Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / hub /pr_2396 /en /datasets-viewer-sql-console.html
HuggingFaceDocBuilder's picture
HuggingFaceDocBuilder
download
raw
34.1 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;SQL Console: Query Hugging Face datasets in your browser&quot;,&quot;local&quot;:&quot;sql-console-query-hugging-face-datasets-in-your-browser&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Examples&quot;,&quot;local&quot;:&quot;examples&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Filtering&quot;,&quot;local&quot;:&quot;filtering&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Histogram&quot;,&quot;local&quot;:&quot;histogram&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Regex Matching&quot;,&quot;local&quot;:&quot;regex-matching&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Saved Queries and Embeds API&quot;,&quot;local&quot;:&quot;saved-queries-and-embeds-api&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Leakage Detection&quot;,&quot;local&quot;:&quot;leakage-detection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/hub/pr_2396/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/entry/start.98590270.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/scheduler.258d2a4d.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/singletons.88781f72.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/index.c8b82093.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/paths.320b8a2d.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/entry/app.ce0d765a.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/preload-helper.ff3454b6.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/index.421344fd.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/nodes/0.b17140ee.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/nodes/66.48ddd64a.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/CopyLLMTxtMenu.dcc2dcf0.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.c1b3a105.js">
 <link rel="modulepreload" href="/docs/hub/pr_2396/en/_app/immutable/chunks/CodeBlock.2e7645a1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;SQL Console: Query Hugging Face datasets in your browser&quot;,&quot;local&quot;:&quot;sql-console-query-hugging-face-datasets-in-your-browser&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Examples&quot;,&quot;local&quot;:&quot;examples&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Filtering&quot;,&quot;local&quot;:&quot;filtering&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Histogram&quot;,&quot;local&quot;:&quot;histogram&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Regex Matching&quot;,&quot;local&quot;:&quot;regex-matching&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Saved Queries and Embeds API&quot;,&quot;local&quot;:&quot;saved-queries-and-embeds-api&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Leakage Detection&quot;,&quot;local&quot;:&quot;leakage-detection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&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="sql-console-query-hugging-face-datasets-in-your-browser" 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="#sql-console-query-hugging-face-datasets-in-your-browser"><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>SQL Console: Query Hugging Face datasets in your browser</span></h1> <p data-svelte-h="svelte-16uuqnr">You can run SQL queries on the dataset in the browser using the SQL Console. The SQL Console is powered by <a href="https://duckdb.org/" rel="nofollow">DuckDB</a> WASM and runs entirely in the browser. You can access the SQL Console from the Data Studio.</p> <div class="flex justify-center" data-svelte-h="svelte-17db6yf"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/sql-ai.png"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/sql-ai-dark.png"></div> <p class="text-sm text-center italic" data-svelte-h="svelte-3vzwz3">To learn more about the SQL Console, see the <a href="https://huggingface.co/blog/sql-console" target="_blank" rel="noopener noreferrer">SQL Console blog post</a>.</p> <p data-svelte-h="svelte-1rn8nni">Through the SQL Console, you can:</p> <ul data-svelte-h="svelte-1bmpj1d"><li>Run <a href="https://duckdb.org/docs/sql/query_syntax/select" rel="nofollow">DuckDB SQL queries</a> on the dataset (<em>checkout <a href="https://huggingface.co/spaces/cfahlgren1/sql-snippets" rel="nofollow">SQL Snippets</a> for useful queries</em>)</li> <li>Share results of the query with others via a link (<em>check out <a href="https://huggingface.co/datasets/gretelai/synthetic-gsm8k-reflection-405b?sql_console=true&sql=FROM+histogram%28%0A++train%2C%0A++topic%2C%0A++bin_count+%3A%3D+10%0A%29" rel="nofollow">this example</a></em>)</li> <li>Download the results of the query to a Parquet or CSV file</li> <li>Embed the results of the query in your own webpage using an iframe</li> <li>Query datasets with natural language</li></ul> <blockquote class="tip" data-svelte-h="svelte-6dndrq"><p>You can also use the DuckDB locally through the CLI to query the dataset via the <code>hf://</code> protocol. See the <a href="https://huggingface.co/docs/hub/en/datasets-duckdb" target="_blank" rel="noopener noreferrer">DuckDB Datasets documentation</a> for more information. The SQL Console provides a convenient <code>Copy to DuckDB CLI</code> button that generates the SQL query for creating views and executing your query in the DuckDB CLI.