diff --git a/module3/exercice/Untitled.ipynb b/module3/exercice/Untitled.ipynb new file mode 100644 index 0000000000000000000000000000000000000000..8a921968de21a324250f4101bb23281ff9d9a859 --- /dev/null +++ b/module3/exercice/Untitled.ipynb @@ -0,0 +1,2116 @@ +{ + "cells": [ + { + "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 grippal sont disponibles du site Web du [Réseau Sentinelles](https://www.sentiweb.fr/france/fr/?page=table). 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.(Donées téléchargées le 28/11/2021)" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "data_url = \"incidence-PAY-3.csv\"" + ] + }, + { + "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": 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
020214633987733319.046435.06050.070.0FRFrance
120214532068716810.024564.03125.037.0FRFrance
220214431901715056.022978.02923.035.0FRFrance
320214332704021935.032145.04133.049.0FRFrance
420214232834323382.033304.04335.051.0FRFrance
520214132504320586.029500.03831.045.0FRFrance
620214032628621842.030730.04033.047.0FRFrance
720213932215518014.026296.03428.040.0FRFrance
820213831561412310.018918.02419.029.0FRFrance
920213731367310404.016942.02116.026.0FRFrance
102021363102897505.013073.01612.020.0FRFrance
112021353126099282.015936.01914.024.0FRFrance
122021343130159485.016545.02015.025.0FRFrance
132021333103927042.013742.01611.021.0FRFrance
1420213231558611009.020163.02417.031.0FRFrance
1520213131885513664.024046.02921.037.0FRFrance
162021303139919695.018287.02114.028.0FRFrance
172021293136269618.017634.02115.027.0FRFrance
18202128386365430.011842.0138.018.0FRFrance
192021273106936838.014548.01610.022.0FRFrance
20202126370864109.010063.0116.016.0FRFrance
21202125379425540.010344.0128.016.0FRFrance
22202124348553011.06699.074.010.0FRFrance
23202123367104455.08965.0107.013.0FRFrance
24202122378795495.010263.0128.016.0FRFrance
25202121378275403.010251.0128.016.0FRFrance
262021203102787540.013016.01612.020.0FRFrance
27202119395396860.012218.01410.018.0FRFrance
282021183121359165.015105.01814.022.0FRFrance
292021173120588891.015225.01813.023.0FRFrance
.................................
190419852132609619621.032571.04735.059.0FRFrance
190519852032789620885.034907.05138.064.0FRFrance
190619851934315432821.053487.07859.097.0FRFrance
190719851834055529935.051175.07455.093.0FRFrance
190819851733405324366.043740.06244.080.0FRFrance
190919851635036236451.064273.09166.0116.0FRFrance
191019851536388145538.082224.011683.0149.0FRFrance
19111985143134545114400.0154690.0244207.0281.0FRFrance
19121985133197206176080.0218332.0357319.0395.0FRFrance
19131985123245240223304.0267176.0445405.0485.0FRFrance
19141985113276205252399.0300011.0501458.0544.0FRFrance
19151985103353231326279.0380183.0640591.0689.0FRFrance
19161985093369895341109.0398681.0670618.0722.0FRFrance
19171985083389886359529.0420243.0707652.0762.0FRFrance
19181985073471852432599.0511105.0855784.0926.0FRFrance
19191985063565825518011.0613639.01026939.01113.0FRFrance
19201985053637302592795.0681809.011551074.01236.0FRFrance
19211985043424937390794.0459080.0770708.0832.0FRFrance
19221985033213901174689.0253113.0388317.0459.0FRFrance
192319850239758680949.0114223.0177147.0207.0FRFrance
192419850138548965918.0105060.0155120.0190.0FRFrance
192519845238483060602.0109058.0154110.0198.0FRFrance
1926198451310172680242.0123210.0185146.0224.0FRFrance
19271984503123680101401.0145959.0225184.0266.0FRFrance
1928198449310107381684.0120462.0184149.0219.0FRFrance
192919844837862060634.096606.0143110.0176.0FRFrance
193019844737202954274.089784.013199.0163.0FRFrance
193119844638733067686.0106974.0159123.0195.0FRFrance
19321984453135223101414.0169032.0246184.0308.0FRFrance
193319844436842220056.0116788.012537.0213.0FRFrance
\n", + "

