Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Explore statistics over split data","local":"explore-statistics-over-split-data","sections":[{"title":"Response structure by data type","local":"response-structure-by-data-type","sections":[{"title":"class_label","local":"classlabel","sections":[],"depth":3},{"title":"float","local":"float","sections":[],"depth":3},{"title":"int","local":"int","sections":[],"depth":3},{"title":"bool","local":"bool","sections":[],"depth":3},{"title":"string_label","local":"stringlabel","sections":[],"depth":3},{"title":"string_text","local":"stringtext","sections":[],"depth":3},{"title":"list","local":"list","sections":[],"depth":3},{"title":"audio","local":"audio","sections":[],"depth":3},{"title":"image","local":"image","sections":[],"depth":3},{"title":"datetime","local":"datetime","sections":[],"depth":3}],"depth":2}],"depth":1}"> | |
| <link href="/docs/dataset-viewer/pr_3255/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/entry/start.fe569ee0.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/scheduler.3ed1c2f3.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/singletons.85b0af82.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/index.544d131f.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/paths.bbc57edb.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/entry/app.2ccd3927.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/preload-helper.dcf09c3d.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/index.f0e90566.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/nodes/0.5aa3dcbf.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/nodes/26.8693bd13.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/Tip.921a40b4.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.d48a0be5.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/CodeBlock.774c05e1.js"> | |
| <link rel="modulepreload" href="/docs/dataset-viewer/pr_3255/en/_app/immutable/chunks/InferenceApi.abac6fcf.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Explore statistics over split data","local":"explore-statistics-over-split-data","sections":[{"title":"Response structure by data type","local":"response-structure-by-data-type","sections":[{"title":"class_label","local":"classlabel","sections":[],"depth":3},{"title":"float","local":"float","sections":[],"depth":3},{"title":"int","local":"int","sections":[],"depth":3},{"title":"bool","local":"bool","sections":[],"depth":3},{"title":"string_label","local":"stringlabel","sections":[],"depth":3},{"title":"string_text","local":"stringtext","sections":[],"depth":3},{"title":"list","local":"list","sections":[],"depth":3},{"title":"audio","local":"audio","sections":[],"depth":3},{"title":"image","local":"image","sections":[],"depth":3},{"title":"datetime","local":"datetime","sections":[],"depth":3}],"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 max-sm:gap-0.5 h-6 max-sm:h-5 px-2 max-sm:px-1.5 text-[11px] max-sm:text-[9px] 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"><svg class="w-3 h-3 max-sm:w-2.5 max-sm:h-2.5" 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-6 max-sm:h-5 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 w-3 h-3 max-sm:w-2.5 max-sm:h-2.5 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="explore-statistics-over-split-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="#explore-statistics-over-split-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>Explore statistics over split data</span></h1> <p data-svelte-h="svelte-e6wqpo">The dataset viewer provides a <code>/statistics</code> endpoint for fetching some basic statistics precomputed for a requested dataset. This will get you a quick insight on how the data is distributed.</p> <blockquote class="warning">Currently, statistics are computed only for <a href="./parquet" data-svelte-h="svelte-1im6jtl">datasets with Parquet exports</a>.</blockquote> <p data-svelte-h="svelte-1dfy5if">The <code>/statistics</code> endpoint requires three query parameters:</p> <ul data-svelte-h="svelte-4umse1"><li><code>dataset</code>: the dataset name, for example <code>nyu-mll/glue</code></li> <li><code>config</code>: the subset name, for example <code>cola</code></li> <li><code>split</code>: the split name, for example <code>train</code></li></ul> <p data-svelte-h="svelte-1j4flsh">Let’s get some stats for <code>nyu-mll/glue</code> dataset, <code>cola</code> subset, <code>train</code> split:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><rect width="32" height="32" fill="#f7df1e"></rect><path d="M21.5,25a3.27,3.27,0,0,0,3,1.83c1.25,0,2-.63,2-1.49,0-1-.81-1.39-2.19-2L23.56,23C21.39,22.1,20,20.94,20,18.49c0-2.25,1.72-4,4.41-4a4.44,4.44,0,0,1,4.27,2.41l-2.34,1.5a2,2,0,0,0-1.93-1.29,1.31,1.31,0,0,0-1.44,1.29c0,.9.56,1.27,1.85,1.83l.75.32c2.55,1.1,4,2.21,4,4.72,0,2.71-2.12,4.19-5,4.19a5.78,5.78,0,0,1-5.48-3.07Zm-10.63.26c.48.84.91,1.55,1.94,1.55s1.61-.39,1.61-1.89V14.69h3V25c0,3.11-1.83,4.53-4.49,4.53a4.66,4.66,0,0,1-4.51-2.75Z"></path></svg> JavaScript </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><rect width="32" height="32" rx="4" fill="#1683a5"></rect><path d="M6.71,14A5,5,0,0,1,8.82,9.29l2.64-2.2c1.67-1.37,2.52-1.41,4.6-1.41H21.7c1.19,0,2.45.27,2.45,1.79s-1.4,1.78-2.45,1.78H15.44a3.31,3.31,0,0,0-2,.89L11.24,12c-.55.44-1,.81-1,1.52v4.41c0,.7.41,1.07,1,1.52l2.16,1.82a3.34,3.34,0,0,0,2,.89H21.7c1.05,0,2.45.23,2.45,1.78s-1.26,1.78-2.45,1.78H16.06c-2.08,0-2.94,0-4.6-1.4L8.82,22.09A5.05,5.05,0,0,1,6.71,17.4Z" fill="#fff"></path></svg> cURL </div></div> <div class="language-select"> <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">import</span> requests | |
| headers = {<span class="hljs-string">"Authorization"</span>: <span class="hljs-string">f"Bearer <span class="hljs-subst">{API_TOKEN}</span>"</span>} | |
| API_URL = <span class="hljs-string">"https://datasets-server.huggingface.co/statistics?dataset=nyu-mll/glue&config=cola&split=train"</span> | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">query</span>(): | |
| response = requests.get(API_URL, headers=headers) | |
| <span class="hljs-keyword">return</span> response.json() | |
| data = query()<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-bgjtc5">The response JSON contains three keys:</p> <ul data-svelte-h="svelte-1huk7tw"><li><code>num_examples</code> - number of samples in a split or number of samples in the first chunk of data if dataset is larger than 5GB (see <code>partial</code> field below).</li> <li><code>statistics</code> - list of dictionaries of statistics per each column, each dictionary has three keys: <code>column_name</code>, <code>column_type</code>, and <code>column_statistics</code>. Content of <code>column_statistics</code> depends on a column type, see <a href="./statistics#response-structure-by-data-type">Response structure by data types</a> for more details</li> <li><code>partial</code> - <code>true</code> if statistics are computed on the first 5 GB of data, not on the full split, <code>false</code> otherwise.</li></ul> <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-punctuation">{</span> | |
