{"id":169,"date":"2022-05-16T17:56:16","date_gmt":"2022-05-16T15:56:16","guid":{"rendered":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/?p=169"},"modified":"2022-05-16T17:57:16","modified_gmt":"2022-05-16T15:57:16","slug":"algorithme-des-k-plus-proches-voisins","status":"publish","type":"post","link":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/2022\/05\/16\/algorithme-des-k-plus-proches-voisins\/","title":{"rendered":"Algorithme des k plus proches voisins"},"content":{"rendered":"\n<figure class=\"wp-block-image\"><img src=\"http:\/\/yb-isn.fr\/2021\/nsi\/wp-content\/uploads\/2022\/05\/image-7.png\" alt=\"\" \/><\/figure>\n\n\n\n<h2 class=\"has-text-align-center\"><strong><span class=\"has-inline-color has-light-green-cyan-color\">Le k-NN est le<\/span> <span class=\"has-inline-color has-light-green-cyan-color\">diminutif de<\/span><\/strong><span class=\"has-inline-color has-light-green-cyan-color\"><em>&nbsp;k Nearest Neighbors<\/em><\/span><strong><span class=\"has-inline-color has-light-green-cyan-color\">. C\u2019est un algorithme qui peut servir autant pour la classification que pour la r\u00e9gression. Il est surnomm\u00e9 \u00ab&nbsp;nearest neighbors&nbsp;\u00bb (plus proches voisins, en fran\u00e7ais) car le principe de ce mod\u00e8le consiste en effet \u00e0 choisir les&nbsp;k&nbsp;donn\u00e9es les plus proches du point \u00e9tudi\u00e9 afin d\u2019en pr\u00e9dire sa valeur.<\/span><\/strong><\/h2>\n\n\n\n<h2 class=\"has-text-align-center\"><strong><span class=\"has-inline-color has-light-green-cyan-color\">En fait, le k-NN est un type sp\u00e9cial d\u2019algorithme qui n\u2019utilise pas de mod\u00e8le statistique. Il est &#8220;non param\u00e9trique&#8221; et il se base uniquement sur les donn\u00e9es d\u2019entra\u00eenement. Ce type d\u2019algorithme est appel\u00e9&nbsp;<\/span><\/strong><em><span class=\"has-inline-color has-light-green-cyan-color\">memory-based<\/span><\/em><strong><span class=\"has-inline-color has-light-green-cyan-color\">. A contrario, la r\u00e9gression lin\u00e9aire est param\u00e9trique, de param\u00e8tre&nbsp;\u03b8\u03b8&nbsp;et ne va donc pas avoir besoin de conserver toutes les donn\u00e9es pour effectuer des pr\u00e9dictions, mais seulement&nbsp;\u03b8\u03b8.&nbsp;<\/span><\/strong><\/h2>\n\n\n\n<h1 class=\"has-text-align-center\"><span class=\"has-inline-color has-vivid-purple-color\">Les exemples du programme :<\/span><\/h1>\n\n\n\n<p><a href=\"https:\/\/colab.research.google.com\/drive\/1uGn6byVdSXx9Bmb8081NwH5eAc5N6IFZ?usp=sharing\">https:\/\/colab.research.google.com\/drive\/1uGn6byVdSXx9Bmb8081NwH5eAc5N6IFZ?usp=sharing<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Le k-NN est le diminutif de&nbsp;k Nearest Neighbors. C\u2019est un algorithme qui peut servir autant pour la classification que pour la r\u00e9gression. Il est surnomm\u00e9 \u00ab&nbsp;nearest neighbors&nbsp;\u00bb (plus proches voisins, en fran\u00e7ais) car le principe de ce mod\u00e8le consiste en effet \u00e0 choisir les&nbsp;k&nbsp;donn\u00e9es les plus proches du point \u00e9tudi\u00e9 afin d\u2019en pr\u00e9dire sa valeur. [&hellip;]<\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/posts\/169"}],"collection":[{"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/comments?post=169"}],"version-history":[{"count":3,"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/posts\/169\/revisions"}],"predecessor-version":[{"id":172,"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/posts\/169\/revisions\/172"}],"wp:attachment":[{"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/media?parent=169"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/categories?post=169"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/yb-isn.fr\/2021\/nsi\/romain\/wp-json\/wp\/v2\/tags?post=169"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}