{"id":15869,"date":"2022-04-24T10:50:33","date_gmt":"2022-04-24T09:50:33","guid":{"rendered":"https:\/\/complex-systems-ai.com\/?page_id=15869"},"modified":"2022-04-24T11:22:10","modified_gmt":"2022-04-24T10:22:10","slug":"pipeline-pour-la-classification","status":"publish","type":"page","link":"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/","title":{"rendered":"Tuber\u00eda de clasificaci\u00f3n"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"15869\" class=\"elementor elementor-15869\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-a4c14d9 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"a4c14d9\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-33 elementor-top-column elementor-element elementor-element-6cd06c5\" data-id=\"6cd06c5\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-04c6e15 elementor-align-justify elementor-widget elementor-widget-button\" data-id=\"04c6e15\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/complex-systems-ai.com\/analyse-des-donnees\/\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Analyse des donn\u00e9es<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-33 elementor-top-column elementor-element elementor-element-e1d5405\" data-id=\"e1d5405\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-62267a4 elementor-align-justify elementor-widget elementor-widget-button\" data-id=\"62267a4\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/complex-systems-ai.com\/\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Page d'accueil<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-33 elementor-top-column elementor-element elementor-element-a9055e4\" data-id=\"a9055e4\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-42a7dfd elementor-align-justify elementor-widget elementor-widget-button\" data-id=\"42a7dfd\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/en.wikipedia.org\/wiki\/Data_analysis\" target=\"_blank\" rel=\"noopener\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Wiki<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-c3c46c0 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"c3c46c0\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-b39589e\" data-id=\"b39589e\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-9d7183d elementor-widget elementor-widget-text-editor\" data-id=\"9d7183d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Cette page pr\u00e9sente un pipeline pour la classification. C&rsquo;est \u00e0 dire le suivi d&rsquo;un processus de l&rsquo;exploration des donn\u00e9es \u00e0 la classification en passant par les mod\u00e8les d&rsquo;\u00e9valuation.<\/p><p><img decoding=\"async\" class=\"aligncenter wp-image-11096 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2020\/09\/cropped-Capture.png\" alt=\"pipeline pour la classification\" width=\"97\" height=\"97\" title=\"\"><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-0e4aba2 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"0e4aba2\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-d95a38a\" data-id=\"d95a38a\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6bf4d17 elementor-widget elementor-widget-heading\" data-id=\"6bf4d17\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_2 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Contenus<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Alternar tabla de contenidos\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Survol-de-la-pipeline-pour-la-classification\" >Survol de la pipeline pour la classification<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Regression-logistique\" >Regression logistique<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Arbre-de-decision\" >Arbre de d\u00e9cision<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Random-forest-foret-aleatoire\" >Random forest (for\u00eat al\u00e9atoire)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Machine-a-vecteurs-de-support-SVM\" >Machine \u00e0 vecteurs de support (SVM)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#k-plus-proche-voisin-kNN\" >k plus proche voisin (kNN)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Bayes-naif\" >Bayes na\u00eff<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Faire-la-pipeline-pour-la-classification\" >Faire la pipeline pour la classification<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Chargement-de-lensemble-de-donnees-et-apercu-des-donnees\" >Chargement de l&rsquo;ensemble de donn\u00e9es et aper\u00e7u des donn\u00e9es<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Analyse-exploratoire-des-donnees-EDA\" >Analyse exploratoire des donn\u00e9es (EDA)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Caracteristiques-categorielles-par-rapport-a-la-cible-%E2%80%93-Graphique-a-barres-groupees\" >Caract\u00e9ristiques cat\u00e9gorielles par rapport \u00e0 la cible &#8211; Graphique \u00e0 barres