| <span class="hljs-attr">"num_examples"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">8551</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"idx"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"int"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">8550</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">4275</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">4275</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2468.60541</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">847</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">856</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1712</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">2568</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">3424</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">4280</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">5136</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">5992</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">6848</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">7704</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">8550</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"label"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"class_label"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"no_label_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"no_label_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"n_unique"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"frequencies"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"unacceptable"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2528</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"acceptable"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">6023</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"sentence"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"string_text"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">231</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">40.70074</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">37</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">19.14431</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">2260</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">4512</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1262</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">380</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">102</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">26</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">29</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">52</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">75</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">98</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">121</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">144</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">167</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">190</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">213</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">231</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"partial"</span><span class="hljs-punctuation">:</span> <span class="hljs-literal"><span class="hljs-keyword">false</span></span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="response-structure-by-data-type" 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="#response-structure-by-data-type"><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>Response structure by data type</span></h2> <p data-svelte-h="svelte-jvzhdt">Currently, statistics are supported for strings, float and integer numbers, lists, datetimes, audio and image data and the special <a href="https://huggingface.co/docs/datasets/package_reference/main_classes#datasets.ClassLabel" rel="nofollow"><code>datasets.ClassLabel</code></a> feature type of the <a href="https://huggingface.co/docs/datasets/" rel="nofollow"><code>datasets</code></a> library.</p> <p data-svelte-h="svelte-wu68cg"><code>column_type</code> in response can be one of the following values:</p> <ul data-svelte-h="svelte-1iwpjnc"><li><code>class_label</code> - for <a href="https://huggingface.co/docs/datasets/package_reference/main_classes#datasets.ClassLabel" rel="nofollow"><code>datasets.ClassLabel</code></a> feature which represents categorical data</li> <li><code>float</code> - for float data types</li> <li><code>int</code> - for integer data types</li> <li><code>bool</code> - for boolean data type</li> <li><code>string_label</code> - for string data types being treated as categories (see below)</li> <li><code>string_text</code> - for string data types if they do not represent categories (see below)</li> <li><code>list</code> - for lists of any other data types (including lists)</li> <li><code>audio</code> - for audio data</li> <li><code>image</code> - for image data</li> <li><code>datetime</code> - for datetime data</li></ul> <h3 class="relative group"><a id="classlabel" 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="#classlabel"><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>class_label</span></h3> <p data-svelte-h="svelte-14v5ytk">This type represents categorical data encoded as <a href="https://huggingface.co/docs/datasets/package_reference/main_classes#datasets.ClassLabel" rel="nofollow"><code>ClassLabel</code></a> feature. The following measures are computed:</p> <ul data-svelte-h="svelte-19qzf39"><li>number and proportion of <code>null</code> values</li> <li>number and proportion of values with no label</li> <li>number of unique values (excluding <code>null</code> and <code>no label</code>)</li> <li>value counts for each label (excluding <code>null</code> and <code>no label</code>)</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"label"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"class_label"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"no_label_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"no_label_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"n_unique"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"frequencies"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"unacceptable"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2528</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"acceptable"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">6023</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="float" 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="#float"><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>float</span></h3> <p data-svelte-h="svelte-pj9ye6">The following measures are returned for float data types:</p> <ul data-svelte-h="svelte-pbad08"><li>minimum, maximum, mean, median, and standard deviation values</li> <li>number and proportion of <code>null</code> and <code>NaN</code> values (<code>NaN</code> values are treated as <code>null</code>)</li> <li>histogram with 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"clarity"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"float"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1.67206</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1.8</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.38714</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">17</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">12</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">48</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">52</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">135</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">188</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">814</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">15</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1628</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">2048</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0.2</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0.4</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0.6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0.8</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1.2</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1.4</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1.6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1.8</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">2</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="int" 