{ "cells": [ { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "# Etude de la Varicelle" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import pandas as pd\n", "import isoweek" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Le jeu de données se trouve sur le site [Réseau Sentinelles](http://www.sentiweb.fr/).\n", "Nous le téléchargeons en local.\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "import urllib.request\n", "import os\n", "\n", "data_url = \"https://www.sentiweb.fr/datasets/incidence-PAY-7.csv\"\n", "data_file = \"varicelle.csv\"\n", "\n", "if not os.path.isfile(data_file):\n", " urllib.request.urlretrieve(data_url, data_file)\n" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "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": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Chargement des données" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "hideCode": false, "hidePrompt": false }, "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
02020147388122235539639FRFrance
1202013773415247943511814FRFrance
22020127812357901045612816FRFrance
3202011710198756812828151119FRFrance
420201079011669111331141018FRFrance
52020097136311054416718211626FRFrance
6202008710424770813140161220FRFrance
720200778959657411344141018FRFrance
820200679264692511603141018FRFrance
920200578505631410696131016FRFrance
102020047799158311015112915FRFrance
1120200375968410078369612FRFrance
12202002765344530853810713FRFrance
1320200179835701912651151119FRFrance
142019527794152461063612816FRFrance
1520195175823367579719612FRFrance
16201950764244276857210713FRFrance
17201949766214540870210713FRFrance
1820194875542338377018511FRFrance
192019477753650581001411715FRFrance
202019467263813163960426FRFrance
2120194574492261563697410FRFrance
2220194475728362778299612FRFrance
2320194374834275169177410FRFrance
24201942762793989856910713FRFrance
252019417413020306230639FRFrance
262019407421122186204639FRFrance
272019397313713104964528FRFrance
282019387307814164740528FRFrance
2920193779701621778102FRFrance
.................................
15011991267176081130423912312042FRFrance
15021991257161691070021638281838FRFrance
15031991247161711007122271281739FRFrance
1504199123711947767116223211329FRFrance
1505199122715452995320951271737FRFrance
1506199121714903897520831261636FRFrance
15071991207190531274225364342345FRFrance
15081991197167391124622232291939FRFrance
15091991187213851388228888382551FRFrance
1510199117713462887718047241632FRFrance
15111991167148571006819646261834FRFrance
1512199115713975978118169251832FRFrance
1513199114712265768416846221430FRFrance
151419911379567604113093171123FRFrance
1515199112710864733114397191325FRFrance
15161991117155741118419964271935FRFrance
15171991107166431137221914292038FRFrance
1518199109713741878018702241533FRFrance
1519199108713289881317765231531FRFrance
1520199107712337807716597221529FRFrance
1521199106710877701314741191226FRFrance
1522199105710442654414340181125FRFrance
15231991047791345631126314820FRFrance
15241991037153871048420290271836FRFrance
15251991027162771104621508292038FRFrance
15261991017155651027120859271836FRFrance
15271990527193751329525455342345FRFrance
15281990517190801380724353342543FRFrance
1529199050711079666015498201228FRFrance
15301990497114302610205FRFrance
\n", "

1531 rows × 10 columns

\n", "
