1107 lines
42 KiB
HTML
1107 lines
42 KiB
HTML
<!doctype html>
|
|
<html>
|
|
<head>
|
|
<meta charset="utf-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no">
|
|
|
|
<!-- Edit me start! -->
|
|
<title>This is where your title goes</title>
|
|
<meta name="description" content=" This is where you put a short description ">
|
|
<meta name="author" content=" Your Name ">
|
|
<!-- Edit me end! -->
|
|
|
|
<link rel="stylesheet" href="../reveal.js/dist/reset.css">
|
|
<link rel="stylesheet" href="../reveal.js/dist/reveal.css">
|
|
<link rel="stylesheet" href="../reveal.js/dist/theme/beige.css">
|
|
|
|
<!-- Theme used for syntax highlighted code -->
|
|
<link rel="stylesheet" href="../reveal.js/plugin/highlight/monokai.css">
|
|
</head>
|
|
<body>
|
|
<div class="reveal">
|
|
<div class="slides">
|
|
|
|
|
|
<section>
|
|
<section>
|
|
<h2>An introduction to DataLad<br />👩💻👨💻<br /><small>with a focus on ML application</small></h2>
|
|
|
|
<div style="margin-top:1em;text-align:center">
|
|
<table style="border: none;">
|
|
<tr>
|
|
<td>Adina Wagner
|
|
<br><small>
|
|
<a href="https://twitter.com/AdinaKrik" target="_blank">
|
|
<img data-src="../pics/twitter.png" style="height:30px;margin:0px" />
|
|
@AdinaKrik</a></small></td>
|
|
<td><img style="height:100px;margin-right:10px" data-src="../pics/fzj_logo.svg" />
|
|
<br></td>
|
|
</tr>
|
|
<tr>
|
|
<td>
|
|
<small><a href="http://psychoinformatics.de" target="_blank">Psychoinformatics lab</a>,
|
|
<br> Institute of Neuroscience and
|
|
Medicine, Brain & Behavior (INM-7)<br>
|
|
Research Center Jülich</small><br>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</div>
|
|
<br><br><small>
|
|
Slides: <a href="https://github.com/datalad-handbook/course/blob/master/talks/PDFs/DL-for-ML.pdf" target="_blank">
|
|
https://github.com/datalad-handbook/course/</a></small>
|
|
</a>
|
|
</section>
|
|
</section>
|
|
|
|
<!--...INTRODUCTION...-->
|
|
|
|
<!--...Prerequisites...-->
|
|
|
|
<section>
|
|
<section>
|
|
<h2>Acknowledgements</h2>
|
|
<table>
|
|
<tr style="vertical-align:middle">
|
|
<td style="vertical-align:middle">
|
|
<dl>
|
|
<dt>Software</dt>
|
|
<dd style="margin-left:5px!important">
|
|
<ul style="margin-left:5px!important">
|
|
<li>Michael Hanke (INM-7)</li>
|
|
<li>Yaroslav Halchenko</li>
|
|
<li>Joey Hess (git-annex)</li>
|
|
<li>Kyle Meyer</li>
|
|
<li>Benjamin Poldrack (INM-7)</li>
|
|
<li><em>26 additional contributors</em></li>
|
|
</ul>
|
|
</dd>
|
|
<dt style="margin-top:20px">Documentation project </dt>
|
|
<dd style="margin-left:5px!important">
|
|
<ul style="margin-left:5px!important">
|
|
<li>Michael Hanke (INM-7)</li>
|
|
<li>Laura Waite (INM-7)</li>
|
|
<li><em>28 additional contributors</em></li>
|
|
</ul>
|
|
</dd>
|
|
</dl>
|
|
</td>
|
|
<td style="vertical-align:middle">
|
|
<div style="margin-bottom:-20px;text-align:center"><strong>Funders</strong></div>
|
|
<img style="height:150px;margin-right:50px" data-src="../pics/nsf.png" />
|
|
<img style="height:150px;margin-right:50pxi;margin-left:50px" data-src="../pics/binc.png" />
|
|
<img style="height:150px;margin-left:50px" data-src="../pics/bmbf.png" />
|
|
<br />
|
|
<img style="height:80px;margin-top:-40px;margin-left:auto;margin-right:auto;width:100%" data-src="../pics/fzj_logo.svg" />
|
|
<div style="margin-top:-20px">
|
|
<img style="height:60px;margin-right:20px" data-src="../pics/erdf.png" />
|
|
<img style="height:60px;margin-right:20px" data-src="../pics/cbbs_logo.png" />
|
|
<img style="height:60px" data-src="../pics/LSA-Logo.png" />
|
|
</div>
|
|
<div style="margin-top:40px;margin-bottom:20px;text-align:center"><strong>Collaborators</strong></div>
|
|
<div style="margin-top:-20px">
|
|
<img style="height:100px;margin:20px" data-src="../pics/hbp_logo.png" />
|
|
<img style="height:100px;margin:20px" data-src="../pics/conp_logo.png" />
|
|
<img style="height:100px;margin:20px" data-src="../pics/vbc_logo.png" />
|
|
</div>
|
|
<div style="margin-top:-40px">
|
|
<img style="height:120px;margin:20px" data-src="../pics/openneuro_logo.png" />
|
|
<img style="height:120px;margin:20px" data-src="../pics/cbrain_logo.png" />
|
|
<img style="height:140px;margin:20px" data-src="../pics/brainlife_logo.png" />
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</section>
|
|
|
|
|
|
|
|
<section>
|
|
<h2>Resources and Further Reading</h2>
|
|
<table>
|
|
<tr>
|
|
<td>
|
|
Comprehensive user documentation in the<br>
|
|
DataLad Handbook
|
|
<a href="http://handbook.datalad.org" target="_blank">(handbook.datalad.org)</a>
|
|
</td>
|
|
<td>
|
|
<img src="../pics/logo.svg" height="150">
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
|
|
<table>
|
|
<tr>
|
|
<td><img src="../pics/artwork/src/enter.svg" height="100"></a></td>
|
|
<td>
|
|
<ul>
|
|
<li>High-level function/command overviews, <br>
|
|
Installation, Configuration, Cheatsheet</li>
|
|
</ul>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<td><img src="../pics/artwork/src/basics.svg" height="100"></td>
|
|
<td>
|
|
<ul>
|
|
<li>Narrative-based code-along course</li>
|
|
<li>Independent on background/skill level, <br>
|
|
suitable for data management novices</li>
|
|
</ul>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<td><img src="../pics/artwork/src/usecases.svg" height="100"></td>
|
|
