{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Sujet 6 : 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 \n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Maintenant nous allons telecharger nos données en se servant du lien de téléchargement" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "data_url= \"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": [ "maintenant nous importons nos données localement dans Jupyter " ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "data_file = \"Subject6_smoking.csv\"\n", "\n", "import os\n", "import urllib.request\n", "if not os.path.exists(data_file):\n", " urllib.request.urlretrieve(data_url,data_file)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "raw_data = pd.read_csv(data_file)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Mission 1" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Nous effectuons le calcule des personnes qui ne fumme pas et sont en vie; qui fument et sont en vie; qui ne fument pas et sont mort; qui fument et sont mort " ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [], "source": [ "sum_alive_NotSmoking = raw_data[(raw_data[\"Smoker\"] == \"No\") & (raw_data[\"Status\"] == \"Alive\")].shape[0]\n", "sum_alive_Smoking = raw_data[(raw_data[\"Smoker\"] == \"Yes\") & (raw_data[\"Status\"] == \"Alive\")].shape[0]\n", "sum_death_NotSmoking = raw_data[(raw_data[\"Smoker\"] == \"No\") & (raw_data[\"Status\"] == \"Dead\")].shape[0]\n", "sum_death_Smoking = raw_data[(raw_data[\"Smoker\"] == \"Yes\") & (raw_data[\"Status\"] == \"Dead\")].shape[0]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Maintenant on presente le tableau demandé" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Calcule du taux de mortalité" ] }, { "cell_type": "code", "execution_count": 58, "metadata": {}, "outputs": [], "source": [ "#Pour les femmes qui fumment \n", "taux_fume = (sum_death_Smoking / (sum_death_Smoking+sum_alive_Smoking))*100\n", "taux_fume = round(taux_fume, 2)" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "#Pour les femmes qui ne fument pas \n", "taux_fume_pas = (sum_death_NotSmoking / (sum_death_NotSmoking+sum_alive_NotSmoking))*100\n", "taux_fume_pas = round(taux_fume_pas, 2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Tableau de mortalité" ] }, { "cell_type": "code", "execution_count": 60, "metadata": {}, "outputs": [], "source": [ "données_tab1 = {\"En vie\":[sum_alive_Smoking , sum_alive_NotSmoking], \"Mort\": [sum_death_Smoking, sum_death_NotSmoking], \"Taux mortalité en %\": [taux_fume, taux_fume_pas]}\n", "tab1 = pd.DataFrame(données_tab1)\n", "tab1.index = [\"fume\", \"Ne fume pas\"]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Affichage du premier tableau " ] }, { "cell_type": "code", "execution_count": 61, "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", "
En vieMortTaux mortalité en %
fume44313923.88
Ne fume pas50223031.42
\n", "
" ], "text/plain": [ " En vie Mort Taux mortalité en %\n", "fume 443 139 23.88\n", "Ne fume pas 502 230 31.42" ] }, "execution_count": 61, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tab1" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 62, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "tab1.plot()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Mission 2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Nous commençons d'abord par calculer les nombres de personnes par tranche d'age. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Tranche d'age entre 18 à 34 ans" ] }, { "cell_type": "code", "execution_count": 83, "metadata": {}, "outputs": [], "source": [ "#Tranche d'age allant de 18 à 34 ans et fument\n", "age_18_34f = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Smoker\"] == \"Yes\")].shape[0] # f designe fume\n", "\n", "#Tranche d'age allant de 18 à 34 ans, fument et vivent\n", "age_18_34fv = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fv designe fume et vie \n", "\n", "#Tranche d'age allant de 18 à 34 ans, fument et mort\n", "age_18_34fm = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fm designe fume et mort \n", "\n", "#Tranche d'age allant de 18 à 34 ans et ne fument pas\n", "age_18_34fp = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Smoker\"] == \"No\")].shape[0] # fp désigne ne fume pas\n", "\n", "#Tranche d'age allant de 18 à 34 ans, fument pas et vivent\n", "age_18_34fpv = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fpv designe fume pas et vie \n", "\n", "#Tranche d'age allant de 18 à 34 ans, fument pas et mort\n", "age_18_34fpm = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fpm designe fume pas et mort \n", "\n", "#Tranche d'age