From e84f30e5296952da8e0f6224827db4381819d0e7 Mon Sep 17 00:00:00 2001 From: 6f892419cc99326ee525ed439d8ff5df <6f892419cc99326ee525ed439d8ff5df@app-learninglab.inria.fr> Date: Sun, 28 Feb 2021 17:14:29 +0000 Subject: [PATCH] 1 --- module3/exo1/analyse-syndrome-grippal.ipynb | 2100 ++++++++++++++++++- 1 file changed, 2095 insertions(+), 5 deletions(-) diff --git a/module3/exo1/analyse-syndrome-grippal.ipynb b/module3/exo1/analyse-syndrome-grippal.ipynb index bea8429..f279f28 100644 --- a/module3/exo1/analyse-syndrome-grippal.ipynb +++ b/module3/exo1/analyse-syndrome-grippal.ipynb @@ -340,15 +340,2105 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, - "outputs": [], + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "ename": "TypeError", + "evalue": "parser_f() got an unexpected keyword argument 'data_url'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mraw_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mskiprows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mraw_data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mTypeError\u001b[0m: parser_f() got an unexpected keyword argument 'data_url'" + ] + } + ], "source": [ "raw_data = pd.read_csv(data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\", skiprows=1)\n", "raw_data" ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "import isoweek" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "data_url = \"http://www.sentiweb.fr/datasets/incidence-PAY-3.csv\"" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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
020210732899423212.034776.04435.053.0FRFrance
120210632336519231.027499.03529.041.0FRFrance
220210532242618445.026407.03428.040.0FRFrance
320210432580421491.030117.03932.046.0FRFrance
420210332181017894.025726.03327.039.0FRFrance
520210231732013906.020734.02621.031.0FRFrance
620210132179917778.025820.03327.039.0FRFrance
720205332122016498.025942.03225.039.0FRFrance
820205231642812285.020571.02519.031.0FRFrance
920205132161917370.025868.03327.039.0FRFrance
1020205031684513220.020470.02620.032.0FRFrance
112020493129399923.015955.02015.025.0FRFrance
1220204831380410641.016967.02116.026.0FRFrance
1320204731908515285.022885.02923.035.0FRFrance
1420204632480120503.029099.03831.045.0FRFrance
1520204534251636857.048175.06556.074.0FRFrance
1620204434456738521.050613.06859.077.0FRFrance
1720204334373737523.049951.06657.075.0FRFrance
1820204233514529812.040478.05345.061.0FRFrance
1920204132787723206.032548.04235.049.0FRFrance
2020204032044316381.024505.03125.037.0FRFrance
2120203931981015900.023720.03024.036.0FRFrance
2220203832556221142.029982.03932.046.0FRFrance
2320203731848514649.022321.02822.034.0FRFrance
242020363103907646.013134.01612.020.0FRFrance
25202035399186842.012994.01510.020.0FRFrance
26202034360843090.09078.094.014.0FRFrance
27202033361063411.08801.095.013.0FRFrance
28202032359183330.08506.095.013.0FRFrance
29202031343512269.06433.074.010.0FRFrance
.................................
