BDC-team-1/Identification_entreprise.ipynb
2024-02-20 01:27:30 +00:00

1611 lines
85 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 335,
"id": "482d19ab-5dd1-4e75-b2c1-df734ce5ee66",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 336,
"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": 337,
"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": 343,
"id": "55fbbad2-537e-4098-9a2d-d3850fab7332",
"metadata": {},
"outputs": [
{
"ename": "PermissionError",
"evalue": "The Access Key Id you provided does not exist in our records.",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mClientError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:394\u001b[0m, in \u001b[0;36mS3FileSystem._lsdir\u001b[0;34m(self, path, refresh, max_items)\u001b[0m\n\u001b[1;32m 393\u001b[0m dircache \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m--> 394\u001b[0m \u001b[43m\u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mi\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mit\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 395\u001b[0m \u001b[43m \u001b[49m\u001b[43mdircache\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mextend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mi\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mCommonPrefixes\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/paginate.py:269\u001b[0m, in \u001b[0;36mPageIterator.__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 268\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m--> 269\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_request\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcurrent_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 270\u001b[0m parsed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_extract_parsed_response(response)\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/paginate.py:357\u001b[0m, in \u001b[0;36mPageIterator._make_request\u001b[0;34m(self, current_kwargs)\u001b[0m\n\u001b[1;32m 356\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_make_request\u001b[39m(\u001b[38;5;28mself\u001b[39m, current_kwargs):\n\u001b[0;32m--> 357\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_method\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mcurrent_kwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/client.py:553\u001b[0m, in \u001b[0;36mClientCreator._create_api_method.<locals>._api_call\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 552\u001b[0m \u001b[38;5;66;03m# The \"self\" in this scope is referring to the BaseClient.\u001b[39;00m\n\u001b[0;32m--> 553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_api_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43moperation_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/client.py:1009\u001b[0m, in \u001b[0;36mBaseClient._make_api_call\u001b[0;34m(self, operation_name, api_params)\u001b[0m\n\u001b[1;32m 1008\u001b[0m error_class \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexceptions\u001b[38;5;241m.\u001b[39mfrom_code(error_code)\n\u001b[0;32m-> 1009\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m error_class(parsed_response, operation_name)\n\u001b[1;32m 1010\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"\u001b[0;31mClientError\u001b[0m: An error occurred (InvalidAccessKeyId) when calling the ListObjectsV2 operation: The Access Key Id you provided does not exist in our records.",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mPermissionError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[343], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m BUCKET \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbdc2324-data/2\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mls\u001b[49m\u001b[43m(\u001b[49m\u001b[43mBUCKET\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:619\u001b[0m, in \u001b[0;36mS3FileSystem.ls\u001b[0;34m(self, path, detail, refresh, **kwargs)\u001b[0m\n\u001b[1;32m 604\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\" List single \"directory\" with or without details\u001b[39;00m\n\u001b[1;32m 605\u001b[0m \n\u001b[1;32m 606\u001b[0m \u001b[38;5;124;03mParameters\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 616\u001b[0m \u001b[38;5;124;03m additional arguments passed on\u001b[39;00m\n\u001b[1;32m 617\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 618\u001b[0m path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_strip_protocol(path)\u001b[38;5;241m.\u001b[39mrstrip(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m--> 619\u001b[0m files \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_ls\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrefresh\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrefresh\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 620\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m files:\n\u001b[1;32m 621\u001b[0m files \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_ls(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_parent(path), refresh\u001b[38;5;241m=\u001b[39mrefresh)\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:487\u001b[0m, in \u001b[0;36mS3FileSystem._ls\u001b[0;34m(self, path, refresh)\u001b[0m\n\u001b[1;32m 485\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lsbuckets(refresh)\n\u001b[1;32m 486\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 487\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_lsdir\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrefresh\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:409\u001b[0m, in \u001b[0;36mS3FileSystem._lsdir\u001b[0;34m(self, path, refresh, max_items)\u001b[0m\n\u001b[1;32m 407\u001b[0m f[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m f[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mKey\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m 408\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ClientError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m--> 409\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m translate_boto_error(e)\n\u001b[1;32m 411\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdircache[path] \u001b[38;5;241m=\u001b[39m files\n\u001b[1;32m 412\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m files\n",
"\u001b[0;31mPermissionError\u001b[0m: The Access Key Id you provided does not exist in our records."
