A loose federation of distributed, typed datasets
1<!DOCTYPE html>
2<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
3
4<meta charset="utf-8">
5<meta name="generator" content="quarto-1.7.34">
6
7<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
8
9<meta name="description" content="HuggingFace-style dataset loading interface">
10
11<title>load_dataset API – atdata</title>
12<style>
13code{white-space: pre-wrap;}
14span.smallcaps{font-variant: small-caps;}
15div.columns{display: flex; gap: min(4vw, 1.5em);}
16div.column{flex: auto; overflow-x: auto;}
17div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
18ul.task-list{list-style: none;}
19ul.task-list li input[type="checkbox"] {
20 width: 0.8em;
21 margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
22 vertical-align: middle;
23}
24/* CSS for syntax highlighting */
25html { -webkit-text-size-adjust: 100%; }
26pre > code.sourceCode { white-space: pre; position: relative; }
27pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
28pre > code.sourceCode > span:empty { height: 1.2em; }
29.sourceCode { overflow: visible; }
30code.sourceCode > span { color: inherit; text-decoration: inherit; }
31div.sourceCode { margin: 1em 0; }
32pre.sourceCode { margin: 0; }
33@media screen {
34div.sourceCode { overflow: auto; }
35}
36@media print {
37pre > code.sourceCode { white-space: pre-wrap; }
38pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
39}
40pre.numberSource code
41 { counter-reset: source-line 0; }
42pre.numberSource code > span
43 { position: relative; left: -4em; counter-increment: source-line; }
44pre.numberSource code > span > a:first-child::before
45 { content: counter(source-line);
46 position: relative; left: -1em; text-align: right; vertical-align: baseline;
47 border: none; display: inline-block;
48 -webkit-touch-callout: none; -webkit-user-select: none;
49 -khtml-user-select: none; -moz-user-select: none;
50 -ms-user-select: none; user-select: none;
51 padding: 0 4px; width: 4em;
52 }
53pre.numberSource { margin-left: 3em; padding-left: 4px; }
54div.sourceCode
55 { }
56@media screen {
57pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
58}
59</style>
60
61
62<script src="../site_libs/quarto-nav/quarto-nav.js"></script>
63<script src="../site_libs/quarto-nav/headroom.min.js"></script>
64<script src="../site_libs/clipboard/clipboard.min.js"></script>
65<script src="../site_libs/quarto-search/autocomplete.umd.js"></script>
66<script src="../site_libs/quarto-search/fuse.min.js"></script>
67<script src="../site_libs/quarto-search/quarto-search.js"></script>
68<meta name="quarto:offset" content="../">
69<script src="../site_libs/quarto-html/quarto.js" type="module"></script>
70<script src="../site_libs/quarto-html/tabsets/tabsets.js" type="module"></script>
71<script src="../site_libs/quarto-html/popper.min.js"></script>
72<script src="../site_libs/quarto-html/tippy.umd.min.js"></script>
73<script src="../site_libs/quarto-html/anchor.min.js"></script>
74<link href="../site_libs/quarto-html/tippy.css" rel="stylesheet">
75<link href="../site_libs/quarto-html/quarto-syntax-highlighting-9582434199d49cc9e91654cdeeb4866b.css" rel="stylesheet" class="quarto-color-scheme" id="quarto-text-highlighting-styles">
76<link href="../site_libs/quarto-html/quarto-syntax-highlighting-dark-8dcd8563ea6803ab7cbb3d71ca5772e1.css" rel="stylesheet" class="quarto-color-scheme quarto-color-alternate" id="quarto-text-highlighting-styles">
77<link href="../site_libs/quarto-html/quarto-syntax-highlighting-9582434199d49cc9e91654cdeeb4866b.css" rel="stylesheet" class="quarto-color-scheme-extra" id="quarto-text-highlighting-styles">
78<script src="../site_libs/bootstrap/bootstrap.min.js"></script>
79<link href="../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
80<link href="../site_libs/bootstrap/bootstrap-62bce24ca844314e7bb1a34dbdfe05cc.min.css" rel="stylesheet" append-hash="true" class="quarto-color-scheme" id="quarto-bootstrap" data-mode="light">
81<link href="../site_libs/bootstrap/bootstrap-dark-7964ffd8887b0991fe8d71c6c8bc75d6.min.css" rel="stylesheet" append-hash="true" class="quarto-color-scheme quarto-color-alternate" id="quarto-bootstrap" data-mode="dark">
82<link href="../site_libs/bootstrap/bootstrap-62bce24ca844314e7bb1a34dbdfe05cc.min.css" rel="stylesheet" append-hash="true" class="quarto-color-scheme-extra" id="quarto-bootstrap" data-mode="light">
83<script id="quarto-search-options" type="application/json">{
84 "location": "navbar",
85 "copy-button": false,
86 "collapse-after": 3,
87 "panel-placement": "end",
88 "type": "overlay",
89 "limit": 50,
90 "keyboard-shortcut": [
91 "f",
92 "/",
93 "s"
94 ],
95 "show-item-context": false,
96 "language": {
97 "search-no-results-text": "No results",
98 "search-matching-documents-text": "matching documents",
99 "search-copy-link-title": "Copy link to search",
100 "search-hide-matches-text": "Hide additional matches",
101 "search-more-match-text": "more match in this document",
102 "search-more-matches-text": "more matches in this document",
103 "search-clear-button-title": "Clear",
104 "search-text-placeholder": "",
105 "search-detached-cancel-button-title": "Cancel",
106 "search-submit-button-title": "Submit",
107 "search-label": "Search"
108 }
109}</script>
110
111
112<link rel="stylesheet" href="../assets/styles.css">
113</head>
114
115<body class="nav-sidebar docked nav-fixed quarto-light"><script id="quarto-html-before-body" type="application/javascript">
116 const toggleBodyColorMode = (bsSheetEl) => {
117 const mode = bsSheetEl.getAttribute("data-mode");
118 const bodyEl = window.document.querySelector("body");
119 if (mode === "dark") {
120 bodyEl.classList.add("quarto-dark");
121 bodyEl.classList.remove("quarto-light");
122 } else {
123 bodyEl.classList.add("quarto-light");
124 bodyEl.classList.remove("quarto-dark");
125 }
126 }
127 const toggleBodyColorPrimary = () => {
128 const bsSheetEl = window.document.querySelector("link#quarto-bootstrap:not([rel=disabled-stylesheet])");
129 if (bsSheetEl) {
130 toggleBodyColorMode(bsSheetEl);
131 }
132 }
133 const setColorSchemeToggle = (alternate) => {
134 const toggles = window.document.querySelectorAll('.quarto-color-scheme-toggle');
135 for (let i=0; i < toggles.length; i++) {
136 const toggle = toggles[i];
137 if (toggle) {
138 if (alternate) {
139 toggle.classList.add("alternate");
140 } else {
141 toggle.classList.remove("alternate");
142 }
143 }
144 }
145 };
146 const toggleColorMode = (alternate) => {
147 // Switch the stylesheets
148 const primaryStylesheets = window.document.querySelectorAll('link.quarto-color-scheme:not(.quarto-color-alternate)');
149 const alternateStylesheets = window.document.querySelectorAll('link.quarto-color-scheme.quarto-color-alternate');
150 manageTransitions('#quarto-margin-sidebar .nav-link', false);
151 if (alternate) {
152 // note: dark is layered on light, we don't disable primary!