186519852132609619621.032571.04735.059.0FRFrance
186619852032789620885.034907.05138.064.0FRFrance
186719851934315432821.053487.07859.097.0FRFrance
186819851834055529935.051175.07455.093.0FRFrance
186919851733405324366.043740.06244.080.0FRFrance
187019851635036236451.064273.09166.0116.0FRFrance
187119851536388145538.082224.011683.0149.0FRFrance
18721985143134545114400.0154690.0244207.0281.0FRFrance
18731985133197206176080.0218332.0357319.0395.0FRFrance
18741985123245240223304.0267176.0445405.0485.0FRFrance
18751985113276205252399.0300011.0501458.0544.0FRFrance
18761985103353231326279.0380183.0640591.0689.0FRFrance
18771985093369895341109.0398681.0670618.0722.0FRFrance
18781985083389886359529.0420243.0707652.0762.0FRFrance
18791985073471852432599.0511105.0855784.0926.0FRFrance
18801985063565825518011.0613639.01026939.01113.0FRFrance
18811985053637302592795.0681809.011551074.01236.0FRFrance
18821985043424937390794.0459080.0770708.0832.0FRFrance
18831985033213901174689.0253113.0388317.0459.0FRFrance
188419850239758680949.0114223.0177147.0207.0FRFrance
188519850138548965918.0105060.0155120.0190.0FRFrance
188619845238483060602.0109058.0154110.0198.0FRFrance
1887198451310172680242.0123210.0185146.0224.0FRFrance
18881984503123680101401.0145959.0225184.0266.0FRFrance
1889198449310107381684.0120462.0184149.0219.0FRFrance
189019844837862060634.096606.0143110.0176.0FRFrance
189119844737202954274.089784.013199.0163.0FRFrance
189219844638733067686.0106974.0159123.0195.0FRFrance
18931984453135223101414.0169032.0246184.0308.0FRFrance
189419844436842220056.0116788.012537.0213.0FRFrance
\n", + "

1895 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202107 3 28994 23212.0 34776.0 44 35.0 \n", + "1 202106 3 23365 19231.0 27499.0 35 29.0 \n", + "2 202105 3 22426 18445.0 26407.0 34 28.0 \n", + "3 202104 3 25804 21491.0 30117.0 39 32.0 \n", + "4 202103 3 21810 17894.0 25726.0 33 27.0 \n", + "5 202102 3 17320 13906.0 20734.0 26 21.0 \n", + "6 202101 3 21799 17778.0 25820.0 33 27.0 \n", + "7 202053 3 21220 16498.0 25942.0 32 25.0 \n", + "8 202052 3 16428 12285.0 20571.0 25 19.0 \n", + "9 202051 3 21619 17370.0 25868.0 33 27.0 \n", + "10 202050 3 16845 13220.0 20470.0 26 20.0 \n", + "11 202049 3 12939 9923.0 15955.0 20 15.0 \n", + "12 202048 3 13804 10641.0 16967.0 21 16.0 \n", + "13 202047 3 19085 15285.0 22885.0 29 23.0 \n", + "14 202046 3 24801 20503.0 29099.0 38 31.0 \n", + "15 202045 3 42516 36857.0 48175.0 65 56.0 \n", + "16 202044 3 44567 38521.0 50613.0 68 59.0 \n", + "17 202043 3 43737 37523.0 49951.0 66 57.0 \n", + "18 202042 3 35145 29812.0 40478.0 53 45.0 \n", + "19 202041 3 27877 23206.0 32548.0 42 35.0 \n", + "20 202040 3 20443 16381.0 24505.0 31 25.0 \n", + "21 202039 3 19810 15900.0 23720.0 30 24.0 \n", + "22 202038 3 25562 21142.0 29982.0 39 32.0 \n", + "23 202037 3 18485 14649.0 22321.0 28 22.0 \n", + "24 202036 3 10390 7646.0 13134.0 16 12.0 \n", + "25 202035 3 9918 6842.0 12994.0 15 10.0 \n", + "26 202034 3 6084 3090.0 9078.0 9 4.0 \n", + "27 202033 3 6106 3411.0 8801.0 9 5.0 \n", + "28 202032 3 5918 3330.0 8506.0 9 5.0 \n", + "29 202031 3 4351 2269.0 6433.0 7 4.0 \n", + "... ... ... ... ... ... ... ... \n", + "1865 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "1866 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "1867 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "1868 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "1869 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "1870 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "1871 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "1872 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "1873 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "1874 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "1875 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "1876 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "1877 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "1878 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "1879 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "1880 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "1881 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "1882 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "1883 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "1884 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "1885 