]
}
],
"source": [
"BUCKET = \"bdc2324-data/2\"\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": 341,
"id": "85357844-15f6-4098-9032-18310305c332",
"metadata": {},
"outputs": [
{
"ename": "PermissionError",
"evalue": "Forbidden",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mClientError\u001b[0m Traceback (most recent call last)",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:529\u001b[0m, in \u001b[0;36mS3FileSystem.info\u001b[0;34m(self, path, version_id, refresh)\u001b[0m\n\u001b[1;32m 528\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 529\u001b[0m out \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_s3\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43ms3\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhead_object\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mBucket\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mbucket\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 530\u001b[0m \u001b[43m \u001b[49m\u001b[43mKey\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mversion_id_kw\u001b[49m\u001b[43m(\u001b[49m\u001b[43mversion_id\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreq_kw\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 531\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m 532\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mETag\u001b[39m\u001b[38;5;124m'\u001b[39m: out[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mETag\u001b[39m\u001b[38;5;124m'\u001b[39m],\n\u001b[1;32m 533\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mKey\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;241m.\u001b[39mjoin([bucket, key]),\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 540\u001b[0m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mVersionId\u001b[39m\u001b[38;5;124m'\u001b[39m: out\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mVersionId\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 541\u001b[0m }\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:200\u001b[0m, in \u001b[0;36mS3FileSystem._call_s3\u001b[0;34m(self, method, *akwarglist, **kwargs)\u001b[0m\n\u001b[1;32m 198\u001b[0m additional_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_s3_method_kwargs(method, \u001b[38;5;241m*\u001b[39makwarglist,\n\u001b[1;32m 199\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 200\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmethod\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43madditional_kwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/client.py:553\u001b[0m, in \u001b[0;36mClientCreator._create_api_method.<locals>._api_call\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 552\u001b[0m \u001b[38;5;66;03m# The \"self\" in this scope is referring to the BaseClient.\u001b[39;00m\n\u001b[0;32m--> 553\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_api_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43moperation_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/botocore/client.py:1009\u001b[0m, in \u001b[0;36mBaseClient._make_api_call\u001b[0;34m(self, operation_name, api_params)\u001b[0m\n\u001b[1;32m 1008\u001b[0m error_class \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexceptions\u001b[38;5;241m.\u001b[39mfrom_code(error_code)\n\u001b[0;32m-> 1009\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m error_class(parsed_response, operation_name)\n\u001b[1;32m 1010\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"\u001b[0;31mClientError\u001b[0m: An error occurred (403) when calling the HeadObject operation: Forbidden",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mPermissionError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[341], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m entreprise \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbdc2324-data/2/2\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mevents\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.csv\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m----> 2\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mentreprise\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mrb\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m file_in:\n\u001b[1;32m 3\u001b[0m df_event\u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(file_in, sep\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m,\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/fsspec/spec.py:1295\u001b[0m, in \u001b[0;36mAbstractFileSystem.open\u001b[0;34m(self, path, mode, block_size, cache_options, compression, **kwargs)\u001b[0m\n\u001b[1;32m 1293\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1294\u001b[0m ac \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mautocommit\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_intrans)\n\u001b[0;32m-> 1295\u001b[0m f \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_open\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1296\u001b[0m \u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1297\u001b[0m \u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1298\u001b[0m \u001b[43m \u001b[49m\u001b[43mblock_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mblock_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1299\u001b[0m \u001b[43m \u001b[49m\u001b[43mautocommit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mac\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1300\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1301\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1302\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1303\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m compression \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 