datasets/pr_8021/en/about_cache.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;The cache&quot;,&quot;local&quot;:&quot;the-cache&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Fingerprint&quot;,&quot;local&quot;:&quot;fingerprint&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Hashing&quot;,&quot;local&quot;:&quot;hashing&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/datasets/pr_8021/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/entry/start.467c4c66.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/scheduler.d75c11ed.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/singletons.24e4ec1f.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/index.d12496d4.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/paths.409c1290.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/entry/app.3b2ba720.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/preload-helper.a99c0584.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/index.4ec9dfe9.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/nodes/0.5fda7065.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/nodes/3.3c6b9113.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.ee0f129e.js">
		<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/CodeBlock.5919a092.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;The cache&quot;,&quot;local&quot;:&quot;the-cache&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Fingerprint&quot;,&quot;local&quot;:&quot;fingerprint&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Hashing&quot;,&quot;local&quot;:&quot;hashing&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;: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="the-cache" 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="#the-cache"><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>The cache</span></h1> <p data-svelte-h="svelte-14tcvpe">The cache is one of the reasons why 🤗 Datasets is so efficient. It stores previously downloaded and processed datasets so when you need to use them again, they are reloaded directly from the cache. This avoids having to download a dataset all over again, or reapplying processing functions. Even after you close and start another Python session, 🤗 Datasets will reload your dataset directly from the cache!</p>  <h2 class="relative group"><a id="fingerprint" 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="#fingerprint"><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>Fingerprint</span></h2> <p data-svelte-h="svelte-1nie07o">How does the cache keeps track of what transforms are applied to a dataset? Well, 🤗 Datasets assigns a fingerprint to the cache file. A fingerprint keeps track of the current state of a dataset. The initial fingerprint is computed using a hash from the Arrow table, or a hash of the Arrow files if the dataset is on disk. Subsequent fingerprints are computed by combining the fingerprint of the previous state, and a hash of the latest transform applied.</p> <blockquote class="tip" data-svelte-h="svelte-1rb3g3h"><p>Transforms are any of the processing methods from the <a href="./process">How-to Process</a> guides such as <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.map">Dataset.map()</a> or <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.shuffle">Dataset.shuffle()</a>.</p></blockquote> <p data-svelte-h="svelte-1jtij1i">Here are what the actual fingerprints look like:</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">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> Dataset
<span class="hljs-meta">&gt;&gt;&gt; </span>dataset1 = Dataset.from_dict({<span class="hljs-string">&quot;a&quot;</span>: [<span class="hljs-number">0</span>, <span class="hljs-number">1</span>, <span class="hljs-number">2</span>]})
<span class="hljs-meta">&gt;&gt;&gt; </span>dataset2 = dataset1.<span class="hljs-built_in">map</span>(<span class="hljs-keyword">lambda</span> x: {<span class="hljs-string">&quot;a&quot;</span>: x[<span class="hljs-string">&quot;a&quot;</span>] + <span class="hljs-number">1</span>})
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-built_in">print</span>(dataset1._fingerprint, dataset2._fingerprint)
d19493523d95e2dc 5b86abacd4b42434<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-i7zvcn">In order for a transform to be hashable, it needs to be picklable by <a href="https://dill.readthedocs.io/en/latest/" rel="nofollow">dill</a> or <a href="https://docs.python.org/3/library/pickle" rel="nofollow">pickle</a>.</p> <p data-svelte-h="svelte-13cebff">When you use a non-hashable transform, 🤗 Datasets uses a random fingerprint instead and raises a warning. The non-hashable transform is considered different from the previous transforms. As a result, 🤗 Datasets will recompute all the transforms. Make sure your transforms are serializable with pickle or dill to avoid this!</p> <p data-svelte-h="svelte-159jmpz">An example of when 🤗 Datasets recomputes everything is when caching is disabled. When this happens, the cache files are generated every time and they get written to a temporary directory. Once your Python session ends, the cache files in the temporary directory are deleted. A random hash is assigned to these cache files, instead of a fingerprint.</p> <blockquote class="tip" data-svelte-h="svelte-1j2okm2"><p>When caching is disabled, use <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.save_to_disk">Dataset.save_to_disk()</a> to save your transformed dataset or it will be deleted once the session ends.</p></blockquote>  <h2 class="relative group"><a id="hashing" 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="#hashing"><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>Hashing</span></h2> <p data-svelte-h="svelte-epnhkf">The fingerprint of a dataset is updated by hashing the function passed to <code>map</code> as well as the <code>map</code> parameters (<code>batch_size</code>, <code>remove_columns</code>, etc.).</p> <p data-svelte-h="svelte-z3tz2x">You can check the hash of any Python object using the <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.fingerprint.Hasher">fingerprint.Hasher</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">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets.fingerprint <span class="hljs-keyword">import</span> Hasher
<span class="hljs-meta">&gt;&gt;&gt; </span>my_func = <span class="hljs-keyword">lambda</span> example: {<span class="hljs-string">&quot;length&quot;</span>: <span class="hljs-built_in">len</span>(example[<span class="hljs-string">&quot;text&quot;</span>])}
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-built_in">print</span>(Hasher.<span class="hljs-built_in">hash</span>(my_func))
<span class="hljs-string">&#x27;3d35e2b3e94c81d6&#x27;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-92c3vb">The hash is computed by dumping the object using a <code>dill</code> pickler and hashing the dumped bytes.
The pickler recursively dumps all the variables used in your function, so any change you do to an object that is used in your function, will cause the hash to change.</p> <p data-svelte-h="svelte-t61mhn">If one of your functions doesn’t seem to have the same hash across sessions, it means at least one of its variables contains a Python object that is not deterministic.
When this happens, feel free to hash any object you find suspicious to try to find the object that caused the hash to change.
For example, if you use a list for which the order of its elements is not deterministic across sessions, then the hash won’t be the same across sessions either.</p> <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_cache.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_1tcoqe3 = {
						assets: "/docs/datasets/pr_8021/en",
						base: "/docs/datasets/pr_8021/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/datasets/pr_8021/en/_app/immutable/entry/start.467c4c66.js"),
						import("/docs/datasets/pr_8021/en/_app/immutable/entry/app.3b2ba720.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 3],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>