import{s as de,n as we,o as Te}from"../chunks/scheduler.7da89386.js";import{S as fe,i as he,g as p,s as a,r as c,A as be,h as r,f as s,c as n,j as ue,u as m,x as o,k as Me,y as je,a as l,v as y,d as J,t as u,w as M}from"../chunks/index.20910acc.js";import{C as _}from"../chunks/CodeBlock.143bd81e.js";import{H as Ue,E as We}from"../chunks/getInferenceSnippets.fc2ce523.js";function Ie(ae){let i,Y,V,R,d,F,w,ne="To run the scikit-learn examples make sure you have installed the following library:",H,T,z,f,pe='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>.',G,h,re="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.",x,b,Q,j,ie='Load data from <a href="https://www.openml.org/d/40945" rel="nofollow">https://www.openml.org/d/40945</a>:',E,U,S,W,ce="Alternatively X and y can be obtained directly from the frame attribute:",q,I,A,Z,me="We create the preprocessing pipelines for both numeric and categorical data. Note that pclass could either be treated as a categorical or numeric feature.",L,k,P,$,oe="Append classifier to preprocessing pipeline. Now we have a full prediction pipeline.",D,B,K,X,ye="As <code>Evaluate</code> metrics use lists as inputs for references and predictions, we need to convert them to Python lists.",O,g,ee,v,Je="You can use any suitable <code>evaluate</code> metric with the estimators as long as they are compatible with the task and predictions.",te,C,se,N,le;return d=new Ue({props:{title:"Scikit-Learn",local:"scikit-learn",headingTag:"h1"}}),T=new _({props:{code:"cGlwJTIwaW5zdGFsbCUyMC1VJTIwc2Npa2l0LWxlYXJu",highlighted:"pip install -U scikit-learn",wrap:!1}}),b=new _({props:{code:"aW1wb3J0JTIwbnVtcHklMjBhcyUyMG5wJTBBbnAucmFuZG9tLnNlZWQoMCklMEFpbXBvcnQlMjBldmFsdWF0ZSUwQWZyb20lMjBza2xlYXJuLmNvbXBvc2UlMjBpbXBvcnQlMjBDb2x1bW5UcmFuc2Zvcm1lciUwQWZyb20lMjBza2xlYXJuLmRhdGFzZXRzJTIwaW1wb3J0JTIwZmV0Y2hfb3Blbm1sJTBBZnJvbSUyMHNrbGVhcm4ucGlwZWxpbmUlMjBpbXBvcnQlMjBQaXBlbGluZSUwQWZyb20lMjBza2xlYXJuLmltcHV0ZSUyMGltcG9ydCUyMFNpbXBsZUltcHV0ZXIlMEFmcm9tJTIwc2tsZWFybi5wcmVwcm9jZXNzaW5nJTIwaW1wb3J0JTIwU3RhbmRhcmRTY2FsZXIlMkMlMjBPbmVIb3RFbmNvZGVyJTBBZnJvbSUyMHNrbGVhcm4ubGluZWFyX21vZGVsJTIwaW1wb3J0JTIwTG9naXN0aWNSZWdyZXNzaW9uJTBBZnJvbSUyMHNrbGVhcm4ubW9kZWxfc2VsZWN0aW9uJTIwaW1wb3J0JTIwdHJhaW5fdGVzdF9zcGxpdA==",highlighted:`<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`,wrap:!1}}),U=new _({props:{code:"WCUyQyUyMHklMjAlM0QlMjBmZXRjaF9vcGVubWwoJTIydGl0YW5pYyUyMiUyQyUyMHZlcnNpb24lM0QxJTJDJTIwYXNfZnJhbWUlM0RUcnVlJTJDJTIwcmV0dXJuX1hfeSUzRFRydWUp",highlighted:'X, y = fetch_openml(<span class="hljs-string">&quot;titanic&quot;</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>)',wrap:!1}}),I=new _({props:{code:"WCUyMCUzRCUyMHRpdGFuaWMuZnJhbWUuZHJvcCgnc3Vydml2ZWQnJTJDJTIwYXhpcyUzRDEpJTBBeSUyMCUzRCUyMHRpdGFuaWMuZnJhbWUlNUInc3Vydml2ZWQnJTVE",highlighted:`X = titanic.frame.drop(<span class="hljs-string">&#x27;survived&#x27;</span>, axis=<span class="hljs-number">1</span>)