1304\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mfsspec\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcompression\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m compr\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:375\u001b[0m, in \u001b[0;36mS3FileSystem._open\u001b[0;34m(self, path, mode, block_size, acl, version_id, fill_cache, cache_type, autocommit, requester_pays, **kwargs)\u001b[0m\n\u001b[1;32m 372\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m cache_type \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 373\u001b[0m cache_type \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdefault_cache_type\n\u001b[0;32m--> 375\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mS3File\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mblock_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mblock_size\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43macl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43macl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 376\u001b[0m \u001b[43m \u001b[49m\u001b[43mversion_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mversion_id\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfill_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfill_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 377\u001b[0m \u001b[43m \u001b[49m\u001b[43ms3_additional_kwargs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkw\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcache_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 378\u001b[0m \u001b[43m \u001b[49m\u001b[43mautocommit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mautocommit\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrequester_pays\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrequester_pays\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:1096\u001b[0m, in \u001b[0;36mS3File.__init__\u001b[0;34m(self, s3, path, mode, block_size, acl, version_id, fill_cache, s3_additional_kwargs, autocommit, cache_type, requester_pays)\u001b[0m\n\u001b[1;32m 1094\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39ms3_additional_kwargs \u001b[38;5;241m=\u001b[39m s3_additional_kwargs \u001b[38;5;129;01mor\u001b[39;00m {}\n\u001b[1;32m 1095\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreq_kw \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mRequestPayer\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrequester\u001b[39m\u001b[38;5;124m'\u001b[39m} \u001b[38;5;28;01mif\u001b[39;00m requester_pays \u001b[38;5;28;01melse\u001b[39;00m {}\n\u001b[0;32m-> 1096\u001b[0m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43ms3\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mblock_size\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mautocommit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mautocommit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1097\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_type\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1098\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39ms3 \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfs \u001b[38;5;66;03m# compatibility\u001b[39;00m\n\u001b[1;32m 1099\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mwritable():\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/fsspec/spec.py:1651\u001b[0m, in \u001b[0;36mAbstractBufferedFile.__init__\u001b[0;34m(self, fs, path, mode, block_size, autocommit, cache_type, cache_options, size, **kwargs)\u001b[0m\n\u001b[1;32m 1649\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msize \u001b[38;5;241m=\u001b[39m size\n\u001b[1;32m 1650\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1651\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msize \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdetails\u001b[49m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msize\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 1652\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache \u001b[38;5;241m=\u001b[39m caches[cache_type](\n\u001b[1;32m 1653\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mblocksize, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_fetch_range, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msize, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mcache_options\n\u001b[1;32m 1654\u001b[0m )\n\u001b[1;32m 1655\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/fsspec/spec.py:1664\u001b[0m, in \u001b[0;36mAbstractBufferedFile.details\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1661\u001b[0m \u001b[38;5;129m@property\u001b[39m\n\u001b[1;32m 1662\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdetails\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 1663\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_details \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1664\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_details \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minfo\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1665\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_details\n",
"File \u001b[0;32m/opt/mamba/lib/python3.11/site-packages/s3fs/core.py:548\u001b[0m, in \u001b[0;36mS3FileSystem.info\u001b[0;34m(self, path, version_id, refresh)\u001b[0m\n\u001b[1;32m 546\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m(S3FileSystem, \u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39minfo(path)\n\u001b[1;32m 547\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 548\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ee\n\u001b[1;32m 549\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ParamValidationError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 550\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mFailed to head path \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m'\u001b[39m \u001b[38;5;241m%\u001b[39m (path, e))\n",
