{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Analyse de l'incidence de la 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\n", "import os" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Les données de l'incidence du syndrome grippal sont disponibles du site Web du Réseau Sentinelles. 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 1984 et se termine avec une semaine récente." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "remote_url = \"https://www.sentiweb.fr/datasets/incidence-PAY-7.csv\"\n", "local_path = r\"\\module3\\exo3\\incidence-PAY-7.csv\"\n", "if os.path.exists(local_path):\n", " data_url = local_path\n", " raw_data = pd.read_csv(local_path, skiprows=1, comment='#')\n", "else:\n", " raw_data = pd.read_csv(remote_url, skiprows=1, comment='#')\n", " data.to_csv(local_path)\n", " data_url = local_path" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true }, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
01202335794301986103FRFrance
1220233471179112347204FRFrance
232023337330811845432528FRFrance
342023327799611201487212222FRFrance
452023317331813985238528FRFrance
5620233075821326983739513FRFrance
67202329713558829718819201228FRFrance
78202328767004043935710614FRFrance
89202327772534599990711715FRFrance
91020232679192622312161141018FRFrance
1011202325711498825714739171222FRFrance
1112202324711115796814262171222FRFrance
121320232371256361341899219929FRFrance
1314202322712184812516243181224FRFrance
1415202321711349759815100171123FRFrance
15162023207900046151338514721FRFrance
16172023197934460911259714919FRFrance
1718202318710671729114051161121FRFrance
18192023177918461621220614919FRFrance
1920202316711387801414760171222FRFrance
2021202315714040761320467211131FRFrance
21222023147152471103219462231729FRFrance
2223202313713322970016944201525FRFrance
2324202312710374721813530161121FRFrance
242520231174919288069587410FRFrance
252620231074854273169777410FRFrance
2627202309770044548946011715FRFrance
27282023087817553161103412816FRFrance
2829202307765953782940810614FRFrance
29302023067959560171317314919FRFrance
....................................
167916801991267176081130423912312042FRFrance
168016811991257161691070021638281838FRFrance
168116821991247161711007122271281739FRFrance
16821683199123711947767116223211329FRFrance
16831684199122715452995320951271737FRFrance
16841685199121714903897520831261636FRFrance
168516861991207190531274225364342345FRFrance
168616871991197167391124622232291939FRFrance
168716881991187213851388228888382551FRFrance
16881689199117713462887718047241632FRFrance
168916901991167148571006819646261834FRFrance
16901691199115713975978118169251832FRFrance
16911692199114712265768416846221430FRFrance
1692169319911379567604113093171123FRFrance
16931694199112710864733114397191325FRFrance
169416951991117155741118419964271935FRFrance
169516961991107166431137221914292038FRFrance
16961697199109713741878018702241533FRFrance
16971698199108713289881317765231531FRFrance
16981699199107712337807716597221529FRFrance
16991700199106710877701314741191226FRFrance
17001701199105710442654414340181125FRFrance
170117021991047791345631126314820FRFrance
170217031991037153871048420290271836FRFrance
170317041991027162771104621508292038FRFrance
170417051991017155651027120859271836FRFrance
170517061990527193751329525455342345FRFrance
170617071990517190801380724353342543FRFrance
17071708199050711079666015498201228FRFrance
170817091990497114302610205FRFrance
\n", "

1709 rows × 11 columns

\n", "
" ], "text/plain": [ " 0 week indicator inc inc_low inc_up inc100 inc100_low \\\n", "0 1 202335 7 943 0 1986 1 0 \n", "1 2 202334 7 1179 11 2347 2 0 \n", "2 3 202333 7 3308 1184 5432 5 2 \n", "3 4 202332 7 7996 1120 14872 12 2 \n", "4 5 202331 7 3318 1398 5238 5 2 \n", "5 6 202330 7 5821 3269 8373 9 5 \n", "6 7 202329 7 13558 8297 18819 20 12 \n", "7 8 202328 7 6700 4043 9357 10 6 \n", "8 9 202327 7 7253 4599 9907 11 7 \n", "9 10 202326 7 9192 6223 12161 14 10 \n", "10 11 202325 7 11498 8257 14739 17 12 \n", "11 12 202324 7 11115 7968 14262 17 12 \n", "12 13 202323 7 12563 6134 18992 19 9 \n", "13 14 202322 7 12184 8125 16243 18 12 \n", "14 15 202321 7 11349 7598 15100 17 11 \n", "15 16 202320 7 9000 4615 13385 14 7 \n", "16 17 202319 7 9344 6091 12597 14 9 \n", "17 18 202318 7 10671 7291 14051 16 11 \n", "18 19 202317 7 9184 6162 12206 14 9 \n", "19 20 202316 7 11387 8014 14760 17 12 \n", "20 21 202315 7 14040 7613 20467 21 11 \n", "21 22 202314 7 15247 11032 19462 23 17 \n", "22 23 202313 7 13322 9700 16944 20 15 \n", "23 24 202312 7 10374 7218 13530 16 11 \n", "24 25 202311 7 4919 2880 6958 7 4 \n", "25 26 202310 7 4854 2731 6977 7 4 \n", "26 27 202309 7 7004 