allant de 18 à 34 ans et sont en vie\n", "age_18_34v = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Status\"] == \"Alive\")].shape[0] # v désigne vie\n", "\n", "#Tranche d'age allant de 18 à 34 ans et sont mort\n", "age_18_34m = raw_data[(raw_data[\"Age\"] <= 34) & (raw_data[\"Status\"] == \"Dead\")].shape[0] # m désigne mort " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Tranche d'age allant de 34 à 54 ans (34 exclut mais 54 inclut) " ] }, { "cell_type": "code", "execution_count": 84, "metadata": {}, "outputs": [], "source": [ "#Tranche d'age allant de 34 à 54 ans et fument\n", "age_34_54f = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Smoker\"] == \"Yes\")].shape[0] # f designe fume\n", "\n", "#Tranche d'age allant de 34 à 54 ans, fument et vivent\n", "age_34_54fv = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fv designe fume et vie \n", "\n", "#Tranche d'age allant de 34 à 54 ans, fument et mort\n", "age_34_54fm = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fm designe fume et mort \n", "\n", "#Tranche d'age allant de 34 à 54 ans et ne fument pas\n", "age_34_54fp = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Smoker\"] == \"No\")].shape[0] # fp désigne ne fume pas\n", "\n", "#Tranche d'age allant de 34 à 54 ans, fument pas et vivent\n", "age_34_54fpv = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fpv designe fume pas et vie \n", "\n", "#Tranche d'age allant de 34 à 54 ans, fument pas et mort\n", "age_34_54fpm = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fpm designe fume pas et mort \n", "\n", "#Tranche d'age allant de 34 à 54 ans et sont en vie\n", "age_34_54v = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Status\"] == \"Alive\")].shape[0] # v désigne vie\n", "\n", "#Tranche d'age allant de 34 à 54 ans et sont mort\n", "age_34_54m = raw_data[(raw_data[\"Age\"] > 34) & (raw_data[\"Age\"] <= 54) & (raw_data[\"Status\"] == \"Dead\")].shape[0] # m désigne mort" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Tranche d'age allant de 54 à 64 ans (54 exclut mais 64 inclut) " ] }, { "cell_type": "code", "execution_count": 85, "metadata": {}, "outputs": [], "source": [ "#Tranche d'age allant de 54 à 64 ans et fument\n", "age_54_64f = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Smoker\"] == \"Yes\")].shape[0] # f designe fume\n", "\n", "#Tranche d'age allant de 54 à 64 ans, fument et vivent\n", "age_54_64fv = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fv designe fume et vie \n", "\n", "#Tranche d'age allant de 54 à 64 ans, fument et mort\n", "age_54_64fm = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fm designe fume et mort \n", "\n", "#Tranche d'age allant de 54 à 64 ans et ne fument pas\n", "age_54_64fp = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Smoker\"] == \"No\")].shape[0] # fp désigne ne fume pas\n", "\n", "#Tranche d'age allant de 54 à 64 ans, fument pas et vivent\n", "age_54_64fpv = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fpv designe fume pas et vie \n", "\n", "#Tranche d'age allant de 54 à 64 ans, fument pas et mort\n", "age_54_64fpm = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fpm designe fume pas et mort\n", "\n", "#Tranche d'age allant de 54 à 64 ans et sont en vie\n", "age_54_64v = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Status\"] == \"Alive\")].shape[0] # v désigne vie\n", "\n", "#Tranche d'age allant de 54 à 64 ans et sont mort\n", "age_54_64m = raw_data[(raw_data[\"Age\"] > 54) & (raw_data[\"Age\"] <= 64) & (raw_data[\"Status\"] == \"Dead\")].shape[0] # m désigne mort" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Tranche d'age plus grand que 65 ans ( 65 inclut) " ] }, { "cell_type": "code", "execution_count": 86, "metadata": {}, "outputs": [], "source": [ "#Tranche d'age plus grand que 65 ans et fument\n", "age_65f = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Smoker\"] == \"Yes\")].shape[0] # f designe fume\n", "\n", "#Tranche d'age plus grand que 65 ans, fument et vivent\n", "age_65fv = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fv designe fume et vie \n", "\n", "#Tranche d'age plus grand que 65 ans, fument et mort\n", "age_65fm = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Smoker\"] == \"Yes\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fm designe fume et mort \n", "\n", "#Tranche d'age plus grand que 65 ans et ne fument pas\n", "age_65fp = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Smoker\"] == \"No\")].shape[0] # fp désigne ne fume pas\n", "\n", "#Tranche d'age plus grand que 65 ans, fument pas et vivent\n", "age_65fpv = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Alive\")].shape[0] # fpv