From 6577b46a70f652f18fea08a7ce65fcf3b5a8a3b7 Mon Sep 17 00:00:00 2001 From: Konrad Hinsen Date: Tue, 30 Oct 2018 21:14:53 +0100 Subject: [PATCH] Notebooks adapted to changes in Reseau Sentinelles Web site --- .../analyse-syndrome-grippal-jupyter.ipynb | 1953 ++++++++--------- ...syndrome-grippal-orgmode+Lisp+Python+R.org | 40 +- .../analyse-syndrome-grippal-orgmode+R.org | 30 +- .../analyse-syndrome-grippal-orgmode.org | 55 +- .../analyse-syndrome-grippal-rstudio.Rmd | 26 +- 5 files changed, 1046 insertions(+), 1058 deletions(-) diff --git a/module3/ressources/analyse-syndrome-grippal-jupyter.ipynb b/module3/ressources/analyse-syndrome-grippal-jupyter.ipynb index 263451d..01e5fc8 100644 --- a/module3/ressources/analyse-syndrome-grippal-jupyter.ipynb +++ b/module3/ressources/analyse-syndrome-grippal-jupyter.ipynb @@ -11,7 +11,7 @@ "cell_type": "code", "execution_count": 1, "metadata": { - "collapsed": true + "collapsed": false }, "outputs": [], "source": [ @@ -25,7 +25,7 @@ "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. Les dates de départ et de fin sont codées dans l'URL: \"wstart=198501\" pour semaine 1 de l'année 1985 et \"wend=201730\" pour semaine 30 de l'année 2017. La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skiprows=1`." + "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." ] }, { @@ -36,14 +36,14 @@ }, "outputs": [], "source": [ - "data_url = \"http://websenti.u707.jussieu.fr/sentiweb/api/data/rest/getIncidenceFlat?indicator=3&wstart=198501&wend=201730&geo=PAY1&$format=csv\"" + "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:\n", + "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", @@ -56,7 +56,9 @@ "| 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" + "| 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`." ] }, { @@ -102,115 +104,115 @@ " \n", " \n", " 0\n", - " 201730\n", + " 201842\n", " 3\n", - " 3759\n", - " 1299.0\n", - " 6219.0\n", - " 6\n", - " 2.0\n", - " 10.0\n", + " 7832\n", + " 5145.0\n", + " 10519.0\n", + " 12\n", + " 8.0\n", + " 16.0\n", " FR\n", " France\n", " \n", " \n", " 1\n", - " 201729\n", + " 201841\n", " 3\n", - " 5014\n", - " 1989.0\n", - " 8039.0\n", - " 8\n", - " 3.0\n", - " 13.0\n", + " 8048\n", + " 5098.0\n", + " 10998.0\n", + " 12\n", + " 8.0\n", + " 16.0\n", " FR\n", " France\n", " \n", " \n", " 2\n", - " 201728\n", + " 201840\n", " 3\n", - " 5271\n", - " 2576.0\n", - " 7966.0\n", - " 8\n", - " 4.0\n", - " 12.0\n", + " 7409\n", + " 4717.0\n", + " 10101.0\n", + " 11\n", + " 7.0\n", + " 15.0\n", " FR\n", " France\n", " \n", " \n", " 3\n", - " 201727\n", + " 201839\n", " 3\n", - " 3924\n", - " 1432.0\n", - " 6416.0\n", - " 6\n", - " 2.0\n", - " 10.0\n", + " 7174\n", + " 4235.0\n", + " 10113.0\n", + " 11\n", + " 7.0\n", + " 15.0\n", " FR\n", " France\n", " \n", " \n", " 4\n", - " 201726\n", + " 201838\n", " 3\n", - " 3171\n", - " 1166.0\n", - " 5176.0\n", - " 5\n", - " 2.0\n", - " 8.0\n", + " 6127\n", + " 3482.0\n", + " 8772.0\n", + " 9\n", + " 5.0\n", + " 13.0\n", " FR\n", " France\n", " \n", " \n", " 5\n", - " 201725\n", + " 201837\n", " 3\n", - " 837\n", - " 0.0\n", - " 1721.0\n", - " 1\n", - " 0.0\n", - " 2.0\n", + " 4644\n", + " 2200.0\n", + " 7088.0\n", + " 7\n", + " 3.0\n", + " 11.0\n", " FR\n", " France\n", " \n", " \n", " 6\n", - " 201724\n", + " 201836\n", " 3\n", - " 1566\n", - " 248.0\n", - " 2884.0\n", - " 2\n", - " 0.0\n", - " 4.0\n", + " 3215\n", + " 1349.0\n", + " 5081.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 7\n", - " 201723\n", - " 3\n", - " 1664\n", - " 203.0\n", - " 3125.0\n", + " 201835\n", " 3\n", - " 1.0\n", - " 5.0\n", + " 1506\n", + " 239.0\n", + " 2773.0\n", + " 2\n", + " 0.0\n", + " 4.0\n", " FR\n", " France\n", " \n", " \n", " 8\n", - " 201722\n", + " 201834\n", " 3\n", - " 1305\n", - " 92.0\n", - " 2518.0\n", + " 1368\n", + " 116.0\n", + " 2620.0\n", " 2\n", " 0.0\n", " 4.0\n", @@ -219,63 +221,63 @@ " \n", " \n", " 9\n", - " 201721\n", + " 201833\n", + " 3\n", + " 1962\n", + " 5.0\n", + " 3919.0\n", " 3\n", - " 971\n", - " 0.0\n", - " 2046.0\n", - " 1\n", " 0.0\n", - " 3.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 10\n", - " 201720\n", + " 201832\n", " 3\n", - " 2686\n", - " 793.0\n", - " 4579.0\n", - " 4\n", - " 1.0\n", - " 7.0\n", + " 1839\n", + " 183.0\n", + " 3495.0\n", + " 3\n", + " 0.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 11\n", - " 201719\n", + " 201831\n", " 3\n", - " 3461\n", - " 1490.0\n", - " 5432.0\n", - " 5\n", - " 2.0\n", - " 8.0\n", + " 2048\n", + " 242.0\n", + " 3854.0\n", + " 3\n", + " 0.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 12\n", - " 201718\n", + " 201830\n", " 3\n", - " 2102\n", - " 515.0\n", - " 3689.0\n", + " 1951\n", + " 202.0\n", + " 3700.0\n", " 3\n", - " 1.0\n", - " 5.0\n", + " 0.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 13\n", - " 201717\n", + " 201829\n", " 3\n", - " 2071\n", - " 428.0\n", - " 3714.0\n", + " 1951\n", + " 252.0\n", + " 3650.0\n", " 3\n", " 0.0\n", " 6.0\n", @@ -284,209 +286,209 @@ " \n", " \n", " 14\n", - " 201716\n", + " 201828\n", " 3\n", - " 1380\n", - " 222.0\n", - " 2538.0\n", - " 2\n", - " 0.0\n", - " 4.0\n", + " 1654\n", + " 52.0\n", + " 3256.0\n", + " 3\n", + " 1.0\n", + " 5.0\n", " FR\n", " France\n", " \n", " \n", " 15\n", - " 201715\n", + " 201827\n", " 3\n", - " 479\n", - " 0.0\n", - " 1242.0\n", - " 1\n", - " 0.0\n", + " 3269\n", + " 1145.0\n", + " 5393.0\n", + " 5\n", " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 16\n", - " 201714\n", + " 201826\n", " 3\n", - " 1110\n", - " 0.0\n", - " 2549.0\n", - " 2\n", - " 0.0\n", - " 4.0\n", + " 3758\n", + " 1493.0\n", + " 6023.0\n", + " 6\n", + " 3.0\n", + " 9.0\n", " FR\n", " France\n", " \n", " \n", " 17\n", - " 201713\n", + " 201825\n", " 3\n", - " 7594\n", - " 3808.0\n", - " 11380.0\n", - " 12\n", - " 6.0\n", - " 18.0\n", + " 4580\n", + " 2220.0\n", + " 6940.0\n", + " 7\n", + " 3.0\n", + " 11.0\n", " FR\n", " France\n", " \n", " \n", " 18\n", - " 201712\n", + " 201824\n", " 3\n", - " 8780\n", - " 4834.0\n", - " 12726.0\n", - " 13\n", - " 7.0\n", - " 19.0\n", + " 3223\n", + " 1351.0\n", + " 5095.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 19\n", - " 201711\n", + " 201823\n", " 3\n", - " 7814\n", - " 4329.0\n", - " 11299.0\n", - " 12\n", - " 7.0\n", - " 17.0\n", + " 1207\n", + " 136.0\n", + " 2278.0\n", + " 2\n", + " 0.0\n", + " 4.0\n", " FR\n", " France\n", " \n", " \n", " 20\n", - " 201710\n", + " 201822\n", " 3\n", - " 11802\n", - " 7964.0\n", - " 15640.0\n", - " 18\n", - " 12.0\n", - " 24.0\n", + " 3202\n", + " 1330.0\n", + " 5074.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 21\n", - " 201709\n", + " 201821\n", " 3\n", - " 13111\n", - " 9099.0\n", - " 17123.0\n", - " 20\n", - " 14.0\n", - " 26.0\n", + " 2537\n", + " 763.0\n", + " 4311.0\n", + " 4\n", + " 1.0\n", + " 7.0\n", " FR\n", " France\n", " \n", " \n", " 22\n", - " 201708\n", + " 201820\n", " 3\n", - " 29545\n", - " 23136.0\n", - " 35954.0\n", - " 45\n", - " 35.0\n", - " 55.0\n", + " 2694\n", + " 967.0\n", + " 4421.0\n", + " 4\n", + " 1.0\n", + " 7.0\n", " FR\n", " France\n", " \n", " \n", " 23\n", - " 201707\n", + " 201819\n", " 3\n", - " 59590\n", - " 49764.0\n", - " 69416.0\n", - " 91\n", - " 76.0\n", - " 106.0\n", + " 1025\n", + " 0.0\n", + " 2098.0\n", + " 2\n", + " 0.0\n", + " 4.0\n", " FR\n", " France\n", " \n", " \n", " 24\n", - " 201706\n", + " 201818\n", " 3\n", - " 93628\n", - " 82560.0\n", - " 104696.0\n", - " 144\n", - " 127.0\n", - " 161.0\n", + " 3541\n", + " 1416.0\n", + " 5666.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 25\n", - " 201705\n", + " 201817\n", " 3\n", - " 193677\n", - " 179255.0\n", - " 208099.0\n", - " 297\n", - " 275.0\n", - " 319.0\n", + " 2573\n", + " 1003.0\n", + " 4143.0\n", + " 4\n", + " 2.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 26\n", - " 201704\n", + " 201816\n", " 3\n", - " 256428\n", - " 240618.0\n", - " 272238.0\n", - " 394\n", - " 370.0\n", - " 418.0\n", + " 4818\n", + " 2724.0\n", + " 6912.0\n", + " 7\n", + " 4.0\n", + " 10.0\n", " FR\n", " France\n", " \n", " \n", " 27\n", - " 201703\n", + " 201815\n", " 3\n", - " 267276\n", - " 251345.0\n", - " 283207.0\n", - " 410\n", - " 386.0\n", - " 434.0\n", + " 16311\n", + " 12168.0\n", + " 20454.0\n", + " 25\n", + " 19.0\n", + " 31.0\n", " FR\n", " France\n", " \n", " \n", " 28\n", - " 201702\n", + " 201814\n", " 3\n", - " 260588\n", - " 245070.0\n", - " 276106.0\n", - " 400\n", - " 376.0\n", - " 424.0\n", + " 22666\n", + " 18092.0\n", + " 27240.0\n", + " 35\n", + " 28.0\n", + " 42.0\n", " FR\n", " France\n", " \n", " \n", " 29\n", - " 201701\n", + " 201813\n", " 3\n", - " 255535\n", - " 239743.0\n", - " 271327.0\n", - " 392\n", - " 368.0\n", - " 416.0\n", + " 32680\n", + " 25536.0\n", + " 39824.0\n", + " 50\n", + " 39.0\n", + " 61.0\n", " FR\n", " France\n", " \n", @@ -504,124 +506,7 @@ " ...\n", " \n", " \n", - " 1670\n", - " 198530\n", - " 3\n", - " 11598\n", - " 5507.0\n", - " 17689.0\n", - " 21\n", - " 10.0\n", - " 32.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1671\n", - " 198529\n", - " 3\n", - " 13054\n", - " 6474.0\n", - " 19634.0\n", - " 24\n", - " 12.0\n", - " 36.