From a4f73fe2ec92958d9a042c7d3aba5441a8726c8c Mon Sep 17 00:00:00 2001
From: 42e498459df1b5cd1010918695b12887
 <42e498459df1b5cd1010918695b12887@app-learninglab.inria.fr>
Date: Tue, 15 Sep 2020 20:31:35 +0000
Subject: [PATCH] no commit message

---
 module3/exo3/.ipynb         | 1109 +++++++++++++++++++++++++++++++++++
 module3/exo3/exercice.ipynb | 1088 +++++++++++++++++++++++++++++++++-
 2 files changed, 2194 insertions(+), 3 deletions(-)
 create mode 100644 module3/exo3/.ipynb

diff --git a/module3/exo3/.ipynb b/module3/exo3/.ipynb
new file mode 100644
index 0000000..8de5488
--- /dev/null
+++ b/module3/exo3/.ipynb
@@ -0,0 +1,1109 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Autour du paradoxe des Simpson"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ce sujet a pour but d'étudier un sondage réalisé en 1972-1974 sur un panel de 1314 femmes n'ayant jamais fumé ou fumant actuellement (au moment du sondage). Ce sondage a été effectué afin d'éclairer des travaux portant sur l'impact du tabagisme sur des maladies thyroïdiennes et cardiaques (Tunbridge *et al.* 1977). Une suite de cette étude a été menée vingt ans plus tard (Vanderpump *et al.* 1995) afin de savoir si les personnes sont décédeés ou non. \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import isoweek"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Le fichier récupéré est en format CSV. Sur chaque ligne se trouve les informations suivantes : la personne fume ou non, elle est vivante ou décédée au moment de la seconde étude, et son âge lors du premier sondage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " data_url = \"https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/-/raw/master/module3/Practical_session/Subject6_smoking.csv\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ici pas besoin de sauter la première ligne du fichier CSV, même s'il s'agit d'un commentaire. En effet, si nous sautons la première ligne avec skiprows=1, nous perdons la première ligne de valeur."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Smoker</th>\n",
+       "      <th>Status</th>\n",
+       "      <th>Age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>21.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>19.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>81.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>23.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>24.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>30.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>66.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>27.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>65.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>73.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>33.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>56.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>59.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1284</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1285</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>48.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1286</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1287</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1288</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>39.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1289</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1290</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1291</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1292</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>57.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1293</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1294</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>46.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1295</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>82.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1296</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1297</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>32.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1298</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1299</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1300</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1301</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1302</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>44.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1303</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>31.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1304</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1305</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1306</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>61.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1307</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1308</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>42.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1309</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>35.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1310</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>22.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1311</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1312</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>88.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1313</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1314 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "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": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "raw_data = pd.read_csv(data_url)\n",
+    "raw_data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    " Y a-t-il des points manquants dans ce jeux de données ? Verifions cela"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Smoker</th>\n",
+       "      <th>Status</th>\n",
+       "      <th>Age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [Smoker, Status, Age]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "raw_data[raw_data.isnull().any(axis=1)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "A priori il n'y a pas de donnée manquante. Il n'y a donc pas de données à supprimer\n",
+    "Cependant, afin de clarifier la suite du code, nous définissons plus simplement les données par \"data\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Smoker</th>\n",
+       "      <th>Status</th>\n",
+       "      <th>Age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>21.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>19.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>81.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>23.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>24.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>30.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>66.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>27.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>65.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>73.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>33.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>56.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>59.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1284</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1285</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>48.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1286</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1287</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1288</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>39.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1289</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1290</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1291</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1292</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>57.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1293</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1294</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>46.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1295</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>82.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1296</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1297</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>32.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1298</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1299</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1300</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1301</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1302</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>44.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1303</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>31.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1304</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1305</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1306</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>61.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1307</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1308</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>42.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1309</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>35.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1310</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>22.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1311</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1312</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>88.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1313</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1314 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "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": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = raw_data\n",
+    "data"
+   ]
+  },
+  {
+   "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
+}
diff --git a/module3/exo3/exercice.ipynb b/module3/exo3/exercice.ipynb
index 0bbbe37..eb42c23 100644
--- a/module3/exo3/exercice.ipynb
+++ b/module3/exo3/exercice.ipynb
@@ -1,5 +1,1088 @@
 {
- "cells": [],
