Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / datasets /pr_8113 /en /filesystems.html

HuggingFaceDocBuilder

22 days ago

download

raw

31.5 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Cloud storage","local":"cloud-storage","sections":[{"title":"Hugging Face Datasets","local":"hugging-face-datasets","sections":[],"depth":2},{"title":"Hugging Face Storage Buckets","local":"hugging-face-storage-buckets","sections":[],"depth":2},{"title":"Import data from a cloud storage","local":"import-data-from-a-cloud-storage","sections":[{"title":"Publish a Dataset","local":"publish-a-dataset","sections":[],"depth":3},{"title":"Import raw data to Storage Buckets","local":"import-raw-data-to-storage-buckets","sections":[],"depth":3}],"depth":2}],"depth":1}">
	<link href="/docs/datasets/pr_8113/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/entry/start.969da75e.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/scheduler.d75c11ed.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/singletons.61bfd4fd.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/index.d12496d4.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/paths.4c60f2bc.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/entry/app.687c6ad1.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/preload-helper.a19054d5.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/index.4ec9dfe9.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/nodes/0.4378a702.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/nodes/20.1a8b374d.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.903f9bf7.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8113/en/_app/immutable/chunks/CodeBlock.77fa95e2.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Cloud storage","local":"cloud-storage","sections":[{"title":"Hugging Face Datasets","local":"hugging-face-datasets","sections":[],"depth":2},{"title":"Hugging Face Storage Buckets","local":"hugging-face-storage-buckets","sections":[],"depth":2},{"title":"Import data from a cloud storage","local":"import-data-from-a-cloud-storage","sections":[{"title":"Publish a Dataset","local":"publish-a-dataset","sections":[],"depth":3},{"title":"Import raw data to Storage Buckets","local":"import-raw-data-to-storage-buckets","sections":[],"depth":3}],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="cloud-storage" 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="#cloud-storage"><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>Cloud storage</span></h1> <h2 class="relative group"><a id="hugging-face-datasets" 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="#hugging-face-datasets"><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>Hugging Face Datasets</span></h2> <p data-svelte-h="svelte-pwg4if">The Hugging Face Dataset Hub is home to a growing collection of datasets that span a variety of domains and tasks.</p> <p data-svelte-h="svelte-le6063">It’s more than a cloud storage: the Dataset Hub is a platform that provides data versioning thanks to git, as well as a Dataset Viewer to explore the data, making it a great place to store AI-ready datasets.</p> <p data-svelte-h="svelte-ei4lhv">This guide shows how to import data from other cloud storage using the filesystems implementations from <code>fsspec</code>.</p> <h2 class="relative group"><a id="hugging-face-storage-buckets" 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="#hugging-face-storage-buckets"><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>Hugging Face Storage Buckets</span></h2> <p data-svelte-h="svelte-1f2me8o">Storage Buckets are a repo type on the Hugging Face Hub providing S3-like object storage, powered by the Xet storage backend. Unlike Git-based dataset repositories, buckets are non-versioned and mutable, designed for use cases where you need simple, fast storage such as logs, intermediate artifacts, or any large collection of files that doesn’t need version control.</p> <h2 class="relative group"><a id="import-data-from-a-cloud-storage" 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="#import-data-from-a-cloud-storage"><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>Import data from a cloud storage</span></h2> <p data-svelte-h="svelte-1uadmic">Most cloud storage providers have a <code>fsspec</code> FileSystem implementation, which is useful to import data from any cloud provider with the same code.