153 enableStylesheet(alternateStylesheets);
154 for (const sheetNode of alternateStylesheets) {
155 if (sheetNode.id === "quarto-bootstrap") {
156 toggleBodyColorMode(sheetNode);
157 }
158 }
159 } else {
160 disableStylesheet(alternateStylesheets);
161 enableStylesheet(primaryStylesheets)
162 toggleBodyColorPrimary();
163 }
164 manageTransitions('#quarto-margin-sidebar .nav-link', true);
165 // Switch the toggles
166 setColorSchemeToggle(alternate)
167 // Hack to workaround the fact that safari doesn't
168 // properly recolor the scrollbar when toggling (#1455)
169 if (navigator.userAgent.indexOf('Safari') > 0 && navigator.userAgent.indexOf('Chrome') == -1) {
170 manageTransitions("body", false);
171 window.scrollTo(0, 1);
172 setTimeout(() => {
173 window.scrollTo(0, 0);
174 manageTransitions("body", true);
175 }, 40);
176 }
177 }
178 const disableStylesheet = (stylesheets) => {
179 for (let i=0; i < stylesheets.length; i++) {
180 const stylesheet = stylesheets[i];
181 stylesheet.rel = 'disabled-stylesheet';
182 }
183 }
184 const enableStylesheet = (stylesheets) => {
185 for (let i=0; i < stylesheets.length; i++) {
186 const stylesheet = stylesheets[i];
187 if(stylesheet.rel !== 'stylesheet') { // for Chrome, which will still FOUC without this check
188 stylesheet.rel = 'stylesheet';
189 }
190 }
191 }
192 const manageTransitions = (selector, allowTransitions) => {
193 const els = window.document.querySelectorAll(selector);
194 for (let i=0; i < els.length; i++) {
195 const el = els[i];
196 if (allowTransitions) {
197 el.classList.remove('notransition');
198 } else {
199 el.classList.add('notransition');
200 }
201 }
202 }
203 const isFileUrl = () => {
204 return window.location.protocol === 'file:';
205 }
206 const hasAlternateSentinel = () => {
207 let styleSentinel = getColorSchemeSentinel();
208 if (styleSentinel !== null) {
209 return styleSentinel === "alternate";
210 } else {
211 return false;
212 }
213 }
214 const setStyleSentinel = (alternate) => {
215 const value = alternate ? "alternate" : "default";
216 if (!isFileUrl()) {
217 window.localStorage.setItem("quarto-color-scheme", value);
218 } else {
219 localAlternateSentinel = value;
220 }
221 }
222 const getColorSchemeSentinel = () => {
223 if (!isFileUrl()) {
224 const storageValue = window.localStorage.getItem("quarto-color-scheme");
225 return storageValue != null ? storageValue : localAlternateSentinel;
226 } else {
227 return localAlternateSentinel;
228 }
229 }
230 const toggleGiscusIfUsed = (isAlternate, darkModeDefault) => {
231 const baseTheme = document.querySelector('#giscus-base-theme')?.value ?? 'light';
232 const alternateTheme = document.querySelector('#giscus-alt-theme')?.value ?? 'dark';
233 let newTheme = '';
234 if(authorPrefersDark) {
235 newTheme = isAlternate ? baseTheme : alternateTheme;
236 } else {
237 newTheme = isAlternate ? alternateTheme : baseTheme;
238 }
239 const changeGiscusTheme = () => {
240 // From: https://github.com/giscus/giscus/issues/336
241 const sendMessage = (message) => {
242 const iframe = document.querySelector('iframe.giscus-frame');
243 if (!iframe) return;
244 iframe.contentWindow.postMessage({ giscus: message }, 'https://giscus.app');
245 }
246 sendMessage({
247 setConfig: {
248 theme: newTheme
249 }
250 });
251 }
252 const isGiscussLoaded = window.document.querySelector('iframe.giscus-frame') !== null;
253 if (isGiscussLoaded) {
254 changeGiscusTheme();
255 }
256 };
257 const authorPrefersDark = false;
258 const darkModeDefault = authorPrefersDark;
259 document.querySelector('link#quarto-text-highlighting-styles.quarto-color-scheme-extra').rel = 'disabled-stylesheet';
260 document.querySelector('link#quarto-bootstrap.quarto-color-scheme-extra').rel = 'disabled-stylesheet';
261 let localAlternateSentinel = darkModeDefault ? 'alternate' : 'default';
262 // Dark / light mode switch
263 window.quartoToggleColorScheme = () => {
264 // Read the current dark / light value
265 let toAlternate = !hasAlternateSentinel();
266 toggleColorMode(toAlternate);
267 setStyleSentinel(toAlternate);
268 toggleGiscusIfUsed(toAlternate, darkModeDefault);
269 window.dispatchEvent(new Event('resize'));
270 };
271 // Switch to dark mode if need be
272 if (hasAlternateSentinel()) {
273 toggleColorMode(true);
274 } else {
275 toggleColorMode(false);
276 }
277 </script>
278
279<div id="quarto-search-results"></div>
280 <header id="quarto-header" class="headroom fixed-top">
281 <nav class="navbar navbar-expand-lg " data-bs-theme="dark">
282 <div class="navbar-container container-fluid">
283 <div class="navbar-brand-container mx-auto">
284 <a class="navbar-brand" href="../index.html">
285 <span class="navbar-title">atdata</span>
286 </a>
287 </div>
288 <div id="quarto-search" class="" title="Search"></div>
289 <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbarCollapse" aria-controls="navbarCollapse" role="menu" aria-expanded="false" aria-label="Toggle navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
290 <span class="navbar-toggler-icon"></span>
291</button>
292 <div class="collapse navbar-collapse" id="navbarCollapse">
293 <ul class="navbar-nav navbar-nav-scroll me-auto">
294 <li class="nav-item">
295 <a class="nav-link active" href="../index.html" aria-current="page">
296<span class="menu-text">Guide</span></a>
297 </li>
298 <li class="nav-item dropdown ">
299 <a class="nav-link dropdown-toggle" href="#" id="nav-menu-tutorials" role="link" data-bs-toggle="dropdown" aria-expanded="false">
300 <span class="menu-text">Tutorials</span>
301 </a>
302 <ul class="dropdown-menu" aria-labelledby="nav-menu-tutorials">
303 <li>
304 <a class="dropdown-item" href="../tutorials/quickstart.html">
305 <span class="dropdown-text">Quick Start</span></a>
306 </li>
307 <li>
308 <a class="dropdown-item" href="../tutorials/local-workflow.html">
309 <span class="dropdown-text">Local Workflow</span></a>
310 </li>
311 <li>
312 <a class="dropdown-item" href="../tutorials/atmosphere.html">
313 <span class="dropdown-text">Atmosphere Publishing</span></a>
314 </li>
315 <li>
316 <a class="dropdown-item" href="../tutorials/promotion.html">
317 <span class="dropdown-text">Promotion Workflow</span></a>
318 </li>
319 </ul>
320 </li>
321 <li class="nav-item dropdown ">
322 <a class="nav-link dropdown-toggle" href="#" id="nav-menu-reference" role="link" data-bs-toggle="dropdown" aria-expanded="false">
323 <span class="menu-text">Reference</span>
324 </a>
325 <ul class="dropdown-menu" aria-labelledby="nav-menu-reference">
326 <li>
327 <a class="dropdown-item" href="../reference/architecture.html">
328 <span class="dropdown-text">Architecture Overview</span></a>
329 </li>
330 <li>
331 <a class="dropdown-item" href="../reference/packable-samples.html">
332 <span class="dropdown-text">Packable Samples</span></a>
333 </li>
334 <li>
335 <a class="dropdown-item" href="../reference/datasets.html">
336 <span class="dropdown-text">Datasets</span></a>
337 </li>
338 <li>
339 <a class="dropdown-item" href="../reference/lenses.html">
340 <span class="dropdown-text">Lenses</span></a>
341 </li>
342 <li>
343 <a class="dropdown-item" href="../reference/local-storage.html">
344 <span class="dropdown-text">Local Storage</span></a>
345 </li>
346 <li>
347 <a class="dropdown-item" href="../reference/atmosphere.html">
348 <span class="dropdown-text">Atmosphere</span></a>
349 </li>
350 <li>
351 <a class="dropdown-item" href="../reference/promotion.html">
352 <span class="dropdown-text">Promotion</span></a>
353 </li>
354 <li>
355 <a class="dropdown-item" href="../reference/load-dataset.html">
356 <span class="dropdown-text">load_dataset API</span></a>
357 </li>
358 <li>
359 <a class="dropdown-item" href="../reference/protocols.html">
360 <span class="dropdown-text">Protocols</span></a>
361 </li>
362 <li>
363 <a class="dropdown-item" href="../reference/uri-spec.html">
364 <span class="dropdown-text">URI Specification</span></a>
365 </li>
366 <li>
367 <a class="dropdown-item" href="../reference/troubleshooting.html">
368 <span class="dropdown-text">Troubleshooting & FAQ</span></a>
369 </li>
370 <li>
371 <a class="dropdown-item" href="../reference/deployment.html">
372 <span class="dropdown-text">Deployment Guide</span></a>
373 </li>
374 </ul>
375 </li>
376 <li class="nav-item">
