{ "cells": [ { "cell_type": "code", "execution_count": 56, "id": "482d19ab-5dd1-4e75-b2c1-df734ce5ee66", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 57, "id": "b1b5a536-b76c-427b-ab6b-f0235c84f5ad", "metadata": {}, "outputs": [], "source": [ "import os\n", "import s3fs\n", "# Create filesystem object\n", "S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n", "fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})\n" ] }, { "cell_type": "code", "execution_count": 60, "id": "0469164d-5770-443e-8cf4-d4f1ebd1b853", "metadata": {}, "outputs": [], "source": [ "entreprise_base=['bdc2324-data/1', 'bdc2324-data/2', 'bdc2324-data/3', 'bdc2324-data/4', 'bdc2324-data/5', 'bdc2324-data/6', 'bdc2324-data/7', 'bdc2324-data/8','bdc2324-data/9','bdc2324-data/10','bdc2324-data/11','bdc2324-data/12','bdc2324-data/13','bdc2324-data/14','bdc2324-data/101']" ] }, { "cell_type": "code", "execution_count": 177, "id": "55fbbad2-537e-4098-9a2d-d3850fab7332", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['bdc2324-data/11/11campaign_stats.csv',\n", " 'bdc2324-data/11/11campaigns.csv',\n", " 'bdc2324-data/11/11categories.csv',\n", " 'bdc2324-data/11/11countries.csv',\n", " 'bdc2324-data/11/11currencies.csv',\n", " 'bdc2324-data/11/11customer_target_mappings.csv',\n", " 'bdc2324-data/11/11customersplus.csv',\n", " 'bdc2324-data/11/11event_types.csv',\n", " 'bdc2324-data/11/11events.csv',\n", " 'bdc2324-data/11/11facilities.csv',\n", " 'bdc2324-data/11/11link_stats.csv',\n", " 'bdc2324-data/11/11pricing_formulas.csv',\n", " 'bdc2324-data/11/11product_packs.csv',\n", " 'bdc2324-data/11/11products.csv',\n", " 'bdc2324-data/11/11products_groups.csv',\n", " 'bdc2324-data/11/11purchases.csv',\n", " 'bdc2324-data/11/11representation_category_capacities.csv',\n", " 'bdc2324-data/11/11representations.csv',\n", " 'bdc2324-data/11/11seasons.csv',\n", " 'bdc2324-data/11/11structure_tag_mappings.csv',\n", " 'bdc2324-data/11/11suppliers.csv',\n", " 'bdc2324-data/11/11tags.csv',\n", " 'bdc2324-data/11/11target_types.csv',\n", " 'bdc2324-data/11/11targets.csv',\n", " 'bdc2324-data/11/11tickets.csv']" ] }, "execution_count": 177, "metadata": {}, "output_type": "execute_result" } ], "source": [ "BUCKET = \"bdc2324-data/11\"\n", "fs.ls(BUCKET)" ] }, { "cell_type": "code", "execution_count": 281, "id": "0b76f171-9ae1-4900-a23e-ec4dd57d461a", "metadata": {}, "outputs": [], "source": [ "pd.reset_option('display.max_rows')\n" ] }, { "cell_type": "code", "execution_count": 290, "id": "85357844-15f6-4098-9032-18310305c332", "metadata": {}, "outputs": [], "source": [ "entreprise = 'bdc2324-data/2/2' + 'events' + '.csv'\n", "with fs.open(entreprise, mode=\"rb\") as file_in:\n", " df_event= pd.read_csv(file_in, sep=\",\")" ] }, { "cell_type": "code", "execution_count": 291, "id": "e6117d69-9916-4a81-88aa-0340c6af13e1", "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", "
idcreated_atupdated_atseason_idfacility_idnameevent_type_idmanual_addedis_displayevent_type_key_idfacility_key_ididentifier
0152023-10-13 13:02:09.517079+02:002023-11-03 10:17:04.761407+01:0012„kreativ mit allen sinnen\"1FalseTrue1208f32b3fd76fcbfcb949502f4a78b052
1112023-10-13 13:02:09.515135+02:002023-11-03 10:17:04.761407+01:0011truffes zauber1FalseTrue110eafeafe7396fea2284da359febb069d
2122023-10-13 13:02:09.515619+02:002023-11-03 10:17:04.761407+01:0011choco-schule li – die führung für oberstufen &...1FalseTrue11235c4d3206c90b61f668e0e8051cdf33
