{ "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": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-7.csv\"" ] }, { "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
0202108713464963317295201426FRFrance
12021077136331032516941211626FRFrance
2202106713383979316973201525FRFrance
3202105712210898815432181323FRFrance
4202104712026882615226181323FRFrance
52021037891363751145113917FRFrance
62021027779554301016012816FRFrance
7202101710525775013300161220FRFrance
8202053711978840615550181323FRFrance
9202052712012828515739181224FRFrance
10202051710564757413554161121FRFrance
11202050770634744938211715FRFrance
1220204975026314569078511FRFrance
13202048766834312905410614FRFrance
1420204774999296370358511FRFrance
152020467375219635541639FRFrance
162020457369620165376639FRFrance
1720204474391237564077410FRFrance
1820204374376250562477410FRFrance
192020427400019796021639FRFrance
202020417396120995823639FRFrance
21202040720786753481315FRFrance
22202039710492371861213FRFrance
23202038722537823724315FRFrance
24202037715844052763204FRFrance
2520203679191001738102FRFrance
26202035782801694102FRFrance
27202034722723714173306FRFrance
28202033712841772391204FRFrance
29202032726506894611417FRFrance
.................................
15481991267176081130423912312042FRFrance
15491991257161691070021638281838FRFrance
15501991247161711007122271281739FRFrance
1551199123711947767116223211329FRFrance
1552199122715452995320951271737FRFrance
1553199121714903897520831261636FRFrance
15541991207190531274225364342345FRFrance
15551991197167391124622232291939FRFrance
15561991187213851388228888382551FRFrance
1557199117713462887718047241632FRFrance
15581991167148571006819646261834FRFrance
1559199115713975978118169251832FRFrance
1560199114712265768416846221430FRFrance
156119911379567604113093171123FRFrance
1562199112710864733114397191325FRFrance
15631991117155741118419964271935FRFrance
15641991107166431137221914292038FRFrance
1565199109713741878018702241533FRFrance
1566199108713289881317765231531FRFrance
1567199107712337807716597221529FRFrance
1568199106710877701314741191226FRFrance
1569199105710442654414340181125FRFrance
15701991047791345631126314820FRFrance
15711991037153871048420290271836FRFrance
15721991027162771104621508292038FRFrance
15731991017155651027120859271836FRFrance
15741990527193751329525455342345FRFrance
15751990517190801380724353342543FRFrance
1576199050711079666015498201228FRFrance
15771990497114302610205FRFrance
\n", "

1578 rows × 10 columns

\n", "
" ], "text/plain": [ " week indicator inc inc_low inc_up inc100 inc100_low \\\n", "0 202108 7 13464 9633 17295 20 14 \n", "1 202107 7 13633 10325 16941 21 16 \n", "2 202106 7 13383 9793 16973 20 15 \n", "3 202105 7 12210 8988 15432 18 13 \n", "4 202104 7 12026 8826 15226 18 13 \n", "5 202103 7 8913 6375 11451 13 9 \n", "6 202102 7 7795 5430 10160 12 8 \n", "7 202101 7 10525 7750 13300 16 12 \n", "8 202053 7 11978 8406 15550 18 13 \n", "9 202052 7 12012 8285 15739 18 12 \n", "10 202051 7 10564 7574 13554 16 11 \n", "11 202050 7 7063 4744 9382 11 7 \n", "12 202049 7 5026 3145 6907 8 5 \n", "13 202048 7 6683 4312 9054 10 6 \n", "14 202047 7 4999 2963 7035 8 5 \n", "15 202046 7 3752 1963 5541 6 3 \n", "16 202045 7 3696 2016 5376 6 3 \n", "17 202044 7 4391 2375 6407 7 4 \n", "18 202043 7 4376 2505 6247 7 4 \n", "19 202042 7 4000 1979 6021 6 3 \n", "20 202041 7 3961 2099 5823 6 3 \n", "21 202040 7 2078 675 3481 3 1 \n", "22 202039 7 1049 237 1861 2 1 \n", "23 202038 7 2253 782 3724 3 1 \n", "24 202037 7 1584 405 2763 2 0 \n", "25 202036 7 919 100 1738 1 0 \n", "26 202035 7 828 0 1694 1 0 \n", "27 202034 7 2272 371 4173 3 0 \n", "28 202033 7 1284 177 2391 2 0 \n", "29 202032 7 2650 689 4611 4 1 \n", "... ... ... ... ... ... ... ... \n", "1548 199126 7 17608 11304 23912 31 20 \n", "1549 199125 7 16169 10700 21638 28 18 \n", "1550 199124 7 16171 10071 22271 28 17 \n", "1551 199123 7 11947 7671 16223 21 13 \n", "1552 199122 7 15452 9953 20951 27 17 \n", "1553 199121 7 14903 8975 20831 26 16 \n", "1554 199120 7 19053 12742 25364 34 23 \n", "1555 199119 7 16739 11246 22232 29 19 \n", "1556 199118 7 21385 13882 28888 38 25 \n", "1557 199117 7 13462 8877 18047 24 16 \n", "1558 199116 7 14857 10068 19646 26 18 \n", "1559 199115 7 13975 9781 18169 25 18 \n", "1560 199114 7 12265 7684 16846 22 14 \n", "1561 199113 7 9567 6041 13093 