377 <a class="nav-link" href="../api/index.html">
378<span class="menu-text">API</span></a>
379 </li>
380</ul>
381 <ul class="navbar-nav navbar-nav-scroll ms-auto">
382 <li class="nav-item compact">
383 <a class="nav-link" href="https://github.com/your-org/atdata"> <i class="bi bi-github" role="img">
384</i>
385<span class="menu-text"></span></a>
386 </li>
387</ul>
388 </div> <!-- /navcollapse -->
389 <div class="quarto-navbar-tools">
390 <a href="" class="quarto-color-scheme-toggle quarto-navigation-tool px-1" onclick="window.quartoToggleColorScheme(); return false;" title="Toggle dark mode"><i class="bi"></i></a>
391</div>
392 </div> <!-- /container-fluid -->
393 </nav>
394 <nav class="quarto-secondary-nav">
395 <div class="container-fluid d-flex">
396 <button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
397 <i class="bi bi-layout-text-sidebar-reverse"></i>
398 </button>
399 <nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../reference/architecture.html">Reference</a></li><li class="breadcrumb-item"><a href="../reference/load-dataset.html">load_dataset API</a></li></ol></nav>
400 <a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
401 </a>
402 </div>
403 </nav>
404</header>
405<!-- content -->
406<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article page-navbar">
407<!-- sidebar -->
408 <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
409 <div class="sidebar-menu-container">
410 <ul class="list-unstyled mt-1">
411 <li class="sidebar-item">
412 <div class="sidebar-item-container">
413 <a href="../index.html" class="sidebar-item-text sidebar-link">
414 <span class="menu-text">atdata</span></a>
415 </div>
416</li>
417 <li class="sidebar-item sidebar-item-section">
418 <div class="sidebar-item-container">
419 <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true">
420 <span class="menu-text">Getting Started</span></a>
421 <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section">
422 <i class="bi bi-chevron-right ms-2"></i>
423 </a>
424 </div>
425 <ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">
426 <li class="sidebar-item">
427 <div class="sidebar-item-container">
428 <a href="../tutorials/quickstart.html" class="sidebar-item-text sidebar-link">
429 <span class="menu-text">Quick Start</span></a>
430 </div>
431</li>
432 <li class="sidebar-item">
433 <div class="sidebar-item-container">
434 <a href="../tutorials/local-workflow.html" class="sidebar-item-text sidebar-link">
435 <span class="menu-text">Local Workflow</span></a>
436 </div>
437</li>
438 <li class="sidebar-item">
439 <div class="sidebar-item-container">
440 <a href="../tutorials/atmosphere.html" class="sidebar-item-text sidebar-link">
441 <span class="menu-text">Atmosphere Publishing</span></a>
442 </div>
443</li>
444 <li class="sidebar-item">
445 <div class="sidebar-item-container">
446 <a href="../tutorials/promotion.html" class="sidebar-item-text sidebar-link">
447 <span class="menu-text">Promotion Workflow</span></a>
448 </div>
449</li>
450 </ul>
451 </li>
452 <li class="sidebar-item sidebar-item-section">
453 <div class="sidebar-item-container">
454 <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true">
455 <span class="menu-text">Reference</span></a>
456 <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true" aria-label="Toggle section">
457 <i class="bi bi-chevron-right ms-2"></i>
458 </a>
459 </div>
460 <ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show">
461 <li class="sidebar-item">
462 <div class="sidebar-item-container">
463 <a href="../reference/architecture.html" class="sidebar-item-text sidebar-link">
464 <span class="menu-text">Architecture Overview</span></a>
465 </div>
466</li>
467 <li class="sidebar-item">
468 <div class="sidebar-item-container">
469 <a href="../reference/packable-samples.html" class="sidebar-item-text sidebar-link">
470 <span class="menu-text">Packable Samples</span></a>
471 </div>
472</li>
473 <li class="sidebar-item">
474 <div class="sidebar-item-container">
475 <a href="../reference/datasets.html" class="sidebar-item-text sidebar-link">
476 <span class="menu-text">Datasets</span></a>
477 </div>
478</li>
479 <li class="sidebar-item">
480 <div class="sidebar-item-container">
481 <a href="../reference/lenses.html" class="sidebar-item-text sidebar-link">
482 <span class="menu-text">Lenses</span></a>
483 </div>
484</li>
485 <li class="sidebar-item">
486 <div class="sidebar-item-container">
487 <a href="../reference/local-storage.html" class="sidebar-item-text sidebar-link">
488 <span class="menu-text">Local Storage</span></a>
489 </div>
490</li>
491 <li class="sidebar-item">
492 <div class="sidebar-item-container">
493 <a href="../reference/atmosphere.html" class="sidebar-item-text sidebar-link">
494 <span class="menu-text">Atmosphere (ATProto Integration)</span></a>
495 </div>
496</li>
497 <li class="sidebar-item">
498 <div class="sidebar-item-container">
499 <a href="../reference/promotion.html" class="sidebar-item-text sidebar-link">
500 <span class="menu-text">Promotion Workflow</span></a>
501 </div>
502</li>
503 <li class="sidebar-item">
504 <div class="sidebar-item-container">
505 <a href="../reference/load-dataset.html" class="sidebar-item-text sidebar-link active">
506 <span class="menu-text">load_dataset API</span></a>
507 </div>
508</li>
509 <li class="sidebar-item">
510 <div class="sidebar-item-container">
511 <a href="../reference/protocols.html" class="sidebar-item-text sidebar-link">
512 <span class="menu-text">Protocols</span></a>
513 </div>
514</li>
515 <li class="sidebar-item">
516 <div class="sidebar-item-container">
517 <a href="../reference/uri-spec.html" class="sidebar-item-text sidebar-link">
518 <span class="menu-text">URI Specification</span></a>
519 </div>
520</li>
521 <li class="sidebar-item">
522 <div class="sidebar-item-container">
523 <a href="../reference/troubleshooting.html" class="sidebar-item-text sidebar-link">
524 <span class="menu-text">Troubleshooting & FAQ</span></a>
525 </div>
526</li>
527 <li class="sidebar-item">
528 <div class="sidebar-item-container">
529 <a href="../reference/deployment.html" class="sidebar-item-text sidebar-link">
530 <span class="menu-text">Deployment Guide</span></a>
531 </div>
532</li>
533 </ul>
534 </li>
535 </ul>
536 </div>
537</nav>
538<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
539<!-- margin-sidebar -->
540 <div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
541 <nav id="TOC" role="doc-toc" class="toc-active">
542 <h2 id="toc-title">On this page</h2>
543
544 <ul>
545 <li><a href="#overview" id="toc-overview" class="nav-link active" data-scroll-target="#overview">Overview</a></li>
546 <li><a href="#basic-usage" id="toc-basic-usage" class="nav-link" data-scroll-target="#basic-usage">Basic Usage</a></li>
547 <li><a href="#path-formats" id="toc-path-formats" class="nav-link" data-scroll-target="#path-formats">Path Formats</a>
548 <ul class="collapse">
549 <li><a href="#webdataset-brace-notation" id="toc-webdataset-brace-notation" class="nav-link" data-scroll-target="#webdataset-brace-notation">WebDataset Brace Notation</a></li>
550 <li><a href="#glob-patterns" id="toc-glob-patterns" class="nav-link" data-scroll-target="#glob-patterns">Glob Patterns</a></li>
551 <li><a href="#local-directory" id="toc-local-directory" class="nav-link" data-scroll-target="#local-directory">Local Directory</a></li>
552 <li><a href="#remote-urls" id="toc-remote-urls" class="nav-link" data-scroll-target="#remote-urls">Remote URLs</a></li>
553 <li><a href="#index-lookup" id="toc-index-lookup" class="nav-link" data-scroll-target="#index-lookup">Index Lookup</a></li>
554 </ul></li>
555 <li><a href="#split-detection" id="toc-split-detection" class="nav-link" data-scroll-target="#split-detection">Split Detection</a></li>
556 <li><a href="#datasetdict" id="toc-datasetdict" class="nav-link" data-scroll-target="#datasetdict">DatasetDict</a></li>
557 <li><a href="#explicit-data-files" id="toc-explicit-data-files" class="nav-link" data-scroll-target="#explicit-data-files">Explicit Data Files</a></li>
558 <li><a href="#streaming-mode" id="toc-streaming-mode" class="nav-link" data-scroll-target="#streaming-mode">Streaming Mode</a></li>
559 <li><a href="#auto-type-resolution" id="toc-auto-type-resolution" class="nav-link" data-scroll-target="#auto-type-resolution">Auto Type Resolution</a></li>