1934 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202146 3 39877 33319.0 46435.0 60 50.0 \n", + "1 202145 3 20687 16810.0 24564.0 31 25.0 \n", + "2 202144 3 19017 15056.0 22978.0 29 23.0 \n", + "3 202143 3 27040 21935.0 32145.0 41 33.0 \n", + "4 202142 3 28343 23382.0 33304.0 43 35.0 \n", + "5 202141 3 25043 20586.0 29500.0 38 31.0 \n", + "6 202140 3 26286 21842.0 30730.0 40 33.0 \n", + "7 202139 3 22155 18014.0 26296.0 34 28.0 \n", + "8 202138 3 15614 12310.0 18918.0 24 19.0 \n", + "9 202137 3 13673 10404.0 16942.0 21 16.0 \n", + "10 202136 3 10289 7505.0 13073.0 16 12.0 \n", + "11 202135 3 12609 9282.0 15936.0 19 14.0 \n", + "12 202134 3 13015 9485.0 16545.0 20 15.0 \n", + "13 202133 3 10392 7042.0 13742.0 16 11.0 \n", + "14 202132 3 15586 11009.0 20163.0 24 17.0 \n", + "15 202131 3 18855 13664.0 24046.0 29 21.0 \n", + "16 202130 3 13991 9695.0 18287.0 21 14.0 \n", + "17 202129 3 13626 9618.0 17634.0 21 15.0 \n", + "18 202128 3 8636 5430.0 11842.0 13 8.0 \n", + "19 202127 3 10693 6838.0 14548.0 16 10.0 \n", + "20 202126 3 7086 4109.0 10063.0 11 6.0 \n", + "21 202125 3 7942 5540.0 10344.0 12 8.0 \n", + "22 202124 3 4855 3011.0 6699.0 7 4.0 \n", + "23 202123 3 6710 4455.0 8965.0 10 7.0 \n", + "24 202122 3 7879 5495.0 10263.0 12 8.0 \n", + "25 202121 3 7827 5403.0 10251.0 12 8.0 \n", + "26 202120 3 10278 7540.0 13016.0 16 12.0 \n", + "27 202119 3 9539 6860.0 12218.0 14 10.0 \n", + "28 202118 3 12135 9165.0 15105.0 18 14.0 \n", + "29 202117 3 12058 8891.0 15225.0 18 13.0 \n", + "... ... ... ... ... ... ... ... \n", + "1904 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "1905 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "1906 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "1907 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "1908 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "1909 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "1910 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "1911 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "1912 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "1913 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "1914 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "1915 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "1916 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "1917 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "1918 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "1919 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "1920 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "1921 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "1922 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "1923 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "1924 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "1925 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "1926 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "1927 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "1928 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "1929 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "1930 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "1931 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "1932 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "1933 198444 3 68422 20056.0 116788.0 125 37.0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 70.0 FR France \n", + "1 37.0 FR France \n", + "2 35.0 FR France \n", + "3 49.0 FR France \n", + "4 51.0 FR France \n", + "5 45.0 FR France \n", + "6 47.0 FR France \n", + "7 40.0 FR France \n", + "8 29.0 FR France \n", + "9 26.0 FR France \n", + "10 20.0 FR France \n", + "11 24.0 FR France \n", + "12 25.0 FR France \n", + "13 21.0 FR France \n", + "14 31.0 FR France \n", + "15 37.0 FR France \n", + "16 28.0 FR France \n", + "17 27.0 FR France \n", + "18 18.0 FR France \n", + "19 22.0 FR France \n", + "20 16.0 FR France \n", + "21 16.0 FR France \n", + "22 10.0 FR France \n", + "23 13.0 FR France \n", + "24 16.0 FR France \n", + "25 16.0 FR France \n", + "26 20.0 FR France \n", + "27 18.0 FR France \n", + "28 22.0 FR France \n", + "29 23.0 FR France \n", + "... ... ... ... \n", + "1904 59.0 FR France \n", + "1905 64.0 FR France \n", + "1906 97.0 FR France \n", + "1907 93.0 FR France \n", + "1908 80.0 FR France \n", + "1909 116.0 FR France \n", + "1910 149.0 FR France \n", + "1911 281.0 FR France \n", + "1912 395.0 FR France \n", + "1913 485.0 FR France \n", + "1914 544.0 FR France \n", + "1915 689.0 FR France \n", + "1916 722.0 FR France \n", + "1917 762.0 FR France \n", + "1918 926.0 FR France \n", + "1919 1113.0 FR France \n", + "1920 1236.0 FR France \n", + "1921 832.0 FR France \n", + "1922 459.0 FR France \n", + "1923 207.0 FR France \n", + "1924 190.0 FR France \n", + "1925 198.0 FR France \n", + "1926 224.0 FR France \n", + "1927 266.0 FR France \n", + "1928 219.0 FR France \n", + "1929 176.0 FR France \n", + "1930 163.0 FR France \n", + "1931 195.0 FR France \n", + "1932 308.0 FR France \n", + "1933 213.0 FR France \n", + "\n", + "[1934 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 ? Oui, la semaine 19 de l'année 1989 n'a pas de valeurs associées." + ] + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
