Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / datasets /main /en /nlp_load.html

rtrm

about 1 month ago

download

raw

11.9 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Load text data","local":"load-text-data","sections":[],"depth":1}">
	<link href="/docs/datasets/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/entry/start.4d44eea4.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/scheduler.bdbef820.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/singletons.36b689ad.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/index.8a885b74.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/paths.27092e28.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/entry/app.d83067e8.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/index.c0aea24a.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/nodes/0.bfb01985.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/nodes/29.858e75bf.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/CodeBlock.6ccca92e.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/EditOnGithub.725ee0c1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Load text data","local":"load-text-data","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="load-text-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-text-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 text data</span></h1> <p data-svelte-h="svelte-w06s16">This guide shows you how to load text datasets. To learn how to load any type of dataset, take a look at the <a class="underline decoration-sky-400 decoration-2 font-semibold" href="./loading">general loading guide</a>.</p> <p data-svelte-h="svelte-1nologr">Text files are one of the most common file types for storing a dataset. By default, 🤗 Datasets samples a text file line by line to build the 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> load_dataset
	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"text"</span>, data_files={<span class="hljs-string">"train"</span>: [<span class="hljs-string">"my_text_1.txt"</span>, <span class="hljs-string">"my_text_2.txt"</span>], <span class="hljs-string">"test"</span>: <span class="hljs-string">"my_test_file.txt"</span>})

	<span class="hljs-comment"># Load from a directory</span>
	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"text"</span>, data_dir=<span class="hljs-string">"path/to/text/dataset"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-7z7mls">To sample a text file by paragraph or even an entire document, use the <code>sample_by</code> parameter:</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-comment"># Sample by paragraph</span>
	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"text"</span>, data_files={<span class="hljs-string">"train"</span>: <span class="hljs-string">"my_train_file.txt"</span>, <span class="hljs-string">"test"</span>: <span class="hljs-string">"my_test_file.txt"</span>}, sample_by=<span class="hljs-string">"paragraph"</span>)

	<span class="hljs-comment"># Sample by document</span>
	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"text"</span>, data_files={<span class="hljs-string">"train"</span>: <span class="hljs-string">"my_train_file.txt"</span>, <span class="hljs-string">"test"</span>: <span class="hljs-string">"my_test_file.txt"</span>}, sample_by=<span class="hljs-string">"document"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-19wmves">You can also use grep patterns to load specific files:</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>c4_subset = load_dataset(<span class="hljs-string">"allenai/c4"</span>, data_files=<span class="hljs-string">"en/c4-train.0000*-of-01024.json.gz"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-129tbg5">To load remote text files via HTTP, pass the URLs 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>dataset = load_dataset(<span class="hljs-string">"text"</span>, data_files=<span class="hljs-string">"https://huggingface.co/datasets/lhoestq/test/resolve/main/some_text.txt"</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/nlp_load.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_w3org2 = {
	assets: "/docs/datasets/main/en",
	base: "/docs/datasets/main/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/datasets/main/en/_app/immutable/entry/start.4d44eea4.js"),
	import("/docs/datasets/main/en/_app/immutable/entry/app.d83067e8.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 29],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 11.9 kB
Xet hash:: 85f18cf6aa690cae20ed448d75ee3228464ef2841f17528339fce16fa6fa2a19

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