group\u00e9es<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Caracteristiques-numeriques-par-rapport-a-la-cible-%E2%80%93-Boite-a-moustaches\" >Caract\u00e9ristiques num\u00e9riques par rapport \u00e0 la cible &#8211; Bo\u00eete \u00e0 moustaches<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-13\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Separation-du-jeu-de-donnees\" >S\u00e9paration du jeu de donn\u00e9es<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-14\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Pipeline-pour-la-classification\" >Pipeline pour la classification<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-15\" href=\"https:\/\/complex-systems-ai.com\/es\/analisis-de-datos\/canalizacion-para-clasificacion\/#Evaluation-des-modeles\" >Evaluation des mod\u00e8les<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Survol-de-la-pipeline-pour-la-classification\"><\/span>Survol de la pipeline pour la classification<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-1d611a3 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"1d611a3\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-b3a5a8f\" data-id=\"b3a5a8f\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6f40c58 elementor-widget elementor-widget-text-editor\" data-id=\"6f40c58\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>L&rsquo;apprentissage supervis\u00e9 peut \u00eatre subdivis\u00e9 en algorithmes de classification et de <a href=\"https:\/\/complex-systems-ai.com\/es\/correlacion-y-regresiones\/transformacion-de-datos-y-regresion\/\">r\u00e9gression<\/a>. Le mod\u00e8le de classification identifie la cat\u00e9gorie \u00e0 laquelle appartient un objet, tandis que le mod\u00e8le de r\u00e9gression pr\u00e9dit une sortie continue.<\/p><p>Parfois, il existe une ligne ambigu\u00eb entre les algorithmes de classification et les algorithmes de r\u00e9gression. De nombreux algorithmes peuvent \u00eatre utilis\u00e9s \u00e0 la fois pour la classification et la r\u00e9gression, et la classification n&rsquo;est qu&rsquo;un mod\u00e8le de r\u00e9gression avec un seuil appliqu\u00e9. Lorsque le nombre est sup\u00e9rieur au seuil, il est class\u00e9 comme vrai tandis qu&rsquo;un nombre inf\u00e9rieur est class\u00e9 comme faux.<\/p><p>Dans cet article, nous discuterons des 6 meilleurs algorithmes d&rsquo;apprentissage automatique pour les probl\u00e8mes de classification, notamment : la r\u00e9gression logistique, l&rsquo;arbre de d\u00e9cision, la for\u00eat al\u00e9atoire, la machine \u00e0 vecteurs de support, le voisin le plus proche k et les baies na\u00efves. Voici la pipeline pour la classification.<\/p><p><img fetchpriority=\"high\" decoding=\"async\" class=\"aligncenter wp-image-15875 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628.png\" alt=\"\" width=\"771\" height=\"543\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628.png 771w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628-300x211.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628-768x541.png 768w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628-18x12.png 18w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628-120x85.png 120w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-115628-600x423.png 600w\" sizes=\"(max-width: 771px) 100vw, 771px\" \/><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-908fe8e elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"908fe8e\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-91d870e\" data-id=\"91d870e\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-eadf15d elementor-widget elementor-widget-heading\" data-id=\"eadf15d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Regression-logistique\"><\/span>Regression logistique<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-2967c55 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"2967c55\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-227ed2c\" data-id=\"227ed2c\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-eba8ebc elementor-widget elementor-widget-text-editor\" data-id=\"eba8ebc\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>La r\u00e9gression logistique utilise la fonction sigmo\u00efde ci-dessus pour renvoyer la probabilit\u00e9 d&rsquo;une \u00e9tiquette. Il est largement utilis\u00e9 lorsque le probl\u00e8me de classification est binaire, par exemple vrai ou faux, gagnant ou perdant, positif ou n\u00e9gatif, etc.<\/p><p>La fonction sigmo\u00efde g\u00e9n\u00e8re une sortie de probabilit\u00e9. Et en comparant la probabilit\u00e9 avec un seuil pr\u00e9d\u00e9fini, l&rsquo;objet est affect\u00e9 \u00e0 une \u00e9tiquette en cons\u00e9quence.<\/p><pre id=\"viewer-635c0\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>linear_model <span class=\"_3tKjk\">import<\/span> LogisticRegression\ndtc <span class=\"_3TgEz\">=<\/span> <span class=\"\">DecisionTreeClassifier<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">)<\/span>\ndtc<span class=\"_1zYnF\">.