Validate output format and edge cases #59

	name: Check Data Pipeline

	on:
	pull_request:

	jobs:
	check-status:
	name: "Check data pipeline is up-to-date"
	runs-on: ubuntu-latest
	environment: data-fetch

	steps:
	- name: Checkout
	uses: actions/checkout@v4
	with:
	fetch-depth: 0

	- name: Install environment
	uses: prefix-dev/[email protected]
	with:
	pixi-version: latest
	cache: false
	environments: data
	activate-environment: true

	- name: Fetch pipeline data
	run: \|
	dvc pull
	env:
	AWS_ACCESS_KEY_ID: ${{vars.AWS_ACCESS_KEY_ID}}
	AWS_SECRET_ACCESS_KEY: ${{secrets.AWS_SECRET_ACCESS_KEY}}

	- name: Check pipeline status
	run: \|
	exec /bin/bash scripts/check-dvc-status.sh

	rerun-subset-recs:
	name: "Rerun MIND subset recommendations"
	# run this on MacOS for performance
	runs-on: macos-latest
	environment: data-fetch

	steps:
	- name: Checkout
	uses: actions/checkout@v4
	with:
	fetch-depth: 0

	- name: Install environment
	uses: prefix-dev/[email protected]
	with:
	pixi-version: latest
	cache: true
	environments: eval
	activate-environment: true

	- name: Fetch pipeline data
	run: \|
	dvc pull
	env:
	AWS_ACCESS_KEY_ID: ${{vars.AWS_ACCESS_KEY_ID}}
	AWS_SECRET_ACCESS_KEY: ${{secrets.AWS_SECRET_ACCESS_KEY}}

	- name: Re-run MIND subset outputs
	run: \|
	dvc repro -f measure-mind-subset
	env:
	# POPROX_REC_DEVICE: mps
	POPROX_CPU_COUNT: 1

Provide feedback