"></a>#> 1 Houston <named list [5]> OK <a href="#cb16-8" aria-hidden="true" tabindex="-1"></a>#> 2 Washington <named list [5]> OK <a href="#cb16-9" aria-hidden="true" tabindex="-1"></a>#> 3 Washington <named list [5]> OK <a href="#cb16-10" aria-hidden="true" tabindex="-1"></a>#> 4 New York <named list [5]> OK <a href="#cb16-11" aria-hidden="true" tabindex="-1"></a>#> 5 Chicago <named list [5]> OK <a href="#cb16-12" aria-hidden="true" tabindex="-1"></a>#> 6 Arlington <named list [5]> OK <a href="#cb16-13" aria-hidden="true" tabindex="-1"></a>#> # … with 1 more row</code></pre></div> Now these all have the same components, as revealed by <code>unnest_wider()</code>: <div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a>repurrrsive::gmaps_cities %>% <a href="#cb17-2" aria-hidden="true" tabindex="-1"></a> unnest_wider(json) %>% <a href="#cb17-3" aria-hidden="true" tabindex="-1"></a> unnest_longer(results) %>% <a href="#cb17-4" aria-hidden="true" tabindex="-1"></a> unnest_wider(results) <a href="#cb17-5" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 7 × 7 <a href="#cb17-6" aria-hidden="true" tabindex="-1"></a>#> city address_components formatted_a…¹ geometry place…² types status <a href="#cb17-7" aria-hidden="true" tabindex="-1"></a>#> <chr> <list> <chr> <list> <chr> <list> <chr> <a href="#cb17-8" aria-hidden="true" tabindex="-1"></a>#> 1 Houston <list [4]> Houston, TX,… <named list> ChIJAY… <list> OK <a href="#cb17-9" aria-hidden="true" tabindex="-1"></a>#> 2 Washington <list [2]> Washington, … <named list> ChIJ-b… <list> OK <a href="#cb17-10" aria-hidden="true" tabindex="-1"></a>#> 3 Washington <list [4]>