<\/span><span class=\"\">fit<\/span><span class=\"_1zYnF\">(<\/span>X_train<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">)<\/span>\ny_pred <span class=\"_3TgEz\">=<\/span> dtc<span class=\"_1zYnF\">.<\/span><span class=\"\">predict<\/span><span class=\"_1zYnF\">(<\/span>X_test<span class=\"_1zYnF\">)<\/span><\/span><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-fff343c elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"fff343c\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-f57470a\" data-id=\"f57470a\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-a522c95 elementor-widget elementor-widget-heading\" data-id=\"a522c95\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Arbre-de-decision\"><\/span>Arbre de d\u00e9cision<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-896fb80 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"896fb80\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-267c850\" data-id=\"267c850\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-42cbc1d elementor-widget elementor-widget-text-editor\" data-id=\"42cbc1d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p id=\"viewer-8iqci\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">L&rsquo;arbre de d\u00e9cision construit des branches d&rsquo;arbre dans une approche hi\u00e9rarchique et chaque branche peut \u00eatre consid\u00e9r\u00e9e comme une instruction if-else. Les branches se d\u00e9veloppent en partitionnant l&rsquo;ensemble de donn\u00e9es en sous-ensembles, en fonction des caract\u00e9ristiques les plus importantes.<\/p><pre id=\"viewer-d922c\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>tree <span class=\"_3tKjk\">import<\/span> DecisionTreeClassifier\nreg <span class=\"_3TgEz\">=<\/span> <span class=\"\">LogisticRegression<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">)<\/span>\nreg<span class=\"_1zYnF\">.<\/span><span class=\"\">fit<\/span><span class=\"_1zYnF\">(<\/span>X_train<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">)<\/span>\ny_pred <span class=\"_3TgEz\">=<\/span> reg<span class=\"_1zYnF\">.<\/span><span class=\"\">predict<\/span><span class=\"_1zYnF\">(<\/span>X_test<span class=\"_1zYnF\">)<\/span><\/span><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-e729c2b elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"e729c2b\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-183d2a0\" data-id=\"183d2a0\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6562c53 elementor-widget elementor-widget-heading\" data-id=\"6562c53\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Random-forest-foret-aleatoire\"><\/span>Random forest (for\u00eat al\u00e9atoire)<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-0c749c3 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"0c749c3\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-4adb926\" data-id=\"4adb926\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-4137ba0 elementor-widget elementor-widget-text-editor\" data-id=\"4137ba0\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p id=\"viewer-3df7r\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">Comme son nom l&rsquo;indique, la for\u00eat al\u00e9atoire est une collection d&rsquo;arbres de d\u00e9cision. Il s&rsquo;agit d&rsquo;un type courant de m\u00e9thodes d&rsquo;ensemble &#8211; qui agr\u00e8gent les r\u00e9sultats de plusieurs pr\u00e9dicteurs. La for\u00eat al\u00e9atoire utilise en outre une technique d&rsquo;ensachage qui permet \u00e0 chaque <a href=\"https:\/\/complex-systems-ai.com\/es\/teoria-de-grafos\/arboles-y-arboles\/\">arbre<\/a> d&rsquo;\u00eatre entra\u00een\u00e9 sur un \u00e9chantillonnage al\u00e9atoire de l&rsquo;ensemble de donn\u00e9es d&rsquo;origine et d&rsquo;obtenir le vote majoritaire des arbres. Compar\u00e9 \u00e0 l&rsquo;arbre de d\u00e9cision, il a une meilleure g\u00e9n\u00e9ralisation mais est moins interpr\u00e9table en raison du plus grand nombre de couches ajout\u00e9es au mod\u00e8le.<\/p><pre id=\"viewer-1qg0b\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>ensemble <span class=\"_3tKjk\">import<\/span> RandomForestClassifier\nrfc <span class=\"_3TgEz\">=<\/span> <span class=\"\">RandomForestClassifier<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">)<\/span>\nrfc<span class=\"_1zYnF\">.<\/span><span class=\"\">fit<\/span><span class=\"_1zYnF\">(<\/span>X_train<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">)<\/span>\ny_pred <span class=\"_3TgEz\">=<\/span> rfc<span class=\"_1zYnF\">.