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1672\n", - " 198528\n", - " 3\n", - " 14588\n", - " 7659.0\n", - " 21517.0\n", - " 26\n", - " 13.0\n", - " 39.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1673\n", - " 198527\n", - " 3\n", - " 19670\n", - " 11761.0\n", - " 27579.0\n", - " 36\n", - " 22.0\n", - " 50.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1674\n", - " 198526\n", - " 3\n", - " 18609\n", - " 12637.0\n", - " 24581.0\n", - " 34\n", - " 23.0\n", - " 45.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1675\n", - " 198525\n", - " 3\n", - " 19362\n", - " 12454.0\n", - " 26270.0\n", - " 35\n", - " 22.0\n", - " 48.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1676\n", - " 198524\n", - " 3\n", - " 19855\n", - " 13577.0\n", - " 26133.0\n", - " 36\n", - " 25.0\n", - " 47.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1677\n", - " 198523\n", - " 3\n", - " 19373\n", - " 10010.0\n", - " 28736.0\n", - " 35\n", - " 18.0\n", - " 52.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1678\n", - " 198522\n", - " 3\n", - " 24099\n", - " 17190.0\n", - " 31008.0\n", - " 44\n", - " 31.0\n", - " 57.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1679\n", + " 1743\n", " 198521\n", " 3\n", " 26096\n", @@ -634,7 +519,7 @@ " France\n", " \n", " \n", - " 1680\n", + " 1744\n", " 198520\n", " 3\n", " 27896\n", @@ -647,7 +532,7 @@ " France\n", " \n", " \n", - " 1681\n", + " 1745\n", " 198519\n", " 3\n", " 43154\n", @@ -660,7 +545,7 @@ " France\n", " \n", " \n", - " 1682\n", + " 1746\n", " 198518\n", " 3\n", " 40555\n", @@ -673,7 +558,7 @@ " France\n", " \n", " \n", - " 1683\n", + " 1747\n", " 198517\n", " 3\n", " 34053\n", @@ -686,7 +571,7 @@ " France\n", " \n", " \n", - " 1684\n", + " 1748\n", " 198516\n", " 3\n", " 50362\n", @@ -699,7 +584,7 @@ " France\n", " \n", " \n", - " 1685\n", + " 1749\n", " 198515\n", " 3\n", " 63881\n", @@ -712,7 +597,7 @@ " France\n", " \n", " \n", - " 1686\n", + " 1750\n", " 198514\n", " 3\n", " 134545\n", @@ -725,7 +610,7 @@ " France\n", " \n", " \n", - " 1687\n", + " 1751\n", " 198513\n", " 3\n", " 197206\n", @@ -738,7 +623,7 @@ " France\n", " \n", " \n", - " 1688\n", + " 1752\n", " 198512\n", " 3\n", " 245240\n", @@ -751,7 +636,7 @@ " France\n", " \n", " \n", - " 1689\n", + " 1753\n", " 198511\n", " 3\n", " 276205\n", @@ -764,7 +649,7 @@ " France\n", " \n", " \n", - " 1690\n", + " 1754\n", " 198510\n", " 3\n", " 353231\n", @@ -777,7 +662,7 @@ " France\n", " \n", " \n", - " 1691\n", + " 1755\n", " 198509\n", " 3\n", " 369895\n", @@ -790,7 +675,7 @@ " France\n", " \n", " \n", - " 1692\n", + " 1756\n", " 198508\n", " 3\n", " 389886\n", @@ -803,7 +688,7 @@ " France\n", " \n", " \n", - " 1693\n", + " 1757\n", " 198507\n", " 3\n", " 471852\n", @@ -816,7 +701,7 @@ " France\n", " \n", " \n", - " 1694\n", + " 1758\n", " 198506\n", " 3\n", " 565825\n", @@ -829,7 +714,7 @@ " France\n", " \n", " \n", - " 1695\n", + " 1759\n", " 198505\n", " 3\n", " 637302\n", @@ -842,7 +727,7 @@ " France\n", " \n", " \n", - " 1696\n", + " 1760\n", " 198504\n", " 3\n", " 424937\n", @@ -855,7 +740,7 @@ " France\n", " \n", " \n", - " 1697\n", + " 1761\n", " 198503\n", " 3\n", " 213901\n", @@ -868,7 +753,7 @@ " France\n", " \n", " \n", - " 1698\n", + " 1762\n", " 198502\n", " 3\n", " 97586\n", @@ -881,7 +766,7 @@ " France\n", " \n", " \n", - " 1699\n", + " 1763\n", " 198501\n", " 3\n", " 85489\n", @@ -893,139 +778,256 @@ " FR\n", " France\n", " \n", + " \n", + " 1764\n", + " 198452\n", + " 3\n", + " 84830\n", + " 60602.0\n", + " 109058.0\n", + " 154\n", + " 110.0\n", + " 198.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1765\n", + " 198451\n", + " 3\n", + " 101726\n", + " 80242.0\n", + " 123210.0\n", + " 185\n", + " 146.0\n", + " 224.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1766\n", + " 198450\n", + " 3\n", + " 123680\n", + " 101401.0\n", + " 145959.0\n", + " 225\n", + " 184.0\n", + " 266.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1767\n", + " 198449\n", + " 3\n", + " 101073\n", + " 81684.0\n", + " 120462.0\n", + " 184\n", + " 149.0\n", + " 219.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1768\n", + " 198448\n", + " 3\n", + " 78620\n", + " 60634.0\n", + " 96606.0\n", + " 143\n", + " 110.0\n", + " 176.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1769\n", + " 198447\n", + " 3\n", + " 72029\n", + " 54274.0\n", + " 89784.0\n", + " 131\n", + " 99.0\n", + " 163.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1770\n", + " 198446\n", + " 3\n", + " 87330\n", + " 67686.0\n", + " 106974.0\n", + " 159\n", + " 123.0\n", + " 195.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1771\n", + " 198445\n", + " 3\n", + " 135223\n", + " 101414.0\n", + " 169032.0\n", + " 246\n", + " 184.0\n", + " 308.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1772\n", + " 198444\n", + " 3\n", + " 68422\n", + " 20056.0\n", + " 116788.0\n", + " 125\n", + " 37.0\n", + " 213.0\n", + " FR\n", + " France\n", + " \n", " \n", "\n", - "

1700 rows × 10 columns

\n", + "

1773 rows × 10 columns

\n", "" ], "text/plain": [ - " week indicator inc inc_low inc_up inc100 inc100_low \\\n", - "0 201730 3 3759 1299.0 6219.0 6 2.0 \n", - "1 201729 3 5014 1989.0 8039.0 8 3.0 \n", - "2 201728 3 5271 2576.0 7966.0 8 4.0 \n", - "3 201727 3 3924 1432.0 6416.0 6 2.0 \n", - "4 201726 3 3171 1166.0 5176.0 5 2.0 \n", - "5 201725 3 837 0.0 1721.0 1 0.0 \n", - "6 201724 3 1566 248.0 2884.0 2 0.0 \n", - "7 201723 3 1664 203.0 3125.0 3 1.0 \n", - "8 201722 3 1305 92.0 2518.0 2 0.0 \n", - "9 201721 3 971 0.0 2046.0 1 0.0 \n", - "10 201720 3 2686 793.0 4579.0 4 1.0 \n", - "11 201719 3 3461 1490.0 5432.0 5 2.0 \n", - "12 201718 3 2102 515.0 3689.0 3 1.0 \n", - "13 201717 3 2071 428.0 3714.0 3 0.0 \n", - "14 201716 3 1380 222.0 2538.0 2 0.0 \n", - "15 201715 3 479 0.0 1242.0 1 0.0 \n", - "16 201714 3 1110 0.0 2549.0 2 0.0 \n", - "17 201713 3 7594 3808.0 11380.0 12 6.0 \n", - "18 201712 3 8780 4834.0 12726.0 13 7.0 \n", - "19 201711 3 7814 4329.0 11299.0 12 7.0 \n", - "20 201710 3 11802 7964.0 15640.0 18 12.0 \n", - "21 201709 3 13111 9099.0 17123.0 20 14.0 \n", - "22 201708 3 29545 23136.0 35954.0 45 35.0 \n", - "23 201707 3 59590 49764.0 69416.0 91 76.0 \n", - "24 201706 3 93628 82560.0 104696.0 144 127.0 \n", - "25 201705 3 193677 179255.0 208099.0 297 275.0 \n", - "26 201704 3 256428 240618.0 272238.0 394 370.0 \n", - "27 201703 3 267276 251345.0 283207.0 410 386.0 \n", - "28 201702 3 260588 245070.0 276106.0 400 376.0 \n", - "29 201701 3 255535 239743.0 271327.0 392 368.0 \n", - "... ... ... ... ... ... ... ... \n", - "1670 198530 3 11598 5507.0 17689.0 21 10.0 \n", - "1671 198529 3 13054 6474.0 19634.0 24 12.0 \n", - "1672 198528 3 14588 7659.0 21517.0 26 13.0 \n", - "1673 198527 3 19670 11761.0 27579.0 36 22.0 \n", - "1674 198526 3 18609 12637.0 24581.0 34 23.0 \n", - "1675 198525 3 19362 12454.0 26270.0 35 22.0 \n", - "1676 198524 3 19855 13577.0 26133.0 36 25.0 \n", - "1677 198523 3 19373 10010.0 28736.0 35 18.0 \n", - "1678 198522 3 24099 17190.0 31008.0 44 31.0 \n", - "1679 198521 3 26096 19621.0 32571.0 47 35.0 \n", - "1680 198520 3 27896 20885.0 34907.0 51 38.0 \n", - "1681 198519 3 43154 32821.0 53487.0 78 59.0 \n", - "1682 198518 3 40555 29935.0 51175.0 74 55.0 \n", - "1683 198517 3 34053 24366.0 43740.0 62 44.0 \n", - "1684 198516 3 50362 36451.0 64273.0 91 66.0 \n", - "1685 198515 3 63881 45538.0 82224.0 116 83.0 \n", - "1686 198514 3 134545 114400.0 154690.0 244 207.0 \n", - "1687 198513 3 197206 176080.0 218332.0 357 319.0 \n", - "1688 198512 3 245240 223304.0 267176.0 445 405.0 \n", - "1689 198511 3 276205 252399.0 300011.0 501 458.0 \n", - "1690 198510 3 353231 326279.0 380183.0 640 591.0 \n", - "1691 198509 3 369895 341109.0 398681.0 670 618.0 \n", - "1692 198508 3 389886 359529.0 420243.0 707 652.0 \n", - "1693 198507 3 471852 432599.0 511105.0 855 784.0 \n", - "1694 198506 3 565825 518011.0 613639.0 1026 939.0 \n", - "1695 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", - "1696 198504 3 424937 390794.0 459080.0 770 708.0 \n", - "1697 198503 3 213901 174689.0 253113.0 388 317.0 \n", - "1698 198502 3 97586 80949.0 114223.0 177 147.0 \n", - "1699 198501 3 85489 65918.0 105060.0 155 120.0 \n", + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 201842 3 7832 5145.0 10519.0 12 8.0 \n", + "1 201841 3 8048 5098.0 10998.0 12 8.0 \n", + "2 201840 3 7409 4717.0 10101.0 11 7.0 \n", + "3 201839 3 7174 4235.0 10113.0 11 7.0 \n", + "4 201838 3 6127 3482.0 8772.0 9 5.0 \n", + "5 201837 3 4644 2200.0 7088.0 7 3.0 \n", + "6 201836 3 3215 1349.0 5081.0 5 2.0 \n", + "7 201835 3 1506 239.0 2773.0 2 0.0 \n", + "8 201834 3 1368 116.0 2620.0 2 0.0 \n", + "9 201833 3 1962 5.0 3919.0 3 0.0 \n", + "10 201832 3 1839 183.0 3495.0 3 0.0 \n", + "11 201831 3 2048 242.0 3854.0 3 0.0 \n", + "12 201830 3 1951 202.0 3700.0 3 0.0 \n", + "13 201829 3 1951 252.0 3650.0 3 0.0 \n", + "14 201828 3 1654 52.0 3256.0 3 1.0 \n", + "15 201827 3 3269 1145.0 5393.0 5 2.0 \n", + "16 201826 3 3758 1493.0 