17 11 \n", "1562 199112 7 10864 7331 14397 19 13 \n", "1563 199111 7 15574 11184 19964 27 19 \n", "1564 199110 7 16643 11372 21914 29 20 \n", "1565 199109 7 13741 8780 18702 24 15 \n", "1566 199108 7 13289 8813 17765 23 15 \n", "1567 199107 7 12337 8077 16597 22 15 \n", "1568 199106 7 10877 7013 14741 19 12 \n", "1569 199105 7 10442 6544 14340 18 11 \n", "1570 199104 7 7913 4563 11263 14 8 \n", "1571 199103 7 15387 10484 20290 27 18 \n", "1572 199102 7 16277 11046 21508 29 20 \n", "1573 199101 7 15565 10271 20859 27 18 \n", "1574 199052 7 19375 13295 25455 34 23 \n", "1575 199051 7 19080 13807 24353 34 25 \n", "1576 199050 7 11079 6660 15498 20 12 \n", "1577 199049 7 1143 0 2610 2 0 \n", "\n", " inc100_up geo_insee geo_name \n", "0 26 FR France \n", "1 26 FR France \n", "2 25 FR France \n", "3 23 FR France \n", "4 23 FR France \n", "5 17 FR France \n", "6 16 FR France \n", "7 20 FR France \n", "8 23 FR France \n", "9 24 FR France \n", "10 21 FR France \n", "11 15 FR France \n", "12 11 FR France \n", "13 14 FR France \n", "14 11 FR France \n", "15 9 FR France \n", "16 9 FR France \n", "17 10 FR France \n", "18 10 FR France \n", "19 9 FR France \n", "20 9 FR France \n", "21 5 FR France \n", "22 3 FR France \n", "23 5 FR France \n", "24 4 FR France \n", "25 2 FR France \n", "26 2 FR France \n", "27 6 FR France \n", "28 4 FR France \n", "29 7 FR France \n", "... ... ... ... \n", "1548 42 FR France \n", "1549 38 FR France \n", "1550 39 FR France \n", "1551 29 FR France \n", "1552 37 FR France \n", "1553 36 FR France \n", "1554 45 FR France \n", "1555 39 FR France \n", "1556 51 FR France \n", "1557 32 FR France \n", "1558 34 FR France \n", "1559 32 FR France \n", "1560 30 FR France \n", "1561 23 FR France \n", "1562 25 FR France \n", "1563 35 FR France \n", "1564 38 FR France \n", "1565 33 FR France \n", "1566 31 FR France \n", "1567 29 FR France \n", "1568 26 FR France \n", "1569 25 FR France \n", "1570 20 FR France \n", "1571 36 FR France \n", "1572 38 FR France \n", "1573 36 FR France \n", "1574 45 FR France \n", "1575 43 FR France \n", "1576 28 FR France \n", "1577 5 FR France \n", "\n", "[1578 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 ces données ?" ] }, { "cell_type": "code", "execution_count": 12, "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", "
weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [week, indicator, inc, inc_low, inc_up, inc100, inc100_low, inc100_up, geo_insee, geo_name]\n", "Index: []" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data[raw_data.isnull().any(axis=1)]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "La réponse est non, nous pouvons poursuivre" ] }, { "cell_type": "markdown", "metadata": { "hideCode": true }, "source": [ "Les données utilisent toujours une convention inhabituelle, à savoir que le numéro de la semaine est collé à celui de l'année" ] }, { "cell_type": "markdown", "metadata": { "hideOutput": true }, "source": [ "Pour aider Pandas il va falloir utiliser la bibliothèque Isoweek" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "La première étape est de convertir les dates (l'entier) en chaine de caractère. Je cherche la solution" ] }, { "cell_type": "code", "execution_count": 15, "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
02021077152731101919527231729FRFrance
1202106713642991417370211527FRFrance
2202105712210898815432181323FRFrance
3202104712026882615226181323FRFrance
42021037891363751145113917FRFrance
52021027779554301016012816FRFrance
6202101710525775013300161220FRFrance
7202053711978840615550181323FRFrance
8202052712012828515739181224FRFrance
9202051710564757413554161121FRFrance
10202050770634744938211715FRFrance
1120204975026314569078511FRFrance
12202048766834312905410614FRFrance
1320204774999296370358511FRFrance
142020467375219635541639FRFrance
152020457369620165376639FRFrance
1620204474391237564077410FRFrance
1720204374376250562477410FRFrance
182020427400019796021639FRFrance
192020417396120995823639FRFrance
20202040720786753481315FRFrance
21202039710492371861213FRFrance
22202038722537823724315FRFrance
23202037715844052763204FRFrance
2420203679191001738102FRFrance
25202035782801694102FRFrance
26202034722723714173306FRFrance
27202033712841772391204FRFrance
28202032726506894611417FRFrance
29202031713031002506204FRFrance
.................................
