Checking drift in data with Alibi #12

	name: Data Drift Detection
	run-name: Checking drift in data with Alibi

	on:
	push:
	paths:
	- 'data/**'
	- 'src/**'
	- 'notebooks/6.1-agv-drift-with-alibi.ipynb'
	- 'tests/behavioral_testing/**'
	- 'tests/model_training_testing/**'

	permissions:
	contents: write

	jobs:
	drift-detection:

	runs-on: ubuntu-latest

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

	- name: Set up Python
	uses: actions/setup-python@v4
	with:
	python-version: '3.11'

	- name: Install Python dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements-dev.txt

	- name: Set up DVC
	uses: iterative/setup-dvc@v1

	- name: Pull data with DVC
	env:
	GDRIVE_CREDENTIALS_DATA: ${{ secrets.GDRIVE_CREDENTIALS_DATA }}
	run: \|
	dvc remote modify myremote gdrive_use_service_account true
	dvc pull -r myremote

	- name: Extract data
	run: \|
	sudo apt-get install -y unzip
	unzip data/processed/datasets_processed.zip -d data/processed/datasets_processed

	- name: Data drift detection
	run: \|
	python src/features/drift_detection.py

	- name: Upload log artifact
	uses: actions/upload-artifact@v3
	with:
	name: drift-detection
	path: log/drift-detection.log

	- name: Commit report
	run: \|
	git status
	git config --global user.name "Gitty[bot]"
	git config --global user.email "Gitty[bot]@users.noreply.github.com"
	git commit -am "Automated drift detection logs"
	git push

	- name: Data Drift Detection - Debug mode
	run: \|
	python src/features/drift_detection.py debug=1

Provide feedback