6023.0 6 3.0 \n", + "17 201825 3 4580 2220.0 6940.0 7 3.0 \n", + "18 201824 3 3223 1351.0 5095.0 5 2.0 \n", + "19 201823 3 1207 136.0 2278.0 2 0.0 \n", + "20 201822 3 3202 1330.0 5074.0 5 2.0 \n", + "21 201821 3 2537 763.0 4311.0 4 1.0 \n", + "22 201820 3 2694 967.0 4421.0 4 1.0 \n", + "23 201819 3 1025 0.0 2098.0 2 0.0 \n", + "24 201818 3 3541 1416.0 5666.0 5 2.0 \n", + "25 201817 3 2573 1003.0 4143.0 4 2.0 \n", + "26 201816 3 4818 2724.0 6912.0 7 4.0 \n", + "27 201815 3 16311 12168.0 20454.0 25 19.0 \n", + "28 201814 3 22666 18092.0 27240.0 35 28.0 \n", + "29 201813 3 32680 25536.0 39824.0 50 39.0 \n", + "... ... ... ... ... ... ... ... \n", + "1743 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "1744 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "1745 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "1746 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "1747 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "1748 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "1749 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "1750 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "1751 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "1752 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "1753 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "1754 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "1755 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "1756 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "1757 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "1758 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "1759 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "1760 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "1761 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "1762 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "1763 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "1764 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "1765 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "1766 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "1767 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "1768 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "1769 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "1770 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "1771 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "1772 198444 3 68422 20056.0 116788.0 125 37.0 \n", "\n", " inc100_up geo_insee geo_name \n", - "0 10.0 FR France \n", - "1 13.0 FR France \n", - "2 12.0 FR France \n", - "3 10.0 FR France \n", - "4 8.0 FR France \n", - "5 2.0 FR France \n", - "6 4.0 FR France \n", - "7 5.0 FR France \n", + "0 16.0 FR France \n", + "1 16.0 FR France \n", + "2 15.0 FR France \n", + "3 15.0 FR France \n", + "4 13.0 FR France \n", + "5 11.0 FR France \n", + "6 8.0 FR France \n", + "7 4.0 FR France \n", "8 4.0 FR France \n", - "9 3.0 FR France \n", - "10 7.0 FR France \n", - "11 8.0 FR France \n", - "12 5.0 FR France \n", + "9 6.0 FR France \n", + "10 6.0 FR France \n", + "11 6.0 FR France \n", + "12 6.0 FR France \n", "13 6.0 FR France \n", - "14 4.0 FR France \n", - "15 2.0 FR France \n", - "16 4.0 FR France \n", - "17 18.0 FR France \n", - "18 19.0 FR France \n", - "19 17.0 FR France \n", - "20 24.0 FR France \n", - "21 26.0 FR France \n", - "22 55.0 FR France \n", - "23 106.0 FR France \n", - "24 161.0 FR France \n", - "25 319.0 FR France \n", - "26 418.0 FR France \n", - "27 434.0 FR France \n", - "28 424.0 FR France \n", - "29 416.0 FR France \n", + "14 5.0 FR France \n", + "15 8.0 FR France \n", + "16 9.0 FR France \n", + "17 11.0 FR France \n", + "18 8.0 FR France \n", + "19 4.0 FR France \n", + "20 8.0 FR France \n", + "21 7.0 FR France \n", + "22 7.0 FR France \n", + "23 4.0 FR France \n", + "24 8.0 FR France \n", + "25 6.0 FR France \n", + "26 10.0 FR France \n", + "27 31.0 FR France \n", + "28 42.0 FR France \n", + "29 61.0 FR France \n", "... ... ... ... \n", - "1670 32.0 FR France \n", - "1671 36.0 FR France \n", - "1672 39.0 FR France \n", - "1673 50.0 FR France \n", - "1674 45.0 FR France \n", - "1675 48.0 FR France \n", - "1676 47.0 FR France \n", - "1677 52.0 FR France \n", - "1678 57.0 FR France \n", - "1679 59.0 FR France \n", - "1680 64.0 FR France \n", - "1681 97.0 FR France \n", - "1682 93.0 FR France \n", - "1683 80.0 FR France \n", - "1684 116.0 FR France \n", - "1685 149.0 FR France \n", - "1686 281.0 FR France \n", - "1687 395.0 FR France \n", - "1688 485.0 FR France \n", - "1689 544.0 FR France \n", - "1690 689.0 FR France \n", - "1691 722.0 FR France \n", - "1692 762.0 FR France \n", - "1693 926.0 FR France \n", - "1694 1113.0 FR France \n", - "1695 1236.0 FR France \n", - "1696 832.0 FR France \n", - "1697 459.0 FR France \n", - "1698 207.0 FR France \n", - "1699 190.0 FR France \n", + "1743 59.0 FR France \n", + "1744 64.0 FR France \n", + "1745 97.0 FR France \n", + "1746 93.0 FR France \n", + "1747 80.0 FR France \n", + "1748 116.0 FR France \n", + "1749 149.0 FR France \n", + "1750 281.0 FR France \n", + "1751 395.0 FR France \n", + "1752 485.0 FR France \n", + "1753 544.0 FR France \n", + "1754 689.0 FR France \n", + "1755 722.0 FR France \n", + "1756 762.0 FR France \n", + "1757 926.0 FR France \n", + "1758 1113.0 FR France \n", + "1759 1236.0 FR France \n", + "1760 832.0 FR France \n", + "1761 459.0 FR France \n", + "1762 207.0 FR France \n", + "1763 190.0 FR France \n", + "1764 198.0 FR France \n", + "1765 224.0 FR France \n", + "1766 266.0 FR France \n", + "1767 219.0 FR France \n", + "1768 176.0 FR France \n", + "1769 163.0 FR France \n", + "1770 195.0 FR France \n", + "1771 308.0 FR France \n", + "1772 213.0 FR France \n", "\n", - "[1700 rows x 10 columns]" + "[1773 rows x 10 columns]" ] }, "execution_count": 3, @@ -1087,13 +1089,13 @@ " \n", " \n", " \n", - " 1472\n", + " 1536\n", " 198919\n", " 3\n", - " -\n", + " 0\n", " NaN\n", " NaN\n", - " -\n", + " 0\n", " NaN\n", " NaN\n", " FR\n", @@ -1104,11 +1106,11 @@ "" ], "text/plain": [ - " week indicator inc inc_low inc_up inc100 inc100_low inc100_up \\\n", - "1472 198919 3 - NaN NaN - NaN NaN \n", + " week indicator inc inc_low inc_up inc100 inc100_low inc100_up \\\n", + "1536 198919 3 0 NaN NaN 0 NaN NaN \n", "\n", " geo_insee geo_name \n", - "1472 FR France " + "1536 FR France " ] }, "execution_count": 4, @@ -1170,115 +1172,115 @@ " \n", " \n", " 0\n", - " 201730\n", + " 201842\n", " 3\n", - " 3759\n", - " 1299.0\n", - " 6219.0\n", - " 6\n", - " 2.0\n", - " 10.0\n", + " 7832\n", + " 5145.0\n", + " 10519.0\n", + " 12\n", + " 8.0\n", + " 16.0\n", " FR\n", " France\n", " \n", " \n", " 1\n", - " 201729\n", + " 201841\n", " 3\n", - " 5014\n", - " 1989.0\n", - " 8039.0\n", - " 8\n", - " 3.0\n", - " 13.0\n", + " 8048\n", + " 5098.0\n", + " 10998.0\n", + " 12\n", + " 8.0\n", + " 16.0\n", " FR\n", " France\n", " \n", " \n", " 2\n", - " 201728\n", + " 201840\n", " 3\n", - " 5271\n", - " 2576.0\n", - " 7966.0\n", - " 8\n", - " 4.0\n", - " 12.0\n", + " 7409\n", + " 4717.0\n", + " 10101.0\n", + " 11\n", + " 7.0\n", + " 15.0\n", " FR\n", " France\n", " \n", " \n", " 3\n", - " 201727\n", + " 201839\n", " 3\n", - " 3924\n", - " 1432.0\n", - " 6416.0\n", - " 6\n", - " 2.0\n", - " 10.0\n", + " 7174\n", + " 4235.0\n", + " 10113.0\n", + " 11\n", + " 7.0\n", + " 15.0\n", " FR\n", " France\n", " \n", " \n", " 4\n", - " 201726\n", + " 201838\n", " 3\n", - " 3171\n", - " 1166.0\n", - " 5176.0\n", - " 5\n", - " 2.0\n", - " 8.0\n", + " 6127\n", + " 3482.0\n", + " 8772.0\n", + " 9\n", + " 5.0\n", + " 13.0\n", " FR\n", " France\n", " \n", " \n", " 5\n", - " 201725\n", + " 201837\n", " 3\n", - " 837\n", - " 0.0\n", - " 1721.0\n", - " 1\n", - " 0.0\n", - " 2.0\n", + " 4644\n", + " 2200.0\n", + " 7088.0\n", + " 7\n", + " 3.0\n", + " 11.0\n", " FR\n", " France\n", " \n", " \n", " 6\n", - " 201724\n", + " 201836\n", " 3\n", - " 1566\n", - " 248.0\n", - " 2884.0\n", - " 2\n", - " 0.0\n", - " 4.0\n", + " 3215\n", + " 1349.0\n", + " 5081.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 7\n", - " 201723\n", - " 3\n", - " 1664\n", - " 203.0\n", - " 3125.0\n", + " 201835\n", " 3\n", - " 1.0\n", - " 5.0\n", + " 1506\n", + " 239.0\n", + " 2773.0\n", + " 2\n", + " 0.0\n", + " 4.0\n", " FR\n", " France\n", " \n", " \n", " 8\n", - " 201722\n", + " 201834\n", " 3\n", - " 1305\n", - " 92.0\n", - " 2518.0\n", + " 1368\n", + " 116.0\n", + " 2620.0\n", " 2\n", " 0.0\n", " 4.0\n", @@ -1287,63 +1289,63 @@ " \n", " \n", " 9\n", - " 201721\n", + " 201833\n", + " 3\n", + " 1962\n", + " 5.0\n", + " 3919.0\n", " 3\n", - " 971\n", - " 0.0\n", - " 2046.0\n", - " 1\n", " 0.0\n", - " 3.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 10\n", - " 201720\n", + " 201832\n", " 3\n", - " 2686\n", - " 793.0\n", - " 4579.0\n", - " 4\n", - " 1.0\n", - " 7.0\n", + " 1839\n", + " 183.0\n", + " 3495.0\n", + " 3\n", + " 0.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 11\n", - " 201719\n", + " 201831\n", " 3\n", - " 3461\n", - " 1490.0\n", - " 5432.0\n", - " 5\n", - " 2.0\n", - " 8.0\n", + " 2048\n", + " 242.0\n", + " 3854.0\n", + " 3\n", + " 0.