From 71a9d88188114714c4e166cc56de05ded953dbd9 Mon Sep 17 00:00:00 2001 From: pgoze-ensae Date: Mon, 13 Apr 2026 19:46:26 +0000 Subject: [PATCH] added the notebooks --- .gitignore | 1 - notebooks/push_s3.ipynb | 70 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+), 1 deletion(-) create mode 100644 notebooks/push_s3.ipynb diff --git a/.gitignore b/.gitignore index 0a4dc30..054d278 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,3 @@ data/ data_exploration/ -notebooks/ *.csv diff --git a/notebooks/push_s3.ipynb b/notebooks/push_s3.ipynb new file mode 100644 index 0000000..4152cad --- /dev/null +++ b/notebooks/push_s3.ipynb @@ -0,0 +1,70 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "d2701d07", + "metadata": {}, + "source": [ + "# Helper notebook to allow pushing data on S3" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "5c8fc6c5", + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "import s3fs\n", + "\n", + "def push_file(local_path, s3_path):\n", + " fs = s3fs.S3FileSystem(\n", + " client_kwargs={'endpoint_url': 'https://' + 'minio-simple.lab.groupe-genes.fr'},\n", + " key=os.environ[\"AWS_ACCESS_KEY_ID\"],\n", + " secret=os.environ[\"AWS_SECRET_ACCESS_KEY\"],\n", + " token=os.environ[\"AWS_SESSION_TOKEN\"]\n", + " )\n", + "\n", + " with open(local_path, 'rb') as local_f, fs.open(s3_path, 'wb') as s3_f:\n", + " s3_f.write(local_f.read())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d43b725e", + "metadata": {}, + "outputs": [], + "source": [ + "push_file('repair_challenge/alpha_5%/carmignac_broken_months.csv', 'projet-bdc-carmignac-g3//paco/carmignac_broken_months.csv')\n", + "push_file('repair_challenge/alpha_5%/carmignac_error_account_agg.csv', 'projet-bdc-carmignac-g3//paco/carmignac_error_account_agg.csv')\n", + "push_file('repair_challenge/alpha_5%/carmignac_error_account.csv', 'projet-bdc-carmignac-g3//paco/carmignac_error_account.csv')\n", + "push_file('AUM_repaired.csv', 'projet-bdc-carmignac-g3//paco/AUM_repaired.csv')\n", + "push_file('AUM_paths.csv', 'projet-bdc-carmignac-g3//paco/AUM_paths.csv')\n", + "push_file('AUM_repair_audit.csv', 'projet-bdc-carmignac-g3//paco/AUM_repair_audit.csv')" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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 +}