{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Autour du Paradoxe de Simpson" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import pandas as pd" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Obtention et pré-traitement des données\n", "\n", "Les données sont présentes sur le Gitlab du MOOC. Par sécurité elles sont téléchargées localement. Il n'est néanmoins pas nécessaire (et contre-productif) de re-télécharger le fichier à chaque exécution, le téléchargement n'a lieux que si le fichier de données n'est pas présent sur la machine.\n", "\n" ] }, { "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\"\n", "data_file=\"Subject6_smoking.csv.csv\"\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": "markdown", "metadata": {}, "source": [ "On affiche un aperçu des données :" ] }, { "cell_type": "code", "execution_count": 3, "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", "
YesAlive21
0YesAlive19.3
1NoDead57.5
2NoAlive47.1
3YesAlive81.4
4NoAlive36.8
5NoAlive23.8
6YesDead57.5
7YesAlive24.8
8YesAlive49.5
9YesAlive30.0
10NoDead66.0
11YesAlive49.2
12NoAlive58.4
13NoDead60.6
14NoAlive25.1
15NoAlive43.5
16NoAlive27.1
17NoAlive58.3
18YesAlive65.7
19NoDead73.2
20YesAlive38.3
21NoAlive33.4
22YesDead62.3
23NoAlive18.0
24NoAlive56.2
25YesAlive59.2
26NoAlive25.8
27NoDead36.9
28NoAlive20.2
29YesAlive34.6
............
1283YesDead36.0
1284YesAlive48.3
1285NoAlive63.1
1286NoAlive60.8
1287YesDead39.3
1288NoAlive36.7
1289NoAlive63.8
1290NoDead71.3
1291NoAlive57.7
1292NoAlive63.2
1293NoAlive46.6
1294YesDead82.4
1295YesAlive38.3
1296YesAlive32.7
1297NoAlive39.7
1298YesDead60.0
1299NoDead71.0
1300NoAlive20.5
1301NoAlive44.4
1302YesAlive31.2
1303YesAlive47.8
1304YesAlive60.9
1305NoDead61.4
1306YesAlive43.0
1307NoAlive42.1
1308YesAlive35.9
1309NoAlive22.3
1310YesDead62.1
1311NoDead88.6
1312NoAlive39.1
\n", "

1313 rows × 3 columns

\n", "
" ], "text/plain": [ " Yes Alive 21\n", "0 Yes Alive 19.3\n", "1 No Dead 57.5\n", "2 No Alive 47.1\n", "3 Yes Alive 81.4\n", "4 No Alive 36.8\n", "5 No Alive 23.8\n", "6 Yes Dead 57.5\n", "7 Yes Alive 24.8\n", "8 Yes Alive 49.5\n", "9 Yes Alive 30.0\n", "10 No Dead 66.0\n", "11 Yes Alive 49.2\n", "12 No Alive 58.4\n", "13 No Dead 60.6\n", "14 No Alive 25.1\n", "15 No Alive 43.5\n", "16 No Alive 27.1\n", "17 No Alive 58.3\n", "18 Yes Alive 65.7\n", "19 No Dead 73.2\n", "20 Yes Alive 38.3\n", "21 No Alive 33.4\n", "22 Yes Dead 62.3\n", "23 No Alive 18.0\n", "24 No Alive 56.2\n", "25 Yes Alive 59.2\n", "26 No Alive 25.8\n", "27 No Dead 36.9\n", "28 No Alive 20.2\n", "29 Yes Alive 34.6\n", "... ... ... ...\n", "1283 Yes Dead 36.0\n", "1284 Yes Alive 48.3\n", "1285 No Alive 63.1\n", "1286 No Alive 60.8\n", "1287 Yes Dead 39.3\n", "1288 No Alive 36.7\n", "1289 No Alive 63.8\n", "1290 No Dead 71.3\n", "1291 No Alive 57.7\n", "1292 No Alive 63.2\n", "1293 No Alive 46.6\n", "1294 Yes Dead 82.4\n", "1295 Yes Alive 38.3\n", "1296 Yes Alive 32.7\n", "1297 No Alive 39.7\n", "1298 Yes Dead 60.0\n", "1299 No Dead 71.0\n", "1300 No Alive 20.5\n", "1301 No Alive 44.4\n", "1302 Yes Alive 31.2\n", "1303 Yes Alive 47.8\n", "1304 Yes Alive 60.9\n", "1305 No Dead 61.4\n", "1306 Yes Alive 43.0\n", "1307 No Alive 42.1\n", "1308 Yes Alive 35.9\n", "1309 No Alive 22.3\n", "1310 Yes Dead 62.1\n", "1311 No Dead 88.6\n", "1312 No Alive 39.1\n", "\n", "[1313 rows x 3 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = pd.read_csv(data_file,skiprows=1)\n", "raw_data" ] } ], "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 }