560 <li><a href="#error-handling" id="toc-error-handling" class="nav-link" data-scroll-target="#error-handling">Error Handling</a></li>
561 <li><a href="#complete-example" id="toc-complete-example" class="nav-link" data-scroll-target="#complete-example">Complete Example</a></li>
562 <li><a href="#related" id="toc-related" class="nav-link" data-scroll-target="#related">Related</a></li>
563 </ul>
564<div class="toc-actions"><ul><li><a href="https://github.com/your-org/atdata/edit/main/reference/load-dataset.qmd" class="toc-action"><i class="bi bi-github"></i>Edit this page</a></li><li><a href="https://github.com/your-org/atdata/issues/new" class="toc-action"><i class="bi empty"></i>Report an issue</a></li></ul></div></nav>
565 </div>
566<!-- main -->
567<main class="content" id="quarto-document-content">
568
569
570<header id="title-block-header" class="quarto-title-block default"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item"><a href="../reference/architecture.html">Reference</a></li><li class="breadcrumb-item"><a href="../reference/load-dataset.html">load_dataset API</a></li></ol></nav>
571<div class="quarto-title">
572<h1 class="title">load_dataset API</h1>
573</div>
574
575<div>
576 <div class="description">
577 HuggingFace-style dataset loading interface
578 </div>
579</div>
580
581
582<div class="quarto-title-meta">
583
584
585
586
587 </div>
588
589
590
591</header>
592
593
594<p>The <code>load_dataset()</code> function provides a HuggingFace Datasets-style interface for loading typed datasets.</p>
595<section id="overview" class="level2">
596<h2 class="anchored" data-anchor-id="overview">Overview</h2>
597<p>Key differences from HuggingFace Datasets:</p>
598<ul>
599<li>Requires explicit <code>sample_type</code> parameter (typed dataclass) unless using index</li>
600<li>Returns <code>atdata.Dataset[ST]</code> instead of HF Dataset</li>
601<li>Built on WebDataset for efficient streaming</li>
602<li>No Arrow caching layer</li>
603</ul>
604</section>
605<section id="basic-usage" class="level2">
606<h2 class="anchored" data-anchor-id="basic-usage">Basic Usage</h2>
607<div id="44ca6bce" class="cell">
608<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> atdata</span>
609<span id="cb1-2"><a href="#cb1-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> atdata <span class="im">import</span> load_dataset</span>
610<span id="cb1-3"><a href="#cb1-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> numpy.typing <span class="im">import</span> NDArray</span>
611<span id="cb1-4"><a href="#cb1-4" aria-hidden="true" tabindex="-1"></a></span>
612<span id="cb1-5"><a href="#cb1-5" aria-hidden="true" tabindex="-1"></a><span class="at">@atdata.packable</span></span>
613<span id="cb1-6"><a href="#cb1-6" aria-hidden="true" tabindex="-1"></a><span class="kw">class</span> TextSample:</span>
614<span id="cb1-7"><a href="#cb1-7" aria-hidden="true" tabindex="-1"></a> text: <span class="bu">str</span></span>
615<span id="cb1-8"><a href="#cb1-8" aria-hidden="true" tabindex="-1"></a> label: <span class="bu">int</span></span>
616<span id="cb1-9"><a href="#cb1-9" aria-hidden="true" tabindex="-1"></a></span>
617<span id="cb1-10"><a href="#cb1-10" aria-hidden="true" tabindex="-1"></a><span class="co"># Load a specific split</span></span>
618<span id="cb1-11"><a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>train_ds <span class="op">=</span> load_dataset(<span class="st">"path/to/data.tar"</span>, TextSample, split<span class="op">=</span><span class="st">"train"</span>)</span>
619<span id="cb1-12"><a href="#cb1-12" aria-hidden="true" tabindex="-1"></a></span>
620<span id="cb1-13"><a href="#cb1-13" aria-hidden="true" tabindex="-1"></a><span class="co"># Load all splits (returns DatasetDict)</span></span>
621<span id="cb1-14"><a href="#cb1-14" aria-hidden="true" tabindex="-1"></a>ds_dict <span class="op">=</span> load_dataset(<span class="st">"path/to/data/"</span>, TextSample)</span>
622<span id="cb1-15"><a href="#cb1-15" aria-hidden="true" tabindex="-1"></a>train_ds <span class="op">=</span> ds_dict[<span class="st">"train"</span>]</span>
623<span id="cb1-16"><a href="#cb1-16" aria-hidden="true" tabindex="-1"></a>test_ds <span class="op">=</span> ds_dict[<span class="st">"test"</span>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
624</div>
625</section>
626<section id="path-formats" class="level2">
627<h2 class="anchored" data-anchor-id="path-formats">Path Formats</h2>
628<section id="webdataset-brace-notation" class="level3">
629<h3 class="anchored" data-anchor-id="webdataset-brace-notation">WebDataset Brace Notation</h3>
630<div id="8d0a44f7" class="cell">
631<div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Range notation</span></span>
632<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"data-{000000..000099}.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span>
633<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a></span>
634<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="co"># List notation</span></span>
635<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"data-{train,test,val}.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
636</div>
637</section>
638<section id="glob-patterns" class="level3">
639<h3 class="anchored" data-anchor-id="glob-patterns">Glob Patterns</h3>
640<div id="f88b246c" class="cell">
641<div class="sourceCode cell-code" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Match all tar files</span></span>
642<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"path/to/*.tar"</span>, MySample)</span>
643<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a></span>
644<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="co"># Match pattern</span></span>
645<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"path/to/train-*.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
646</div>
647</section>
648<section id="local-directory" class="level3">
649<h3 class="anchored" data-anchor-id="local-directory">Local Directory</h3>
650<div id="dd112997" class="cell">
651<div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Scans for .tar files</span></span>
652<span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"./my-dataset/"</span>, MySample)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
653</div>
654</section>
655<section id="remote-urls" class="level3">
656<h3 class="anchored" data-anchor-id="remote-urls">Remote URLs</h3>
657<div id="fb8989cb" class="cell">
658<div class="sourceCode cell-code" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="co"># S3 (public buckets)</span></span>
659<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"s3://bucket/data-{000..099}.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span>
660<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a></span>
661<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a><span class="co"># HTTP/HTTPS</span></span>
662<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"https://example.com/data.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span>
663<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a></span>
664<span id="cb5-7"><a href="#cb5-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Google Cloud Storage</span></span>
665<span id="cb5-8"><a href="#cb5-8" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"gs://bucket/data.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
666</div>
667<div class="callout callout-style-default callout-note callout-titled">
668<div class="callout-header d-flex align-content-center">
669<div class="callout-icon-container">
670<i class="callout-icon"></i>
671</div>
672<div class="callout-title-container flex-fill">
673Note
674</div>
675</div>
676<div class="callout-body-container callout-body">
677<p>For private S3 buckets or S3-compatible storage with authentication, use <code>atdata.S3Source</code> with <code>Dataset</code> directly. See <a href="../reference/datasets.html">Datasets</a> for details.</p>
678</div>
679</div>
680</section>
681<section id="index-lookup" class="level3">
682<h3 class="anchored" data-anchor-id="index-lookup">Index Lookup</h3>
683<div id="415c2094" class="cell">
