dagzoo 0.9.7__tar.gz

dagzoo-0.9.7/.github/workflows/benchmark.yml

@@ -0,0 +1,148 @@
+name: benchmark-suite
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+  schedule:
+    - cron: "0 10 * * 1"
+  workflow_dispatch:
+
+concurrency:
+  group: benchmark-suite-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  benchmark-smoke-pr:
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.13'
+
+      - name: Install uv
+        run: python -m pip install --upgrade uv
+
+      - name: Install dependencies
+        run: uv sync --group dev
+
+      - name: Run smoke benchmark (CPU)
+        run: |
+          uv run dagzoo benchmark \
+            --suite smoke \
+            --preset cpu \
+            --baseline benchmarks/baselines/cpu_smoke.json \
+            --warn-threshold-pct 10 \
+            --fail-threshold-pct 20 \
+            --fail-on-regression \
+            --hardware-policy none \
+            --no-memory \
+            --out-dir benchmarks/results/ci_smoke
+
+      - name: Upload smoke benchmark artifacts
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: benchmark-smoke-pr
+          path: benchmarks/results/ci_smoke
+          if-no-files-found: warn
+
+      - name: Comment smoke benchmark summary on PR
+        if: always()
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const fs = require('fs');
+            const marker = '<!-- dagzoo-benchmark-smoke -->';
+            const summaryPath = 'benchmarks/results/ci_smoke/summary.md';
+
+            let summary = 'Benchmark summary file was not generated.';
+            if (fs.existsSync(summaryPath)) {
+              summary = fs.readFileSync(summaryPath, 'utf8');
+            }
+
+            const body = `${marker}\n## Benchmark Smoke (CPU)\n\n${summary}`;
+            const { owner, repo } = context.repo;
+            const issue_number = context.issue.number;
+
+            const comments = await github.paginate(github.rest.issues.listComments, {
+              owner,
+              repo,
+              issue_number,
+              per_page: 100,
+            });
+
+            const existing = comments.find((c) => c.user?.type === 'Bot' && c.body?.includes(marker));
+            if (existing) {
+              await github.rest.issues.updateComment({
+                owner,
+                repo,
+                comment_id: existing.id,
+                body,
+              });
+            } else {
+              await github.rest.issues.createComment({
+                owner,
+                repo,
+                issue_number,
+                body,
+              });
+            }
+
+  benchmark-standard-scheduled:
+    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.13'
+
+      - name: Install uv
+        run: python -m pip install --upgrade uv
+
+      - name: Install dependencies
+        run: uv sync --group dev
+
+      - name: Run standard benchmark (CPU)
+        run: |
+          uv run dagzoo benchmark \
+            --suite standard \
+            --preset cpu \
+            --baseline benchmarks/baselines/cpu_standard.json \
+            --warn-threshold-pct 10 \
+            --fail-threshold-pct 20 \
+            --fail-on-regression \
+            --hardware-policy none \
+            --out-dir benchmarks/results/ci_standard
+
+      - name: Upload standard benchmark artifacts
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: benchmark-standard-scheduled
+          path: benchmarks/results/ci_standard
+          if-no-files-found: warn
+
+      - name: Publish standard benchmark summary
+        if: always()
+        run: |
+          if [ -f benchmarks/results/ci_standard/summary.md ]; then
+            cat benchmarks/results/ci_standard/summary.md >> "$GITHUB_STEP_SUMMARY"
+          else
+            echo "summary.md was not generated." >> "$GITHUB_STEP_SUMMARY"
+          fi

