diff --git a/module3/exo2/module3_exo1_analyse-syndrome-grippal.ipynb b/module3/exo2/module3_exo1_analyse-syndrome-grippal.ipynb deleted file mode 100644 index 0240ae2dbf095babfcb40b913f53031ce66af174..0000000000000000000000000000000000000000 --- a/module3/exo2/module3_exo1_analyse-syndrome-grippal.ipynb +++ /dev/null @@ -1,1358 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Incidence du syndrome grippal" - ] - }, - { - "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": [ - "Les données de l'incidence du syndrome grippal sont disponibles du site Web du [Réseau Sentinelles](http://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 1984 et se termine avec une semaine récente." - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [], - "source": [ - "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\"" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Téléchargement des données si les données n'existent pas en local." - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": {}, - "outputs": [], - "source": [ - "data_file = \"syndrome-grippal.csv\"\n", - "\n", - "import os\n", - "import urllib.request\n", - "if not os.path.exists(data_file):\n", - " urllib.request.urlretrieve(data_url, data_file)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Voici l'explication des colonnes données [sur le site d'origine](https://ns.sentiweb.fr/incidence/csv-schema-v1.json):\n", - "\n", - "| Nom de colonne | Libellé de colonne |\n", - "|----------------|-----------------------------------------------------------------------------------------------------------------------------------|\n", - "| week | Semaine calendaire (ISO 8601) |\n", - "| indicator | Code de l'indicateur de surveillance |\n", - "| inc | Estimation de l'incidence de consultations en nombre de cas |\n", - "| inc_low | Estimation de la borne inférieure de l'IC95% du nombre de cas de consultation |\n", - "| inc_up | Estimation de la borne supérieure de l'IC95% du nombre de cas de consultation |\n", - "| inc100 | Estimation du taux d'incidence du nombre de cas de consultation (en cas pour 100,000 habitants) |\n", - "| inc100_low | Estimation de la borne inférieure de l'IC95% du taux d'incidence du nombre de cas de consultation (en cas pour 100,000 habitants) |\n", - "| inc100_up | Estimation de la borne supérieure de l'IC95% du taux d'incidence du nombre de cas de consultation (en cas pour 100,000 habitants) |\n", - "| geo_insee | Code de la zone géographique concernée (Code INSEE) http://www.insee.fr/fr/methodes/nomenclatures/cog/ |\n", - "| geo_name | Libellé de la zone géographique (ce libellé peut être modifié sans préavis) |\n", - "\n", - "La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skiprows=1`." - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "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
020233634179134243.049339.06352.074.0FRFrance
120233533194526217.037673.04839.057.0FRFrance
220233432666321057.032269.04032.048.0FRFrance
320233331914413161.025127.02920.038.0FRFrance
420233231464110285.018997.02215.029.0FRFrance
520233131528610705.019867.02316.030.0FRFrance
62023303132058647.017763.02013.027.0FRFrance
72023293111227113.015131.01711.023.0FRFrance
8202328391795703.012655.0149.019.0FRFrance
9202327389995763.012235.0149.019.0FRFrance
10202326390235934.012112.0149.019.0FRFrance
112023253100906739.013441.01510.020.0FRFrance
122023243113087639.014977.01711.023.0FRFrance
1320232331430010661.017939.02217.027.0FRFrance
1420232231830313822.022784.02821.035.0FRFrance
1520232131646012188.020732.02519.031.0FRFrance
1620232031616211963.020361.02418.030.0FRFrance
1720231931690112577.021225.02518.032.0FRFrance
1820231831992915402.024456.03023.037.0FRFrance
1920231732700721779.032235.04133.049.0FRFrance
2020231632787522767.032983.04234.050.0FRFrance
2120231533745530993.043917.05646.066.0FRFrance
2220231434806040671.055449.07261.083.0FRFrance
2320231336485956800.072918.09886.0110.0FRFrance
2420231237275064499.081001.010997.0121.0FRFrance
2520231137463866420.082856.0112100.0124.0FRFrance
2620231037636868243.084493.0115103.0127.0FRFrance
2720230936206254778.069346.09382.0104.0FRFrance
2820230837639168065.084717.0115102.0128.0FRFrance
2920230738985180397.099305.0135121.0149.0FRFrance
.................................