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 12\n", - " 201718\n", + " 201830\n", " 3\n", - " 2102\n", - " 515.0\n", - " 3689.0\n", + " 1951\n", + " 202.0\n", + " 3700.0\n", " 3\n", - " 1.0\n", - " 5.0\n", + " 0.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 13\n", - " 201717\n", + " 201829\n", " 3\n", - " 2071\n", - " 428.0\n", - " 3714.0\n", + " 1951\n", + " 252.0\n", + " 3650.0\n", " 3\n", " 0.0\n", " 6.0\n", @@ -1352,209 +1354,209 @@ " \n", " \n", " 14\n", - " 201716\n", + " 201828\n", " 3\n", - " 1380\n", - " 222.0\n", - " 2538.0\n", - " 2\n", - " 0.0\n", - " 4.0\n", + " 1654\n", + " 52.0\n", + " 3256.0\n", + " 3\n", + " 1.0\n", + " 5.0\n", " FR\n", " France\n", " \n", " \n", " 15\n", - " 201715\n", + " 201827\n", " 3\n", - " 479\n", - " 0.0\n", - " 1242.0\n", - " 1\n", - " 0.0\n", + " 3269\n", + " 1145.0\n", + " 5393.0\n", + " 5\n", " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 16\n", - " 201714\n", + " 201826\n", " 3\n", - " 1110\n", - " 0.0\n", - " 2549.0\n", - " 2\n", - " 0.0\n", - " 4.0\n", + " 3758\n", + " 1493.0\n", + " 6023.0\n", + " 6\n", + " 3.0\n", + " 9.0\n", " FR\n", " France\n", " \n", " \n", " 17\n", - " 201713\n", + " 201825\n", " 3\n", - " 7594\n", - " 3808.0\n", - " 11380.0\n", - " 12\n", - " 6.0\n", - " 18.0\n", + " 4580\n", + " 2220.0\n", + " 6940.0\n", + " 7\n", + " 3.0\n", + " 11.0\n", " FR\n", " France\n", " \n", " \n", " 18\n", - " 201712\n", + " 201824\n", " 3\n", - " 8780\n", - " 4834.0\n", - " 12726.0\n", - " 13\n", - " 7.0\n", - " 19.0\n", + " 3223\n", + " 1351.0\n", + " 5095.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 19\n", - " 201711\n", + " 201823\n", " 3\n", - " 7814\n", - " 4329.0\n", - " 11299.0\n", - " 12\n", - " 7.0\n", - " 17.0\n", + " 1207\n", + " 136.0\n", + " 2278.0\n", + " 2\n", + " 0.0\n", + " 4.0\n", " FR\n", " France\n", " \n", " \n", " 20\n", - " 201710\n", + " 201822\n", " 3\n", - " 11802\n", - " 7964.0\n", - " 15640.0\n", - " 18\n", - " 12.0\n", - " 24.0\n", + " 3202\n", + " 1330.0\n", + " 5074.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 21\n", - " 201709\n", + " 201821\n", " 3\n", - " 13111\n", - " 9099.0\n", - " 17123.0\n", - " 20\n", - " 14.0\n", - " 26.0\n", + " 2537\n", + " 763.0\n", + " 4311.0\n", + " 4\n", + " 1.0\n", + " 7.0\n", " FR\n", " France\n", " \n", " \n", " 22\n", - " 201708\n", + " 201820\n", " 3\n", - " 29545\n", - " 23136.0\n", - " 35954.0\n", - " 45\n", - " 35.0\n", - " 55.0\n", + " 2694\n", + " 967.0\n", + " 4421.0\n", + " 4\n", + " 1.0\n", + " 7.0\n", " FR\n", " France\n", " \n", " \n", " 23\n", - " 201707\n", + " 201819\n", " 3\n", - " 59590\n", - " 49764.0\n", - " 69416.0\n", - " 91\n", - " 76.0\n", - " 106.0\n", + " 1025\n", + " 0.0\n", + " 2098.0\n", + " 2\n", + " 0.0\n", + " 4.0\n", " FR\n", " France\n", " \n", " \n", " 24\n", - " 201706\n", + " 201818\n", " 3\n", - " 93628\n", - " 82560.0\n", - " 104696.0\n", - " 144\n", - " 127.0\n", - " 161.0\n", + " 3541\n", + " 1416.0\n", + " 5666.0\n", + " 5\n", + " 2.0\n", + " 8.0\n", " FR\n", " France\n", " \n", " \n", " 25\n", - " 201705\n", + " 201817\n", " 3\n", - " 193677\n", - " 179255.0\n", - " 208099.0\n", - " 297\n", - " 275.0\n", - " 319.0\n", + " 2573\n", + " 1003.0\n", + " 4143.0\n", + " 4\n", + " 2.0\n", + " 6.0\n", " FR\n", " France\n", " \n", " \n", " 26\n", - " 201704\n", + " 201816\n", " 3\n", - " 256428\n", - " 240618.0\n", - " 272238.0\n", - " 394\n", - " 370.0\n", - " 418.0\n", + " 4818\n", + " 2724.0\n", + " 6912.0\n", + " 7\n", + " 4.0\n", + " 10.0\n", " FR\n", " France\n", " \n", " \n", " 27\n", - " 201703\n", + " 201815\n", " 3\n", - " 267276\n", - " 251345.0\n", - " 283207.0\n", - " 410\n", - " 386.0\n", - " 434.0\n", + " 16311\n", + " 12168.0\n", + " 20454.0\n", + " 25\n", + " 19.0\n", + " 31.0\n", " FR\n", " France\n", " \n", " \n", " 28\n", - " 201702\n", + " 201814\n", " 3\n", - " 260588\n", - " 245070.0\n", - " 276106.0\n", - " 400\n", - " 376.0\n", - " 424.0\n", + " 22666\n", + " 18092.0\n", + " 27240.0\n", + " 35\n", + " 28.0\n", + " 42.0\n", " FR\n", " France\n", " \n", " \n", " 29\n", - " 201701\n", + " 201813\n", " 3\n", - " 255535\n", - " 239743.0\n", - " 271327.0\n", - " 392\n", - " 368.0\n", - " 416.0\n", + " 32680\n", + " 25536.0\n", + " 39824.0\n", + " 50\n", + " 39.0\n", + " 61.0\n", " FR\n", " France\n", " \n", @@ -1572,124 +1574,7 @@ " ...\n", " \n", " \n", - " 1670\n", - " 198530\n", - " 3\n", - " 11598\n", - " 5507.0\n", - " 17689.0\n", - " 21\n", - " 10.0\n", - " 32.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1671\n", - " 198529\n", - " 3\n", - " 13054\n", - " 6474.0\n", - " 19634.0\n", - " 24\n", - " 12.0\n", - " 36.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1672\n", - " 198528\n", - " 3\n", - " 14588\n", - " 7659.0\n", - " 21517.0\n", - " 26\n", - " 13.0\n", - " 39.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1673\n", - " 198527\n", - " 3\n", - " 19670\n", - " 11761.0\n", - " 27579.0\n", - " 36\n", - " 22.0\n", - " 50.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1674\n", - " 198526\n", - " 3\n", - " 18609\n", - " 12637.0\n", - " 24581.0\n", - " 34\n", - " 23.0\n", - " 45.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1675\n", - " 198525\n", - " 3\n", - " 19362\n", - " 12454.0\n", - " 26270.0\n", - " 35\n", - " 22.0\n", - " 48.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1676\n", - " 198524\n", - " 3\n", - " 19855\n", - " 13577.0\n", - " 26133.0\n", - " 36\n", - " 25.0\n", - " 47.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1677\n", - " 198523\n", - " 3\n", - " 19373\n", - " 10010.0\n", - " 28736.0\n", - " 35\n", - " 18.0\n", - " 52.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1678\n", - " 198522\n", - " 3\n", - " 24099\n", - " 17190.0\n", - " 31008.0\n", - " 44\n", - " 31.0\n", - " 57.0\n", - " FR\n", - " France\n", - " \n", - " \n", - " 1679\n", + " 1743\n", " 198521\n", " 3\n", " 26096\n", @@ -1702,7 +1587,7 @@ " France\n", " \n", " \n", - " 1680\n", + " 1744\n", " 198520\n", " 3\n", " 27896\n", @@ -1715,7 +1600,7 @@ " France\n", " \n", " \n", - " 1681\n", + " 1745\n", " 198519\n", " 3\n", " 43154\n", @@ -1728,7 +1613,7 @@ " France\n", " \n", " \n", - " 1682\n", + " 1746\n", " 198518\n", " 3\n", " 40555\n", @@ -1741,7 +1626,7 @@ " France\n", " \n", " \n", - " 1683\n", + " 1747\n", " 198517\n", " 3\n", " 34053\n", @@ -1754,7 +1639,7 @@ " France\n", " \n", " \n", - " 1684\n", + " 1748\n", " 198516\n", " 3\n", " 50362\n", @@ -1767,7 +1652,7 @@ " France\n", " \n", " \n", - " 1685\n", + " 1749\n", " 198515\n", " 3\n", " 63881\n", @@ -1780,7 +1665,7 @@ " France\n", " \n", " \n", - " 1686\n", + " 1750\n", " 198514\n", " 3\n", " 134545\n", @@ -1793,7 +1678,7 @@ " France\n", " \n", " \n", - " 1687\n", + " 1751\n", " 198513\n", " 3\n", " 197206\n", @@ -1806,7 +1691,7 @@ " France\n", " \n", " \n", - " 1688\n", + " 1752\n", " 198512\n", " 3\n", " 245240\n", @@ -1819,7 +1704,7 @@ " France\n", " \n", " \n", - " 1689\n", + " 1753\n", " 198511\n", " 3\n", " 276205\n", @@ -1832,7 +1717,7 @@ " France\n", " \n", " \n", - " 1690\n", + " 1754\n", " 198510\n", " 3\n", " 353231\n", @@ -1845,7 +1730,7 @@ " France\n", " \n", " \n", - " 1691\n", + " 1755\n", " 198509\n", " 3\n", " 369895\n", @@ -1858,7 +1743,7 @@ " France\n", " \n", " \n", - " 1692\n", + " 1756\n", " 198508\n", " 3\n", " 389886\n", @@ -1871,7 +1756,7 @@ " France\n", " \n", " \n", - " 1693\n", + " 1757\n", " 198507\n", " 3\n", " 471852\n", @@ -1884,7 +1769,7 @@ " France\n", " \n", " \n", - " 1694\n", + " 1758\n", " 198506\n", " 3\n", " 565825\n", @@ -1897,7 +1782,7 @@ " France\n", " \n", " \n", - " 1695\n", + " 1759\n", " 198505\n", " 3\n", " 637302\n", @@ -1910,7 +1795,7 @@ " France\n", " \n", " \n", - " 1696\n", + " 1760\n", " 198504\n", " 3\n", " 424937\n", @@ -1923,7 +1808,7 @@ " France\n", " \n", " \n", - " 1697\n", + " 1761\n", " 198503\n", " 3\n", " 213901\n", @@ -1936,7 +1821,7 @@ " France\n", " \n", " \n", - " 1698\n", + " 1762\n", " 198502\n", " 3\n", " 97586\n", @@ -1949,7 +1834,7 @@ " France\n", " \n", " \n", - " 1699\n", + " 1763\n", " 198501\n", " 3\n", " 85489\n", @@ -1961,139 +1846,256 @@ " FR\n", " France\n", " \n", + " \n", + " 1764\n", + " 198452\n", + " 3\n", + " 84830\n", + " 60602.0\n", + " 109058.0\n", + " 154\n", + " 110.0\n", + " 198.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1765\n", + " 198451\n", + " 3\n", + " 101726\n", + " 80242.0\n", + " 123210.0\n", + " 185\n", + " 146.0\n", + " 224.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1766\n", + " 198450\n", + " 3\n", + " 123680\n", + " 101401.0\n", + " 145959.0\n", + " 225\n", + " 184.0\n", + " 266.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1767\n", + " 198449\n", + " 3\n", + " 101073\n", + " 81684.0\n", + " 120462.0\n", + " 184\n", + " 149.0\n", + " 219.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1768\n", + " 198448\n", + " 3\n", + " 78620\n", + " 60634.0\n", + " 96606.0\n", + " 143\n", + " 110.0\n", + " 176.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1769\n", + " 198447\n", + " 3\n", + " 72029\n", + " 54274.0\n", + " 89784.0\n", + " 131\n", + " 99.0\n", + " 163.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1770\n", + " 198446\n", + " 3\n", + " 87330\n", + " 67686.0\n", + " 106974.0\n", + " 159\n", + " 123.0\n", + " 195.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1771\n", + " 198445\n", + " 3\n", + " 135223\n", + " 101414.0\n", + " 169032.0\n", + " 246\n", + " 184.0\n", + " 308.0\n", + " FR\n", + " France\n", + " \n", + " \n", + " 1772\n", + " 198444\n", + " 3\n", + " 68422\n", + " 20056.0\n", + " 116788.0\n", + " 125\n", + " 37.0\n", + " 213.0\n", + " FR\n", + " France\n", + " \n", " \n", "\n", - "