3142023-10-13 13:02:09.516604+02:002023-11-03 10:17:05.663186+01:0011„formen & veredeln\"44FalseTrue12ed3d806039d13f9a7999033ef68ebe81
4102023-10-13 13:02:09.514640+02:002023-11-03 10:17:04.761407+01:0012truffes zauber1FalseTrue121d4c8761a169128962464ec99ba135f8
5182023-10-13 13:02:09.518522+02:002023-11-03 10:17:04.761407+01:0011choco-welt – die öffentliche führung1FalseTrue11e4e2915fd5ba2a5d14fb51d8df063bed
6172023-10-13 13:02:09.518037+02:002023-11-03 10:17:04.761407+01:0011schokoladentour – familien1FalseTrue115bf172dd5a3bf11f2b346eee5588c97a
7412023-10-13 13:07:51.131668+02:002023-11-03 10:17:04.761407+01:0012ausfahrtsticket1FalseTrue1204fe59a3f6db96a83f6c9734905acb7e
832023-10-13 13:02:09.510741+02:002023-11-03 10:17:04.761407+01:0011choco-welt – gruppenführung1FalseTrue118cf7a143170249b3286c2b76b9580f4b
912023-10-13 13:02:09.443323+02:002023-11-03 10:17:04.761407+01:0011schokoladentour – einzelticket1FalseTrue1134c2ab5c6c6750f78d6e475023db1dcb
1092023-10-13 13:02:09.514157+02:002023-11-03 10:17:04.761407+01:0011„formen & veredeln\"1FalseTrue1140d0622668130a47c06aa63742cc1c55
1172023-10-13 13:02:09.513141+02:002023-11-03 10:17:04.761407+01:0012choco-deluxe – die öffentliche führung1FalseTrue12af69a8da972bb9975f78748655a6bdad
124512023-10-13 15:49:57.226957+02:002023-11-03 10:17:04.761407+01:0011weihnachts-special1FalseTrue11e48ae983e2654f7dd1055f0ed25b4155
1362023-10-13 13:02:09.512552+02:002023-11-03 10:17:04.761407+01:0012gutschein schokoladentour1FalseTrue12662a3e0d8e88a64afb792d6aecc20395
1442023-10-13 13:02:09.511362+02:002023-11-03 10:17:04.761407+01:0011choco-deluxe – die öffentliche führung (de)1FalseTrue1198e165773ac25e1ef8ef84ccc8c45eb4
1552023-10-13 13:02:09.511954+02:002023-11-03 10:17:04.761407+01:0011„kreativ mit allen sinnen\"1FalseTrue118180dfe4fc995269bfac5336c13ec931
164532023-10-13 15:49:57.238792+02:002023-11-03 10:17:04.761407+01:0011privater chocolateria workshop1FalseTrue117cc2c03196cdc8adfc4102c87f15056e
177592023-10-31 03:20:00.509720+01:002023-11-03 10:17:04.761407+01:0011choco-schule i – die führung für primarschulkl...1FalseTrue11582a63d22864911766d8e019c277d1b3
18242023-10-13 13:02:09.521575+02:002023-11-03 10:17:04.761407+01:0012choco-welt – die gruppenführung1FalseTrue129fa748c7defa0d4f6976faa875d8c394
19212023-10-13 13:02:09.520019+02:002023-11-03 10:17:04.761407+01:0012chocolateria1FalseTrue12169b7c348566ccfd0e6ccdeeb6ac5f5a
20402023-10-13 13:07:51.131049+02:002023-11-03 10:17:04.761407+01:0012verlängerungspauschale führungen1FalseTrue12d22a3ae3c0712be5dfe9858b97a22034
2122023-10-13 13:02:09.509959+02:002023-11-03 10:17:04.761407+01:0011choco-deluxe – die öffentliche führung (en)1FalseTrue1184d0ef8ed664798bfa6a0d297f45bf2d
22222023-10-13 13:02:09.520492+02:002023-11-03 10:17:04.761407+01:0011weihnacht-special1FalseTrue11634f074cc18efa0e0ce88bdec14f248e
23202023-10-13 13:02:09.519518+02:002023-11-03 10:17:04.761407+01:0012gutschein gruppentarife1FalseTrue12f005c784b0a8db8244177e61e774a9b6
24132023-10-13 13:02:09.516105+02:002023-11-03 10:17:04.761407+01:0011choco-deluxe – die exklusive gruppenführung1FalseTrue11acb6ff9ac2bac1c55043bcb67a72a3a0
251032023-10-13 13:24:59.980586+02:002023-11-03 10:17:04.761407+01:0011choco-schule l – die führung für primarschulkl...1FalseTrue117b44ae19449523c65c1140c8aa4db924
26812023-10-13 13:19:30.509755+02:002023-11-03 10:17:04.761407+01:0011jumper-deluxe (de) – die weihnachtliche führung1FalseTrue11274024d1c45dc56a82612f8c71e727de
272212023-10-13 13:52:42.848999+02:002023-11-03 10:17:04.761407+01:0011jumper-deluxe (en) – the christmas guided tour1FalseTrue11576951a8841585f9bb3a6e4b72289f95