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="#int"><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>int</span></h3> <p data-svelte-h="svelte-1k93h4e">The following measures are returned for integer data types:</p> <ul data-svelte-h="svelte-1age2aj"><li>minimum, maximum, mean, median, and standard deviation values</li> <li>number and proportion of <code>null</code> values</li> <li>histogram with less than or equal to 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"direction"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"int"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.49925</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.5</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">50075</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">49925</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="bool" 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="#bool"><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>bool</span></h3> <p data-svelte-h="svelte-1s8i9jz">The following measures are returned for bool data type:</p> <ul data-svelte-h="svelte-a80cmd"><li>number and proportion of <code>null</code> values</li> <li>value counts for <code>'True'</code> and <code>'False'</code> values</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"penalty"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"bool"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> | |
| <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">3</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.15</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"frequencies"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"False"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">7</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"True"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">10</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="stringlabel" 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="#stringlabel"><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>string_label</span></h3> <p data-svelte-h="svelte-amq8ug">If the proportion of unique values in a string column within requested split is lower than or equal to 0.2 and the number of unique values is lower than 1000, or if the number of unique values is lower or equal to 10 (independently of the proportion), it is considered to be a category. The following measures are returned:</p> <ul data-svelte-h="svelte-g4wz8u"><li>number and proportion of <code>null</code> values</li> <li>number of unique values (excluding <code>null</code>)</li> <li>value counts for each label (excluding <code>null</code>)</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"answerKey"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"string_label"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"n_unique"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">4</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"frequencies"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"D"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1221</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"C"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1146</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"A"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1378</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"B"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1212</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="stringtext" 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="#stringtext"><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>string_text</span></h3> <p data-svelte-h="svelte-z9mqkl">If string column does not satisfy the conditions to be treated as a <code>string_label</code>, it is considered to be a column containing texts and response contains statistics over text lengths which are calculated by character number. The following measures are computed:</p> <ul data-svelte-h="svelte-1kqobsx"><li>minimum, maximum, mean, median, and standard deviation of text lengths</li> <li>number and proportion of <code>null</code> values</li> <li>histogram of text lengths with 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"sentence"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"string_text"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">231</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">40.70074</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">37</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">19.14431</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">2260</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">4512</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1262</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">380</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">102</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">26</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">6</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">29</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">52</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">75</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">98</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">121</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">144</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">167</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">190</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">213</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">231</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="list" 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="#list"><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>list</span></h3> <p data-svelte-h="svelte-1f5hue6">For lists, the distribution of their lengths is computed. The following measures are returned:</p> <ul data-svelte-h="svelte-102ghxr"><li>minimum, maximum, mean, median, and standard deviation of lists lengths</li> <li>number and proportion of <code>null</code> values</li> <li>histogram of lists lengths with up to 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"chat_history"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"list"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">3</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1.01741</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.13146</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">11177</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">196</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">2</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">3</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">3</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <p data-svelte-h="svelte-a3oh8u">Note that dictionaries of lists are not supported.