diff --git a/module3/exo2/exercice.ipynb b/module3/exo2/exercice.ipynb index cd315207488e7aa853a63b24d256b6c3a370750a..9da5ee83bd0f4a000568456f71356e52cf9e6ff6 100644 --- a/module3/exo2/exercice.ipynb +++ b/module3/exo2/exercice.ipynb @@ -6,6 +6,1075 @@ "source": [ "# Incidence du syndrome de varicelle" ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "import isoweek" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Les données de l'incidence du syndrome de varicelle sont disponibles du site Web du [Réseau Sentinelles](https://www.sentiweb.fr). Nous les récupérons sous forme d'un fichier en format CSV dont chaque ligne correspond à une semaine de la période demandée. Nous téléchargeons toujours le jeu de données complet, qui commence en 1991 et se termine avec une semaine récente." + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-7.csv\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant skiprows=1." + ] + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
02020127821058231059712816FRFrance
1202011710198756812828151119FRFrance
220201079011669111331141018FRFrance
32020097136311054416718211626FRFrance
4202008710424770813140161220FRFrance
520200778959657411344141018FRFrance
620200679264692511603141018FRFrance
720200578505631410696131016FRFrance
82020047799158311015112915FRFrance
920200375968410078369612FRFrance
10202002765344530853810713FRFrance
1120200179835701912651151119FRFrance
122019527794152461063612816FRFrance
1320195175823367579719612FRFrance
14201950764244276857210713FRFrance
15201949766214540870210713FRFrance
1620194875542338377018511FRFrance
172019477753650581001411715FRFrance
182019467263813163960426FRFrance
1920194574492261563697410FRFrance
2020194475728362778299612FRFrance
2120194374834275169177410FRFrance
22201942762793989856910713FRFrance
232019417413020306230639FRFrance
242019407421122186204639FRFrance
252019397313713104964528FRFrance
262019387307814164740528FRFrance
2720193779701621778102FRFrance
28201936712772632291204FRFrance
29201935792201857102FRFrance
.................................
14991991267176081130423912312042FRFrance
15001991257161691070021638281838FRFrance
15011991247161711007122271281739FRFrance
1502199123711947767116223211329FRFrance
1503199122715452995320951271737FRFrance
1504199121714903897520831261636FRFrance
15051991207190531274225364342345FRFrance
15061991197167391124622232291939FRFrance
15071991187213851388228888382551FRFrance
1508199117713462887718047241632FRFrance
15091991167148571006819646261834FRFrance
1510199115713975978118169251832FRFrance
1511199114712265768416846221430FRFrance
151219911379567604113093171123FRFrance
1513199112710864733114397191325FRFrance
15141991117155741118419964271935FRFrance
15151991107166431137221914292038FRFrance
1516199109713741878018702241533FRFrance
1517199108713289881317765231531FRFrance
1518199107712337807716597221529FRFrance
1519199106710877701314741191226FRFrance
1520199105710442654414340181125FRFrance
15211991047791345631126314820FRFrance
15221991037153871048420290271836FRFrance
15231991027162771104621508292038FRFrance
15241991017155651027120859271836FRFrance
15251990527193751329525455342345FRFrance
15261990517190801380724353342543FRFrance
1527199050711079666015498201228FRFrance
15281990497114302610205FRFrance
\n", + "

1529 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202012 7 8210 5823 10597 12 8 \n", + "1 202011 7 10198 7568 12828 15 11 \n", + "2 202010 7 9011 6691 11331 14 10 \n", + "3 202009 7 13631 10544 16718 21 16 \n", + "4 202008 7 10424 7708 13140 16 12 \n", + "5 202007 7 8959 6574 11344 14 10 \n", + "6 202006 7 9264 6925 11603 14 10 \n", + "7 202005 7 8505 6314 10696 13 10 \n", + "8 202004 7 7991 5831 10151 12 9 \n", + "9 202003 7 5968 4100 7836 9 6 \n", + "10 202002 7 6534 4530 8538 10 7 \n", + "11 202001 7 9835 7019 12651 15 11 \n", + "12 201952 7 7941 5246 10636 12 8 \n", + "13 201951 7 5823 3675 7971 9 6 \n", + "14 201950 7 6424 4276 8572 10 7 \n", + "15 201949 7 6621 4540 8702 10 7 \n", + "16 201948 7 5542 3383 7701 8 5 \n", + "17 201947 7 7536 5058 10014 11 7 \n", + "18 201946 7 2638 1316 3960 4 2 \n", + "19 201945 7 4492 2615 6369 7 4 \n", + "20 201944 7 5728 3627 7829 9 6 \n", + "21 201943 7 4834 2751 6917 7 4 \n", + "22 201942 7 6279 3989 8569 10 7 \n", + "23 201941 7 4130 2030 6230 6 3 \n", + "24 201940 7 4211 2218 6204 6 3 \n", + "25 201939 7 3137 1310 4964 5 2 \n", + "26 201938 7 3078 1416 4740 5 2 \n", + "27 201937 7 970 162 1778 1 0 \n", + "28 201936 7 1277 263 2291 2 0 \n", + "29 201935 7 922 0 1857 1 0 \n", + "... ... ... ... ... ... ... ... \n", + "1499 199126 7 17608 11304 23912 31 20 \n", + "1500 199125 7 16169 10700 21638 28 18 \n", + "1501 