autotrain/pr_749/en/tabular_params.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Tabular Parameters&quot;,&quot;local&quot;:&quot;tabular-parameters&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/autotrain/pr_749/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/entry/start.b4f8a0ef.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/chunks/scheduler.0219f8bd.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/chunks/singletons.74a96c49.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/chunks/paths.5815e531.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/entry/app.4f18d4a0.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/chunks/index.f61edf3b.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/nodes/0.3ba41ccf.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/nodes/27.ba7b6d23.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/chunks/CodeBlock.38e566ae.js">
		<link rel="modulepreload" href="/docs/autotrain/pr_749/en/_app/immutable/chunks/EditOnGithub.48fa589f.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Tabular Parameters&quot;,&quot;local&quot;:&quot;tabular-parameters&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="tabular-parameters" 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="#tabular-parameters"><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>Tabular Parameters</span></h1> <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-comment">--batch-size BATCH_SIZE</span>
                    Training batch size <span class="hljs-keyword">to</span> <span class="hljs-keyword">use</span>
<span class="hljs-comment">--seed SEED           Random seed for reproducibility</span>
<span class="hljs-comment">--target-columns TARGET_COLUMNS</span>
                    Specify the names <span class="hljs-keyword">of</span> the target <span class="hljs-keyword">or</span> <span class="hljs-keyword">label</span> columns separated by commas <span class="hljs-keyword">if</span> multiple. These columns are what the model will
                    predict. Required <span class="hljs-keyword">for</span> defining the output <span class="hljs-keyword">of</span> the model.
<span class="hljs-comment">--categorical-columns CATEGORICAL_COLUMNS</span>
                    List the names <span class="hljs-keyword">of</span> columns that contain categorical data, useful <span class="hljs-keyword">for</span> models that need explicit handling <span class="hljs-keyword">of</span> such data.
                    Categorical data <span class="hljs-keyword">is</span> typically processed differently from numerical data, such as through encoding. <span class="hljs-keyword">If</span> <span class="hljs-keyword">not</span> specified, the
                    model will infer the data <span class="hljs-keyword">type</span>.
<span class="hljs-comment">--numerical-columns NUMERICAL_COLUMNS</span>
                    Identify columns that contain numerical data. Proper specification helps <span class="hljs-keyword">in</span> applying appropriate scaling <span class="hljs-keyword">and</span> normalization
                    techniques, which can significantly impact model performance. <span class="hljs-keyword">If</span> <span class="hljs-keyword">not</span> specified, the model will infer the data <span class="hljs-keyword">type</span>.
<span class="hljs-comment">--id-column ID_COLUMN</span>
                    Specify the column name that uniquely identifies each row <span class="hljs-keyword">in</span> the dataset. This <span class="hljs-keyword">is</span> critical <span class="hljs-keyword">for</span> tracking samples through the
                    model pipeline <span class="hljs-keyword">and</span> <span class="hljs-keyword">is</span> often excluded from model training. Required field.
<span class="hljs-comment">--task {classification,regression}</span>
                    Define the <span class="hljs-keyword">type</span> <span class="hljs-keyword">of</span> machine learning task, such as <span class="hljs-symbol">&#x27;classification</span>&#x27;, <span class="hljs-symbol">&#x27;regression</span>&#x27;. This <span class="hljs-keyword">parameter</span> determines the model<span class="hljs-symbol">&#x27;s</span>
                    <span class="hljs-keyword">architecture</span> <span class="hljs-keyword">and</span> the loss <span class="hljs-keyword">function</span> <span class="hljs-keyword">to</span> <span class="hljs-keyword">use</span>. Required <span class="hljs-keyword">to</span> properly configure the model.
<span class="hljs-comment">--num-trials NUM_TRIALS</span>
                    Set the number <span class="hljs-keyword">of</span> trials <span class="hljs-keyword">for</span> hyperparameter tuning <span class="hljs-keyword">or</span> model experimentation. More trials can lead <span class="hljs-keyword">to</span> better model
                    configurations but require more computational resources. <span class="hljs-keyword">Default</span> <span class="hljs-keyword">is</span> <span class="hljs-number">100</span> trials.
<span class="hljs-comment">--time-limit TIME_LIMIT</span>
                    mpose a <span class="hljs-built_in">time</span> limit (<span class="hljs-keyword">in</span> seconds) <span class="hljs-keyword">for</span> training <span class="hljs-keyword">or</span> searching <span class="hljs-keyword">for</span> the best model <span class="hljs-keyword">configuration</span>. This helps manage resource
                    allocation <span class="hljs-keyword">and</span> ensures the <span class="hljs-keyword">process</span> does <span class="hljs-keyword">not</span> exceed available computational budgets. The <span class="hljs-keyword">default</span> <span class="hljs-keyword">is</span> <span class="hljs-number">3600</span> seconds (<span class="hljs-number">1</span> hour).
<span class="hljs-comment">--categorical-imputer {most_frequent,None}</span>
                    <span class="hljs-keyword">Select</span> the method <span class="hljs-keyword">or</span> strategy <span class="hljs-keyword">to</span> impute missing values <span class="hljs-keyword">in</span> categorical columns. Options might include <span class="hljs-symbol">&#x27;most_frequent</span>&#x27;,
                    <span class="hljs-symbol">&#x27;None</span>&#x27;. Correct imputation can prevent biases <span class="hljs-keyword">and</span> improve model accuracy.
<span class="hljs-comment">--numerical-imputer {mean,median,None}</span>
                    Choose the imputation strategy <span class="hljs-keyword">for</span> missing values <span class="hljs-keyword">in</span> numerical columns. Common strategies include <span class="hljs-symbol">&#x27;mean</span>&#x27;, &amp; <span class="hljs-symbol">&#x27;median</span>&#x27;.
                    Accurate imputation <span class="hljs-keyword">is</span> vital <span class="hljs-keyword">for</span> maintaining the integrity <span class="hljs-keyword">of</span> numerical data.
<span class="hljs-comment">--numeric-scaler {standard,minmax,normal,robust}</span>
                    Determine the <span class="hljs-keyword">type</span> <span class="hljs-keyword">of</span> scaling <span class="hljs-keyword">to</span> apply <span class="hljs-keyword">to</span> numerical data. Examples include <span class="hljs-symbol">&#x27;standard</span>&#x27; (zero mean <span class="hljs-keyword">and</span> unit variance), <span class="hljs-symbol">&#x27;min</span>-
                    max&#x27; (scaled between given <span class="hljs-keyword">range</span>), etc. Scaling <span class="hljs-keyword">is</span> essential <span class="hljs-keyword">for</span> many algorithms <span class="hljs-keyword">to</span> perform optimally<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/autotrain-advanced/blob/main/docs/source/tabular_params.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_ewvlbq = {
						assets: "/docs/autotrain/pr_749/en",
						base: "/docs/autotrain/pr_749/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/autotrain/pr_749/en/_app/immutable/entry/start.b4f8a0ef.js"),
						import("/docs/autotrain/pr_749/en/_app/immutable/entry/app.4f18d4a0.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 27],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>