</p></blockquote> <h2 class="relative group"><a id="examples" 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="#examples"><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>Examples</span></h2> <h3 class="relative group"><a id="filtering" 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="#filtering"><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>Filtering</span></h3> <p data-svelte-h="svelte-1ckd63i">The SQL Console makes filtering datasets really easy. For example, if you want to filter the <code>SkunkworksAI/reasoning-0.01</code> dataset for instructions and responses with a reasoning length of at least 10, you can use the following query:</p> <div class="flex justify-center" data-svelte-h="svelte-2zc1wz"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-filtering.png"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-filtering-dark.png"></div> <p data-svelte-h="svelte-ogls81">Here’s the SQL to sort by length of the reasoning</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-keyword">SELECT</span> <span class="hljs-operator">*</span>
<span class="hljs-keyword">FROM</span> train
<span class="hljs-keyword">WHERE</span> LENGTH(reasoning_chains) <span class="hljs-operator">&gt;</span> <span class="hljs-number">10</span>;<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="histogram" 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="#histogram"><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>Histogram</span></h3> <p data-svelte-h="svelte-1ydnrvt">Many dataset authors choose to include statistics about the distribution of the data in the dataset. Using the DuckDB <code>histogram</code> function, we can plot a histogram of a column’s values.</p> <p data-svelte-h="svelte-odj8eb">For example, to plot a histogram of the <code>Rating</code> column in the <a href="https://huggingface.co/datasets/Lichess/chess-puzzles" rel="nofollow">Lichess/chess-puzzles</a> dataset, you can use the following query:</p> <div class="flex justify-center" data-svelte-h="svelte-1lawvyv"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-histogram.png"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-histogram-dark.png"></div> <p class="text-sm text-center italic" data-svelte-h="svelte-76g6n3">Learn more about the `histogram` function and parameters <a href="https://cfahlgren1-sql-snippets.hf.space/histogram" target="_blank" rel="noopener noreferrer">here</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-keyword">from</span> histogram(train, Rating)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="regex-matching" 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="#regex-matching"><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>Regex Matching</span></h3> <p data-svelte-h="svelte-1uol9na">One of the most powerful features of DuckDB is the deep support for regular expressions. You can use the <code>regexp</code> function to match patterns in your data.</p> <p data-svelte-h="svelte-19m4u7z">Using the <a href="https://duckdb.org/docs/sql/functions/char.html#regexp_matchesstring-pattern" rel="nofollow">regexp_matches</a> function, we can filter the <a href="https://huggingface.co/datasets/GeneralReasoning/GeneralThought-195K" rel="nofollow">GeneralReasoning/GeneralThought-195k</a> dataset for instructions that contain markdown code blocks.</p> <div class="flex justify-center" data-svelte-h="svelte-1y1w7dn"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-regex.png"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-regex-dark.png"></div> <p class="text-sm text-center italic" data-svelte-h="svelte-1mmzq6p">Learn more about the DuckDB regex functions <a href="https://duckdb.org/docs/sql/functions/regular_expressions.html" target="_blank" rel="noopener noreferrer">here</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-keyword">SELECT</span> <span class="hljs-operator">*</span>
<span class="hljs-keyword">FROM</span> train
<span class="hljs-keyword">WHERE</span> regexp_matches(model_answer, <span class="hljs-string">&#x27;```&#x27;</span>)
LIMIT <span class="hljs-number">10</span>;<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="saved-queries-and-embeds-api" 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="#saved-queries-and-embeds-api"><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>Saved Queries and Embeds API</span></h3> <p data-svelte-h="svelte-rdbmax">You can create, update, and delete SQL Console embeds programmatically. Embeds are saved queries that can be shared via link or embedded in other pages.</p> <p data-svelte-h="svelte-p82n31"><strong>Create an embed:</strong></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 -->POST <span class="hljs-regexp">/api/</span>datasets<span class="hljs-regexp">/{namespace}/</span>{repo}<span class="hljs-regexp">/sql-console/</span>embed
Content-Type: application/json
Authorization: Bearer {token}
{
 <span class="hljs-string">&quot;sql&quot;</span>: <span class="hljs-string">&quot;SELECT * FROM train LIMIT 10&quot;</span>,