28232023-10-13 13:02:09.521089+02:002023-11-03 10:17:04.761407+01:0012choco-deluxe – die exklusive gruppenführung1FalseTrue12cc601355e3b07a57631806317f239000
291262023-10-13 13:30:21.301532+02:002023-11-03 10:17:04.761407+01:0011choco-schule railaway 10%1FalseTrue11ac0a1b09039cd2f078f2d09404f6c981
30822023-10-13 13:19:30.511942+02:002023-11-03 10:17:04.761407+01:0012gutschein saisonkurs1FalseTrue128f86ea0275633432963ebdceae17ce7c
31162023-10-13 13:02:09.517575+02:002023-11-03 10:17:04.761407+01:0012choco-welt – die öffentliche führung1FalseTrue12944fc565655297b2e67c4ae00f020074
32252023-10-13 13:02:09.522012+02:002023-11-03 10:17:04.761407+01:0012weihnacht-special1FalseTrue1268c8841c32b53e7ab121a070043ec1c3
33192023-10-13 13:02:09.519025+02:002023-11-03 10:17:04.761407+01:0011choco-schule – die führung für schulklassen1FalseTrue1163615b4e41ea135189db55a27c55e481
3482023-10-13 13:02:09.513651+02:002023-11-03 10:17:04.761407+01:0011schokoladentour – gruppenticket1FalseTrue11f227b307bebc96449506e7e344c80e80
351062023-10-13 13:24:59.981928+02:002023-11-03 10:17:04.761407+01:0011valentinstags-special1FalseTrue11c3ff8a48ad090434023c8b84b556babe
361322023-10-13 13:30:21.303904+02:002023-11-03 10:17:04.761407+01:0011muttertags-special1FalseTrue11cb7fd9470daa045117b40a6189e9267f
371082023-10-13 13:24:59.982672+02:002023-11-03 10:17:04.761407+01:0011osterkurs1FalseTrue11225f5c434a1a05e093ee996b02c774f3
\n", "
" ], "text/plain": [ " id created_at updated_at \\\n", "0 15 2023-10-13 13:02:09.517079+02:00 2023-11-03 10:17:04.761407+01:00 \n", "1 11 2023-10-13 13:02:09.515135+02:00 2023-11-03 10:17:04.761407+01:00 \n", "2 12 2023-10-13 13:02:09.515619+02:00 2023-11-03 10:17:04.761407+01:00 \n", "3 14 2023-10-13 13:02:09.516604+02:00 2023-11-03 10:17:05.663186+01:00 \n", "4 10 2023-10-13 13:02:09.514640+02:00 2023-11-03 10:17:04.761407+01:00 \n", "5 18 2023-10-13 13:02:09.518522+02:00 2023-11-03 10:17:04.761407+01:00 \n", "6 17 2023-10-13 13:02:09.518037+02:00 2023-11-03 10:17:04.761407+01:00 \n", "7 41 2023-10-13 13:07:51.131668+02:00 2023-11-03 10:17:04.761407+01:00 \n", "8 3 2023-10-13 13:02:09.510741+02:00 2023-11-03 10:17:04.761407+01:00 \n", "9 1 2023-10-13 13:02:09.443323+02:00 2023-11-03 10:17:04.761407+01:00 \n", "10 9 2023-10-13 13:02:09.514157+02:00 2023-11-03 10:17:04.761407+01:00 \n", "11 7 2023-10-13 13:02:09.513141+02:00 2023-11-03 10:17:04.761407+01:00 \n", "12 451 2023-10-13 15:49:57.226957+02:00 2023-11-03 10:17:04.761407+01:00 \n", "13 6 2023-10-13 13:02:09.512552+02:00 2023-11-03 10:17:04.761407+01:00 \n", "14 4 2023-10-13 13:02:09.511362+02:00 2023-11-03 10:17:04.761407+01:00 \n", "15 5 2023-10-13 13:02:09.511954+02:00 2023-11-03 10:17:04.761407+01:00 \n", "16 453 2023-10-13 15:49:57.238792+02:00 2023-11-03 10:17:04.761407+01:00 \n", "17 759 2023-10-31 03:20:00.509720+01:00 2023-11-03 10:17:04.761407+01:00 \n", "18 24 2023-10-13 13:02:09.521575+02:00 2023-11-03 10:17:04.761407+01:00 \n", "19 21 2023-10-13 13:02:09.520019+02:00 2023-11-03 10:17:04.761407+01:00 \n", "20 40 2023-10-13 13:07:51.131049+02:00 2023-11-03 10:17:04.761407+01:00 \n", "21 2 2023-10-13 13:02:09.509959+02:00 2023-11-03 10:17:04.761407+01:00 \n", "22 22 2023-10-13 13:02:09.520492+02:00 2023-11-03 10:17:04.761407+01:00 \n", "23 20 2023-10-13 13:02:09.519518+02:00 2023-11-03 10:17:04.761407+01:00 \n", "24 13 2023-10-13 13:02:09.516105+02:00 2023-11-03 10:17:04.761407+01:00 \n", "25 103 