From 7dda79b09e592f8621bdb9ec0224650aba0e0d2e Mon Sep 17 00:00:00 2001 From: 62003ad659b42f2646d4732566ceeffb <62003ad659b42f2646d4732566ceeffb@app-learninglab.inria.fr> Date: Thu, 17 Dec 2020 01:17:22 +0000 Subject: [PATCH] Paradoxe_Simpson_Sujet6 --- module3/exo3/Paradoxe_Simpson.ipynb | 604 ++++++++++++++++++++++++++++ module3/exo3/exercice.ipynb | 25 -- 2 files changed, 604 insertions(+), 25 deletions(-) create mode 100644 module3/exo3/Paradoxe_Simpson.ipynb delete mode 100644 module3/exo3/exercice.ipynb diff --git a/module3/exo3/Paradoxe_Simpson.ipynb b/module3/exo3/Paradoxe_Simpson.ipynb new file mode 100644 index 0000000..63b4397 --- /dev/null +++ b/module3/exo3/Paradoxe_Simpson.ipynb @@ -0,0 +1,604 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Autour du Paradoxe de Simpson" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import numpy as np\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Les données traitées sont sur [gitlab](https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/-/raw/master/module3/Practical_session/Subject6_smoking.csv?inline=false)" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# On récupère les données grâce au module pandas au format CVS\n", + "datas = pd.read_csv(\"https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/-/raw/master/module3/Practical_session/Subject6_smoking.csv?inline=false\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "On crée une fonction pour faire le compte des femmes fumeuses/non fumeuses, vivantes/mortes." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "def nb_etat_datas(data):\n", + " \n", + " s_d = 0 # smoker and dead\n", + " s_l = 0 # smoker and alive\n", + " ns_d = 0 # not smoker and dead\n", + " ns_l = 0 # not smoker and alive\n", + " \n", + " for st, sm in zip(data[\"Status\"], data[\"Smoker\"]):\n", + " if st == \"Alive\" and sm == \"Yes\":\n", + " s_l += 1\n", + " elif st == \"Alive\" and sm == \"No\":\n", + " ns_l += 1\n", + " elif st == \"Dead\" and sm == \"Yes\":\n", + " s_d += 1\n", + " elif st == \"Dead\" and sm == \"No\":\n", + " ns_d += 1\n", + " \n", + " return s_d,s_l,ns_d,ns_l" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "#nb_w = nombre de femmes\n", + "# nb_s_d = nombre de fumeuses mortes\n", + "# nb_s_l = nombre de fumeuses vivantes\n", + "# nb_ns_d = nombre de non fumeuses mortes\n", + "# nb_ns_l = nombre de non fumeuses vivantes\n", + "\n", + "nb_w = len(datas)\n", + "smoker_or_not = [\"smoker\", \"not smoker\"]\n", + "nb_s_d, nb_s_l, nb_ns_d, nb_ns_l = nb_etat_datas(datas)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "live = pd.Series([nb_s_l, nb_ns_l], index = smoker_or_not)\n", + "dead = pd.Series([nb_s_d, nb_ns_d], index = smoker_or_not)\n", + "df = pd.DataFrame({\"alive\":live, \"dead\" : dead})" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Voici le tableau du nombre total de femmes vivantes et décédées en fonction de leur tabagisme" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
alivedead
smoker443139
not smoker502230
\n", + "
" + ], + "text/plain": [ + " alive dead\n", + "smoker 443 139\n", + "not smoker 502 230" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Voici le taux de mortalité chez les femmes fumeuses et non fumeuses" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Le taux de mortalité chez les femmes fumeuses est de : 0.24\n", + "Le taux de mortalité chez les femmes non fumeuse est de : 0.31\n" + ] + } + ], + "source": [ + "t_m_smoker = nb_s_d/(nb_s_d + nb_s_l) # taux de mortalité chez les fumeuses\n", + "t_m_nsmoker = nb_ns_d/(nb_ns_d + nb_ns_l) # taux de mortalité