<\/span><span class=\"\">predict<\/span><span class=\"_1zYnF\">(<\/span>X_test<span class=\"_1zYnF\">)<\/span><\/span><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-46e7aeb elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"46e7aeb\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-540b769\" data-id=\"540b769\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-449122a elementor-widget elementor-widget-heading\" data-id=\"449122a\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Machine-a-vecteurs-de-support-SVM\"><\/span>Machine \u00e0 vecteurs de support (SVM)<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-ef4efa0 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"ef4efa0\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-fb97777\" data-id=\"fb97777\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6567a2e elementor-widget elementor-widget-text-editor\" data-id=\"6567a2e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p id=\"viewer-9svii\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">La machine \u00e0 vecteurs de support trouve le meilleur moyen de classer les donn\u00e9es en fonction de la position par rapport \u00e0 une fronti\u00e8re entre classe positive et classe n\u00e9gative. Cette fronti\u00e8re est connue sous le nom d&rsquo;hyperplan qui maximise la distance entre les points de donn\u00e9es de diff\u00e9rentes classes. Semblable \u00e0 l&rsquo;arbre de d\u00e9cision et \u00e0 la for\u00eat al\u00e9atoire, la machine \u00e0 vecteurs de support peut \u00eatre utilis\u00e9e \u00e0 la fois dans la classification et la r\u00e9gression, SVC (classificateur de vecteurs de support) est choisi pour le probl\u00e8me de classification.<\/p><pre id=\"viewer-1srj4\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>svm <span class=\"_3tKjk\">import<\/span> <span class=\"\">SVC<\/span>\nsvc <span class=\"_3TgEz\">=<\/span> <span class=\"\">SVC<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">)<\/span>\nsvc<span class=\"_1zYnF\">.<\/span><span class=\"\">fit<\/span><span class=\"_1zYnF\">(<\/span>X_train<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">)<\/span>\ny_pred <span class=\"_3TgEz\">=<\/span> svc<span class=\"_1zYnF\">.<\/span><span class=\"\">predict<\/span><span class=\"_1zYnF\">(<\/span>X_test<span class=\"_1zYnF\">)<\/span><\/span><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-902bbcd elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"902bbcd\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-6b8632c\" data-id=\"6b8632c\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-447e6b7 elementor-widget elementor-widget-heading\" data-id=\"447e6b7\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"k-plus-proche-voisin-kNN\"><\/span>k plus proche voisin (kNN)<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-fbe53de elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"fbe53de\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-951eec4\" data-id=\"951eec4\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-f5909d3 elementor-widget elementor-widget-text-editor\" data-id=\"f5909d3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p id=\"viewer-5s84s\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\">You can think of k nearest neighbour algorithm as representing each data point in a n dimensional space &#8211; which is defined by n features. And it calculates the distance between one point to another, then assign the label of unobserved data based on the labels of nearest observed data points.\u00a0<\/span><\/p><pre id=\"viewer-6hlau\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>neighbors <span class=\"_3tKjk\">import<\/span> KNeighborsClassifier\nknn <span class=\"_3TgEz\">=<\/span> <span class=\"\">KNeighborsClassifier<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">)<\/span>\nknn<span class=\"_1zYnF\">.<\/span><span class=\"\">fit<\/span><span class=\"_1zYnF\">(<\/span>X_train<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">)<\/span>\ny_pred <span class=\"_3TgEz\">=<\/span> knn<span class=\"_1zYnF\">.<\/span><span class=\"\">predict<\/span><span class=\"_1zYnF\">(<\/span>X_test<span class=\"_1zYnF\">)<\/span><\/span><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-eb8a416 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"eb8a416\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-0fcbe49\" data-id=\"0fcbe49\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-eb1b681 elementor-widget elementor-widget-heading\" data-id=\"eb1b681\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Bayes-naif\"><\/span>Bayes na\u00eff<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-b1b4d7d elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"b1b4d7d\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-e0d725c\" data-id=\"e0d725c\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-c8b9b93 elementor-widget elementor-widget-text-editor\" data-id=\"c8b9b93\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p id=\"viewer-6cn9c\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">Naive Bayes est bas\u00e9 sur le th\u00e9or\u00e8me de Bayes &#8211; une approche pour calculer la probabilit\u00e9 conditionnelle bas\u00e9e sur des connaissances ant\u00e9rieures et l&rsquo;hypoth\u00e8se na\u00efve selon laquelle chaque caract\u00e9ristique est ind\u00e9pendante l&rsquo;une de l&rsquo;autre. Le plus grand avantage de Naive Bayes est que, bien que la plupart des algorithmes d&rsquo;apprentissage automatique reposent sur une grande quantit\u00e9 de donn\u00e9es d&rsquo;entra\u00eenement, il fonctionne relativement bien m\u00eame lorsque la taille des donn\u00e9es d&rsquo;entra\u00eenement est petite. Gaussian Naive Bayes est un type de classificateur Naive Bayes qui suit la distribution normale.