199124 7 16171 10071 22271 28 17 \n", + "1502 199123 7 11947 7671 16223 21 13 \n", + "1503 199122 7 15452 9953 20951 27 17 \n", + "1504 199121 7 14903 8975 20831 26 16 \n", + "1505 199120 7 19053 12742 25364 34 23 \n", + "1506 199119 7 16739 11246 22232 29 19 \n", + "1507 199118 7 21385 13882 28888 38 25 \n", + "1508 199117 7 13462 8877 18047 24 16 \n", + "1509 199116 7 14857 10068 19646 26 18 \n", + "1510 199115 7 13975 9781 18169 25 18 \n", + "1511 199114 7 12265 7684 16846 22 14 \n", + "1512 199113 7 9567 6041 13093 17 11 \n", + "1513 199112 7 10864 7331 14397 19 13 \n", + "1514 199111 7 15574 11184 19964 27 19 \n", + "1515 199110 7 16643 11372 21914 29 20 \n", + "1516 199109 7 13741 8780 18702 24 15 \n", + "1517 199108 7 13289 8813 17765 23 15 \n", + "1518 199107 7 12337 8077 16597 22 15 \n", + "1519 199106 7 10877 7013 14741 19 12 \n", + "1520 199105 7 10442 6544 14340 18 11 \n", + "1521 199104 7 7913 4563 11263 14 8 \n", + "1522 199103 7 15387 10484 20290 27 18 \n", + "1523 199102 7 16277 11046 21508 29 20 \n", + "1524 199101 7 15565 10271 20859 27 18 \n", + "1525 199052 7 19375 13295 25455 34 23 \n", + "1526 199051 7 19080 13807 24353 34 25 \n", + "1527 199050 7 11079 6660 15498 20 12 \n", + "1528 199049 7 1143 0 2610 2 0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 16 FR France \n", + "1 19 FR France \n", + "2 18 FR France \n", + "3 26 FR France \n", + "4 20 FR France \n", + "5 18 FR France \n", + "6 18 FR France \n", + "7 16 FR France \n", + "8 15 FR France \n", + "9 12 FR France \n", + "10 13 FR France \n", + "11 19 FR France \n", + "12 16 FR France \n", + "13 12 FR France \n", + "14 13 FR France \n", + "15 13 FR France \n", + "16 11 FR France \n", + "17 15 FR France \n", + "18 6 FR France \n", + "19 10 FR France \n", + "20 12 FR France \n", + "21 10 FR France \n", + "22 13 FR France \n", + "23 9 FR France \n", + "24 9 FR France \n", + "25 8 FR France \n", + "26 8 FR France \n", + "27 2 FR France \n", + "28 4 FR France \n", + "29 2 FR France \n", + "... ... ... ... \n", + "1499 42 FR France \n", + "1500 38 FR France \n", + "1501 39 FR France \n", + "1502 29 FR France \n", + "1503 37 FR France \n", + "1504 36 FR France \n", + "1505 45 FR France \n", + "1506 39 FR France \n", + "1507 51 FR France \n", + "1508 32 FR France \n", + "1509 34 FR France \n", + "1510 32 FR France \n", + "1511 30 FR France \n", + "1512 23 FR France \n", + "1513 25 FR France \n", + "1514 35 FR France \n", + "1515 38 FR France \n", + "1516 33 FR France \n", + "1517 31 FR France \n", + "1518 29 FR France \n", + "1519 26 FR France \n", + "1520 25 FR France \n", + "1521 20 FR France \n", + "1522 36 FR France \n", + "1523 38 FR France \n", + "1524 36 FR France \n", + "1525 45 FR France \n", + "1526 43 FR France \n", + "1527 28 FR France \n", + "1528 5 FR France \n", + "\n", + "[1529 rows x 10 columns]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "raw_data = pd.read_csv(data_url, skiprows=1)\n", + "raw_data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + " Y a-t-il des points manquants dans ce jeux de données ? Non" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "raw_data[raw_data.isnull().any(axis=1)]\n", + "data = raw_data.copy()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Nos données utilisent une convention inhabituelle: le numéro de semaine est collé à l'année, donnant l'impression qu'il s'agit de nombre entier. C'est comme ça que Pandas les interprète.Un deuxième problème est que Pandas ne comprend pas les numéros de semaine. Il faut lui fournir les dates de début et de fin de semaine. Nous utilisons pour cela la bibliothèque isoweek. Comme la conversion des semaines est devenu assez complexe, nous écrivons une petite fonction Python pour cela. Ensuite, nous l'appliquons à tous les points de nos donnés. Les résultats vont dans une nouvelle colonne 'period'." + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "def convert_week(year_and_week_int):\n", + " year_and_week_str = str(year_and_week_int)\n", + " year = int(year_and_week_str[:4])\n", + " week = int(year_and_week_str[4:])\n", + " w = isoweek.Week(year, week)\n", + " return pd.Period(w.day(0), 'W')\n", + "\n", + "data['period'] = [convert_week(yw) for yw in data['week']]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Il reste deux petites modifications à faire.Premièrement, nous définissons les périodes d'observation\n", + "comme nouvel index de notre jeux de données. Ceci en fait\n", + "une suite chronologique, ce qui sera pratique par la suite.Deuxièmement, nous trions les points par période, dans\n", + "le sens chronologique." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": {