chez les non fumeuses\n", + "print(f\"Le taux de mortalité chez les femmes fumeuses est de : {t_m_smoker : 0.2}\")\n", + "print(f\"Le taux de mortalité chez les femmes non fumeuse est de : {t_m_nsmoker : 0.2}\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Représentons les taux de mortalité calculés ci-dessus avec un histogramme" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "# J'ai décalé les éléments de fumeuse de longueur 582 et non fumeuses de longueur 732 pour bien espacer les bars \n", + "\n", + "plt.axis([0, 2*nb_w, 0, 100])\n", + "fumeuse = list(range(100,nb_s_l+nb_s_d+101))\n", + "non_fumeuse = list(range(nb_s_l+nb_s_d+201, nb_ns_l+nb_ns_d + 202 + nb_s_l+nb_s_d))\n", + "\n", + "width = 1\n", + "height_s = t_m_smoker * 100 * np.ones(len(fumeuse))\n", + "height_ns = t_m_nsmoker * 100 * np.ones(len(non_fumeuse))\n", + "\n", + "b_fumeuse = plt.bar(fumeuse, height_s, width, color = \"blue\")\n", + "b_nfumeuse = plt.bar(non_fumeuse, height_ns, width, color = \"red\")\n", + "\n", + "plt.title(\"Taux de mortalité\")\n", + "plt.ylabel(\"Pourcentage %\")\n", + "leg = plt.legend([b_fumeuse, b_nfumeuse], ['fumeuse', 'non fumeuse'])" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "D'après les calculs et les histogrammes ci-dessus, on remarque que les femmes qui fument vivent plus longtemps que les femmes qui ne fument pas. On peut conclure que fumer, c'est bon pour la santé." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Prenons en compte des tranches d'âge pour l'étude à savoir 18-34 ans, 34-54 ans, 55-64 ans et plus de 65 ans et mieux comprendre la conclusion précédente." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "hideCode": false + }, + "outputs": [], + "source": [ + "# On va considérer des tranches d'âges\n", + "def nb_etat_datas_v2(data):\n", + " \n", + " # classe 18 - 34 ans\n", + " s_d_1834 = 0 # smoker and dead\n", + " s_l_1834 = 0 # smoker and alive\n", + " ns_d_1834 = 0 # not smoker and dead\n", + " ns_l_1834 = 0 # not smoker and alive\n", + " \n", + " # classe 34 - 54 ans\n", + " s_d_3454 = 0 # smoker and dead\n", + " s_l_3454 = 0 # smoker and alive\n", + " ns_d_3454 = 0 # not smoker and dead\n", + " ns_l_3454 = 0 # not smoker and alive\n", + " \n", + " # classe 55 - 64 ans\n", + " s_d_5564 = 0 # smoker and dead\n", + " s_l_5564 = 0 # smoker and alive\n", + " ns_d_5564 = 0 # not smoker and dead\n", + " ns_l_5564 = 0 # not smoker and alive\n", + " \n", + " # classe 65 et plus\n", + " s_d_65_p = 0 # smoker and dead\n", + " s_l_65_p = 0 # smoker and alive\n", + " ns_d_65_p = 0 # not smoker and dead\n", + " ns_l_65_p = 0 # not smoker and alive\n", + " \n", + " for st, sm, age in zip(data[\"Status\"], data[\"Smoker\"], data[\"Age\"]):\n", + " if 18 <= age < 34:\n", + " if st == \"Alive\" and sm == \"Yes\":\n", + " s_l_1834 += 1\n", + " elif st == \"Alive\" and sm == \"No\":\n", + " ns_l_1834 += 1\n", + " elif st == \"Dead\" and sm == \"Yes\":\n", + " s_d_1834 += 1\n", + " elif st == \"Dead\" and sm == \"No\":\n", + " ns_d_1834 += 1\n", + " elif 34 <= age <= 54:\n", + " if st == \"Alive\" and sm == \"Yes\":\n", + " s_l_3454 += 1\n", + " elif st == \"Alive\" and sm == \"No\":\n", + " ns_l_3454 += 1\n", + " elif st == \"Dead\" and sm == \"Yes\":\n", + " s_d_3454 += 1\n", + " elif st == \"Dead\" and sm == \"No\":\n", + " ns_d_3454 += 1\n", + " elif 55 <= age <= 64:\n", + " if st == \"Alive\" and sm == \"Yes\":\n", + " s_l_5564 += 1\n", + " elif st == \"Alive\" and sm == \"No\":\n", + " ns_l_5564 += 1\n", + " elif st == \"Dead\" and sm == \"Yes\":\n", + " s_d_5564 += 1\n", + " elif st == \"Dead\" and sm == \"No\":\n", + " ns_d_5564 += 1\n", + " elif age >= 65:\n", + " if st == \"Alive\" and sm == \"Yes\":\n", + " s_l_65_p += 1\n", + " elif st == \"Alive\" and sm == \"No\":\n", + " ns_l_65_p += 1\n", + " elif st == \"Dead\" and sm == \"Yes\":\n", + " s_d_65_p += 1\n", + " elif st == \"Dead\" and sm == \"No\":\n", + " ns_d_65_p += 1\n", + " \n", + " return (s_d_1834, s_l_1834, ns_d_1834, ns_l_1834),(s_d_3454, s_l_3454, ns_d_3454, ns_l_3454),(s_d_5564 ,s_l_5564 ,ns_d_5564 ,ns_l_5564),(s_d_65_p ,s_l_65_p ,ns_d_65_p ,ns_l_65_p)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "La fonction nb_etat_datas_v2 est une version améliorée où l'on prend en compte des classes d'âges" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [], + "source": [ + "classe_age = [\"18-34\", \"34-54\", \"55-64\", \"65 et plus\"]\n", + "data_1834, data_3454, data_5564, data_65_p = nb_etat_datas_v2(datas)" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "s_live = pd.Series([data_1834[1], data_3454[1], data_5564[1], data_65_p[1]], index = classe_age) # fumeuse_vivante\n", + "ns_live = pd.Series([data_1834[3], data_3454[3], data_5564[3], data_65_p[3]], index = classe_age) # non fumeuse vivante\n", + "s_dead = pd.Series([data_1834[0], data_3454[0], data_5564[0], data_65_p[0]], index = classe_age) # fumeuse morte\n", + "ns_dead = pd.Series([data_1834[2], data_3454[2], data_5564[2], data_65_p[2]], index = classe_age) # non fumeuse morte\n", + "df_v2 = pd.DataFrame({\"smocker-alive\": s_live,\n", + " \"smocker-dead\" : s_dead,\n", + " \"not-smocker-alive\" : ns_live, \n", + " \"not-smocker-dead\": ns_dead}\n", + " )" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Voici le nouveau tableau avec les tranches d'âges pris en considération" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
not-smocker-alivenot-smocker-deadsmocker-alivesmocker-dead
18-3421361745
34-541801919841
55-6481406451
65 et plus28165742
\n", + "
" + ], + "text/plain": [ + " not-smocker-alive not-smocker-dead smocker-alive smocker-dead\n", + "18-34 213 6 174 5\n", + "34-54 180 19 198 41\n", + "55-64 81 40 64 51\n", + "65 et plus 28 165 7 42" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_v2" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "On peut remarquer que les femmes ayant plus 65 ans et ne fumant pas possèdent un taux de mortalité élevé par rapport aux autres\n", + "femmes de différentes classes d'âge; et la mortalité chez les fumeuses (hormis la dernière tranche d'âge) est élevée par rapport à celle chez les non fumeuses.\n", + "Voici un graphique illustrant de nouveau le problème posé (le couple bleu/rouge représente une classe d'âge par ordre croissant)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "hideCode": false + }, + "outputs": [], + "source": [ + "# On calcule les taux de mortalité pour les différentes classes d'âges en s'inspirant de ce qui a déjà été fait précédemment\n", + "t_m_s_1834 = data_1834[0] / (data_1834[0] + data_1834[1])\n", + "t_m_ns_1834 = data_1834[2] / (data_1834[2] + data_1834[3])\n", + "\n", + "t_m_s_3454 = data_3454[0] / (data_3454[0] + data_3454[1])\n", + "t_m_ns_3454 = data_3454[2] / (data_3454[2] + data_3454[3])\n", + "\n", + "t_m_s_5564 = data_5564[0] / (data_5564[0] + data_5564[1])\n", + "t_m_ns_5564 = data_5564[2] / (data_5564[2] + data_5564[3])\n", + "\n", + "t_m_s_65_p = data_65_p[0] / (data_65_p[0] + data_65_p[1])\n", + "t_m_ns_65_p = data_65_p[2] / (data_65_p[2] + data_65_p[3])" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "hideCode": false + }, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.axis([0, 2*nb_w, 0, 