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "1886 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "1887 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "1888 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "1889 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "1890 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "1891 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "1892 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "1893 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "1894 198444 3 68422 20056.0 116788.0 125 37.0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 53.0 FR France \n", + "1 41.0 FR France \n", + "2 40.0 FR France \n", + "3 46.0 FR France \n", + "4 39.0 FR France \n", + "5 31.0 FR France \n", + "6 39.0 FR France \n", + "7 39.0 FR France \n", + "8 31.0 FR France \n", + "9 39.0 FR France \n", + "10 32.0 FR France \n", + "11 25.0 FR France \n", + "12 26.0 FR France \n", + "13 35.0 FR France \n", + "14 45.0 FR France \n", + "15 74.0 FR France \n", + "16 77.0 FR France \n", + "17 75.0 FR France \n", + "18 61.0 FR France \n", + "19 49.0 FR France \n", + "20 37.0 FR France \n", + "21 36.0 FR France \n", + "22 46.0 FR France \n", + "23 34.0 FR France \n", + "24 20.0 FR France \n", + "25 20.0 FR France \n", + "26 14.0 FR France \n", + "27 13.0 FR France \n", + "28 13.0 FR France \n", + "29 10.0 FR France \n", + "... ... ... ... \n", + "1865 59.0 FR France \n", + "1866 64.0 FR France \n", + "1867 97.0 FR France \n", + "1868 93.0 FR France \n", + "1869 80.0 FR France \n", + "1870 116.0 FR France \n", + "1871 149.0 FR France \n", + "1872 281.0 FR France \n", + "1873 395.0 FR France \n", + "1874 485.0 FR France \n", + "1875 544.0 FR France \n", + "1876 689.0 FR France \n", + "1877 722.0 FR France \n", + "1878 762.0 FR France \n", + "1879 926.0 FR France \n", + "1880 1113.0 FR France \n", + "1881 1236.0 FR France \n", + "1882 832.0 FR France \n", + "1883 459.0 FR France \n", + "1884 207.0 FR France \n", + "1885 190.0 FR France \n", + "1886 198.0 FR France \n", + "1887 224.0 FR France \n", + "1888 266.0 FR France \n", + "1889 219.0 FR France \n", + "1890 176.0 FR France \n", + "1891 163.0 FR France \n", + "1892 195.0 FR France \n", + "1893 308.0 FR France \n", + "1894 213.0 FR France \n", + "\n", + "[1895 rows x 10 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "raw_data = pd.read_csv(data_url, skiprows=1)\n", + "raw_data" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "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
165819891930NaNNaN0NaNNaNFRFrance
\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low inc100_up \\\n", + "1658 198919 3 0 NaN NaN 0 NaN NaN \n", + "\n", + " geo_insee geo_name \n", + "1658 FR France " + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "raw_data[raw_data.isnull().any(axis=1)]" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "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
020210732899423212.034776.04435.053.0FRFrance
120210632336519231.027499.03529.041.0FRFrance
220210532242618445.026407.03428.040.0FRFrance
320210432580421491.030117.03932.046.0FRFrance
420210332181017894.025726.03327.039.0FRFrance
520210231732013906.020734.02621.031.0FRFrance
620210132179917778.025820.03327.039.0FRFrance
720205332122016498.025942.03225.039.0FRFrance
820205231642812285.020571.02519.031.0FRFrance
920205132161917370.025868.03327.039.0FRFrance
1020205031684513220.020470.02620.032.0FRFrance
112020493129399923.015955.02015.025.0FRFrance
1220204831380410641.016967.02116.026.0FRFrance
1320204731908515285.022885.02923.035.0FRFrance
1420204632480120503.029099.03831.045.0FRFrance
1520204534251636857.048175.06556.074.0FRFrance
1620204434456738521.050613.06859.077.0FRFrance
1720204334373737523.049951.06657.075.0FRFrance
1820204233514529812.040478.05345.061.0FRFrance
1920204132787723206.032548.04235.049.0FRFrance
2020204032044316381.024505.03125.037.0FRFrance
2120203931981015900.023720.03024.036.0FRFrance
2220203832556221142.029982.03932.046.0FRFrance
2320203731848514649.022321.02822.034.0FRFrance
242020363103907646.013134.01612.020.0FRFrance
25202035399186842.012994.01510.020.0FRFrance
26202034360843090.09078.094.014.0FRFrance
27202033361063411.08801.095.013.0FRFrance
28202032359183330.08506.095.013.0FRFrance
29202031343512269.06433.074.010.0FRFrance
.................................