<\/p><pre id=\"viewer-46i7i\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>naive_bayes <span class=\"_3tKjk\">import<\/span> GaussianNB\ngnb <span class=\"_3TgEz\">=<\/span> <span class=\"\">KNeighborsClassifier<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">)<\/span>\ngnb<span class=\"_1zYnF\">.<\/span><span class=\"\">fit<\/span><span class=\"_1zYnF\">(<\/span>X_train<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">)<\/span>\ny_pred <span class=\"_3TgEz\">=<\/span> gnb<span class=\"_1zYnF\">.<\/span><span class=\"\">predict<\/span><span class=\"_1zYnF\">(<\/span>X_test<span class=\"_1zYnF\">)<\/span><\/span><\/pre>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-9dd97bc elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"9dd97bc\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-26c8381\" data-id=\"26c8381\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-608225b elementor-widget elementor-widget-heading\" data-id=\"608225b\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Faire-la-pipeline-pour-la-classification\"><\/span>Faire la pipeline pour la classification<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-84cca9a elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"84cca9a\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-fe58c49\" data-id=\"fe58c49\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-8041c9f elementor-widget elementor-widget-text-editor\" data-id=\"8041c9f\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<h3 id=\"viewer-d22o\" class=\"_3qMKZ _1j-51 _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"ez-toc-section\" id=\"Chargement-de-lensemble-de-donnees-et-apercu-des-donnees\"><\/span>Chargement de l&rsquo;ensemble de donn\u00e9es et aper\u00e7u des donn\u00e9es<span class=\"ez-toc-section-end\"><\/span><\/h3><p id=\"viewer-b9s5l\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">J&rsquo;ai choisi l&rsquo;ensemble de donn\u00e9es populaire Heart Disease UCI sur Kaggle pour pr\u00e9dire la pr\u00e9sence d&rsquo;une maladie cardiaque en fonction de plusieurs facteurs li\u00e9s \u00e0 la sant\u00e9. La premi\u00e8re \u00e9tape de la pipeline pour la classification est la compr\u00e9hension des donn\u00e9es.<\/p><p id=\"viewer-dma06\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">Utilisez df.info() pour avoir une vue r\u00e9sum\u00e9e de l&rsquo;ensemble de donn\u00e9es, y compris le type de donn\u00e9es, les donn\u00e9es manquantes et le nombre d&rsquo;enregistrements.<\/p><h3 id=\"viewer-7ndao\" class=\"_3qMKZ _1j-51 _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"ez-toc-section\" id=\"Analyse-exploratoire-des-donnees-EDA\"><\/span>Analyse exploratoire des donn\u00e9es (EDA)<span class=\"ez-toc-section-end\"><\/span><\/h3><p id=\"viewer-a3ib0\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">L&rsquo;histogramme, le diagramme \u00e0 barres group\u00e9es et le diagramme en bo\u00eete sont des techniques EDA appropri\u00e9es pour les algorithmes d&rsquo;apprentissage automatique de classification.<\/p><p id=\"viewer-bd4b4\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><strong>Analyse univari\u00e9e<\/strong><\/span><\/p><div id=\"viewer-30g0l\" class=\"_2vd5k JP7h-\"><div class=\"_3CWa- Dv9jC Dv9jC\"><div class=\"_2kEVY\" tabindex=\"0\" role=\"button\" data-hook=\"imageViewer\"><div class=\"_3WJnn\" aria-label=\"histogram\"><img decoding=\"async\" class=\"aligncenter wp-image-15876 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120807.png\" alt=\"\" width=\"740\" height=\"630\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120807.png 740w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120807-300x255.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120807-14x12.png 14w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120807-600x511.png 600w\" sizes=\"(max-width: 740px) 100vw, 740px\" \/><\/div><div class=\"\">\u00a0<\/div><\/div><\/div><\/div><p id=\"viewer-dd5nt\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">Pour effectuer une analyse univari\u00e9e, l&rsquo;histogramme est utilis\u00e9 pour toutes les caract\u00e9ristiques. En effet, toutes les entit\u00e9s ont \u00e9t\u00e9 encod\u00e9es en valeurs num\u00e9riques dans le jeu de donn\u00e9es. Cela nous fait gagner du temps pour l&rsquo;encodage cat\u00e9goriel qui se produit g\u00e9n\u00e9ralement pendant la phase d&rsquo;ing\u00e9nierie des fonctionnalit\u00e9s<\/p><h3 id=\"viewer-1b89i\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"ez-toc-section\" id=\"Caracteristiques-categorielles-par-rapport-a-la-cible-%E2%80%93-Graphique-a-barres-groupees\"><\/span>Caract\u00e9ristiques cat\u00e9gorielles par rapport \u00e0 la cible &#8211; Graphique \u00e0 barres group\u00e9es<span class=\"ez-toc-section-end\"><\/span><\/h3><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-15877 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120923.png\" alt=\"\" width=\"726\" height=\"523\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120923.png 726w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120923-300x216.