2023-10-13 13:24:59.980586+02:00 2023-11-03 10:17:04.761407+01:00 \n", "26 81 2023-10-13 13:19:30.509755+02:00 2023-11-03 10:17:04.761407+01:00 \n", "27 221 2023-10-13 13:52:42.848999+02:00 2023-11-03 10:17:04.761407+01:00 \n", "28 23 2023-10-13 13:02:09.521089+02:00 2023-11-03 10:17:04.761407+01:00 \n", "29 126 2023-10-13 13:30:21.301532+02:00 2023-11-03 10:17:04.761407+01:00 \n", "30 82 2023-10-13 13:19:30.511942+02:00 2023-11-03 10:17:04.761407+01:00 \n", "31 16 2023-10-13 13:02:09.517575+02:00 2023-11-03 10:17:04.761407+01:00 \n", "32 25 2023-10-13 13:02:09.522012+02:00 2023-11-03 10:17:04.761407+01:00 \n", "33 19 2023-10-13 13:02:09.519025+02:00 2023-11-03 10:17:04.761407+01:00 \n", "34 8 2023-10-13 13:02:09.513651+02:00 2023-11-03 10:17:04.761407+01:00 \n", "35 106 2023-10-13 13:24:59.981928+02:00 2023-11-03 10:17:04.761407+01:00 \n", "36 132 2023-10-13 13:30:21.303904+02:00 2023-11-03 10:17:04.761407+01:00 \n", "37 108 2023-10-13 13:24:59.982672+02:00 2023-11-03 10:17:04.761407+01:00 \n", "\n", " season_id facility_id name \\\n", "0 1 2 „kreativ mit allen sinnen\" \n", "1 1 1 truffes zauber \n", "2 1 1 choco-schule li – die führung für oberstufen &... \n", "3 1 1 „formen & veredeln\" \n", "4 1 2 truffes zauber \n", "5 1 1 choco-welt – die öffentliche führung \n", "6 1 1 schokoladentour – familien \n", "7 1 2 ausfahrtsticket \n", "8 1 1 choco-welt – gruppenführung \n", "9 1 1 schokoladentour – einzelticket \n", "10 1 1 „formen & veredeln\" \n", "11 1 2 choco-deluxe – die öffentliche führung \n", "12 1 1 weihnachts-special \n", "13 1 2 gutschein schokoladentour \n", "14 1 1 choco-deluxe – die öffentliche führung (de) \n", "15 1 1 „kreativ mit allen sinnen\" \n", "16 1 1 privater chocolateria workshop \n", "17 1 1 choco-schule i – die führung für primarschulkl... \n", "18 1 2 choco-welt – die gruppenführung \n", "19 1 2 chocolateria \n", "20 1 2 verlängerungspauschale führungen \n", "21 1 1 choco-deluxe – die öffentliche führung (en) \n", "22 1 1 weihnacht-special \n", "23 1 2 gutschein gruppentarife \n", "24 1 1 choco-deluxe – die exklusive gruppenführung \n", "25 1 1 choco-schule l – die führung für primarschulkl... \n", "26 1 1 jumper-deluxe (de) – die weihnachtliche führung \n", "27 1 1 jumper-deluxe (en) – the christmas guided tour \n", "28 1 2 choco-deluxe – die exklusive gruppenführung \n", "29 1 1 choco-schule railaway 10% \n", "30 1 2 gutschein saisonkurs \n", "31 1 2 choco-welt – die öffentliche führung \n", "32 1 2 weihnacht-special \n", "33 1 1 choco-schule – die führung für schulklassen \n", "34 1 1 schokoladentour – gruppenticket \n", "35 1 1 valentinstags-special \n", "36 1 1 muttertags-special \n", "37 1 1 osterkurs \n", "\n", " event_type_id manual_added is_display event_type_key_id \\\n", "0 1 False True 1 \n", "1 1 False True 1 \n", "2 1 False True 1 \n", "3 44 False True 1 \n", "4 1 False True 1 \n", "5 1 False True 1 \n", "6 1 False True 1 \n", "7 1 False True 1 \n", "8 1 False True 1 \n", "9 1 False True 1 \n", "10 1 False True 1 \n", "11 1 False True 1 \n", "12 1 False True 1 \n", "13 1 False True 1 \n", "14 1 False True 1 \n", "15 1 False True 1 \n", "16 1 False True 1 \n", "17 1 False True 1 \n", "18 1 False True 1 \n", "19 1 False True 1 \n", "20 1 False True 1 \n", "21 1 False True 1 \n", "22 1 False True 1 \n", "23 1 False True 1 \n", "24 1 False True 1 \n", "25 1 False True 1 \n", "26 1 False True 1 \n", "27 1 False True 1 \n", "28 1 False True 1 \n", "29 1 False True 1 \n", "30 1 False True 1 \n", "31 1 False