Data Cleaning Pipeline #46

	name: Data Cleaning Pipeline

	on:
	schedule:
	- cron: '0 0 * * *' # runs daily at midnight UTC
	workflow_dispatch: # allows manual "Run workflow" button on GitHub

	permissions:
	contents: write

	jobs:
	clean-data:
	runs-on: ubuntu-latest

	steps:
	- name: Checkout repository
	uses: actions/checkout@v4

	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: '3.11'

	- name: Install dependencies
	run: pip install pandas

	- name: Run data cleaning script
	working-directory: python
	run: python 02_data_cleaning.py

	- name: Run database creation script
	working-directory: python
	run: python 03_create_database.py

	- name: Commit and push updated data
	run: \|
	git config --global user.name "github-actions[bot]"
	git config --global user.email "github-actions[bot]@users.noreply.github.com"
	git add data/cleaned data/olist.db
	git commit -m "Automated data refresh" \|\| echo "No changes to commit"
	git push

Provide feedback