	This is especially useful to publish datasets on Hugging Face.</p> <p data-svelte-h="svelte-1enr8yq">Take a look at the following table for some example of supported cloud storage providers:</p> <table data-svelte-h="svelte-40f5jy"><thead><tr><th>Storage provider</th> <th>Filesystem implementation</th></tr></thead> <tbody><tr><td>Amazon S3</td> <td><a href="https://s3fs.readthedocs.io/en/latest/" rel="nofollow">s3fs</a></td></tr> <tr><td>Google Cloud Storage</td> <td><a href="https://gcsfs.readthedocs.io/en/latest/" rel="nofollow">gcsfs</a></td></tr> <tr><td>Azure Blob/DataLake</td> <td><a href="https://github.com/fsspec/adlfs" rel="nofollow">adlfs</a></td></tr> <tr><td>Oracle Cloud Storage</td> <td><a href="https://ocifs.readthedocs.io/en/latest/" rel="nofollow">ocifs</a></td></tr></tbody></table> <p data-svelte-h="svelte-tdsgr3">This guide will show you how to import data files from any cloud storage and save a dataset on Hugging Face.</p> <p data-svelte-h="svelte-19vswnu">Let’s say we want to publish a dataset on Hugging Face from Parquet files from a cloud storage.</p> <p data-svelte-h="svelte-1fbzvas">First, instantiate your cloud storage filesystem and list the files you’d like to import:</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-meta">>>> </span><span class="hljs-keyword">import</span> fsspec
	<span class="hljs-meta">>>> </span>fs = fsspec.filesystem(<span class="hljs-string">"..."</span>) <span class="hljs-comment"># s3 / gcs / abfs / adl / oci / ...</span>
	<span class="hljs-meta">>>> </span>data_dir = <span class="hljs-string">"path/to/my/data/"</span>
	<span class="hljs-meta">>>> </span>pattern = <span class="hljs-string">"*.parquet"</span>
	<span class="hljs-meta">>>> </span>data_files = fs.glob(data_dir + pattern)
	[<span class="hljs-string">"path/to/my/data/0001.parquet"</span>, <span class="hljs-string">"path/to/my/data/0001.parquet"</span>, ...]<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="publish-a-dataset" 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="#publish-a-dataset"><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>Publish a Dataset</span></h3> <p data-svelte-h="svelte-br8k8v">Then you can create a dataset on Hugging Face and import the data files, using for example:</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-meta">>>> </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> create_repo, upload_folder
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tqdm.auto <span class="hljs-keyword">import</span> tqdm
	<span class="hljs-meta">>>> </span>destination_dataset = <span class="hljs-string">"username/my-dataset"</span>
	<span class="hljs-meta">>>> </span>create_repo(destination_dataset, repo_type=<span class="hljs-string">"dataset"</span>)
	<span class="hljs-meta">>>> </span>batch_size = <span class="hljs-number">100</span>
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> data_files <span class="hljs-keyword">in</span> batched(tqdm(fs.glob(data_dir + pattern)), batch_size):
	<span class="hljs-meta">... </span> <span class="hljs-keyword">with</span> TemporaryDirectory() <span class="hljs-keyword">as</span> tmp_dir:
	<span class="hljs-meta">... </span> tmp_files = [os.path.join(tmp_dir, x[<span class="hljs-built_in">len</span>(data_dir):]) <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> data_files]
	<span class="hljs-meta">... </span> fs.download(data_files, tmp_files)
	<span class="hljs-meta">... </span> upload_folder(
	<span class="hljs-meta">... </span> repo_id=destination_dataset,
	<span class="hljs-meta">... </span> folder_path=tmp_dir,
	<span class="hljs-meta">... </span> repo_type=<span class="hljs-string">"dataset"</span>,
	<span class="hljs-meta">... </span> )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-drsgq7">Check out the <a href="https://huggingface.co/docs/huggingface_hub" rel="nofollow">huggingface_hub</a> documentation on files uploads <a href="https://huggingface.co/docs/huggingface_hub/en/guides/upload" rel="nofollow">here</a> if you’re looking for more upload options.</p> <p data-svelte-h="svelte-5gahax">Finally you can now load the dataset using 🤗 Datasets:</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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span>ds = load_dataset(<span class="hljs-string">"username/my-dataset"</span>)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="import-raw-data-to-storage-buckets" 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="#import-raw-data-to-storage-buckets"><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>Import raw data to Storage Buckets</span></h3> <p data-svelte-h="svelte-1afdv1v">Alternatively if you wish not to publish a dataset but simply import raw data files in a Hugging Face <a href="https://huggingface.co/docs/hub/storage-buckets" rel="nofollow">Storage Bucket</a>, you can use:</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-meta">>>> </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> create_bucket, sync_bucket
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tqdm.auto <span class="hljs-keyword">import</span> tqdm