<td>
|
|
<ul>
|
|
<li>Step-by-step solutions to common <br>
|
|
data management problems, like<br />how to
|
|
make a reproducible paper</li>
|
|
</ul>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
|
|
</section>
|
|
|
|
|
|
|
|
<section>
|
|
<h2>Resources and Further Reading</h2>
|
|
|
|
<br>
|
|
<ul>
|
|
<li>Specifically relevant handbook sections to ML:</li>
|
|
<ul>
|
|
<li>DataLad ML example: <br>
|
|
<a href="http://handbook.datalad.org/en/latest/usecases/ml-analysis.html" target="_blank">handbook.datalad.org/r.html?ml-usecase</a></li>
|
|
<li>Code list with further links: <a href="http://handbook.datalad.org/en/latest/code_from_chapters/usecase_ml_code.html" target="_blank">handbook.datalad.org/r.html?FZJmlcode</a></li>
|
|
</ul>
|
|
<br>
|
|
<li>Not-text-based resources:</li>
|
|
<ul>
|
|
<li><a href="https://www.youtube.com/channel/UCB8-Zf7D0DSzAsREoIt0Bvw" target="_blank">DataLad Youtube channel</a> with talks and tutorials</li>
|
|
</ul>
|
|
</ul>
|
|
</section>
|
|
|
|
|
|
|
|
<section>
|
|
<h2>Questions/interaction</h2>
|
|
<ul>
|
|
<li>Ask questions via chat or by speaking up at any point</li>
|
|
<li>Happy to discuss specific use cases at the end</li>
|
|
<li>Reach out to us via
|
|
<a href="https://app.element.io/#/room/#datalad:matrix.org" target="_blank">Matrix</a> or
|
|
<a href="https://github.com/datalad/datalad" target="_blank">GitHub</a> at any later point</li>
|
|
</ul>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>Live polling system</h2>
|
|
<iframe src="https://directpoll.com/r?XDbzPBd3ixYqg8i8jvqUUgxCLuaFlwU0nFt6VBVC",
|
|
style="border: 0", width="930", height="900"></iframe>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Live coding</h2>
|
|
<ul>
|
|
<li>Live-demonstration of DataLad examples and workflows throughout the talk</li>
|
|
<li>Code along with copy-paste code snippets: <a href="https://handbook.datalad.org/r.html?FZJmlcode" target="_blank">handbook.datalad.org/r.html?FZJmlcode</a> </li>
|
|
<li>Requirements:
|
|
<ul>
|
|
<li>DataLad version >= 0.12 (installation instructions at
|
|
<a href="https://handbook.datalad.org/en/latest/intro/installation.html" target="_blank">
|
|
handbook.datalad.org</a>) </li>
|
|
<li>For containerized analyses: DataLad extension <a href="http://handbook.datalad.org/en/latest/extension_pkgs.html#extensions-intro" target="_blank">
|
|
datalad-containers</a> (available via pip) + <a href="https://sylabs.io/guides/3.6/user-guide/" target="_blank">
|
|
Singularity
|
|
</a> </li>
|
|
</ul></li>
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
|
|
<!--...Datalad tech facts...-->
|
|
|
|
|
|
<section>
|
|
<section>
|
|
<h2> <img src="../pics/datalad_logo_wide.svg"></h2>
|
|
<ul>
|
|
<li>A command-line tool, available for all major operating systems
|
|
(Linux, macOS/OSX, Windows), MIT-licensed</li>
|
|
<li>Build on top of <a href="https://git-scm.com/" target="_blank">Git</a>
|
|
and <a href="https://git-annex.branchable.com/" target="_blank">Git-annex</a></li>
|
|
<dt><li>Allows...</li></dt>
|
|
<dt>... version-controlling arbitrarily large content </dt>
|
|
<dd>version control data and software alongside to code!</dd>
|
|
<dt>... transport mechanisms for sharing and obtaining data </dt>
|
|
<dd>consume and collaborate on data (analyses) like software</dd>
|
|
<dt>... (computationally) reproducible data analysis</dt>
|
|
<dd>Track and share provenance of all digital objects</dd>
|
|
<dt>... and <i>much</i> more </dt>
|
|
<li>Completely domain-agnostic</li>
|
|
<br>
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
|
|
|
|
<!--...Datalad core features...-->
|
|
|
|
|
|
<section>
|
|
<section>
|
|
<h2>Core concepts & features</h2>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Everything happens in DataLad datasets</h2>
|
|
<img src="../pics/artwork/src/dataset.svg" width="600"> <br>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Dataset = Git/git-annex repository</h2>
|
|
<ul>
|
|
<li>content agnostic</li>
|
|
<li>no custom data structures</li>
|
|
<li>complete decentralization</li>
|
|
<li>Looks and feels like a directory on your computer:</li>
|
|
</ul>
|
|
<br>
|
|
<br>
|
|
<img src="../pics/remodnav-ds-nautilus.png" width="500"> <img src="../pics/remodnav-ds-terminal.png" width="500">
|
|
<small>File viewer and terminal view of a DataLad dataset</small>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>version control arbitrarily large files</h2>
|
|
<img src="../pics/artwork/src/local_wf.svg" width="600"> <br>
|
|
|
|
<ul><p class="fragment fade-in">
|
|
Stay flexible:
|
|
<li class="fragment fade-in">Non-complex DataLad core API (easy for data management novices)</li>
|
|
<li class="fragment fade-in">Pure Git or git-annex commands (for regular Git or git-annex users, or to use specific functionality)</li>
|
|
</ul></p>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Use a datasets' history</h2>
|
|
<img src="../pics/researchlog.png">
|
|
<ul>
|
|
<li class="fragment fade-in"> reset your dataset (or subset of it) to a previous state, </li>
|
|
<li class="fragment fade-in"> revert changes or bring them back, </li>
|
|
<li class="fragment fade-in"> find out what was done when, how, why, and by whom </li>
|
|
