{"id":2917,"date":"2020-05-24T17:50:37","date_gmt":"2020-05-24T17:50:37","guid":{"rendered":"https:\/\/datascientest.com\/?p=2917"},"modified":"2023-11-09T14:14:35","modified_gmt":"2023-11-09T14:14:35","slug":"correlation-entre-variables-comment-mesurer-la-dependance","status":"publish","type":"post","link":"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance","title":{"rendered":"Correlation entre variables: comment mesurer la d\u00e9pendance ?"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"2917\" class=\"elementor elementor-2917\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-bb89b9a e-flex e-con-boxed e-con\" data-id=\"bb89b9a\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-6ee8a70 elementor-widget elementor-widget-text-editor\" data-id=\"6ee8a70\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t<h2>En Data science, il est primordial de d\u00e9couvrir et quantifier \u00e0 quel point deux variables sont li\u00e9es. Ces relations peuvent \u00eatre complexes et ne sont pas forc\u00e9ment visibles. Or certaines de ces d\u00e9pendances affaiblissent les performances d\u2019algorithme de Machine Learning comme des r\u00e9gressions lin\u00e9aires. Il devient alors imp\u00e9ratif de mieux pr\u00e9parer vos donn\u00e9es.<\/h2>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e5b47c9 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"e5b47c9\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/formations-data\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">D\u00e9couvrir nos formations au Machine Learning<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-cc062e9 elementor-widget elementor-widget-text-editor\" data-id=\"cc062e9\" data-element_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<p>Nous allons voir ici comment obtenir la d\u00e9pendance entre deux variables cat\u00e9gorielles et entre des variables cat\u00e9gorielles et continues.<\/p><p>Tout d\u2019abord, il faut se rappeler qu\u2019une<strong> variable cat\u00e9gorielle<\/strong> est une variable qui <b>p<\/b><strong>oss\u00e8de un nombre fini de cat\u00e9gories<\/strong> ou de groupes distincts. Par exemple, le sexe d&rsquo;individus, le type de mat\u00e9riel ou le mode de paiement. A contrario, les <strong>variables continues<\/strong> peuvent prendre en th\u00e9orie un nombre infini de valeurs.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-0d75140 e-flex e-con-boxed e-con\" data-id=\"0d75140\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-d05e93f elementor-widget elementor-widget-heading\" data-id=\"d05e93f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h3 class=\"elementor-heading-title elementor-size-default\">Corr\u00e9lation entre deux variables cat\u00e9gorielles\u00a0:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8fd0a5a elementor-widget elementor-widget-text-editor\" data-id=\"8fd0a5a\" data-element_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<p>Pour savoir si deux variables cat\u00e9gorielles sont li\u00e9es, on utilise le c\u00e9l\u00e8bre <b>test du khi-deux.<\/b> Pour ceux qui ne sont pas familiers des tests statistiques pas de panique\u00a0!<\/p><blockquote><p><em>Un test statistique est une proc\u00e9dure de d\u00e9cision entre deux hypoth\u00e8ses.<\/em><br \/><em>Il s&rsquo;agit d&rsquo;une d\u00e9marche consistant \u00e0 rejeter ou \u00e0 ne pas rejeter une\u00a0hypoth\u00e8se statistique, appel\u00e9e hypoth\u00e8se nulle H0, en fonction d&rsquo;un jeu\u00a0de donn\u00e9es.<\/em><\/p><\/blockquote><p>Dans le test qui nous int\u00e9resse l\u2019hypoth\u00e8se nulle est simplement \u00ab les deux variables test\u00e9es sont ind\u00e9pendantes \u00bb. Enfin le test s\u2019accompagne d\u2019une statistique de test qui participe \u00e0 la d\u00e9cision de rejeter ou non l\u2019hypoth\u00e8se nulle. Cette statistique par la mani\u00e8re dont le test est construit, a le bon go\u00fbt de suivre une loi de khi-deux avec un certain degr\u00e9 de libert\u00e9.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2806f76 elementor-widget elementor-widget-heading\" data-id=\"2806f76\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Mais comment d\u00e9cider de rejeter ou non l\u2019hypoth\u00e8se nulle\u00a0?<\/h4>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-bf9c46c elementor-widget elementor-widget-text-editor\" data-id=\"bf9c46c\" data-element_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<p>Sans rentrer dans les d\u00e9tails math\u00e9matiques chaque test statistique dispose de ce qu\u2019on appelle la p-valeur. On peut la voir comme une <strong>valeur r\u00e9f\u00e9rence pour d\u00e9cider du rejet ou non de l\u2019hypoth\u00e8se nulle<\/strong>.