Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / dataset-viewer /pr_3255 /en /analyze_data.html

rtrm

about 2 months ago

download

raw

26 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Analyze a dataset on the Hub","local":"analyze-a-dataset-on-the-hub","sections":[{"title":"Get a dataset","local":"get-a-dataset","sections":[],"depth":2},{"title":"Read dataset with Pandas","local":"read-dataset-with-pandas","sections":[],"depth":2},{"title":"Calculate mean code length by time complexity","local":"calculate-mean-code-length-by-time-complexity","sections":[],"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/2.0de562c0.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/DocNotebookDropdown.cb669ef3.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":"Analyze a dataset on the Hub","local":"analyze-a-dataset-on-the-hub","sections":[{"title":"Get a dataset","local":"get-a-dataset","sections":[],"depth":2},{"title":"Read dataset with Pandas","local":"read-dataset-with-pandas","sections":[],"depth":2},{"title":"Calculate mean code length by time complexity","local":"calculate-mean-code-length-by-time-complexity","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 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> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button> </div> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button> </div></div> <h1 class="relative group"><a id="analyze-a-dataset-on-the-hub" 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="#analyze-a-dataset-on-the-hub"><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>Analyze a dataset on the Hub</span></h1> <p data-svelte-h="svelte-1azbnlv">In the Quickstart, you were introduced to various endpoints for interacting with datasets on the Hub. One of the most useful ones is the <code>/parquet</code> endpoint, which allows you to get a dataset stored on the Hub and analyze it. This is a great way to explore the dataset, and get a better understanding of it’s contents.</p> <p data-svelte-h="svelte-ex80rz">To demonstrate, this guide will show you an end-to-end example of how to retrieve a dataset from the Hub and do some basic data analysis with the Pandas library.</p> <h2 class="relative group"><a id="get-a-dataset" 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="#get-a-dataset"><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>Get a dataset</span></h2> <p data-svelte-h="svelte-4xu1ut">The <a href="https://huggingface.co/datasets" rel="nofollow">Hub</a> is home to more than 200,000 datasets across a wide variety of tasks, sizes, and languages. For this example, you’ll use the <a href="https://huggingface.co/datasets/codeparrot/codecomplex" rel="nofollow"><code>codeparrot/codecomplex</code></a> dataset, but feel free to explore and find another dataset that interests you! The dataset contains Java code from programming competitions, and the time complexity of the code is labeled by a group of algorithm experts.</p> <p data-svelte-h="svelte-nzg195">Let’s say you’re interested in the average length of the submitted code as it relates to the time complexity. Here’s how you can get started.</p> <p data-svelte-h="svelte-1e6p8nz">Use the <code>/parquet</code> endpoint to convert the dataset to a Parquet file and return the URL to it:</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
	API_URL = <span class="hljs-string">"https://datasets-server.huggingface.co/parquet?dataset=codeparrot/codecomplex"</span>
	<span class="hljs-keyword">def</span> <span class="hljs-title function_">query</span>():
	response = requests.get(API_URL)
	<span class="hljs-keyword">return</span> response.json()
	data = query()<!-- HTML_TAG_END --></pre></div> </div> <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">"parquet_files"</span><span class="hljs-punctuation">:</span>
	<span class="hljs-punctuation">[</span>
	<span class="hljs-punctuation">{</span><span class="hljs-attr">"dataset"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"codeparrot/codecomplex"</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">"config"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"default"</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">"split"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"train"</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">"url"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"https://huggingface.co/datasets/codeparrot/codecomplex/resolve/refs%2Fconvert%2Fparquet/default/train/0000.parquet"</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">"filename"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"0000.parquet"</span><span class="hljs-punctuation">,</span> <span class="hljs-attr">"size"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">4115908</span><span class="hljs-punctuation">}</span>
	<span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"pending"</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">"failed"</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="read-dataset-with-pandas" 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="#read-dataset-with-pandas"><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>Read dataset with Pandas</span></h2> <p data-svelte-h="svelte-10uozo5">With the URL, you can read the Parquet file into a Pandas DataFrame:</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">import</span> pandas <span class="hljs-keyword">as</span> pd

	url = <span class="hljs-string">"https://huggingface.co/datasets/codeparrot/codecomplex/resolve/refs%2Fconvert%2Fparquet/default/train/0000.parquet"</span>
	df = pd.read_parquet(url)
	df.head(<span class="hljs-number">5</span>)<!-- HTML_TAG_END --></pre></div> <table data-svelte-h="svelte-lqg1es"><thead><tr><th align="right">src</th> <th align="right">complexity</th> <th align="right">problem</th> <th align="right">from</th></tr></thead> <tbody><tr><td align="right">import java.io.*;\nimport java.math.BigInteger…</td> <td align="right">quadratic</td> <td align="right">1179_B. Tolik and His Uncle</td> <td align="right">CODEFORCES</td></tr> <tr><td align="right">import java.util.Scanner;\n \npublic class pil…</td> <td align="right">linear</td> <td align="right">1197_B. Pillars</td> <td align="right">CODEFORCES</td></tr> <tr><td align="right">import java.io.BufferedReader;\nimport java.io…</td> <td align="right">linear</td> <td align="right">1059_C. Sequence Transformation</td> <td align="right">CODEFORCES</td></tr> <tr><td align="right">import java.util.<em>;\n\nimport java.io.</em>;\npubl…</td> <td align="right">linear</td> <td align="right">1011_A. Stages</td> <td align="right">CODEFORCES</td></tr> <tr><td align="right">import java.io.OutputStream;\nimport java.io.I…</td> <td align="right">linear</td> <td align="right">1190_C. Tokitsukaze and Duel</td> <td align="right">CODEFORCES</td></tr></tbody></table> <h2 class="relative group"><a id="calculate-mean-code-length-by-time-complexity" 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="#calculate-mean-code-length-by-time-complexity"><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>Calculate mean code length by time complexity</span></h2> <p data-svelte-h="svelte-eoewpk">Pandas is a powerful library for data analysis; group the dataset by time complexity, apply a function to calculate the average length of the code snippet, and plot the results:</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 -->df.groupby(<span class="hljs-string">'complexity'</span>)[<span class="hljs-string">'src'</span>].apply(<span class="hljs-keyword">lambda</span> x: x.<span class="hljs-built_in">str</span>.<span class="hljs-built_in">len</span>().mean()).sort_values(ascending=<span class="hljs-literal">False</span>).plot.barh(color=<span class="hljs-string">"orange"</span>)<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-3dvwc"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets-server/codecomplex.png"></div> <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/analyze_data.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, 2],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 26 kB
Xet hash:: 61b8c5c36bdaef0e50c1adf823a77bddbffc823df2ccddc6fe0e139763049f10

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