186519852132609619621.032571.04735.059.0FRFrance
186619852032789620885.034907.05138.064.0FRFrance
186719851934315432821.053487.07859.097.0FRFrance
186819851834055529935.051175.07455.093.0FRFrance
186919851733405324366.043740.06244.080.0FRFrance
187019851635036236451.064273.09166.0116.0FRFrance
187119851536388145538.082224.011683.0149.0FRFrance
18721985143134545114400.0154690.0244207.0281.0FRFrance
18731985133197206176080.0218332.0357319.0395.0FRFrance
18741985123245240223304.0267176.0445405.0485.0FRFrance
18751985113276205252399.0300011.0501458.0544.0FRFrance
18761985103353231326279.0380183.0640591.0689.0FRFrance
18771985093369895341109.0398681.0670618.0722.0FRFrance
18781985083389886359529.0420243.0707652.0762.0FRFrance
18791985073471852432599.0511105.0855784.0926.0FRFrance
18801985063565825518011.0613639.01026939.01113.0FRFrance
18811985053637302592795.0681809.011551074.01236.0FRFrance
18821985043424937390794.0459080.0770708.0832.0FRFrance
18831985033213901174689.0253113.0388317.0459.0FRFrance
188419850239758680949.0114223.0177147.0207.0FRFrance
188519850138548965918.0105060.0155120.0190.0FRFrance
188619845238483060602.0109058.0154110.0198.0FRFrance
1887198451310172680242.0123210.0185146.0224.0FRFrance
18881984503123680101401.0145959.0225184.0266.0FRFrance
1889198449310107381684.0120462.0184149.0219.0FRFrance
189019844837862060634.096606.0143110.0176.0FRFrance
189119844737202954274.089784.013199.0163.0FRFrance
189219844638733067686.0106974.0159123.0195.0FRFrance
18931984453135223101414.0169032.0246184.0308.0FRFrance
189419844436842220056.0116788.012537.0213.0FRFrance
\n", + "

1894 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " week indicator inc inc_low inc_up inc100 inc100_low \\\n", + "0 202107 3 28994 23212.0 34776.0 44 35.0 \n", + "1 202106 3 23365 19231.0 27499.0 35 29.0 \n", + "2 202105 3 22426 18445.0 26407.0 34 28.0 \n", + "3 202104 3 25804 21491.0 30117.0 39 32.0 \n", + "4 202103 3 21810 17894.0 25726.0 33 27.0 \n", + "5 202102 3 17320 13906.0 20734.0 26 21.0 \n", + "6 202101 3 21799 17778.0 25820.0 33 27.0 \n", + "7 202053 3 21220 16498.0 25942.0 32 25.0 \n", + "8 202052 3 16428 12285.0 20571.0 25 19.0 \n", + "9 202051 3 21619 17370.0 25868.0 33 27.0 \n", + "10 202050 3 16845 13220.0 20470.0 26 20.0 \n", + "11 202049 3 12939 9923.0 15955.0 20 15.0 \n", + "12 202048 3 13804 10641.0 16967.0 21 16.0 \n", + "13 202047 3 19085 15285.0 22885.0 29 23.0 \n", + "14 202046 3 24801 20503.0 29099.0 38 31.0 \n", + "15 202045 3 42516 36857.0 48175.0 65 56.0 \n", + "16 202044 3 44567 38521.0 50613.0 68 59.0 \n", + "17 202043 3 43737 37523.0 49951.0 66 57.0 \n", + "18 202042 3 35145 29812.0 40478.0 53 45.0 \n", + "19 202041 3 27877 23206.0 32548.0 42 35.0 \n", + "20 202040 3 20443 16381.0 24505.0 31 25.0 \n", + "21 202039 3 19810 15900.0 23720.0 30 24.0 \n", + "22 202038 3 25562 21142.0 29982.0 39 32.0 \n", + "23 202037 3 18485 14649.0 22321.0 28 22.0 \n", + "24 202036 3 10390 7646.0 13134.0 16 12.0 \n", + "25 202035 3 9918 6842.0 12994.0 15 10.0 \n", + "26 202034 3 6084 3090.0 9078.0 9 4.0 \n", + "27 202033 3 6106 3411.0 8801.0 9 5.0 \n", + "28 202032 3 5918 3330.0 8506.0 9 5.0 \n", + "29 202031 3 4351 2269.0 6433.0 7 4.0 \n", + "... ... ... ... ... ... ... ... \n", + "1865 198521 3 26096 19621.0 32571.0 47 35.0 \n", + "1866 198520 3 27896 20885.0 34907.0 51 38.0 \n", + "1867 198519 3 43154 32821.0 53487.0 78 59.0 \n", + "1868 198518 3 40555 29935.0 51175.0 74 55.0 \n", + "1869 198517 3 34053 24366.0 43740.0 62 44.0 \n", + "1870 