<\/p><p>Si cette derni\u00e8re est en-dessous de 5% alors on rejette l\u2019hypoth\u00e8se nulle. Le seuil de 5% est d&rsquo;usage de praticien il peut varier suivant les secteurs d\u2019activit\u00e9.<\/p><p>En <a href=\"https:\/\/datascientest.com\/python-tout-savoir\">Python <\/a>le test est facilement impl\u00e9mentable \u00e0 l\u2019aide de la biblioth\u00e8que scipy et de sa fonction chi2_contingency. Elle permet d\u2019obtenir rapidement la p-valeur du test ainsi que la statistique et le degr\u00e9 de libert\u00e9 associ\u00e9. Dans la pratique le test du khi-deux demande, en amont, un petit travail sur les donn\u00e9es. Pour pouvoir effectuer le test il faut <strong>d\u2019abord d\u00e9terminer la table de contingence.<\/strong> C\u2019est un <strong>tableau de croisement entre les modalit\u00e9s des deux variables<\/strong>. Il s\u2019obtient facilement avec la fonction crosstab de Pandas. Ensuite on r\u00e9alise le test en utilisant la table de contingence\u00a0:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a554aca elementor-widget elementor-widget-image\" data-id=\"a554aca\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.15.0 - 02-08-2023 *\/\n.elementor-widget-image{text-align:center}.elementor-widget-image a{display:inline-block}.elementor-widget-image a img[src$=\".svg\"]{width:48px}.elementor-widget-image img{vertical-align:middle;display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"612\" height=\"302\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.25.png\" class=\"attachment-large size-large wp-image-2925\" alt=\"python\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.25.png 612w, https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.25-300x148.png 300w\" sizes=\"(max-width: 612px) 100vw, 612px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-193e2e0 elementor-widget elementor-widget-text-editor\" data-id=\"193e2e0\" data-element_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<p>Dans notre exemple ci-dessus la p-valeur est bien inf\u00e9rieur \u00e0 5% on peut donc rejeter l\u2019hypoth\u00e8se selon laquelle les deux variables test\u00e9es sont ind\u00e9pendantes.<\/p><p>Enfin on peut \u00e9galement mesurer le niveau de corr\u00e9lation entre les deux variables en utilisant le <strong>V de Cramer.<\/strong> Il se calcule \u00e0 l\u2019aide de la statistique de test, du degr\u00e9 de libert\u00e9 et des dimensions de la table de contingence.<strong> Il renvoie une valeur entre 0 et 1. Si la valeur est <\/strong><strong>renvoy\u00e9e est sup\u00e9rieure \u00e0 0.9 on peut qualifier la relation de tr\u00e8s <\/strong><strong>forte. Si la valeur est inf\u00e9rieure \u00e0 0.10 on peut qualifier la relation de faible.<\/strong><\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f02dbb3 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"f02dbb3\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/formations-data\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Apprendre \u00e0 coder en Python<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-f7008f5 e-flex e-con-boxed e-con\" data-id=\"f7008f5\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-e5067fe elementor-widget elementor-widget-heading\" data-id=\"e5067fe\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Corr\u00e9lation entre deux variables continues\u00a0:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-cc73ecf elementor-widget elementor-widget-text-editor\" data-id=\"cc73ecf\" data-element_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<p>Comme pour les variables cat\u00e9gorielles il existe un test pour d\u00e9terminer si deux variables continues sont ind\u00e9pendantes : <b>le test de corr\u00e9lation de Pearson. <\/b>L\u2019hypoth\u00e8se nulle \u00e0 tester est identique : \u00ab les deux variables test\u00e9es sont ind\u00e9pendantes \u00bb. Comme pour le test du chi-deux, celui-ci s\u2019accompagne d\u2019une statistique de test et d\u2019une p-valeur qui d\u00e9termine du rejet ou non de l\u2019hypoth\u00e8se nulle.