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> itertools <span class="hljs-keyword">import</span> batched
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tempfile <span class="hljs-keyword">import</span> TemporaryDirectory
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> os
	<span class="hljs-meta">>>> </span>create_bucket(<span class="hljs-string">"username/my-bucket"</span>)
	<span class="hljs-meta">>>> </span>bucket_files_location = <span class="hljs-string">"hf://buckets/username/my-bucket/path/to/raw/files"</span>
	<span class="hljs-meta">>>> </span>batch_size = <span class="hljs-number">100</span>
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> data_files <span class="hljs-keyword">in</span> batched(tqdm(fs.glob(data_dir + pattern)), batch_size):
	<span class="hljs-meta">... </span> <span class="hljs-keyword">with</span> TemporaryDirectory() <span class="hljs-keyword">as</span> tmp_dir:
	<span class="hljs-meta">... </span> tmp_files = [os.path.join(tmp_dir, x[<span class="hljs-built_in">len</span>(data_dir):]) <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> data_files]
	<span class="hljs-meta">... </span> fs.download(data_files, tmp_files)
	<span class="hljs-meta">... </span> sync_bucket(tmp_dir, bucket_files_location)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1d7y2kh">Check out the <a href="https://huggingface.co/docs/huggingface_hub" rel="nofollow">huggingface_hub</a> documentation on Storage Buckets <a href="https://huggingface.co/docs/hub/storage-buckets" rel="nofollow">here</a> if you’re looking for more upload options.</p> <p data-svelte-h="svelte-r4lftr">Then later you can load the raw files using 🤗 Datasets, transform them and upload the final AI-ready datasets, e.g. in a streaming manner:</p> <p data-svelte-h="svelte-8p9hs7">If the files are in a format supported by 🤗 Datasets:</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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span>ds = load_dataset(bucket_files_location, streaming=<span class="hljs-literal">True</span>)
	<span class="hljs-meta">>>> </span>ds = ds.<span class="hljs-built_in">map</span>(...).<span class="hljs-built_in">filter</span>(...)
	<span class="hljs-meta">>>> </span>ds.push_to_hub(<span class="hljs-string">"username/my-dataset"</span>, num_proc=<span class="hljs-number">4</span>)
	<span class="hljs-meta">>>> </span><span class="hljs-comment"># and later</span>
	<span class="hljs-meta">>>> </span>ds = load_dataset(<span class="hljs-string">"username/my-dataset"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1imogd5">Otherwise you can use your own file parsing function:</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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> IterableDataset
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> hffs
	<span class="hljs-meta">>>> </span>data_files = hffs.find(bucket_files_location)
	<span class="hljs-meta">>>> </span>num_shards = <span class="hljs-number">1024</span> <span class="hljs-comment"># For parallelism. PS: every shard should fit in RAM</span>
	<span class="hljs-meta">>>> </span>ds = IterableDataset.from_dict({<span class="hljs-string">"data_file"</span>: data_files}, num_shards=num_shards)
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">parse_data_files</span>(<span class="hljs-params">data_files</span>):
	<span class="hljs-meta">... </span> ...
	<span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> {<span class="hljs-string">"col_1"</span>: [...], <span class="hljs-string">"col_2"</span>: [...]}
	<span class="hljs-meta">>>> </span>ds = ds.<span class="hljs-built_in">map</span>(parse_data_files, batched=<span class="hljs-literal">True</span>, input_column=[<span class="hljs-string">"data_file"</span>])
	<span class="hljs-meta">>>> </span>ds.push_to_hub(<span class="hljs-string">"username/my-dataset"</span>, num_proc=<span class="hljs-number">4</span>)
	<span class="hljs-meta">>>> </span><span class="hljs-comment"># and later</span>
	<span class="hljs-meta">>>> </span>ds = load_dataset(<span class="hljs-string">"username/my-dataset"</span>)<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/datasets/blob/main/docs/source/filesystems.mdx" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_1j7f9j2 = {
	assets: "/docs/datasets/pr_8113/en",
	base: "/docs/datasets/pr_8113/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/datasets/pr_8113/en/_app/immutable/entry/start.969da75e.js"),
	import("/docs/datasets/pr_8113/en/_app/immutable/entry/app.687c6ad1.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 20],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 31.5 kB
Xet hash:: 2fd65d310cc044fafc2529c7bd5c4cba6792578d841acc6d3209a0ffee774212

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.