1699 rows × 10 columns

\n", + "

1772 rows × 10 columns

\n", "" ], "text/plain": [ - " week indicator inc inc_low inc_up inc100 inc100_low \\\n", - "0 201730 3 3759 1299.0 6219.0 6 2.0 \n", - "1 201729 3 5014 1989.0 8039.0 8 3.0 \n", - "2 201728 3 5271 2576.0 7966.0 8 4.0 \n", - "3 201727 3 3924 1432.0 6416.0 6 2.0 \n", - "4 201726 3 3171 1166.0 5176.0 5 2.0 \n", - "5 201725 3 837 0.0 1721.0 1 0.0 \n", - "6 201724 3 1566 248.0 2884.0 2 0.0 \n", - "7 201723 3 1664 203.0 3125.0 3 1.0 \n", - "8 201722 3 1305 92.0 2518.0 2 0.0 \n", - "9 201721 3 971 0.0 2046.0 1 0.0 \n", - "10 201720 3 2686 793.0 4579.0 4 1.0 \n", - "11 201719 3 3461 1490.0 5432.0 5 2.0 \n", - "12 201718 3 2102 515.0 3689.0 3 1.0 \n", - "13 201717 3 2071 428.0 3714.0 3 0.0 \n", - "14 201716 3 1380 222.0 2538.0 2 0.0 \n", - "15 201715 3 479 0.0 1242.0 1 0.0 \n", - "16 201714 3 1110 0.0 2549.0 2 0.0 \n", - "17 201713 3 7594 3808.0 11380.0 12 6.0 \n", - "18 201712 3 8780 4834.0 12726.0 13 7.0 \n", - "19 201711 3 7814 4329.0 11299.0 12 7.0 \n", - "20 201710 3 11802 7964.0 15640.0 18 12.0 \n", - "21 201709 3 13111 9099.0 17123.0 20 14.0 \n", - "22 201708 3 29545 23136.0 35954.0 45 35.0 \n", - "23 201707 3 59590 49764.0 69416.0 91 76.0 \n", - "24 201706 3 93628 82560.0 104696.0 144 127.0 \n", - "25 201705 3 193677 179255.0 208099.0 297 275.0 \n", - "26 201704 3 256428 240618.0 272238.0 394 370.0 \n", - "27 201703 3 267276 251345.0 283207.0 410 386.0 \n", - "28 201702 3 260588 245070.0 276106.0 400 376.0 \n", - "29 201701 3 255535 239743.0 271327.0 392 368.0 \n", - "... ... ... ... ... ... ... ... \n", - "1670 198530 3 11598 5507.0 17689.0 21 10.0 \n", - "1671 198529 3 13054 6474.0 19634.0 24 12.0 \n", - "1672 198528 3 14588 7659.0 21517.0 26 13.0 \n", - "1673 198527 3 19670 11761.0 27579.0 36 22.0 \n", - "1674 198526 3 18609 12637.0 24581.0 34 23.0 \n", - "1675 198525 3 19362 12454.0 26270.0 35 22.0 \n", - "1676 198524 3 19855 13577.0 26133.0 36 25.0 \n", - "1677 198523 3 19373 10010.0 28736.0 35 18.0 \n", - "1678 198522 3 24099 17190.0 31008.0 44 31.0 \n", - "1679 198521 3 26096 19621.0 32571.0 47 35.0 \n", - "1680 198520 3 27896 20885.0 34907.0 51 38.0 \n", - "1681 198519 3 43154 32821.0 53487.0 78 59.0 \n", - "1682 198518 3 40555 29935.0 51175.0 74 55.0 \n", - "1683 198517 3 34053 24366.0 43740.0 62 44.0 \n", - "1684 198516 3 50362 36451.0 64273.0 91 66.0 \n", - "1685 198515 3 63881 45538.0 82224.0 116 83.0 \n", - "1686 198514 3 134545 114400.0 154690.0 244 207.0 \n", - "1687 198513 3 197206 176080.0 218332.0 357 319.0 \n", - "1688 198512 3 245240 223304.0 267176.0 445 405.0 \n", - "1689 198511 3 276205 252399.0 300011.0 501 458.0 \n", - "1690 198510 3 353231 326279.0 380183.0 640 591.0 \n", - "1691 198509 3 369895 341109.0 398681.0 670 618.0 \n", - "1692 198508 3 389886 359529.0 420243.0 707 652.0 \n", - "1693 198507 3 471852 432599.0 511105.0 855 784.0 \n", - "1694 198506 3 565825 518011.0 613639.0 1026 939.0 \n", - "1695 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", - "1696 198504 3 424937 390794.0 459080.0 770 708.0 \n", - "1697 198503 3 213901 174689.0 253113.0 388 317.0 \n", - "1698 198502 3 97586 80949.0 114223.0 177 147.0 \n", - "1699 198501 3 85489 65918.0 105060.0 155 120.0 \n", + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 201842 3 7832 5145.0 10519.0 12 8.0 \n", + "1 201841 3 8048 5098.0 10998.0 12 8.0 \n", + "2 201840 3 7409 4717.0 10101.0 11 7.0 \n", + "3 201839 3 7174 4235.0 10113.0 11 7.0 \n", + "4 201838 3 6127 3482.0 8772.0 9 5.0 \n", + "5 201837 3 4644 2200.0 7088.0 7 3.0 \n", + "6 201836 3 3215 1349.0 5081.0 5 2.0 \n", + "7 201835 3 1506 239.0 2773.0 2 0.0 \n", + "8 201834 3 1368 116.0 2620.0 2 0.0 \n", + "9 201833 3 1962 5.0 3919.0 3 0.0 \n", + "10 201832 3 1839 183.0 3495.0 3 0.0 \n", + "11 201831 3 2048 242.0 3854.0 3 0.0 \n", + "12 201830 3 1951 202.0 3700.0 3 0.0 \n", + "13 201829 3 1951 252.0 3650.0 3 0.0 \n", + "14 201828 3 1654 52.0 3256.0 3 1.0 \n", + "15 201827 3 3269 1145.0 5393.0 5 2.0 \n", + "16 201826 3 3758 1493.0 6023.0 6 3.0 \n", + "17 201825 3 4580 2220.0 6940.0 7 3.0 \n", + "18 201824 3 3223 1351.0 5095.0 5 2.0 \n", + "19 201823 3 1207 136.0 2278.0 2 0.0 \n", + "20 201822 3 3202 1330.0 5074.0 5 2.0 \n", + "21 201821 3 2537 763.0 4311.0 4 1.0 \n", + "22 201820 3 2694 967.0 4421.0 4 1.0 \n", + "23 201819 3 1025 0.0 2098.0 2 0.0 \n", + "24 201818 3 3541 1416.0 5666.0 5 2.0 \n", + "25 201817 3 2573 1003.0 4143.0 4 2.0 \n", + "26 201816 3 4818 2724.0 6912.0 7 4.0 \n", + "27 201815 3 16311 12168.0 20454.0 25 19.0 \n", + "28 201814 3 22666 18092.0 27240.0 35 28.0 \n", + "29 201813 3 32680 25536.0 39824.0 50 39.0 \n", + "... ... ... ... ... ... ... ... \n", + "1743 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "1744 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "1745 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "1746 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "1747 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "1748 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "1749 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "1750 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "1751 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "1752 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "1753 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "1754 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "1755 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "1756 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "1757 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "1758 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "1759 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "1760 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "1761 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "1762 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "1763 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "1764 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "1765 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "1766 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "1767 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "1768 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "1769 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "1770 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "1771 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "1772 198444 3 68422 20056.0 116788.0 125 37.0 \n", "\n", " inc100_up geo_insee geo_name \n", - "0 10.0 FR France \n", - "1 13.0 FR France \n", - "2 12.0 FR France \n", - "3 10.0 FR France \n", - "4 8.0 FR France \n", - "5 2.0 FR France \n", - "6 4.0 FR France \n", - "7 5.0 FR France \n", + "0 16.0 FR France \n", + "1 16.0 FR France \n", + "2 15.0 FR France \n", + "3 15.0 FR France \n", + "4 13.0 FR France \n", + "5 11.0 FR France \n", + "6 8.0 FR France \n", + "7 4.0 FR France \n", "8 4.0 FR France \n", - "9 3.0 FR France \n", - "10 7.0 FR France \n", - "11 8.0 FR France \n", - "12 5.0 FR France \n", + "9 6.0 FR France \n", + "10 6.0 FR France \n", + "11 6.0 FR France \n", + "12 6.0 FR France \n", "13 6.0 FR France \n", - "14 4.0 FR France \n", - "15 2.0 FR France \n", - "16 4.0 FR France \n", - "17 18.0 FR France \n", - "18 19.0 FR France \n", - "19 17.0 FR France \n", - "20 24.0 FR France \n", - "21 26.0 FR France \n", - "22 55.0 FR France \n", - "23 106.0 FR France \n", - "24 161.0 FR France \n", - "25 319.0 FR France \n", - "26 418.0 FR France \n", - "27 434.0 FR France \n", - "28 424.0 FR France \n", - "29 416.0 FR France \n", + "14 5.0 FR France \n", + "15 8.0 FR France \n", + "16 9.0 FR France \n", + "17 11.0 FR France \n", + "18 8.0 FR France \n", + "19 4.0 FR France \n", + "20 8.0 FR France \n", + "21 7.0 FR France \n", + "22 7.0 FR France \n", + "23 4.0 FR France \n", + "24 8.0 FR France \n", + "25 6.0 FR France \n", + "26 10.0 FR France \n", + "27 31.0 FR France \n", + "28 42.0 FR France \n", + "29 61.0 FR France \n", "... ... ... ... \n", - "1670 32.0 FR France \n", - "1671 36.0 FR France \n", - "1672 39.0 FR France \n", - "1673 50.0 FR France \n", - "1674 45.0 FR France \n", - "1675 48.0 FR France \n", - "1676 47.0 FR France \n", - "1677 52.0 FR France \n", - "1678 57.0 FR France \n", - "1679 59.0 FR France \n", - "1680 64.0 FR France \n", - "1681 97.0 FR France \n", - "1682 93.0 FR France \n", - "1683 80.0 FR France \n", - "1684 116.0 FR France \n", - "1685 149.0 FR France \n", - "1686 281.0 FR France \n", - "1687 395.0 FR France \n", - "1688 