<\/p><p>On peut tr\u00e8s facilement impl\u00e9menter ce test \u00e0 l\u2019aide de la biblioth\u00e8que scipy et de sa <a href=\"https:\/\/docs.scipy.org\/doc\/scipy-0.14.0\/reference\/generated\/scipy.stats.pearsonr.html\">fonction pearsonr<\/a>. Il n\u2019y a pas besoin de faire un travail sur les donn\u00e9es en amont \u00e0 condition qu\u2019elles ne contiennent <b>pas de valeurs manquantes<\/b>. Voici un exemple d\u2019impl\u00e9mentation avec python\u00a0:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c82e0a6 elementor-widget elementor-widget-image\" data-id=\"c82e0a6\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"596\" height=\"268\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.19.png\" class=\"attachment-large size-large wp-image-2924\" alt=\"python\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.19.png 596w, https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.19-300x135.png 300w\" sizes=\"(max-width: 596px) 100vw, 596px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-aff6b1f elementor-widget elementor-widget-text-editor\" data-id=\"aff6b1f\" data-element_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<p>Dans notre exemple la p-valeur est inf\u00e9rieur \u00e0 5%. On en d\u00e9duit que les variables ne sont pas ind\u00e9pendantes. Le coefficient de Pearson permet de mesurer le niveau de corr\u00e9lation entre les deux variables. <strong>Il renvoie une valeur entre -1 et 1. S&rsquo;il est proche de 1 cela signifie que les variables sont corr\u00e9l\u00e9es, proche de 0 que les variables sont d\u00e9corr\u00e9l\u00e9es et proche de -1 qu\u2019elles sont corr\u00e9l\u00e9es n\u00e9gativement<\/strong>. Dans notre exemple, le coefficient a une valeur de 0.80319 ce qui signifie que les variables sont fortement corr\u00e9l\u00e9es.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-58fe47c e-flex e-con-boxed e-con\" data-id=\"58fe47c\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-9af2d4c elementor-widget elementor-widget-heading\" data-id=\"9af2d4c\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Corr\u00e9lation entre une variable continue et une\nvariable cat\u00e9gorielle\u00a0:<\/h3>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b8efa28 elementor-widget elementor-widget-text-editor\" data-id=\"b8efa28\" data-element_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<p>Pour \u00e9tudier ce type de corr\u00e9lation on a recours \u00e0 <strong>l&rsquo;analyse de la <\/strong><strong>variance (ANOVA) \u00e0 un facteur<\/strong> qui permet de comparer les moyennes d&rsquo;\u00e9chantillon. L&rsquo;objectif de ce test est de conclure sur<strong> l&rsquo;influence d&rsquo;une <\/strong><strong>variable cat\u00e9gorielle sur la loi d&rsquo;une variable continue \u00e0 expliquer.<\/strong><\/p><p>Imaginez que vous disposez de 3 variables. La premi\u00e8re renseigne un num\u00e9ro client, la deuxi\u00e8me une cat\u00e9gorie (1,2 ou 3) et la derni\u00e8re les sommes d\u00e9pens\u00e9es. La question qu\u2019on peut se poser : est-ce que la variable cat\u00e9gorie a une influence sur les sommes d\u00e9pens\u00e9es ? Notons \u00b51, \u00b52 et \u00b53 les moyennes des sommes d\u00e9pens\u00e9es pour chacune des 3 cat\u00e9gories. Un raisonnement simple consiste \u00e0 dire que si la variable cat\u00e9gorie n\u2019a pas d\u2019influence sur les sommes d\u00e9pens\u00e9es alors les moyennes devraient \u00eatre identiques.<\/p><p>Autrement dit \u00b51 = \u00b52 = \u00b53. C\u2019est exactement l\u2019hypoth\u00e8se que nous testons quand on a recours \u00e0 l&rsquo;analyse de la variance. Comme pour les tests du chi-deux et Pearson ce test s\u2019accompagne d\u2019une statistique de test et d\u2019une p-valeur qui d\u00e9termine du rejet ou non de l\u2019hypoth\u00e8se nulle.<\/p><p>Ce test est facilement impl\u00e9mentable en python en utilisant la librairie statsmodels. Voici un exemple d\u2019impl\u00e9mentation\u00a0:<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0e9be78 elementor-widget elementor-widget-image\" data-id=\"0e9be78\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"800\" height=\"236\" src=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.38.png\" class=\"attachment-large size-large wp-image-2926\" alt=\"python\" srcset=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.38.png 950w, https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.38-300x88.png 300w, https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/Capture-d\u2019e\u0301cran-2020-05-24-a\u0300-19.42.38-768x226.png 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-375e3aa elementor-widget elementor-widget-text-editor\" data-id=\"375e3aa\" data-element_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<p>Dans notre exemple, df renseigne le degr\u00e9 de libert\u00e9 de la statistique de test F qui suit une loi de Fisher. PR(&gt;F) renseigne la valeur de la p-valeur du test. Celle-ci est inf\u00e9rieure \u00e0 5% nous concluons donc que la variable pledged a une influence sur main_category.