198516 3 50362 36451.0 64273.0 91 66.0 \n", + "1871 198515 3 63881 45538.0 82224.0 116 83.0 \n", + "1872 198514 3 134545 114400.0 154690.0 244 207.0 \n", + "1873 198513 3 197206 176080.0 218332.0 357 319.0 \n", + "1874 198512 3 245240 223304.0 267176.0 445 405.0 \n", + "1875 198511 3 276205 252399.0 300011.0 501 458.0 \n", + "1876 198510 3 353231 326279.0 380183.0 640 591.0 \n", + "1877 198509 3 369895 341109.0 398681.0 670 618.0 \n", + "1878 198508 3 389886 359529.0 420243.0 707 652.0 \n", + "1879 198507 3 471852 432599.0 511105.0 855 784.0 \n", + "1880 198506 3 565825 518011.0 613639.0 1026 939.0 \n", + "1881 198505 3 637302 592795.0 681809.0 1155 1074.0 \n", + "1882 198504 3 424937 390794.0 459080.0 770 708.0 \n", + "1883 198503 3 213901 174689.0 253113.0 388 317.0 \n", + "1884 198502 3 97586 80949.0 114223.0 177 147.0 \n", + "1885 198501 3 85489 65918.0 105060.0 155 120.0 \n", + "1886 198452 3 84830 60602.0 109058.0 154 110.0 \n", + "1887 198451 3 101726 80242.0 123210.0 185 146.0 \n", + "1888 198450 3 123680 101401.0 145959.0 225 184.0 \n", + "1889 198449 3 101073 81684.0 120462.0 184 149.0 \n", + "1890 198448 3 78620 60634.0 96606.0 143 110.0 \n", + "1891 198447 3 72029 54274.0 89784.0 131 99.0 \n", + "1892 198446 3 87330 67686.0 106974.0 159 123.0 \n", + "1893 198445 3 135223 101414.0 169032.0 246 184.0 \n", + "1894 198444 3 68422 20056.0 116788.0 125 37.0 \n", + "\n", + " inc100_up geo_insee geo_name \n", + "0 53.0 FR France \n", + "1 41.0 FR France \n", + "2 40.0 FR France \n", + "3 46.0 FR France \n", + "4 39.0 FR France \n", + "5 31.0 FR France \n", + "6 39.0 FR France \n", + "7 39.0 FR France \n", + "8 31.0 FR France \n", + "9 39.0 FR France \n", + "10 32.0 FR France \n", + "11 25.0 FR France \n", + "12 26.0 FR France \n", + "13 35.0 FR France \n", + "14 45.0 FR France \n", + "15 74.0 FR France \n", + "16 77.0 FR France \n", + "17 75.0 FR France \n", + "18 61.0 FR France \n", + "19 49.0 FR France \n", + "20 37.0 FR France \n", + "21 36.0 FR France \n", + "22 46.0 FR France \n", + "23 34.0 FR France \n", + "24 20.0 FR France \n", + "25 20.0 FR France \n", + "26 14.0 FR France \n", + "27 13.0 FR France \n", + "28 13.0 FR France \n", + "29 10.0 FR France \n", + "... ... ... ... \n", + "1865 59.0 FR France \n", + "1866 64.0 FR France \n", + "1867 97.0 FR France \n", + "1868 93.0 FR France \n", + "1869 80.0 FR France \n", + "1870 116.0 FR France \n", + "1871 149.0 FR France \n", + "1872 281.0 FR France \n", + "1873 395.0 FR France \n", + "1874 485.0 FR France \n", + "1875 544.0 FR France \n", + "1876 689.0 FR France \n", + "1877 722.0 FR France \n", + "1878 762.0 FR France \n", + "1879 926.0 FR France \n", + "1880 1113.0 FR France \n", + "1881 1236.0 FR France \n", + "1882 832.0 FR France \n", + "1883 459.0 FR France \n", + "1884 207.0 FR France \n", + "1885 190.0 FR France \n", + "1886 198.0 FR France \n", + "1887 224.0 FR France \n", + "1888 266.0 FR France \n", + "1889 219.0 FR France \n", + "1890 176.0 FR France \n", + "1891 163.0 FR France \n", + "1892 195.0 FR France \n", + "1893 308.0 FR France \n", + "1894 213.0 FR France \n", + "\n", + "[1894 rows x 10 columns]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = raw_data.dropna().copy()\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "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": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "sorted_data = data.set_index('period').sort_index()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { -- 2.18.1