y = titanic.frame[<span class="hljs-string">&#x27;survived&#x27;</span>]`,wrap:!1}}),k=new _({props:{code:"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",highlighted:`numeric_features = [<span class="hljs-string">&quot;age&quot;</span>, <span class="hljs-string">&quot;fare&quot;</span>]
numeric_transformer = Pipeline(
    steps=[(<span class="hljs-string">&quot;imputer&quot;</span>, SimpleImputer(strategy=<span class="hljs-string">&quot;median&quot;</span>)), (<span class="hljs-string">&quot;scaler&quot;</span>, StandardScaler())]
)

categorical_features = [<span class="hljs-string">&quot;embarked&quot;</span>, <span class="hljs-string">&quot;sex&quot;</span>, <span class="hljs-string">&quot;pclass&quot;</span>]
categorical_transformer = OneHotEncoder(handle_unknown=<span class="hljs-string">&quot;ignore&quot;</span>)

preprocessor = ColumnTransformer(
    transformers=[
        (<span class="hljs-string">&quot;num&quot;</span>, numeric_transformer, numeric_features),
        (<span class="hljs-string">&quot;cat&quot;</span>, categorical_transformer, categorical_features),
    ]
)`,wrap:!1}}),B=new _({props:{code:"Y2xmJTIwJTNEJTIwUGlwZWxpbmUoJTBBJTIwJTIwJTIwJTIwc3RlcHMlM0QlNUIoJTIycHJlcHJvY2Vzc29yJTIyJTJDJTIwcHJlcHJvY2Vzc29yKSUyQyUyMCglMjJjbGFzc2lmaWVyJTIyJTJDJTIwTG9naXN0aWNSZWdyZXNzaW9uKCkpJTVEJTBBKSUwQSUwQVhfdHJhaW4lMkMlMjBYX3Rlc3QlMkMlMjB5X3RyYWluJTJDJTIweV90ZXN0JTIwJTNEJTIwdHJhaW5fdGVzdF9zcGxpdChYJTJDJTIweSUyQyUyMHRlc3Rfc2l6ZSUzRDAuMiUyQyUyMHJhbmRvbV9zdGF0ZSUzRDApJTBBJTBBY2xmLmZpdChYX3RyYWluJTJDJTIweV90cmFpbiklMEF5X3ByZWQlMjAlM0QlMjBjbGYucHJlZGljdChYX3Rlc3Qp",highlighted:`clf = Pipeline(
    steps=[(<span class="hljs-string">&quot;preprocessor&quot;</span>, preprocessor), (<span class="hljs-string">&quot;classifier&quot;</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)`,wrap:!1}}),g=new _({props:{code:"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",highlighted:`<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">&quot;accuracy&quot;</span>)
accuracy = accuracy_metric.compute(references=y_test, predictions=y_pred)
<span class="hljs-built_in">print</span>(<span class="hljs-string">&quot;Accuracy:&quot;</span>, accuracy)
<span class="hljs-comment"># Accuracy: 0.79</span>`,wrap:!1}}),C=new We({props:{source:"https://github.com/huggingface/evaluate/blob/main/docs/source/sklearn_integrations.mdx"}}),{c(){i=p("meta"),Y=a(),V=p("p"),R=a(),c(d.$$.fragment),F=a(),w=p("p"),w.textContent=ne,H=a(),c(T.$$.fragment),z=a(),f=p("p"),f.innerHTML=pe,G=a(),h=p("p"),h.innerHTML=re,x=a(),c(b.$$.fragment),Q=a(),j=p("p"),j.innerHTML=ie,E=a(),c(U.