"\u001b[0;31mPermissionError\u001b[0m: Forbidden"
]
}
],
"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": 342,
"id": "e6117d69-9916-4a81-88aa-0340c6af13e1",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>season_id</th>\n",
" <th>facility_id</th>\n",
" <th>name</th>\n",
" <th>event_type_id</th>\n",
" <th>manual_added</th>\n",
" <th>is_display</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>15</td>\n",
" <td>2023-10-13 13:02:09.517079+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>„kreativ mit allen sinnen\"</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>08f32b3fd76fcbfcb949502f4a78b052</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>11</td>\n",
" <td>2023-10-13 13:02:09.515135+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>truffes zauber</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0eafeafe7396fea2284da359febb069d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>12</td>\n",
" <td>2023-10-13 13:02:09.515619+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-schule li die führung für oberstufen &amp;...</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>235c4d3206c90b61f668e0e8051cdf33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>14</td>\n",
" <td>2023-10-13 13:02:09.516604+02:00</td>\n",
" <td>2023-11-03 10:17:05.663186+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>„formen &amp; veredeln\"</td>\n",
" <td>44</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>ed3d806039d13f9a7999033ef68ebe81</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>10</td>\n",
" <td>2023-10-13 13:02:09.514640+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>truffes zauber</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1d4c8761a169128962464ec99ba135f8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>18</td>\n",
" <td>2023-10-13 13:02:09.518522+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-welt die öffentliche führung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>e4e2915fd5ba2a5d14fb51d8df063bed</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>17</td>\n",
" <td>2023-10-13 13:02:09.518037+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>schokoladentour familien</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>5bf172dd5a3bf11f2b346eee5588c97a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>41</td>\n",
" <td>2023-10-13 13:07:51.131668+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>ausfahrtsticket</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>04fe59a3f6db96a83f6c9734905acb7e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>3</td>\n",
" <td>2023-10-13 13:02:09.510741+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-welt gruppenführung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>8cf7a143170249b3286c2b76b9580f4b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>1</td>\n",
" <td>2023-10-13 13:02:09.443323+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>schokoladentour einzelticket</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>34c2ab5c6c6750f78d6e475023db1dcb</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>9</td>\n",
" <td>2023-10-13 13:02:09.514157+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>„formen &amp; veredeln\"</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>40d0622668130a47c06aa63742cc1c55</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>7</td>\n",
" <td>2023-10-13 13:02:09.513141+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>choco-deluxe die öffentliche führung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>af69a8da972bb9975f78748655a6bdad</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>451</td>\n",
" <td>2023-10-13 15:49:57.226957+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>weihnachts-special</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>e48ae983e2654f7dd1055f0ed25b4155</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>6</td>\n",
" <td>2023-10-13 13:02:09.512552+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>gutschein schokoladentour</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>662a3e0d8e88a64afb792d6aecc20395</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>4</td>\n",
" <td>2023-10-13 13:02:09.511362+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-deluxe die öffentliche führung (de)</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>98e165773ac25e1ef8ef84ccc8c45eb4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>5</td>\n",
" <td>2023-10-13 13:02:09.511954+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>„kreativ mit allen sinnen\"</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>8180dfe4fc995269bfac5336c13ec931</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>453</td>\n",
" <td>2023-10-13 15:49:57.238792+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>privater chocolateria workshop</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>7cc2c03196cdc8adfc4102c87f15056e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>759</td>\n",
" <td>2023-10-31 03:20:00.509720+01:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-schule i die führung für primarschulkl...</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>582a63d22864911766d8e019c277d1b3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>24</td>\n",
" <td>2023-10-13 13:02:09.521575+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>choco-welt die gruppenführung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>9fa748c7defa0d4f6976faa875d8c394</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>21</td>\n",
