Skip to content

M
mooc-rr
Commit c701238b authored by 86d2379a8cd828206f6e8576c862739f's avatar 86d2379a8cd828206f6e8576c862739f
Browse files
Options

no commit message

parent 808877d7
Show whitespace changes
Inline Side-by-side
Showing with 576 additions and 28 deletions
module3/exo3/exercice.ipynb
View file @ c701238b
...@@ -11,7 +11,7 @@ ...@@ -11,7 +11,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"blabla intro" "Ce document présente une analyse de données pour le MOOC recherche reproductible. Le but est d'analyser les données autour du paradoxe de Simpson, qui donne l'impression - en premier lieu - donner des conclusions surprenantes sur l'effet du tabagisme sur la santé."
] ]
}, },
{ {
...@@ -23,7 +23,7 @@ ...@@ -23,7 +23,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
...@@ -41,7 +41,7 @@ ...@@ -41,7 +41,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
...@@ -50,7 +50,7 @@ ...@@ -50,7 +50,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
...@@ -66,7 +66,7 @@ ...@@ -66,7 +66,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -534,7 +534,7 @@ ...@@ -534,7 +534,7 @@
"[1314 rows x 3 columns]" "[1314 rows x 3 columns]"
] ]
}, },
"execution_count": 4, "execution_count": 5,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
...@@ -552,7 +552,7 @@ ...@@ -552,7 +552,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -592,7 +592,7 @@ ...@@ -592,7 +592,7 @@
"Index: []" "Index: []"
] ]
}, },
"execution_count": 5, "execution_count": 6,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
...@@ -603,7 +603,7 @@ ...@@ -603,7 +603,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -643,7 +643,7 @@ ...@@ -643,7 +643,7 @@
"Index: []" "Index: []"
] ]
}, },
"execution_count": 17, "execution_count": 7,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
...@@ -654,7 +654,7 @@ ...@@ -654,7 +654,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -694,7 +694,7 @@ ...@@ -694,7 +694,7 @@
"Index: []" "Index: []"
] ]
}, },
"execution_count": 19, "execution_count": 8,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
...@@ -712,7 +712,7 @@ ...@@ -712,7 +712,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 20, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
...@@ -735,7 +735,7 @@ ...@@ -735,7 +735,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 36, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -768,7 +768,7 @@ ...@@ -768,7 +768,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Taux de mortalité par classes d'age" "## Taux de mortalité par classes d'age (question 2)"
] ]
}, },
{ {
...@@ -780,7 +780,7 @@ ...@@ -780,7 +780,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 49, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
...@@ -822,7 +822,7 @@ ...@@ -822,7 +822,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Vérification de l'hypothèse - régression logistique" "## Vérification de l'hypothèse - régression logistique (question 3)"
] ]
}, },
{ {
...@@ -834,20 +834,570 @@ ...@@ -834,20 +834,570 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 56, "execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"dead_bool = [(data['Status'][i] == \"Dead\") for i in range(len(data))]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"data.insert(4, \"Dead?\",data)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"data['Dead?'] = dead_bool"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"ename": "SyntaxError", "data": {
"evalue": "invalid syntax (<ipython-input-56-12aabec9006d>, line 1)", "text/html": [
"output_type": "error", "<div>\n",
"traceback": [ "<style scoped>\n",
"\u001b[0;36m File \u001b[0;32m\"<ipython-input-56-12aabec9006d>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m dead_bool = [(col[i]['Status'] == \"Dead\") for i in 1:len(data)]\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\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",
" <th>Dead?</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",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>19.3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>57.5</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>47.1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>81.4</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>36.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>23.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Yes</td>\n",
" <td>Dead</td>\n",
" <td>57.5</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>24.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>49.5</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>30.0</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>66.0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>49.2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>58.4</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>60.6</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>25.1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>43.5</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>27.1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>58.3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>65.7</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>73.2</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>38.3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>33.4</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>Yes</td>\n",
" <td>Dead</td>\n",
