Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Batch mapping","local":"batch-mapping","sections":[{"title":"Need for speed","local":"need-for-speed","sections":[],"depth":2},{"title":"Input size != output size","local":"input-size--output-size","sections":[],"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/6.4ec91ed4.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":"Batch mapping","local":"batch-mapping","sections":[{"title":"Need for speed","local":"need-for-speed","sections":[],"depth":2},{"title":"Input size != output size","local":"input-size--output-size","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="batch-mapping" 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="#batch-mapping"><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>Batch mapping</span></h1> <p data-svelte-h="svelte-1d4w9n2">Combining the utility of <a href="/docs/datasets/pr_8113/en/package_reference/main_classes#datasets.Dataset.map">Dataset.map()</a> with batch mode is very powerful. It allows you to speed up processing, and freely control the size of the generated dataset.</p> <h2 class="relative group"><a id="need-for-speed" 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="#need-for-speed"><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>Need for speed</span></h2> <p data-svelte-h="svelte-ftplyc">The primary objective of batch mapping is to speed up processing. Often times, it is faster to work with batches of data instead of single examples. Naturally, batch mapping lends itself to tokenization. For example, the 🤗 <a href="https://huggingface.co/docs/tokenizers/python/latest/" rel="nofollow">Tokenizers</a> library works faster with batches because it parallelizes the tokenization of all the examples in a batch.</p> <h2 class="relative group"><a id="input-size--output-size" 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="#input-size--output-size"><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>Input size != output size</span></h2> <p data-svelte-h="svelte-catkrd">The ability to control the size of the generated dataset can be leveraged for many interesting use-cases. In the How-to <a href="#map">map</a> section, there are examples of using batch mapping to:</p> <ul data-svelte-h="svelte-min2km"><li>Split long sentences into shorter chunks.</li> <li>Augment a dataset with additional tokens.</li></ul> <p data-svelte-h="svelte-1t0thr9">It is helpful to understand how this works, so you can come up with your own ways to use batch mapping. At this point, you may be wondering how you can control the size of the generated dataset. The answer is: <strong>the mapped function does not have to return an output batch of the same size</strong>.</p> <p data-svelte-h="svelte-14uwqpb">In other words, your mapped function input can be a batch of size <code>N</code> and return a batch of size <code>M</code>. The output <code>M</code> can be greater than or less than <code>N</code>. This means you can concatenate your examples, divide it up, and even add more examples!</p> <p data-svelte-h="svelte-5jxdnp">However, remember that all values in the output dictionary must contain the <strong>same number of elements</strong> as the other fields in the output dictionary. Otherwise, it is not possible to define the number of examples in the output returned by the mapped function. The number can vary between successive batches processed by the mapped function. For a single batch though, all values of the output dictionary should have the same length (i.e., the number of elements).</p> <p data-svelte-h="svelte-1ac2mdx">For example, from a dataset of 1 column and 3 rows, if you use <code>map</code> to return a new column with twice as many rows, then you will have an error. | |
| In this case, you end up with one column with 3 rows, and one column with 6 rows. As you can see, the table will not be valid:</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> Dataset | |
| <span class="hljs-meta">>>> </span>dataset = Dataset.from_dict({<span class="hljs-string">"a"</span>: [<span class="hljs-number">0</span>, <span class="hljs-number">1</span>, <span class="hljs-number">2</span>]}) | |
| <span class="hljs-meta">>>> </span>dataset.<span class="hljs-built_in">map</span>(<span class="hljs-keyword">lambda</span> batch: {<span class="hljs-string">"b"</span>: batch[<span class="hljs-string">"a"</span>] * <span class="hljs-number">2</span>}, batched=<span class="hljs-literal">True</span>) <span class="hljs-comment"># new column with 6 elements: [0, 1, 2, 0, 1, 2]</span> | |
| <span class="hljs-string">'ArrowInvalid: Column 1 named b expected length 3 but got length 6'</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-b6xcy8">To make it valid, you have to drop one of the columns:</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> Dataset | |
| <span class="hljs-meta">>>> </span>dataset = Dataset.from_dict({<span class="hljs-string">"a"</span>: [<span class="hljs-number">0</span>, <span class="hljs-number">1</span>, <span class="hljs-number">2</span>]}) | |
| <span class="hljs-meta">>>> </span>dataset_with_duplicates = dataset.<span class="hljs-built_in">map</span>(<span class="hljs-keyword">lambda</span> batch: {<span class="hljs-string">"b"</span>: batch[<span class="hljs-string">"a"</span>] * <span class="hljs-number">2</span>}, remove_columns=[<span class="hljs-string">"a"</span>], batched=<span class="hljs-literal">True</span>) | |
| <span class="hljs-meta">>>> </span><span class="hljs-built_in">len</span>(dataset_with_duplicates) | |
| <span class="hljs-number">6</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-nsvoi3">Alternatively, you can overwrite the existing column to achieve the same result. | |
| For example, here’s how to duplicate every row in the dataset by overwriting column <code>"a"</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> Dataset | |
| <span class="hljs-meta">>>> </span>dataset = Dataset.from_dict({<span class="hljs-string">"a"</span>: [<span class="hljs-number">0</span>, <span class="hljs-number">1</span>, <span class="hljs-number">2</span>]}) | |
| <span class="hljs-comment"># overwrites the existing "a" column with duplicated values</span> | |
| <span class="hljs-meta">>>> </span>duplicated_dataset = dataset.<span class="hljs-built_in">map</span>( | |
| <span class="hljs-meta">... </span> <span class="hljs-keyword">lambda</span> batch: {<span class="hljs-string">"a"</span>: [x <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> batch[<span class="hljs-string">"a"</span>] <span class="hljs-keyword">for</span> _ <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-number">2</span>)]}, | |
| <span class="hljs-meta">... </span> batched=<span class="hljs-literal">True</span> | |
| <span class="hljs-meta">... </span>) | |
| <span class="hljs-meta">>>> </span>duplicated_dataset | |
| Dataset({ | |
| features: [<span class="hljs-string">'a'</span>], | |
| num_rows: <span class="hljs-number">6</span> | |
| }) | |
| <span class="hljs-meta">>>> </span>duplicated_dataset[<span class="hljs-string">"a"</span>] | |
| [<span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">1</span>, <span class="hljs-number">1</span>, <span class="hljs-number">2</span>, <span class="hljs-number">2</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/about_map_batch.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, 6], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 19.1 kB
- Xet hash:
- 6bbc2f59d2e34f509103f137b314b2214429926b5a71e9e540d948df3546951e
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.