684<div class="sourceCode cell-code" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> atdata.local <span class="im">import</span> LocalIndex</span>
685<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a></span>
686<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a>index <span class="op">=</span> LocalIndex()</span>
687<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a></span>
688<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a><span class="co"># Load from local index (auto-resolves type from schema)</span></span>
689<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"@local/my-dataset"</span>, index<span class="op">=</span>index, split<span class="op">=</span><span class="st">"train"</span>)</span>
690<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a></span>
691<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a><span class="co"># With explicit type</span></span>
692<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"@local/my-dataset"</span>, MySample, index<span class="op">=</span>index, split<span class="op">=</span><span class="st">"train"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
693</div>
694</section>
695</section>
696<section id="split-detection" class="level2">
697<h2 class="anchored" data-anchor-id="split-detection">Split Detection</h2>
698<p>Splits are automatically detected from filenames and directories:</p>
699<table class="caption-top table">
700<thead>
701<tr class="header">
702<th>Pattern</th>
703<th>Detected Split</th>
704</tr>
705</thead>
706<tbody>
707<tr class="odd">
708<td><code>train-*.tar</code>, <code>training-*.tar</code></td>
709<td>train</td>
710</tr>
711<tr class="even">
712<td><code>test-*.tar</code>, <code>testing-*.tar</code></td>
713<td>test</td>
714</tr>
715<tr class="odd">
716<td><code>val-*.tar</code>, <code>valid-*.tar</code>, <code>validation-*.tar</code></td>
717<td>validation</td>
718</tr>
719<tr class="even">
720<td><code>dev-*.tar</code>, <code>development-*.tar</code></td>
721<td>validation</td>
722</tr>
723<tr class="odd">
724<td><code>train/*.tar</code> (directory)</td>
725<td>train</td>
726</tr>
727<tr class="even">
728<td><code>test/*.tar</code> (directory)</td>
729<td>test</td>
730</tr>
731</tbody>
732</table>
733<div class="callout callout-style-default callout-note callout-titled">
734<div class="callout-header d-flex align-content-center">
735<div class="callout-icon-container">
736<i class="callout-icon"></i>
737</div>
738<div class="callout-title-container flex-fill">
739Note
740</div>
741</div>
742<div class="callout-body-container callout-body">
743<p>Files without a detected split default to “train”.</p>
744</div>
745</div>
746</section>
747<section id="datasetdict" class="level2">
748<h2 class="anchored" data-anchor-id="datasetdict">DatasetDict</h2>
749<p>When loading without <code>split=</code>, returns a <code>DatasetDict</code>:</p>
750<div id="22c1bc35" class="cell">
751<div class="sourceCode cell-code" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>ds_dict <span class="op">=</span> load_dataset(<span class="st">"path/to/data/"</span>, MySample)</span>
752<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a></span>
753<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a><span class="co"># Access splits</span></span>
754<span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a>train_ds <span class="op">=</span> ds_dict[<span class="st">"train"</span>]</span>
755<span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a>test_ds <span class="op">=</span> ds_dict[<span class="st">"test"</span>]</span>
756<span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a></span>
757<span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a><span class="co"># Iterate splits</span></span>
758<span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> name, dataset <span class="kw">in</span> ds_dict.items():</span>
759<span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"</span><span class="sc">{</span>name<span class="sc">}</span><span class="ss">: </span><span class="sc">{</span><span class="bu">len</span>(dataset.shard_list)<span class="sc">}</span><span class="ss"> shards"</span>)</span>
760<span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a></span>
761<span id="cb7-11"><a href="#cb7-11" aria-hidden="true" tabindex="-1"></a><span class="co"># Properties</span></span>
762<span id="cb7-12"><a href="#cb7-12" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(ds_dict.num_shards) <span class="co"># {'train': 10, 'test': 2}</span></span>
763<span id="cb7-13"><a href="#cb7-13" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(ds_dict.sample_type) <span class="co"># <class 'MySample'></span></span>
764<span id="cb7-14"><a href="#cb7-14" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(ds_dict.streaming) <span class="co"># False</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
765</div>
766</section>
767<section id="explicit-data-files" class="level2">
768<h2 class="anchored" data-anchor-id="explicit-data-files">Explicit Data Files</h2>
769<p>Override automatic detection with <code>data_files</code>:</p>
770<div id="452b998f" class="cell">
771<div class="sourceCode cell-code" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Single pattern</span></span>
772<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(</span>
773<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a> <span class="st">"path/to/"</span>,</span>
774<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a> MySample,</span>
775<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a> data_files<span class="op">=</span><span class="st">"custom-*.tar"</span>,</span>
776<span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a>)</span>
777<span id="cb8-7"><a href="#cb8-7" aria-hidden="true" tabindex="-1"></a></span>
778<span id="cb8-8"><a href="#cb8-8" aria-hidden="true" tabindex="-1"></a><span class="co"># List of patterns</span></span>
779<span id="cb8-9"><a href="#cb8-9" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(</span>
780<span id="cb8-10"><a href="#cb8-10" aria-hidden="true" tabindex="-1"></a> <span class="st">"path/to/"</span>,</span>
781<span id="cb8-11"><a href="#cb8-11" aria-hidden="true" tabindex="-1"></a> MySample,</span>
782<span id="cb8-12"><a href="#cb8-12" aria-hidden="true" tabindex="-1"></a> data_files<span class="op">=</span>[<span class="st">"shard-000.tar"</span>, <span class="st">"shard-001.tar"</span>],</span>
783<span id="cb8-13"><a href="#cb8-13" aria-hidden="true" tabindex="-1"></a>)</span>
784<span id="cb8-14"><a href="#cb8-14" aria-hidden="true" tabindex="-1"></a></span>
785<span id="cb8-15"><a href="#cb8-15" aria-hidden="true" tabindex="-1"></a><span class="co"># Explicit split mapping</span></span>
786<span id="cb8-16"><a href="#cb8-16" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(</span>
787<span id="cb8-17"><a href="#cb8-17" aria-hidden="true" tabindex="-1"></a> <span class="st">"path/to/"</span>,</span>
788<span id="cb8-18"><a href="#cb8-18" aria-hidden="true" tabindex="-1"></a> MySample,</span>
789<span id="cb8-19"><a href="#cb8-19" aria-hidden="true" tabindex="-1"></a> data_files<span class="op">=</span>{</span>
790<span id="cb8-20"><a href="#cb8-20" aria-hidden="true" tabindex="-1"></a> <span class="st">"train"</span>: <span class="st">"training-shards-*.tar"</span>,</span>
791<span id="cb8-21"><a href="#cb8-21" aria-hidden="true" tabindex="-1"></a> <span class="st">"test"</span>: <span class="st">"eval-data.tar"</span>,</span>
792<span id="cb8-22"><a href="#cb8-22" aria-hidden="true" tabindex="-1"></a> },</span>
793<span id="cb8-23"><a href="#cb8-23" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
794</div>
795</section>
796<section id="streaming-mode" class="level2">
797<h2 class="anchored" data-anchor-id="streaming-mode">Streaming Mode</h2>
798<p>The <code>streaming</code> parameter signals intent for streaming mode:</p>
799<div id="9de4892c" class="cell">
800<div class="sourceCode cell-code" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="co"># Mark as streaming</span></span>
801<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a>ds_dict <span class="op">=</span> load_dataset(<span class="st">"path/to/data.tar"</span>, MySample, streaming<span class="op">=</span><span class="va">True</span>)</span>