</p> <h3 class="relative group"><a id="audio" 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="#audio"><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>audio</span></h3> <p data-svelte-h="svelte-b6jp4k">For audio data, the distribution of audio files durations is computed. The following measures are returned:</p> <ul data-svelte-h="svelte-1ok3495"><li>minimum, maximum, mean, median, and standard deviation of audio files durations</li> <li>number and proportion of <code>null</code> values</li> <li>histogram of audio files durations with 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"audio"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"audio"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1.02</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">15</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">13.93042</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">14.77</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">2.63734</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">32</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">25</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">18</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">24</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">22</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">17</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">18</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">19</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">55</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1770</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">1.02</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">2.418</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">3.816</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">5.214</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">6.612</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">8.01</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">9.408</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">10.806</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">12.204</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">13.602</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">15</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="image" 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="#image"><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>image</span></h3> <p data-svelte-h="svelte-1prqm7w">For image data, the distribution of images widths is computed. The following measures are returned:</p> <ul data-svelte-h="svelte-8shemo"><li>minimum, maximum, mean, median, and standard deviation of widths of image files</li> <li>number and proportion of <code>null</code> values</li> <li>histogram of images widths with 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"image"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"image"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">256</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">873</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">327.99339</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">341.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">60.07286</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">1734</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1637</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1326</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">121</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">10</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">3</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">3</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">2</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">256</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">318</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">380</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">442</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">504</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">566</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">628</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">690</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">752</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">814</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">873</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <h3 class="relative group"><a id="datetime" 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="#datetime"><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>datetime</span></h3> <p data-svelte-h="svelte-1k6lge8">The distribution of datetime is computed. The following measures are returned:</p> <ul data-svelte-h="svelte-1rp39y1"><li>minimum, maximum, mean, median, and standard deviation of datetimes represented as strings with precision up to seconds</li> <li>number and proportion of <code>null</code> values</li> <li>histogram of datetimes with 10 bins</li></ul> <details><summary data-svelte-h="svelte-vpylii">Example</summary> <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-punctuation">{</span> | |
| <span class="hljs-attr">"column_name"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"date"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_type"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"datetime"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"column_statistics"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"nan_count"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"nan_proportion"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">0.0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"min"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"2013-05-18 04:54:11"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"max"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"2013-06-20 10:01:41"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"mean"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"2013-05-27 18:03:39"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"median"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"2013-05-23 11:55:50"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"std"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"11 days, 4:57:32.322450"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"histogram"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span> | |
| <span class="hljs-attr">"hist"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-number">318776</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">393036</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">173904</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">0</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-number">206284</span> | |
| <span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-attr">"bin_edges"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span> | |
| <span class="hljs-string">"2013-05-18 04:54:11"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-05-21 12:36:57"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-05-24 20:19:43"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-05-28 04:02:29"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-05-31 11:45:15"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-06-03 19:28:01"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-06-07 03:10:47"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-06-10 10:53:33"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-06-13 18:36:19"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-06-17 02:19:05"</span><span class="hljs-punctuation">,</span> | |
| <span class="hljs-string">"2013-06-20 10:01:41"</span> | |
| <span class="hljs-punctuation">]</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span> | |
| <span class="hljs-punctuation">}</span><!-- HTML_TAG_END --></pre></div></p></details> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/dataset-viewer/blob/main/docs/source/statistics.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_1s2n2i8 = { | |
| assets: "/docs/dataset-viewer/pr_3255/en", | |
| base: "/docs/dataset-viewer/pr_3255/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/dataset-viewer/pr_3255/en/_app/immutable/entry/start.fe569ee0.js"), | |
| import("/docs/dataset-viewer/pr_3255/en/_app/immutable/entry/app.2ccd3927.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 26], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 92.1 kB
- Xet hash:
- 33c27a56273428f100696adf2a14b98297fee6e2098c1a17743fffc449dc9bf9
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.