{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Incidence du syndrome grippal" ] }, { "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\n", "import os\n", "from os import path" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Les données de l'incidence du syndrome grippal sont disponibles du site Web du [Réseau Sentinelles](http://www.sentiweb.fr/). 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." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "data_url = \"http://www.sentiweb.fr/datasets/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": "markdown", "metadata": {}, "source": [ "Pour éviter de télécharger les données à chaque fois, on vérifie si le fichier existe ou non.\n", "Si c'est le cas, on charge la version locale.\n", "Si ce n'est pas le cas, on le télécharge en utilisant l'URL indiquée plus haut, puis on le sauvegarde pour une utilsation ultérieure.\n", "Ceci permet:\n", "- de gagner du temps lors de la prochaine utilisation du notebook\n", "- de travailler hors ligne\n", "- de travailler avec la même version des données\n", "\n", "Le désavantage est qu'on ne travaillera pas forcément avec le jeu le plus récent des données. " ] }, { "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
020210332813922926.033352.04335.051.0FRFrance
120210231801014474.021546.02722.032.0FRFrance
220210132180917786.025832.03327.039.0FRFrance
320205332122016498.025942.03225.039.0FRFrance
420205231642812285.020571.02519.031.0FRFrance
520205132161917370.025868.03327.039.0FRFrance
620205031684513220.020470.02620.032.0FRFrance
72020493129399923.015955.02015.025.0FRFrance
820204831380410641.016967.02116.026.0FRFrance
920204731908515285.022885.02923.035.0FRFrance
1020204632480120503.029099.03831.045.0FRFrance
1120204534251636857.048175.06556.074.0FRFrance
1220204434456738521.050613.06859.077.0FRFrance
1320204334373737523.049951.06657.075.0FRFrance
1420204233514529812.040478.05345.061.0FRFrance
1520204132787723206.032548.04235.049.0FRFrance
1620204032044316381.024505.03125.037.0FRFrance
1720203931981015900.023720.03024.036.0FRFrance
1820203832556221142.029982.03932.046.0FRFrance
1920203731848514649.022321.02822.034.0FRFrance
202020363103907646.013134.01612.020.0FRFrance
21202035399186842.012994.01510.020.0FRFrance
22202034360843090.09078.094.014.0FRFrance
23202033361063411.08801.095.013.0FRFrance
24202032359183330.08506.095.013.0FRFrance
25202031343512269.06433.074.010.0FRFrance
26202030381795442.010916.0128.016.0FRFrance
27202029386875860.011514.0139.017.0FRFrance
28202028383405701.010979.0139.017.0FRFrance
29202027340662406.05726.063.09.0FRFrance
.................................
186119852132609619621.032571.04735.059.0FRFrance
186219852032789620885.034907.05138.064.0FRFrance
186319851934315432821.053487.07859.097.0FRFrance
186419851834055529935.051175.07455.093.0FRFrance
186519851733405324366.043740.06244.080.0FRFrance
186619851635036236451.064273.09166.0116.0FRFrance
186719851536388145538.082224.011683.0149.0FRFrance
18681985143134545114400.0154690.0244207.0281.0FRFrance
18691985133197206176080.0218332.0357319.0395.0FRFrance
18701985123245240223304.0267176.0445405.0485.0FRFrance
18711985113276205252399.0300011.0501458.0544.0FRFrance
18721985103353231326279.0380183.0640591.0689.0FRFrance
18731985093369895341109.0398681.0670618.0722.0FRFrance
18741985083389886359529.0420243.0707652.0762.0FRFrance
18751985073471852432599.0511105.0855784.0926.0FRFrance
18761985063565825518011.0613639.01026939.01113.0FRFrance
18771985053637302592795.0681809.011551074.01236.0FRFrance
18781985043424937390794.0459080.0770708.0832.0FRFrance
18791985033213901174689.0253113.0388317.0459.0FRFrance
188019850239758680949.0114223.0177147.0207.0FRFrance
188119850138548965918.0105060.0155120.0190.0FRFrance
188219845238483060602.0109058.0154110.0198.0FRFrance
1883198451310172680242.0123210.0185146.0224.0FRFrance
18841984503123680101401.0145959.0225184.0266.0FRFrance
1885198449310107381684.0120462.0184149.0219.0FRFrance
188619844837862060634.096606.0143110.0176.0FRFrance
188719844737202954274.089784.013199.0163.0FRFrance
188819844638733067686.0106974.0159123.0195.0FRFrance
18891984453135223101414.0169032.0246184.0308.0FRFrance
189019844436842220056.0116788.012537.0213.0FRFrance
\n", "

1891 rows × 10 columns

\n", "
" ], "text/plain": [ " week indicator inc inc_low inc_up inc100 inc100_low \\\n", "0 202103 3 28139 22926.0 33352.0 43 35.0 \n", "1 202102 3 18010 14474.0 21546.0 27 22.0 \n", "2 202101 3 21809 17786.0 25832.0 33 27.0 \n", "3 202053 3 21220 16498.0 25942.0 32 25.0 \n", "4 202052 3 16428 12285.0 20571.0 25 19.0 \n", "5 202051 3 21619 17370.0 25868.0 33 27.0 \n", "6 202050 3 16845 13220.0 20470.0 26 20.0 \n", "7 202049 3 12939 9923.0 15955.0 20 15.0 \n", "8 202048 3 13804 10641.0 16967.0 21 16.0 \n", "9 202047 3 19085 15285.0 22885.0 29 23.0 \n", "10 202046 3 24801 20503.0 29099.0 38 31.0 \n", "11 202045 3 42516 36857.0 48175.0 65 56.0 \n", "12 202044 3 44567 38521.0 50613.0 68 59.0 \n", "13 202043 3 43737 37523.0 49951.0 66 57.0 \n", "14 202042 3 35145 29812.0 40478.0 53 45.0 \n", "15 202041 3 27877 23206.0 32548.0 42 35.0 \n", "16 202040 3 20443 16381.0 24505.0 31 25.0 \n", "17 202039 3 19810 15900.0 23720.0 30 24.0 \n", "18 202038 3 25562 21142.0 29982.0 39 32.0 \n", "19 202037 3 18485 14649.0 22321.0 28 22.0 \n", "20 202036 3 10390 7646.0 13134.0 16 12.0 \n", "21 202035 3 9918 6842.0 12994.0 15 10.0 \n", "22 202034 3 6084 3090.0 9078.0 9 4.0 \n", "23 202033 3 6106 3411.0 8801.0 9 5.0 \n", "24 202032 3 5918 3330.0 8506.0 9 5.0 \n", "25 202031 3 4351 2269.0 6433.0 7 4.0 \n", "26 202030 3 8179 5442.0 10916.0 12 8.0 \n", "27 202029 3 8687 5860.0 11514.0 13 9.0 \n", "28 202028 3 8340 5701.0 10979.0 13 9.0 \n", "29 202027 3 4066 2406.0 5726.0 6 3.0 \n", "... ... ... ... ... ... ... ... \n", "1861 198521 3 26096 19621.0 32571.0 47 35.0 \n", "1862 198520 3 27896 20885.0 34907.0 51 38.0 \n", "1863 198519 3 43154 32821.0 53487.0 78 59.0 \n", "1864 198518 3 40555 29935.0 51175.0 74 55.0 \n", "1865 198517 3 34053 24366.0 43740.0 62 44.0 \n", "1866 198516 3 50362 36451.0 64273.0 91 66.0 \n", "1867 198515 3 63881 45538.0 82224.0 116 83.0 \n", "1868 198514 3 134545 114400.0 154690.0 244 207.0 \n", "1869 198513 3 197206 176080.0 218332.0 357 319.0 \n", "1870 198512 3 245240 223304.0 267176.0 445 405.0 \n", "1871 198511 3 276205 252399.0 300011.0 501 458.0 \n", "1872 198510 3 353231 326279.0 380183.0 640 591.0 \n", "1873 198509 3 369895 341109.0 398681.0 670 618.0 \n", "1874 198508 3 389886 359529.0 420243.0 707 652.0 \n", "1875 198507 3 471852 432599.0 511105.0 855 784.0 \n", "1876 198506 3 565825 518011.0 613639.0 1026 939.0 \n", "1877 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", "1878 198504 3 424937 390794.0 459080.0 770 708.0 \n", "1879 198503 3 213901 174689.0 253113.0 388 317.0 \n", "1880 198502 3 97586 80949.0 114223.0 177 147.0 \n", "1881 198501 3 85489 65918.0 105060.0 155 120.0 \n", "1882 198452 3 84830 60602.0 109058.0 154 110.0 \n", "1883 198451 3 101726 80242.0 123210.0 185 146.0 \n", "1884 198450 3 123680 101401.0 145959.0 225 184.0 \n", "1885 198449 3 101073 81684.0 120462.0 184 149.0 \n", "1886 198448 3 78620 60634.0 96606.0 143 110.0 \n", "1887 198447 3 72029 54274.0 89784.0 131 99.0 \n", "1888 198446 3 87330 67686.0 106974.0 159 123.0 \n", "1889 198445 3 135223 101414.0 169032.0 246 184.0 \n", "1890 198444 3 68422 20056.0 116788.0 125 37.0 \n", "\n", " inc100_up geo_insee geo_name \n", "0 51.0 FR France \n", "1 32.0 FR France \n", "2 39.0 FR France \n", "3 39.0 FR France \n", "4 31.0 FR France \n", "5 39.0 FR France \n", "6 32.0 FR France \n", "7 25.0 FR France \n", "8 26.0 FR France \n", "9 35.0 FR France \n", "10 45.0 FR France \n", "11 74.0 FR France \n", "12 77.0 FR France \n", "13 75.0 FR France \n", "14 61.0 FR France \n", "15 49.0 FR France \n", "16 37.0 FR France \n", "17 36.0 FR France \n", "18 46.0 FR France \n", "19 34.0 FR France \n", "20 20.0 FR France \n", "21 20.0 FR France \n", "22 14.0 FR France \n", "23 13.0 FR France \n", "24 13.0 FR France \n", "25 10.0 FR France \n", "26 16.0 FR France \n", "27 17.0 FR France \n", "28 17.0 FR France \n", "29 9.0 FR France \n", "... ... ... ... \n", "1861 59.0 FR France \n", "1862 64.0 FR France \n", "1863 97.0 FR France \n", "1864 93.0 FR France \n", "1865 80.0 FR France \n", "1866 116.0 FR France \n", "1867 149.0 FR France \n", "1868 281.0 FR France \n", "1869 395.0 FR France \n", "1870 485.0 FR France \n", "1871 544.0 FR France \n", "1872 689.0 FR France \n", "1873 722.0 FR France \n", "1874 762.0 FR France \n", "1875 926.0 FR France \n", "1876 1113.0 FR France \n", "1877 1236.0 FR France \n", "1878 832.0 FR France \n", "1879 459.0 FR France \n", "1880 207.0 FR France \n", "1881 190.0 FR France \n", "1882 198.0 FR France \n", "1883 224.0 FR France \n", "1884 266.0 FR France \n", "1885 219.0 FR France \n", "1886 176.0 FR France \n", "1887 163.0 FR France \n", "1888 195.0 FR France \n", "1889 308.0 FR France \n", "1890 213.0 FR France \n", "\n", "[1891 rows x 10 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "if (path.exists(\"incidence.csv\")):\n", " raw_data = pd.read_csv(\"incidence.csv\", index_col = 0)\n", "else:\n", " raw_data = pd.read_csv(data_url, skiprows=1)\n", " raw_data.to_csv(\"incidence.csv\")\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
165219891930NaNNaN0NaNNaNFRFrance
\n", "
" ], "text/plain": [ " week indicator inc inc_low inc_up inc100 inc100_low inc100_up \\\n", "1652 198919 3 0 NaN NaN 0 NaN NaN \n", "\n", " geo_insee geo_name \n", "1652 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
020210133016824407.035929.04637.055.0FRFrance
120205332144916669.026229.03326.040.0FRFrance
220205231642812285.020571.02519.031.0FRFrance
320205132161917370.025868.03327.039.0FRFrance
420205031684513220.020470.02620.032.0FRFrance
52020493129399923.015955.02015.025.0FRFrance
620204831380410641.016967.02116.026.0FRFrance
720204731908515285.022885.02923.035.0FRFrance
820204632480120503.029099.03831.045.0FRFrance
920204534251636857.048175.06556.074.0FRFrance
1020204434456738521.050613.06859.077.0FRFrance
1120204334373737523.049951.06657.075.0FRFrance
1220204233514529812.040478.05345.061.0FRFrance
1320204132787723206.032548.04235.049.0FRFrance
1420204032044316381.024505.03125.037.0FRFrance
1520203931981015900.023720.03024.036.0FRFrance
1620203832556221142.029982.03932.046.0FRFrance
1720203731848514649.022321.02822.034.0FRFrance
182020363103907646.013134.01612.020.0FRFrance
19202035399186842.012994.01510.020.0FRFrance
20202034360843090.09078.094.014.0FRFrance
21202033361063411.08801.095.013.0FRFrance
22202032359183330.08506.095.013.0FRFrance
23202031343512269.06433.074.010.0FRFrance
24202030381795442.010916.0128.016.0FRFrance
25202029386875860.011514.0139.017.0FRFrance
26202028383405701.010979.0139.017.0FRFrance
27202027340662406.05726.063.09.0FRFrance
28202026340392389.05689.063.09.0FRFrance
29202025328531488.04218.042.06.0FRFrance
.................................