802<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a></span>
803<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a><span class="co"># Check streaming status</span></span>
804<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a><span class="cf">if</span> ds_dict.streaming:</span>
805<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Streaming mode"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
806</div>
807<div class="callout callout-style-default callout-tip callout-titled">
808<div class="callout-header d-flex align-content-center">
809<div class="callout-icon-container">
810<i class="callout-icon"></i>
811</div>
812<div class="callout-title-container flex-fill">
813Tip
814</div>
815</div>
816<div class="callout-body-container callout-body">
817<p>atdata datasets are always lazy/streaming via WebDataset pipelines. This parameter primarily signals intent.</p>
818</div>
819</div>
820</section>
821<section id="auto-type-resolution" class="level2">
822<h2 class="anchored" data-anchor-id="auto-type-resolution">Auto Type Resolution</h2>
823<p>When using index lookup, the sample type can be resolved automatically:</p>
824<div id="04d401c9" class="cell">
825<div class="sourceCode cell-code" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> atdata.local <span class="im">import</span> LocalIndex</span>
826<span id="cb10-2"><a href="#cb10-2" aria-hidden="true" tabindex="-1"></a></span>
827<span id="cb10-3"><a href="#cb10-3" aria-hidden="true" tabindex="-1"></a>index <span class="op">=</span> LocalIndex()</span>
828<span id="cb10-4"><a href="#cb10-4" aria-hidden="true" tabindex="-1"></a></span>
829<span id="cb10-5"><a href="#cb10-5" aria-hidden="true" tabindex="-1"></a><span class="co"># No sample_type needed - resolved from schema</span></span>
830<span id="cb10-6"><a href="#cb10-6" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> load_dataset(<span class="st">"@local/my-dataset"</span>, index<span class="op">=</span>index, split<span class="op">=</span><span class="st">"train"</span>)</span>
831<span id="cb10-7"><a href="#cb10-7" aria-hidden="true" tabindex="-1"></a></span>
832<span id="cb10-8"><a href="#cb10-8" aria-hidden="true" tabindex="-1"></a><span class="co"># Type is inferred from the stored schema</span></span>
833<span id="cb10-9"><a href="#cb10-9" aria-hidden="true" tabindex="-1"></a>sample_type <span class="op">=</span> ds.sample_type</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
834</div>
835</section>
836<section id="error-handling" class="level2">
837<h2 class="anchored" data-anchor-id="error-handling">Error Handling</h2>
838<div id="fdcf842d" class="cell">
839<div class="sourceCode cell-code" id="cb11"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a><span class="cf">try</span>:</span>
840<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a> ds <span class="op">=</span> load_dataset(<span class="st">"path/to/data.tar"</span>, MySample, split<span class="op">=</span><span class="st">"train"</span>)</span>
841<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a><span class="cf">except</span> <span class="pp">FileNotFoundError</span>:</span>
842<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"No data files found"</span>)</span>
843<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a><span class="cf">except</span> <span class="pp">ValueError</span> <span class="im">as</span> e:</span>
844<span id="cb11-6"><a href="#cb11-6" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> <span class="st">"Split"</span> <span class="kw">in</span> <span class="bu">str</span>(e):</span>
845<span id="cb11-7"><a href="#cb11-7" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Requested split not found"</span>)</span>
846<span id="cb11-8"><a href="#cb11-8" aria-hidden="true" tabindex="-1"></a> <span class="cf">else</span>:</span>
847<span id="cb11-9"><a href="#cb11-9" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"Invalid configuration: </span><span class="sc">{</span>e<span class="sc">}</span><span class="ss">"</span>)</span>
848<span id="cb11-10"><a href="#cb11-10" aria-hidden="true" tabindex="-1"></a><span class="cf">except</span> <span class="pp">KeyError</span>:</span>
849<span id="cb11-11"><a href="#cb11-11" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Dataset not found in index"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
850</div>
851</section>
852<section id="complete-example" class="level2">
853<h2 class="anchored" data-anchor-id="complete-example">Complete Example</h2>
854<div id="6d45dd17" class="cell">
855<div class="sourceCode cell-code" id="cb12"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> numpy <span class="im">as</span> np</span>
856<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> numpy.typing <span class="im">import</span> NDArray</span>
857<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> atdata</span>
858<span id="cb12-4"><a href="#cb12-4" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> atdata <span class="im">import</span> load_dataset</span>
859<span id="cb12-5"><a href="#cb12-5" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> webdataset <span class="im">as</span> wds</span>
860<span id="cb12-6"><a href="#cb12-6" aria-hidden="true" tabindex="-1"></a></span>
861<span id="cb12-7"><a href="#cb12-7" aria-hidden="true" tabindex="-1"></a><span class="co"># 1. Define sample type</span></span>
862<span id="cb12-8"><a href="#cb12-8" aria-hidden="true" tabindex="-1"></a><span class="at">@atdata.packable</span></span>
863<span id="cb12-9"><a href="#cb12-9" aria-hidden="true" tabindex="-1"></a><span class="kw">class</span> ImageSample:</span>
864<span id="cb12-10"><a href="#cb12-10" aria-hidden="true" tabindex="-1"></a> image: NDArray</span>
865<span id="cb12-11"><a href="#cb12-11" aria-hidden="true" tabindex="-1"></a> label: <span class="bu">str</span></span>
866<span id="cb12-12"><a href="#cb12-12" aria-hidden="true" tabindex="-1"></a></span>
867<span id="cb12-13"><a href="#cb12-13" aria-hidden="true" tabindex="-1"></a><span class="co"># 2. Create dataset files</span></span>
868<span id="cb12-14"><a href="#cb12-14" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> split <span class="kw">in</span> [<span class="st">"train"</span>, <span class="st">"test"</span>]:</span>
869<span id="cb12-15"><a href="#cb12-15" aria-hidden="true" tabindex="-1"></a> <span class="cf">with</span> wds.writer.TarWriter(<span class="ss">f"</span><span class="sc">{</span>split<span class="sc">}</span><span class="ss">-000.tar"</span>) <span class="im">as</span> sink:</span>
870<span id="cb12-16"><a href="#cb12-16" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> i <span class="kw">in</span> <span class="bu">range</span>(<span class="dv">100</span>):</span>
871<span id="cb12-17"><a href="#cb12-17" aria-hidden="true" tabindex="-1"></a> sample <span class="op">=</span> ImageSample(</span>
872<span id="cb12-18"><a href="#cb12-18" aria-hidden="true" tabindex="-1"></a> image<span class="op">=</span>np.random.rand(<span class="dv">64</span>, <span class="dv">64</span>, <span class="dv">3</span>).astype(np.float32),</span>
873<span id="cb12-19"><a href="#cb12-19" aria-hidden="true" tabindex="-1"></a> label<span class="op">=</span><span class="ss">f"sample_</span><span class="sc">{</span>i<span class="sc">}</span><span class="ss">"</span>,</span>
874<span id="cb12-20"><a href="#cb12-20" aria-hidden="true" tabindex="-1"></a> )</span>
875<span id="cb12-21"><a href="#cb12-21" aria-hidden="true" tabindex="-1"></a> sink.write({<span class="op">**</span>sample.as_wds, <span class="st">"__key__"</span>: <span class="ss">f"</span><span class="sc">{</span>i<span class="sc">:06d}</span><span class="ss">"</span>})</span>
876<span id="cb12-22"><a href="#cb12-22" aria-hidden="true" tabindex="-1"></a></span>
877<span id="cb12-23"><a href="#cb12-23" aria-hidden="true" tabindex="-1"></a><span class="co"># 3. Load with split detection</span></span>
878<span id="cb12-24"><a href="#cb12-24" aria-hidden="true" tabindex="-1"></a>ds_dict <span class="op">=</span> load_dataset(<span class="st">"./"</span>, ImageSample)</span>
879<span id="cb12-25"><a href="#cb12-25" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(ds_dict.keys()) <span class="co"># dict_keys(['train', 'test'])</span></span>
