hub/main/en/datasets-dask.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Dask&quot;,&quot;local&quot;:&quot;dask&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/hub/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/entry/start.d0cd5065.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/scheduler.d6170356.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/singletons.d032f1eb.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/paths.752f1c6b.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/entry/app.b6abe3c1.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/index.fcd4cc08.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/nodes/0.f045427f.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/nodes/16.9b0381a3.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/CodeBlock.7b16bdef.js">
		<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/EditOnGithub.da2b595c.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Dask&quot;,&quot;local&quot;:&quot;dask&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="dask" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#dask"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Dask</span></h1> <p data-svelte-h="svelte-1i0h8ri"><a href="https://github.com/dask/dask" rel="nofollow">Dask</a> is a parallel and distributed computing library that scales the existing Python and PyData ecosystem.
Since it uses <a href="https://filesystem-spec.readthedocs.io" rel="nofollow">fsspec</a> to read and write remote data, you can use the Hugging Face paths (<a href="/docs/huggingface_hub/guides/hf_file_system#integrations"><code>hf://</code></a>) to read and write data on the Hub:</p> <p data-svelte-h="svelte-1jdzygp">First you need to <a href="/docs/huggingface_hub/quick-start#login">Login with your Hugging Face account</a>, for example using:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->huggingface-<span class="hljs-keyword">cli</span> login<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-wfb25d">Then you can <a href="/docs/huggingface_hub/quick-start#create-a-repository">Create a dataset repository</a>, for example using:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> HfApi

HfApi().create_repo(repo_id=<span class="hljs-string">&quot;username/my_dataset&quot;</span>, repo_type=<span class="hljs-string">&quot;dataset&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1vftqwj">Finally, you can use <a href="/docs/huggingface_hub/guides/hf_file_system#integrations">Hugging Face paths</a> in Dask:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> dask.dataframe <span class="hljs-keyword">as</span> dd

df.to_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset&quot;</span>)

<span class="hljs-comment"># or write in separate directories if the dataset has train/validation/test splits</span>
df_train.to_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset/train&quot;</span>)
df_valid.to_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset/validation&quot;</span>)
df_test .to_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset/test&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-14rczfs">This creates a dataset repository <code>username/my_dataset</code> containing your Dask dataset in Parquet format.
You can reload it later:</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> dask.dataframe <span class="hljs-keyword">as</span> dd

df = dd.read_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset&quot;</span>)

<span class="hljs-comment"># or read from separate directories if the dataset has train/validation/test splits</span>
df_train = dd.read_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset/train&quot;</span>)
df_valid = dd.read_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset/validation&quot;</span>)
df_test  = dd.read_parquet(<span class="hljs-string">&quot;hf://datasets/username/my_dataset/test&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-smuvdf">For more information on the Hugging Face paths and how they are implemented, please refer to the <a href="/docs/huggingface_hub/guides/hf_file_system">the client library’s documentation on the HfFileSystem</a>.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/hub/datasets-dask.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1vatp3t = {
						assets: "/docs/hub/main/en",
						base: "/docs/hub/main/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/hub/main/en/_app/immutable/entry/start.d0cd5065.js"),
						import("/docs/hub/main/en/_app/immutable/entry/app.b6abe3c1.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 16],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>