<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-580739f e-flex e-con-boxed e-con\" data-id=\"580739f\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-293b7fd elementor-widget elementor-widget-text-editor\" data-id=\"293b7fd\" data-element_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<p>Vous avez maintenant toutes les cartes en main pour \u00e9tudier les corr\u00e9lations au sein d\u2019un jeu de donn\u00e9es. Datascientest vous offrira la possibilit\u00e9 d\u2019aller plus loin en apprenant \u00e0 ma\u00eetriser la gestion d\u2019un projet data de A \u00e0 Z.\u00a0<a href=\"https:\/\/datascientest.com\/#formations\" target=\"_blank\" rel=\"noopener\">D\u00e9couvrez nos formations<\/a>, n\u2019h\u00e9sitez plus\u00a0!<\/p>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a6ca0b1 elementor-align-center button-principale elementor-widget elementor-widget-button\" data-id=\"a6ca0b1\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm elementor-animation-grow\" href=\"https:\/\/datascientest.com\/formations-data\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">D\u00e9couvrir nos formations en Data Science<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>En Data science, il est primordial de d\u00e9couvrir et quantifier \u00e0 quel point deux variables sont li\u00e9es. Ces relations peuvent \u00eatre complexes et ne sont pas forc\u00e9ment visibles. Or certaines de ces d\u00e9pendances affaiblissent les performances d\u2019algorithme de Machine Learning comme des r\u00e9gressions lin\u00e9aires. Il devient alors imp\u00e9ratif de mieux pr\u00e9parer vos donn\u00e9es. D\u00e9couvrir nos [&hellip;]<\/p>\n","protected":false},"author":77,"featured_media":3041,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_theme","format":"standard","meta":{"content-type":"","inline_featured_image":false},"categories":[2497],"tags":[166,164,162,165],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.7 (Yoast SEO v21.7) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Correlation entre variables: comment mesurer la d\u00e9pendance ?<\/title>\n<meta name=\"description\" content=\"En Data science, il est primordial d&#039;\u00e9tudier la correlation entre variables. Mais comment obtenir la d\u00e9pendance entre deux variables ?\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Correlation entre variables: comment mesurer la d\u00e9pendance ?\" \/>\n<meta property=\"og:url\" content=\"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance\" \/>\n<meta property=\"og:site_name\" content=\"Formation Data Science | DataScientest.com\" \/>\n<meta property=\"article:published_time\" content=\"2020-05-24T17:50:37+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-09T14:14:35+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/black-chain-147635-scaled.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1707\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Raphael Kassel\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Raphael Kassel\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance\",\"url\":\"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance\",\"name\":\"Correlation entre variables: comment mesurer la d\u00e9pendance ?\",\"isPartOf\":{\"@id\":\"https:\/\/datascientest.com\/#website\"},\"datePublished\":\"2020-05-24T17:50:37+00:00\",\"dateModified\":\"2023-11-09T14:14:35+00:00\",\"author\":{\"@id\":\"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1\"},\"description\":\"En Data science, il est primordial d'\u00e9tudier la correlation entre variables. Mais comment obtenir la d\u00e9pendance entre deux variables ?\",\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/datascientest.com\/#website\",\"url\":\"https:\/\/datascientest.com\/\",\"name\":\"Formation Data Science | DataScientest.com\",\"description\":\"Leader de la formation en Data Science\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/datascientest.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1\",\"name\":\"Raphael Kassel\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/datascientest.