===== lab03a - Wed Nov 4 12:38:17 PM UTC 2026 ===== $ pwd /home/onyxia/work $ mkdir /home/onyxia/work/ece-2026-bigdata $ cd /home/onyxia/work/ece-2026-bigdata $ git config --global init.defaultBranch main $ git init Initialized empty Git repository in /home/onyxia/work/ece-2026-bigdata/.git/ $ cat $ git config --global user.name m-anane-ece $ git config --global user.email mohamed.anane@edu.ece.fr $ command -v uv /opt/python/bin/uv $ uv init --package Initialized project `ece-2026-bigdata` $ uv sync Using CPython 3.13.15 interpreter at: /opt/python/bin/python3.13 Creating virtual environment at: .venv Resolved 1 package in 4ms Building ece-2026-bigdata @ file:///home/onyxia/work/ece-2026-bigdata Built ece-2026-bigdata @ file:///home/onyxia/work/ece-2026-bigdata Prepared 1 package in 13ms Installed 1 package in 4ms + ece-2026-bigdata==0.1.0 (from file:///home/onyxia/work/ece-2026-bigdata) $ ls -a . .. .git .gitignore pyproject.toml .python-version README.md src uv.lock .venv $ cat pyproject.toml [project] name = "ece-2026-bigdata" version = "0.1.0" description = "Add your description here" readme = "README.md" authors = [ { name = "m-anane-ece", email = "mohamed.anane@edu.ece.fr" } ] requires-python = ">=3.13" dependencies = [] [project.scripts] ece-2026-bigdata = "ece_2026_bigdata:main" [build-system] requires = ["uv_build>=0.12.10,<0.13.0"] build-backend = "uv_build" $ git add .gitignore .python-version pyproject.toml README.md src uv.lock $ git commit -m 'feat: initial project layout' [main (root-commit) 96d03bc] feat: initial project layout 6 files changed, 32 insertions(+) create mode 100644 .gitignore create mode 100644 .python-version create mode 100644 README.md create mode 100644 pyproject.toml create mode 100644 src/ece_2026_bigdata/__init__.py create mode 100644 uv.lock $ gpush -u origin main $ git remote get-url origin $ echo '[push differe : le depot GitHub n'\''est pas encore relie]' [push differe : le depot GitHub n'est pas encore relie] $ cat $ git add README.md $ git commit -m 'docs: project introduction and usages' [main 93e283a] docs: project introduction and usages 1 file changed, 13 insertions(+) $ gpush $ git remote get-url origin $ echo '[push differe : le depot GitHub n'\''est pas encore relie]' [push differe : le depot GitHub n'est pas encore relie] $ cat $ uv add 'faker>=40.37.0' Resolved 3 packages in 266ms Building ece-2026-bigdata @ file:///home/onyxia/work/ece-2026-bigdata Built ece-2026-bigdata @ file:///home/onyxia/work/ece-2026-bigdata Downloading faker (2.0MiB) Downloaded faker Prepared 2 packages in 123ms Uninstalled 1 package in 0.67ms Installed 2 packages in 49ms ~ ece-2026-bigdata==0.1.0 (from file:///home/onyxia/work/ece-2026-bigdata) + faker==40.44.0 $ cat pyproject.toml [project] name = "ece-2026-bigdata" version = "0.1.0" description = "Add your description here" readme = "README.md" authors = [ { name = "m-anane-ece", email = "mohamed.anane@edu.ece.fr" } ] requires-python = ">=3.13" dependencies = [ "faker>=40.37.0", ] [project.scripts] ece-2026-bigdata = "ece_2026_bigdata:main" [build-system] requires = ["uv_build>=0.12.10,<0.13.0"] build-backend = "uv_build" $ cat $ cat $ python3 - $ cat pyproject.toml [project] name = "ece-2026-bigdata" version = "0.1.0" description = "Add your description here" readme = "README.md" authors = [ { name = "m-anane-ece", email = "mohamed.anane@edu.ece.fr" } ] requires-python = ">=3.13" dependencies = [ "faker>=40.37.0", ] [project.scripts] dataset-users = "ece_2026_bigdata.dataset_users:main" dataset-orders = "ece_2026_bigdata.dataset_orders:main" [build-system] requires = ["uv_build>=0.12.10,<0.13.0"] build-backend = "uv_build" $ uv run dataset-users -h Building ece-2026-bigdata @ file:///home/onyxia/work/ece-2026-bigdata Built ece-2026-bigdata @ file:///home/onyxia/work/ece-2026-bigdata Uninstalled 1 package in 0.48ms Installed 1 package in 3ms usage: dataset-users [-h] [-c COUNT] [-o {csv,json,jsonline}] Users generator options: -h, --help show this help message and exit -c, --count COUNT Number of users to generate. -o, --output {csv,json,jsonline} Output format. $ uv run dataset-users -c 2 -o jsonline {"uuid": "bdd640fb-0667-4ad1-9c80-317fa3b1799d", "username": "garzaanthony", "name": "Charles Garcia", "sex": "M", "address": "908 Jennifer Squares\nRobinsonshire, KY 01352", "mail": "helenpeterson@gmail.com", "birthdate": "1935-10-26"} {"uuid": "17be3111-1a2a-43ed-962b-0f79c37459ee", "username": "blairamanda", "name": "Ryan Munoz", "sex": "M", "address": "Unit 6184 Box 9593\nDPO AP 09617", "mail": "stanleykendra@gmail.com", "birthdate": "2010-01-21"} $ uv run dataset-orders -h usage: dataset-orders [-h] [-C COUNT_MIN] [-c COUNT_MAX] [-d DATE_FROM] [-o {csv,json,jsonline}] [-u COUNT_USERS] Orders generator options: -h, --help show this help message and exit -C, --count-min COUNT_MIN Minimum number of orders to generate per user. -c, --count-max COUNT_MAX Maximum number of orders to generate per user. -d, --date-from DATE_FROM Date of the first order, in ISO format (default: 2020-01-01). -o, --output {csv,json,jsonline} Output format. -u, --count-users COUNT_USERS Number of users to generate. $ uv run dataset-orders -u 2 -C 1 -c 2 -o json $ jq '.[0]' { "uuid": "a2bc372f-7412-4293-8729-4739614ff3d7", "user_uuid": "bdd640fb-0667-4ad1-9c80-317fa3b1799d", "date": "2020-01-01 00:50:02.797536+00:00", "quantity": 2, "product": "cookie" } $ git add pyproject.toml uv.lock src $ git commit -m 'feat: dataset generation scripts' [main 79b8620] feat: dataset generation scripts 5 files changed, 172 insertions(+), 2 deletions(-) create mode 100644 src/ece_2026_bigdata/dataset_orders.py create mode 100644 src/ece_2026_bigdata/dataset_users.py create mode 100644 src/ece_2026_bigdata/serialize.py $ gpush $ git remote get-url origin $ echo '[push differe : le depot GitHub n'\''est pas encore relie]' [push differe : le depot GitHub n'est pas encore relie] $ git log --oneline 79b8620 feat: dataset generation scripts 93e283a docs: project introduction and usages 96d03bc feat: initial project layout $ true EXIT_CODE=0