" <td>62.3</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>18.0</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>56.2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>59.2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>25.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>36.9</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>20.2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\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",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1285</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>48.3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1286</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>63.1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1287</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>60.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1288</th>\n",
" <td>Yes</td>\n",
" <td>Dead</td>\n",
" <td>39.3</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1289</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>36.7</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1290</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>63.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1291</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>71.3</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1292</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>57.7</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1293</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>63.2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1294</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>46.6</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1295</th>\n",
" <td>Yes</td>\n",
" <td>Dead</td>\n",
" <td>82.4</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1296</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>38.3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1297</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>32.7</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1298</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>39.7</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1299</th>\n",
" <td>Yes</td>\n",
" <td>Dead</td>\n",
" <td>60.0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1300</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>71.0</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1301</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>20.5</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1302</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>44.4</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1303</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>31.2</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1304</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>47.8</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1305</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>60.9</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1306</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>61.4</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1307</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>43.0</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1308</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>42.1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1309</th>\n",
" <td>Yes</td>\n",
" <td>Alive</td>\n",
" <td>35.9</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1310</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>22.3</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1311</th>\n",
" <td>Yes</td>\n",
" <td>Dead</td>\n",
" <td>62.1</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1312</th>\n",
" <td>No</td>\n",
" <td>Dead</td>\n",
" <td>88.6</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1313</th>\n",
" <td>No</td>\n",
" <td>Alive</td>\n",
" <td>39.1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1314 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" Smoker Status Age Dead?\n",
"0 Yes Alive 21.0 False\n",
"1 Yes Alive 19.3 False\n",
"2 No Dead 57.5 True\n",
"3 No Alive 47.1 False\n",
"4 Yes Alive 81.4 False\n",
"5 No Alive 36.8 False\n",
"6 No Alive 23.8 False\n",
"7 Yes Dead 57.5 True\n",
"8 Yes Alive 24.8 False\n",
"9 Yes Alive 49.5 False\n",
"10 Yes Alive 30.0 False\n",
"11 No Dead 66.0 True\n",
"12 Yes Alive 49.2 False\n",
"13 No Alive 58.4 False\n",
"14 No Dead 60.6 True\n",
"15 No Alive 25.1 False\n",
"16 No Alive 43.5 False\n",
"17 No Alive 27.1 False\n",
"18 No Alive 58.3 False\n",
"19 Yes Alive 65.7 False\n",
"20 No Dead 73.2 True\n",
"21 Yes Alive 38.3 False\n",
"22 No Alive 33.4 False\n",
"23 Yes Dead 62.3 True\n",
"24 No Alive 18.0 False\n",
"25 No Alive 56.2 False\n",
"26 Yes Alive 59.2 False\n",
"27 No Alive 25.8 False\n",
"28 No Dead 36.9 True\n",
"29 No Alive 20.2 False\n",
"... ... ... ... ...\n",
"1284 Yes Dead 36.0 True\n",
"1285 Yes Alive 48.3 False\n",
"1286 No Alive 63.1 False\n",
"1287 No Alive 60.8 False\n",
"1288 Yes Dead 39.3 True\n",
"1289 No Alive 36.7 False\n",
"1290 No Alive 63.8 False\n",
"1291 No Dead 71.3 True\n",
"1292 No Alive 57.7 False\n",
"1293 No Alive 63.2 False\n",
"1294 No Alive 46.6 False\n",
"1295 Yes Dead 82.4 True\n",
"1296 Yes Alive 38.3 False\n",
"1297 Yes Alive 32.7 False\n",
"1298 No Alive 39.7 False\n",
"1299 Yes Dead 60.0 True\n",
"1300 No Dead 71.0 True\n",
"1301 No Alive 20.5 False\n",
"1302 No Alive 44.4 False\n",
"1303 Yes Alive 31.2 False\n",
"1304 Yes Alive 47.8 False\n",
"1305 Yes Alive 60.9 False\n",
"1306 No Dead 61.4 True\n",
"1307 Yes Alive 43.0 False\n",
"1308 No Alive 42.1 False\n",
"1309 Yes Alive 35.9 False\n",
"1310 No Alive 22.3 False\n",
"1311 Yes Dead 62.1 True\n",
"1312 No Dead 88.6 True\n",
"1313 No Alive 39.1 False\n",
"\n",
"[1314 rows x 4 columns]"
] ]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
} }
], ],
"source": [ "source": [
"dead_bool = [(col[i]['Status'] == \"Dead\") for i in 1:len(data)]" "data"
] ]
}, },
{ {
...@@ -855,9 +1405,7 @@ ...@@ -855,9 +1405,7 @@
"execution_count": null, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": []
"data.insert(4, \"Dead?\",data)"
]
} }
], ],
"metadata": { "metadata": {
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment