Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / datasets /pr_7625 /en /load_hub.html

rtrm

about 1 month ago

download

raw

25.7 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Load a dataset from the Hub","local":"load-a-dataset-from-the-hub","sections":[{"title":"Load a dataset","local":"load-a-dataset","sections":[],"depth":2},{"title":"Splits","local":"splits","sections":[],"depth":2},{"title":"Configurations","local":"configurations","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/datasets/pr_7625/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/entry/start.e3554493.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/scheduler.bdbef820.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/singletons.3033ce13.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/index.8a885b74.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/paths.d336aca3.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/entry/app.53b28564.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/index.c0aea24a.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/nodes/0.5c9c8fde.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/nodes/28.c6d122d5.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/CodeBlock.e814ab8d.js">
	<link rel="modulepreload" href="/docs/datasets/pr_7625/en/_app/immutable/chunks/getInferenceSnippets.fbead63c.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Load a dataset from the Hub","local":"load-a-dataset-from-the-hub","sections":[{"title":"Load a dataset","local":"load-a-dataset","sections":[],"depth":2},{"title":"Splits","local":"splits","sections":[],"depth":2},{"title":"Configurations","local":"configurations","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="load-a-dataset-from-the-hub" 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-a-dataset-from-the-hub"><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 a dataset from the Hub</span></h1> <p data-svelte-h="svelte-9qr6ee">Finding high-quality datasets that are reproducible and accessible can be difficult. One of 🤗 Datasets main goals is to provide a simple way to load a dataset of any format or type. The easiest way to get started is to discover an existing dataset on the <a href="https://huggingface.co/datasets" rel="nofollow">Hugging Face Hub</a> - a community-driven collection of datasets for tasks in NLP, computer vision, and audio - and use 🤗 Datasets to download and generate the dataset.</p> <p data-svelte-h="svelte-1nd3fhb">This tutorial uses the <a href="https://huggingface.co/datasets/rotten_tomatoes" rel="nofollow">rotten_tomatoes</a> and <a href="https://huggingface.co/datasets/PolyAI/minds14" rel="nofollow">MInDS-14</a> datasets, but feel free to load any dataset you want and follow along. Head over to the Hub now and find a dataset for your task!</p> <h2 class="relative group"><a id="load-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="#load-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>Load a dataset</span></h2> <p data-svelte-h="svelte-ym5r24">Before you take the time to download a dataset, it’s often helpful to quickly get some general information about a dataset. A dataset’s information is stored inside <a href="/docs/datasets/pr_7625/en/package_reference/main_classes#datasets.DatasetInfo">DatasetInfo</a> and can include information such as the dataset description, features, and dataset size.</p> <p data-svelte-h="svelte-1xk3ota">Use the <a href="/docs/datasets/pr_7625/en/package_reference/loading_methods#datasets.load_dataset_builder">load_dataset_builder()</a> function to load a dataset builder and inspect a dataset’s attributes without committing to downloading it:</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_builder
	<span class="hljs-meta">>>> </span>ds_builder = load_dataset_builder(<span class="hljs-string">"cornell-movie-review-data/rotten_tomatoes"</span>)

	<span class="hljs-comment"># Inspect dataset description</span>
	<span class="hljs-meta">>>> </span>ds_builder.info.description
	Movie Review Dataset. This <span class="hljs-keyword">is</span> a dataset of containing <span class="hljs-number">5</span>,<span class="hljs-number">331</span> positive <span class="hljs-keyword">and</span> <span class="hljs-number">5</span>,<span class="hljs-number">331</span> negative processed sentences <span class="hljs-keyword">from</span> Rotten Tomatoes movie reviews. This data was first used <span class="hljs-keyword">in</span> Bo Pang <span class="hljs-keyword">and</span> Lillian Lee, ``Seeing stars: Exploiting <span class="hljs-keyword">class</span> <span class="hljs-title class_">relationships</span> <span class="hljs-keyword">for</span> sentiment categorization <span class="hljs-keyword">with</span> respect to rating scales.<span class="hljs-string">''</span>, Proceedings of the ACL, <span class="hljs-number">2005.</span>

	<span class="hljs-comment"># Inspect dataset features</span>
	<span class="hljs-meta">>>> </span>ds_builder.info.features
	{<span class="hljs-string">'label'</span>: ClassLabel(names=[<span class="hljs-string">'neg'</span>, <span class="hljs-string">'pos'</span>]),
	<span class="hljs-string">'text'</span>: Value(dtype=<span class="hljs-string">'string'</span>)}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-cfmghe">If you’re happy with the dataset, then load it with <a href="/docs/datasets/pr_7625/en/package_reference/loading_methods#datasets.load_dataset">load_dataset()</a>:</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>dataset = load_dataset(<span class="hljs-string">"cornell-movie-review-data/rotten_tomatoes"</span>, split=<span class="hljs-string">"train"</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="splits" 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="#splits"><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>Splits</span></h2> <p data-svelte-h="svelte-kmno5f">A split is a specific subset of a dataset like <code>train</code> and <code>test</code>. List a dataset’s split names with the <a href="/docs/datasets/pr_7625/en/package_reference/loading_methods#datasets.get_dataset_split_names">get_dataset_split_names()</a> 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> get_dataset_split_names

	<span class="hljs-meta">>>> </span>get_dataset_split_names(<span class="hljs-string">"cornell-movie-review-data/rotten_tomatoes"</span>)
	[<span class="hljs-string">'train'</span>, <span class="hljs-string">'validation'</span>, <span class="hljs-string">'test'</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-zyp0kw">Then you can load a specific split with the <code>split</code> parameter. Loading a dataset <code>split</code> returns a <a href="/docs/datasets/pr_7625/en/package_reference/main_classes#datasets.Dataset">Dataset</a> object:</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>dataset = load_dataset(<span class="hljs-string">"cornell-movie-review-data/rotten_tomatoes"</span>, split=<span class="hljs-string">"train"</span>)
	<span class="hljs-meta">>>> </span>dataset
	Dataset({
	features: [<span class="hljs-string">'text'</span>, <span class="hljs-string">'label'</span>],
	num_rows: <span class="hljs-number">8530</span>
	})<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-v4hlw3">If you don’t specify a <code>split</code>, 🤗 Datasets returns a <a href="/docs/datasets/pr_7625/en/package_reference/main_classes#datasets.DatasetDict">DatasetDict</a> object instead:</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>dataset = load_dataset(<span class="hljs-string">"cornell-movie-review-data/rotten_tomatoes"</span>)
	DatasetDict({
	train: Dataset({
	features: [<span class="hljs-string">'text'</span>, <span class="hljs-string">'label'</span>],
	num_rows: <span class="hljs-number">8530</span>
	})
	validation: Dataset({
	features: [<span class="hljs-string">'text'</span>, <span class="hljs-string">'label'</span>],
	num_rows: <span class="hljs-number">1066</span>
	})
	test: Dataset({
	features: [<span class="hljs-string">'text'</span>, <span class="hljs-string">'label'</span>],
	num_rows: <span class="hljs-number">1066</span>
	})
	})<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="configurations" 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="#configurations"><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>Configurations</span></h2> <p data-svelte-h="svelte-2wgw8k">Some datasets contain several sub-datasets. For example, the <a href="https://huggingface.co/datasets/PolyAI/minds14" rel="nofollow">MInDS-14</a> dataset has several sub-datasets, each one containing audio data in a different language. These sub-datasets are known as <em>configurations</em> or <em>subsets</em>, and you must explicitly select one when loading the dataset. If you don’t provide a configuration name, 🤗 Datasets will raise a <code>ValueError</code> and remind you to choose a configuration.</p> <p data-svelte-h="svelte-gpzvth">Use the <a href="/docs/datasets/pr_7625/en/package_reference/loading_methods#datasets.get_dataset_config_names">get_dataset_config_names()</a> function to retrieve a list of all the possible configurations available to your dataset:</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> get_dataset_config_names

	<span class="hljs-meta">>>> </span>configs = get_dataset_config_names(<span class="hljs-string">"PolyAI/minds14"</span>)
	<span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(configs)
	[<span class="hljs-string">'cs-CZ'</span>, <span class="hljs-string">'de-DE'</span>, <span class="hljs-string">'en-AU'</span>, <span class="hljs-string">'en-GB'</span>, <span class="hljs-string">'en-US'</span>, <span class="hljs-string">'es-ES'</span>, <span class="hljs-string">'fr-FR'</span>, <span class="hljs-string">'it-IT'</span>, <span class="hljs-string">'ko-KR'</span>, <span class="hljs-string">'nl-NL'</span>, <span class="hljs-string">'pl-PL'</span>, <span class="hljs-string">'pt-PT'</span>, <span class="hljs-string">'ru-RU'</span>, <span class="hljs-string">'zh-CN'</span>, <span class="hljs-string">'all'</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-avfjb">Then load the configuration you want:</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>mindsFR = load_dataset(<span class="hljs-string">"PolyAI/minds14"</span>, <span class="hljs-string">"fr-FR"</span>, split=<span class="hljs-string">"train"</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/load_hub.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_kk99bk = {
	assets: "/docs/datasets/pr_7625/en",
	base: "/docs/datasets/pr_7625/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/datasets/pr_7625/en/_app/immutable/entry/start.e3554493.js"),
	import("/docs/datasets/pr_7625/en/_app/immutable/entry/app.53b28564.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 28],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 25.7 kB
Xet hash:: 89559051c605a0df292ffc1b2a300cb82d663f5b4198e15ecbf3531a4d683c13

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