$$.fragment),S=a(),W=p("p"),W.textContent=ce,q=a(),c(I.$$.fragment),A=a(),Z=p("p"),Z.textContent=me,L=a(),c(k.$$.fragment),P=a(),$=p("p"),$.textContent=oe,D=a(),c(B.$$.fragment),K=a(),X=p("p"),X.innerHTML=ye,O=a(),c(g.$$.fragment),ee=a(),v=p("p"),v.innerHTML=Je,te=a(),c(C.$$.fragment),se=a(),N=p("p"),this.h()},l(e){const t=be("svelte-u9bgzb",document.head);i=r(t,"META",{name:!0,content:!0}),t.forEach(s),Y=n(e),V=r(e,"P",{}),ue(V).forEach(s),R=n(e),m(d.$$.fragment,e),F=n(e),w=r(e,"P",{"data-svelte-h":!0}),o(w)!=="svelte-pb1681"&&(w.textContent=ne),H=n(e),m(T.$$.fragment,e),z=n(e),f=r(e,"P",{"data-svelte-h":!0}),o(f)!=="svelte-k0enqt"&&(f.innerHTML=pe),G=n(e),h=r(e,"P",{"data-svelte-h":!0}),o(h)!=="svelte-13ps3um"&&(h.innerHTML=re),x=n(e),m(b.$$.fragment,e),Q=n(e),j=r(e,"P",{"data-svelte-h":!0}),o(j)!=="svelte-1po732b"&&(j.innerHTML=ie),E=n(e),m(U.$$.fragment,e),S=n(e),W=r(e,"P",{"data-svelte-h":!0}),o(W)!=="svelte-mki1gd"&&(W.textContent=ce),q=n(e),m(I.$$.fragment,e),A=n(e),Z=r(e,"P",{"data-svelte-h":!0}),o(Z)!=="svelte-1vob52e"&&(Z.textContent=me),L=n(e),m(k.$$.fragment,e),P=n(e),$=r(e,"P",{"data-svelte-h":!0}),o($)!=="svelte-4wccpt"&&($.textContent=oe),D=n(e),m(B.$$.fragment,e),K=n(e),X=r(e,"P",{"data-svelte-h":!0}),o(X)!=="svelte-4ry0to"&&(X.innerHTML=ye),O=n(e),m(g.$$.fragment,e),ee=n(e),v=r(e,"P",{"data-svelte-h":!0}),o(v)!=="svelte-1lzytmq"&&(v.innerHTML=Je),te=n(e),m(C.$$.fragment,e),se=n(e),N=r(e,"P",{}),ue(N).forEach(s),this.h()},h(){Me(i,"name","hf:doc:metadata"),Me(i,"content",Ze)},m(e,t){je(document.head,i),l(e,Y,t),l(e,V,t),l(e,R,t),y(d,e,t),l(e,F,t),l(e,w,t),l(e,H,t),y(T,e,t),l(e,z,t),l(e,f,t),l(e,G,t),l(e,h,t),l(e,x,t),y(b,e,t),l(e,Q,t),l(e,j,t),l(e,E,t),y(U,e,t),l(e,S,t),l(e,W,t),l(e,q,t),y(I,e,t),l(e,A,t),l(e,Z,t),l(e,L,t),y(k,e,t),l(e,P,t),l(e,$,t),l(e,D,t),y(B,e,t),l(e,K,t),l(e,X,t),l(e,O,t),y(g,e,t),l(e,ee,t),l(e,v,t),l(e,te,t),y(C,e,t),l(e,se,t),l(e,N,t),le=!0},p:we,i(e){le||(J(d.$$.fragment,e),J(T.$$.fragment,e),J(b.$$.fragment,e),J(U.$$.fragment,e),J(I.$$.fragment,e),J(k.$$.fragment,e),J(B.$$.fragment,e),J(g.$$.fragment,e),J(C.$$.fragment,e),le=!0)},o(e){u(d.$$.fragment,e),u(T.$$.fragment,e),u(b.$$.fragment,e),u(U.$$.fragment,e),u(I.$$.fragment,e),u(k.$$.fragment,e),u(B.$$.fragment,e),u(g.$$.fragment,e),u(C.$$.fragment,e),le=!1},d(e){e&&(s(Y),s(V),s(R),s(F),s(w),s(H),s(z),s(f),s(G),s(h),s(x),s(Q),s(j),s(E),s(S),s(W),s(q),s(A),s(Z),s(L),s(P),s($),s(D),s(K),s(X),s(O),s(ee),s(v),s(te),s(se),s(N)),s(i),M(d,e),M(T,e),M(b,e),M(U,e),M(I,e),M(k,e),M(B,e),M(g,e),M(C,e)}}}const Ze='{"title":"Scikit-Learn","local":"scikit-learn","sections":[],"depth":1}';function ke(ae){return Te(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ve extends fe{constructor(i){super(),he(this,i,ke,Ie,de,{})}}export{ve as component};