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg\",\"contentUrl\":\"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg\",\"caption\":\"Raphael Kassel\"},\"description\":\"Raphael Kassel est le Head of Data Programs chez DataScientest. Il supervise une \u00e9quipe Data, impl\u00e9mente de nouveaux parcours comme \\\"Chef de projet IA\\\" et \\\"Data Product Manager\\\", et contribue \u00e0 la modernisation des op\u00e9rations du groupe. En collaboration \u00e9troite avec l'\u00e9quipe de d\u00e9veloppement, il adapte l'accompagnement acad\u00e9mique aux \u00e9volutions de l'\u00e9quipe data et \u00e0 l'internationalisation.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/raphaelkassel\/\",\"Data Science\"],\"url\":\"https:\/\/datascientest.com\/author\/raphaelkassel\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Correlation entre variables: comment mesurer la d\u00e9pendance ?","description":"En Data science, il est primordial d'\u00e9tudier la correlation entre variables. Mais comment obtenir la d\u00e9pendance entre deux variables ?","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance","og_locale":"fr_FR","og_type":"article","og_title":"Correlation entre variables: comment mesurer la d\u00e9pendance ?","og_url":"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance","og_site_name":"Formation Data Science | DataScientest.com","article_published_time":"2020-05-24T17:50:37+00:00","article_modified_time":"2023-11-09T14:14:35+00:00","og_image":[{"width":2560,"height":1707,"url":"https:\/\/datascientest.com\/wp-content\/uploads\/2020\/05\/black-chain-147635-scaled.jpg","type":"image\/jpeg"}],"author":"Raphael Kassel","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"Raphael Kassel","Dur\u00e9e de lecture estim\u00e9e":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance","url":"https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance","name":"Correlation entre variables: comment mesurer la d\u00e9pendance ?","isPartOf":{"@id":"https:\/\/datascientest.com\/#website"},"datePublished":"2020-05-24T17:50:37+00:00","dateModified":"2023-11-09T14:14:35+00:00","author":{"@id":"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1"},"description":"En Data science, il est primordial d'\u00e9tudier la correlation entre variables. Mais comment obtenir la d\u00e9pendance entre deux variables ?","inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/datascientest.com\/correlation-entre-variables-comment-mesurer-la-dependance"]}]},{"@type":"WebSite","@id":"https:\/\/datascientest.com\/#website","url":"https:\/\/datascientest.com\/","name":"Formation Data Science | DataScientest.com","description":"Leader de la formation en Data Science","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/datascientest.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"fr-FR"},{"@type":"Person","@id":"https:\/\/datascientest.com\/#\/schema\/person\/6eca16f63daaafcbc96e15549b9d4ee1","name":"Raphael Kassel","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/datascientest.com\/#\/schema\/person\/image\/","url":"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg","contentUrl":"https:\/\/datascientest.com\/wp-content\/uploads\/2023\/11\/raph.jpeg","caption":"Raphael Kassel"},"description":"Raphael Kassel est le Head of Data Programs chez DataScientest. Il supervise une \u00e9quipe Data, impl\u00e9mente de nouveaux parcours comme \"Chef de projet IA\" et \"Data Product Manager\", et contribue \u00e0 la modernisation des op\u00e9rations du groupe. En collaboration \u00e9troite avec l'\u00e9quipe de d\u00e9veloppement, il adapte l'accompagnement acad\u00e9mique aux \u00e9volutions de l'\u00e9quipe data et \u00e0 l'internationalisation.","sameAs":["https:\/\/www.linkedin.com\/in\/raphaelkassel\/","Data Science"],"url":"https:\/\/datascientest.com\/author\/raphaelkassel"}]}},"_links":{"self":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/posts\/2917"}],"collection":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/users\/77"}],"replies":[{"embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/comments?post=2917"}],"version-history":[{"count":0,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/posts\/2917\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/media\/3041"}],"wp:attachment":[{"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/media?parent=2917"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/categories?post=2917"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascientest.com\/wp-json\/wp\/v2\/tags?post=2917"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}