<li class="fragment fade-in"> Identify precise versions: Use data in the most recent version, or the one from 2018, or... </li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Consume and collaborate</h2>
|
|
<img src="../pics/artwork/src/collaboration.svg" width="900"> <br>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>machine-readable, re-executable provenance</h2>
|
|
<img src="../pics/artwork/src/reproducible_execution.svg" width="900"> <br>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Seamless nesting and dataset linkage</h2>
|
|
|
|
<img src="../pics/artwork/src/linkage_subds.svg" width="900"> <br>
|
|
<!-- <ul>
|
|
<li class="fragment fade-in" data-fragment-index="2">Overcomes scaling issues with large amounts of files</li>
|
|
<pre class="fragment fade-in" data-fragment-index="2"><code>adina@bulk1 in /ds/hcp/super on git:master❱ datalad status --annex -r
|
|
15530572 annex'd files (77.9 TB recorded total size)
|
|
nothing to save, working tree clean</code></pre>
|
|
<small><a class="fragment fade-in" data-fragment-index="2" href="https://github.com/datalad-datasets/human-connectome-project-openaccess" target="_blank">(github.com/datalad-datasets/human-connectome-project-openaccess)</a></small>
|
|
<li class="fragment fade-in">Modularizes research components for transparency, reuse, and access management</li>
|
|
</ul>
|
|
-->
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Third party integrations</h2>
|
|
<img src="../pics/artwork/src/thirdparty.svg" width="900"> <br>
|
|
<small>Apart from <b>local computing infrastructure</b> (from private laptops to computational clusters),
|
|
datasets can be hosted in major <b>third party repository hosting and cloud storage</b> services.
|
|
More info: Chapter on <a href="http://handbook.datalad.org/en/latest/basics/basics-thirdparty.html" target="_blank">
|
|
Third party infrastructure</a>.</small>
|
|
</section>
|
|
|
|
<section data-transition="None">
|
|
<h3>
|
|
Examples of what DataLad can be used for:
|
|
</h3>
|
|
<ul>
|
|
<li class="fragment fade-in-then-semi-out"> <b>Publish or consume datasets</b> via GitHub, GitLab, OSF, or similar services</li>
|
|
<img height="850" class="fragment fade-in" src="../pics/clonedata.gif" alt="a screenrecording of cloning studyforrest data from github">
|
|
</ul>
|
|
</section>
|
|
|
|
<section data-transition="None">
|
|
<h3>
|
|
Examples of what DataLad can be used for:
|
|
</h3>
|
|
<ul>
|
|
<li class="fragment fade-in-then-semi-out"> <b>Creating and sharing reproducible, open science</b>: Sharing data, software, code, and provenance </li>
|
|
<img height="850" class="fragment fade-in" src="../pics/shareresearch2.gif" alt="a screenrecording of cloning REMODNAV paper dataset from github">
|
|
</ul>
|
|
</section>
|
|
|
|
<section data-transition="None">
|
|
<h3>
|
|
Examples of what DataLad can be used for:
|
|
</h3>
|
|
<ul>
|
|
<li class="fragment fade-in-then-semi-out"><b>Central data management</b> and archival system</li>
|
|
<img height="850" class="fragment fade-in" src="../pics/centralmanagement.gif">
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
|
|
|
|
|
|
<!--...Datalad Basics...-->
|
|
|
|
<section>
|
|
<section>
|
|
<h2>Live demo Basics</h2>
|
|
|
|
Code to follow along:
|
|
<a href="http://handbook.datalad.org/r.html?FZJmlcode" target="_blank">
|
|
handbook.datalad.org/r.html?FZJmlcode
|
|
</a>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>DataLad Datasets</h2>
|
|
|
|
<ul>
|
|
<li>DataLad's core data structure</li>
|
|
<ul>
|
|
<li class="fragment fade-in">Dataset = A directory managed by DataLad</li>
|
|
<li class="fragment fade-in">Any directory of your computer can be managed by DataLad.</li>
|
|
<li class="fragment fade-in">Datasets can be <i>created</i> (from scratch) or <i>installed</i></li>
|
|
<li class="fragment fade-in">Datasets can be nested: <i>linked subdirectories</i></li>
|
|
</ul>
|
|
</ul>
|
|
|
|
<aside class="notes">
|
|
<li>anything can be managed: CV, website, music library, phd</li>
|
|
<li>show this on the manuscript repo: history, looks/feels</li>
|
|
</aside>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Questions!</h2>
|
|
<iframe src="https://directpoll.com/r?XDbzPBd3ixYqg8i8jvqUUgxCLuaFlwU0nFt6VBVC",
|
|
style="border: 0", width="930", height="900"></iframe>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Why version control?</h2>
|
|
<img src="../pics/final.png" style="box-shadow: 10px 10px 8px #888888;height=600px" height="600"><br>
|
|
<ul>
|
|
<li class="fragment fade-in">keep things organized</li>
|
|
<li class="fragment fade-in">keep track of changes</li>
|
|
<li class="fragment fade-in">revert changes or go back to previous states</li>
|
|
</ul>
|
|
<aside class="notes">
|
|
<li>Not only manuscripts, but also data!</li>
|
|
</aside>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Version Control</h2>
|
|
|
|
<ul>
|
|
<li>DataLad knows two things: Datasets and files</li>
|
|
<img class="fragment fade-in" data-fragment-index="1" style="box-shadow: 5px 5px 3px #888888" src="../pics/artwork/src/dataset.svg" height="330"> <img style="box-shadow: 5px 5px 3px #888888" height="330" class="fragment fade-in" data-fragment-index="2" src="../pics/artwork/src/local_wf.svg">
|
|
</ul><br>
|
|
<li class="fragment fade-in">
|
|
Every file you put into a in a dataset can be easily version-controlled,