" <td>2023-10-13 13:02:09.520019+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>chocolateria</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>169b7c348566ccfd0e6ccdeeb6ac5f5a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>40</td>\n",
" <td>2023-10-13 13:07:51.131049+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>verlängerungspauschale führungen</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>d22a3ae3c0712be5dfe9858b97a22034</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>2</td>\n",
" <td>2023-10-13 13:02:09.509959+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-deluxe die öffentliche führung (en)</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>84d0ef8ed664798bfa6a0d297f45bf2d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>22</td>\n",
" <td>2023-10-13 13:02:09.520492+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>weihnacht-special</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>634f074cc18efa0e0ce88bdec14f248e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>20</td>\n",
" <td>2023-10-13 13:02:09.519518+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>gutschein gruppentarife</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>f005c784b0a8db8244177e61e774a9b6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>13</td>\n",
" <td>2023-10-13 13:02:09.516105+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-deluxe die exklusive gruppenführung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>acb6ff9ac2bac1c55043bcb67a72a3a0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>103</td>\n",
" <td>2023-10-13 13:24:59.980586+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-schule l die führung für primarschulkl...</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>7b44ae19449523c65c1140c8aa4db924</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>81</td>\n",
" <td>2023-10-13 13:19:30.509755+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>jumper-deluxe (de) die weihnachtliche führung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>274024d1c45dc56a82612f8c71e727de</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>221</td>\n",
" <td>2023-10-13 13:52:42.848999+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>jumper-deluxe (en) the christmas guided tour</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>576951a8841585f9bb3a6e4b72289f95</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>23</td>\n",
" <td>2023-10-13 13:02:09.521089+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>choco-deluxe die exklusive gruppenführung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>cc601355e3b07a57631806317f239000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>126</td>\n",
" <td>2023-10-13 13:30:21.301532+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-schule railaway 10%</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>ac0a1b09039cd2f078f2d09404f6c981</td>\n",
" </tr>\n",
" <tr>\n",
" <th>30</th>\n",
" <td>82</td>\n",
" <td>2023-10-13 13:19:30.511942+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>gutschein saisonkurs</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>8f86ea0275633432963ebdceae17ce7c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31</th>\n",
" <td>16</td>\n",
" <td>2023-10-13 13:02:09.517575+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>choco-welt die öffentliche führung</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>944fc565655297b2e67c4ae00f020074</td>\n",
" </tr>\n",
" <tr>\n",
" <th>32</th>\n",
" <td>25</td>\n",
" <td>2023-10-13 13:02:09.522012+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>weihnacht-special</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>68c8841c32b53e7ab121a070043ec1c3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>19</td>\n",
" <td>2023-10-13 13:02:09.519025+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>choco-schule die führung für schulklassen</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>63615b4e41ea135189db55a27c55e481</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>8</td>\n",
" <td>2023-10-13 13:02:09.513651+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>schokoladentour gruppenticket</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>f227b307bebc96449506e7e344c80e80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>35</th>\n",
" <td>106</td>\n",
" <td>2023-10-13 13:24:59.981928+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>valentinstags-special</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>c3ff8a48ad090434023c8b84b556babe</td>\n",
" </tr>\n",
" <tr>\n",
" <th>36</th>\n",
" <td>132</td>\n",
" <td>2023-10-13 13:30:21.303904+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>muttertags-special</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>cb7fd9470daa045117b40a6189e9267f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>37</th>\n",
" <td>108</td>\n",
" <td>2023-10-13 13:24:59.982672+02:00</td>\n",
" <td>2023-11-03 10:17:04.761407+01:00</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>osterkurs</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>225f5c434a1a05e093ee996b02c774f3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"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": 342,
"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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>id</th>\n",
" <th>created_at</th>\n",
" <th>updated_at</th>\n",
" <th>season_id</th>\n",
" <th>facility_id</th>\n",
" <th>name</th>\n",
" <th>event_type_id</th>\n",
" <th>manual_added</th>\n",
" <th>is_display</th>\n",
" <th>event_type_key_id</th>\n",
" <th>facility_key_id</th>\n",
" <th>identifier</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>14370</td>\n",
" <td>2023-04-27 15:40:36.110558+02:00</td>\n",
" <td>2023-10-20 12:55:20.877464+02:00</td>\n",