4548 9460 11 7 \n", "27 28 202308 7 8175 5316 11034 12 8 \n", "28 29 202307 7 6595 3782 9408 10 6 \n", "29 30 202306 7 9595 6017 13173 14 9 \n", "... ... ... ... ... ... ... ... ... \n", "1679 1680 199126 7 17608 11304 23912 31 20 \n", "1680 1681 199125 7 16169 10700 21638 28 18 \n", "1681 1682 199124 7 16171 10071 22271 28 17 \n", "1682 1683 199123 7 11947 7671 16223 21 13 \n", "1683 1684 199122 7 15452 9953 20951 27 17 \n", "1684 1685 199121 7 14903 8975 20831 26 16 \n", "1685 1686 199120 7 19053 12742 25364 34 23 \n", "1686 1687 199119 7 16739 11246 22232 29 19 \n", "1687 1688 199118 7 21385 13882 28888 38 25 \n", "1688 1689 199117 7 13462 8877 18047 24 16 \n", "1689 1690 199116 7 14857 10068 19646 26 18 \n", "1690 1691 199115 7 13975 9781 18169 25 18 \n", "1691 1692 199114 7 12265 7684 16846 22 14 \n", "1692 1693 199113 7 9567 6041 13093 17 11 \n", "1693 1694 199112 7 10864 7331 14397 19 13 \n", "1694 1695 199111 7 15574 11184 19964 27 19 \n", "1695 1696 199110 7 16643 11372 21914 29 20 \n", "1696 1697 199109 7 13741 8780 18702 24 15 \n", "1697 1698 199108 7 13289 8813 17765 23 15 \n", "1698 1699 199107 7 12337 8077 16597 22 15 \n", "1699 1700 199106 7 10877 7013 14741 19 12 \n", "1700 1701 199105 7 10442 6544 14340 18 11 \n", "1701 1702 199104 7 7913 4563 11263 14 8 \n", "1702 1703 199103 7 15387 10484 20290 27 18 \n", "1703 1704 199102 7 16277 11046 21508 29 20 \n", "1704 1705 199101 7 15565 10271 20859 27 18 \n", "1705 1706 199052 7 19375 13295 25455 34 23 \n", "1706 1707 199051 7 19080 13807 24353 34 25 \n", "1707 1708 199050 7 11079 6660 15498 20 12 \n", "1708 1709 199049 7 1143 0 2610 2 0 \n", "\n", " inc100_up geo_insee geo_name \n", "0 3 FR France \n", "1 4 FR France \n", "2 8 FR France \n", "3 22 FR France \n", "4 8 FR France \n", "5 13 FR France \n", "6 28 FR France \n", "7 14 FR France \n", "8 15 FR France \n", "9 18 FR France \n", "10 22 FR France \n", "11 22 FR France \n", "12 29 FR France \n", "13 24 FR France \n", "14 23 FR France \n", "15 21 FR France \n", "16 19 FR France \n", "17 21 FR France \n", "18 19 FR France \n", "19 22 FR France \n", "20 31 FR France \n", "21 29 FR France \n", "22 25 FR France \n", "23 21 FR France \n", "24 10 FR France \n", "25 10 FR France \n", "26 15 FR France \n", "27 16 FR France \n", "28 14 FR France \n", "29 19 FR France \n", "... ... ... ... \n", "1679 42 FR France \n", "1680 38 FR France \n", "1681 39 FR France \n", "1682 29 FR France \n", "1683 37 FR France \n", "1684 36 FR France \n", "1685 45 FR France \n", "1686 39 FR France \n", "1687 51 FR France \n", "1688 32 FR France \n", "1689 34 FR France \n", "1690 32 FR France \n", "1691 30 FR France \n", "1692 23 FR France \n", "1693 25 FR France \n", "1694 35 FR France \n", "1695 38 FR France \n", "1696 33 FR France \n", "1697 31 FR France \n", "1698 29 FR France \n", "1699 26 FR France \n", "1700 25 FR France \n", "1701 20 FR France \n", "1702 36 FR France \n", "1703 38 FR France \n", "1704 36 FR France \n", "1705 45 FR France \n", "1706 43 FR France \n", "1707 28 FR France \n", "1708 5 FR France \n", "\n", "[1709 rows x 11 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = raw_data.dropna(axis=1)\n", "raw_data.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "On s'assure qu'il ny a pas de valeurs manquantes" ] }, { "cell_type": "code", "execution_count": 4, "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", "
0weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [0, week, indicator, inc, inc_low, inc_up, inc100, inc100_low, inc100_up, geo_insee, geo_name]\n", "Index: []" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data[raw_data.isnull().any(axis=1)]" ] }, { "cell_type": "code", "execution_count": 6, "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", "
0weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
01202335794301986103FRFrance
1220233471179112347204FRFrance
232023337330811845432528FRFrance
342023327799611201487212222FRFrance
452023317331813985238528FRFrance
\n", "
" ], "text/plain": [ " 0 week indicator inc inc_low inc_up inc100 inc100_low inc100_up \\\n", "0 1 202335 7 943 0 1986 1 0 3 \n", "1 2 202334 7 1179 11 2347 2 0 4 \n", "2 3 202333 7 3308 1184 5432 5 2 8 \n", "3 4 202332 7 7996 1120 14872 12 2 22 \n", "4 5 202331 7 3318 1398 5238 5 2 8 \n", "\n", " geo_insee geo_name \n", "0 FR France \n", "1 FR France \n", "2 FR France \n", "3 FR France \n", "4 FR France " ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data = raw_data.dropna().copy()\n", "data.head()" ] }, { "cell_type": "code", "execution_count": null, "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']]" ] } ], "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 }