169719891930NaNNaN0NaNNaNFRFrance
\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low inc100_up \\\n", + "1697 198919 3 0 NaN NaN 0 NaN NaN \n", + "\n", + " geo_insee geo_name \n", + "1697 FR France " + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "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": 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
020214633987733319.046435.06050.070.0FRFrance
120214532068716810.024564.03125.037.0FRFrance
220214431901715056.022978.02923.035.0FRFrance
320214332704021935.032145.04133.049.0FRFrance
420214232834323382.033304.04335.051.0FRFrance
520214132504320586.029500.03831.045.0FRFrance
620214032628621842.030730.04033.047.0FRFrance
720213932215518014.026296.03428.040.0FRFrance
820213831561412310.018918.02419.029.0FRFrance
920213731367310404.016942.02116.026.0FRFrance
102021363102897505.013073.01612.020.0FRFrance
112021353126099282.015936.01914.024.0FRFrance
122021343130159485.016545.02015.025.0FRFrance
132021333103927042.013742.01611.021.0FRFrance
1420213231558611009.020163.02417.031.0FRFrance
1520213131885513664.024046.02921.037.0FRFrance
162021303139919695.018287.02114.028.0FRFrance
172021293136269618.017634.02115.027.0FRFrance
18202128386365430.011842.0138.018.0FRFrance
192021273106936838.014548.01610.022.0FRFrance
20202126370864109.010063.0116.016.0FRFrance
21202125379425540.010344.0128.016.0FRFrance
22202124348553011.06699.074.010.0FRFrance
23202123367104455.08965.0107.013.0FRFrance
24202122378795495.010263.0128.016.0FRFrance
25202121378275403.010251.0128.016.0FRFrance
262021203102787540.013016.01612.020.0FRFrance
27202119395396860.012218.01410.018.0FRFrance
282021183121359165.015105.01814.022.0FRFrance
292021173120588891.015225.01813.023.0FRFrance
.................................
190419852132609619621.032571.04735.059.0FRFrance
190519852032789620885.034907.05138.064.0FRFrance
190619851934315432821.053487.07859.097.0FRFrance
190719851834055529935.051175.07455.093.0FRFrance
190819851733405324366.043740.06244.080.0FRFrance
190919851635036236451.064273.09166.0116.0FRFrance
191019851536388145538.082224.011683.0149.0FRFrance
19111985143134545114400.0154690.0244207.0281.0FRFrance
19121985133197206176080.0218332.0357319.0395.0FRFrance
19131985123245240223304.0267176.0445405.0485.0FRFrance
19141985113276205252399.0300011.0501458.0544.0FRFrance
19151985103353231326279.0380183.0640591.0689.0FRFrance
19161985093369895341109.0398681.0670618.0722.0FRFrance
19171985083389886359529.0420243.0707652.0762.0FRFrance
19181985073471852432599.0511105.0855784.0926.0FRFrance
19191985063565825518011.0613639.01026939.01113.0FRFrance
19201985053637302592795.0681809.011551074.01236.0FRFrance
19211985043424937390794.0459080.0770708.0832.0FRFrance
19221985033213901174689.0253113.0388317.0459.0FRFrance
192319850239758680949.0114223.0177147.0207.0FRFrance
192419850138548965918.0105060.0155120.0190.0FRFrance
192519845238483060602.0109058.0154110.0198.0FRFrance
1926198451310172680242.0123210.0185146.0224.0FRFrance
19271984503123680101401.0145959.0225184.0266.0FRFrance
1928198449310107381684.0120462.0184149.0219.0FRFrance
192919844837862060634.096606.0143110.0176.0FRFrance
193019844737202954274.089784.013199.0163.0FRFrance
193119844638733067686.0106974.0159123.0195.0FRFrance
19321984453135223101414.0169032.0246184.0308.0FRFrance
193319844436842220056.0116788.012537.0213.0FRFrance
\n", + "

1933 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202146 3 39877 33319.0 46435.0 60 50.0 \n", + "1 202145 3 20687 16810.0 24564.0 31 25.0 \n", + "2 202144 3 19017 15056.0 22978.0 29 23.0 \n", + "3 202143 3 27040 21935.0 32145.0 41 33.0 \n", + "4 202142 3 28343 23382.0 33304.0 43 35.0 \n", + "5 202141 3 25043 20586.0 29500.0 38 31.0 \n", + "6 202140 3 26286 21842.0 30730.0 40 33.0 \n", + "7 202139 3 22155 18014.0 26296.0 34 28.0 \n", + "8 202138 3 15614 12310.0 18918.0 24 19.0 \n", + "9 202137 3 13673 10404.0 16942.0 21 16.0 \n", + "10 202136 3 10289 7505.0 13073.0 16 12.0 \n", + "11 202135 3 12609 9282.0 15936.0 19 14.0 \n", + "12 202134 3 13015 9485.0 16545.0 20 15.0 \n", + "13 202133 3 10392 7042.0 13742.0 16 11.0 \n", + "14 202132 3 15586 11009.0 20163.0 24 17.0 \n", + "15 202131 3 18855 13664.0 24046.0 29 