|
|
regardless of size, with the same command. </li>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>Local version control</h2>
|
|
|
|
<p>Procedurally, version control is easy with DataLad!</p>
|
|
<img class="fragment fade-in" src="../pics/local_wf.svg" height="500"> <!-- .element: class="fragment" -->
|
|
<br>
|
|
|
|
<b class="fragment fade-in">Advice:</b>
|
|
<ul>
|
|
<li class="fragment fade-in">Save <i>meaningful</i> units of change</li>
|
|
<li class="fragment fade-in">Attach helpful commit messages</li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section data-markdown><script type="text/template" >
|
|
|
|
### This means: You can also version control data! <!-- .element: class="fragment" -->
|
|
|
|
<pre><code class="bash" style="max-height:none">$ datalad save \
|
|
-m "Adding raw data from neuroimaging study 1" \
|
|
sub-*
|
|
add(ok): sub-1/anat/T1w.json (file)
|
|
add(ok): sub-1/anat/T1w.nii.gz (file)
|
|
add(ok): sub-1/anat/T2w.json (file)
|
|
add(ok): sub-1/anat/T2w.nii.gz (file)
|
|
add(ok): sub-1/func/sub-1-run-1_bold.json (file)
|
|
add(ok): sub-1/func/sub-1-run-1_bold.nii.gz (file)
|
|
add(ok): sub-10/anat/T1w.json (file)
|
|
add(ok): sub-10/anat/T1w.nii.gz (file)
|
|
add(ok): sub-10/anat/T2w.json (file)
|
|
add(ok): sub-10/anat/T2w.nii.gz (file)
|
|
[110 similar messages have been suppressed]
|
|
save(ok): . (dataset)
|
|
action summary:
|
|
add (ok: 120)
|
|
save (ok: 1)
|
|
</code></pre> <!-- .element: class="fragment" -->
|
|
|
|
</script>
|
|
</section>
|
|
|
|
<section data-markdown><script type="text/template" >
|
|
## Version Control
|
|
* Your dataset can be a complete research log, capturing everything that was done, when, by whom, and how
|
|
|
|
* Interact with the history:
|
|
* reset your dataset (or subset of it) to a previous state,
|
|
* throw out changes or bring them back,
|
|
* find out what was done when, how, why, and by whom
|
|
* Identify precise versions: Use data in the most recent version, or the one from 2018, or...
|
|
* ...
|
|
</script>
|
|
</section>
|
|
|
|
<section>
|
|
<h3>Summary - Local version control</h3>
|
|
|
|
<dl>
|
|
<dt class="fragment fade-in"><code>datalad create</code> creates an empty dataset.</dt> <dd class="fragment fade-in">Configurations (<b>-c yoda</b>, <b>-c text2git</b>) are useful (details soon).</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">A dataset has a <i>history</i> to track files and their modifications. </dt><dd class="fragment fade-in">Explore it with Git (<b>git log</b>) or external tools (e.g., <b>tig</b>).</dd>
|
|
<br>
|
|
<dt class="fragment fade-in"><code>datalad save</code> records the dataset or file state to the history. </dt><dd class="fragment fade-in">Concise <b>commit messages</b> should summarize the change for future you and others.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in"><code>datalad download-url</code> obtains web content and records its origin. </dt><dd class="fragment fade-in">It even takes care of saving the change.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in"><code>datalad status</code> reports the current state of the dataset.</dt>
|
|
<dd class="fragment fade-in">A clean dataset status (no modifications, not untracked files) is good practice.</dd>
|
|
</dl>
|
|
</section>
|
|
|
|
|
|
<section data-markdown><script type="text/template">
|
|
## From here <span class="fragment" data-fragment-index="1" style="margin-left:350px">to this:</span>
|
|
<!-- .element: height="780" style="box-shadow: 10px 10px 8px #888888" -->
|
|
<!-- .element: class="fragment" data-fragment-index="1" height="780" style="box-shadow: 10px 10px 8px #888888" -->
|
|
|
|
<p class="fragment" data-fragment-index="2">BUT: Version control is only one aspect of data management</p>
|
|
|
|
</script>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>Questions!</h2>
|
|
<iframe src="https://directpoll.com/r?XDbzPBd3ixYqg8i8jvqUUgxCLuaFlwU0nFt6VBVC",
|
|
style="border: 0", width="930", height="900"></iframe>
|
|
</section>
|
|
</section>
|
|
|
|
<section>
|
|
|
|
<section data-markdown><script type="text/template" >
|
|
## Consuming datasets
|
|
* A dataset can be created from scratch/existing directories:
|
|
<pre><code class="bash" style="max-height:none">$ datalad create mydataset
|
|
[INFO ] Creating a new annex repo at /home/adina/mydataset
|
|
create(ok): /home/adina/mydataset (dataset)
|
|
</code></pre>
|
|
* but datasets can also be installed from paths or from URLs:
|
|
<pre><code class="bash" style="max-height:none">$ datalad clone \
|
|
https://github.com/datalad-datasets/human-connectome-project-openaccess \
|
|
HCP
|
|
install(ok): /tmp/HCP (dataset)
|
|
</code></pre>
|
|
</script>
|
|
</section>
|
|
<section>
|
|
<h2>Consuming datasets</h2>
|
|
|
|
<ul>
|
|
<li class="fragment fade-in">Here's how a dataset looks after installation:</li>
|
|
<img class="fragment fade-in" src="../pics/getdata.gif" height="700">
|
|
<li class="fragment fade-in">Datasets are light-weight: Upon installation, only small
|
|
files and meta data about file availability are retrieved.</li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Plenty of data, but little disk-usage</h2>
|
|
<ul>
|
|
<li class="fragment fade-in-then-semi-out">Cloned datasets are lean.