485.0 FR France \n", - "1689 544.0 FR France \n", - "1690 689.0 FR France \n", - "1691 722.0 FR France \n", - "1692 762.0 FR France \n", - "1693 926.0 FR France \n", - "1694 1113.0 FR France \n", - "1695 1236.0 FR France \n", - "1696 832.0 FR France \n", - "1697 459.0 FR France \n", - "1698 207.0 FR France \n", - "1699 190.0 FR France \n", + "1743 59.0 FR France \n", + "1744 64.0 FR France \n", + "1745 97.0 FR France \n", + "1746 93.0 FR France \n", + "1747 80.0 FR France \n", + "1748 116.0 FR France \n", + "1749 149.0 FR France \n", + "1750 281.0 FR France \n", + "1751 395.0 FR France \n", + "1752 485.0 FR France \n", + "1753 544.0 FR France \n", + "1754 689.0 FR France \n", + "1755 722.0 FR France \n", + "1756 762.0 FR France \n", + "1757 926.0 FR France \n", + "1758 1113.0 FR France \n", + "1759 1236.0 FR France \n", + "1760 832.0 FR France \n", + "1761 459.0 FR France \n", + "1762 207.0 FR France \n", + "1763 190.0 FR France \n", + "1764 198.0 FR France \n", + "1765 224.0 FR France \n", + "1766 266.0 FR France \n", + "1767 219.0 FR France \n", + "1768 176.0 FR France \n", + "1769 163.0 FR France \n", + "1770 195.0 FR France \n", + "1771 308.0 FR France \n", + "1772 213.0 FR France \n", "\n", - "[1699 rows x 10 columns]" + "[1772 rows x 10 columns]" ] }, "execution_count": 5, @@ -2206,26 +2208,6 @@ " print(p1, p2)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Les incidences hebdomadaires ne sont pas des entiers mais des chaînes de caractères. Ceci est dû au point manquant montré ci-dessous, pour lequel la valeur fournie est \"-\".\n", - "\n", - "Nous convertissons ces chaînes de caractères en entiers." - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "sorted_data['inc'] = sorted_data['inc'].astype(int)" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -2235,7 +2217,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 9, "metadata": { "collapsed": false }, @@ -2243,18 +2225,18 @@ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 10, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY0AAAEPCAYAAAC+35gCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY0AAAEPCAYAAAC+35gCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYRiGYQRjomEYhmEE8/8B7bUFBeO7tZIAAAAASUVORK5CYII=\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -2274,7 +2256,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 10, "metadata": { "collapsed": false }, @@ -2282,18 +2264,18 @@ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 11, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEbCAYAAAAxukhGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niEgn/x+bG6CRG/BGAAAAAABJRU5ErkJggg==\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEbCAYAAAAxukhGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -2326,19 +2308,22 @@ "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." + "modification ne risque pas de fausser nos conclusions.\n", + "\n", + "Encore un petit détail: les données commencent an octobre 1984, ce qui\n", + "rend la première année incomplète. Nous commençons donc l'analyse en 1985." ] }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 11, "metadata": { "collapsed": true }, "outputs": [], "source": [ "first_august_week = [pd.Period(pd.Timestamp(y, 8, 1), 'W')\n", - " for y in range(sorted_data.index[0].year,\n", + " for y in range(1985,\n", " sorted_data.index[-1].year)]" ] }, @@ -2353,7 +2338,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 12, "metadata": { "collapsed": false }, @@ -2379,7 +2364,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 13, "metadata": { "collapsed": false }, @@ -2387,18 +2372,18 @@ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 14, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAEACAYAAABLfPrqAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY0AAAEACAYAAABPiSrXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nZpabg4aZmeXmoGFmZrn9f1gAJxPxoq2fAAAAAElFTkSuQmCC\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -2418,7 +2403,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 14, "metadata": { "collapsed": false }, @@ -2432,6 +2417,7 @@ "2012 2175217\n", "2003 2234584\n", "2006 2307352\n", + "2017 2321583\n", "2001 2529279\n", "1992 2574578\n", "1993 2703886\n", @@ -2460,7 +2446,7 @@ "dtype: int64" ] }, - "execution_count": 15, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -2479,7 +2465,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 15, "metadata": { "collapsed": false }, @@ -2487,18 +2473,18 @@ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 16, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEPCAYAAABcA4N7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRU5ErkJggg==\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -2508,6 +2494,15 @@ "source": [ "yearly_incidence.hist(xrot=20)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] } ], "metadata": { diff --git a/module3/ressources/analyse-syndrome-grippal-orgmode+Lisp+Python+R.org b/module3/ressources/analyse-syndrome-grippal-orgmode+Lisp+Python+R.org index 6604eb2..0ffc5e7 100644 --- a/module3/ressources/analyse-syndrome-grippal-orgmode+Lisp+Python+R.org +++ b/module3/ressources/analyse-syndrome-grippal-orgmode+Lisp+Python+R.org @@ -54,11 +54,11 @@ Nous n'utilisons que des fonctionnalités de base du langage R, une version ant * Préparation des données -Les données de l'incidence du syndrome grippal sont disponibles du site Web du [[http://www.sentiweb.fr/][Réseau Sentinelles]]. Nous les récupérons en format CSV dont chaque ligne correspond à une semaine de la période demandée. Les dates de départ et de fin sont codées dans l'URL: "wstart=198501" pour semaine 1 de l'année 1985 et "wend=201730" pour semaine 30 de l'année 2017. L'URL complet est: +Les données de l'incidence du syndrome grippal sont disponibles du site Web du [[http://www.sentiweb.fr/][Réseau Sentinelles]]. 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. L'URL est: #+NAME: data-url -http://websenti.u707.jussieu.fr/sentiweb/api/data/rest/getIncidenceFlat?indicator=3&wstart=198501&wend=201730&geo=PAY1&$format=csv +http://www.sentiweb.fr/datasets/incidence-PAY-3.csv -Voici l'explication des colonnes donnée sur le site d'origine: +Voici l'explication des colonnes donnée sur [[https://ns.sentiweb.fr/incidence/csv-schema-v1.json][le site d'origine:]] | Nom de colonne | Libellé de colonne | |----------------+-----------------------------------------------------------------------------------------------------------------------------------| @@ -89,22 +89,29 @@ Pour éviter de télécharger les données plusieurs fois, nous les gardons dans (setq buffer-read-only t))) #+END_SRC -La prochaine étape est l'extraction des données qui nous intéressent. D'abord nous découpons le contenu du fichier en lignes, dont nous jetons la première qui ne contient qu'un commentaire. Les autres lignes sont découpées en colonnes, dont nous ne gardons que la première (~"week"~) et la troisième (~"inc"~). Nous insérons ~hline~ comme deuxième élément de notre tableau pour indiquer à org-mode la séparation entre l'en-tête (les noms des colonnes) et les données. +La prochaine étape est l'extraction des données qui nous intéressent. D'abord nous découpons le contenu du fichier en lignes, dont nous jetons la première qui ne contient qu'un commentaire. Les autres lignes sont découpées en colonnes. Pour détecter les données manquantes, nous vérifions si une ligne contient au moins un champ vide. Nous affichons les lignes concernées, et traitons seulement les autres par la suite. Nous n'en gardons que la première (~"week"~) et la troisième (~"inc"~) colonne. Nous insérons ~hline~ comme deuxième élément de notre tableau pour indiquer à org-mode la séparation entre l'en-tête (les noms des colonnes) et les données. -#+NAME: raw-data +#+NAME: data #+BEGIN_SRC emacs-lisp :results silent :var name=data-buffer-name (require 'cl) (require 'dash) +(defun missing-data? (row) + (--any (string= it "") row)) (with-current-buffer name (let* ((lines (split-string (buffer-string) "\n" t)) (table (rest lines)) (columns (--map (split-string it ",") table))) + (setq missing-data-lines (-filter 'missing-data? columns)) (-insert-at 1 'hline - (-select-columns '(0 2) columns)))) + (-select-columns '(0 2) (-remove 'missing-data? columns))))) +#+END_SRC + +#+BEGIN_SRC emacs-lisp +missing-data-lines #+END_SRC Regardons les premières et les dernières lignes: -#+BEGIN_SRC emacs-lisp :results value :var data=raw-data :colnames yes +#+BEGIN_SRC emacs-lisp :results value :var data=data :colnames yes (-concat (-take 5 data) '(hline) (-take-last 5 data)) @@ -113,7 +120,7 @@ Regardons les premières et les dernières lignes: ** Vérification Il est toujours prudent de vérifier si les données semblent crédibles. Nous savons que les semaines sont données par six chiffres (quatre pour l'année et deux pour la semaine), dont les deux premiers sont ou "19" ou "20", et que les incidences sont des nombres entiers positifs. -#+BEGIN_SRC emacs-lisp :results output :var data=raw-data :colnames yes +#+BEGIN_SRC emacs-lisp :results output :var