Add dataset dataset_43 #180
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Preprocessing | |
| on: | |
| pull_request_target: | |
| # (re)opened PR or new commit in fork | |
| types: [ opened, synchronize, reopened ] | |
| paths: | |
| - 'raw_data/**' | |
| - 'processed_data/**' | |
| jobs: | |
| preprocess: | |
| name: Preprocess raw data | |
| runs-on: ubuntu-latest | |
| container: | |
| image: ghcr.io/${{ github.repository_owner }}/repo_rt_preprocessing:latest | |
| env: | |
| RENV_PATHS_LIBRARY: '/renv/library' | |
| defaults: | |
| run: | |
| shell: bash | |
| steps: | |
| - name: Checkout fork repository | |
| uses: actions/checkout@v3 | |
| with: | |
| fetch-depth: 0 | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| ref: ${{ github.head_ref }} | |
| lfs: true | |
| - name: Get changed files | |
| id: files | |
| uses: Ana06/[email protected] | |
| - name: Get new/changed datasets | |
| id: filesfolders | |
| shell: bash {0} | |
| run: echo "files=$(for f in ${{ steps.files.outputs.added_modified_renamed }}; do basename $(dirname $f); done | grep -E '^([0-9]+)|(draft_.*)$' | sort | uniq | tr '\n' ' ')" >> $GITHUB_OUTPUT | |
| - name: List all added files | |
| run: | | |
| for f in ${{ steps.filesfolders.outputs.files }}; do | |
| ls -lh raw_data/$f | |
| done | |
| - name: Standardize compounds | |
| run: Rscript scripts/R_ci/compounds_standardize.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Compounds classyfire classes | |
| run: Rscript scripts/R_ci/compounds_classyfire.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Compounds descriptors | |
| run: Rscript scripts/R_ci/compounds_descriptors.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Compounds fingerprints | |
| run: Rscript scripts/R_ci/compounds_fingerprints.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Metadata standardization | |
| run: Rscript scripts/R_ci/metadata_standardize.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Generate dataset reports | |
| run: Rscript scripts/R_ci/compounds_overview.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Verify that required files are present | |
| run: Rscript scripts/R_ci/files_complete.R ${{ steps.filesfolders.outputs.files }} | |
| - name: Update overview table of all datasets | |
| run: python3 scripts/Python/datasets_overview.py | |
| continue-on-error: true | |
| - name: QSPR-based validation | |
| run: python3 scripts/Python/validation_qspr.py ${{ steps.filesfolders.outputs.files }} | |
| continue-on-error: true | |
| - name: Retention order-based validation for datasets with nominally identical setups | |
| run: python3 scripts/Python/validation_order.py --mode same_condition ${{ steps.filesfolders.outputs.files }} | |
| continue-on-error: true | |
| - name: Retention order-based validation for datasets of systematic measurements | |
| run: python3 scripts/Python/validation_order.py --mode systematic ${{ steps.filesfolders.outputs.files }} | |
| continue-on-error: true | |
| - name: Commit preprocessing | |
| run: | | |
| git config --global user.email '[email protected]' | |
| git config --global user.name 'Github Actions' | |
| # because of dockerized environment, git will otherwise complain about "dubious ownership of directory" | |
| git config --global safe.directory '*' | |
| # Use LFS storage of main repository: no push access to fork LFS storage | |
| # TODO: change once repository is moved | |
| git config lfs.url 'https://github.com/michaelwitting/RepoRT.git/info/lfs' | |
| git add processed_data raw_data | |
| git commit -m "Preprocessing ${{ steps.filesfolders.outputs.files }}" | |
| git lfs push origin HEAD # first push LFS, otherwise failure because of lfs.url | |
| git push origin HEAD | |
| - name: Add comment with report to PR | |
| uses: actions/github-script@v6 | |
| with: | |
| script: | | |
| github.rest.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: (await exec.getExecOutput('python3 scripts/Python/report.py', '${{ steps.filesfolders.outputs.files }}'.trim().split(' '))).stdout | |
| }) | |
| continue-on-error: true | |
| - name: Label as successfully preprocessed | |
| if: ${{ success() }} | |
| uses: andymckay/labeler@master | |
| with: | |
| add-labels: "preprocessing successful" | |
| remove-labels: "preprocessing failed" | |
| - name: Add comment on how to proceed with PR | |
| uses: actions/github-script@v6 | |
| with: | |
| script: | | |
| github.rest.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: 'This Pull Request is in "draft" status. When all issues (if any) are addressed, the status can manually be set to "ready for review". Subsequently, the temporary dataset IDs will be replaced with the final ones; then the Pull Request can be merged.' | |
| }) | |
| continue-on-error: true | |
| - name: Label as failed | |
| if: ${{ failure() }} | |
| uses: andymckay/labeler@master | |
| with: | |
| add-labels: "preprocessing failed" | |
| remove-labels: "preprocessing successful" |