880<span id="cb12-26"><a href="#cb12-26" aria-hidden="true" tabindex="-1"></a></span>
881<span id="cb12-27"><a href="#cb12-27" aria-hidden="true" tabindex="-1"></a><span class="co"># 4. Iterate</span></span>
882<span id="cb12-28"><a href="#cb12-28" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> batch <span class="kw">in</span> ds_dict[<span class="st">"train"</span>].ordered(batch_size<span class="op">=</span><span class="dv">16</span>):</span>
883<span id="cb12-29"><a href="#cb12-29" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(batch.image.shape) <span class="co"># (16, 64, 64, 3)</span></span>
884<span id="cb12-30"><a href="#cb12-30" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(batch.label) <span class="co"># ['sample_0', 'sample_1', ...]</span></span>
885<span id="cb12-31"><a href="#cb12-31" aria-hidden="true" tabindex="-1"></a> <span class="cf">break</span></span>
886<span id="cb12-32"><a href="#cb12-32" aria-hidden="true" tabindex="-1"></a></span>
887<span id="cb12-33"><a href="#cb12-33" aria-hidden="true" tabindex="-1"></a><span class="co"># 5. Load specific split</span></span>
888<span id="cb12-34"><a href="#cb12-34" aria-hidden="true" tabindex="-1"></a>train_ds <span class="op">=</span> load_dataset(<span class="st">"./"</span>, ImageSample, split<span class="op">=</span><span class="st">"train"</span>)</span>
889<span id="cb12-35"><a href="#cb12-35" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> batch <span class="kw">in</span> train_ds.ordered(batch_size<span class="op">=</span><span class="dv">32</span>):</span>
890<span id="cb12-36"><a href="#cb12-36" aria-hidden="true" tabindex="-1"></a> process(batch)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
891</div>
892</section>
893<section id="related" class="level2">
894<h2 class="anchored" data-anchor-id="related">Related</h2>
895<ul>
896<li><a href="../reference/datasets.html">Datasets</a> - Dataset iteration and batching</li>
897<li><a href="../reference/packable-samples.html">Packable Samples</a> - Defining sample types</li>
898<li><a href="../reference/local-storage.html">Local Storage</a> - LocalIndex for index lookup</li>
899<li><a href="../reference/protocols.html">Protocols</a> - AbstractIndex interface</li>
900</ul>
901
902
903</section>
904
905</main> <!-- /main -->
906<script id="quarto-html-after-body" type="application/javascript">
907 window.document.addEventListener("DOMContentLoaded", function (event) {
908 // Ensure there is a toggle, if there isn't float one in the top right
909 if (window.document.querySelector('.quarto-color-scheme-toggle') === null) {
910 const a = window.document.createElement('a');
911 a.classList.add('top-right');
912 a.classList.add('quarto-color-scheme-toggle');
913 a.href = "";
914 a.onclick = function() { try { window.quartoToggleColorScheme(); } catch {} return false; };
915 const i = window.document.createElement("i");
916 i.classList.add('bi');
917 a.appendChild(i);
918 window.document.body.appendChild(a);
919 }
920 setColorSchemeToggle(hasAlternateSentinel())
921 const icon = "";
922 const anchorJS = new window.AnchorJS();
923 anchorJS.options = {
924 placement: 'right',
925 icon: icon
926 };
927 anchorJS.add('.anchored');
928 const isCodeAnnotation = (el) => {
929 for (const clz of el.classList) {
930 if (clz.startsWith('code-annotation-')) {
931 return true;
932 }
933 }
934 return false;
935 }
936 const onCopySuccess = function(e) {
937 // button target
938 const button = e.trigger;
939 // don't keep focus
940 button.blur();
941 // flash "checked"
942 button.classList.add('code-copy-button-checked');
943 var currentTitle = button.getAttribute("title");
944 button.setAttribute("title", "Copied!");
945 let tooltip;
946 if (window.bootstrap) {
947 button.setAttribute("data-bs-toggle", "tooltip");
948 button.setAttribute("data-bs-placement", "left");
949 button.setAttribute("data-bs-title", "Copied!");
950 tooltip = new bootstrap.Tooltip(button,
951 { trigger: "manual",
952 customClass: "code-copy-button-tooltip",
953 offset: [0, -8]});
954 tooltip.show();
955 }
956 setTimeout(function() {
957 if (tooltip) {
958 tooltip.hide();
959 button.removeAttribute("data-bs-title");
960 button.removeAttribute("data-bs-toggle");
961 button.removeAttribute("data-bs-placement");
962 }
963 button.setAttribute("title", currentTitle);
964 button.classList.remove('code-copy-button-checked');
965 }, 1000);
966 // clear code selection
967 e.clearSelection();
968 }
969 const getTextToCopy = function(trigger) {
970 const codeEl = trigger.previousElementSibling.cloneNode(true);
971 for (const childEl of codeEl.children) {
972 if (isCodeAnnotation(childEl)) {
973 childEl.remove();
974 }
975 }
976 return codeEl.innerText;
977 }
978 const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
979 text: getTextToCopy
980 });
981 clipboard.on('success', onCopySuccess);
982 if (window.document.getElementById('quarto-embedded-source-code-modal')) {
983 const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', {
984 text: getTextToCopy,
985 container: window.document.getElementById('quarto-embedded-source-code-modal')
986 });
987 clipboardModal.on('success', onCopySuccess);
988 }
989 var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
990 var mailtoRegex = new RegExp(/^mailto:/);
991 var filterRegex = new RegExp("https:\/\/github\.com\/your-org\/atdata");
992 var isInternal = (href) => {
993 return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href);
994 }
995 // Inspect non-navigation links and adorn them if external
996 var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool):not(.about-link)');
997 for (var i=0; i<links.length; i++) {
998 const link = links[i];
999 if (!isInternal(link.href)) {
1000 // undo the damage that might have been done by quarto-nav.js in the case of
1001 // links that we want to consider external
1002 if (link.dataset.originalHref !== undefined) {
1003 link.href = link.dataset.originalHref;
1004 }
1005 }
1006 }
1007 function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) {
1008 const config = {
1009 allowHTML: true,
1010 maxWidth: 500,
1011 delay: 100,
1012 arrow: false,
1013 appendTo: function(el) {
1014 return el.parentElement;
1015 },
1016 interactive: true,
1017 interactiveBorder: 10,
1018 theme: 'quarto',
1019 placement: 'bottom-start',
1020 };
1021 if (contentFn) {
1022 config.content = contentFn;
1023 }
1024 if (onTriggerFn) {
1025 config.onTrigger = onTriggerFn;
1026 }
1027 if (onUntriggerFn) {
1028 config.onUntrigger = onUntriggerFn;
1029 }
1030 window.tippy(el, config);
1031 }
1032 const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
1033 for (var i=0; i<noterefs.length; i++) {
1034 const ref = noterefs[i];
1035 tippyHover(ref, function() {
1036 // use id or data attribute instead here
1037 let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
1038 try { href = new URL(href).hash; } catch {}
1039 const id = href.replace(/^#\/?/, "");
1040 const note = window.document.getElementById(id);
1041 if (note) {
1042 return note.innerHTML;
1043 } else {
1044 return "";
1045 }
1046 });
1047 }
1048 const xrefs = window.document.querySelectorAll('a.quarto-xref');
1049 const processXRef = (id, note) => {
1050 // Strip column container classes
1051 const stripColumnClz = (el) => {
1052 el.classList.remove("page-full", "page-columns");
1053 if (el.children) {
1054 for (const child of el.children) {
1055 stripColumnClz(child);
1056 }
1057 }
1058 }
1059 stripColumnClz(note)
1060 if (id === null || id.startsWith('sec-')) {
1061 // Special case sections, only their first couple elements
1062 const container = document.createElement("div");
1063 if (note.children && note.children.length > 2) {
1064 container.appendChild(note.children[0].cloneNode(true));
1065 for (let i = 1; i < note.children.length; i++) {
1066 const child = note.children[i];
1067 if (child.tagName === "P" && child.innerText === "") {
1068 continue;
1069 } else {
1070 container.appendChild(child.cloneNode(true));
1071 break;
1072 }
1073 }
1074 if (window.Quarto?.typesetMath) {
1075 window.Quarto.typesetMath(container);
1076 }
1077 return container.innerHTML
1078 } else {
1079 if (window.Quarto?.typesetMath) {
1080 window.Quarto.typesetMath(note);
1081 }
1082 return note.innerHTML;
1083 }
1084 } else {