100])\n", + "\n", + "# somme pour la classe 18-34 du nombre de fumeuse et de non fumeuse\n", + "in_f_1834 = data_1834[0] + data_1834[1]\n", + "in_nf_1834 = data_1834[2] + data_1834[3]\n", + "\n", + "# somme pour la classe 34-54 du nombre de fumeuse et de non fumeuse\n", + "in_f_3454 = data_3454[0] + data_3454[1]\n", + "in_nf_3454 = data_3454[2] + data_3454[3]\n", + "\n", + "# somme pour la classe 54-64 du nombre de fumeuse et de non fumeuse\n", + "in_f_5564 = data_5564[0] + data_5564[1]\n", + "in_nf_5564 = data_5564[2] + data_5564[3]\n", + "\n", + "# somme pour la classe 65 et plus du nombre de fumeuse et de non fumeuse\n", + "in_f_65p = data_65_p[0] + data_65_p[1]\n", + "in_nf_65p = data_65_p[2] + data_65_p[3]\n", + "\n", + "# classe 18 - 34\n", + "f_1834 = list(range(0, in_f_1834 + 1))\n", + "nf_1834 = list(range(in_f_1834 + 10, in_nf_1834 + in_f_1834 + 11))\n", + "\n", + "s_1834 = in_nf_1834 + in_f_1834\n", + "\n", + "# classe 34 - 54\n", + "f_3454 = list(range(s_1834 + 30, in_f_3454 + s_1834 + 31))\n", + "nf_3454 = list(range(in_f_3454 + s_1834 + 40, in_nf_3454 + in_f_3454 + s_1834 + 41))\n", + "\n", + "s_3454 = in_nf_3454 + in_f_3454 + s_1834\n", + "\n", + "# classe 55 - 64\n", + "f_5564 = list(range(s_3454 + 50, in_f_5564 + s_3454 + 51))\n", + "nf_5564 = list(range(in_f_5564 + s_3454 + 60, in_nf_5564 + in_f_5564 + s_3454 + 61))\n", + "\n", + "s_5564 = in_nf_5564 + in_f_5564 + s_3454\n", + "\n", + "# classe 65 et plus\n", + "f_65_p = list(range(s_5564 + 70, in_f_65p + s_5564 + 71))\n", + "nf_65_p = list(range(in_f_65p + s_5564 + 80, in_nf_65p + in_f_65p + s_5564 + 81))\n", + "\n", + "width = 1\n", + "\n", + "# hauteurs pour la classe 18 - 34 \n", + "h_s_1834 = t_m_s_1834 * 100 * np.ones(len(f_1834))\n", + "h_ns_1834 = t_m_ns_1834 * 100 * np.ones(len(nf_1834))\n", + "\n", + "# hauteurs pour la classe 34 - 54 \n", + "h_s_3454 = t_m_s_3454 * 100 * np.ones(len(f_3454))\n", + "h_ns_3454 = t_m_ns_3454 * 100 * np.ones(len(nf_3454))\n", + "\n", + "# hauteurs pour la classe 55 - 64\n", + "h_s_5564 = t_m_s_5564 * 100 * np.ones(len(f_5564))\n", + "h_ns_5564 = t_m_ns_5564 * 100 * np.ones(len(nf_5564))\n", + "\n", + "# hauteurs pour la classe 65 et plus\n", + "h_s_65p = t_m_s_65_p * 100 * np.ones(len(f_65_p))\n", + "h_ns_65p = t_m_ns_65_p * 100 * np.ones(len(nf_65_p))\n", + "\n", + "# On trace des bars pour chaque classe\n", + "b_f1834 = plt.bar(f_1834, h_s_1834, width, color = \"blue\")\n", + "b_nf1834 = plt.bar(nf_1834, h_ns_1834, width, color = \"red\")\n", + "\n", + "b_f3454 = plt.bar(f_3454, h_s_3454, width, color = \"blue\")\n", + "b_nf3454 = plt.bar(nf_3454, h_ns_3454, width, color = \"red\")\n", + "\n", + "b_f5564 = plt.bar(f_5564, h_s_5564, width, color = \"blue\")\n", + "b_nf5564 = plt.bar(nf_5564, h_ns_5564, width, color = \"red\")\n", + "\n", + "b_f65p = plt.bar(f_65_p, h_s_65p, width, color = \"blue\")\n", + "b_nf65p = plt.bar(nf_65_p, h_ns_65p, width, color = \"red\")\n", + "\n", + "plt.title(\"Taux de mortalité\")\n", + "plt.xlabel(\"Classe d\\'age\")\n", + "plt.ylabel(\"Pourcentage %\")\n", + "leg = plt.legend([b_f1834, b_nf1834], ['fumeuse', 'non fumeuse'])" + ] + } + ], + "metadata": { + "celltoolbar": "Hide code", + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.4" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/module3/exo3/exercice.ipynb b/module3/exo3/exercice.ipynb deleted file mode 100644 index 0bbbe37..0000000 --- a/module3/exo3/exercice.ipynb +++ /dev/null @@ -1,25 +0,0 @@ -{ - "cells": [], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.6.3" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} - -- 2.18.1