True 1 \n", "32 1 False True 1 \n", "33 1 False True 1 \n", "34 1 False True 1 \n", "35 1 False True 1 \n", "36 1 False True 1 \n", "37 1 False True 1 \n", "\n", " facility_key_id identifier \n", "0 2 08f32b3fd76fcbfcb949502f4a78b052 \n", "1 1 0eafeafe7396fea2284da359febb069d \n", "2 1 235c4d3206c90b61f668e0e8051cdf33 \n", "3 2 ed3d806039d13f9a7999033ef68ebe81 \n", "4 2 1d4c8761a169128962464ec99ba135f8 \n", "5 1 e4e2915fd5ba2a5d14fb51d8df063bed \n", "6 1 5bf172dd5a3bf11f2b346eee5588c97a \n", "7 2 04fe59a3f6db96a83f6c9734905acb7e \n", "8 1 8cf7a143170249b3286c2b76b9580f4b \n", "9 1 34c2ab5c6c6750f78d6e475023db1dcb \n", "10 1 40d0622668130a47c06aa63742cc1c55 \n", "11 2 af69a8da972bb9975f78748655a6bdad \n", "12 1 e48ae983e2654f7dd1055f0ed25b4155 \n", "13 2 662a3e0d8e88a64afb792d6aecc20395 \n", "14 1 98e165773ac25e1ef8ef84ccc8c45eb4 \n", "15 1 8180dfe4fc995269bfac5336c13ec931 \n", "16 1 7cc2c03196cdc8adfc4102c87f15056e \n", "17 1 582a63d22864911766d8e019c277d1b3 \n", "18 2 9fa748c7defa0d4f6976faa875d8c394 \n", "19 2 169b7c348566ccfd0e6ccdeeb6ac5f5a \n", "20 2 d22a3ae3c0712be5dfe9858b97a22034 \n", "21 1 84d0ef8ed664798bfa6a0d297f45bf2d \n", "22 1 634f074cc18efa0e0ce88bdec14f248e \n", "23 2 f005c784b0a8db8244177e61e774a9b6 \n", "24 1 acb6ff9ac2bac1c55043bcb67a72a3a0 \n", "25 1 7b44ae19449523c65c1140c8aa4db924 \n", "26 1 274024d1c45dc56a82612f8c71e727de \n", "27 1 576951a8841585f9bb3a6e4b72289f95 \n", "28 2 cc601355e3b07a57631806317f239000 \n", "29 1 ac0a1b09039cd2f078f2d09404f6c981 \n", "30 2 8f86ea0275633432963ebdceae17ce7c \n", "31 2 944fc565655297b2e67c4ae00f020074 \n", "32 2 68c8841c32b53e7ab121a070043ec1c3 \n", "33 1 63615b4e41ea135189db55a27c55e481 \n", "34 1 f227b307bebc96449506e7e344c80e80 \n", "35 1 c3ff8a48ad090434023c8b84b556babe \n", "36 1 cb7fd9470daa045117b40a6189e9267f \n", "37 1 225f5c434a1a05e093ee996b02c774f3 " ] }, "execution_count": 291, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_event" ] }, { "cell_type": "code", "execution_count": 277, "id": "27ce6b38-505e-461d-985f-aab803be190e", "metadata": {}, "outputs": [], "source": [ "entreprise_101 = 'bdc2324-data/101/101' + 'event_types' + '.csv'\n", "with fs.open(entreprise_101, mode=\"rb\") as file_in:\n", " df_event_types_101= pd.read_csv(file_in, sep=\",\")" ] }, { "cell_type": "code", "execution_count": 278, "id": "f3fcdd71-0f5f-42a7-83e5-c0b9613b9e91", "metadata": {}, "outputs": [], "source": [ "dfs['df_event_types_101']=df_event_types_101" ] }, { "cell_type": "code", "execution_count": 72, "id": "eccdaffd-9971-45a9-be39-6d3a95a91b2f", "metadata": {}, "outputs": [ { "ename": "IndentationError", "evalue": "expected an indented block after 'for' statement on line 1 (2015796903.py, line 2)", "output_type": "error", "traceback": [ "\u001b[0;36m Cell \u001b[0;32mIn[72], line 2\u001b[0;36m\u001b[0m\n\u001b[0;31m entreprise1 = 'bdc2324-data/i/i' + 'event_types' + '.csv'\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mIndentationError\u001b[0m\u001b[0;31m:\u001b[0m expected an indented block after 'for' statement on line 1\n" ] } ], "source": [ "for i in range(14):\n", "entreprise_i = 'bdc2324-data/i/i' + 'event_types' + '.csv'\n", "with fs.open(entreprise1, mode=\"rb\") as file_in:\n", " df_event_types_'i'= pd.read_csv(file_in, sep=\",\")" ] }, { "cell_type": "code", "execution_count": 191, "id": "18820c35-7da3-4520-b645-1a467104ddc8", "metadata": {}, "outputs": [], "source": [ "del dfs" ] }, { "cell_type": "code", "execution_count": 