diff --git a/module3/exo1/analyse-syndrome-grippal.ipynb b/module3/exo1/analyse-syndrome-grippal.ipynb index 59d72b5b58a3ae26346460dd39e62a39c55243d7..e111ce950ffe4be3dbaf787ef6a90ec5b1ec2512 100644 --- a/module3/exo1/analyse-syndrome-grippal.ipynb +++ b/module3/exo1/analyse-syndrome-grippal.ipynb @@ -9,14 +9,15 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", - "import isoweek" + "import isoweek\n", + "import os.path" ] }, { @@ -28,13 +29,12 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, + "execution_count": 3, + "metadata": {}, "outputs": [], "source": [ - "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\"" + "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\"\n", + "data_local_path = \"https://app-learninglab.inria.fr/moocrr/jupyter/user/a12707740afaaa5fb65905502cc0ab13/notebooks/work/module3/exo1/incidence-PAY-3.csv\"" ] }, { @@ -56,16 +56,994 @@ "| 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`." + "La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skiprows=1`. Avant de télécharger le fichier .csv sur le site d'origine, on vérifie si une copie locale existe. Pour cela, on utilise la librairie os.path dont la fonction exists() renvoie True si le fichier renseigné en argument existe et False sinon. Ici comme le notebook est accessible sur le site de l'inria, la notion de localité est relative bien sûr. " ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "False\n" + ] + }, + { + "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
020234236733157544.077118.010186.0116.0FRFrance
120234135927551833.066717.08978.0100.0FRFrance
220234036889460069.077719.010491.0117.0FRFrance
320233937200363452.080554.010895.0121.0FRFrance
420233836321855227.071209.09583.0107.0FRFrance
520233734908542079.056091.07463.085.0FRFrance
620233633824732237.044257.05849.067.0FRFrance
720233533169526013.037377.04839.057.0FRFrance
820233432666321057.032269.04032.048.0FRFrance
920233331914413161.025127.02920.038.0FRFrance
1020233231464110285.018997.02215.029.0FRFrance
1120233131528610705.019867.02316.030.0FRFrance
122023303132058647.017763.02013.027.0FRFrance
132023293111227113.015131.01711.023.0FRFrance
14202328391795703.012655.0149.019.0FRFrance
15202327389995763.012235.0149.019.0FRFrance
16202326390235934.012112.0149.019.0FRFrance
172023253100906739.013441.01510.020.0FRFrance
182023243113087639.014977.01711.023.0FRFrance
1920232331430010661.017939.02217.027.0FRFrance
2020232231830313822.022784.02821.035.0FRFrance
2120232131646012188.020732.02519.031.0FRFrance
2220232031616211963.020361.02418.030.0FRFrance
2320231931690112577.021225.02518.032.0FRFrance
2420231831992915402.024456.03023.037.0FRFrance
2520231732700721779.032235.04133.049.0FRFrance
2620231632787522767.032983.04234.050.0FRFrance
2720231533745530993.043917.05646.066.0FRFrance
2820231434806040671.055449.07261.083.0FRFrance
2920231336485956800.072918.09886.0110.0FRFrance
.................................
200419852132609619621.032571.04735.059.0FRFrance
200519852032789620885.034907.05138.064.0FRFrance
200619851934315432821.053487.07859.097.0FRFrance
200719851834055529935.051175.07455.093.0FRFrance
200819851733405324366.043740.06244.080.0FRFrance
200919851635036236451.064273.09166.0116.0FRFrance
201019851536388145538.082224.011683.0149.0FRFrance
20111985143134545114400.0154690.0244207.0281.0FRFrance
20121985133197206176080.0218332.0357319.0395.0FRFrance
20131985123245240223304.0267176.0445405.0485.0FRFrance
20141985113276205252399.0300011.0501458.0544.0FRFrance
20151985103353231326279.0380183.0640591.0689.0FRFrance
20161985093369895341109.0398681.0670618.0722.0FRFrance
20171985083389886359529.0420243.0707652.0762.0FRFrance
20181985073471852432599.0511105.0855784.0926.0FRFrance
20191985063565825518011.0613639.01026939.01113.0FRFrance
20201985053637302592795.0681809.011551074.01236.0FRFrance
20211985043424937390794.0459080.0770708.0832.0FRFrance
20221985033213901174689.0253113.0388317.0459.0FRFrance
202319850239758680949.0114223.0177147.0207.0FRFrance
202419850138548965918.0105060.0155120.0190.0FRFrance
202519845238483060602.0109058.0154110.0198.0FRFrance
2026198451310172680242.0123210.0185146.0224.0FRFrance
20271984503123680101401.0145959.0225184.0266.0FRFrance
2028198449310107381684.0120462.0184149.0219.0FRFrance
202919844837862060634.096606.0143110.0176.0FRFrance
203019844737202954274.089784.013199.0163.0FRFrance
203119844638733067686.0106974.0159123.0195.0FRFrance
20321984453135223101414.0169032.0246184.0308.0FRFrance
203319844436842220056.0116788.012537.0213.0FRFrance
\n", + "

