diff --git a/module3/exo2/exercice.ipynb b/module3/exo2/exercice.ipynb index 0bbbe371b01e359e381e43239412d77bf53fb1fb..98a780034c75a7045e8a628074343b2214419bdc 100644 --- a/module3/exo2/exercice.ipynb +++ b/module3/exo2/exercice.ipynb @@ -1,5 +1,1381 @@ { - "cells": [], + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Analyse de l'incidence de la varicelle" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "import isoweek\n", + "import pandas as pd" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Les données sont téléchargées en local, on peut donc les lire grâce à la bibliothèque pandas" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "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
0202443727017254677417FRFrance
12024427265912604058426FRFrance
2202441720353813689315FRFrance
3202440721257253525315FRFrance
42024397289813334463426FRFrance
5202438775101513102FRFrance
62024377916281804102FRFrance
7202436722358703600315FRFrance
8202435716202852955204FRFrance
9202434725606224498417FRFrance
10202433719715363406315FRFrance
1120243274399194468547311FRFrance
1220243174500221367877410FRFrance
13202430770044278973011715FRFrance
1420242979270630312237141018FRFrance
1520242879364649812230141018FRFrance
16202427710247709013404151020FRFrance
172024267143681039918337221628FRFrance
18202425711174803914309171222FRFrance
19202424712621935715885191424FRFrance
202024237146571133917975221727FRFrance
21202422711628836114895171222FRFrance
2220242179701685112551151119FRFrance
232024207136611020917113201525FRFrance
2420241971008364131375315921FRFrance
25202418713438951417362201426FRFrance
262024177153031121919387231729FRFrance
272024167181381354022736272034FRFrance
282024157249291731532543372648FRFrance
292024147161811254419818241929FRFrance
.................................
17391991267176081130423912312042FRFrance
17401991257161691070021638281838FRFrance
17411991247161711007122271281739FRFrance
1742199123711947767116223211329FRFrance
1743199122715452995320951271737FRFrance
1744199121714903897520831261636FRFrance
17451991207190531274225364342345FRFrance
17461991197167391124622232291939FRFrance
17471991187213851388228888382551FRFrance
1748199117713462887718047241632FRFrance
17491991167148571006819646261834FRFrance
1750199115713975978118169251832FRFrance
1751199114712265768416846221430FRFrance
175219911379567604113093171123FRFrance
1753199112710864733114397191325FRFrance
17541991117155741118419964271935FRFrance
17551991107166431137221914292038FRFrance
1756199109713741878018702241533FRFrance
1757199108713289881317765231531FRFrance
1758199107712337807716597221529FRFrance
1759199106710877701314741191226FRFrance
1760199105710442654414340181125FRFrance
17611991047791345631126314820FRFrance
17621991037153871048420290271836FRFrance
17631991027162771104621508292038FRFrance
17641991017155651027120859271836FRFrance
17651990527193751329525455342345FRFrance
17661990517190801380724353342543FRFrance
1767199050711079666015498201228FRFrance
17681990497114302610205FRFrance
\n", + "

1769 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202443 7 2701 725 4677 4 1 \n", + "1 202442 7 2659 1260 4058 4 2 \n", + "2 202441 7 2035 381 3689 3 1 \n", + "3 202440 7 2125 725 3525 3 1 \n", + "4 202439 7 2898 1333 4463 4 2 \n", + "5 202438 7 751 0 1513 1 0 \n", + "6 202437 7 916 28 1804 1 0 \n", + "7 202436 7 2235 870 3600 3 1 \n", + "8 202435 7 1620 285 2955 2 0 \n", + "9 202434 7 2560 622 4498 4 1 \n", + "10 202433 7 1971 536 3406 3 1 \n", + "11 202432 7 4399 1944 6854 7 3 \n", + "12 202431 7 4500 2213 6787 7 4 \n", + "13 202430 7 7004 4278 9730 11 7 \n", + "14 202429 7 9270 6303 12237 14 10 \n", + "15 202428 7 9364 6498 12230 14 10 \n", + "16 202427 7 10247 7090 13404 15 10 \n", + "17 202426 7 14368 10399 18337 22 16 \n", + "18 202425 7 11174 8039 14309 17 12 \n", + "19 202424 7 12621 9357 15885 19 14 \n", + "20 202423 7 14657 11339 17975 22 17 \n", + "21 202422 7 11628 8361 14895 17 12 \n", + "22 202421 7 9701 6851 12551 15 11 \n", + "23 202420 7 