293, "id": "9b4a932f-cbb7-4057-bf96-b5d2fd7036a4", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "# Création d'un dictionnaire pour stocker les DataFrames events de chaque compagnie\n", "dfs = {}\n", "\n", "for i in range(1, 15): # Assurez-vous que i varie de 1 à 4\n", " entreprise_i = f'bdc2324-data/{i}/{i}events.csv' # Utilisation de f-strings pour formater la chaîne\n", " with fs.open(entreprise_i, mode=\"rb\") as file_in: # Utilisation de fsspec.open pour ouvrir le fichier\n", " df_events_i = pd.read_csv(file_in, sep=\",\") # Lecture du fichier CSV et assignation à un DataFrame\n", " dfs[f'df_events_{i}'] = df_events_i # Stockage du DataFrame dans le dictionnaire avec une clé appropriée\n" ] }, { "cell_type": "code", "execution_count": 246, "id": "14ed2fa0-0ec6-4a49-a4d9-183a77326f5d", "metadata": {}, "outputs": [], "source": [ "pd.set_option('display.max_rows', 1000)#afficher les ligne maximales" ] }, { "cell_type": "code", "execution_count": 295, "id": "0ac766c6-1960-4422-bf2c-4ba924394998", "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", "
idcreated_atupdated_atseason_idfacility_idnameevent_type_idmanual_addedis_displayevent_type_key_idfacility_key_ididentifier
0143702023-04-27 15:40:36.110558+02:002023-10-20 12:55:20.877464+02:0014351044abonnement - saison 2023 - 20241123FalseTrue11231044ee604d3e64a27c663a3a1d9de76596e1
1176342023-07-06 18:02:47.697110+02:002023-10-20 12:55:20.854693+02:001435832sf paris / racing 92824FalseTrue82483222d7950f7cbce0f2c8f3c4d272ed6926
2176352023-07-06 18:02:47.697577+02:002023-10-20 12:55:20.854693+02:001435832sf paris / stade toulousain824FalseTrue8248324ae51c31e231eaca1bc2db3afafe417b
3176322023-07-06 18:02:47.694821+02:002023-10-20 12:55:20.854693+02:001435832sf paris / montpellier hr824FalseTrue824832389c8fb7577d0ab030d53e521fda600c
4176332023-07-06 18:02:47.696477+02:002023-10-20 12:55:20.854693+02:001435832sf paris / castres olympique824FalseTrue82483205c9dc3878a4c5c3bfe87bc7667c52d8
.......................................
21488102023-04-04 18:21:47.463967+02:002023-10-20 12:55:20.854693+02:00672832sf paris / racing 92 (ercc)824FalseTrue824832019a7e2faca12acff64ef458cf0c5975
21588042023-04-04 18:21:47.457687+02:002023-10-20 12:55:20.854693+02:00672832sf paris / stade toulousain824FalseTrue824832ef8b8362079d64a10811ac758ca22a63
21688002023-04-04 18:21:47.453369+02:002023-10-20 12:55:20.854693+02:00672832sf paris / stade rochelais824FalseTrue824832451e36ee5ad882a0c25447e2e129fedd
21788062023-04-04 18:21:47.459782+02:002023-10-20 12:55:20.854693+02:00672832sf paris / section paloise824FalseTrue8248322fbea7b0e293de5bf9e9f11d7a4780f8
21888072023-04-04 18:21:47.460842+02:002023-10-20 12:55:20.854693+02:00672832sf paris / ca brive-correze824FalseTrue82483264af51a1bcd04ca63b4d824379283aeb
\n", "

219 rows × 12 columns

\n", "
" ], "text/plain": [ " id created_at \\\n", "0 14370 2023-04-27 15:40:36.110558+02:00 \n", "1 17634 2023-07-06 18:02:47.697110+02:00 \n", "2 17635 2023-07-06 18:02:47.697577+02:00 \n", "3 17632 2023-07-06 18:02:47.694821+02:00 \n", "4 17633 2023-07-06 18:02:47.696477+02:00 \n", ".. ... ... \n", "214 8810 2023-04-04 18:21:47.463967+02:00 \n", "215 8804 2023-04-04 18:21:47.457687+02:00 \n", "216 8800 2023-04-04 18:21:47.453369+02:00 \n", "217 8806 2023-04-04 18:21:47.459782+02:00 \n", "218 8807 2023-04-04 18:21:47.460842+02:00 \n", "\n", " updated_at season_id facility_id \\\n", "0 2023-10-20 12:55:20.877464+02:00 1435 1044 \n", "1 2023-10-20 12:55:20.854693+02:00 1435 832 \n", "2 2023-10-20 