Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Load scientific data","local":"load-scientific-data","sections":[{"title":"HDF5","local":"hdf5","sections":[],"depth":2},{"title":"Zarr","local":"zarr","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/datasets/pr_7983/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/entry/start.eaaaeb15.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/scheduler.d75c11ed.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/singletons.5ee5c9bc.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/index.d12496d4.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/paths.4d36687c.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/entry/app.e5bdc7ca.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/preload-helper.81822ca6.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/index.4ec9dfe9.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/nodes/0.36d5eb30.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/nodes/42.e2b1d2f9.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.a2aed191.js"> | |
| <link rel="modulepreload" href="/docs/datasets/pr_7983/en/_app/immutable/chunks/CodeBlock.e9e455f8.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Load scientific data","local":"load-scientific-data","sections":[{"title":"HDF5","local":"hdf5","sections":[],"depth":2},{"title":"Zarr","local":"zarr","sections":[],"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="load-scientific-data" 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="#load-scientific-data"><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>Load scientific data</span></h1> <p data-svelte-h="svelte-1nsvvnl">Scientific datasets are often stored in formats like HDF5 or Zarr (chunked, N-dimensional arrays). 🤗 Datasets can stream these formats directly from local files (and remote filesystems supported by <code>fsspec</code>) without converting the full dataset to Arrow first.</p> <h2 class="relative group"><a id="hdf5" 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="#hdf5"><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>HDF5</span></h2> <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">"hdf5"</span>, data_files=[<span class="hljs-string">"/path/to/data.h5"</span>], split=<span class="hljs-string">"train"</span>, streaming=<span class="hljs-literal">True</span>) | |
| <span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(<span class="hljs-built_in">next</span>(<span class="hljs-built_in">iter</span>(ds))) | |
| {<span class="hljs-string">'temperature'</span>: <span class="hljs-number">280.12</span>, <span class="hljs-string">'pressure'</span>: <span class="hljs-number">101325.0</span>, ...}<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="zarr" 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="#zarr"><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>Zarr</span></h2> <p data-svelte-h="svelte-blm3wz">Zarr support is currently experimental. Install it with <code>pip install "datasets[zarr]"</code> (or <code>pip install zarr</code>).</p> <p data-svelte-h="svelte-1dvzkds">Zarr stores are directory-based. You can point <code>data_files</code> to either the Zarr store root directory (recommended for convenience) or the Zarr root metadata file:</p> <ul data-svelte-h="svelte-kmrsct"><li>Zarr store root directory: <code>.../store.zarr</code> (auto-detects metadata)</li> <li>Zarr v3: <code>.../store.zarr/zarr.json</code></li> <li>Zarr v2 (consolidated): <code>.../store.zarr/.zmetadata</code></li></ul> <p data-svelte-h="svelte-1bya70j">For Zarr v2 non-consolidated stores, pass the store root (<code>.../store.zarr</code>) with <code>consolidated=False</code>.</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">"zarr"</span>, data_files=[<span class="hljs-string">"/path/to/store.zarr"</span>], split=<span class="hljs-string">"train"</span>, streaming=<span class="hljs-literal">True</span>) | |
| <span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(<span class="hljs-built_in">next</span>(<span class="hljs-built_in">iter</span>(ds))) | |
| {<span class="hljs-string">'int32'</span>: <span class="hljs-number">0</span>, <span class="hljs-string">'float32'</span>: <span class="hljs-number">0.0</span>, <span class="hljs-string">'matrix_2d'</span>: [[...], ...]}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1fokjvr">In streaming mode, Zarr is sharded by row ranges aligned to axis-0 chunk boundaries (instead of one shard per metadata file). You can control this with:</p> <ul data-svelte-h="svelte-268umz"><li><code>rows_per_shard</code>: target number of rows per shard (rounded up to chunk boundaries)</li> <li><code>target_num_shards</code>: target number of shards across each input store</li></ul> <p data-svelte-h="svelte-p05v58">If a root group contains arrays with different axis-0 lengths (for example coordinate arrays and time-varying arrays together), 🤗 Datasets automatically infers the primary row dimension (preferring N-D data arrays) and ignores non-row-aligned arrays. You can also target a specific subgroup with <code>group=...</code> for more control.</p> <p data-svelte-h="svelte-ipn7q">You can also load from the Hub via the <code>hf://</code> protocol:</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> DownloadConfig, load_dataset | |
| <span class="hljs-meta">>>> </span>download_config = DownloadConfig(storage_options={<span class="hljs-string">"hf"</span>: {<span class="hljs-string">"token"</span>: <span class="hljs-literal">None</span>}}) <span class="hljs-comment"># set token for private/gated repos</span> | |
| <span class="hljs-meta">>>> </span>ds = load_dataset( | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"zarr"</span>, | |
| <span class="hljs-meta">... </span> data_files=[<span class="hljs-string">"hf://datasets/<user>/<repo>@main/path/to/store.zarr"</span>], | |
| <span class="hljs-meta">... </span> split=<span class="hljs-string">"train"</span>, | |
| <span class="hljs-meta">... </span> streaming=<span class="hljs-literal">True</span>, | |
| <span class="hljs-meta">... </span> download_config=download_config, | |
| <span class="hljs-meta">... </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/scientific_load.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_1cxlhuj = { | |
| assets: "/docs/datasets/pr_7983/en", | |
| base: "/docs/datasets/pr_7983/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/datasets/pr_7983/en/_app/immutable/entry/start.eaaaeb15.js"), | |
| import("/docs/datasets/pr_7983/en/_app/immutable/entry/app.e5bdc7ca.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 42], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 17.2 kB
- Xet hash:
- a1a535273bb54bf9ea407185b792bf733aa75d4bd51925bbf9ed44a5f69cc76d
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.