data=data :colnames yes (defun check-week (week) (unless (string-match-p (rx (or "19" "20") (repeat 4 digit)) week) (princ (format "Invalid week value: %s\n" week)))) @@ -128,23 +135,16 @@ Il est toujours prudent de vérifier si les données semblent crédibles. Nous s data) #+END_SRC -La vérification a mis en évidence un point manquant dans le jeu de données. Nous l'éliminons, ce qui n'a pas d'impact fort sur notre analyse qui est assez simple. - -#+NAME: valid-data -#+BEGIN_SRC emacs-lisp :results silent :var data=raw-data :colnames yes -(-remove (lambda (week+inc) - (equal "-" (second week+inc))) - data) -#+END_SRC +Rien à signaler ! ** Conversions Pour faciliter les traitements suivants, nous remplaçons les numéros de semaine ISO par les dates qui correspondent aux lundis. A cette occasion, nous trions aussi les données par la date, et nous transformons les incidences en nombres entiers. Nous utilisons le langage Python 3 parce qu'il est un des rares à proposer la conversion de semaines ISO en dates dans sa biblithèque standard. -#+BEGIN_SRC python :results silent :var data=valid-data +#+BEGIN_SRC python :results silent :var input_data=data import datetime data = [(datetime.datetime.strptime(year_and_week + ":1" , '%G%V:%u').date(), int(inc)) - for year_and_week, inc in data] + for year_and_week, inc in input_data] data.sort(key = lambda record: record[0]) #+END_SRC @@ -204,9 +204,9 @@ pic_annuel = function(annee) { } #+END_SRC -Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en janvier 1985, ce qui ne permet pas de quantifier complètement le pic attribué à cette année. Nous le supprimons donc de notre analyse. Par contre, les données se terminent en été 2017, peu avant le 1er août, ce qui nous permet d'inclure cette année dans l'analyse. +Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en octobre 1984, ce qui ne permet pas de quantifier complètement le pic attribué à l'année 1985. Nous le supprimons donc de notre analyse. Par contre, les données se terminent après le 1er août 2018 (pour une exécution après cette date bien sûr), ce qui nous permet d'inclure cette année dans l'analyse. #+BEGIN_SRC R :results silent -annees <- 1986:2017 +annees <- 1986:2018 #+END_SRC #+BEGIN_SRC R :results value diff --git a/module3/ressources/analyse-syndrome-grippal-orgmode+R.org b/module3/ressources/analyse-syndrome-grippal-orgmode+R.org index a271f6f..2d93296 100644 --- a/module3/ressources/analyse-syndrome-grippal-orgmode+R.org +++ b/module3/ressources/analyse-syndrome-grippal-orgmode+R.org @@ -39,11 +39,11 @@ options(width=150) * Préparation des données -Les données de l'incidence du syndrome grippal sont disponibles du site Web du [[http://www.sentiweb.fr/][Réseau Sentinelles]]. Nous les récupérons en format CSV dont chaque ligne correspond à une semaine de la période demandée. Les dates de départ et de fin sont codées dans l'URL: "wstart=198501" pour semaine 1 de l'année 1985 et "wend=201730" pour semaine 30 de l'année 2017. L'URL complet est: +Les données de l'incidence du syndrome grippal sont disponibles du site Web du [[http://www.sentiweb.fr/][Réseau Sentinelles]]. 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. L'URL est: #+NAME: data-url -http://websenti.u707.jussieu.fr/sentiweb/api/data/rest/getIncidenceFlat?indicator=3&wstart=198501&wend=201730&geo=PAY1&$format=csv +http://www.sentiweb.fr/datasets/incidence-PAY-3.csv -Voici l'explication des colonnes donnée sur le site d'origine: +Voici l'explication des colonnes donnée sur [[https://ns.sentiweb.fr/incidence/csv-schema-v1.json][le site d'origine:]] | Nom de colonne | Libellé de colonne | |----------------+-----------------------------------------------------------------------------------------------------------------------------------| @@ -59,12 +59,14 @@ Voici l'explication des colonnes donnée sur le site d'origine: | ~geo_name~ | Libellé de la zone géographique (ce libellé peut être modifié sans préavis) | ** Téléchargement -Après avoir téléchargé les données, nous commençons par l'extraction des données qui nous intéressent. D'abord nous découpons le contenu du fichier en lignes, dont nous jetons la première qui ne contient qu'un commentaire. Les autres lignes sont découpées en colonnes. +La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skip=1`. #+BEGIN_SRC R :session :results silent :var url=data-url data = read.csv(trimws(url), skip=1) #+END_SRC +Après avoir téléchargé les données, nous commençons par l'extraction des données qui nous intéressent. D'abord nous découpons le contenu du fichier en lignes, dont nous jetons la première qui ne contient qu'un commentaire. Les autres lignes sont découpées en colonnes. + #+BEGIN_SRC R :results output head(data) tail(data) @@ -83,22 +85,12 @@ class(data$week) class(data$inc) #+END_SRC -Les semaines ont été lues comme entiers, il va falloir les interpréter correctement. L'approche la plus facile est de relire les données en expliquant à R que le "-" indique une valeur manquante: -#+BEGIN_SRC R :session :results output :var url=data-url -data = read.csv(trimws(url), skip=1, na.strings="-") -head(data) -#+END_SRC - -Maintenant les deux colonnes `week` et `inc` sont de classe `integer`: -#+BEGIN_SRC R :session :results output :var url=data-url -class(data$week) -class(data$inc) -#+END_SRC +Ce sont des entiers, tout va bien ! ** Conversions Pour faciliter les traitements suivants, nous remplaçons les numéros de semaine ISO par les dates qui correspondent aux lundis. D'abord, une petite fonction qui fait le travail: #+BEGIN_SRC R :results silent -converti_week = function(w) { +convert_week = function(w) { ws = paste(w) iso = paste0(substring(ws,1,4), "-W", substring(ws,5,6)) as.Date(parse_iso_8601(iso)) @@ -107,7 +99,7 @@ converti_week = function(w) { Nous appliquons cette fonction à tous les points, créant une nouvelle colonne `date` dans notre jeu de données: #+BEGIN_SRC R :results output -data$date = as.Date(sapply(data$week, convert_week)) +data$date = as.Date(convert_week(data$week)) #+END_SRC Vérifions qu'elle est de classe `Date`: @@ -152,9 +144,9 @@ pic_annuel = function(annee) { } #+END_SRC -Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en janvier 1985, ce qui ne permet pas de quantifier complètement le pic attribué à cette année. Nous le supprimons donc de notre analyse. Par contre, les données se terminent en été 2017, peu avant le 1er août, ce qui nous permet d'inclure cette année dans l'analyse. +Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en octobre 1984, ce qui ne permet pas de quantifier complètement le pic attribué à l'année 1985. Nous le supprimons donc de notre analyse. Par contre, pour une exécution en octobre 2018, les données se terminent après le 1er août 2018, ce qui nous permet d'inclure cette année. #+BEGIN_SRC R :results silent -annees <- 1986:2017 +annees <- 1986:2018 #+END_SRC Nous créons un nouveau jeu de données pour l'incidence annuelle, en applicant la fonction `pic_annuel` à chaque année: diff --git a/module3/ressources/analyse-syndrome-grippal-orgmode.org b/module3/ressources/analyse-syndrome-grippal-orgmode.org index 91a8ffc..f3c780a 100644 --- a/module3/ressources/analyse-syndrome-grippal-orgmode.org +++ b/module3/ressources/analyse-syndrome-grippal-orgmode.org @@ -42,11 +42,11 @@ Nous n'utilisons que des fonctionnalités de base du langage R, une version ant * Préparation des données -Les données de l'incidence du syndrome grippal sont disponibles du site Web du [[http://www.sentiweb.fr/][Réseau Sentinelles]]. Nous les récupérons en format CSV dont chaque ligne correspond à une semaine de la période demandée. Les dates de départ et de fin sont codées dans l'URL: "wstart=198501" pour semaine 1 de l'année 1985 et "wend=201730" pour semaine 30 de l'année 2017. L'URL complet est: +Les données de l'incidence du syndrome grippal sont disponibles du site Web du [[http://www.sentiweb.fr/][Réseau Sentinelles]]. 