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Autour du paradoxe des Simpson"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ce sujet a pour but d'étudier un sondage réalisé en 1972-1974 sur un panel de 1314 femmes n'ayant jamais fumé ou fumant actuellement (au moment du sondage). Ce sondage a été effectué afin d'éclairer des travaux portant sur l'impact du tabagisme sur des maladies thyroïdiennes et cardiaques (Tunbridge *et al.* 1977). Une suite de cette étude a été menée vingt ans plus tard (Vanderpump *et al.* 1995) afin de savoir si les personnes sont décédeés ou non. \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import isoweek"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Le fichier récupéré est en format CSV. Sur chaque ligne se trouve les informations suivantes : la personne fume ou non, elle est vivante ou décédée au moment de la seconde étude, et son âge lors du premier sondage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " data_url = \"https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/-/raw/master/module3/Practical_session/Subject6_smoking.csv\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ici pas besoin de sauter la première ligne du fichier CSV, même s'il s'agit d'un commentaire. En effet, si nous sautons la première ligne avec skiprows=1, nous perdons la première ligne de valeur."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Smoker</th>\n",
+       "      <th>Status</th>\n",
+       "      <th>Age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>21.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>19.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>81.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>23.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>24.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>30.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>66.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>27.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>65.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>73.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>33.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>56.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>59.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1284</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1285</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>48.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1286</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1287</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1288</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>39.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1289</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1290</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1291</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1292</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>57.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1293</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1294</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>46.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1295</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>82.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1296</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1297</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>32.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1298</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1299</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1300</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1301</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1302</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>44.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1303</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>31.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1304</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1305</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1306</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>61.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1307</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1308</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>42.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1309</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>35.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1310</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>22.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1311</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1312</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>88.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1313</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1314 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "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": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "raw_data = pd.read_csv(data_url)\n",
+    "raw_data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    " Y a-t-il des points manquants dans ce jeux de données ? Verifions cela"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Smoker</th>\n",
+       "      <th>Status</th>\n",
+       "      <th>Age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [Smoker, Status, Age]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "raw_data[raw_data.isnull().any(axis=1)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "A priori il n'y a pas de donnée manquante. Il n'y a donc pas de données à supprimer\n",
+    "Cependant, afin de clarifier la suite du code, nous définissons plus simplement les données par \"data\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Smoker</th>\n",
+       "      <th>Status</th>\n",
+       "      <th>Age</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>21.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>19.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>81.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>23.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>57.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>24.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>30.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>66.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>49.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>27.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>58.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>65.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>73.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>33.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>56.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>59.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>25.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1284</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>36.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1285</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>48.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1286</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1287</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1288</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>39.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1289</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>36.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1290</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1291</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1292</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>57.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1293</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>63.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1294</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>46.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1295</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>82.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1296</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>38.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1297</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>32.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1298</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1299</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>60.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1300</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>71.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1301</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>20.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1302</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>44.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1303</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>31.2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1304</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>47.8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1305</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>60.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1306</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>61.4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1307</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>43.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1308</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>42.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1309</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>35.9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1310</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>22.3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1311</th>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>62.1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1312</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Dead</td>\n",
+       "      <td>88.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1313</th>\n",
+       "      <td>No</td>\n",
+       "      <td>Alive</td>\n",
+       "      <td>39.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1314 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "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": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = raw_data\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  }
+ ],
  "metadata": {
   "kernelspec": {
    "display_name": "Python 3",
@@ -16,10 +1099,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.3"
+   "version": "3.6.4"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 2
 }
-
-- 
2.18.1