12:55:20.854693+02:00 1435 832 \n", "3 2023-10-20 12:55:20.854693+02:00 1435 832 \n", "4 2023-10-20 12:55:20.854693+02:00 1435 832 \n", ".. ... ... ... \n", "214 2023-10-20 12:55:20.854693+02:00 672 832 \n", "215 2023-10-20 12:55:20.854693+02:00 672 832 \n", "216 2023-10-20 12:55:20.854693+02:00 672 832 \n", "217 2023-10-20 12:55:20.854693+02:00 672 832 \n", "218 2023-10-20 12:55:20.854693+02:00 672 832 \n", "\n", " name event_type_id manual_added is_display \\\n", "0 abonnement - saison 2023 - 2024 1123 False True \n", "1 sf paris / racing 92 824 False True \n", "2 sf paris / stade toulousain 824 False True \n", "3 sf paris / montpellier hr 824 False True \n", "4 sf paris / castres olympique 824 False True \n", ".. ... ... ... ... \n", "214 sf paris / racing 92 (ercc) 824 False True \n", "215 sf paris / stade toulousain 824 False True \n", "216 sf paris / stade rochelais 824 False True \n", "217 sf paris / section paloise 824 False True \n", "218 sf paris / ca brive-correze 824 False True \n", "\n", " event_type_key_id facility_key_id identifier \n", "0 1123 1044 ee604d3e64a27c663a3a1d9de76596e1 \n", "1 824 832 22d7950f7cbce0f2c8f3c4d272ed6926 \n", "2 824 832 4ae51c31e231eaca1bc2db3afafe417b \n", "3 824 832 389c8fb7577d0ab030d53e521fda600c \n", "4 824 832 05c9dc3878a4c5c3bfe87bc7667c52d8 \n", ".. ... ... ... \n", "214 824 832 019a7e2faca12acff64ef458cf0c5975 \n", "215 824 832 ef8b8362079d64a10811ac758ca22a63 \n", "216 824 832 451e36ee5ad882a0c25447e2e129fedd \n", "217 824 832 2fbea7b0e293de5bf9e9f11d7a4780f8 \n", "218 824 832 64af51a1bcd04ca63b4d824379283aeb \n", "\n", "[219 rows x 12 columns]" ] }, "execution_count": 295, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfs['df_events_5']" ] }, { "cell_type": "code", "execution_count": 321, "id": "e3e46c87-a516-474f-b123-455e345fbb36", "metadata": {}, "outputs": [], "source": [ "compagnie_event={\n", " 'compagnie1':['museum','bdc2324-data/1'],\n", " 'compagnie2':['museum','bdc2324-data/2'],\n", " 'compagnie3':['museum','bdc2324-data/3'],\n", " 'compagnie4':['museum','bdc2324-data/4'],\n", " 'compagnie5':['sport','bdc2324-data/5'],\n", " 'compagnie6':['sport','bdc2324-data/6'],\n", " 'compagnie7':['sport','bdc2324-data/7'],\n", " 'compagnie8':['sport','bdc2324-data/8'],\n", " 'compagnie9':['sport','bdc2324-data/9'],\n", " 'compagnie10':['spectable/theater','bdc2324-data/10'],\n", " 'compagnie11':['spectable/theater','bdc2324-data/11'],\n", " 'compagnie12':['spectable/theater','bdc2324-data/12'],\n", " 'compagnie13':['spectable/theater','bdc2324-data/13'],\n", " 'compagnie14':['spectable/theater','bdc2324-data/14'],\n", " 'compagnie101':['museum','bdc2324-data/101']\n", "}\n" ] }, { "cell_type": "code", "execution_count": 322, "id": "4c200191-8bfa-44f4-a592-c1393a0e1b0e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "15" ] }, "execution_count": 322, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(compagnie_event)" ] }, { "cell_type": "code", "execution_count": 323, "id": "5a8861b2-b466-4429-8cf8-b5a8b48ee32e", "metadata": {}, "outputs": [], "source": [ "compagnie_act = pd.DataFrame(compagnie_event)" ] }, { "cell_type": "code", "execution_count": 324, "id": "b963844d-8516-41e0-8a7e-f797320338cf", "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", "
compagnie1compagnie2compagnie3compagnie4compagnie5compagnie6compagnie7compagnie8compagnie9compagnie10compagnie11compagnie12compagnie13compagnie14compagnie101
0museummuseummuseummuseumsportsportsportsportsportspectable/theaterspectable/theaterspectable/theaterspectable/theaterspectable/theatermuseum
