Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Scikit-Learn","local":"scikit-learn","sections":[],"depth":1}"> | |
| <link href="/docs/evaluate/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/entry/start.138f3e02.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/scheduler.5f3e6389.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/singletons.3420a244.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/paths.65ada1b9.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/entry/app.ad076786.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/preload-helper.0572feea.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/index.62df735e.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/nodes/0.11bd9b89.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/nodes/19.88c8eee5.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.e306bd5b.js"> | |
| <link rel="modulepreload" href="/docs/evaluate/main/en/_app/immutable/chunks/CodeBlock.dc1e8be0.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Scikit-Learn","local":"scikit-learn","sections":[],"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 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="scikit-learn" 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="#scikit-learn"><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>Scikit-Learn</span></h1> <p data-svelte-h="svelte-pb1681">To run the scikit-learn examples make sure you have installed the following library:</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 -->pip install -U scikit-learn<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-k0enqt">The metrics in <code>evaluate</code> can be easily integrated with an Scikit-Learn estimator or <a href="https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html#sklearn.pipeline.Pipeline" rel="nofollow">pipeline</a>.</p> <p data-svelte-h="svelte-13ps3um">However, these metrics require that we generate the predictions from the model. The predictions and labels from the estimators can be passed to <code>evaluate</code> mertics to compute the required values.</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> numpy <span class="hljs-keyword">as</span> np | |
| np.random.seed(<span class="hljs-number">0</span>) | |
| <span class="hljs-keyword">import</span> evaluate | |
| <span class="hljs-keyword">from</span> sklearn.compose <span class="hljs-keyword">import</span> ColumnTransformer | |
| <span class="hljs-keyword">from</span> sklearn.datasets <span class="hljs-keyword">import</span> fetch_openml | |
| <span class="hljs-keyword">from</span> sklearn.pipeline <span class="hljs-keyword">import</span> Pipeline | |
| <span class="hljs-keyword">from</span> sklearn.impute <span class="hljs-keyword">import</span> SimpleImputer | |
| <span class="hljs-keyword">from</span> sklearn.preprocessing <span class="hljs-keyword">import</span> StandardScaler, OneHotEncoder | |
| <span class="hljs-keyword">from</span> sklearn.linear_model <span class="hljs-keyword">import</span> LogisticRegression | |
| <span class="hljs-keyword">from</span> sklearn.model_selection <span class="hljs-keyword">import</span> train_test_split<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1po732b">Load data from <a href="https://www.openml.org/d/40945" rel="nofollow">https://www.openml.org/d/40945</a>:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->X, y = fetch_openml(<span class="hljs-string">"titanic"</span>, version=<span class="hljs-number">1</span>, as_frame=<span class="hljs-literal">True</span>, return_X_y=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-mki1gd">Alternatively X and y can be obtained directly from the frame attribute:</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 -->X = titanic.frame.drop(<span class="hljs-string">'survived'</span>, axis=<span class="hljs-number">1</span>) | |
| y = titanic.frame[<span class="hljs-string">'survived'</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1vob52e">We create the preprocessing pipelines for both numeric and categorical data. Note that pclass could either be treated as a categorical or numeric feature.</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 -->numeric_features = [<span class="hljs-string">"age"</span>, <span class="hljs-string">"fare"</span>] | |
| numeric_transformer = Pipeline( | |
| steps=[(<span class="hljs-string">"imputer"</span>, SimpleImputer(strategy=<span class="hljs-string">"median"</span>)), (<span class="hljs-string">"scaler"</span>, StandardScaler())] | |
| ) | |
| categorical_features = [<span class="hljs-string">"embarked"</span>, <span class="hljs-string">"sex"</span>, <span class="hljs-string">"pclass"</span>] | |
| categorical_transformer = OneHotEncoder(handle_unknown=<span class="hljs-string">"ignore"</span>) | |
| preprocessor = ColumnTransformer( | |
| transformers=[ | |
| (<span class="hljs-string">"num"</span>, numeric_transformer, numeric_features), | |
| (<span class="hljs-string">"cat"</span>, categorical_transformer, categorical_features), | |
| ] | |
| )<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-4wccpt">Append classifier to preprocessing pipeline. Now we have a full prediction pipeline.</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 -->clf = Pipeline( | |
| steps=[(<span class="hljs-string">"preprocessor"</span>, preprocessor), (<span class="hljs-string">"classifier"</span>, LogisticRegression())] | |
| ) | |
| X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=<span class="hljs-number">0.2</span>, random_state=<span class="hljs-number">0</span>) | |
| clf.fit(X_train, y_train) | |
| y_pred = clf.predict(X_test)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-4ry0to">As <code>Evaluate</code> metrics use lists as inputs for references and predictions, we need to convert them to Python lists.</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-comment"># Evaluate metrics accept lists as inputs for values of references and predictions</span> | |
| y_test = y_test.tolist() | |
| y_pred = y_pred.tolist() | |
| <span class="hljs-comment"># Accuracy</span> | |
| accuracy_metric = evaluate.load(<span class="hljs-string">"accuracy"</span>) | |
| accuracy = accuracy_metric.compute(references=y_test, predictions=y_pred) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">"Accuracy:"</span>, accuracy) | |
| <span class="hljs-comment"># Accuracy: 0.79</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1lzytmq">You can use any suitable <code>evaluate</code> metric with the estimators as long as they are compatible with the task and predictions.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/evaluate/blob/main/docs/source/sklearn_integrations.mdx" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_95ljrq = { | |
| assets: "/docs/evaluate/main/en", | |
| base: "/docs/evaluate/main/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/evaluate/main/en/_app/immutable/entry/start.138f3e02.js"), | |
| import("/docs/evaluate/main/en/_app/immutable/entry/app.ad076786.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 19], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 19.6 kB
- Xet hash:
- 35f9a2d32d7eb8baff9f67a36377003701b18a29088e569b26a088912b839402
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.