" ], "text/plain": [ " week indicator inc inc_low inc_up inc100 inc100_low \\\n", "0 202014 7 3881 2223 5539 6 3 \n", "1 202013 7 7341 5247 9435 11 8 \n", "2 202012 7 8123 5790 10456 12 8 \n", "3 202011 7 10198 7568 12828 15 11 \n", "4 202010 7 9011 6691 11331 14 10 \n", "5 202009 7 13631 10544 16718 21 16 \n", "6 202008 7 10424 7708 13140 16 12 \n", "7 202007 7 8959 6574 11344 14 10 \n", "8 202006 7 9264 6925 11603 14 10 \n", "9 202005 7 8505 6314 10696 13 10 \n", "10 202004 7 7991 5831 10151 12 9 \n", "11 202003 7 5968 4100 7836 9 6 \n", "12 202002 7 6534 4530 8538 10 7 \n", "13 202001 7 9835 7019 12651 15 11 \n", "14 201952 7 7941 5246 10636 12 8 \n", "15 201951 7 5823 3675 7971 9 6 \n", "16 201950 7 6424 4276 8572 10 7 \n", "17 201949 7 6621 4540 8702 10 7 \n", "18 201948 7 5542 3383 7701 8 5 \n", "19 201947 7 7536 5058 10014 11 7 \n", "20 201946 7 2638 1316 3960 4 2 \n", "21 201945 7 4492 2615 6369 7 4 \n", "22 201944 7 5728 3627 7829 9 6 \n", "23 201943 7 4834 2751 6917 7 4 \n", "24 201942 7 6279 3989 8569 10 7 \n", "25 201941 7 4130 2030 6230 6 3 \n", "26 201940 7 4211 2218 6204 6 3 \n", "27 201939 7 3137 1310 4964 5 2 \n", "28 201938 7 3078 1416 4740 5 2 \n", "29 201937 7 970 162 1778 1 0 \n", "... ... ... ... ... ... ... ... \n", "1501 199126 7 17608 11304 23912 31 20 \n", "1502 199125 7 16169 10700 21638 28 18 \n", "1503 199124 7 16171 10071 22271 28 17 \n", "1504 199123 7 11947 7671 16223 21 13 \n", "1505 199122 7 15452 9953 20951 27 17 \n", "1506 199121 7 14903 8975 20831 26 16 \n", "1507 199120 7 19053 12742 25364 34 23 \n", "1508 199119 7 16739 11246 22232 29 19 \n", "1509 199118 7 21385 13882 28888 38 25 \n", "1510 199117 7 13462 8877 18047 24 16 \n", "1511 199116 7 14857 10068 19646 26 18 \n", "1512 199115 7 13975 9781 18169 25 18 \n", "1513 199114 7 12265 7684 16846 22 14 \n", "1514 199113 7 9567 6041 13093 17 11 \n", "1515 199112 7 10864 7331 14397 19 13 \n", "1516 199111 7 15574 11184 19964 27 19 \n", "1517 199110 7 16643 11372 21914 29 20 \n", "1518 199109 7 13741 8780 18702 24 15 \n", "1519 199108 7 13289 8813 17765 23 15 \n", "1520 199107 7 12337 8077 16597 22 15 \n", "1521 199106 7 10877 7013 14741 19 12 \n", "1522 199105 7 10442 6544 14340 18 11 \n", "1523 199104 7 7913 4563 11263 14 8 \n", "1524 199103 7 15387 10484 20290 27 18 \n", "1525 199102 7 16277 11046 21508 29 20 \n", "1526 199101 7 15565 10271 20859 27 18 \n", "1527 199052 7 19375 13295 25455 34 23 \n", "1528 199051 7 19080 13807 24353 34 25 \n", "1529 199050 7 11079 6660 15498 20 12 \n", "1530 199049 7 1143 0 2610 2 0 \n", "\n", " inc100_up geo_insee geo_name \n", "0 9 FR France \n", "1 14 FR France \n", "2 16 FR France \n", "3 19 FR France \n", "4 18 FR France \n", "5 26 FR France \n", "6 20 FR France \n", "7 18 FR France \n", "8 18 FR France \n", "9 16 FR France \n", "10 15 FR France \n", "11 12 FR France \n", "12 13 FR France \n", "13 19 FR France \n", "14 16 FR France \n", "15 12 FR France \n", "16 13 FR France \n", "17 13 FR France \n", "18 11 FR France \n", "19 15 FR France \n", "20 6 FR France \n", "21 10 FR France \n", "22 12 FR France \n", "23 10 FR France \n", "24 13 FR France \n", "25 9 FR France \n", "26 9 FR France \n", "27 8 FR France \n", "28 8 FR France \n", "29 2 FR France \n", "... ... ... ... \n", "1501 42 FR France \n", "1502 38 FR France \n", "1503 39 FR France \n", "1504 29 FR France \n", "1505 37 FR France \n", "1506 36 FR France \n", "1507 45 FR France \n", "1508 39 FR France \n", "1509 51 FR France \n", "1510 32 FR France \n", "1511 34 FR France \n", "1512 32 FR France \n", "1513 30 FR France \n", "1514 23 FR France \n", "1515 25 FR France \n", "1516 35 FR France \n", "1517 38 FR France \n", "1518 33 FR France \n", "1519 31 FR France \n", "1520 29 FR France \n", "1521 26 FR France \n", "1522 25 FR France \n", "1523 20 FR France \n", "1524 36 FR France \n", "1525 38 FR France \n", "1526 36 FR France \n", "1527 45 FR France \n", "1528 43 FR France \n", "1529 28 FR France \n", "1530 5 FR France \n", "\n", "[1531 rows x 10 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = pd.read_csv(data_file, skiprows=1)\n", "raw_data" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Vérification des données" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Y a-t-il