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120923-18x12.png 18w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120923-120x85.png 120w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-120923-600x432.png 600w\" sizes=\"(max-width: 726px) 100vw, 726px\" \/><\/p><p id=\"viewer-52amf\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">Pour montrer comment la valeur cat\u00e9gorique p\u00e8se dans la d\u00e9termination de la valeur cible, le graphique \u00e0 barres group\u00e9es est une repr\u00e9sentation simple. Par exemple, sexe = 1 et sexe = 0 ont une distribution distincte de la valeur cible, ce qui indique qu&rsquo;il est susceptible de contribuer davantage \u00e0 la pr\u00e9diction de la cible. Au contraire, si la distribution cible est la m\u00eame quelles que soient les caract\u00e9ristiques cat\u00e9gorielles, cela signifie qu&rsquo;elles ne sont pas corr\u00e9l\u00e9es.<\/p><h3 id=\"viewer-1hoda\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"ez-toc-section\" id=\"Caracteristiques-numeriques-par-rapport-a-la-cible-%E2%80%93-Boite-a-moustaches\"><\/span>Caract\u00e9ristiques num\u00e9riques par rapport \u00e0 la cible &#8211; Bo\u00eete \u00e0 moustaches<span class=\"ez-toc-section-end\"><\/span><\/h3><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-15878 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121102.png\" alt=\"\" width=\"751\" height=\"623\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121102.png 751w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121102-300x249.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121102-14x12.png 14w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121102-600x498.png 600w\" sizes=\"(max-width: 751px) 100vw, 751px\" \/><\/p><p id=\"viewer-7h188\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">La bo\u00eete \u00e0 moustaches montre comment les valeurs des caract\u00e9ristiques num\u00e9riques varient selon les groupes cibles. Par exemple, nous pouvons dire que \u00ab\u00a0oldpeak\u00a0\u00bb a une diff\u00e9rence distincte lorsque la cible est 0 par rapport \u00e0 la cible est 1, ce qui sugg\u00e8re qu&rsquo;il s&rsquo;agit d&rsquo;un pr\u00e9dicteur important. Cependant, \u00abtrestbps\u00bb et \u00abchol\u00bb semblent \u00eatre moins remarquables, car la distribution de la bo\u00eete \u00e0 moustaches est similaire entre les groupes cibles.<\/p><h3 id=\"viewer-3oh4v\" class=\"_3qMKZ _1j-51 _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"ez-toc-section\" id=\"Separation-du-jeu-de-donnees\"><\/span><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><strong>S\u00e9paration du jeu de donn\u00e9es<\/strong><\/span><span class=\"ez-toc-section-end\"><\/span><\/h3><p id=\"viewer-caooe\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">L&rsquo;algorithme de classification rel\u00e8ve de la cat\u00e9gorie de l&rsquo;apprentissage supervis\u00e9, de sorte que l&rsquo;ensemble de donn\u00e9es doit \u00eatre divis\u00e9 en un sous-ensemble pour la formation et un sous-ensemble pour les tests (parfois \u00e9galement un ensemble de validation). Le mod\u00e8le est entra\u00een\u00e9 sur l&rsquo;ensemble d&rsquo;apprentissage, puis examin\u00e9 \u00e0 l&rsquo;aide de l&rsquo;ensemble de test.<\/p><pre id=\"viewer-d9ca8\" class=\"_3M8UJ _3Dd1B md9lk _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\"><span class=\"_3tKjk\">from<\/span> sklearn<span class=\"_1zYnF\">.<\/span>model_selection <span class=\"_3tKjk\">import<\/span> train_test_split\n<span class=\"_3tKjk\">from<\/span> sklearn <span class=\"_3tKjk\">import<\/span> preprocessing\n\n<span class=\"\">X<\/span> <span class=\"_3TgEz\">=<\/span> df<span class=\"_1zYnF\">.