199819852132609619621.032571.04735.059.0FRFrance
199919852032789620885.034907.05138.064.0FRFrance
200019851934315432821.053487.07859.097.0FRFrance
200119851834055529935.051175.07455.093.0FRFrance
200219851733405324366.043740.06244.080.0FRFrance
200319851635036236451.064273.09166.0116.0FRFrance
200419851536388145538.082224.011683.0149.0FRFrance
20051985143134545114400.0154690.0244207.0281.0FRFrance
20061985133197206176080.0218332.0357319.0395.0FRFrance
20071985123245240223304.0267176.0445405.0485.0FRFrance
20081985113276205252399.0300011.0501458.0544.0FRFrance
20091985103353231326279.0380183.0640591.0689.0FRFrance
20101985093369895341109.0398681.0670618.0722.0FRFrance
20111985083389886359529.0420243.0707652.0762.0FRFrance
20121985073471852432599.0511105.0855784.0926.0FRFrance
20131985063565825518011.0613639.01026939.01113.0FRFrance
20141985053637302592795.0681809.011551074.01236.0FRFrance
20151985043424937390794.0459080.0770708.0832.0FRFrance
20161985033213901174689.0253113.0388317.0459.0FRFrance
201719850239758680949.0114223.0177147.0207.0FRFrance
201819850138548965918.0105060.0155120.0190.0FRFrance
201919845238483060602.0109058.0154110.0198.0FRFrance
2020198451310172680242.0123210.0185146.0224.0FRFrance
20211984503123680101401.0145959.0225184.0266.0FRFrance
2022198449310107381684.0120462.0184149.0219.0FRFrance
202319844837862060634.096606.0143110.0176.0FRFrance
202419844737202954274.089784.013199.0163.0FRFrance
202519844638733067686.0106974.0159123.0195.0FRFrance
20261984453135223101414.0169032.0246184.0308.0FRFrance
202719844436842220056.0116788.012537.0213.0FRFrance
\n", - "

2028 rows × 10 columns

\n", - "
" - ], - "text/plain": [ - " week indicator inc inc_low inc_up inc100 inc100_low \\\n", - "0 202336 3 41791 34243.0 49339.0 63 52.0 \n", - "1 202335 3 31945 26217.0 37673.0 48 39.0 \n", - "2 202334 3 26663 21057.0 32269.0 40 32.0 \n", - "3 202333 3 19144 13161.0 25127.0 29 20.0 \n", - "4 202332 3 14641 10285.0 18997.0 22 15.0 \n", - "5 202331 3 15286 10705.0 19867.0 23 16.0 \n", - "6 202330 3 13205 8647.0 17763.0 20 13.0 \n", - "7 202329 3 11122 7113.0 15131.0 17 11.0 \n", - "8 202328 3 9179 5703.0 12655.0 14 9.0 \n", - "9 202327 3 8999 5763.0 12235.0 14 9.0 \n", - "10 202326 3 9023 5934.0 12112.0 14 9.0 \n", - "11 202325 3 10090 6739.0 13441.0 15 10.0 \n", - "12 202324 3 11308 7639.0 14977.0 17 11.0 \n", - "13 202323 3 14300 10661.0 17939.0 22 17.0 \n", - "14 202322 3 18303 13822.0 22784.0 28 21.0 \n", - "15 202321 3 16460 12188.0 20732.0 25 19.0 \n", - "16 202320 3 16162 11963.0 20361.0 24 18.0 \n", - "17 202319 3 16901 12577.0 21225.0 25 18.0 \n", - "18 202318 3 19929 15402.0 24456.0 30 23.0 \n", - "19 202317 3 27007 21779.0 32235.0 41 33.0 \n", - "20 202316 3 27875 22767.0 32983.0 42 34.0 \n", - "21 202315 3 37455 30993.0 43917.0 56 46.0 \n", - "22 202314 3 48060 40671.0 55449.0 72 61.0 \n", - "23 202313 3 64859 56800.0 72918.0 98 86.0 \n", - "24 202312 3 72750 64499.0 81001.0 109 97.0 \n", - "25 202311 3 74638 66420.0 82856.0 112 100.0 \n", - "26 202310 3 76368 68243.0 84493.0 115 103.0 \n", - "27 202309 3 62062 54778.0 69346.0 93 82.0 \n", - "28 202308 3 76391 68065.0 84717.0 115 102.0 \n", - "29 202307 3 89851 80397.0 99305.0 135 121.0 \n", - "... ... ... ... ... ... ... ... \n", - "1998 198521 3 26096 19621.0 32571.0 47 35.0 \n", - "1999 198520 3 27896 20885.0 34907.0 51 38.0 \n", - "2000 198519 3 43154 32821.0 53487.0 78 59.0 \n", - "2001 198518 3 40555 29935.0 51175.0 74 55.0 \n", - "2002 198517 3 34053 24366.0 43740.0 62 44.0 \n", - "2003 198516 3 50362 36451.0 64273.0 91 66.0 \n", - "2004 198515 3 63881 45538.0 82224.0 116 83.0 \n", - "2005 198514 3 134545 114400.0 154690.0 244 207.0 \n", - "2006 198513 3 197206 176080.0 218332.0 357 319.0 \n", - "2007 198512 3 245240 223304.0 267176.0 445 405.0 \n", - "2008 198511 3 276205 252399.0 300011.0 501 458.0 \n", - "2009 198510 3 353231 326279.0 380183.0 640 591.0 \n", - "2010 198509 3 369895 341109.0 398681.0 670 618.0 \n", - "2011 198508 3 389886 359529.0 420243.0 707 652.0 \n", - "2012 198507 3 471852 432599.0 511105.0 855 784.0 \n", - "2013 198506 3 565825 518011.0 613639.0 1026 939.0 \n", - "2014 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", - "2015 