185919852132609619621.032571.04735.059.0FRFrance
186019852032789620885.034907.05138.064.0FRFrance
186119851934315432821.053487.07859.097.0FRFrance
186219851834055529935.051175.07455.093.0FRFrance
186319851733405324366.043740.06244.080.0FRFrance
186419851635036236451.064273.09166.0116.0FRFrance
186519851536388145538.082224.011683.0149.0FRFrance
18661985143134545114400.0154690.0244207.0281.0FRFrance
18671985133197206176080.0218332.0357319.0395.0FRFrance
18681985123245240223304.0267176.0445405.0485.0FRFrance
18691985113276205252399.0300011.0501458.0544.0FRFrance
18701985103353231326279.0380183.0640591.0689.0FRFrance
18711985093369895341109.0398681.0670618.0722.0FRFrance
18721985083389886359529.0420243.0707652.0762.0FRFrance
18731985073471852432599.0511105.0855784.0926.0FRFrance
18741985063565825518011.0613639.01026939.01113.0FRFrance
18751985053637302592795.0681809.011551074.01236.0FRFrance
18761985043424937390794.0459080.0770708.0832.0FRFrance
18771985033213901174689.0253113.0388317.0459.0FRFrance
187819850239758680949.0114223.0177147.0207.0FRFrance
187919850138548965918.0105060.0155120.0190.0FRFrance
188019845238483060602.0109058.0154110.0198.0FRFrance
1881198451310172680242.0123210.0185146.0224.0FRFrance
18821984503123680101401.0145959.0225184.0266.0FRFrance
1883198449310107381684.0120462.0184149.0219.0FRFrance
188419844837862060634.096606.0143110.0176.0FRFrance
188519844737202954274.089784.013199.0163.0FRFrance
188619844638733067686.0106974.0159123.0195.0FRFrance
18871984453135223101414.0169032.0246184.0308.0FRFrance
188819844436842220056.0116788.012537.0213.0FRFrance
\n", "

1888 rows × 10 columns

\n", "
" ], "text/plain": [ " week indicator inc inc_low inc_up inc100 inc100_low \\\n", "0 202101 3 30168 24407.0 35929.0 46 37.0 \n", "1 202053 3 21449 16669.0 26229.0 33 26.0 \n", "2 202052 3 16428 12285.0 20571.0 25 19.0 \n", "3 202051 3 21619 17370.0 25868.0 33 27.0 \n", "4 202050 3 16845 13220.0 20470.0 26 20.0 \n", "5 202049 3 12939 9923.0 15955.0 20 15.0 \n", "6 202048 3 13804 10641.0 16967.0 21 16.0 \n", "7 202047 3 19085 15285.0 22885.0 29 23.0 \n", "8 202046 3 24801 20503.0 29099.0 38 31.0 \n", "9 202045 3 42516 36857.0 48175.0 65 56.0 \n", "10 202044 3 44567 38521.0 50613.0 68 59.0 \n", "11 202043 3 43737 37523.0 49951.0 66 57.0 \n", "12 202042 3 35145 29812.0 40478.0 53 45.0 \n", "13 202041 3 27877 23206.0 32548.0 42 35.0 \n", "14 202040 3 20443 16381.0 24505.0 31 25.0 \n", "15 202039 3 19810 15900.0 23720.0 30 24.0 \n", "16 202038 3 25562 21142.0 29982.0 39 32.0 \n", "17 202037 3 18485 14649.0 22321.0 28 22.0 \n", "18 202036 3 10390 7646.0 13134.0 16 12.0 \n", "19 202035 3 9918 6842.0 12994.0 15 10.0 \n", "20 202034 3 6084 3090.0 9078.0 9 4.0 \n", "21 202033 3 6106 3411.0 8801.0 9 5.0 \n", "22 202032 3 5918 3330.0 8506.0 9 5.0 \n", "23 202031 3 4351 2269.0 6433.0 7 4.0 \n", "24 202030 3 8179 5442.0 10916.0 12 8.0 \n", "25 202029 3 8687 5860.0 11514.0 13 9.0 \n", "26 202028 3 8340 5701.0 10979.0 13 9.0 \n", "27 202027 3 4066 2406.0 5726.0 6 3.0 \n", "28 202026 3 4039 2389.0 5689.0 6 3.0 \n", "29 202025 3 2853 1488.0 4218.0 4 2.0 \n", "... ... ... ... ... ... ... ... \n", "1859 198521 3 26096 19621.0 32571.0 47 35.0 \n", "1860 198520 3 27896 20885.0 34907.0 51 38.0 \n", "1861 198519 3 43154 32821.0 53487.0 78 59.0 \n", "1862 198518 3 40555 29935.0 51175.0 74 55.0 \n", "1863 198517 3 34053 24366.0 43740.0 62 44.0 \n", "1864 198516 3 50362 36451.0 64273.0 91 66.0 \n", "1865 198515 3 63881 45538.0 82224.0 116 83.0 \n", "1866 198514 3 134545 114400.0 154690.0 244 207.0 \n", "1867 198513 3 197206 176080.0 218332.0 357 319.0 \n", "1868 198512 3 245240 223304.0 267176.0 445 405.0 \n", "1869 198511 3 276205 252399.0 300011.0 501 458.0 \n", "1870 198510 3 353231 326279.0 380183.0 640 591.0 \n", "1871 198509 3 369895 341109.0 398681.0 670 618.0 \n", "1872 198508 3 389886 359529.0 420243.0 707 652.0 \n", "1873 198507 3 471852 432599.0 511105.0 855 784.0 \n", "1874 198506 3 565825 518011.0 613639.0 1026 939.0 \n", "1875 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", "1876 198504 3 424937 390794.0 459080.0 770 708.0 \n", "1877 198503 3 213901 174689.0 253113.0 388 317.0 \n", "1878 198502 3 97586 80949.0 114223.0 177 147.0 \n", "1879 198501 3 85489 65918.0 105060.0 155 120.0 \n", "1880 198452 3 84830 60602.0 109058.0 154 110.0 \n", "1881 198451 3 101726 80242.0 123210.0 185 146.0 \n", "1882 198450 3 123680 101401.0 145959.0 225 184.0 \n", "1883 198449 3 101073 81684.0 120462.0 184 149.0 \n", "1884 198448 3 78620 60634.0 96606.0 143 110.0 \n", "1885 198447 3 72029 54274.0 89784.0 131 99.0 \n", "1886 198446 3 87330 67686.0 106974.0 159 123.0 \n", "1887 198445 3 135223 101414.0 169032.0 246 184.0 \n", "1888 198444 3 68422 20056.0 116788.0 125 37.0 \n", "\n", " inc100_up geo_insee geo_name \n", "0 55.0 FR France \n", "1 40.0 FR France \n", "2 31.0 FR France \n", "3 39.0 FR France \n", "4 32.0 FR France \n", "5 25.0 FR France \n", "6 26.0 FR France \n", "7 35.0 FR France \n", "8 45.0 FR France \n", "9 74.0 FR France \n", "10 77.0 FR France \n", "11 75.0 FR France \n", "12 61.0 FR France \n", "13 49.0 FR France \n", "14 37.0 FR France \n", "15 36.0 FR France \n", "16 46.0 FR France \n", "17 34.0 FR France \n", "18 20.0 FR France \n", "19 20.0 FR France \n", "20 14.0 FR France \n", "21 13.0 FR France \n", "22 13.0 FR France \n", "23 10.0 FR France \n", "24 16.0 FR France \n", "25 17.0 FR France \n", "26 17.0 FR France \n", "27 9.0 FR France \n", "28 9.0 FR France \n", "29 6.0 FR France \n", "... ... ... ... \n", "1859 59.0 FR France \n", "1860 64.0 FR France \n", "1861 97.0 FR France \n", "1862 93.0 FR France \n", "1863 80.0 FR France \n", "1864 116.0 FR France \n", "1865 149.0 FR France \n", "1866 281.0 FR France \n", "1867 395.0 FR France \n", "1868 485.0 FR France \n", "1869 544.0 FR France \n", "1870 689.0 FR France \n", "1871 722.0 FR France \n", "1872 762.0 FR France \n", "1873 926.0 FR France \n", "1874 1113.0 FR France \n", "1875 1236.0 FR France \n", "1876 832.0 FR France \n", "1877 459.0 FR France \n", "1878 207.0 FR France \n", "1879 190.0 FR France \n", "1880 198.0 FR France \n", "1881 224.0 FR France \n", "1882 266.0 FR France \n", "1883 219.0 FR France \n", "1884 176.0 FR France \n", "1885 163.0 FR France \n", "1886 195.0 FR France \n", "1887 308.0 FR France \n", "1888 213.0 FR France \n", "\n", "[1888 rows x 10 columns]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data = raw_data.dropna().copy()\n", "data" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Nos données utilisent une convention inhabituelle: le numéro de\n", "semaine est collé à l'année, donnant l'impression qu'il s'agit\n", "de nombre entier. C'est comme ça que Pandas les interprète.