<\/span><span class=\"\">drop<\/span><span class=\"_1zYnF\">(<\/span><span class=\"_1zYnF\">[<\/span><span class=\"_1SM9u\">'target'<\/span><span class=\"_1zYnF\">]<\/span><span class=\"_1zYnF\">,<\/span> axis<span class=\"_3TgEz\">=<\/span><span class=\"_2nB1v\">1<\/span><span class=\"_1zYnF\">)<\/span>\ny <span class=\"_3TgEz\">=<\/span> df<span class=\"_1zYnF\">[<\/span><span class=\"_1SM9u\">\"target\"<\/span><span class=\"_1zYnF\">]<\/span>\n\nX_train<span class=\"_1zYnF\">,<\/span> X_test<span class=\"_1zYnF\">,<\/span> y_train<span class=\"_1zYnF\">,<\/span> y_test <span class=\"_3TgEz\">=<\/span> <span class=\"\">train_test_split<\/span><span class=\"_1zYnF\">(<\/span><span class=\"\">X<\/span><span class=\"_1zYnF\">,<\/span> y<span class=\"_1zYnF\">,<\/span> test_size<span class=\"_3TgEz\">=<\/span><span class=\"_2nB1v\">0.33<\/span><span class=\"_1zYnF\">,<\/span> random_state<span class=\"_3TgEz\">=<\/span><span class=\"_2nB1v\">42<\/span><span class=\"_1zYnF\">)<\/span><\/span><\/pre><h3 id=\"viewer-2tu1p\" class=\"_3qMKZ _1j-51 _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\"><span class=\"ez-toc-section\" id=\"Pipeline-pour-la-classification\"><\/span>Pipeline pour la classification<span class=\"ez-toc-section-end\"><\/span><\/h3><p id=\"viewer-d23d9\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">Afin de cr\u00e9er un pipeline, j&rsquo;ajoute tous les 6 principaux algorithmes de classification mentionn\u00e9s ci-dessus dans la liste des mod\u00e8les et je les parcourrai plus tard pour former, tester, pr\u00e9dire et \u00e9valuer.<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-15879 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121300.png\" alt=\"\" width=\"482\" height=\"325\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121300.png 482w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121300-300x202.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121300-18x12.png 18w\" sizes=\"(max-width: 482px) 100vw, 482px\" \/><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-90f4479 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"90f4479\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-2556ff9\" data-id=\"2556ff9\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-59091fd elementor-widget elementor-widget-heading\" data-id=\"59091fd\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><span class=\"ez-toc-section\" id=\"Evaluation-des-modeles\"><\/span>Evaluation des mod\u00e8les<span class=\"ez-toc-section-end\"><\/span><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-6dc3484 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"6dc3484\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-2efd08a\" data-id=\"2efd08a\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-9daad3b elementor-widget elementor-widget-text-editor\" data-id=\"9daad3b\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Voici une explication abstraite des m\u00e9thodes d&rsquo;\u00e9valuation couramment utilis\u00e9es pour les mod\u00e8les de classification &#8211; pr\u00e9cision, ROC et AUC et matrice de confusion. La pipeline pour la classification comprend \u00e0 la fois le traitement des donn\u00e9es, les mod\u00e8les et leur \u00e9valuation.<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-15880 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121533.png\" alt=\"pipeline pour la classification\" width=\"736\" height=\"282\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121533.png 736w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121533-300x115.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121533-18x7.png 18w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121533-600x230.png 600w\" sizes=\"(max-width: 736px) 100vw, 736px\" \/><\/p><p>La pr\u00e9cision est l&rsquo;indicateur le plus simple de la performance du mod\u00e8le. Il mesure le pourcentage de pr\u00e9dictions exactes.<\/p><p>Le ROC est le graphique du taux de faux positifs par rapport au taux de vrais positifs \u00e0 diff\u00e9rents seuils de classification. AUC est la zone sous la courbe ROC, et une AUC plus \u00e9lev\u00e9e indique une meilleure performance du mod\u00e8le.<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-15881 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121639.png\" alt=\"pipeline pour la classification\" width=\"746\" height=\"282\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121639.png 746w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121639-300x113.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121639-18x7.png 18w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121639-600x227.png 600w\" sizes=\"(max-width: 746px) 100vw, 746px\" \/><\/p><p id=\"viewer-cm5eg\" class=\"mm8Nw _1j-51 iWv3d _1FoOD _3M0Fe aujbK iWv3d public-DraftStyleDefault-block-depth0 fixed-tab-size public-DraftStyleDefault-text-ltr\">La matrice de confusion indique les valeurs r\u00e9elles par rapport aux valeurs pr\u00e9dites et r\u00e9sume les valeurs vraies n\u00e9gatives, fausses positives, fausses n\u00e9gatives et vraies positives dans un format matriciel.