Labeler: Training #10
This file contains hidden or 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
| # Workflow template imported and updated from: | |
| # https://github.com/dotnet/issue-labeler/wiki/Onboarding | |
| # | |
| # See labeler.md for more information | |
| # | |
| # Train the Issues and Pull Requests models for label prediction | |
| name: "Labeler: Training" | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| type: | |
| description: "Issues or Pull Requests" | |
| type: choice | |
| required: true | |
| default: "Both" | |
| options: | |
| - "Both" | |
| - "Issues" | |
| - "Pull Requests" | |
| steps: | |
| description: "Training Steps" | |
| type: choice | |
| required: true | |
| default: "All" | |
| options: | |
| - "All" | |
| - "Download Data" | |
| - "Train Model" | |
| - "Test Model" | |
| limit: | |
| description: "Max number of items to download for training/testing the model (newest items are used). Defaults to the max number of pages times the page size." | |
| type: number | |
| page_size: | |
| description: "Number of items per page in GitHub API requests. Defaults to 100 for issues. Always uses 1 for pull requests." | |
| type: number | |
| page_limit: | |
| description: "Maximum number of pages to download for training/testing the model. Defaults to 1000 for issues, 4000 for pull requests." | |
| type: number | |
| cache_key_suffix: | |
| description: "The cache key suffix to use for staged data/models (use 'ACTIVE' to bypass staging). Defaults to 'staged'." | |
| required: true | |
| default: "staged" | |
| env: | |
| CACHE_KEY: ${{ inputs.cache_key_suffix }} | |
| REPOSITORY: ${{ github.repository }} | |
| LABEL_PREFIX: "area-" | |
| THRESHOLD: "0.40" | |
| LIMIT: ${{ inputs.limit }} | |
| PAGE_SIZE: ${{ inputs.page_size }} | |
| PAGE_LIMIT: ${{ inputs.page_limit }} | |
| EXCLUDED_AUTHORS: "" # Comma-separated list of authors to exclude from training data | |
| jobs: | |
| download-issues: | |
| if: ${{ contains(fromJSON('["Both", "Issues"]'), inputs.type) && contains(fromJSON('["All", "Download Data"]'), inputs.steps) }} | |
| runs-on: ubuntu-latest | |
| permissions: | |
| issues: read | |
| steps: | |
| - name: "Download Issues" | |
| uses: dotnet/issue-labeler/download@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0 | |
| with: | |
| type: "issues" | |
| cache_key: ${{ env.CACHE_KEY }} | |
| repository: ${{ env.REPOSITORY }} | |
| label_prefix: ${{ env.LABEL_PREFIX }} | |
| limit: ${{ env.LIMIT }} | |
| page_size: ${{ env.PAGE_SIZE }} | |
| page_limit: ${{ env.PAGE_LIMIT }} | |
| excluded_authors: ${{ env.EXCLUDED_AUTHORS }} | |
| env: | |
| GITHUB_TOKEN: ${{ github.token }} | |
| download-pulls: | |
| if: ${{ contains(fromJSON('["Both", "Pull Requests"]'), inputs.type) && contains(fromJSON('["All", "Download Data"]'), inputs.steps) }} | |
| runs-on: ubuntu-latest | |
| permissions: | |
| pull-requests: read | |
| steps: | |
| - name: "Download Pull Requests" | |
| uses: dotnet/issue-labeler/download@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0 | |
| with: | |
| type: "pulls" | |
| cache_key: ${{ env.CACHE_KEY }} | |
| repository: ${{ env.REPOSITORY }} | |
| label_prefix: ${{ env.LABEL_PREFIX }} | |
| limit: ${{ env.LIMIT }} | |
| page_size: 1 # This repository can only successfully download pulls one at a time due to GitHub's API performance | |
| page_limit: 10000 # Download the newest 10,000 pull requests | |
| excluded_authors: ${{ env.EXCLUDED_AUTHORS }} | |
| env: | |
| GITHUB_TOKEN: ${{ github.token }} | |
| train-issues: | |
| if: ${{ always() && contains(fromJSON('["Both", "Issues"]'), inputs.type) && contains(fromJSON('["All", "Train Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.download-issues.result) }} | |
| runs-on: ubuntu-latest | |
| permissions: {} | |
| needs: download-issues | |
| steps: | |
| - name: "Train Model for Issues" | |
| uses: dotnet/issue-labeler/train@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0 | |
| with: | |
| type: "issues" | |
| data_cache_key: ${{ env.CACHE_KEY }} | |
| model_cache_key: ${{ env.CACHE_KEY }} | |
| train-pulls: | |
| if: ${{ always() && contains(fromJSON('["Both", "Pull Requests"]'), inputs.type) && contains(fromJSON('["All", "Train Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.download-pulls.result) }} | |
| runs-on: ubuntu-latest | |
| permissions: {} | |
| needs: download-pulls | |
| steps: | |
| - name: "Train Model for Pull Requests" | |
| uses: dotnet/issue-labeler/train@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0 | |
| with: | |
| type: "pulls" | |
| data_cache_key: ${{ env.CACHE_KEY }} | |
| model_cache_key: ${{ env.CACHE_KEY }} | |
| test-issues: | |
| if: ${{ always() && contains(fromJSON('["Both", "Issues"]'), inputs.type) && contains(fromJSON('["All", "Test Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.train-issues.result) }} | |
| runs-on: ubuntu-latest | |
| permissions: | |
| issues: read | |
| needs: train-issues | |
| steps: | |
| - name: "Test Model for Issues" | |
| uses: dotnet/issue-labeler/test@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0 | |
| with: | |
| type: "issues" | |
| cache_key: ${{ env.CACHE_KEY }} | |
| repository: ${{ env.REPOSITORY }} | |
| label_prefix: ${{ env.LABEL_PREFIX }} | |
| threshold: ${{ env.THRESHOLD }} | |
| limit: ${{ env.LIMIT }} | |
| page_size: ${{ env.PAGE_SIZE }} | |
| page_limit: ${{ env.PAGE_LIMIT }} | |
| excluded_authors: ${{ env.EXCLUDED_AUTHORS }} | |
| env: | |
| GITHUB_TOKEN: ${{ github.token }} | |
| test-pulls: | |
| if: ${{ always() && contains(fromJSON('["Both", "Pull Requests"]'), inputs.type) && contains(fromJSON('["All", "Test Model"]'), inputs.steps) && contains(fromJSON('["success", "skipped"]'), needs.train-pulls.result) }} | |
| runs-on: ubuntu-latest | |
| permissions: | |
| pull-requests: read | |
| needs: train-pulls | |
| steps: | |
| - name: "Test Model for Pull Requests" | |
| uses: dotnet/issue-labeler/test@46125e85e6a568dc712f358c39f35317366f5eed # v2.0.0 | |
| with: | |
| type: "pulls" | |
| cache_key: ${{ env.CACHE_KEY }} | |
| repository: ${{ env.REPOSITORY }} | |
| label_prefix: ${{ env.LABEL_PREFIX }} | |
| threshold: ${{ env.THRESHOLD }} | |
| limit: ${{ env.LIMIT }} | |
| page_size: 1 # This repository can only successfully download pulls one at a time due to GitHub's API performance | |
| page_limit: 10000 # Download the newest 10,000 pull requests | |
| excluded_authors: ${{ env.EXCLUDED_AUTHORS }} | |
| env: | |
| GITHUB_TOKEN: ${{ github.token }} |