\n", " \n", "Un deuxième problème est que Pandas ne comprend pas les numéros de\n", "semaine. Il faut lui fournir les dates de début et de fin de\n", "semaine. Nous utilisons pour cela la bibliothèque `isoweek`.\n", "\n", "Comme la conversion des semaines est devenu assez complexe, nous\n", "écrivons une petite fonction Python pour cela. Ensuite, nous\n", "l'appliquons à tous les points de nos donnés. Les résultats vont\n", "dans une nouvelle colonne 'period'." ] }, { "cell_type": "code", "execution_count": 6, "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", "data['period'] = [convert_week(yw) for yw in data['week']]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Il reste deux petites modifications à faire.\n", "\n", "Premièrement, nous définissons les périodes d'observation\n", "comme nouvel index de notre jeu de données. Ceci en fait\n", "une suite chronologique, ce qui sera pratique par la suite.\n", "\n", "Deuxièmement, nous trions les points par période, dans\n", "le sens chronologique." ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "sorted_data = data.set_index('period').sort_index()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Nous vérifions la cohérence des données. Entre la fin d'une période et\n", "le début de la période qui suit, la différence temporelle doit être\n", "zéro, ou au moins très faible. Nous laissons une \"marge d'erreur\"\n", "d'une seconde.\n", "\n", "Ceci s'avère tout à fait juste sauf pour deux périodes consécutives\n", "entre lesquelles il manque une semaine.\n", "\n", "Nous reconnaissons ces dates: c'est la semaine sans observations\n", "que nous avions supprimées !" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1989-05-01/1989-05-07 1989-05-15/1989-05-21\n" ] } ], "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": [ "Un premier regard sur les données !" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZQAAAEKCAYAAAA1qaOTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJztnXncHEWd/z/fmXnuPDmeXISEkATCkQAKRC5BUG5wxRXdRdclurgI8vPaXV1wV3F1QVhdUVRQRBCQFRBRQM7IjZwJV0hiSMh9H0+SJ8lzzVG/P7qqp7qnqrtnpueZnuT7fr2e1/TTXV1dXd1d3/oeVUVCCDAMwzBMtaTqXQCGYRhmz4AFCsMwDBMLLFAYhmGYWGCBwjAMw8QCCxSGYRgmFligMAzDMLHAAoVhGIaJBRYoDMMwTCywQGEYhmFiIVPvAgwlY8aMEVOmTKl3MRiGYRqKefPmbRFCjA1Lt1cJlClTpmDu3Ln1LgbDMExDQUQro6RjkxfDMAwTCyxQGIZhmFhggcIwDMPEAgsUhmEYJhZYoDAMwzCxECpQiOgWItpERG9r+7qIaA4RLZG/o7RjVxDRUiJaTERnavuPJqL58tj1RERyfwsR3S33v0xEU7RzZstrLCGi2dr+qTLtEnluc/VVwTAMw1RDFA3l1wDO8u27HMATQojpAJ6Q/4OIZgC4AMBMec4NRJSW59wI4GIA0+WfyvMiANuEEAcCuA7AtTKvLgBXAjgWwDEArtQE17UArpPX3ybzYBiGYepIqEARQjwLoNu3+zwAt8nt2wB8VNt/lxBiQAixHMBSAMcQ0QQAw4UQLwpnzeHbfeeovO4FcKrUXs4EMEcI0S2E2AZgDoCz5LEPybT+6+/xPDJ/PbbuGqh3MRiGYUqo1IcyXgixHgDk7zi5fyKA1Vq6NXLfRLnt3+85RwiRA7ADwOiAvEYD2C7T+vPao9m6awCX3vkaLr5jXr2LwjAMU0LcTnky7BMB+ys5Jyiv0gIRXUxEc4lo7ubNm23JGoK+bB4AsH57X51LwjAMU0qlAmWjNGNB/m6S+9cA2E9LNwnAOrl/kmG/5xwiygAYAcfEZstrC4CRMq0/rxKEEDcJIWYJIWaNHRs6FU2iyRccuZlJc3AewzDJo9KW6QEAKupqNoD7tf0XyMitqXCc769Is9hOIjpO+kAu9J2j8vo4gCeln+UxAGcQ0SjpjD8DwGPy2FMyrf/6ezQ5JVBSJiWNYRimvoRODklEvwVwCoAxRLQGTuTVNQDuIaKLAKwC8AkAEEIsIKJ7ACwEkANwmRAiL7O6FE7EWBuAR+QfAPwKwB1EtBSOZnKBzKubiL4L4FWZ7jtCCBUc8O8A7iKi/wbwusxjjyeXdwRKmgUKwzAJJFSgCCE+aTl0qiX9VQCuMuyfC+Aww/5+SIFkOHYLgFsM+5fBCSXeq8gVCgBYoDAMk0zYGN9AFH0oLFAYhkkeLFAaCCVQ0sQChWGY5MECpQGxxkgzDMPUERYoDYhgicIwTAJhgdJACPeXJQrDMMmDBUoDwhoKwzBJhAVKA6EECQsUhmGSCAuUBoTlCcMwSYQFSkPhiBLBKgrDMAmEBUoDwXKEYZgkwwKlAWHBwjBMEmGB0kBw2DDDMEmGBUoDwhoKwzBJhAVKA+GGDde3GAzDMEZYoDQQKror6VFem3b2Y8rlD+GR+evrXRSGYYYQFigNSLLFCbB4w04AwG9eXlnnkjAMM5SwQGkgRMlGMiHw9PoMszfCAqUBSbg8YRhmL4UFSgNRnMurMURKgxSTYZiYYIHSgBS4oWYYJoGwQGkgeEAjwzBJhgVKIyHlSdKXlE96+RiGqQ0sUBoQ9k0wDJNEWKA0EI0mR1jwMczeBQsUJnbY4sUweycsUBoI7vEzDJNkWKA0ECrKq1Gc3hyVxjB7FyxQGpDEayoNIvAYhokXFigNROIFCcMwezUsUPYw7nplFY67+ol6FwMAC0CG2duoSqAQ0VeJaAERvU1EvyWiViLqIqI5RLRE/o7S0l9BREuJaDERnantP5qI5stj1xM5XgIiaiGiu+X+l4loinbObHmNJUQ0u5r7aBSitM+X3zcfG3r6a16WIHi2YYbZO6lYoBDRRABfAjBLCHEYgDSACwBcDuAJIcR0AE/I/0FEM+TxmQDOAnADEaVldjcCuBjAdPl3ltx/EYBtQogDAVwH4FqZVxeAKwEcC+AYAFfqgotJxgSS9S8BwzBDSbUmrwyANiLKAGgHsA7AeQBuk8dvA/BRuX0egLuEEANCiOUAlgI4hogmABguhHhROK3g7b5zVF73AjhVai9nApgjhOgWQmwDMAdFIbTHUo6QqKc8aZQoNIZh4qVigSKEWAvgBwBWAVgPYIcQ4nEA44UQ62Wa9QDGyVMmAlitZbFG7psot/37PecIIXIAdgAYHZDXHk05MoK1A4ZhhppqTF6j4GgQUwHsC6CDiD4ddIphnwjYX+k5/nJeTERziWju5s2bA4q3Z1FIgMmLpRrD7F1UY/I6DcByIcRmIUQWwH0ATgCwUZqxIH83yfRrAOynnT8Jjolsjdz27/ecI81qIwB0B+RVghDiJiHELCHErLFjx1Z4qwmhjAa6riav+l2aYZg6Uo1AWQXgOCJql36NUwEsAvAAABV1NRvA/XL7AQAXyMitqXCc769Is9hOIjpO5nOh7xyV18cBPCn9LI8BOIOIRklN6Qy5j5HwKHWGYYaaTKUnCiFeJqJ7AbwGIAfgdQA3ARgG4B4iugiO0PmETL+AiO4BsFCmv0wIkZfZXQrg1wDaADwi/wDgVwDuIKKlcDSTC2Re3UT0XQCvynTfEUJ0V3ovjUI5QiIZFq8EFIJhmCGjYoECAEKIK+GE7+oMwNFWTOmvAnCVYf9cAIcZ9vdDCiTDsVsA3FJmkRuacoREEgQKwzB7FzxSfg+FtQOGYYYaFigNRKNoKMQDURhmr4QFyh4K6ycMwww1LFAaiChCQikHSRiHkoAiMAwzhLBAaUCi+EcafeqVQkHg4tvn4tUVe3zwHsPsMbBAaSDKmvCxwbWDLbsH8PjCjbj0N/PqXRSGYSLCAqWBKM5HE64CJCHKK54SsIOfYRoFFigNSJCwUM1vgadeYRhmiGGB0kCUFzZcfw2FYZi9CxYoeyhJECdVCbUk3ADDMGXBAqWhCG9l1aDCRo/ycv1FbD9jmIaBBUoDEUVIqPY3CSavOErA8oRhGgcWKHso9RcnDMPsbbBAaSDKWgK4jhIlAcoRwzB1gAXKHkoixqFU45Ovf/EZhikTFigNRCQfijuXV23LEkScl2anPMM0DixQ9lDq6ZRn7YJh9k5YoDQQjbYEcDUkwWTHMEx5sEBpIBpFSMSpHUWZt4xhmGTAAmUPQzXA9VwPJY4rN4rwZBimCAuUBiJSGys79ElokKspAo+UZ5jGgwXKHko95UkcwiwJI/0ZhikPFigNRDmNbCIa5CrKkITiMwxTHixQ9jCSsB4KR2gxzN4JC5Q9lsYe2aiCCtiFwjCNAwuUBqK8BbZqV47IZajmXHkyBXjldw/ksL13sIqrMAwTJyxQymDhuh48+vaGehcjkrCoq1N+iPI4+ftP4b3fmRPD1RiGiYNMvQvQSJxz/XMAgBXXnFuX60fxTRTn8mrsqVeiBBVs2cXaCcMkCdZQGoiGM3nxCsAMs1fBAmUPQ42Ur+t6KDGIgyQIRIZhyoMFSgNRdFRHSJuAPn51Zah/+RmGKY+qBAoRjSSie4nor0S0iIiOJ6IuIppDREvk7ygt/RVEtJSIFhPRmdr+o4lovjx2PcnQHiJqIaK75f6XiWiKds5seY0lRDS7mvtoNIJ675SAqVfiuHahDOHJMEwyqFZD+TGAR4UQhwB4D4BFAC4H8IQQYjqAJ+T/IKIZAC4AMBPAWQBuIKK0zOdGABcDmC7/zpL7LwKwTQhxIIDrAFwr8+oCcCWAYwEcA+BKXXDtqTTMEsBx5MEKCsM0HBULFCIaDuADAH4FAEKIQSHEdgDnAbhNJrsNwEfl9nkA7hJCDAghlgNYCuAYIpoAYLgQ4kXhhPbc7jtH5XUvgFOl9nImgDlCiG4hxDYAc1AUQgwSYvKqyilf//IzDFMe1Wgo0wBsBnArEb1ORDcTUQeA8UKI9QAgf8fJ9BMBrNbOXyP3TZTb/v2ec4QQOQA7AIwOyGuPpry5vGpYkNBrx+eUZ5MXwzQO1QiUDICjANwohDgSwG5I85YFU9MgAvZXeo73okQXE9FcIpq7efPmgOIln3KaaV4PhWGYoaYagbIGwBohxMvy/3vhCJiN0owF+btJS7+fdv4kAOvk/kmG/Z5ziCgDYASA7oC8ShBC3CSEmCWEmDV27NgKbtOYZyz51AIlaZNbwmiwyYthGo+KBYoQYgOA1UR0sNx1KoCFAB4AoKKuZgO4X24/AOACGbk1FY7z/RVpFttJRMdJ/8iFvnNUXh8H8KT0szwG4AwiGiWd8WfIfUNCvl5T+Ua4rJr7qq4yL5aR8s4vLwHMMI1DtVOvfBHAnUTUDGAZgM/CEVL3ENFFAFYB+AQACCEWENE9cIRODsBlQoi8zOdSAL8G0AbgEfkHOA7/O4hoKRzN5AKZVzcRfRfAqzLdd4QQ3VXeS2TyQjTAnDX1NHnxwEaG2Rupql0UQrwBYJbh0KmW9FcBuMqwfy6Awwz7+yEFkuHYLQBuKae8cVEvDaWchjoJDXIcUV7slGeYxoFHyldA3QRKFJOX/K3rAlsxmryY6GzY0Y8plz+EOQs31rsozF4KC5QKKBTqXYJwkhA4wBOvDC1vr90BAPjtK6vqXBJmb4UFSgXk69RYlzVSvmaliHDtIZq+fm/iiUUb0Z/NB6Zh8yBTb1igVEDdorzKoNGnXnHn8oohr0bn9VXbcNFtc3H1w4sipWdhzNQLFigVUK9Bg5Eu604OWf9GpboyKKc8i5QdfVkAwPItuwPTJaWq5q3chk09/fUuBlMHWKBUQENoKPW8doxTr9QbIQS+/cACvLVme93KUK5QrXfVnX/jC/jwT56vcymYesACpQKSHDbsjpRvcJNXvRtFRe9gHr9+YQX+/hcv1a0MUZ9pkgaBbto5UO8iMHWABUoFJDls2E2bmCa5MpKioaSkdtCfC3aI1xJ3jZuIz7SedZfLN0AIZETWbu/DlMsfwiPz19e7KA0DC5QKqFeUVxSUeaTxx6EM3Q1k8wWs295nLodsxOv5yCMv65wABWUgt+cIlCUbdwIA/o/DsCPDAqUCCnUzeZWRtsEn8wqabjpuvvnHt3HCNU9iZ3+25FgS3GVKqEUNBqlnkcNCmxuJjhZnIpHewT3nnmoNC5QKqLeGEuXyCWgHq+rVu43nEEiUx+XIclPvOgnRcrm8U4ZUiHM+AQoKckmQwDHR1uQsKLt7IFfnkjQOLFAqoH6zDZflRKkbsbTBQ1j+rBQkmVRpk5yE5jEr/RJhAkVRTyGYAPkbG6kkzNzdYLBAqYB6Tb3imoEC2hV1rJ4LbCmqCQwYytJnAx6oiOlZL9m4M3QcibUM7m9wrSRhzE6jB4PoqG9oT7qnWsMCpQLqbfKKQsOHDQ/hSPls3u54j6sxOf26Z/HBHzxd0bmqXEPRkdk1kMODbxrXqotEA3waTA1J/rIeCaQxwobrRxyLYw1lr1A9T9MVk+ESiNZTjkP4XnHffDz45jpMG9uBmfuOKPv8RFRXTCRBy280WEMpA2ViDxIod72yCq+v2lbTcgS958VBcPX/GKoyedWh+KYGJAn1qF63qEWppsgqfLrSyKYk1BfgRJsde/Wf8dTiTeGJLZRb7wwLlLJIS4kSJFAuv28+/vaGF2py/SgfayLGocTQT1WN+1D6Bcwmr/ojIjZscVSV6jRVGhqflMZ33fY+bOwZwH89sKDiPJIiHBsJFihlUGysG+FFa+xIn3qU3iQIk/Csyx+HUnmZkzR9SzW0ypDfagZaJsPc2ViwQCmDKCavWlLewMaaFWNoylCH6euN5U1QPYYJlDiFQaW3HfbMu3cPYsOO2s9ErKwJ1Qy0VBpKAl6BhoGd8mWg4tLrtsBWhMsmYgngWPIY+htIrMnL9xuavppCu8sfVHZ62HM76rtzAAArrjm3sgtELYcshpr6v6I8YirL3gRrKGWgBEq9pl4phyTEzleloNSh+Ik1eQll8gpJF8Mzd4M6EvD+VEMhYp0F5tEA33nSYIFSBtQAJq/iwMaaFiWQRl0PxVRnCZAnLmH1GkdZq3XsJ6W+4ugIFKO8EnJTDQALlDJINZBTvtE/giizArhpY7pXUz5JeNbuiO2QokRNF4Trh6nY5JUM4gkMScrdNA4sUMpAOeVtE+DVWkWO1nAmZ/6hahp6N2w4gqM5rns1+lASUY/yN6SBi6Oo1Wq4SenIxLOEQvV57G2wQCmDsHEoSZiSpdzFmGrBUH/Mcd1pAh6fkahTrxSjkqoIG67W5FXd6bER51iopNxTI8ACpQzCxqEkYa15N8qrjuscxSPMoucRm8krqU553681XYxFrfQZJqC6AMTjQ0zKvTQSLFDKoDgOxXy81o1Po8zlpRiqKK9aaihJaFSEa/4LJo6pQiKvDmklARWGuJzyrq2RiQgLlDIICxtOwuJCSZi+fqhHysd1q6Y6S5KGEpouhrJSdT75RAhggH0o9YIFShmEDWysuVO+nM+8rmHD8eURKcorpps15ZKINiViXRQS0KFORH0hptD1xNxN48ACpQzCxqEkw4eSoNDmagaVlVH+PT7KS1ZkuHCNQ0NRJq/G9qHEUQzlh0zILTUEVQsUIkoT0etE9Cf5fxcRzSGiJfJ3lJb2CiJaSkSLiehMbf/RRDRfHrue5FtNRC1EdLfc/zIRTdHOmS2vsYSIZld7H1FwNZQ6CZRG8aEMrUs+ToFSmlESwmDVaxUWQu2+flX5UGQWFY9DqX99AfF0qJJxJ41FHBrKlwEs0v6/HMATQojpAJ6Q/4OIZgC4AMBMAGcBuIGI0vKcGwFcDGC6/DtL7r8IwDYhxIEArgNwrcyrC8CVAI4FcAyAK3XBVSvqHTYcaRRKAnwoiuqc8mVoKHu4yWso1kFRJGAV4ViIoy6S8A01GlUJFCKaBOBcADdru88DcJvcvg3AR7X9dwkhBoQQywEsBXAMEU0AMFwI8aJwWpHbfeeovO4FcKrUXs4EMEcI0S2E2AZgDopCqGaENdbJMHk51PNbiLNXH2U9FDZ5OcSxBnq1c3klob6AmDQUd+aBhNxUA1CthvIjAF8HoAfSjhdCrAcA+TtO7p8IYLWWbo3cN1Fu+/d7zhFC5ADsADA6IK+a0ggmL9UA/+cf30bOFt9cY1Qxq+ns1sO8l9gor6gaSgzXKvpQKjs/AdUFgKO86kXFAoWIPgxgkxBiXtRTDPtEwP5Kz/FelOhiIppLRHM3b94cqaA23HEoCdZQdOaurO1SxGFUZfKqx8DGxGooEdPFMJdXMa8Kz0uEkTAuk1f1ecTBqq29uOX55fUuRiSq0VDeD+AjRLQCwF0APkREvwGwUZqxIH/Vos5rAOynnT8JwDq5f5Jhv+ccIsoAGAGgOyCvEoQQNwkhZgkhZo0dO7ayO5WEjUOp+cDGhHysocTxMUvlKoqWE1etJHWkvGodw+oiFh+KyqvC85NQXUC8AxvrfUufuvklfOdPC6ta22WoqFigCCGuEEJMEkJMgeNsf1II8WkADwBQUVezAdwvtx8AcIGM3JoKx/n+ijSL7SSi46R/5ELfOSqvj8trCACPATiDiEZJZ/wZcl9NIdfkZT5eawtTUj7WMOIQfGVFecVU70mt36jFiqMRrfcSDXEx1JGGtcQVJEkpUAC1WLHxGgD3ENFFAFYB+AQACCEWENE9ABYCyAG4TAih1ue8FMCvAbQBeET+AcCvANxBREvhaCYXyLy6iei7AF6V6b4jhOiuwb14UL03m8krV88JtCS647ZSH8bba3egIASOmDSyqrJUY4pypxsZyoGNhmySoKG4RQipjHiKGj4OZVNPP0a2N6M5U9ofTUB1AYjXKc9EJxaBIoR4GsDTcnsrgFMt6a4CcJVh/1wAhxn290MKJMOxWwDcUmmZK0G9XnmL4EiAPImFD//keQCVL9PaqFOvmE1e8eRdDYWIJq84TTS2+xZC4Jirn8C5h0/Az/7hqNLjEa9eKAikUtWEbQQTZ9hwUuRKI5i8eaR8Gagei9XklYA3L0njCKqqjbpEeZn2xftMK+n1Rp2GJo6ShgWeZPPO/kfeXm8uQ8RC1H4i1Tg0lBgKEgeyHIkpTwAsUCpgIJc37rdpLnFR7kcSZQxHLYjHfl2PKK/SfOI2e1SSXflRXlWMQ1GTQ4ZEMqYs71bUK9e68xWHZpkE7VQnCR3WMFiglIF6nrsHcsbjdRr24SHKCoe1Zugnh4wHUz5xNyqV9MyjTl8fZ3tjK2dWdpqsAiViIWrdNsbREYhjoGicJMGfFwYLlDJQL9buQZuGUms1PjxNokxeVVRH1PmrnLS101DinkG6lq9IHLMNu5OLWjpHOWnySlXZctT6W4kl+4S1343go2WBUgaqvemvl0CJkCYJ8iSesOGhd6KYo7ziybuYX+U+lNB0scw27PxaIxmlGp6uwOSlC+xGGLOVFI1AlSIp5QmCBUoZqMdpW0irEWycQ8FQjNTWG6damrw816mTo7c4l1e02YarKWaYDyUb5kMJuLZ+rNa97ThHyifls26EsUEsUMpAfWS2nkLNF9iKkH1aC8Wst/mrml5i2Jl6Vcf1wZueX9zXqaROXH9S1IQxYHuV83kl3KyFCMizeKzmM3PX6VnVkqQItiBYoJSBq6HkLeaABuhBDAWx1ELI1+PVUGLyoRj2FWI201Tyirj+pCFYsZFCJkB1nfKWMSSBGoq2XWvzTb2eVS0I68gmCRYo5SCfZ91mG47QVOgp6qagxGEakr+2RlS/QmwDG40+FF2gVH+NinwoEUVELGvKh+SlOlOV+FA8dVlzp3wc5kkZ5ZWQdrwRTOosUMqg6EOxjJRPghqfoHeuqigv2eDYhKKed2w+FOM4FK1MFd6QR5uqwHdQNHlFXbGxdr3zrHTK2/w5kX0oNX5P48g+ae13I0wFwwKlDIoj5WuroQghsLGnv7JzYylBdcTyMYccL7e3+7+PL8aDb5ZOSB3m3NevU+n3XIhBKEUhjpzDTF451ylvKUPA/emHau9DiUOoJuFrKpKEcW5hsEApg6KGUluBcufLq3Ds1U9g4boe4/UboadSLXHf4k+eXIov/vb1kv1hTvc4hEG14bKiqKJESleVD0X+2lclDRnYGJD3UJq84ozyqjeqGEkTcCZYoJSBep611lBeWrYVALB0866yz41T2FSaVzwRNpIIppXqBlAGN/ZxOOW9Qqn88yOPQxmC9kbN5ZWuwCkftS4ffHMdZv33HOyyzEgRhTg+xaR13Fig7GEo56hVoMT0wJvSzmMpWcI3Qg80zleu0o8ynvEawXnojupqorw8Jq2QclRcH1WWNeoZcc6Oa2u8wkbKB92fXn9Bna+bn1uGLbsGsbq7N7ygFoZyzNClv5mH/3pwQdXXC4NHyu9hlKOh2F7o9Tv6sCxE81DmBJtpLarjs9pxKNX2iGrZoSpHQwkyr3jzMWkowcejUK02FXUcSjw+FOfX6pQPMXkFElFTG5RCK1uF0yCO51YU0MHnP/L2Btz6lxUVXePbDyzAz595NzCNunwjaCi1WGBrj0U9zyg+lIIA0oZv7vjvPQkgeK2RTMrsGI3yOsU5GCtfEGhKl39eHCUIFRIhmoXOYEDDFOZ0jyNsuFqzmbseSug4FKXB1q53rgY2WgVKDCYv9f4P5ioXKH7N0vQthuZR8dWj8+sXVgAALjn5gNC0HDa8h2LTUOIaBJdJmzUUlWVQg+G9bHUqStgtPL14E3r6S9e5jtPkYg0bNqS1EdTT9fRkQxbYqtwpb84v8vkVXKdarCavggobtpQhYp5Bdan8M0EdAQB4fMEGrNveF1qOyn1fyWrAk+bTMcECpQzUA7WNQ9FH0FfzMqoPqsSHEoE437mgHtGmnf34zK2v4ov/Vxo5FQfqytaGqwwzkm1mAyBcQ4ljQsOqo5siXncoBuINSK2hyeJECaqjqD4