Update data #27

	name: DVC Workflow

	on:
	pull_request:
	branches:
	- main
	paths:
	- '*/.dvc'
	- '.dvc/**'

	jobs:
	format:
	runs-on: ubuntu-latest
	steps:
	- name: Checkout code
	uses: actions/checkout@v4

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

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements.txt
	pip install dvc[gdrive]

	- name: Authenticate with Google Cloud
	uses: google-github-actions/auth@v2
	with:
	credentials_json: ${{ secrets.GCP_SA_KEY }}

	- name: Prepare DVC Authentication
	run: \|
	mv $(find $GITHUB_WORKSPACE -name "gha-creds-*.json") /home/runner/work/my_project/credentials.json

	- name: Pull data from DVC
	run: \|
	dvc pull --no-run-cache -v

	- name: Debug paths
	run: \|
	pwd
	ls -R

	- name: Check data statistics
	run: \|
	python src/my_project/data.py > data_statistics.md
	echo '![](./mnist_images.png "MNIST images")' >> data_statistics.md
	echo '![](./train_label_distribution.png "Train label distribution")' >> data_statistics.md
	echo '![](./test_label_distribution.png "Test label distribution")' >> data_statistics.md

	- name: Setup CML
	uses: iterative/setup-cml@v2

	- name: Comment on PR
	env:
	REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
	run: \|
	cml comment create data_statistics.md --watermark-title="Data Checker"

Provide feedback