des points manquants dans ce jeux de données ? NON" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "raw_data[raw_data.isnull().any(axis=1)]\n", "# pour maintenir la cohérence avec la source (cas grippe)\n", "data = raw_data.copy()" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Le format de semaine n'est pas standard. Nous créons une fonction de conversion qui permettra d'utiliser les outils pandas et python classique" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "hideCode": false, "hidePrompt": false }, "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": { "hideCode": false, "hidePrompt": false }, "source": [ "Tri des données et utilisation de la semaine comme index" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "sorted_data = data.set_index('period').sort_index()" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Vérification de l'écart entre les semaines dans la base : le jeu est complet" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "hideCode": false, "hidePrompt": false }, "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": { "hideCode": false, "hidePrompt": false }, "source": [ "## Etude des données" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Un premier regard en zoomant sur les 200 dernières semaines. Les cas sont cycliques avec un minimum en fin d'été" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "sorted_data['inc'][-200:].plot()" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Afin de faire une analyse statistique par année, il faut changer le début de l'année. On pourrait chercher la position moyenne des minima mais l'exercice demande à ce que cela soit la semaine du 1er septembre. \n", "Les données pour 1990 (première année) commence en décembre, donc on va travailler à partir de 1991.\n", "2020 est incomplète et il faut également l'enlever.\n", "\n", "Le bloc suivant calcule la liste des semaines (période) incluant le 1er septembre" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "first_sept_week = [pd.Period(pd.Timestamp(y, 9, 1), 'W')\n", " for y in range(1991,\n", " sorted_data.index[-1].year)]" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "A partir de cette liste, nous fabricons la liste des incidences de chaque année (one_year qui va de sem(année N) à sem(année N+1) -1, \n", "puis vérifions qu'elle contient 51 ou 52 semaines (assert ...), \n", "puis calculons la somme des occurences (yearly incidence), \n", "en paralallèle nous créeons un 2ème tableau qui contient les nom des années.\n", "A la fin, nous convertissons les 2 tableaux en une série numpy avec les années comme indice et les occurences comme data" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "year = []\n", "yearly_incidence = []\n", "for week1, week2 in zip(first_sept_week[:-1],\n", " first_sept_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": { "hideCode": false, "hidePrompt": false }, "source": [ "Voilà les incidences annuelles\n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "yearly_incidence.plot(style='*')" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "La question porte sur les années avec le plus et le moins de varicelle.\n", "numpy fournit des fonctions pour cela.\n", "\n", "L'année avec le moins de varicelle a été : " ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/plain": [ "2002" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "yearly_incidence.idxmin()" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "L'année avec le plus de varicelle a été : " ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2009" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "yearly_incidence.idxmax()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "hide_code_all_hidden": false, "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 }