198504 3 424937 390794.0 459080.0 770 708.0 \n", - "2016 198503 3 213901 174689.0 253113.0 388 317.0 \n", - "2017 198502 3 97586 80949.0 114223.0 177 147.0 \n", - "2018 198501 3 85489 65918.0 105060.0 155 120.0 \n", - "2019 198452 3 84830 60602.0 109058.0 154 110.0 \n", - "2020 198451 3 101726 80242.0 123210.0 185 146.0 \n", - "2021 198450 3 123680 101401.0 145959.0 225 184.0 \n", - "2022 198449 3 101073 81684.0 120462.0 184 149.0 \n", - "2023 198448 3 78620 60634.0 96606.0 143 110.0 \n", - "2024 198447 3 72029 54274.0 89784.0 131 99.0 \n", - "2025 198446 3 87330 67686.0 106974.0 159 123.0 \n", - "2026 198445 3 135223 101414.0 169032.0 246 184.0 \n", - "2027 198444 3 68422 20056.0 116788.0 125 37.0 \n", - "\n", - " inc100_up geo_insee geo_name \n", - "0 74.0 FR France \n", - "1 57.0 FR France \n", - "2 48.0 FR France \n", - "3 38.0 FR France \n", - "4 29.0 FR France \n", - "5 30.0 FR France \n", - "6 27.0 FR France \n", - "7 23.0 FR France \n", - "8 19.0 FR France \n", - "9 19.0 FR France \n", - "10 19.0 FR France \n", - "11 20.0 FR France \n", - "12 23.0 FR France \n", - "13 27.0 FR France \n", - "14 35.0 FR France \n", - "15 31.0 FR France \n", - "16 30.0 FR France \n", - "17 32.0 FR France \n", - "18 37.0 FR France \n", - "19 49.0 FR France \n", - "20 50.0 FR France \n", - "21 66.0 FR France \n", - "22 83.0 FR France \n", - "23 110.0 FR France \n", - "24 121.0 FR France \n", - "25 124.0 FR France \n", - "26 127.0 FR France \n", - "27 104.0 FR France \n", - "28 128.0 FR France \n", - "29 149.0 FR France \n", - "... ... ... ... \n", - "1998 59.0 FR France \n", - "1999 64.0 FR France \n", - "2000 97.0 FR France \n", - "2001 93.0 FR France \n", - "2002 80.0 FR France \n", - "2003 116.0 FR France \n", - "2004 149.0 FR France \n", - "2005 281.0 FR France \n", - "2006 395.0 FR France \n", - "2007 485.0 FR France \n", - "2008 544.0 FR France \n", - "2009 689.0 FR France \n", - "2010 722.0 FR France \n", - "2011 762.0 FR France \n", - "2012 926.0 FR France \n", - "2013 1113.0 FR France \n", - "2014 1236.0 FR France \n", - "2015 832.0 FR France \n", - "2016 459.0 FR France \n", - "2017 207.0 FR France \n", - "2018 190.0 FR France \n", - "2019 198.0 FR France \n", - "2020 224.0 FR France \n", - "2021 266.0 FR France \n", - "2022 219.0 FR France \n", - "2023 176.0 FR France \n", - "2024 163.0 FR France \n", - "2025 195.0 FR France \n", - "2026 308.0 FR France \n", - "2027 213.0 FR France \n", - "\n", - "[2028 rows x 10 columns]" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "raw_data = pd.read_csv(data_file, skiprows=1)\n", - "raw_data" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Y a-t-il des points manquants dans ce jeux de données ? Oui, la semaine 19 de l'année 1989 n'a pas de valeurs associées." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "raw_data[raw_data.isnull().any(axis=1)]" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Nous éliminons ce point, ce qui n'a pas d'impact fort sur notre analyse qui est assez simple." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "data = raw_data.dropna().copy()\n", - "data" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Nos données utilisent une convention inhabituelle: le numéro de\n", - "semaine est collé à l'année, donnant l'impression qu'il s'agit\n", - "de nombre entier. C'est comme ça que Pandas les interprète.\n", - " \n", - "Un deuxième problème est que Pandas ne comprend pas les numéros de\n", - "semaine. Il faut lui fournir les dates de début et de fin de\n", - "semaine. Nous utilisons pour cela la bibliothèque `isoweek`.\n", - "\n", - "Comme la conversion des semaines est devenu assez complexe, nous\n", - "écrivons une petite fonction Python pour cela. Ensuite, nous\n", - "l'appliquons à tous les points de nos donnés. Les résultats vont\n", - "dans une nouvelle colonne 'period'." - ] - }, - { - "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']]" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Il restent deux petites modifications à faire.\n", - "\n", - "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.\n", - "\n", - "Deuxièmement, nous trions les points par période, dans\n", - "le sens chronologique." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "sorted_data = data.set_index('period').sort_index()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Nous vérifions la cohérence des données. Entre la fin d'une période et\n", - "le début de la période qui suit, la différence temporelle doit être\n", - "zéro, ou au moins très faible. Nous laissons une \"marge d'erreur\"\n", - "d'une seconde.\n", - "\n", - "Ceci s'avère tout à fait juste sauf pour deux périodes consécutives\n", - "entre lesquelles il manque une semaine.\n", - "\n", - "Nous reconnaissons ces dates: c'est la semaine sans observations\n", - "que nous avions supprimées !" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "periods = sorted_data.index\n", - "for p1, p2 in zip(periods[:-1], periods[1:]):\n", - " delta = p2.to_timestamp() - p1.end_time\n", - " if delta > pd.Timedelta('1s'):\n", - " print(p1, p2)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Un premier regard sur les données !" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "sorted_data['inc'].plot()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Un zoom sur les dernières années montre mieux la situation des pics en hiver. Le creux des incidences se trouve en été." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "sorted_data['inc'][-200:].plot()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Etude de l'incidence annuelle" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Etant donné que le pic de l'épidémie se situe en hiver, à cheval\n", - "entre deux années civiles, nous définissons la période de référence\n", - "entre deux minima de l'incidence, du 1er août de l'année $N$ au\n", - "1er août de l'année $N+1$.\n", - "\n", - "Notre tâche est un peu compliquée par le fait que l'année ne comporte\n", - "pas un nombre entier de semaines. Nous modifions donc un peu nos périodes\n", - "de référence: à la place du 1er août de chaque année, nous utilisons le\n", - "premier jour de la semaine qui contient le 1er août.\n", - "\n", - "Comme l'incidence de syndrome grippal est très faible en été, cette\n", - "modification ne risque pas de fausser nos conclusions.\n", - "\n", - "Encore un petit détail: les données commencent an octobre 1984, ce qui\n", - "rend la première année incomplète. Nous commençons donc l'analyse en 1985." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "first_august_week = [pd.Period(pd.Timestamp(y, 8, 1), 'W')\n", - " for y in range(1985,\n", - " sorted_data.index[-1].year)]" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "En partant de cette liste des semaines qui contiennent un 1er août, nous obtenons nos intervalles d'environ un an comme les périodes entre deux semaines adjacentes dans cette liste. Nous calculons les sommes des incidences hebdomadaires pour toutes ces périodes.\n", - "\n", - "Nous vérifions également que ces périodes contiennent entre 51 et 52 semaines, pour nous protéger contre des éventuelles erreurs dans notre code." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "year = []\n", - "yearly_incidence = []\n", - "for week1, week2 in zip(first_august_week[:-1],\n", - " first_august_week[1:]):\n", - " one_year = sorted_data['inc'][week1:week2-1]\n", - " assert abs(len(one_year)-52) < 2\n", - " yearly_incidence.append(one_year.sum())\n", - " year.append(week2.year)\n", - "yearly_incidence = pd.Series(data=yearly_incidence, index=year)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Voici les incidences annuelles." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "yearly_incidence.plot(style='*')" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Une liste triée permet de plus facilement répérer les valeurs les plus élevées (à la fin)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "yearly_incidence.sort_values()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Enfin, un histogramme montre bien que les épidémies fortes, qui touchent environ 10% de la population\n", - " française, sont assez rares: il y en eu trois au cours des 35 dernières années." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "yearly_incidence.hist(xrot=20)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, - "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": 1 -}