 <span class="hljs-string">&quot;title&quot;</span>: <span class="hljs-string">&quot;Sample rows&quot;</span>,
 <span class="hljs-string">&quot;private&quot;</span>: <span class="hljs-keyword">false</span>,
 <span class="hljs-string">&quot;views&quot;</span>: [{<span class="hljs-string">&quot;key&quot;</span>: <span class="hljs-string">&quot;default/train&quot;</span>, <span class="hljs-string">&quot;displayName&quot;</span>: <span class="hljs-string">&quot;Train&quot;</span>, <span class="hljs-string">&quot;viewName&quot;</span>: <span class="hljs-string">&quot;train&quot;</span>}]
}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-13tei4y"><strong>Update an embed:</strong></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 -->PATCH <span class="hljs-regexp">/api/</span>datasets<span class="hljs-regexp">/{namespace}/</span>{repo}<span class="hljs-regexp">/sql-console/</span>embed/{embed_id}
Content-Type: application/json
Authorization: Bearer {token}
{
 <span class="hljs-string">&quot;sql&quot;</span>: <span class="hljs-string">&quot;SELECT * FROM train LIMIT 20&quot;</span>,
 <span class="hljs-string">&quot;title&quot;</span>: <span class="hljs-string">&quot;Updated title&quot;</span>,
 <span class="hljs-string">&quot;private&quot;</span>: <span class="hljs-keyword">true</span>
}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ci8dww"><strong>Delete an embed:</strong></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-keyword">DELETE</span> <span class="hljs-regexp">/api/</span>datasets<span class="hljs-regexp">/{namespace}/</span>{repo}<span class="hljs-regexp">/sql-console/</span>embed/{embed_id}
Authorization: Bearer {token}<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="leakage-detection" 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="#leakage-detection"><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>Leakage Detection</span></h3> <p data-svelte-h="svelte-17u8u2y">Leakage detection is the process of identifying whether data in a dataset is present in multiple splits, for example, whether the test set is present in the training set.</p> <div class="flex justify-center" data-svelte-h="svelte-1v6knqz"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-leakage.png"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/datastudio-leakage-dark.png"></div> <p class="text-sm text-center italic" data-svelte-h="svelte-pyab48">Learn more about leakage detection <a href="https://huggingface.co/blog/lbourdois/lle">here</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-keyword">WITH</span>
 overlapping_rows <span class="hljs-keyword">AS</span> (
 <span class="hljs-keyword">SELECT</span> <span class="hljs-built_in">COALESCE</span>(
 (<span class="hljs-keyword">SELECT</span> <span class="hljs-built_in">COUNT</span>(<span class="hljs-operator">*</span>) <span class="hljs-keyword">AS</span> overlap_count
 <span class="hljs-keyword">FROM</span> train
 <span class="hljs-keyword">INTERSECT</span>
 <span class="hljs-keyword">SELECT</span> <span class="hljs-built_in">COUNT</span>(<span class="hljs-operator">*</span>) <span class="hljs-keyword">AS</span> overlap_count
 <span class="hljs-keyword">FROM</span> test),
 <span class="hljs-number">0</span>
 ) <span class="hljs-keyword">AS</span> overlap_count
 ),
 total_unique_rows <span class="hljs-keyword">AS</span> (
 <span class="hljs-keyword">SELECT</span> <span class="hljs-built_in">COUNT</span>(<span class="hljs-operator">*</span>) <span class="hljs-keyword">AS</span> total_count
 <span class="hljs-keyword">FROM</span> (
 <span class="hljs-keyword">SELECT</span> <span class="hljs-operator">*</span> <span class="hljs-keyword">FROM</span> train
 <span class="hljs-keyword">UNION</span>
 <span class="hljs-keyword">SELECT</span> <span class="hljs-operator">*</span> <span class="hljs-keyword">FROM</span> test
 ) combined
 )
<span class="hljs-keyword">SELECT</span>
 overlap_count,
 total_count,
 <span class="hljs-keyword">CASE</span>
<span class="hljs-keyword">WHEN</span> total_count <span class="hljs-operator">&gt;</span> <span class="hljs-number">0</span> <span class="hljs-keyword">THEN</span> (overlap_count <span class="hljs-operator">*</span> <span class="hljs-number">100.0</span> <span class="hljs-operator">/</span> total_count)
 <span class="hljs-keyword">ELSE</span> <span class="hljs-number">0</span>
 <span class="hljs-keyword">END</span> <span class="hljs-keyword">AS</span> overlap_percentage
<span class="hljs-keyword">FROM</span> overlapping_rows, total_unique_rows;<!-- 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/hub-docs/blob/main/docs/hub/datasets-viewer-sql-console.md" 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_evh6pd = {
 assets: "/docs/hub/pr_2396/en",
 base: "/docs/hub/pr_2396/en",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/hub/pr_2396/en/_app/immutable/entry/start.98590270.js"),
 import("/docs/hub/pr_2396/en/_app/immutable/entry/app.ce0d765a.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 66],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
34.1 kB
·
Xet hash:
20783e4c224279dcd04039d49f1e315e080952b48846570477bafbb33ec6e8ec

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