1085 // Remove any anchor links if they are present
1086 const anchorLink = note.querySelector('a.anchorjs-link');
1087 if (anchorLink) {
1088 anchorLink.remove();
1089 }
1090 if (window.Quarto?.typesetMath) {
1091 window.Quarto.typesetMath(note);
1092 }
1093 if (note.classList.contains("callout")) {
1094 return note.outerHTML;
1095 } else {
1096 return note.innerHTML;
1097 }
1098 }
1099 }
1100 for (var i=0; i<xrefs.length; i++) {
1101 const xref = xrefs[i];
1102 tippyHover(xref, undefined, function(instance) {
1103 instance.disable();
1104 let url = xref.getAttribute('href');
1105 let hash = undefined;
1106 if (url.startsWith('#')) {
1107 hash = url;
1108 } else {
1109 try { hash = new URL(url).hash; } catch {}
1110 }
1111 if (hash) {
1112 const id = hash.replace(/^#\/?/, "");
1113 const note = window.document.getElementById(id);
1114 if (note !== null) {
1115 try {
1116 const html = processXRef(id, note.cloneNode(true));
1117 instance.setContent(html);
1118 } finally {
1119 instance.enable();
1120 instance.show();
1121 }
1122 } else {
1123 // See if we can fetch this
1124 fetch(url.split('#')[0])
1125 .then(res => res.text())
1126 .then(html => {
1127 const parser = new DOMParser();
1128 const htmlDoc = parser.parseFromString(html, "text/html");
1129 const note = htmlDoc.getElementById(id);
1130 if (note !== null) {
1131 const html = processXRef(id, note);
1132 instance.setContent(html);
1133 }
1134 }).finally(() => {
1135 instance.enable();
1136 instance.show();
1137 });
1138 }
1139 } else {
1140 // See if we can fetch a full url (with no hash to target)
1141 // This is a special case and we should probably do some content thinning / targeting
1142 fetch(url)
1143 .then(res => res.text())
1144 .then(html => {
1145 const parser = new DOMParser();
1146 const htmlDoc = parser.parseFromString(html, "text/html");
1147 const note = htmlDoc.querySelector('main.content');
1148 if (note !== null) {
1149 // This should only happen for chapter cross references
1150 // (since there is no id in the URL)
1151 // remove the first header
1152 if (note.children.length > 0 && note.children[0].tagName === "HEADER") {
1153 note.children[0].remove();
1154 }
1155 const html = processXRef(null, note);
1156 instance.setContent(html);
1157 }
1158 }).finally(() => {
1159 instance.enable();
1160 instance.show();
1161 });
1162 }
1163 }, function(instance) {
1164 });
1165 }
1166 let selectedAnnoteEl;
1167 const selectorForAnnotation = ( cell, annotation) => {
1168 let cellAttr = 'data-code-cell="' + cell + '"';
1169 let lineAttr = 'data-code-annotation="' + annotation + '"';
1170 const selector = 'span[' + cellAttr + '][' + lineAttr + ']';
1171 return selector;
1172 }
1173 const selectCodeLines = (annoteEl) => {
1174 const doc = window.document;
1175 const targetCell = annoteEl.getAttribute("data-target-cell");
1176 const targetAnnotation = annoteEl.getAttribute("data-target-annotation");
1177 const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation));
1178 const lines = annoteSpan.getAttribute("data-code-lines").split(",");
1179 const lineIds = lines.map((line) => {
1180 return targetCell + "-" + line;
1181 })
1182 let top = null;
1183 let height = null;
1184 let parent = null;
1185 if (lineIds.length > 0) {
1186 //compute the position of the single el (top and bottom and make a div)
1187 const el = window.document.getElementById(lineIds[0]);
1188 top = el.offsetTop;
1189 height = el.offsetHeight;
1190 parent = el.parentElement.parentElement;
1191 if (lineIds.length > 1) {
1192 const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]);
1193 const bottom = lastEl.offsetTop + lastEl.offsetHeight;
1194 height = bottom - top;
1195 }
1196 if (top !== null && height !== null && parent !== null) {
1197 // cook up a div (if necessary) and position it
1198 let div = window.document.getElementById("code-annotation-line-highlight");
1199 if (div === null) {
1200 div = window.document.createElement("div");
1201 div.setAttribute("id", "code-annotation-line-highlight");
1202 div.style.position = 'absolute';
1203 parent.appendChild(div);
1204 }
1205 div.style.top = top - 2 + "px";
1206 div.style.height = height + 4 + "px";
1207 div.style.left = 0;
1208 let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter");
1209 if (gutterDiv === null) {
1210 gutterDiv = window.document.createElement("div");
1211 gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter");
1212 gutterDiv.style.position = 'absolute';
1213 const codeCell = window.document.getElementById(targetCell);
1214 const gutter = codeCell.querySelector('.code-annotation-gutter');
1215 gutter.appendChild(gutterDiv);
1216 }
1217 gutterDiv.style.top = top - 2 + "px";
1218 gutterDiv.style.height = height + 4 + "px";
1219 }
1220 selectedAnnoteEl = annoteEl;
1221 }
1222 };
1223 const unselectCodeLines = () => {
1224 const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"];
1225 elementsIds.forEach((elId) => {
1226 const div = window.document.getElementById(elId);
1227 if (div) {
1228 div.remove();
1229 }
1230 });
1231 selectedAnnoteEl = undefined;
1232 };
1233 // Handle positioning of the toggle
1234 window.addEventListener(
1235 "resize",
1236 throttle(() => {
1237 elRect = undefined;
1238 if (selectedAnnoteEl) {
1239 selectCodeLines(selectedAnnoteEl);
1240 }
1241 }, 10)
1242 );
1243 function throttle(fn, ms) {
1244 let throttle = false;
1245 let timer;
1246 return (...args) => {
1247 if(!throttle) { // first call gets through
1248 fn.apply(this, args);
1249 throttle = true;
1250 } else { // all the others get throttled
1251 if(timer) clearTimeout(timer); // cancel #2
1252 timer = setTimeout(() => {
1253 fn.apply(this, args);
1254 timer = throttle = false;
1255 }, ms);
1256 }
1257 };
1258 }
1259 // Attach click handler to the DT
1260 const annoteDls = window.document.querySelectorAll('dt[data-target-cell]');
1261 for (const annoteDlNode of annoteDls) {
1262 annoteDlNode.addEventListener('click', (event) => {
1263 const clickedEl = event.target;
1264 if (clickedEl !== selectedAnnoteEl) {
1265 unselectCodeLines();
1266 const activeEl = window.document.querySelector('dt[data-target-cell].code-annotation-active');
1267 if (activeEl) {
1268 activeEl.classList.remove('code-annotation-active');
1269 }
1270 selectCodeLines(clickedEl);
1271 clickedEl.classList.add('code-annotation-active');
1272 } else {
1273 // Unselect the line
1274 unselectCodeLines();
1275 clickedEl.classList.remove('code-annotation-active');
1276 }
1277 });
1278 }
1279 const findCites = (el) => {
1280 const parentEl = el.parentElement;
1281 if (parentEl) {
1282 const cites = parentEl.dataset.cites;
1283 if (cites) {
1284 return {
1285 el,
1286 cites: cites.split(' ')
1287 };
1288 } else {
1289 return findCites(el.parentElement)
1290 }
1291 } else {
1292 return undefined;
1293 }
1294 };
1295 var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
1296 for (var i=0; i<bibliorefs.length; i++) {
1297 const ref = bibliorefs[i];
1298 const citeInfo = findCites(ref);
1299 if (citeInfo) {
1300 tippyHover(citeInfo.el, function() {
1301 var popup = window.document.createElement('div');
1302 citeInfo.cites.forEach(function(cite) {
1303 var citeDiv = window.document.createElement('div');
1304 citeDiv.classList.add('hanging-indent');
1305 citeDiv.classList.add('csl-entry');
1306 var biblioDiv = window.document.getElementById('ref-' + cite);
1307 if (biblioDiv) {
1308 citeDiv.innerHTML = biblioDiv.innerHTML;
1309 }
1310 popup.appendChild(citeDiv);
1311 });
1312 return popup.innerHTML;
1313 });
1314 }
1315 }
1316 });
1317 </script>
1318</div> <!-- /content -->
1319<footer class="footer">
1320 <div class="nav-footer">
1321 <div class="nav-footer-left">
1322<p>Built with <a href="https://quarto.org/">Quarto</a></p>
1323</div>
1324 <div class="nav-footer-center">
1325
1326 <div class="toc-actions d-sm-block d-md-none"><ul><li><a href="https://github.com/your-org/atdata/edit/main/reference/load-dataset.qmd" class="toc-action"><i class="bi bi-github"></i>Edit this page</a></li><li><a href="https://github.com/your-org/atdata/issues/new" class="toc-action"><i class="bi empty"></i>Report an issue</a></li></ul></div></div>
1327 <div class="nav-footer-right">
1328<p>MIT License</p>
1329</div>
1330 </div>
1331</footer>
1332
1333
1334
1335
1336</body></html>