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. L'URL est: #+NAME: data-url -http://websenti.u707.jussieu.fr/sentiweb/api/data/rest/getIncidenceFlat?indicator=3&wstart=198501&wend=201730&geo=PAY1&$format=csv +http://www.sentiweb.fr/datasets/incidence-PAY-3.csv -Voici l'explication des colonnes donnée sur le site d'origine: +Voici l'explication des colonnes donnée sur [[https://ns.sentiweb.fr/incidence/csv-schema-v1.json][le site d'origine:]] | Nom de colonne | Libellé de colonne | |----------------+-----------------------------------------------------------------------------------------------------------------------------------| @@ -70,7 +70,7 @@ Après avoir téléchargé les données, nous commençons par l'extraction des d from urllib.request import urlopen data = urlopen(data_url).read() -lines = data.decode('utf-8').strip().split('\n') +lines = data.decode('latin-1').strip().split('\n') data_lines = lines[1:] table = [line.split(',') for line in data_lines] #+END_SRC @@ -80,59 +80,70 @@ Regardons ce que nous avons obtenu: table[:5] #+END_SRC +** Recherche de données manquantes +Il y a malheureusement beaucoup de façon d'indiquer l'absence d'un point de données. Nous testons ici seulement pour la présence de champs vides. Il faudrait aussi rechercher des valeurs non-numériques dans les colonnes à priori numériques. Nous ne le faisons pas ici, mais une vérification ultérieure capterait des telles anomalies. + +Nous construisons un nouveau jeu de données sans les lignes qui contiennent des champs vides. Nous affichons ces lignes pour en garder une trace. +#+BEGIN_SRC python :results output +valid_table = [] +for row in table: + missing = any([column == '' for column in row]) + if missing: + print(row) + else: + valid_table.append(row) +#+END_SRC + ** Extraction des colonnes utilisées Il y a deux colonnes qui nous intéressent: la première (~"week"~) et la troisième (~"inc"~). Nous vérifions leurs noms dans l'en-tête, que nous effaçons par la suite. Enfin, nous créons un tableau avec les deux colonnes pour le traitement suivant. #+BEGIN_SRC python :results silent -week = [row[0] for row in table] +week = [row[0] for row in valid_table] assert week[0] == 'week' del week[0] -inc = [row[2] for row in table] +inc = [row[2] for row in valid_table] assert inc[0] == 'inc del inc[0] -raw_data = list(zip(week, inc)) +data = list(zip(week, inc)) #+END_SRC Regardons les premières et les dernières lignes. Nous insérons ~None~ pour indiquer à org-mode la séparation entre les trois sections du tableau: en-tête, début des données, fin des données. #+BEGIN_SRC python :results value -[('week', 'inc'), None] + raw_data[:5] + [None] + raw_data[-5:] +[('week', 'inc'), None] + data[:5] + [None] + data[-5:] #+END_SRC ** Vérification Il est toujours prudent de vérifier si les données semblent crédibles. Nous savons que les semaines sont données par six chiffres (quatre pour l'année et deux pour la semaine), et que les incidences sont des nombres entiers positifs. #+BEGIN_SRC python :results output -for week, inc in raw_data: +for week, inc in data: if len(week) != 6 or not week.isdigit(): print("Valeur suspecte dans la colonne 'week': ", (week, inc)) if not inc.isdigit(): print("Valeur suspecte dans la colonne 'inc': ", (week, inc)) #+END_SRC -La vérification a mis en évidence un point manquant dans le jeux de données. Nous l'éliminons, ce qui n'a pas d'impact fort sur notre analyse qui est assez simple. -#+BEGIN_SRC python :results silent -valid_data = [record for record in raw_data if record[1] != '-'] -#+END_SRC +Pas de problème ! ** Conversions Pour faciliter les traitements suivants, nous remplaçons les numéros de semaine ISO par les dates qui correspondent aux lundis. A cette occasion, nous trions aussi les données par la date, et nous transformons les incidences en nombres entiers. #+BEGIN_SRC python :results silent import datetime -data = [(datetime.datetime.strptime(year_and_week + ":1" , '%G%V:%u').date(), - int(inc)) - for year_and_week, inc in valid_data] -data.sort(key = lambda record: record[0]) +converted_data = [(datetime.datetime.strptime(year_and_week + ":1" , '%G%V:%u').date(), + int(inc)) + for year_and_week, inc in data] +converted_data.sort(key = lambda record: record[0]) #+END_SRC Regardons de nouveau les premières et les dernières lignes: #+BEGIN_SRC python :results value -str_data = [(str(date), str(inc)) for date, inc in data] +str_data = [(str(date), str(inc)) for date, inc in converted_data] [('date', 'inc'), None] + str_data[:5] + [None] + str_data[-5:] #+END_SRC ** Vérification des dates Nous faisons encore une vérification: nos dates doivent être séparées d'exactement une semaine, sauf autour du point manquant. #+BEGIN_SRC python :results output -dates = [date for date, _ in data] +dates = [date for date, _ in converted_data] for date1, date2 in zip(dates[:-1], dates[1:]): if date2-date1 != datetime.timedelta(weeks=1): print(f"Il y a {date2-date1} entre {date1} et {date2}") @@ -144,7 +155,7 @@ Nous passons au langage R pour inspecter nos données, parce que l'analyse et la Nous utilisons le mécanisme d'échange de données proposé par org-mode, ce qui nécessite un peu de code Python pour transformer les données dans le bon format. #+NAME: data-for-R #+BEGIN_SRC python :results silent -[('date', 'inc'), None] + [(str(date), inc) for date, inc in data] +[('date', 'inc'), None] + [(str(date), inc) for date, inc in converted_data] #+END_SRC En R, les données arrivent sous forme d'un data frame, mais il faut encore convertir les dates, qui arrivent comme chaînes de caractères. @@ -179,9 +190,9 @@ pic_annuel = function(annee) { } #+END_SRC -Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en janvier 1985, ce qui ne permet pas de quantifier complètement le pic attribué à cette année. Nous le supprimons donc de notre analyse. Par contre, les données se terminent en été 2017, peu avant le 1er août, ce qui nous permet d'inclure cette année dans l'analyse. +Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en octobre 1984, ce qui ne permet pas de quantifier complètement le pic attribué à l'année 1985. Nous le supprimons donc de notre analyse. Par contre, les données se terminent après le 1er août 2018 (pour une exécution après cette date bien sûr), ce qui nous permet d'inclure cette année dans l'analyse. #+BEGIN_SRC R :results silent -annees <- 1986:2017 +annees <- 1986:2018 #+END_SRC #+BEGIN_SRC R :results value diff --git a/module3/ressources/analyse-syndrome-grippal-rstudio.Rmd b/module3/ressources/analyse-syndrome-grippal-rstudio.Rmd index 1501796..771e78f 100644 --- a/module3/ressources/analyse-syndrome-grippal-rstudio.Rmd +++ b/module3/ressources/analyse-syndrome-grippal-rstudio.Rmd @@ -21,12 +21,12 @@ knitr::opts_chunk$set(echo = TRUE) ## Préparation des données -Les données de l'incidence du syndrome grippal sont disponibles du site Web du [Réseau Sentinelles](http://www.sentiweb.fr/). Nous les récupérons en format CSV dont chaque ligne correspond à une semaine de la période demandée. Les dates de départ et de fin sont codées dans l'URL: "wstart=198501" pour semaine 1 de l'année 1985 et "wend=201730" pour semaine 30 de l'année 2017. L'URL complet est: +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. L'URL est: ```{r} -data_url = "http://websenti.u707.jussieu.fr/sentiweb/api/data/rest/getIncidenceFlat?indicator=3&wstart=198501&wend=201730&geo=PAY1&$format=csv" +data_url = "http://www.sentiweb.fr/datasets/incidence-PAY-3.csv" ``` -Voici l'explication des colonnes donnée sur le site d'origine: +Voici l'explication des colonnes donnée sur le [sur le site d'origine](https://ns.sentiweb.fr/incidence/csv-schema-v1.json): | Nom de colonne | Libellé de colonne | |----------------+-----------------------------------------------------------------------------------------------------------------------------------| @@ -41,6 +41,7 @@ Voici l'explication des colonnes donnée sur le site d'origine: | `geo_insee` | Code de la zone géographique concernée (Code INSEE) http://www.insee.fr/fr/methodes/nomenclatures/cog/ | | `geo_name` | Libellé de la zone géographique (ce libellé peut être modifié sans préavis) | +La première ligne du fichier CSV est un commentaire, que nous ignorons en précisant `skip=1`. ### Téléchargement ```{r} data = read.csv(data_url, skip=1) @@ -63,18 +64,7 @@ Les deux colonnes qui nous intéressent sont `week` et `inc`. Vérifions leurs c class(data$week) class(data$inc) ``` - -La colonne `inc` est de classe `factor` à cause du point manquant dont la valeur de `inc` est `'-'`. Pour faciliter le traîtement ultérieur, nous relisons les données en demandant à `R` de traiter cette valeur comme `na`: -```{r} -data = read.csv(data_url, skip=1, na.strings="-") -head(data) -``` - -Maintenant les deux colonnes `week` et `inc` sont de classe `integer`: -```{r} -class(data$week) -class(data$inc) -``` +Ce sont des entiers, tout va bien ! ### Conversion des numéros de semaine @@ -96,7 +86,7 @@ convert_week = function(w) { Nous appliquons cette fonction à tous les points, créant une nouvelle colonne `date` dans notre jeu de données: ```{r} -data$date = as.Date(sapply(data$week, convert_week)) +data$date = as.Date(convert_week(data$week)) ``` Vérifions qu'elle est de classe `Date`: @@ -141,9 +131,9 @@ pic_annuel = function(annee) { } ``` -Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en janvier 1985, ce qui ne permet pas de quantifier complètement le pic attribué à cette année. Nous l'enlevons donc de notre analyse. Par contre, les données se terminent en été 2017, peu avant le 1er août, ce qui nous permet d'inclure cette année. +Nous devons aussi faire attention aux premières et dernières années de notre jeux de données. Les données commencent en octobre 1984, ce qui ne permet pas de quantifier complètement le pic attribué à 1985. Nous l'enlevons donc de notre analyse. Par contre, pour une exécution en octobre 2018, les données se terminent après le 1er août 2018, ce qui nous permet d'inclure cette année. ```{r} -annees = 1986:2017 +annees = 1986:2018 ``` Nous créons un nouveau jeu de données pour l'incidence annuelle, en applicant la fonction `pic_annuel` à chaque année: -- 2.18.1