clustering
This commit is contained in:
parent
0cf1dc330f
commit
9b95e91c01
74
.ipynb_checkpoints/Clustering-checkpoint.ipynb
Normal file
74
.ipynb_checkpoints/Clustering-checkpoint.ipynb
Normal file
|
|
@ -0,0 +1,74 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7aa09644-4d17-4a7a-841e-3bfcfb8a8901",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Import des données\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"import s3fs\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"s3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
|
||||
"\n",
|
||||
"fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': s3_ENDPOINT_URL})\n",
|
||||
"\n",
|
||||
"BUCKET = \"projet-bdc-data\"\n",
|
||||
"carmignac_path = \"projet-bdc-data/carmignac\"\n",
|
||||
"\n",
|
||||
"# Liste des fichiers FLOWS\n",
|
||||
"all_files = fs.ls(carmignac_path)\n",
|
||||
"flows_files = [f for f in all_files if \"Flows\" in f and f.endswith(\".csv\")]\n",
|
||||
"print(\"Fichiers Flows :\", flows_files)\n",
|
||||
"\n",
|
||||
"# Lire tous les fichiers dans un dictionnaire\n",
|
||||
"flows_data = {}\n",
|
||||
"for file_path in flows_files:\n",
|
||||
" with fs.open(file_path, 'r') as f:\n",
|
||||
" df = pd.read_csv(f, sep=';',low_memory=False)\n",
|
||||
" flows_data[os.path.basename(file_path)] = df\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Liste des fichiers AUM\n",
|
||||
"all_files = fs.ls(carmignac_path)\n",
|
||||
"aum_files = [f for f in all_files if \"AUM\" in f and f.endswith(\".csv\")]\n",
|
||||
"print(\"Fichiers AUM :\", aum_files)\n",
|
||||
"\n",
|
||||
"# Lire tous les fichiers dans un dictionnaire\n",
|
||||
"aum_data = {}\n",
|
||||
"for file_path in aum_files:\n",
|
||||
" with fs.open(file_path, 'r') as f:\n",
|
||||
" df = pd.read_csv(f, sep=';',low_memory=False)\n",
|
||||
" aum_data[os.path.basename(file_path)] = df\n",
|
||||
"\n",
|
||||
"df = aum_data['AUM ENSAE V2 -20251105.csv']\n",
|
||||
"dg = flows_data['Flows ENSAE V2 -20251105.csv']"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.13.12"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
4665
Clustering.ipynb
Normal file
4665
Clustering.ipynb
Normal file
File diff suppressed because one or more lines are too long
Binary file not shown.
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue
Block a user