dagzoo-0.9.7/.github/workflows/docs.yml

@@ -0,0 +1,149 @@
+name: docs
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    paths:
+      - "docs/**"
+      - "site/**"
+      - "scripts/docs/**"
+      - ".github/workflows/docs.yml"
+      - "README.md"
+  push:
+    branches: [main]
+    paths:
+      - "docs/**"
+      - "site/**"
+      - "scripts/docs/**"
+      - ".github/workflows/docs.yml"
+      - "README.md"
+  workflow_dispatch:
+
+concurrency:
+  group: docs-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Install uv
+        run: python -m pip install --upgrade uv
+
+      - name: Install dependencies
+        run: uv sync --group dev
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "24"
+          cache: "npm"
+          cache-dependency-path: site/package-lock.json
+
+      - name: Install docs build dependencies
+        run: npm ci --prefix site
+
+      - name: Sync docs content
+        run: uv run python scripts/docs/sync_hugo_content.py
+
+      - name: Verify docs sync (idempotence)
+        run: uv run python scripts/docs/sync_hugo_content.py --check
+
+      - name: Check docs links
+        run: uv run python scripts/docs/check_links.py
+
+      - name: Setup Go (for Hugo modules)
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: site/go.mod
+
+      - name: Setup Hugo
+        uses: peaceiris/actions-hugo@v3
+        with:
+          hugo-version: "0.152.2"
+          extended: true
+
+      - name: Build site
+        run: hugo --source site --minify --gc --destination public
+
+      - name: Check built-output links
+        run: uv run python scripts/docs/check_built_output_links.py site/public
+
+  deploy:
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    needs: validate
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Configure GitHub Pages
+        uses: actions/configure-pages@v5
+        with:
+          enablement: true
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.13"
+
+      - name: Install uv
+        run: python -m pip install --upgrade uv
+
+      - name: Install dependencies
+        run: uv sync --group dev
+
+      - name: Setup Node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "24"
+          cache: "npm"
+          cache-dependency-path: site/package-lock.json
+
+      - name: Install docs build dependencies
+        run: npm ci --prefix site
+
+      - name: Sync docs content
+        run: uv run python scripts/docs/sync_hugo_content.py
+
+      - name: Setup Go (for Hugo modules)
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: site/go.mod
+
+      - name: Setup Hugo
+        uses: peaceiris/actions-hugo@v3
+        with:
+          hugo-version: "0.152.2"
+          extended: true
+
+      - name: Build site
+        run: hugo --source site --minify --gc --destination public
+
+      - name: Upload Pages artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: site/public
+
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

dagzoo-0.9.7/.github/workflows/package.yml

@@ -0,0 +1,107 @@
+name: package
+
+on:
+  push:
+    branches: [main]
+    tags: ['v*']
+
+jobs:
+  check-version:
+    if: github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    outputs:
+      changed: ${{ steps.check.outputs.changed }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+
+      - name: Check for version change
+        id: check
+        run: |
+          CURR=$(grep -m1 '^version' pyproject.toml | sed 's/.*= *"\(.*\)"/\1/')
+          PREV=$(git show HEAD~1:pyproject.toml | grep -m1 '^version' | sed 's/.*= *"\(.*\)"/\1/')
+          if [ "$CURR" != "$PREV" ]; then
+            echo "changed=true" >> "$GITHUB_OUTPUT"
+            echo "Version changed: $PREV -> $CURR"
+          else
+            echo "changed=false" >> "$GITHUB_OUTPUT"
+            echo "Version unchanged: $CURR"
+          fi
+
+  build:
+    if: >-
+      always() && (
+        (needs.check-version.result == 'success' && needs.check-version.outputs.changed == 'true')
+        || startsWith(github.ref, 'refs/tags/v')
+      )
+    needs: check-version
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.13'
+
+      - name: Install uv
+        run: python -m pip install --upgrade uv
+
+      - name: Build sdist and wheel
+        run: uv build
+
+      - name: Upload build artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+          retention-days: 30
+
+  publish-pypi:
+    if: always() && startsWith(github.ref, 'refs/tags/v')
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Download build artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  release:
+    if: always() && startsWith(github.ref, 'refs/tags/v')
+    needs:
+      - build
+      - publish-pypi
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    steps:
+      - name: Download build artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: dist/*
+          generate_release_notes: true

dagzoo-0.9.7/.github/workflows/test.yml

@@ -0,0 +1,41 @@
+name: test
+on:
+  push:
+    branches: [main]
+  pull_request:
+    types: [opened, synchronize, reopened]
+  workflow_dispatch:
+concurrency:
+  group: test-${{ github.ref }}
+  cancel-in-progress: true
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.14'
+      - run: python -m pip install --upgrade uv
+      - run: uv sync --group dev
+      - name: Lint
+        run: uv run ruff check src tests
+      - name: Type check
+        run: uv run mypy src
+      - name: Dead code
+        run: >
+          uv run vulture src/dagzoo tests
+          --ignore-names __getattr__
+      - name: Test with coverage
+        run: >
+          uv run pytest
+          --cov=dagzoo
+          --cov-report=term-missing
+          --cov-report=xml:coverage.xml
+          -q
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: coverage-report-py3.14
+          path: coverage.xml
+          retention-days: 14