<\/p><div data-hook=\"rcv-block103\">\u00a0<\/div><div id=\"viewer-510a8\" class=\"_2vd5k JP7h-\"><div class=\"_34Kbu\"><div class=\"ZZwd4\"><table class=\"_3S0Qj\"><colgroup> <col \/> <col \/><\/colgroup><thead><\/thead><tbody><tr><td class=\"_3c5-u\" colspan=\"1\" rowspan=\"1\" data-hook=\"table-plugin-cell\"><div class=\"_3iIc8 _3NvqW\"><div class=\"_1Rg3q _30RxK\"><div class=\"kvdbP _1O7aH\" dir=\"ltr\"><div class=\"_1hN1O erqrj _3sj65 n4Axb\"><p id=\"viewer-acjpx313t\" class=\"mm8Nw _1j-51 _1FoOD _3M0Fe public-DraftStyleDefault-block-depth0 public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\">\u200bTrue Negative<\/span><\/p><\/div><\/div><\/div><\/div><div class=\"\">\u00a0<\/div><\/td><td class=\"_3c5-u\" colspan=\"1\" rowspan=\"1\" data-hook=\"table-plugin-cell\"><div class=\"_3iIc8 _3NvqW\"><div class=\"_1Rg3q _30RxK\"><div class=\"kvdbP _1O7aH\" dir=\"ltr\"><div class=\"_1hN1O erqrj _3sj65 n4Axb\"><p id=\"viewer-wev04wur7\" class=\"mm8Nw _1j-51 _1FoOD _3M0Fe public-DraftStyleDefault-block-depth0 public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\">False Positive<\/span><\/p><\/div><\/div><\/div><\/div><div class=\"\">\u00a0<\/div><\/td><\/tr><tr><td class=\"_3c5-u\" colspan=\"1\" rowspan=\"1\" data-hook=\"table-plugin-cell\"><div class=\"_3iIc8 _3NvqW\"><div class=\"_1Rg3q _30RxK\"><div class=\"kvdbP _1O7aH\" dir=\"ltr\"><div class=\"_1hN1O erqrj _3sj65 n4Axb\"><p id=\"viewer-qmgnmk8uj\" class=\"mm8Nw _1j-51 _1FoOD _3M0Fe public-DraftStyleDefault-block-depth0 public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\">False Negative<\/span><\/p><\/div><\/div><\/div><\/div><div class=\"\">\u00a0<\/div><\/td><td class=\"_3c5-u\" colspan=\"1\" rowspan=\"1\" data-hook=\"table-plugin-cell\"><div class=\"_3iIc8 _3NvqW\"><div class=\"_1Rg3q _30RxK\"><div class=\"kvdbP _1O7aH\" dir=\"ltr\"><div class=\"_1hN1O erqrj _3sj65 n4Axb\"><p id=\"viewer-oihajdqzy\" class=\"mm8Nw _1j-51 _1FoOD _3M0Fe public-DraftStyleDefault-block-depth0 public-DraftStyleDefault-text-ltr\"><span class=\"_2PHJq public-DraftStyleDefault-ltr\">True Positive<\/span><\/p><\/div><\/div><\/div><\/div><div class=\"\">\u00a0<\/div><\/td><\/tr><\/tbody><\/table><\/div><\/div><\/div><div data-hook=\"rcv-block104\">Ensuite, nous pouvons utiliser seaborn pour visualiser la matrice de confusion dans une carte thermique.<\/div><div data-hook=\"rcv-block104\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-15882 size-full\" src=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121805.png\" alt=\"\" width=\"768\" height=\"622\" title=\"\" srcset=\"https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121805.png 768w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121805-300x243.png 300w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121805-15x12.png 15w, https:\/\/complex-systems-ai.com\/wp-content\/uploads\/2022\/04\/2022-04-24-121805-600x486.png 600w\" sizes=\"(max-width: 768px) 100vw, 768px\" \/><\/div><div data-hook=\"rcv-block104\"><p>Sur la base des trois m\u00e9thodes d&rsquo;\u00e9valuation ci-dessus, les for\u00eats al\u00e9atoires et les baies na\u00efves ont les meilleures performances alors que KNN ne se porte pas bien. Cependant, cela ne signifie pas que les for\u00eats al\u00e9atoires et les baies na\u00efves sont des algorithmes sup\u00e9rieurs. Nous pouvons seulement dire qu&rsquo;ils sont plus adapt\u00e9s \u00e0 cet ensemble de donn\u00e9es o\u00f9 la taille est relativement plus petite et les donn\u00e9es ne sont pas \u00e0 la m\u00eame \u00e9chelle.<\/p><p>Chaque <a href=\"https:\/\/complex-systems-ai.com\/es\/algoritmico\/\">algorithme<\/a> a sa propre pr\u00e9f\u00e9rence et n\u00e9cessite diff\u00e9rentes techniques de traitement des donn\u00e9es et d&rsquo;ing\u00e9nierie des caract\u00e9ristiques, par exemple KNN est sensible aux caract\u00e9ristiques \u00e0 diff\u00e9rentes \u00e9chelles et la multicolin\u00e9arit\u00e9 affecte le r\u00e9sultat de la r\u00e9gression logistique. Comprendre les caract\u00e9ristiques de chacun nous permet d&rsquo;\u00e9quilibrer le compromis et de s\u00e9lectionner le mod\u00e8le appropri\u00e9 en fonction de l&rsquo;ensemble de donn\u00e9es.<\/p><p>Ceci marque la fin de la pipeline pour la classification !<\/p><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>P\u00e1gina de inicio de Wiki de an\u00e1lisis de datos Esta p\u00e1gina presenta un conducto para la clasificaci\u00f3n. Es decir el seguimiento de un proceso de exploraci\u00f3n de datos\u2026 <\/p>","protected":false},"author":1,"featured_media":0,"parent":15503,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-15869","page","type-page","status-publish","hentry"],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/pages\/15869","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/comments?post=15869"}],"version-history":[{"count":3,"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/pages\/15869\/revisions"}],"predecessor-version":[{"id":15885,"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/pages\/15869\/revisions\/15885"}],"up":[{"embeddable":true,"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/pages\/15503"}],"wp:attachment":[{"href":"https:\/\/complex-systems-ai.com\/es\/wp-json\/wp\/v2\/media?parent=15869"}],"curies":[{"name":"gracias","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}