|
|
"Meta data" (file names, availability) are present, but <b>no file content</b>:</li>
|
|
<pre class="fragment fade-in"><code>$ datalad clone git@github.com:psychoinformatics-de/studyforrest-data-phase2.git
|
|
install(ok): /tmp/studyforrest-data-phase2 (dataset)
|
|
$ cd studyforrest-data-phase2 && du -sh
|
|
18M .</code></pre>
|
|
|
|
<li class="fragment fade-in-then-semi-out"> file's contents can be retrieved on demand:</li>
|
|
</ul>
|
|
<pre class="fragment fade-in"><code>$ datalad get sub-01/ses-movie/func/sub-01_ses-movie_task-movie_run-1_bold.nii.gz
|
|
get(ok): /tmp/studyforrest-data-phase2/sub-01/ses-movie/func/sub-01_ses-movie_task-movie_run-1_bold.nii.gz (file) [from mddatasrc...]</code></pre>
|
|
|
|
<li class="fragment fade-in">Have more access to your computer than you have disk-space:</li>
|
|
<pre class="fragment fade-in"><code># eNKI dataset (1.5TB, 34k files):
|
|
$ du -sh
|
|
1.5G .
|
|
# HCP dataset (80TB, 15 million files)
|
|
$ du -sh
|
|
48G .
|
|
</code></pre>
|
|
</section>
|
|
|
|
<section data-markdown> <script type="text/template">
|
|
## Plenty of data, but little disk-usage
|
|
|
|
Drop file content that is not needed:
|
|
<pre class="fragment fade-in-then-semi-out"><code>$ datalad drop sub-01/ses-movie/func/sub-01_ses-movie_task-movie_run-1_bold.nii.gz
|
|
drop(ok): /tmp/studyforrest-data-phase2/sub-01/ses-movie/func/sub-01_ses-movie_task-movie_run-1_bold.nii.gz (file) [checking https://arxiv.org/pdf/0904.3664v1.pdf...]</code></pre>
|
|
When files are dropped, only "meta data" stays behind, and they can be re-obtained on demand.
|
|
This allows disk-space aware computations: <!-- .element: class="fragment fade-in" -->
|
|
|
|
|
|
Install your input data <!-- .element: class="fragment fade-in" -->
|
|
*➡ get the data you need* <!-- .element: class="fragment fade-in" -->
|
|
*➡ compute your results* <!-- .element: class="fragment fade-in" -->
|
|
*➡ drop input data (and potentially all automatically re-computable results)* <!-- .element: class="fragment fade-in" -->
|
|
|
|
</script></section>
|
|
|
|
<section>
|
|
<h2>Git versus Git-annex</h2>
|
|
<dl>
|
|
<dt>Data in datasets is either stored in Git or git-annex</dt>
|
|
<dd>By default, everything is <i>annexed</i>, i.e., stored in a dataset annex by git-annex</dd><br>
|
|
<li class="fragment fade-in-then-semi-out">With annexed data, only content identity (hash)
|
|
and location information is put into Git, rather than file content.
|
|
The annex, and transport to and from it is managed with <b>git-annex</b>
|
|
<br>
|
|
<br>
|
|
<small>
|
|
<table>
|
|
<tr>
|
|
<td><b>Git</b></td>
|
|
<td><b>git-annex</b></td>
|
|
</tr>
|
|
<tr>
|
|
<td>handles <b>small</b> files well (text, code)</td>
|
|
<td>handles <b>all</b> types and sizes of files well</td>
|
|
</tr>
|
|
<tr>
|
|
<td>file contents are in the Git history
|
|
and will be <b>shared</b> upon git/datalad push</td>
|
|
<td>file contents are in the annex. Not necessarily shared</td>
|
|
</tr>
|
|
<tr>
|
|
<td>Shared with every dataset clone</td>
|
|
<td><b>Can be kept private</b> on a per-file level when sharing the dataset</td>
|
|
</tr>
|
|
<tr>
|
|
<td>Useful: Small, non-binary, frequently modified, need-to-be-accessible (DUA, README) files </td>
|
|
<td>Useful: Large files, private files</td>
|
|
</tr>
|
|
</table>
|
|
</small>
|
|
</dl>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>Git versus Git-annex</h2>
|
|
<small>Useful background information for demo later. Read
|
|
<a href="http://handbook.datalad.org/en/latest/basics/101-115-symlinks.html" target="_blank">
|
|
this handbook chapter</a> for details
|
|
</a> </small><br>
|
|
Git and Git-annex handle files differently: annexed files are stored in an annex.
|
|
File content is hashed & only content-identity is committed to Git.
|
|
<ul>
|
|
<table>
|
|
<tr>
|
|
<td>
|
|
<li>Files stored in Git are modifiable, files stored in Git-annex are content-locked</li>
|
|
</td>
|
|
<td width="60%">
|
|
<img src="../pics/git_vs_gitannex.svg" height="500">
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
|
|
<li>Annexed contents are not available right after cloning,
|
|
only content- and availability information (as they are stored in Git)</li>
|
|
</ul>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>Git versus Git-annex</h2>
|
|
<ul>
|
|
When sharing datasets with someone without access to the same computational
|
|
infrastructure, annexed data is not necessarily stored together with the rest
|
|
of the dataset.
|
|
</ul>
|
|
<img src="../pics/services_connected.png" height="500">
|
|
<ul>
|
|
Transport logistics exist to interface with all major storage providers.
|
|
If the one you use isn't supported, let us know!