dagzoo-0.9.7/.gitignore

@@ -0,0 +1,66 @@
+# OS / editor
+.DS_Store
+Thumbs.db
+.idea/
+.vscode/
+
+# Python bytecode / caches
+__pycache__/
+*.py[cod]
+*.pyo
+*.pyd
+*.so
+.python-version
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# Test / lint / type-check caches and coverage
+.pytest_cache/
+.testmondata
+.mypy_cache/
+.ruff_cache/
+.coverage
+.coverage.*
+htmlcov/
+coverage.xml
+.tox/
+.nox/
+
+# Packaging / build artifacts
+build/
+dist/
+*.egg-info/
+.eggs/
+pip-wheel-metadata/
+
+# Local env files / secrets
+.env
+.env.*
+.envrc
+*.local
+
+# Runtime outputs / generated data
+data/
+benchmarks/results/
+*.parquet
+*.feather
+*.arrow
+*.log
+
+# Reference PDFs (large binary files)
+*.pdf
+
+effective_config_artifacts/
+
+# Hugo docs build artifacts
+public/
+site/public/
+site/resources/
+site/.hugo_build.lock
+site/.generated/
+site/node_modules/
+
+.codex

dagzoo-0.9.7/.importlinter

@@ -0,0 +1,29 @@
+[importlinter]
+root_package = dagzoo
+
+[importlinter:contract:core_product_surface]
+name = dagzoo.core does not depend on product entrypoints
+type = forbidden
+source_modules =
+    dagzoo.core
+forbidden_modules =
+    dagzoo.cli
+    dagzoo.bench
+    dagzoo.diagnostics
+
+[importlinter:contract:library_product_surface]
+name = dagzoo libraries do not depend on product entrypoints
+type = forbidden
+source_modules =
+    dagzoo.functions
+    dagzoo.converters
+    dagzoo.sampling
+    dagzoo.io
+    dagzoo.filtering
+    dagzoo.graph
+    dagzoo.math
+    dagzoo.postprocess
+forbidden_modules =
+    dagzoo.cli
+    dagzoo.bench
+    dagzoo.diagnostics

dagzoo-0.9.7/.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+repos:
+
+- repo: local
+  hooks:
+  - id: ruff-check
+    name: ruff check
+    entry: ./.venv/bin/ruff check
+    language: system
+    types_or: [python, pyi]
+    pass_filenames: true
+  - id: ruff-format
+    name: ruff format
+    entry: ./.venv/bin/ruff format
+    language: system
+    types_or: [python, pyi]
+    pass_filenames: true
+  - id: mypy
+    name: mypy
+    entry: ./.venv/bin/python -m mypy src
+    language: system
+    types_or: [python, pyi]
+    pass_filenames: false
+  - id: mdformat
+    name: mdformat
+    entry: ./.venv/bin/mdformat
+    language: system
+    types: [markdown]
+    exclude: ^(WORKFLOW\.md|docs/transforms.md|site/)
+    pass_filenames: true
+  - id: deptry
+    name: deptry
+    entry: ./.venv/bin/deptry .
+    language: system
+    pass_filenames: false
+    files: ^(pyproject\.toml|src/dagzoo/)
+  - id: release-contract
+    name: release contract
+    entry: ./.venv/bin/python scripts/dev.py contract --source staged
+    language: system
+    pass_filenames: false
+    files: ^(src/dagzoo/|configs/|scripts/devlib/|pyproject\.toml$|CHANGELOG\.md$|\.pre-commit-config\.yaml$)

dagzoo-0.9.7/AGENTS.md

@@ -0,0 +1,12 @@
+# Development Patterns
+
+- Use `.venv/` for commands and tests in this repo.
+- Prefer breaking dependency cycles and centralizing shared wiring in `src/dagzoo/core`; avoid "legacy" pathways, duplicate pathways, and shims. Do not introduce parallel implementations of the same logic in different layers of the codebase.
+- We optimize for iteration speed: internal Python APIs and internal config structure may change without backward-compat guarantees.
+- If CLI flags, persisted metadata schema, or dataset artifact contract changes, treat it as a user-facing break and call it out explicitly.
+- For behavior/schema changes under `src/dagzoo`, bump version in `pyproject.toml` just before merging into main so that the version reflects the latest changes (patch by default; minor for intentionally broad user-facing breaks). Docs/tests-only changes do not require a bump.
+- On every version bump, update `CHANGELOG.md` in the same PR.
+- We prefer shared utility packages over hand-rolled helpers to keep invariants centralized
+- We don’t probe data “YOLO-style”—we validate boundaries or rely on typed SDKs
+- Prior to declaring a branch ready for review, compare branch to main and verify that all intended changes are included and no unintended changes are included
+- Canonical local verification is `./scripts/dev verify quick`; use `./scripts/dev impact` when you need a dependency-aware ripple check before broader refactors