15471991267176081130423912312042FRFrance
15481991257161691070021638281838FRFrance
15491991247161711007122271281739FRFrance
1550199123711947767116223211329FRFrance
1551199122715452995320951271737FRFrance
1552199121714903897520831261636FRFrance
15531991207190531274225364342345FRFrance
15541991197167391124622232291939FRFrance
15551991187213851388228888382551FRFrance
1556199117713462887718047241632FRFrance
15571991167148571006819646261834FRFrance
1558199115713975978118169251832FRFrance
1559199114712265768416846221430FRFrance
156019911379567604113093171123FRFrance
1561199112710864733114397191325FRFrance
15621991117155741118419964271935FRFrance
15631991107166431137221914292038FRFrance
1564199109713741878018702241533FRFrance
1565199108713289881317765231531FRFrance
1566199107712337807716597221529FRFrance
1567199106710877701314741191226FRFrance
1568199105710442654414340181125FRFrance
15691991047791345631126314820FRFrance
15701991037153871048420290271836FRFrance
15711991027162771104621508292038FRFrance
15721991017155651027120859271836FRFrance
15731990527193751329525455342345FRFrance
15741990517190801380724353342543FRFrance
1575199050711079666015498201228FRFrance
15761990497114302610205FRFrance
\n", "

1577 rows × 10 columns

\n", "
" ], "text/plain": [ " week indicator inc inc_low inc_up inc100 inc100_low \\\n", "0 202107 7 15273 11019 19527 23 17 \n", "1 202106 7 13642 9914 17370 21 15 \n", "2 202105 7 12210 8988 15432 18 13 \n", "3 202104 7 12026 8826 15226 18 13 \n", "4 202103 7 8913 6375 11451 13 9 \n", "5 202102 7 7795 5430 10160 12 8 \n", "6 202101 7 10525 7750 13300 16 12 \n", "7 202053 7 11978 8406 15550 18 13 \n", "8 202052 7 12012 8285 15739 18 12 \n", "9 202051 7 10564 7574 13554 16 11 \n", "10 202050 7 7063 4744 9382 11 7 \n", "11 202049 7 5026 3145 6907 8 5 \n", "12 202048 7 6683 4312 9054 10 6 \n", "13 202047 7 4999 2963 7035 8 5 \n", "14 202046 7 3752 1963 5541 6 3 \n", "15 202045 7 3696 2016 5376 6 3 \n", "16 202044 7 4391 2375 6407 7 4 \n", "17 202043 7 4376 2505 6247 7 4 \n", "18 202042 7 4000 1979 6021 6 3 \n", "19 202041 7 3961 2099 5823 6 3 \n", "20 202040 7 2078 675 3481 3 1 \n", "21 202039 7 1049 237 1861 2 1 \n", "22 202038 7 2253 782 3724 3 1 \n", "23 202037 7 1584 405 2763 2 0 \n", "24 202036 7 919 100 1738 1 0 \n", "25 202035 7 828 0 1694 1 0 \n", "26 202034 7 2272 371 4173 3 0 \n", "27 202033 7 1284 177 2391 2 0 \n", "28 202032 7 2650 689 4611 4 1 \n", "29 202031 7 1303 100 2506 2 0 \n", "... ... ... ... ... ... ... ... \n", "1547 199126 7 17608 11304 23912 31 20 \n", "1548 199125 7 16169 10700 21638 28 18 \n", "1549 199124 7 16171 10071 22271 28 17 \n", "1550 199123 7 11947 7671 16223 21 13 \n", "1551 199122 7 15452 9953 20951 27 17 \n", "1552 199121 7 14903 8975 20831 26 16 \n", "1553 199120 7 19053 12742 25364 34 23 \n", "1554 199119 7 16739 11246 22232 29 19 \n", "1555 199118 7 21385 13882 28888 38 25 \n", "1556 199117 7 13462 8877 18047 24 16 \n", "1557 199116 7 14857 10068 19646 26 18 \n", "1558 199115 7 13975 9781 18169 25 18 \n", "1559 199114 7 12265 7684 16846 22 14 \n", "1560 199113 7 9567 6041 13093 17 11 \n", "1561 199112 7 10864 7331 14397 19 13 \n", "1562 199111 7 15574 11184 19964 27 19 \n", "1563 199110 7 16643 11372 21914 29 20 \n", "1564 199109 7 13741 8780 18702 24 15 \n", "1565 199108 7 13289 8813 