|
|
</ul>
|
|
</section>
|
|
|
|
|
|
<section>
|
|
<h2>Git versus Git-annex</h2>
|
|
<ul>
|
|
Users can decide which files are annexed:
|
|
<br><br>
|
|
<li><b>Pre-made run-procedures</b>, provided by DataLad (e.g., <code>text2git</code>, <code>yoda</code>)
|
|
or created and shared by users
|
|
(<a href="http://handbook.datalad.org/en/latest/basics/101-124-procedures.html" target="_blank">Tutorial</a>) </li>
|
|
<li>Self-made configurations in <code>.gitattributes</code> (e.g., based on file type,
|
|
file/path name, size, ...; <a href="http://handbook.datalad.org/en/latest/basics/101-123-config2.html#gitattributes" target="_blank">
|
|
rules and examples
|
|
</a> )</li>
|
|
<li>Per-command basis (e.g., via <code>datalad save --to-git</code>)</li>
|
|
</ul>
|
|
</section>
|
|
|
|
|
|
<section data-transition="None">
|
|
<h2>Dataset nesting</h2>
|
|
|
|
<ul>
|
|
<li>Seamless nesting mechanisms:
|
|
<img height="330" src="../pics/artwork/src/linkage_subds.svg">
|
|
<br>
|
|
<li class="fragment fade-in" data-fragment-index="2">Overcomes scaling issues with large amounts of files</li>
|
|
<pre class="fragment fade-in" data-fragment-index="2"><code>adina@bulk1 in /ds/hcp/super on git:master❱ datalad status --annex -r
|
|
15530572 annex'd files (77.9 TB recorded total size)
|
|
nothing to save, working tree clean</code></pre>
|
|
<small><a class="fragment fade-in" data-fragment-index="2" href="https://github.com/datalad-datasets/human-connectome-project-openaccess" target="_blank">(github.com/datalad-datasets/human-connectome-project-openaccess)</a></small>
|
|
<li class="fragment fade-in">Modularizes research components for transparency, reuse, and access management</li>
|
|
</ul>
|
|
|
|
|
|
|
|
<aside class="notes">
|
|
Two advantages:
|
|
<ul>
|
|
<li>Scalable, size-independent version control</li>
|
|
<li>Modularization of research components to increase transparency
|
|
and aid component reuse, as individual components can be flexibly
|
|
puzzled together into new research objects, while being uniquely identified and versioned</li>
|
|
</ul>
|
|
|
|
At this point: Fixed data management, layed a foundation for updating data
|
|
</aside>
|
|
</section>
|
|
|
|
|
|
|
|
<section>
|
|
<h2>Dataset nesting</h2>
|
|
<img src="../pics/linkage.svg" height="500">
|
|
</section>
|
|
|
|
<section>
|
|
<h3>Summary - Dataset consumption & nesting</h3>
|
|
|
|
<ul>
|
|
<dt class="fragment fade-in"><code>datalad clone</code> installs a dataset.</dt><dd class="fragment fade-in"> It can be installed “on its own”:
|
|
Specify the source (url, path, ...) of the dataset, and an optional <b>path</b> for it to be installed to.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Datasets can be installed as subdatasets within an existing dataset. </dt> <dd class="fragment fade-in"> The <b>--dataset/-d</b> option needs a path to the root of the superdataset.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Only small files and metadata about file availability are present locally after an install. </dt>
|
|
<dd class="fragment fade-in">To retrieve actual file content of annexed files,
|
|
<code>datalad get </code> downloads file content on demand.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Datasets preserve their history.</dt> <dd class="fragment fade-in">The superdataset records only the <i>version state</i> of the subdataset.</dd>
|
|
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Questions!</h2>
|
|
<iframe src="https://directpoll.com/r?XDbzPBd3ixYqg8i8jvqUUgxCLuaFlwU0nFt6VBVC",
|
|
style="border: 0", width="930", height="900"></iframe>
|
|
</section>
|
|
</section>
|
|
|
|
<section>
|
|
<section data-transition="fade">
|
|
<h2>reproducible data analysis</h2>
|
|
Your past self is the worst collaborator:
|
|
<img src="../pics/ownlegacycode_phd.png" height="500">
|
|
<imgcredit>Full comic at <a href="http://phdcomics.com/comics.php?f=1689">http://phdcomics.com/comics.php?f=1979</a></imgcredit>
|
|
</p>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Basic organizational principles for datasets</h2>
|
|
<dl>
|
|
<dt>Keep everything clean and modular</dt>
|
|
<li>An analysis is a superdataset, its components are subdatasets, and its structure modular</li>
|
|
<table>
|
|
<tr>
|
|
<td><img src="../pics/dataset_modules.png" height="400"></td>
|
|
<td><pre><code class="bash" style="max-height:none">├── code/
|
|
│ ├── tests/
|
|
│ └── myscript.py
|
|
├── docs
|
|
│ ├── build/
|
|
│ └── source/
|
|
├── envs
|
|
│ └── Singularity
|
|
├── inputs/
|
|
│ └─── data/
|
|
│ ├── dataset1/
|
|
│ │ └── datafile_a
|
|
│ └── dataset2/
|
|
│ └── datafile_a
|
|
├── outputs/
|
|
│ └── important_results/
|
|
│ └── figures/
|
|
└── README.md</code></pre></td>
|
|
</tr>
|
|
</table>
|
|
|
|
</dl>
|
|
<ul>
|
|
<li>do not touch/modify raw data: save any results/computations <i>outside</i> of input datasets</li>
|
|
<li>Keep a superdataset self-contained: Scripts reference subdatasets or files with <i>relative paths</i></li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Basic organizational principles for datasets</h2>
|
|
<dl>
|
|
<dt>Record where you got it from, where it is now, and what you do to it</dt>
|
|
<li>Link datasets (as subdatasets), record data origin</li>
|
|
<li>Collect and store provenance of all contents of a dataset that you create</li>
|
|
<table style="verticala-lign:middle">
|
|
<tr><img src="../pics/dataset_linkage_provenance.png"></tr>
|
|
</table>
|
|
<dl>
|
|
<dt>Document everything:</dt>
|
|
<li>Which script produced which output? From which data? In which software environment? ... </li>
|
|
</dl>
|
|
</dl>
|
|
<note>Find out more about organizational principles in
|
|
<a href="" target="_blank">the YODA principles</a>!</note>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>A classification analysis on the iris flower dataset</h2>
|
|
<img src="../pics/iris-machinelearning.png" height="300">
|
|
<img src="../pics/iris_cluster.png" height="450">
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Reproducible execution & provenance capture</h2>
|
|
|
|
<p>datalad run</p>
|
|
<img class="fragment fade-in" src="../pics/run_prov.svg" height="600"> <!-- .element: class="fragment" -->
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Computational reproducibility</h2>
|
|
<ul>
|
|
<li>Code may fail (to reproduce) if run with different software</li>
|
|
<li>Datasets can store (and share) software environments (Docker or Singularity containers)
|
|
and reproducibly execute code inside of the software container, capturing software as additional
|
|
provenance</li>
|
|
<li>DataLad extension: <code>datalad-container</code></li>
|
|
</ul>
|
|
|
|
<p>datalad-containers run</p>
|
|
<img class="fragment fade-in" src="../pics/containers-run.svg" height="600"> <!-- .element: class="fragment" -->
|
|
</section>
|
|
|
|
<section>
|
|
<h3>Summary - Reproducible execution</h3>
|
|
|
|
<ul>
|
|
<dt class="fragment fade-in"><code>datalad run</code> records a command and
|
|
its impact on the dataset.</dt>
|
|
<dd class="fragment fade-in">All dataset modifications are saved - use it
|
|
in a clean dataset.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Data/directories specified as <code>--input</code>
|
|
are retrieved prior to command execution.</dt>
|
|
<dd class="fragment fade-in"> Use one flag per input.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Data/directories specified as <code>--output</code>
|
|
will be unlocked for modifications prior to a rerun of the command. </dt>
|
|
<dd class="fragment fade-in">Its optional to specify, but helpful for recomputations.</dd>
|
|
<br>
|
|
<dt class="fragment fade-in"><code>datalad containers-run</code> can be used
|
|
to capture the software environment as provenance.</dt>
|
|
<dd class="fragment fade-in">Its ensures computations are ran in the desired software set up.
|
|
Supports Docker and Singularity containers</dd>
|
|
<br>
|
|
<dt class="fragment fade-in"><code>datalad rerun</code> can automatically re-execute run-records later.</dt>
|
|
<dd class="fragment fade-in">They can be identified with any commit-ish (hash, tag, range, ...)</dd>
|
|
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Questions!</h2>
|
|
<iframe src="https://directpoll.com/r?XDbzPBd3ixYqg8i8jvqUUgxCLuaFlwU0nFt6VBVC",
|
|
style="border: 0", width="930", height="900"></iframe>
|
|
</section>
|
|
</section>
|
|
|
|
<!--...Datalad ML Tutorial...-->
|
|
|
|
<section>
|
|
<section>
|
|
<h2>A machine-learning example</h2>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Analysis layout</h2>
|
|
<table>
|
|
<tr>
|
|
<td>
|
|
<ul>
|
|
<li>Prepare an input data set</li>
|
|
<li class="fragment fade-in">Configure and setup an analysis dataset</li>
|
|
<li class="fragment fade-in">Prepare data</li>
|
|
<li class="fragment fade-in">Train models and evaluate them</li>
|
|
<li class="fragment fade-in">Compare different models, repeat with updated data</li>
|
|
</ul>
|
|
</td>
|
|
<td>
|
|
<img src="../pics/imagenette.png" width="800">
|
|
<small>Imagenette dataset</small>
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Prepare an input dataset</h2>
|
|
<ul>
|
|
<li>Create a stand-alone input dataset</li>
|
|
<li>Either add data and <code>datalad save</code> it, or use commands such as <code>datalad download-url</code>
|
|
or <code>datalad add-urls</code> to retrieve it from web-sources</li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Configure and setup an analysis dataset</h2>
|
|
<ul>
|
|
<li>Given the purpose of an analysis dataset, configurations can make it easier to use:</li>
|
|
<ul>
|
|
<li><code>-c yoda</code> prepares a useful structure</li>
|
|
<li><code>-c text2git</code> keeps text files such as scripts in Git</li>
|
|
</ul>
|
|
<li>The input dataset is installed as a subdataset</li>
|
|
<li>Required software is containerized and added to the dataset</li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Prepare data</h2>
|
|
<ul>
|
|
<li>Add a script for data preparation (labels train and validation images)</li>
|
|
<li>Execute it using <code>datalad containers-run</code></li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Train models and evaluate them</h2>
|
|
<ul>
|
|
<li>Add scripts for training and evaluation.
|
|
This dataset state can be tagged to identify it easily at a later point</li>
|
|
<li>Execute the scripts using <code>datalad containers-run</code></li>
|
|
<li>By dumping a trained model as a joblib object the trained classifier stays reusable</li>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Tips and tricks for ML applications</h2>
|
|
<ul>
|
|
<dt class="fragment fade-in">Standalone input datasets keep input data extendable and reusable</dt>
|
|
<dd class="fragment fade-in">Subdatasets can be registered in precise versions, and updated to the newest state</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Software containers aid greatly with reproducibility</dt>
|
|
<dd class="fragment fade-in">The correct software environment is preserved and can be shared</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Re-executable run-records can capture all provenance</dt>
|
|
<dd class="fragment fade-in">This can also capture command-line parametrization</dd>
|
|
<br>
|
|
<dt class="fragment fade-in">Git workflows can be helpful elements in ML workflows</dt>
|
|
<dd class="fragment fade-in">DataLad is no workflow manager, but by checking out out tags
|
|
or branches one can switch easy and fast between results of different models</dd>
|
|
|
|
</li>
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
|
|
<section>
|
|
<section data-transition="None">
|
|
<h2>Why use DataLad?</h2>
|
|
<ul>
|
|
<li class="fragment fade-in">Mistakes are not forever anymore: Easy version control, regardless of file size</li>
|
|
<li class="fragment fade-in">Who needs short-term memory when you can have run-records?</li>
|
|
<li class="fragment fade-in">Disk-usage magic: Have access to more data than your hard drive has space</li>
|
|
<li class="fragment fade-in">Collaboration and updating mechanisms: Alice shares her data with Bob. Alice fixes a mistake and pushes the fix.