U9f5nA54bAFx8xzz87Q1/CS1HpcEyxQ5cMuCw4T0M9WJF0VDCPuqg3oYyJ/gvo3rQQ9VRCWocBrLO2710U6k/aChMXt6LhGgoAd5MfaBh6IqNlssIIXDZna/h2Xc2m4970gYU1FbGiOfGqqFY3nFlhrJFeQU13p7ghICyqlH4D71VOm7IX76NPQPma1Xpt3LOS4YoUfWWNI3JBAuUMijHKR/WK6omrDHo1Dg/gqDedNB64LFE2IQICW8PNDivdzbYgyC8nQCDyStE4Kj9D81fjwtvecV43Cu0yq+bqKfEOTuuLQtlhmqyOCUCBUpEDaWjxXHcPfr2BmuaMH9CnOHeSWnHWaDsYahGzuaU1/eHPfygDyqKmWcoCBJ6USasq0awhPbGte0w4f3pX71sPRbm3I/SMIV3HoKvEYarmUZMFwe2e61GQ4k62/DkrnYAwInTx1jTlGPGqqcP5dUV3Xh+yZaq8wEaI2yYo7zKIExDKXgESnBeUT4If4McxfShH6o2bDiojOpYrYWcfS6v6m3kQHh4qdehHm7qNKEfrUpDCTk1jtmGS67pQwmUTNrcF42qoQR1NpSwCfJ9lSPEKx9PJX+rqNFP/PxFAMFRnVHLwRrKHoZ6nFEW2ArrnQf10MKXvY320VZL0D2oOgiMOKvi2u7kkBGm+KgmnNK7gJahHBH8YmVpKJUIlMgJlZC3n/HWmu14e+2OsCyseWRDVmwMehZRzZTqWGCHJszkpeVf+fih8E7TUPpZGiFsmDWUMojTh5IP6H1VY/KKdRxKUC+yoExehjLU0IZvuka+CluAN2w4+LjV5BWmoXjyKKNwvuuG+5W86U185KdOVJStx6zOtS6wJava9o5G1VCimEoDhVNIRXq1wsCkoXkEnR8UidafNS8VXilJCRIIgjWUspAvekEYH65HoFShobhXsyQJ7jEVt6tdDyXoQ1LmCGOobRlCTQiBU//3adz/xlrf/vDzFNWEU5Y3l5clj7DGrVoHccRTwnx85VziNX6XAAAgAElEQVTK9gyr8Q1GDZ9WeQTlFXaP8TjlwzW+oDFOKhIyLjhseA8jLEol7/lggvOyjWUBtEWOfB91uQtsVUvQR6/KH3W6cns+Au9u3o1/uedN77khd6IfDarLMOIYh1JORF8lRXUb+ZD6VNcJ8j2EXitEQwkLxghq6KNqalHuI3Q8T0RtKIgoGl+QQAkbmBmVoqbEGsoehf44TRpGoRwNpYIoL1WAoJzjfOei9BBNKcpxZtquEa6hFLeriX7xOIoNx6PMCRVq8tJyDmoU7nttjdG/EdXUoZJVMwdW0YdiPu42spZLxBHlpdLFpaFU+k0UneH2NEEmr7gESrE8yRco7EMpg7DIIv0lD/KR2M4vvZ73/2iT1cX30gU1fsUor9I0ak94cIE9n7C70BvpqM5Kk6AOHYcSyeQVfN2oFiilpfn9G0UBHYwqfzVzYIW9Y0UfS/naWtRpbFyBEuH9s6EfrXYdm4o1FO05FAoicOxWFNjktYfhNbPUUkOhkusBtQ/R9RP0ISlzROjo8hBUPZXea1jDpuURUUUxRSZ5NZDg61TulI+moVjPLzNdNT3jMOGl6sN2z8ENvVYPEXwoQVrIUIQNR1kOIEig6MfiiNBik9cehseHYtBA9JcmNMorSKAYrgfoDtNoZbSF3EYl0Ckf4EMpx+Rla1jCGrZKnPKmHqJ30KHpXvRG0JxvuFNev15IIQPODzN5qHJUZfLy5VVaFntHAoiuoUQxjQV1FMJHymvbFUqUosmreg0ljsX3WKDsYQghihM3mpzyMY2Ut+URpccU9ZVbtL4HL767NTBNpT6UcnDzKRGewQ2XN0AiWgOaMQiUMIER90j5yjSUaHWtjodNqgjYhVPYMsJBpk79eNixKBGE1Tjl9YlVK22Hoznlw78RgAVKKES0HxE9RUSLiGgBEX1Z7u8iojlEtET+jtLOuYKIlhLRYiI6U9t/NBHNl8euJ9m1JqIWIrpb7n+ZiKZo58yW11hCRLMrvY9yECg2SqaHW9Y4lKCXQy1y5MsjyvsU1XF39o+fwyd/+VJgmkAfSkDYcMEiJIzXCNNQImQStUPealjcpZxxKLailDMOpaKBjRFP0Z3ZlWrIYb1y1+QVYXBv0DWj+FACTa6hAqU6Ie4thz1NkIaiC7VqQrkVe7oPJQfgX4UQhwI4DsBlRDQDwOUAnhBCTAfwhPwf8tgFAGYCOAvADUSkvvAbAVwMYLr8O0vuvwjANiHEgQCuA3CtzKsLwJUAjgVwDIArdcFVMwTQrJbnNWoo+nb0F96PcmbbPs7AUN2I6aIQ1PHPBfRUXbNJhMtb71EdjxAFFtU+3WYUKMENTxTtIqy3HMWeHzwgMJqA1o+Hmb1sDVyYFhw+8NE5YPI/e01/4cKiGh+KPsO07VqPzF+PKZc/hK27zDMWK4JnHrDPOhCmoZT7fdruQwiBm59bho09/WXlVwsqFihCiPVCiNfk9k4AiwBMBHAegNtkstsAfFRunwfgLiHEgBBiOYClAI4hogkAhgshXhRODd/uO0fldS+AU6X2ciaAOUKIbiHENgBzUBRCNaMgBJoyTpUZfSgRXuIox11zj+8lLI6YthOnVhz80ResZSmeFl4Ym2ANa7i803hE67q1NJW+7mFTdERpBMPDhvXrmdMGjaWJ+kj18ocJFNtxVbwwk5jtPooCpVSiRPUxRhnYWE6Hzfbc1GqJizfsNB6PoqH85x/fjlRG0/ONrLSEPJMVW3vx3w8twqW/mRcxw9oRiw9FmqKOBPAygPFCiPWAI3QAjJPJJgJYrZ22Ru6bKLf9+z3nCCFyAHYAGB2Ql6lsFxPRXCKau3mzeb2KqBRE0eRlekH0tjFUJY8wAMzfUBXNQPZ8PXNTBZYgnGhTr5g0lOhXDuv1W01inrJEu5apkdOvHxa5V4l2AUR7JkEaa1iAginvMD+K7Xi4IPem86Pq0BQPotdT0DvsRnkFTQ4ZIsR1c5PtXppl59AWFRfF9BaELrTD/HPVmHbVudt6S1dPHWqqFihENAzA7wF8RQjRE5TUsE8E7K/0HO9OIW4SQswSQswaO3ZsQPHCERBokiYvUyPiaXyqiPIq9tB8+Ws2cnsZte0qJUrg5JBBPhTh/Q3CPi+ayiO4p+ykDZYoLbLhMAo/bZfxmQo9rU34BV4+UuhxYAcjooDW8w4bi2JbDTRs3rCwMSJ5N/qv9FjUGaJzAZ2VKOcDQDaCv0Z9yzbBpXfgbM9+ZHtTpDIaO6Da8YEIY4ds91Fc4bL+TpaqBAoRNcERJncKIe6TuzdKMxbk7ya5fw2A/bTTJwFYJ/dPMuz3nENEGQAjAHQH5FVTCqK4sJDpg9JfmmrChm09I/VfYO+sWrVEI3hGWNXwmMoQvWcXtvql7V69IajB1wjS7DwaiqFhieT/KMspb04TtNyze04Z1wk1eYWYrMI0FGuAQkBHIOpcd6ozVo0PJReiHQDB1gYgWkDGiQeO0dJ4E4X5UPQ66h0Mn0gyLMowjkiyaqkmyosA/ArAIiHED7VDDwCYLbdnA7hf23+BjNyaCsf5/oo0i+0kouNknhf6zlF5fRzAk9LP8hiAM4holHTGnyH31RQhRGCvxuOUD/n4o8zK6k/jRuCUa3ytkCC7vuv0NPVE5W+UcoYNkLNXY3QNJR8g4Ly+GJMGE97TjSNsOKrWGXyd4nZYj9euochr2gRKSOOlnoXpcNTlHXIRGshQDSWCD8W21LapjLY8dvbntDTeY3obEab99kWYmdjuf3P2RwkXrzXVTL3yfgD/CGA+Eb0h930DwDUA7iGiiwCsAvAJABBCLCCiewAshBMhdpkQQtXipQB+DaANwCPyD3AE1h1EtBSOZnKBzKubiL4L4FWZ7jtCiO4q7iUSjoYSYPLSX8CQXnMlTsko03rrR6o1eQXdQ5APJcp4GX8+JftDzHteDSVag24ua3HbtPZ8PkKjEqaJeR375jQ2jcE5P0Ab9KaMXCarUz4gek/P1y4YtdII4Rlcq1dvFO23GoGiTx1vq4qwcb9RntuuAV2gCKQ1a3yYxULf19OXxcSRbYHlscmL4rNsYIEihHge9hnST7WccxWAqwz75wI4zLC/H1IgGY7dAuCWqOWNg4IQrsnLpI57VNwqNBSryUvrPfo/1mKa+F6qIA3F9aEYjtmCCkzYw4KDGy7vRIP2/IUQmmZnvw5gi9zT05qvEYuGEsUpH1Kd3gY7eg/ek0dIZyDc5OUdUKi/ot29gyXXMecRQaCEVIbe46804jLKc/M6/71pvD4UQ2dG2/fu5l04dMLwwHLavu0gf+ZQwyPly0CI4tKnNqe8O/Ax5AWKMkVFqQ8l/Hxh2a6EoJX9okwOWY0PxdWArAJHTxvB/wBzWfXszWOLwkPBy5l6xboSYsR7CLxOhPdDYXNE5y3vXrEswY29x6zlO/al377ubkcRKEEdmrDJV/sGowsUe+h6cdvq+/IE4tiPhfpQBuwmr+KsERaBEhDCP9SwQImI+pBcp7xFhW0KGvioO4AjmDhKo7zMeXnPtWZbNj94/B3rsWyArdzVCCKUJcx0YncOi5K0xnxCnOphPhQ974qd8tqnXomWU5x6JaynrW+HaCiWxjpsrq5yZhsOHA0fQfuotYaitCeb+S/KsgNB9xvmQ9HvoXcwV3K89Frm/VlXQ6m/SGGBEhH1PgT5UPJCuLHtYTbTKD20oKlXbJ23KI1XHASbaKK/4OEDG6vTULymseBnUqmGUtYCW5akeqNWMpV/VA3FUycVaihu9F5lGkzksSZBx2LwoehBCWEdG1vnzutDsWkH9m9af3fMJq/i9u4qoryqWVAtbligREQ9zKIGYo4rbw4Y8xDWeBWvJdMHmbwCGtrDJ46Q27V70YLUeWHZbyIsyiuaQLHnH2Zu0sdrmCKfokQmhTvly+vp2uoz7HGWM01++Eh583nugFPL8aAG1pSPOY+i9hs2It/GYK7gTpNUToixp4wh2q0/72pMXn1RBIqlEFk2eTUe6tkrH4lNAwl6ib1TTwTZzMM1lCAfSjmz1lcqdPTr+xunMLOJjnXlv4imF6cs0TQUU156TzZ0BmnLZfoGg0P6vLZ4S6Og9TL95Yj6iLzvV3DaSqO8VGMf5vsKI1jYaPlVqBUO5AruVDthwnXQ0sPXn4P9udk12FCTl7ZvdwSTl1WIs1O+8XA1lIzdR6JHgRlDVAvRPnjXhlxi+tAbN8vbI+wLdJmI+P2XkA1Q56M0oMVzgxu2sIGPQLA9PczMqE+7UamZ8rL/e816fcCvOYSX09/YRw3DDtJyAO87U+kcamGaY1AZzpq5T/FYwM1EGSAcrqHk3clAbR0BNQmrTUPJ58t7biUCpQwN5Y4XV5ovgPCoSVV+9qE0CKu7e/HEImfAv9JATA16Lh/dhxLcqy5ND3gFRNAHWc6yWkGRNEHoH1s259dQitthAiusYbKavDxpg/LXtg2FGdCct2EzSFcqfPXTooSf+kN6o059Hib8vPOWWRpRJbxCrhEluEAv9y3PL8ejCzZglJyqJNC/EtIQB+1XDOYLaGuWAiW0UxOuoUTxofi/Sa8PJXhyyGATeLDWmA15JkMJrykfgXN+/Bx2ygFMmYAFthwNJapAsV+vYGlMwxpHwPGzKJNXlBfM/57rL+24zhbrefr9l5i8fNEx6QARZ6sHt6dsdZhGE84qXYrM9aE0lBSZ8/GOq6jsi9XvwZaFXp/+HrPbAw25TlhDrDd4NjOPShLWgEZp6HX/1C+fWwagOLI8qsPd1tCGRXkN5goY1d4cKa3N/Bc1ICOdIuQLouTZho3Wj2IeFEJYhxGYyllvWEOJwE5tNKwah2J7QZqCjkdsBNULbhsp78/Lm6Y4pUSUSQVtMxoDxdlYjefpAqUCX0/xuO1jDja9FDzXsOev0mVSKbPJSzZ6Hc0ZS6i3+ZombL6rSBqKVg/++owaFhpmBtSrOtQRba33YM3RI1C0ayhtIWgaHLdsBeGupxJFcJnqxfGhpK3H9TLYzH+5KB2BfNH5HziwMWCeuAPHDXP+N9xrlOAT9/0wHx5SWKCUSahTXjbCppHIUVR5/Zj/BRKGNH4EyjN5+fMJmyzRPaY3gCUmr/APsXh9y36hfoN70k4eAQPg5P1l0mTMSwmUtua0ZX42TUMJ+WRNSwwD3jq1N0x2DSVqD9QbQBDcoVm3vS+wHGEhqlaBomtB2nvR0ewYQ1wNKOT9b8k4wsBqmvNoyObn2takrAXm66jzbGNyovjPnE6keU6wbIgvSOXZ0eLUjWn+tShRhjkeh9K4ZCwDG4UQWLZld3FqFsNb7OkhBnxQtum7w9Y/V2ncdT8slwiaRjyqXVdvAEtNXnp+wS95mFM+Sqhu4NxmKpginTJ+1KrRa29OWzsJtgYD8D5n03orThm8+ZnIBTSQUX0ouUJwlKFeZxt7zKsUFkN2Q3r1BWF8NjaTl9JQAGe69aBbyhdEMULL1uGwaEL6tV2nfIhWaNVQIjjlc1on0i8kcwGRe0DxHoa1OOU0DW4MG3jr5M1hww2LzaT1+MKNAIC/LN0KwDbXV3j0ip6uVGgVt02NqLK3qvURbFcIij6J4rj1n+dvAL1O+eDX3LZuhzovUpRXoEPT+W3OpJDNlzaCg/kCiICWTNo6tiiTcp65cRyL1pilI2goUQSKvxyqYfqrZWVB/TpRowx39psXYwoLQS0u/RweZq0/23ZNoKQoPDKvOWC8l/86fg25UBDIFUTRKW+p84GsEijma+jXDhoPE8XkZX4ezq/S3kwzDuu3b3vNsxw23LgUTV7e/Vt861Kbek1Re9U2s0JYw6R22Ro207m2CSj1chjLGOCU94z9CLHWWJ2uIT6UqH4aVc/Fj957XA2Ay6TJqqFkAhppvdFMWzQUT11ZKkRv1Pz1rjdsQeum5AvaEtWGZHmPQDGPe1DP0lalNoFRLKuuORQbyGEtxfifFFHo1CtB0ZIqjb/Mxes6/7c2pUvSmtKFrQ0DmBtrIRzB1ZQxv1vZgGfqpFcaihQohsGN5UxQ2ZfN46Zn3zWmGSpYoJSJK1ACGmLA/AJ5NIOg5U0tkTRhjah64VJKQ7H2aOyaksqDKHiRJk8j52sk9RwrH7GtCyWTNlbcjhIx1+L6tryJB3IFNGdSyKRTVqd8MVS8NH/d7p2yaSgBvWlFkIDWNUB9uvSSsmpBIcZpZrR9tvVSiuUINwOZBIqKevJfo7O1KFAck5dF85TRUs0B472cchTz9t+L0jxaXZOXMQsM5PIleekMekxe9g6cLbIz6lxeyodi0lCiLJ+g19HPn1lmTDNUsEApkybLOBT9P1tjrH+AQRpK1iZQtO2gsOR0iFc+KDigoPXoo/pQBnPxm7zKGVOxTZsW3Y9KZuvxDuQKaMmkkEnZNJRCoIaiGi/nWuEfvG3aeL0+/T3VKJqFShc0Tkqva1u9F7Vj8zX6c8WyGZ3IBYF22ZB7r+HU4WdOmIIUkbUTkHM7AMHmqmyAD29AakbFgY0WDSUX7EPpDxmjpDpSqs79zz9bKFg7oHq5lEAxrdooPCYvW10UE33w4HHGNEMFC5QI6CYk9fCDQnqb0imro1ARHOVldoyGzdWk9qWVzd/Sy8wG9Jx0n0Pe4nj1n1cqPPVyGk93sY8z0Lft99rV0YyVW3db8y+Zg83XeCiTVzpFxk6A3us3VYUy64xqb4o2Ct7qEyju37rbKyD1cgVqKCJ4Nmz9uQ/kzHNHufNCWZ5732De/R5sGoryXfjnSdtneCu+/ZGZSFG4078lREPR68T/rbmReyFOeSUQTd8q4DjJ1UDMfpP2IMvmmhl918nlhaslmcetOb/KKR+moViFcN4Js544si3SUIFawgIlArolo90w+va6Oe/gW/cvAOB80M3plLHXE1WgZHNmDSV8KgfnV7Z/ZY9m1o+pD8HWox7IFaxrchci9KoUNhNQ2GBAtWtcZwt29AU1slLjUiYvX1kH8854BbuGEjy2qF9qKCPbm6NFcOVsDWRxf7dPoIT5LYrpCoEmr2yAmUhdxw3rtTy23sE8RrY5jazuI9HzUN+If1qbpozzvqQCTF6qrsJ8KEF1qoeCB+URpqH0DeYxqsMZHGkSwKoMKjzZn0++INCqQpctnRVAM3mF+FCC1tLJpFJoaUqFLv1ca1igREB/IY8/YHTJvl9ojrB7Pn88Mmlzb3cgZN4ohVrZzv+ee3wfASGbYU55XQD4GyhlT25rCh4HsGsgh5FyJHKJySuGpWjDxuyoj2tUezN6+rKhMfrqfvx5rd3Wi2y+gHSKrFFLQWHD6gNubUpbzZieObQiRC35NRS9XEENRjYXHNk06JbV3PDo74LtqfUN5jHC7bXbNBQ5rkI7ni0INEnNOU12gaJ8i2Eaisd8Z/CLAfo7HKyh2J5JXzaPLvmOG+/V9275y5HNF1zTnUlmRXLKh3wHqhyZNKElkw7scAwFLFAioJ7jOYfvg/HDWwF4G3QVVgoA08YOQ1M6ZWwor/j9fHfb9nJk8wVs3ulEjPkbBc9UDiYNxRUoyuRlxuP/8E/z4Woo9gGagGMOGCkbltLZhrUyhWjgg5Z7CotuUW3AyPYmDOYLxg9eL1tR4/Kme23VdqzZ1mcdp6KHDQePtDePYwH8kU+Wcsobam9Oo3u3N2JQL7PJ9KKna83YHdHq2p2tTcaG5/onl7jbJgGdyxcwmC9oGoqhkRXC7bF7NZSC29GhAB9K3mfyCht7AZR2itT/I9rs5io9nekdz+YLyOaF22kyNfauhmIw8anjLe7gSnvUpxIovaFOeeNtIJt3NNPmDGsoDcXMfUe4g9f0xk9XCFqbUmhKkWFshsCGnn73f1uv6Ydziqsk+j+mbL4QOCWFevnCnPKeUe4lo7K9Ji9bBMzugaLpw9/DCxux7SmLPimiZZyOcS14+auE2o4+y7gKn4C0NVDpFJlHymtjO8xTfOTdcuQLwmga8UwSaFvYSu4f19mCddv7vcciaiiO+c5u8lINXmdLxljOl5ZtdbdNwlM1eEXN1OKUlxqKfjybF+60RemU/b1wHd0hAkU3c9nChtW7YfJNAFqUl+EFUw7yrg4plAz1lXW1+YyxHLqADxqzo0xe/SahFRJpBjjaU1tTGi2ZFAYtvrGhggVKBE4+aCwA4JKTD3B7Wfq7o7/0zekUmjKlGoreWxvemrE2DEs27gIAjBnWbBzgFhRbXxo2bH8B3XLlSj8CAIEfAuCs36A+WH90StRFlvTrAT4zV4iGogSRmgBw14BtoJ7X/GHqjZ592D7IpMjYsOTyug+lNP9XlncDcIIDAEfQ+tFfBZuJT0X2HThuGBb7BjBm8wITR7YBsDvTAedZtgZENqlrD2vNeMxRijNmONPLjxnWYvRbqV66q6FYBEqrIcrL0fSkD4XM0+A45XZ+wwY26vVY8q0pwdnaBCK7KcmdesXwTiitRvlQTBpw8TpmgZLLaxpKwDiUoCgv/XnbvqW+bB5tzY5AYQ2lAbj6Y4fjma+dgnSKkKLSsGB9+U4iQpPBKd8rG5pv/80M9PTn8NtXVpVcpz+bx58XOSPuTzxwTMlLnM0XXDXe1HCpb099uFY7uNZj8zcKqlFvcU1eNg0lh31lI7diizfKyjPCuAyTV86i2RgdzPK4Emqm+gCKjUWrwSek7vXgfTqtPpSCCB7YeMPTjv+sq8OZmXmXIaxXaSipgLE9eRliOmlUe0kkV65QwPTxzgSCJkGgyOYLVl+ROg44JpYBQznU/U0c1WbWUAa9Goot8snklM/mi+HXzYYOl0I9H9f3YHmB9Ma3ZByKbISbMym0NaWNAkXXOExauKuhBNyrur+OFpvJq1A03Rk7Rc6+5nQKzekUerOl747eBti+pb5sHq1SQwl6P4YCFigRmDiyDfuP7gDgCIxhLRnPR68ata+fdTAAp0H325dVemUOAEobl0/+8iV5DeeD8vdGs/kCxsop5bftLh174Y9osg2e1D8O/8dYjFxRJi+zmSebFxjX2YIxw1pKGsCwabs919M1FM/YguA8VHTYyDalGZgjvVQD1WqIxFH129qURrPF75UriNDGDXA0SgDYadCUlNBsa0oHjkNJpwhtzemSOZ3yeRE4gaAimy9GFQX5ezpbMxjMFUo02N7BHFLk+C9Mj02Va/xw5x00jYnJFQpuGQYsGkpQw6fqOMzk1ZvNu9+dv7FX99mclgLFIAz0sps6EupeixqKQaAo/5l8Nv4lAXIyQtBZGsHwPPLFd7OtOW00eXk0FEtd9GfzaGtyfCg2H91QwQKlAjp9AmV7r9OIXPKBAwCYe2AqjfoIgNIBea+v2g4A+OIHD0RrU6pEQ+nPFjC5qx3DWjKYv3ZHSbnUC6fMVbZeoN6787+AJT4Uw0usggbGDGvBsJZ0qclLyzNsBlTP9BQ+57Uye9zw1LuYcvlDvrTS8Srr0zY+I1eioRSvoXqubU1ptLekXS1SZyBbwDDXpGG/F2V6u/vV1SXHlNYysr3Z+kzWbO9DOkVol0JHNVb5gkBvNh84HgJw6rl3MGcdJwUUG7xhLU5efuHUN1hAe3PGunaM8u3sM8IJTNlu8FvlC05QSGtTyrt4Wb4Y3NDaVNpZUqh3XtW5LWqpdyDnmhn934m6r+aM01CHCZQgk1cUDUU51f0h8MpcatN+lVBtyaTR1lT6HelpgACT16AyednrdahggVIBbc1pPLdkMwDvh6t8F8NaMujxfWxbZeTO6GHN+OmnjgQAbNtdTPOl377ubg/IsRH6y/GdBxdi7fY+tDWlMX38MLy7eVdJuf701noARXOVqbeyqacfn79jnvu/1YfSZLdhb5TBBeNHtKLVYFKIMjJcoZsL/cECShv79QsrAMDT4Kt8lT3ftia3P8pLd5D3a2G0HS0Zz7o3ioFcHp0tZhu5jupR325YyvXpdzYhRfYp8pdu2oWH3lqP3sE8Jkgz4uptvQCcMSn5gsB+o9plecxl+N28NSiI4jgpo5nQZ/MvESjZHFqb0k6UouG5//PtcwEA+8hIx+89vKgkTd9gDu3NaXS2NqFHb7S1GQeCbP09ctJKdQ2TMMjlC5i7cpvbo/enUebPtmanoTYJAzU5ZmtTKtDkNbzN8cME+VDU5I6msOFMipypZkwCRZ7f0pTCsNaM8R3WO0q2zkTvoLPccXM65Q39FgK/fHYZFq7rMZ5XC1igVMC7m3djY88AlmzciX///VsAgNMOLU55sP/odryzcZfn4T62wPGNjO5ocXtWSsgM5PJ44M11bto0EVozjoaievi3/GU5AGDjzgGMam8uiWpaumknrn30rwB0DaX0JV680evw9QsU90NqlRFchjwWyBd0n+Gtxh6gfk7QVCEA8NcNxZfdP0/UuOHeFSNNdu9RAc5w5xy/47R4DfWBtjal0dnimIH89TGQdZaSNfk//vRW8ZmdPmO88frbdg/i9VXbURCOaURpdzprpPAAgNHyflSHZNNOR3jv19WOpjS5Da6fr9/rvIeqiKbn9r1HHAGgetT+e+0bzKNdNsImv4NbxmHOc/H3ugtSm+poTmN4awZbtQlT+waLa7y3ZMxaA1C8b2VWM5VDvcPrdjh1429oF63vwbCWDCYMb0VHSwY9hoGv6r3sam82ag/vbnI6bPt1taE1YxZKync4aZTTCShxykuTVyZlnsZIdRhbMikMa8kYv5UXZeTdpFFt1m+pX/lQfOOLVm7txVUPL8KX73rdeF4tYIFSBbsH87h33hoAwIeP2Nfdf9TkUdg1kHMbitXdva4TvmtYsytQlIbif+HTKXJXm/P3ev5u1iR0tpa+fJt3Fs1ntqgToHRhJX90lBqlrcwaJhV6zsKNmNzVjoPGdxobn1yh4JZhe8A8W/e/sRaru4vl0RuZbL6A8Z2tnvSmuZVcDcWgXazf0edqfsqRbJozq7Up7ZqK/PkMyMgp03Q63/zj2+52a1MaXzjlAGRS5DHz6T3M90wagcAFc0cAABqlSURBVEUbekrMgHrnQEWUKcG3SQqg8cMdf5VJIOmo8FG/CbBQENiyy3kWyt/jf7a9UqC0N5vNL4p9R7Ya9/dl8xACaG/JYPq4TixcX+ws7OzPoVN2UiaPbsfSjbuMZjn1Xo8L0FBWdzvf1dfPOhgpQxTXiq27MW1sB1IpwsSRbcbFxHZqZkiTWW3djn60NqXcTpMpbHibNGNPGeP4V/359GfzaMnYfSj9msnL9E0DwO9l+zJ1TIfxePfuQSzbshvNmVSJhrJuh3PfSzaVWjNqBQuUCpi1/ygA8Ji1dN+IesFWyhf/vx5c4B4b3trkChQ1Iv6Gp5d68iciNzpEvXTtzWn843H748NH7IvO1kxJg7FRG+OiGk+TQFm5tdfz/9UP/9XdHsjl8UXZAB8glyVVjZDil88uw3NLtuDwSSMcJ7LB