21.0 \n", + "16 202130 3 13991 9695.0 18287.0 21 14.0 \n", + "17 202129 3 13626 9618.0 17634.0 21 15.0 \n", + "18 202128 3 8636 5430.0 11842.0 13 8.0 \n", + "19 202127 3 10693 6838.0 14548.0 16 10.0 \n", + "20 202126 3 7086 4109.0 10063.0 11 6.0 \n", + "21 202125 3 7942 5540.0 10344.0 12 8.0 \n", + "22 202124 3 4855 3011.0 6699.0 7 4.0 \n", + "23 202123 3 6710 4455.0 8965.0 10 7.0 \n", + "24 202122 3 7879 5495.0 10263.0 12 8.0 \n", + "25 202121 3 7827 5403.0 10251.0 12 8.0 \n", + "26 202120 3 10278 7540.0 13016.0 16 12.0 \n", + "27 202119 3 9539 6860.0 12218.0 14 10.0 \n", + "28 202118 3 12135 9165.0 15105.0 18 14.0 \n", + "29 202117 3 12058 8891.0 15225.0 18 13.0 \n", + "... ... ... ... ... ... ... ... \n", + "1904 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "1905 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "1906 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "1907 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "1908 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "1909 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "1910 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "1911 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "1912 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "1913 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "1914 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "1915 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "1916 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "1917 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "1918 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "1919 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "1920 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "1921 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "1922 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "1923 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "1924 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "1925 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "1926 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "1927 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "1928 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "1929 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "1930 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "1931 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "1932 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "1933 198444 3 68422 20056.0 116788.0 125 37.0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 70.0 FR France \n", + "1 37.0 FR France \n", + "2 35.0 FR France \n", + "3 49.0 FR France \n", + "4 51.0 FR France \n", + "5 45.0 FR France \n", + "6 47.0 FR France \n", + "7 40.0 FR France \n", + "8 29.0 FR France \n", + "9 26.0 FR France \n", + "10 20.0 FR France \n", + "11 24.0 FR France \n", + "12 25.0 FR France \n", + "13 21.0 FR France \n", + "14 31.0 FR France \n", + "15 37.0 FR France \n", + "16 28.0 FR France \n", + "17 27.0 FR France \n", + "18 18.0 FR France \n", + "19 22.0 FR France \n", + "20 16.0 FR France \n", + "21 16.0 FR France \n", + "22 10.0 FR France \n", + "23 13.0 FR France \n", + "24 16.0 FR France \n", + "25 16.0 FR France \n", + "26 20.0 FR France \n", + "27 18.0 FR France \n", + "28 22.0 FR France \n", + "29 23.0 FR France \n", + "... ... ... ... \n", + "1904 59.0 FR France \n", + "1905 64.0 FR France \n", + "1906 97.0 FR France \n", + "1907 93.0 FR France \n", + "1908 80.0 FR France \n", + "1909 116.0 FR France \n", + "1910 149.0 FR France \n", + "1911 281.0 FR France \n", + "1912 395.0 FR France \n", + "1913 485.0 FR France \n", + "1914 544.0 FR France \n", + "1915 689.0 FR France \n", + "1916 722.0 FR France \n", + "1917 762.0 FR France \n", + "1918 926.0 FR France \n", + "1919 1113.0 FR France \n", + "1920 1236.0 FR France \n", + "1921 832.0 FR France \n", + "1922 459.0 FR France \n", + "1923 207.0 FR France \n", + "1924 190.0 FR France \n", + "1925 198.0 FR France \n", + "1926 224.0 FR France \n", + "1927 266.0 FR France \n", + "1928 219.0 FR France \n", + "1929 176.0 FR France \n", + "1930 163.0 FR France \n", + "1931 195.0 FR France \n", + "1932 308.0 FR France \n", + "1933 213.0 FR France \n", + "\n", + "[1933 rows x 10 columns]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = raw_data.dropna().copy()\n", + "data" + ] + } + ], + "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": 4 +}