|
|
Bob says "datalad update" and gets her changes. And vice-versa.</li>
|
|
<li class="fragment fade-in">Transparency: Shared datasets keep their history. No need to track down a former student,
|
|
ask their project what was done.</li>
|
|
</ul>
|
|
</section>
|
|
<section>
|
|
<h2>Thank you for your attention!</h2>
|
|
<h3>Questions!</h3>
|
|
<iframe src="https://directpoll.com/r?XDbzPBd3ixYqg8i8jvqUUgxCLuaFlwU0nFt6VBVC",
|
|
style="border: 0", width="930", height="900"></iframe>
|
|
</section>
|
|
</section>
|
|
|
|
|
|
|
|
<!--...Other things that can be helpful...-->
|
|
|
|
<section>
|
|
<section>
|
|
<h2>More useful information</h2>
|
|
<h4>(But please ask if there's anything else you want to know)</h4>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Scalability</h2>
|
|
<ul>
|
|
<b>How large can datasets get?</b>
|
|
<br>
|
|
<br>
|
|
<li>In general: <b>Size is not a problem</b>, as long as large files are handled with git-annex</li>
|
|
<li>Bottle-neck: <b>Number of files</b>. 100-200k per dataset!</li>
|
|
<li>How to scale up? Nest datasets as subdatasets</li>
|
|
<ul>
|
|
<li>Currently largest dataset:
|
|
<a href="https://github.com/datalad-datasets/human-connectome-project-openaccess" target="_blank">
|
|
human connectome project data</a>, 80TB, 15 million files, ~4500 subdataset</li>
|
|
<li>Currently in the making: institute archival system, 125TB </li>
|
|
<li>Currently worked towards: Processing UKBiobank data, 0.5PB</li>
|
|
</ul>
|
|
|
|
<br>
|
|
<small>Need more information? Read the <a href="http://handbook.datalad.org/en/latest/beyond_basics/basics-scaling.html" target="_blank">
|
|
chapter on scaling up</a> at handbook.datalad.org </small>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Transfer existing projects</h2>
|
|
|
|
<ul>
|
|
<b>Can existing projects become dataset?</b>
|
|
<br>
|
|
<br>
|
|
<li>In general: <b>Yes</b> (but make a backup, just in case)</li>
|
|
<li><code>datalad create -f</code> can transform any directory or Git repository into a dataset</li>
|
|
<li>Afterwards, untracked contents need to be saved</li>
|
|
|
|
|
|
<br>
|
|
<small>Need more information? Read the <a href="http://handbook.datalad.org/en/latest/beyond_basics/101-164-dataladdening.html" target="_blank">
|
|
section on transitioning existing projects to DataLad</a> at handbook.datalad.org </small>
|
|
</ul>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Easy storage for annex</h2>
|
|
|
|
<ul>
|
|
<b>How can I share annexed data fast and easy?</b>
|
|
<br>
|
|
<br>
|
|
<li>In general: <b>Dozens of services are supported</b> via git-annex "special remote" concept, (Amazon S3, Dropbox, GDrive, private webserver...)</li>
|
|
<li>Some repository hosting services also host annexed data: GIN (free, supports anonymous read access), GitHub & GitLab if used with GitLFS (non-free)</li>
|
|
<li><b>datalad-osf</b> extension for hosting datasets on the open science frameworf (OSF)</li>
|
|
|
|
|
|
<br>
|
|
<small>Need more information? Read the <a href="http://handbook.datalad.org/en/latest/basics/basics-thirdparty.html" target="_blank">
|
|
chapter on third party infrastructure</a> at handbook.datalad.org </small>
|
|
</ul>
|
|
</section>
|
|
</section>
|
|
|
|
<!--...Over and out...-->
|
|
|
|
<section>
|
|
<section>
|
|
<h2>Thanks for your attention!</h2>
|
|
<ul>Speak up now or reach out to us later with any questions</ul>
|
|
<img src="../pics/logo.svg" height="600">
|
|
</section>
|
|
</section>
|
|
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<script src="../reveal.js/dist/reveal.js"></script>
|
|
<script src="../reveal.js/plugin/notes/notes.js"></script>
|
|
<script src="../reveal.js/plugin/markdown/markdown.js"></script>
|
|
<script src="../reveal.js/plugin/highlight/highlight.js"></script>
|
|
<script>
|
|
// More info about initialization & config:
|
|
// - https://revealjs.com/initialization/
|
|
// - https://revealjs.com/config/
|
|
Reveal.initialize({
|
|
hash: true,
|
|
// The "normal" size of the presentation, aspect ratio will be preserved
|
|
// when the presentation is scaled to fit different resolutions. Can be
|
|
// specified using percentage units.
|
|
width: 1280,
|
|
height: 960,
|
|
// Factor of the display size that should remain empty around the content
|
|
margin: 0.3,
|
|
// Bounds for smallest/largest possible scale to apply to content
|
|
minScale: 0.2,
|
|
maxScale: 1.0,
|
|
|
|
controls: true,
|
|
progress: true,
|
|
history: true,
|
|
center: true,
|
|
slideNumber: 'c',
|
|
pdfSeparateFragments: false,
|
|
pdfMaxPagesPerSlide: 1,
|
|
pdfPageHeightOffset: -1,
|
|
transition: 'slide', // none/fade/slide/convex/concave/zoom
|
|
// Learn about plugins: https://revealjs.com/plugins/
|
|
plugins: [ RevealMarkdown, RevealHighlight, RevealNotes ]
|
|
});
|
|
</script>
|
|
</body>
|
|
</html>
|