1bdc2324-data/1bdc2324-data/2bdc2324-data/3bdc2324-data/4bdc2324-data/5bdc2324-data/6bdc2324-data/7bdc2324-data/8bdc2324-data/9bdc2324-data/10bdc2324-data/11bdc2324-data/12bdc2324-data/13bdc2324-data/14bdc2324-data/101
\n", "
" ], "text/plain": [ " compagnie1 compagnie2 compagnie3 compagnie4 \\\n", "0 museum museum museum museum \n", "1 bdc2324-data/1 bdc2324-data/2 bdc2324-data/3 bdc2324-data/4 \n", "\n", " compagnie5 compagnie6 compagnie7 compagnie8 \\\n", "0 sport sport sport sport \n", "1 bdc2324-data/5 bdc2324-data/6 bdc2324-data/7 bdc2324-data/8 \n", "\n", " compagnie9 compagnie10 compagnie11 compagnie12 \\\n", "0 sport spectable/theater spectable/theater spectable/theater \n", "1 bdc2324-data/9 bdc2324-data/10 bdc2324-data/11 bdc2324-data/12 \n", "\n", " compagnie13 compagnie14 compagnie101 \n", "0 spectable/theater spectable/theater museum \n", "1 bdc2324-data/13 bdc2324-data/14 bdc2324-data/101 " ] }, "execution_count": 324, "metadata": {}, "output_type": "execute_result" } ], "source": [ "compagnie_act" ] }, { "cell_type": "code", "execution_count": 325, "id": "8d7ce22e-d4e8-4cf1-9c04-3bddf50d4381", "metadata": {}, "outputs": [], "source": [ "nv_index=['type_event','base_compagnie']\n", "compagnie_act.index=nv_index" ] }, { "cell_type": "code", "execution_count": 326, "id": "3b4943ad-75ba-45d8-9442-010ebc18a15d", "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", "
compagnie1compagnie2compagnie3compagnie4compagnie5compagnie6compagnie7compagnie8compagnie9compagnie10compagnie11compagnie12compagnie13compagnie14compagnie101
type_eventmuseummuseummuseummuseumsportsportsportsportsportspectable/theaterspectable/theaterspectable/theaterspectable/theaterspectable/theatermuseum
base_compagniebdc2324-data/1bdc2324-data/2bdc2324-data/3bdc2324-data/4bdc2324-data/5bdc2324-data/6bdc2324-data/7bdc2324-data/8bdc2324-data/9bdc2324-data/10bdc2324-data/11bdc2324-data/12bdc2324-data/13bdc2324-data/14bdc2324-data/101
\n", "
" ], "text/plain": [ " compagnie1 compagnie2 compagnie3 \\\n", "type_event museum museum museum \n", "base_compagnie bdc2324-data/1 bdc2324-data/2 bdc2324-data/3 \n", "\n", " compagnie4 compagnie5 compagnie6 \\\n", "type_event museum sport sport \n", "base_compagnie bdc2324-data/4 bdc2324-data/5 bdc2324-data/6 \n", "\n", " compagnie7 compagnie8 compagnie9 \\\n", "type_event sport sport sport \n", "base_compagnie bdc2324-data/7 bdc2324-data/8 bdc2324-data/9 \n", "\n", " compagnie10 compagnie11 compagnie12 \\\n", "type_event spectable/theater spectable/theater spectable/theater \n", "base_compagnie bdc2324-data/10 bdc2324-data/11 bdc2324-data/12 \n", "\n", " compagnie13 compagnie14 compagnie101 \n", "type_event spectable/theater spectable/theater museum \n", "base_compagnie bdc2324-data/13 bdc2324-data/14 bdc2324-data/101 " ] }, "execution_count": 326, "metadata": {}, "output_type": "execute_result" } ], "source": [ "compagnie_act" ] }, { "cell_type": "code", "execution_count": 327, "id": "ede8210c-5d79-4159-8132-85afd0950f85", "metadata": {}, "outputs": [], "source": [ "compagnie_act.to_csv(r'C:\\Users\\fanta\\OneDrive\\Bureau\\BDC\\compagnie_type_event.csv', index=False)" ] }, { "cell_type": "code", "execution_count": null, "id": "771079f3-d346-4a63-a987-354b811f5b41", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "eda1201a-2cc1-45bc-bf67-70f426183757", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.6" } }, "nbformat": 4, "nbformat_minor": 5 }