designe fume pas et vie \n", "\n", "#Tranche d'age plus grand que 65 ans, fument pas et mort\n", "age_65fpm = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Smoker\"] == \"No\")& (raw_data[\"Status\"] == \"Dead\")].shape[0] # fpm designe fume pas et mort\n", "\n", "#Tranche d'age plus grand que 65 ans et sont en vie\n", "age_65v = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Status\"] == \"Alive\")].shape[0] # v désigne vie\n", "\n", "#Tranche d'age plus grand que 65 ans et sont mort\n", "age_65m = raw_data[(raw_data[\"Age\"] >= 65) & (raw_data[\"Status\"] == \"Dead\")].shape[0] # m désigne mort" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Calcule des taux de mortalité" ] }, { "cell_type": "code", "execution_count": 87, "metadata": {}, "outputs": [], "source": [ "#Pour les d'age allant de 18 à 34 ans qui fument\n", "taux_18_34f = (age_18_34fm/ (age_18_34fm+age_18_34fv))*100\n", "taux_18_34f = round(taux_18_34f, 2)\n", "\n", "#Pour les d'age allant de 18 à 34 ans qui ne fument pas\n", "taux_18_34fp = (age_18_34fpm/ (age_18_34fpm+age_18_34fpv))*100\n", "taux_18_34fp = round(taux_18_34fp, 2)" ] }, { "cell_type": "code", "execution_count": 88, "metadata": {}, "outputs": [], "source": [ "#Pour les d'age allant de 34 à 54 ans qui fument\n", "taux_34_54f = (age_34_54fm/ (age_34_54fm+age_34_54fv))*100\n", "taux_34_54f = round(taux_34_54f, 2)\n", "\n", "#Pour les d'age allant de 34 à 54 ans qui ne fument pas\n", "taux_34_54fp = (age_34_54fpm/ (age_34_54fpm+age_34_54fpv))*100\n", "taux_34_54fp = round(taux_34_54fp, 2)" ] }, { "cell_type": "code", "execution_count": 89, "metadata": {}, "outputs": [], "source": [ "#Pour les d'age allant de 54 à 64 ans qui fument\n", "taux_54_64f = (age_54_64fm/ (age_54_64fm+age_54_64fv))*100\n", "taux_54_64f = round(taux_54_64f, 2)\n", "\n", "#Pour les d'age allant de 54 à 64 ans qui ne fument pas\n", "taux_54_64fp = (age_54_64fpm/ (age_54_64fpm+age_54_64fpv))*100\n", "taux_54_64fp = round(taux_54_64fp, 2)" ] }, { "cell_type": "code", "execution_count": 90, "metadata": {}, "outputs": [], "source": [ "#Pour les d'age plus grand que 65 ans qui fument\n", "taux_65f = (age_65fm/ (age_65fm+age_65fv))*100\n", "taux_65f = round(taux_65f, 2)\n", "\n", "#Pour les d'age plus grand que 65 ans qui ne fument pas\n", "taux_65fp = (age_65fpm/ (age_65fpm+age_65fpv))*100\n", "taux_65fp = round(taux_65fp, 2)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Tableau de mortalité " ] }, { "cell_type": "code", "execution_count": 91, "metadata": {}, "outputs": [], "source": [ "données_tab2 = {\"Fume\":[age_18_34f, age_34_54f, age_54_64f, age_65f],\"Ne fume pas\":[age_18_34fp, age_34_54fp, age_54_64fp, age_65fp],\"En vie\":[age_18_34v, age_34_54v, age_54_64v, age_65v],\"Mort\":[age_18_34m, age_34_54m, age_54_64m, age_65m], \"Taux mortalité de ceux qui fument en %\": [taux_18_34f, taux_34_54f, taux_54_64f, taux_65f], \"Taux mortalité de ceux qui ne fument pas en %\": [taux_18_34fp, taux_34_54fp, taux_54_64fp, taux_65fp]}\n", "tab2 = pd.DataFrame(données_tab2)\n", "tab2.index = [\"18 à 34\", \"34 à 54\", \"54 à 64\", \">=65\"]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Afichage du deuxième tableau" ] }, { "cell_type": "code", "execution_count": 92, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
En vieFumeMortNe fume pasTaux mortalité de ceux qui fument en %Taux mortalité de ceux qui ne fument pas en %
18 à 34389181112192.762.74
34 à 543762376019917.309.55
54 à 641451159112144.3533.06
>=65354920719385.7185.49
\n", "
" ], "text/plain": [ " En vie Fume Mort Ne fume pas \\\n", "18 à 34 389 181 11 219 \n", "34 à 54 376 237 60 199 \n", "54 à 64 145 115 91 121 \n", ">=65 35 49 207 193 \n", "\n", " Taux mortalité de ceux qui fument en % \\\n", "18 à 34 2.76 \n", "34 à 54 17.30 \n", "54 à 64 44.35 \n", ">=65 85.71 \n", "\n", " Taux mortalité de ceux qui ne fument pas en % \n", "18 à 34 2.74 \n", "34 à 54 9.55 \n", "54 à 64 33.06 \n", ">=65 85.49 " ] }, "execution_count": 92, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tab2" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Le taux de mortalité de ceux qui on plus de 65 ans est élevé qu'elle fument ou pas." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Generation du graphique " ] }, { "cell_type": "code", "execution_count": 93, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 93, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "tab2.plot()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Mission 3" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "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": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 }