6TmYFxgre7G28SFLN+3Cl+96w7NPBRoI4YR0+jWUPkMwgTJJmATKj+YUB+qNMgzCVI1me3Pa7bWres3mC/jj62udsR3yY7VNm6LoaHGWEdYFj94IqEbBPxJer6Piip9OHjfKKLJxna0Y2xkuUN43ZRQ6W5s8650UCgJrthUb1eJ0In6Tl9PTbW/JGOvzPfuNxEnTx6C9OYNPHzfZ1aYUyic4sq0JE0a2un7DPy/ciLXb+9xOxhETR2DnQA4rDHOwKQ1MDSA2CbZLfvMaAGciRNP719Ofc6MhR3U0GX09b69zfJD7dbUZzbobdvRj/PBWkLQW9A2WpvndPMdfprR5v0WgbzCP9pa0nMm69PwdfVk0px1/k+mbBoCj9h+FfUe0Ylxnq3ENm+vkuLU3Vm0v0VD0NuG8n/0lcM67uGCBUgHXnH8EAOCN1dvdfaM7io3f/l2OvXuVbLzfkWNLTj3EMYspB+5bq7dj3sptbqiwIk1FDWUgl0cuX0DvYB6jZc9SNRh6T1cfNKkc1f45oYCiQDnt0FITzS3Pr3C3p0uB4m/ArpJ2cyUwlm3ZjQXrvL3u3QM5TJRmAJtA+fjPX3C3b75wlqe8SoiO6/QKlK2acNvRl0VrU8rRLpoz2GUweelTpqsQZ9XoLd20Cz9+wvkYR3e0lAiUu15Zha/c7Qi8lkwaTZnSRsHfkKkgAmXefOqvm3DO9c8BAK44+xBMlR2N5b4wa6Wp/vafj3MHUaqephKyE0a0YsKIVjzzzmZPL3Tt9j4c/70n3P9POHAMhrdmPP6Lf//9W/jA958CAFzzscNd05M/CEGZvMYMa0F372BJj3v3QM5tPJ0693dqpDY1ohX7DG/FroEc1m3vw+ek70X5xFTI91d8HQqg2EkbM6wZKSo1Z+nv2ehhzUaT647eQVegmL4VIQTuemUVpoxux+hhLSXmwdXdvXh38y5XQx7R3owdfaUTdi7b7DxH1Qkoqa/BHNqbM2hOm6PadvRlZYdIRo5aNJDp4zsxvM2swaiBzp88ZjKa085sDcoc/NW733TTvbl6uxutWEtYoFTAAWM7MLazxTOqffLodnd7bGcLWptSWCU1lMFcAcdO7cIvZcPZlE5heGsGv5u3Buff+ALOPdwxl334iAkAnJekQzpXN+zodz9cZTIY1pJBNi88H9IGaU9OpwiH7jMcAPCjPy9xB94BwBX3zcdD89fjtEPH4ebZs3D6jPHugDnA26NxemdegaKbFg6bOAJAsXFUvdGtuwawdNMuDG9rQksm5ZbLj0q//+h2Ny+lsd3/xloAjvahozfE23YPuoKZANz3+hpP2nkru3Hz847fiagonO6Zuxo7+7M4/8YX3NU1x3Q2u1FFqmeur23SIscz+D9ov6P2qP1HAgD+8NoaPL14Ez7761fdY2fO3AeHTnCey9wV27Q88rjuz++gOZ3C8QeMdk1eSssZ3taEEw4YjUw6henjOgEAX7m7aBO/7YUVWC/r+AunOFGGuvlECIHfzSvWzUePnOhq0Hpgx3k/fR5zV25DW1Ma+41qgxCOyVDx2IINWLpplzvmor3ZGZyrO7Q3qWCNzlYcLbV4fZCmGiA8WXa4/BrK4g078YPH33FMvobIJyEEpl7xsPv/2GEtaG0qhtsKIXDWj57Fiq29rlN/eGsTsnnheVa/fWU1tvVm0Z8tYExHM7b3ZT0L5J32w2ewYF2PqyGPGdbs0dR7+rP47z8tdP9PpxyBsF0TOpt3DqA/64wb6zBEQgLAjr5B17IxvLUJ2/sGS5bnfmvNDowe1owRbU3YOZArEVqrunsxuasdnztpKoa3STNzX9YYaKA6pLWkoQUKEZ1FRIuJaCkRXT6E18VFJ051///nk6a6PSJ1vLO1Cb96fjl29GWxoacf7z9wjKeR0nuQQjjrWKhefSpFOOXgcUiRE7mlGgfV41amhhnfegyvLO9GviCwaWc/po7pwCvfONX1fwDAW2scLSqbL7h+nGOmdgEA9h3RirXb+9yGWmkTXzvzYDSlU+hq904Nr9JdesoBOP+oiQCA/zz3UADFKKtjr3Z6y+u29+HwiSPw5F83eeru0bfXY8rlDwEATpo+Bk//2ymuCfCmZ5dhMFfA5fc5c5719GXxmROmYIZsiPUBlH9etNG1Sx8yoRPbe7O4VQYuCCFw/o0vFsv9vXNdDeSlZd245DfzPJpTV3uz60MxRXqt3Lob44a34Jl3NuNnTy3Fjl6v1qWex9H7d+HYqV3Y0DOAz9z6qifNlDEdGD+8FZO72nHto3/Ftx9YgA07+nHINx8FUBQguskrXxCYt3Kba/5pl435w/M3uIJPH7OiGurO1ia3p++/n9amNKaO6UCKigJlIJfHm2scE9A+I1oxSUaUKf/WQC7vRgaqqYeUYNGj9FSwxvjhLa7QekcLAlEdh5MPGovmdApHTR7lKdsX7nSuoZ6rf0zOnS8XBwP/80lTQUQY3dGMzVIY7OjLusskK9+T+mYO/dajeGnZVgzmCvjGH5z367QZ43DKIeOQLwi8ttIR8v3ZvGs2UhFzozua3QAaAPj50+/iNhnNd8H79gMAjzlSCIGLbnOe/7FTu9DRUqrNXf3wIjw8f4Nr2tx3ZBv6swWPVUHV3bQxHe6zVZ1UdZ03Vm/H8dNGg4hw0HinwzFv5bYSUzVQ9M/VkoYVKESUBvAzAGcDmAHgk0Q0Y6iuf8nJB7jbY32mGaDYsz/x2icBFKNWFPr/v3h2GaaO6cDB8oU4aHwnujqaMbmrHTc9uwwn/Y9jrlDO1IP36XTP/btfvIj/fmghHp6/ARNGtLoROHdffBwA5wV85p3NHt/J7BOmOGWb7vQYz/7xs1i3vQ8be/px5OSRuOyDBwJwGpc/vrHOFSRzVzrazvlHTQLJhkUJr/95dDE29vS7zvIf/f17ccbM8dIktgODOaeBfOadzW45rvybGSAitxFdubUXq7qLQuOo/Ufh2x+ZiYe/fBIOHt+JN6Vw/MKd87CtN+s2Gl878xAAwH89uNBT9zqkLc+rNBPA8QtkpMYIOJrP1l0D+I8/FB3u23qzeH3VdnTvHsT3H1uM93zncRQKzhoUh08cgef+/YNu2mOnjcai9fYwzXFaKPTHbviLu3/28fsDKA4o/eVzy/GyjPBRAuXYqaPd9Cd//2n86M/veHq+J04fA8AZiPvG6u3Y2NOP7dKcNmFEK372qaMAOA1LQTgCvFAQeGlZUYv97PunYL8up2Pz9OJNWL+jz1Of6r1X2uPq7l709Gcxd0U3fvqU4wsc1d7sCtnvPVL00el85L374pl3NmP3QA4vLN2C7b2DJTM7TBs7zKPNPahFQl5xttORmTiqDWu39aFQEHho/nr3+EePdLR+3ex5x4sr8bV7i2agb314JqbKActvrtmObL7ght4DwD/JTuPYzhZs2NGPfEEgXxDu7AiHTRyO733scCeNFjDx9toevCUF9JGTR2FEWxOeeWezK1Q29fTjpmeXAShqxGPUgGWppQ/k8vjCnY6v6JzDJ2DaWMcErWvpX77rDWzrzWLmRKfD9b4pXWhtSuH+N9biq9Jc+6UPOd/y1848GENBJjxJYjkGwFIhxDIAIKK7AJwHYGHgWTHy/Y8fga/d+5bb89K57wsn4GM3vOBqF8dNG+05fu8lJ+D8G19wG8XDJ43A3x45EQfv04mZ+zr5ffzoSfjB40Wz2rQxzkt15ORRuPJvZrgN6K1/WQEA7uR7gNOwje1swe0vrsTtL67EKQc7wuN3lxzv2lJVqGt/toATrnEE30ffW4xW+49zDsWnbn4ZH/zB056yHzC2w91WvqMH3lznhj5ffvYh2H90h2viOff650vq59bPvg8HjisKxq+deTC+/9hiXHy700u983PH4oQDxrjHT5sxDj976l2ced2zbtjor2bPkvUx0k2ntB/FN845xN0m34C9r552EP6f/OBUr/xf7nkTfj593P5oa0rj7rnFQYsH/sfDKAjgvPfu65n9YMIIbwTUQeOHuQ05UHSIA8Ww1xkThuPKv5kJAK4J8s3V2/Gpm18GAHxQPruj9x+F46Z14aVl3diyawA/+rMTdHDKwWPx688e4+arwliVtggAP77gSFczVQzkCph55WM467B9ivc1rtM1l9z8/HLXbAgAN/7DUa7m8b4pTl4f/on32Z592D6uJn7A2A68K/0Mv7/0BE+602eMx73z1mDmlY/Bz7+cfpCT9xET8K37F5Q808+fPM29xrjOVjw8fwOmfaNoCnviX0/GAbIBVu8gAI/A+Z/zj0BzJoWmtCMYf/bUu/jZU8VlKOZ89QOYLjt4+45sQzYvcMA3HsbnpJA5fcZ4/PiC97odlY6WNJ5avNlT1o8dNRHpFOHswybguSVb8JGfPo/3TBqJP7y+1k3zXx85DEAxWvG0Hz6LL33oQLy0vBvLt+zGyPYmTBs7zNWor7jvLewaOBSFAtzv7f0HOt9JcyaFIyaNxMPzN2h1dQC+8MED3XFYtaZhNRQAEwHow5LXyH1Dxidm7YfXvnm6p+FTHDV5FD4jNQF96hbFfl3t+NOXTgTgjDi//OxDQESuMAGAyz54IE6Q66+cf9Qk92MGgM++fype/Y/TcNL04rV1MxzgRPwonl7saAb6BwYAT//bKZ4G+SBN+znhwDGu3Vvxkffs6+ntH73/KHdKDYXyBb1vSldJAws4DaR/qdJPHTMZna0ZLNuyG10dzThikldIn32Yk6cSJp8/eRpOlYEFTekU7rjoGPh5/Zun4+IPFDXJH/39e/FFKUCA4gcPOKYgf918/uRpWHHNuThmaheuOf9w17wHFOdVOmQf7zn+8ShXnH2o2zABwJdPnV5Szoe+dKLbQKZShAultqLQ353/+9xxbudA8TdayDoAnOw7Dji9aZ2PSZNlXzaPP7y+1qn7q88B4HRMlA9C50AZqAEAU0a3g7yPHZkU4cZPH+3+/9hXPoCPHTUR3z1vputTUZw5cx/3+9B57usfxJdkHf29NCfp/Oe5h+LrZxY7Cf58R7U3ucIEKAaX6JxwwGj8ncybiLC/5v8EgL89cqLnmZ05syhwlYD91zMO8nQkPnfSNNesCjh19cO/ey+Aolls2ebdrjBpyaTwpy+eiHPlt3KI9t1d/+RSvLK8GycfNBb3XnI8AGcq/oPGD8OWXYP46t1v4l9/9ybSKcJT/3aK534/fVzx3bn6bw9HR0tmyIQJAFDY1BhJhYg+AeBMIcTn5P//COAYIcQXfekuBnAxAEyePPnolStLRzLXisFcAfe/sRZH7z/KVVn99MpIkEopFATmLNqIkw8aW/Li9GfzuO2FFRjR1oRb/rIc3zjnUJxiWXP6gTfXoTmdwukzxpcs0JWTC1Bl88I1T/np6c9iU88Apo3p8PiKAGeg2S+eeRcpInzx1OmY3NVuXASsbzCPW19YjrNm7mOsr009/Xho/nqs2daHL5823Y04UizZuBMbewbw4rIt+Oz7p2LMsFJTJOBM0z66o9nTaACO7b4gBNZu60OuIDwNqM5dr6zC9U8swU8+dVRJgwY45orfz1uLJZt24lsfnuERwIq/bujBc+9swYcOHedpEFQ5VmzdjZVbd2MgW8DZh08wliObL+DN1dsxa0pXybH+bB6runvxxKJNOOuwfdwIM52+wTw+/vMXsGBdDx7/6gdcGzzgvFfre/rxoznv4LklW/DV06fj79832XN+Ll/APXPXoKujGcNbMzh4n07X5BqVt9fuwIg2x9/4iVmTPB0qwPk+1u/oxwNvrMOnjp3smv/0ci7ZtAuZNGEgW8CMfb2CE3C0vbwQWLxhJzpbMzjnsAmed1QIgZ6+HPqyefRl8xg/vMX4Ta7u7sUL727Bjr4s/vmkacbnumh9D97ZuBOnHTre9csBju/w5eXdGDOsBR95z77oaMm4vkPFy8u24tEFG3DqIeOxsz+L02aM9/g9tu4awCNvb8DC9T2YNqYDx04djcMnlVpHBnMF63daKUQ0TwgxKzRdAwuU4wF8Wwhxpvz/CgAQQnzPds6sWbPE3Llzh6iEDMMwewZRBUojm7xeBTCdiKYSUTOACwA8UOcyMQzD7LU0rFNeCJEjov8H4DEAaQC3CCEWhJzGMAzD1IiGFSgAIIR4GMDDoQkZhmGYmtPIJi+GYRgmQbBAYRiGYWKBBQrDMAwTCyxQGIZhmFhggcIwDMPEQsMObKwEItoJYHFAkhEAdgQcnwxgVcDxKHmEHY8rj7CyJqGcXJ/x51FtOeMoB9dnvOVIQjkPFkJ0Wo4VEULsNX8A5oYcvynk+OYI1wjLI/B4jHkEljUJ5eT6TF45Y3quXJ8NVp9hacLaTvXHJi8vD4Yc3x5yPEoeYcfjyiOsrEkoJ9dn/HlUW844ysH1GW85klLOUPY2k9dcEWE+mlqdP5Q0QlkboYyKRikrlzNeuJzl5b+3aSg31fn8oaQRytoIZVQ0Slm5nPHC5Swj/71KQ2EYhmFqx96moTAMwzA1Yq8XKER0CxFtIqK3tX3vIaIXiWg+ET1IRMPl/iYiuk3uX6TWYJHHniaixUT0hvwzr2Q1NOVsJqJb5f43iegU7Zyj5f6lRHQ9mVYJSkY5a12f+xHRU/I5LiCiL8v9XUQ0h4iWyN9R2jlXyHpbTERnavtrVqcxl7NmdVpuOYlotEy/i4h+6ssrMfUZUs4k1efpRDRP1ts8IvqQlldNv3kPUULB9uQ/AB8AcBSAt7V9rwI4WW7/E4Dvyu1PAbhLbrcDWAFgivz/aQCzElLOywDcKrfHAZgHICX/fwXA8QAIwCMAzk5oOWtdnxMAHCW3OwG8A2AGgP8BcLncfzmAa+X2DABvAmgBMBXAuwDSta7TmMtZszqtoJwdAE4EcAmAn/rySlJ9BpUzSfV5JIB95fZhANYORX36//Z6DUUI8SyAbt/ugwE8K7fnADhfJQfQQUQZAG0ABgH0JLCcMwA8Ic/bBCekcBYRTQAwXAjxonDetNsBfDRp5YyzPDaEEOuFEK/J7Z0AFgGYCOA8ALfJZLehWD/nwelMDAghlgNYCuCYWtdpXOWMqzxxlVMIsVsI8TyAfj2fpNWnrZy1poJyvi6EWCf3LwDQSkQtQ/HN6+z1AsXC2wA+Irc/AWA/uX0vgN0A1sMZlfoDIYTeeN4qVd9v1lStDC/nmwDOI6IMEU0FcLQ8NhHAGu38NXJf0sqpGJL6JKIpcHp4LwMYL4RYDzgfNRzNCXDqabV2mqq7IavTKsupqHmdRiynjaTVZxhJrM/zAbwuhBjAEH/zLFDM/BOAy4hoHhx1c1DuPwZAHsC+cMwJ/0pE0+SxfxBCHA7gJPn3j3Us5y1wXpy5AH4E4AUAOTgqr5+hCPMrt5zAENUnEQ0D8HsAXxFCBGmbtrobkjqNoZzAENRpGeW0ZmHYV8/6DCJx9UlEMwFcC+DzapchWc2+eRYoBoQQfxVCnCGEOBrAb+HYoQHHh/KoECIrTTR/gTTRCCHWyt+dAP4PQ2NmMJZTCJETQnxVCPFeIcR5AEYCWAKn8Z6kZTEJwDp/vgko55DUJxE1wflY7xRC3Cd3b5RmAmV+2ST3r4FXe1J1V/M6jamcNa/TMstpI2n1aSVp9UlEkwD8AcCFQgjVZg3pN88CxYCK1iCiFID/BPBzeWgVgA+RQweA4wD8VZpsxshzmgB8GI6Zpy7lJKJ2WT4Q0ekAckKIhVJF3klEx0n1/EIA9yetnENRn/L+fwVgkRDih9qhBwDMltuzUayfBwBcIO3SUwFMB/BKres0rnLWuk4rKKeRBNanLZ9E1ScRjQTwEIArhBB/UYmH/JuP28vfaH9weszrAWThSPOLAHwZTlTFOwCuQXEA6DAAv4Pj9FoI4GuiGAkyD8Bb8tiPISNr6lTOKXBmVV4E4M8A9tfymQXnxX8XwE/VOUkq5xDV54lwVP+3ALwh/84BMBpOoMAS+dulnfMfst4WQ4uUqWWdxlXOWtdpheVcASeAY5d8V2YktD5Lypm0+oTTUdutpX0DwLih+Ob1Px4pzzAMw8QCm7wYhmGYWGCBwjAMw8QCCxSGYRgmFligMAzDMLHAAoVhGIaJBRYoDJMQiOgSIrqwjPRTSJvVmWHqTabeBWAYxhkoJ4T4eXhKhkkuLFAYJibkJH6PwpnE70g4AzkvBHAogB/CGRi7BcBnhBDriehpOPOXvR/AA0TUCWCXEOIHRPReODMKtMMZkPZPQohtRHQ0nDnQegE8P3R3xzDhsMmLYeLlYAA3CSGOgLO0wWUAfgLg48KZy+wWAFdp6UcKIU4WQvyvL5/bAfy7zGc+gCvl/lsBfEkIcXwtb4JhKoE1FIaJl9WiOJfSbwB8A86CR3Pk7OZpOFPTKO72Z0BEI+AImmfkrtsA/M6w/w4AZ8d/CwxTGSxQGCZe/HMZ7QSwIECj2F1G3mTIn2ESA5u8GCZeJhOREh6fBPASgLFqHxE1yTUrrAghdgDYRkQnyV3/COAZIcR2ADuI6ES5/x/iLz7DVA5rKAwTL4sAzCaiX8CZEfYnAB4DcL00WWXgLCa2ICSf2QB+TkTtAJYB+Kzc/1kAtxBRr8yXYRIDzzbMMDEho7z+JIQ4rM5FYZi6wCYvhmEYJhZYQ2EYhmFigTUUhmEYJhZYoDAMwzCxwAKFYRiGiQUWKAzDMEwssEBhGIZhYoEFCsMwDBML/x+bURFg17+dfQAAAABJRU5ErkJggg==\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "sorted_data['inc'].plot()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Un zoom sur les dernières années montre mieux la situation des pics en hiver. Le creux des incidences se trouve en été." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 10, "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": {}, "source": [ "## Etude de l'incidence annuelle" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Etant donné que le pic de l'épidémie se situe en hiver, à cheval\n", "entre deux années civiles, nous définissons la période de référence\n", "entre deux minima de l'incidence, du 1er août de l'année $N$ au\n", "1er août de l'année $N+1$.\n", "\n", "Notre tâche est un peu compliquée par le fait que l'année ne comporte\n", "pas un nombre entier de semaines. Nous modifions donc un peu nos périodes\n", "de référence: à la place du 1er août de chaque année, nous utilisons le\n", "premier jour de la semaine qui contient le 1er août.\n", "\n", "Comme l'incidence de syndrome grippal est très faible en été, cette\n", "modification ne risque pas de fausser nos conclusions.\n", "\n", "Encore un petit détail: les données commencent en octobre 1984, ce qui\n", "rend la première année incomplète. Nous commençons donc l'analyse en 1985." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "first_august_week = [pd.Period(pd.Timestamp(y, 8, 1), 'W')\n", " for y in range(1985,\n", " sorted_data.index[-1].year)]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "En partant de cette liste des semaines qui contiennent un 1er août, nous obtenons nos intervalles d'environ un an comme les périodes entre deux semaines adjacentes dans cette liste. Nous calculons les sommes des incidences hebdomadaires pour toutes ces périodes.\n", "\n", "Nous vérifions également que ces périodes contiennent entre 51 et 52 semaines, pour nous protéger contre des éventuelles erreurs dans notre code." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "year = []\n", "yearly_incidence = []\n", "for week1, week2 in zip(first_august_week[:-1],\n", " first_august_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": [ "Voici les incidences annuelles." ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 14, "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": {}, "source": [ "Une liste triée permet de plus facilement répérer les valeurs les plus élevées (à la fin)." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2014 1600941\n", "1991 1659249\n", "1995 1840410\n", "2020 2042389\n", "2012 2175217\n", "2003 2234584\n", "2019 2254386\n", "2006 2307352\n", "2017 2321583\n", "2001 2529279\n", "1992 2574578\n", "1993 2703886\n", "2018 2705325\n", "1988 2765617\n", "2007 2780164\n", "1987 2855570\n", "2016 2856393\n", "2011 2857040\n", "2008 2973918\n", "1998 3034904\n", "2002 3125418\n", "2009 3444020\n", "1994 3514763\n", "1996 3539413\n", "2004 3567744\n", "1997 3620066\n", "2015 3654892\n", "2000 3826372\n", "2005 3835025\n", "1999 3908112\n", "2010 4111392\n", "2013 4182691\n", "1986 5115251\n", "1990 5235827\n", "1989 5466192\n", "dtype: int64" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "yearly_incidence.sort_values()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Enfin, un histogramme montre bien que les épidémies fortes, qui touchent environ 10% de la population\n", " française, sont assez rares: il y en eu trois au cours des 35 dernières années." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 16, "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.hist(xrot=20)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "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": 1 }