39k Pfizer dataset (#188) (#189) #571

	# Runs process_dataset.py on all files in the database.

	name: Validation

	on:
	push:
	branches:
	- main
	pull_request:
	paths:
	# Runs when this file is modified in a PR.
	- '.github/workflows/validation.yml'

	env:
	ORD_SCHEMA_TAG: v0.3.81

	jobs:
	validate_database:
	runs-on: ubuntu-latest
	strategy:
	matrix:
	filter: [
	'data/[0-4][0-4]',
	'data/[0-4][5-9]',
	'data/[0-4][a-f]',
	'data/[5-9][0-4]',
	'data/[5-9][5-9]',
	'data/[5-9][a-f]',
	'data/[a-f][0-4]',
	'data/[a-f][5-9]',
	'data/[a-f][a-f]',
	]
	steps:
	- name: Checkout ord-data
	uses: actions/checkout@v2
	with:
	lfs: true
	- name: Checkout ord-schema
	uses: actions/checkout@v2
	with:
	repository: Open-Reaction-Database/ord-schema
	ref: ${{ env.ORD_SCHEMA_TAG }}
	path: ord-schema
	- uses: actions/setup-python@v4
	with:
	python-version: '3.10'
	- name: Install ord_schema
	run: \|
	cd "${GITHUB_WORKSPACE}/ord-schema"
	python -m pip install --upgrade pip
	python -m pip install wheel
	python -m pip install .
	- name: Validate datasets
	env:
	FILTER: ${{ matrix.filter }}
	run: \|
	cd "${GITHUB_WORKSPACE}"
	python ./ord-schema/ord_schema/scripts/validate_dataset.py --input="data//.pb*" --filter="${FILTER}"

Provide feedback