2034 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202342 3 67331 57544.0 77118.0 101 86.0 \n", + "1 202341 3 59275 51833.0 66717.0 89 78.0 \n", + "2 202340 3 68894 60069.0 77719.0 104 91.0 \n", + "3 202339 3 72003 63452.0 80554.0 108 95.0 \n", + "4 202338 3 63218 55227.0 71209.0 95 83.0 \n", + "5 202337 3 49085 42079.0 56091.0 74 63.0 \n", + "6 202336 3 38247 32237.0 44257.0 58 49.0 \n", + "7 202335 3 31695 26013.0 37377.0 48 39.0 \n", + "8 202334 3 26663 21057.0 32269.0 40 32.0 \n", + "9 202333 3 19144 13161.0 25127.0 29 20.0 \n", + "10 202332 3 14641 10285.0 18997.0 22 15.0 \n", + "11 202331 3 15286 10705.0 19867.0 23 16.0 \n", + "12 202330 3 13205 8647.0 17763.0 20 13.0 \n", + "13 202329 3 11122 7113.0 15131.0 17 11.0 \n", + "14 202328 3 9179 5703.0 12655.0 14 9.0 \n", + "15 202327 3 8999 5763.0 12235.0 14 9.0 \n", + "16 202326 3 9023 5934.0 12112.0 14 9.0 \n", + "17 202325 3 10090 6739.0 13441.0 15 10.0 \n", + "18 202324 3 11308 7639.0 14977.0 17 11.0 \n", + "19 202323 3 14300 10661.0 17939.0 22 17.0 \n", + "20 202322 3 18303 13822.0 22784.0 28 21.0 \n", + "21 202321 3 16460 12188.0 20732.0 25 19.0 \n", + "22 202320 3 16162 11963.0 20361.0 24 18.0 \n", + "23 202319 3 16901 12577.0 21225.0 25 18.0 \n", + "24 202318 3 19929 15402.0 24456.0 30 23.0 \n", + "25 202317 3 27007 21779.0 32235.0 41 33.0 \n", + "26 202316 3 27875 22767.0 32983.0 42 34.0 \n", + "27 202315 3 37455 30993.0 43917.0 56 46.0 \n", + "28 202314 3 48060 40671.0 55449.0 72 61.0 \n", + "29 202313 3 64859 56800.0 72918.0 98 86.0 \n", + "... ... ... ... ... ... ... ... \n", + "2004 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "2005 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "2006 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "2007 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "2008 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "2009 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "2010 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "2011 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "2012 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "2013 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "2014 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "2015 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "2016 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "2017 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "2018 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "2019 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "2020 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "2021 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "2022 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "2023 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "2024 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "2025 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "2026 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "2027 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "2028 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "2029 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "2030 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "2031 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "2032 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "2033 198444 3 68422 20056.0 116788.0 125 37.0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 116.0 FR France \n", + "1 100.0 FR France \n", + "2 117.0 FR France \n", + "3 121.0 FR France \n", + "4 107.0 FR France \n", + "5 85.0 FR France \n", + "6 67.0 FR France \n", + "7 57.0 FR France \n", + "8 48.0 FR France \n", + "9 38.0 FR France \n", + "10 29.0 FR France \n", + "11 30.0 FR France \n", + "12 27.0 FR France \n", + "13 23.0 FR France \n", + "14 19.0 FR France \n", + "15 19.0 FR France \n", + "16 19.0 FR France \n", + "17 20.0 FR France \n", + "18 23.0 FR France \n", + "19 27.0 FR France \n", + "20 35.0 FR France \n", + "21 31.0 FR France \n", + "22 30.0 FR France \n", + "23 32.0 FR France \n", + "24 37.0 FR France \n", + "25 49.0 FR France \n", + "26 50.0 FR France \n", + "27 66.0 FR France \n", + "28 83.0 FR France \n", + "29 110.0 FR France \n", + "... ... ... ... \n", + "2004 59.0 FR France \n", + "2005 64.0 FR France \n", + "2006 97.0 FR France \n", + "2007 93.0 FR France \n", + "2008 80.0 FR France \n", + "2009 116.0 FR France \n", + "2010 149.0 FR France \n", + "2011 281.0 FR France \n", + "2012 395.0 FR France \n", + "2013 485.0 FR France \n", + "2014 544.0 FR France \n", + "2015 689.0 FR France \n", + "2016 722.0 FR France \n", + "2017 762.0 FR France \n", + "2018 926.0 FR France \n", + "2019 1113.0 FR France \n", + "2020 1236.0 FR France \n", + "2021 832.0 FR France \n", + "2022 459.0 FR France \n", + "2023 207.0 FR France \n", + "2024 190.0 FR France \n", + "2025 198.0 FR France \n", + "2026 224.0 FR France \n", + "2027 266.0 FR France \n", + "2028 219.0 FR France \n", + "2029 176.0 FR France \n", + "2030 163.0 FR France \n", + "2031 195.0 FR France \n", + "2032 308.0 FR France \n", + "2033 213.0 FR France \n", + "\n", + "[2034 rows x 10 columns]" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "raw_data = pd.read_csv(data_url, skiprows=1)\n", + "print(os.path.exists(data_local_path))\n", + "if os.path.exists(data_local_path):\n", + " raw_data = pd.read_csv(data_local_path, skiprows=1)\n", + "else:\n", + " raw_data = pd.read_csv(data_url, skiprows=1)\n", "raw_data" ] }, @@ -364,7 +1342,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.1" + "version": "3.6.4" } }, "nbformat": 4,