" <td>1435</td>\n",
" <td>1044</td>\n",
" <td>abonnement - saison 2023 - 2024</td>\n",
" <td>1123</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>1123</td>\n",
" <td>1044</td>\n",
" <td>ee604d3e64a27c663a3a1d9de76596e1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>17634</td>\n",
" <td>2023-07-06 18:02:47.697110+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>1435</td>\n",
" <td>832</td>\n",
" <td>sf paris / racing 92</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>22d7950f7cbce0f2c8f3c4d272ed6926</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>17635</td>\n",
" <td>2023-07-06 18:02:47.697577+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>1435</td>\n",
" <td>832</td>\n",
" <td>sf paris / stade toulousain</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>4ae51c31e231eaca1bc2db3afafe417b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>17632</td>\n",
" <td>2023-07-06 18:02:47.694821+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>1435</td>\n",
" <td>832</td>\n",
" <td>sf paris / montpellier hr</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>389c8fb7577d0ab030d53e521fda600c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>17633</td>\n",
" <td>2023-07-06 18:02:47.696477+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>1435</td>\n",
" <td>832</td>\n",
" <td>sf paris / castres olympique</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>05c9dc3878a4c5c3bfe87bc7667c52d8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>214</th>\n",
" <td>8810</td>\n",
" <td>2023-04-04 18:21:47.463967+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>672</td>\n",
" <td>832</td>\n",
" <td>sf paris / racing 92 (ercc)</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>019a7e2faca12acff64ef458cf0c5975</td>\n",
" </tr>\n",
" <tr>\n",
" <th>215</th>\n",
" <td>8804</td>\n",
" <td>2023-04-04 18:21:47.457687+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>672</td>\n",
" <td>832</td>\n",
" <td>sf paris / stade toulousain</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>ef8b8362079d64a10811ac758ca22a63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>216</th>\n",
" <td>8800</td>\n",
" <td>2023-04-04 18:21:47.453369+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>672</td>\n",
" <td>832</td>\n",
" <td>sf paris / stade rochelais</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>451e36ee5ad882a0c25447e2e129fedd</td>\n",
" </tr>\n",
" <tr>\n",
" <th>217</th>\n",
" <td>8806</td>\n",
" <td>2023-04-04 18:21:47.459782+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>672</td>\n",
" <td>832</td>\n",
" <td>sf paris / section paloise</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>2fbea7b0e293de5bf9e9f11d7a4780f8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>218</th>\n",
" <td>8807</td>\n",
" <td>2023-04-04 18:21:47.460842+02:00</td>\n",
" <td>2023-10-20 12:55:20.854693+02:00</td>\n",
" <td>672</td>\n",
" <td>832</td>\n",
" <td>sf paris / ca brive-correze</td>\n",
" <td>824</td>\n",
" <td>False</td>\n",
" <td>True</td>\n",
" <td>824</td>\n",
" <td>832</td>\n",
" <td>64af51a1bcd04ca63b4d824379283aeb</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>219 rows × 12 columns</p>\n",
"</div>"
],
"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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>compagnie1</th>\n",
" <th>compagnie2</th>\n",
" <th>compagnie3</th>\n",
" <th>compagnie4</th>\n",
" <th>compagnie5</th>\n",
" <th>compagnie6</th>\n",
" <th>compagnie7</th>\n",
" <th>compagnie8</th>\n",
" <th>compagnie9</th>\n",
" <th>compagnie10</th>\n",
" <th>compagnie11</th>\n",
" <th>compagnie12</th>\n",
" <th>compagnie13</th>\n",
" <th>compagnie14</th>\n",
" <th>compagnie101</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>museum</td>\n",
" <td>museum</td>\n",
" <td>museum</td>\n",
" <td>museum</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>museum</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>bdc2324-data/1</td>\n",
" <td>bdc2324-data/2</td>\n",
" <td>bdc2324-data/3</td>\n",
" <td>bdc2324-data/4</td>\n",
" <td>bdc2324-data/5</td>\n",
" <td>bdc2324-data/6</td>\n",
" <td>bdc2324-data/7</td>\n",
" <td>bdc2324-data/8</td>\n",
" <td>bdc2324-data/9</td>\n",
" <td>bdc2324-data/10</td>\n",
" <td>bdc2324-data/11</td>\n",
" <td>bdc2324-data/12</td>\n",
" <td>bdc2324-data/13</td>\n",
" <td>bdc2324-data/14</td>\n",
" <td>bdc2324-data/101</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>compagnie1</th>\n",
" <th>compagnie2</th>\n",
" <th>compagnie3</th>\n",
" <th>compagnie4</th>\n",
" <th>compagnie5</th>\n",
" <th>compagnie6</th>\n",
" <th>compagnie7</th>\n",
" <th>compagnie8</th>\n",
" <th>compagnie9</th>\n",
" <th>compagnie10</th>\n",
" <th>compagnie11</th>\n",
" <th>compagnie12</th>\n",
" <th>compagnie13</th>\n",
" <th>compagnie14</th>\n",
" <th>compagnie101</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>type_event</th>\n",
" <td>museum</td>\n",
" <td>museum</td>\n",
" <td>museum</td>\n",
" <td>museum</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>sport</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>spectable/theater</td>\n",
" <td>museum</td>\n",
" </tr>\n",
" <tr>\n",
" <th>base_compagnie</th>\n",
" <td>bdc2324-data/1</td>\n",
" <td>bdc2324-data/2</td>\n",
" <td>bdc2324-data/3</td>\n",
" <td>bdc2324-data/4</td>\n",
" <td>bdc2324-data/5</td>\n",
" <td>bdc2324-data/6</td>\n",
" <td>bdc2324-data/7</td>\n",
" <td>bdc2324-data/8</td>\n",
" <td>bdc2324-data/9</td>\n",
" <td>bdc2324-data/10</td>\n",
" <td>bdc2324-data/11</td>\n",
" <td>bdc2324-data/12</td>\n",
" <td>bdc2324-data/13</td>\n",
" <td>bdc2324-data/14</td>\n",
" <td>bdc2324-data/101</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"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
}