From 165a479874b87dfda9d1e3c1b58e28e6377d9e93 Mon Sep 17 00:00:00 2001 From: 57ddaac15ab76d1b1db01438dbac1880 <57ddaac15ab76d1b1db01438dbac1880@app-learninglab.inria.fr> Date: Sun, 5 Dec 2021 15:09:07 +0000 Subject: [PATCH] Autour du Paradoxe de Simpson --- module3/exo3/exercice.ipynb | 742 +++++++++++++++++++++++++++++++++++- 1 file changed, 739 insertions(+), 3 deletions(-) diff --git a/module3/exo3/exercice.ipynb b/module3/exo3/exercice.ipynb index 0bbbe37..90e90c0 100644 --- a/module3/exo3/exercice.ipynb +++ b/module3/exo3/exercice.ipynb @@ -1,5 +1,742 @@ { - "cells": [], + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Autour du Paradoxe de Simpson" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import isoweek" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + " ### Les données" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "data_raw = 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": "code", + "execution_count": 14, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SmokerStatusAge
0YesAlive21.0
1YesAlive19.3
2NoDead57.5
3NoAlive47.1
4YesAlive81.4
5NoAlive36.8
6NoAlive23.8
7YesDead57.5
8YesAlive24.8
9YesAlive49.5
10YesAlive30.0
11NoDead66.0
12YesAlive49.2
13NoAlive58.4
14NoDead60.6
15NoAlive25.1
16NoAlive43.5
17NoAlive27.1
18NoAlive58.3
19YesAlive65.7
20NoDead73.2
21YesAlive38.3
22NoAlive33.4
23YesDead62.3
24NoAlive18.0
25NoAlive56.2
26YesAlive59.2
27NoAlive25.8
28NoDead36.9
29NoAlive20.2
............
1284YesDead36.0
1285YesAlive48.3
1286NoAlive63.1
1287NoAlive60.8
1288YesDead39.3
1289NoAlive36.7
1290NoAlive63.8
1291NoDead71.3
1292NoAlive57.7
1293NoAlive63.2
1294NoAlive46.6
1295YesDead82.4
1296YesAlive38.3
1297YesAlive32.7
1298NoAlive39.7
1299YesDead60.0
1300NoDead71.0
1301NoAlive20.5
1302NoAlive44.4
1303YesAlive31.2
1304YesAlive47.8
1305YesAlive60.9
1306NoDead61.4
1307YesAlive43.0
1308NoAlive42.1
1309YesAlive35.9
1310NoAlive22.3
1311YesDead62.1
1312NoDead88.6
1313NoAlive39.1
\n", + "

1314 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " Smoker Status Age\n", + "0 Yes Alive 21.0\n", + "1 Yes Alive 19.3\n", + "2 No Dead 57.5\n", + "3 No Alive 47.1\n", + "4 Yes Alive 81.4\n", + "5 No Alive 36.8\n", + "6 No Alive 23.8\n", + "7 Yes Dead 57.5\n", + "8 Yes Alive 24.8\n", + "9 Yes Alive 49.5\n", + "10 Yes Alive 30.0\n", + "11 No Dead 66.0\n", + "12 Yes Alive 49.2\n", + "13 No Alive 58.4\n", + "14 No Dead 60.6\n", + "15 No Alive 25.1\n", + "16 No Alive 43.5\n", + "17 No Alive 27.1\n", + "18 No Alive 58.3\n", + "19 Yes Alive 65.7\n", + "20 No Dead 73.2\n", + "21 Yes Alive 38.3\n", + "22 No Alive 33.4\n", + "23 Yes Dead 62.3\n", + "24 No Alive 18.0\n", + "25 No Alive 56.2\n", + "26 Yes Alive 59.2\n", + "27 No Alive 25.8\n", + "28 No Dead 36.9\n", + "29 No Alive 20.2\n", + "... ... ... ...\n", + "1284 Yes Dead 36.0\n", + "1285 Yes Alive 48.3\n", + "1286 No Alive 63.1\n", + "1287 No Alive 60.8\n", + "1288 Yes Dead 39.3\n", + "1289 No Alive 36.7\n", + "1290 No Alive 63.8\n", + "1291 No Dead 71.3\n", + "1292 No Alive 57.7\n", + "1293 No Alive 63.2\n", + "1294 No Alive 46.6\n", + "1295 Yes Dead 82.4\n", + "1296 Yes Alive 38.3\n", + "1297 Yes Alive 32.7\n", + "1298 No Alive 39.7\n", + "1299 Yes Dead 60.0\n", + "1300 No Dead 71.0\n", + "1301 No Alive 20.5\n", + "1302 No Alive 44.4\n", + "1303 Yes Alive 31.2\n", + "1304 Yes Alive 47.8\n", + "1305 Yes Alive 60.9\n", + "1306 No Dead 61.4\n", + "1307 Yes Alive 43.0\n", + "1308 No Alive 42.1\n", + "1309 Yes Alive 35.9\n", + "1310 No Alive 22.3\n", + "1311 Yes Dead 62.1\n", + "1312 No Dead 88.6\n", + "1313 No Alive 39.1\n", + "\n", + "[1314 rows x 3 columns]" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data_raw" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + " ### Le taux de mortalité" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [], + "source": [ + "data_raw.values[:,1]= str(data_raw.values[:,1])\n" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [], + "source": [ + "m=0\n", + "n=0\n", + "dataArray = []\n", + "for j in range(0,1314):\n", + " if 'Yes' in data_raw.values[j,0]:\n", + " n=n+1\n", + " if 'Dead' in data_raw.values[j,1]:\n", + " m=m+1\n" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "23.883161512027492" + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(m/n)*100" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [], + "source": [ + "a=0\n", + "b=0\n", + "for j in range(0,1314):\n", + " if 'No' in data_raw.values[j,0]:\n", + " a=a+1\n", + " if 'Dead' in data_raw.values[j,1]:\n", + " b=b+1\n" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "31.420765027322407" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(b/a)*100" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Ce résultat est surprenant car le taux de mortalité des femmes nom fumeuses est plus grand que le taux de mortalité des femmes\n", + "fumeuses" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [], + "source": [ + "i=0\n", + "s=0\n", + "z=0\n", + "r=0\n", + "x=0\n", + "h=0\n", + "t=0\n", + "y=0\n", + "for j in range(0,1314):\n", + " if int(data_raw.values[j,2])>=18 & int(data_raw.values[j,2])<=34:\n", + " if 'Yes' in data_raw.values[j,0]:\n", + " s=s+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " i=i+1 \n", + " if int(data_raw.values[j,2])>=35 & int(data_raw.values[j,2])<=54:\n", + " if 'Yes' in data_raw.values[j,0]:\n", + " z=z+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " r=r+1\n", + " if int(data_raw.values[j,2])>=55 & int(data_raw.values[j,2])<=64:\n", + " if 'Yes' in data_raw.values[j,0]:\n", + " x=x+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " h=h+1\n", + " if int(data_raw.values[j,2])>=65:\n", + " if 'Yes' in data_raw.values[j,0]:\n", + " y=y+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " t=t+1\n", + " \n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(23.883161512027492, 23.883161512027492, 23.883161512027492, 85.71428571428571)" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(i/s)*100,(r/z)*100,(h/x)*100,(t/y)*100" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [], + "source": [ + "i=0\n", + "s=0\n", + "z=0\n", + "r=0\n", + "x=0\n", + "h=0\n", + "t=0\n", + "y=0\n", + "for j in range(0,1314):\n", + " if int(data_raw.values[j,2])>=18 & int(data_raw.values[j,2])<=34:\n", + " if 'No' in data_raw.values[j,0]:\n", + " s=s+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " i=i+1 \n", + " if int(data_raw.values[j,2])>=35 & int(data_raw.values[j,2])<=54:\n", + " if 'No' in data_raw.values[j,0]:\n", + " z=z+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " r=r+1\n", + " if int(data_raw.values[j,2])>=55 & int(data_raw.values[j,2])<=64:\n", + " if 'No' in data_raw.values[j,0]:\n", + " x=x+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " h=h+1\n", + " if int(data_raw.values[j,2])>=65:\n", + " if 'No' in data_raw.values[j,0]:\n", + " y=y+1\n", + " if'Dead' in data_raw.values[j,1]:\n", + " t=t+1\n", + " \n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(31.420765027322407, 31.420765027322407, 31.420765027322407, 85.49222797927462)" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(i/s)*100,(r/z)*100,(h/x)*100,(t/y)*100" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Ce résultat est surprenant car on a trouvé que le taux de mortalité n'a pas varié pour les fumeuses de 18 à 64 ans mais seulement pour celles qui sont plus grand que 65 ans le taux a augmenté beaucoup, même chose pour les non fumeuses. On peut conclure que les cigarettes ont un effet indirect sur la santé qui peut être remarqué après longtemps, et d'autre part le système immunitaire peut résister aux effets toxiques de la cigarettes pour une certaine période de vie.\n", + "Donc on peut conclure sur la nocivité du tabagisme." + ] + } + ], "metadata": { "kernelspec": { "display_name": "Python 3", @@ -16,10 +753,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.3" + "version": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 } - -- 2.18.1