17765 23 15 \n", "1566 199107 7 12337 8077 16597 22 15 \n", "1567 199106 7 10877 7013 14741 19 12 \n", "1568 199105 7 10442 6544 14340 18 11 \n", "1569 199104 7 7913 4563 11263 14 8 \n", "1570 199103 7 15387 10484 20290 27 18 \n", "1571 199102 7 16277 11046 21508 29 20 \n", "1572 199101 7 15565 10271 20859 27 18 \n", "1573 199052 7 19375 13295 25455 34 23 \n", "1574 199051 7 19080 13807 24353 34 25 \n", "1575 199050 7 11079 6660 15498 20 12 \n", "1576 199049 7 1143 0 2610 2 0 \n", "\n", " inc100_up geo_insee geo_name \n", "0 29 FR France \n", "1 27 FR France \n", "2 23 FR France \n", "3 23 FR France \n", "4 17 FR France \n", "5 16 FR France \n", "6 20 FR France \n", "7 23 FR France \n", "8 24 FR France \n", "9 21 FR France \n", "10 15 FR France \n", "11 11 FR France \n", "12 14 FR France \n", "13 11 FR France \n", "14 9 FR France \n", "15 9 FR France \n", "16 10 FR France \n", "17 10 FR France \n", "18 9 FR France \n", "19 9 FR France \n", "20 5 FR France \n", "21 3 FR France \n", "22 5 FR France \n", "23 4 FR France \n", "24 2 FR France \n", "25 2 FR France \n", "26 6 FR France \n", "27 4 FR France \n", "28 7 FR France \n", "29 4 FR France \n", "... ... ... ... \n", "1547 42 FR France \n", "1548 38 FR France \n", "1549 39 FR France \n", "1550 29 FR France \n", "1551 37 FR France \n", "1552 36 FR France \n", "1553 45 FR France \n", "1554 39 FR France \n", "1555 51 FR France \n", "1556 32 FR France \n", "1557 34 FR France \n", "1558 32 FR France \n", "1559 30 FR France \n", "1560 23 FR France \n", "1561 25 FR France \n", "1562 35 FR France \n", "1563 38 FR France \n", "1564 33 FR France \n", "1565 31 FR France \n", "1566 29 FR France \n", "1567 26 FR France \n", "1568 25 FR France \n", "1569 20 FR France \n", "1570 36 FR France \n", "1571 38 FR France \n", "1572 36 FR France \n", "1573 45 FR France \n", "1574 43 FR France \n", "1575 28 FR France \n", "1576 5 FR France \n", "\n", "[1577 rows x 10 columns]" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = pd.read_csv(data_url, skiprows=1)\n", "raw_data" ] }, { "cell_type": "code", "execution_count": 39, "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')" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "ename": "NameError", "evalue": "name 'data' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'period'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mconvert_week\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0myw\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0myw\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'week'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mNameError\u001b[0m: name 'data' is not defined" ] } ], "source": [ "data['period'] = [convert_week(yw) for yw in data['week']]" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "ename": "NameError", "evalue": "name 'data' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0msorted_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'period'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msort_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mNameError\u001b[0m: name 'data' is not defined" ] } ], "source": [ "sorted_data = data.set_index('period').sort_index()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "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": 2 }