13661 10209 17113 20 15 \n", + "24 202419 7 10083 6413 13753 15 9 \n", + "25 202418 7 13438 9514 17362 20 14 \n", + "26 202417 7 15303 11219 19387 23 17 \n", + "27 202416 7 18138 13540 22736 27 20 \n", + "28 202415 7 24929 17315 32543 37 26 \n", + "29 202414 7 16181 12544 19818 24 19 \n", + "... ... ... ... ... ... ... ... \n", + "1739 199126 7 17608 11304 23912 31 20 \n", + "1740 199125 7 16169 10700 21638 28 18 \n", + "1741 199124 7 16171 10071 22271 28 17 \n", + "1742 199123 7 11947 7671 16223 21 13 \n", + "1743 199122 7 15452 9953 20951 27 17 \n", + "1744 199121 7 14903 8975 20831 26 16 \n", + "1745 199120 7 19053 12742 25364 34 23 \n", + "1746 199119 7 16739 11246 22232 29 19 \n", + "1747 199118 7 21385 13882 28888 38 25 \n", + "1748 199117 7 13462 8877 18047 24 16 \n", + "1749 199116 7 14857 10068 19646 26 18 \n", + "1750 199115 7 13975 9781 18169 25 18 \n", + "1751 199114 7 12265 7684 16846 22 14 \n", + "1752 199113 7 9567 6041 13093 17 11 \n", + "1753 199112 7 10864 7331 14397 19 13 \n", + "1754 199111 7 15574 11184 19964 27 19 \n", + "1755 199110 7 16643 11372 21914 29 20 \n", + "1756 199109 7 13741 8780 18702 24 15 \n", + "1757 199108 7 13289 8813 17765 23 15 \n", + "1758 199107 7 12337 8077 16597 22 15 \n", + "1759 199106 7 10877 7013 14741 19 12 \n", + "1760 199105 7 10442 6544 14340 18 11 \n", + "1761 199104 7 7913 4563 11263 14 8 \n", + "1762 199103 7 15387 10484 20290 27 18 \n", + "1763 199102 7 16277 11046 21508 29 20 \n", + "1764 199101 7 15565 10271 20859 27 18 \n", + "1765 199052 7 19375 13295 25455 34 23 \n", + "1766 199051 7 19080 13807 24353 34 25 \n", + "1767 199050 7 11079 6660 15498 20 12 \n", + "1768 199049 7 1143 0 2610 2 0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 7 FR France \n", + "1 6 FR France \n", + "2 5 FR France \n", + "3 5 FR France \n", + "4 6 FR France \n", + "5 2 FR France \n", + "6 2 FR France \n", + "7 5 FR France \n", + "8 4 FR France \n", + "9 7 FR France \n", + "10 5 FR France \n", + "11 11 FR France \n", + "12 10 FR France \n", + "13 15 FR France \n", + "14 18 FR France \n", + "15 18 FR France \n", + "16 20 FR France \n", + "17 28 FR France \n", + "18 22 FR France \n", + "19 24 FR France \n", + "20 27 FR France \n", + "21 22 FR France \n", + "22 19 FR France \n", + "23 25 FR France \n", + "24 21 FR France \n", + "25 26 FR France \n", + "26 29 FR France \n", + "27 34 FR France \n", + "28 48 FR France \n", + "29 29 FR France \n", + "... ... ... ... \n", + "1739 42 FR France \n", + "1740 38 FR France \n", + "1741 39 FR France \n", + "1742 29 FR France \n", + "1743 37 FR France \n", + "1744 36 FR France \n", + "1745 45 FR France \n", + "1746 39 FR France \n", + "1747 51 FR France \n", + "1748 32 FR France \n", + "1749 34 FR France \n", + "1750 32 FR France \n", + "1751 30 FR France \n", + "1752 23 FR France \n", + "1753 25 FR France \n", + "1754 35 FR France \n", + "1755 38 FR France \n", + "1756 33 FR France \n", + "1757 31 FR France \n", + "1758 29 FR France \n", + "1759 26 FR France \n", + "1760 25 FR France \n", + "1761 20 FR France \n", + "1762 36 FR France \n", + "1763 38 FR France \n", + "1764 36 FR France \n", + "1765 45 FR France \n", + "1766 43 FR France \n", + "1767 28 FR France \n", + "1768 5 FR France \n", + "\n", + "[1769 rows x 10 columns]" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data_path = \"inc-7-PAY.csv\"\n", + "\n", + "raw_data = pd.read_csv(data_path, skiprows=1)\n", + "raw_data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Regardons si certaines lignes sont vides" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "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": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "raw_data[raw_data.isnull().any(axis=1)]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Il n'y a pas de données manquantes\n", + "\n", + "On convertit maintenant les dates" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [], + "source": [ + "def convert_week(year_and_week_int):\n", + " year_and_week_str = str(year_and_week_int)\n", + " year = int(year_and_week_str[:4])\n", + " week = int(year_and_week_str[4:])\n", + " w = isoweek.Week(year, week)\n", + " return pd.Period(w.day(0), 'W')\n", + "\n", + "raw_data['period'] = [convert_week(yw) for yw in raw_data['week']]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Trions les données par ordre chronologique" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [], + "source": [ + "sorted_data = raw_data.set_index('period').sort_index()" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "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", + "
weekindicatorincinc_lowinc_upinc100inc100_lowinc100_upgeo_inseegeo_name
period
1990-12-03/1990-12-091990497114302610205FRFrance
1990-12-10/1990-12-16199050711079666015498201228FRFrance
1990-12-17/1990-12-231990517190801380724353342543FRFrance
1990-12-24/1990-12-301990527193751329525455342345FRFrance
1990-12-31/1991-01-061991017155651027120859271836FRFrance
\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 \\\n", + "period \n", + "1990-12-03/1990-12-09 199049 7 1143 0 2610 2 \n", + "1990-12-10/1990-12-16 199050 7 11079 6660 15498 20 \n", + "1990-12-17/1990-12-23 199051 7 19080 13807 24353 34 \n", + "1990-12-24/1990-12-30 199052 7 19375 13295 25455 34 \n", + "1990-12-31/1991-01-06 199101 7 15565 10271 20859 27 \n", + "\n", + " inc100_low inc100_up geo_insee geo_name \n", + "period \n", + "1990-12-03/1990-12-09 0 5 FR France \n", + "1990-12-10/1990-12-16 12 28 FR France \n", + "1990-12-17/1990-12-23 25 43 FR France \n", + "1990-12-24/1990-12-30 23 45 FR France \n", + "1990-12-31/1991-01-06 18 36 FR France " + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sorted_data.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Nous vérifions maintenant la cohérence des données, il ne doit pas y avoir d'écart d'une période à une autre" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [], + "source": [ + "periods = sorted_data.index\n", + "for p1, p2 in zip(periods[:-1], periods[1:]):\n", + " delta = p2.to_timestamp() - p1.end_time\n", + " if delta > pd.Timedelta('1s'):\n", + " print(p1, p2)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Rien ne s'affiche, les périodes semblent cohérentes.\n", + "\n", + "Les données commencent en décembre 1990. Comme notre date référence est le 1er septembre, nous commençons l'analyse en septembre 1991" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [], + "source": [ + "first_septembre_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": {}, + "source": [ + "Nous calculons maintenant l'incidence chaque année en vérifiant qu'il y ait toujours 51 ou 52 semaines par années" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [], + "source": [ + "year = []\n", + "yearly_incidence = []\n", + "for week1, week2 in zip(first_septembre_week[:-1],\n", + " first_septembre_week[1:]):\n", + " one_year = sorted_data['inc'][week1:week2-1]\n", + " assert abs(len(one_year)-52) < 2\n", + " yearly_incidence.append(one_year.sum())\n", + " year.append(week2.year)\n", + "yearly_incidence = pd.Series(data=yearly_incidence, index=year)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Nous cherchons maintenant les années durant lesquelles l'épidémie était la plus forte et la plus faible, c'est à dire les années durant lesquelles l'incidence était respectivement la plus élevée et la plus petite." + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "2009" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "yearly_incidence.idxmax()" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "2020" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "yearly_incidence.idxmin()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "L'épidémie était la plus forte en 2009 et la plus faible en 2020" + ] + } + ], "metadata": { "kernelspec": { "display_name": "Python 3", @@ -16,10 +1392,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.3" + "version": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 } -