Skip to content

Supporting v2-datasets loading outside running a pipeline e.g. when using kedro ipython #141

Supporting v2-datasets loading outside running a pipeline e.g. when using kedro ipython

Supporting v2-datasets loading outside running a pipeline e.g. when using kedro ipython #141

name: "Test and Publish"
on:
push:
branches:
- master
- develop
paths-ignore:
- "docs/**"
pull_request:
branches:
- master
- develop
paths-ignore:
- "docs/**"
jobs:
unit_tests:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [ '3.8', '3.9', '3.10']
steps:
- uses: actions/checkout@v2
- name: Setup python ${{ matrix.python-version }}
uses: actions/[email protected]
with:
python-version: ${{ matrix.python-version }}
- name: Setup poetry
run: |
python -V
python -m pip install poetry
- name: Check pre-commit status
run: |
poetry install -v
poetry run pre-commit run --all-files
- name: Test with tox
run: |
pip install tox-pip-version tox-gh-actions "tox<4.0.0"
tox -v
- name: Store coverage reports
uses: actions/upload-artifact@v3
with:
name: coverage-${{ matrix.python-version }}
path: coverage.xml
if-no-files-found: error
sonarcloud:
runs-on: ubuntu-latest
needs: unit_tests
steps:
- uses: actions/checkout@v2
with:
fetch-depth: 0
- uses: actions/download-artifact@v3
with:
name: coverage-3.9
path: .
- name: SonarCloud Scan
uses: sonarsource/sonarcloud-github-action@master
with:
projectBaseDir: ${{ github.workspace }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
SONAR_TOKEN: ${{ secrets.SONARCLOUD_TOKEN }}
codeql:
runs-on: ubuntu-latest
needs: unit_tests
permissions:
actions: read
contents: read
security-events: write
steps:
- name: Checkout repository
uses: actions/checkout@v3
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v2
with:
languages: python
- name: Autobuild
uses: github/codeql-action/autobuild@v2
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v2
### PROJECT SPECIFIC CONFIGURATION HERE
e2e_tests:
if: (github.event.pull_request.head.repo.full_name == github.repository || github.event.pull_request == null)
needs: [unit_tests, sonarcloud]
runs-on: ubuntu-latest
strategy:
matrix:
e2e_config: ["e2e", "e2e_pipeline_data_passing"]
steps:
- uses: actions/checkout@v2
- name: Setup python
uses: actions/[email protected]
with:
python-version: "3.10"
- name: Setup poetry
run: |
python -V
python -m pip install poetry
- name: Build the package
run: |
poetry build -f sdist
- name: Initialize starter project
run: |
pip install $(find "./dist" -name "*.tar.gz")
kedro new --starter spaceflights --config tests/conf/${{ matrix.e2e_config }}/starter-config.yml --verbose
- name: Install starter requirements
working-directory: ./spaceflights
run: |
find "../dist" -name "*.tar.gz" | xargs -I@ cp @ kedro-azureml.tar.gz
echo -e "\n./kedro-azureml.tar.gz\n" >> src/requirements.txt
echo -e "kedro-docker\n" >> src/requirements.txt
echo -e "openpyxl\n" >> src/requirements.txt # temp fix for kedro-datasets issues with optional packages
sed -i '/kedro-telemetry/d' src/requirements.txt
echo $(cat src/requirements.txt)
pip install -r src/requirements.txt
- name: Update starter configs
working-directory: ./spaceflights
run: |
kedro docker init
sed -i 's/\(COPY src\/requirements.txt.*\)$/\1\nCOPY kedro-azureml.tar.gz ./g' Dockerfile
cat Dockerfile
echo "!data/01_raw" >> .dockerignore
rm conf/base/catalog.yml
cp ../tests/conf/${{ matrix.e2e_config }}/catalog.yml conf/base/catalog.yml
cp ../tests/conf/${{ matrix.e2e_config }}/azureml.yml conf/base/azureml.yml
sed -i 's/{container_registry}/${{ secrets.REGISTRY_LOGIN_SERVER }}/g' conf/base/azureml.yml
sed -i 's/{image_tag}/${{ matrix.e2e_config }}/g' conf/base/azureml.yml
cat conf/base/azureml.yml
- name: Login via Azure CLI
uses: azure/login@v1
with:
creds: ${{ secrets.AZURE_CREDENTIALS }}
- name: Login to acr.io
uses: azure/docker-login@v1
with:
login-server: ${{ secrets.REGISTRY_LOGIN_SERVER }}
username: ${{ secrets.AZURE_CLIENT_ID }}
password: ${{ secrets.AZURE_CLIENT_SECRET }}
- name: Build and push docker image
working-directory: ./spaceflights
run: |
docker pull ${{ secrets.REGISTRY_LOGIN_SERVER }}/kedro-azureml-e2e:${{ matrix.e2e_config }} || true
docker build --build-arg BASE_IMAGE=python:3.10-buster -t ${{ secrets.REGISTRY_LOGIN_SERVER }}/kedro-azureml-e2e:${{ matrix.e2e_config }} --cache-from=${{ secrets.REGISTRY_LOGIN_SERVER }}/kedro-azureml-e2e:${{ matrix.e2e_config }} .
docker push ${{ secrets.REGISTRY_LOGIN_SERVER }}/kedro-azureml-e2e:${{ matrix.e2e_config }}
- name: Run on Azure ML Pipelines
working-directory: ./spaceflights
env:
AZURE_STORAGE_ACCOUNT_KEY: ${{ secrets.AZURE_STORAGE_ACCOUNT_KEY }}
AZURE_SUBSCRIPTION_ID: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
AZURE_TENANT_ID: ${{ secrets.AZURE_TENANT_ID }}
AZURE_CLIENT_SECRET: ${{ secrets.AZURE_CLIENT_SECRET }}
AZURE_CLIENT_ID: ${{ secrets.AZURE_CLIENT_ID }}
run: |
kedro azureml run --wait-for-completion --env-var 'GETINDATA=ROCKS!'
publish:
# only run on push to master
if: github.event.pull_request == null && github.ref == 'refs/heads/master'
needs: [e2e_tests, codeql]
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [ 3.8 ]
env:
PYTHON_PACKAGE: kedro_azureml
steps:
- name: Checkout the repo
uses: actions/checkout@v2
with:
fetch-depth: 0 # necessary to enable merging, all the history is needed
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v1
with:
python-version: ${{ matrix.python-version }}
- name: Build package dist from source # A better way will be : https://packaging.python.org/guides/publishing-package-distribution-releases-using-github-actions-ci-cd-workflows/ but pep 517 is still marked as experimental
run: |
pip install poetry
poetry build
- name: Merge back to develop # we have to set the config first on a fresh machine
run: |
git config user.name github-actions
git config user.email [email protected]
git checkout -B develop --track origin/develop
git merge master
git push
- name: Set dynamically package version as output variable # see https://github.com/actions/create-release/issues/39
# see https://docs.github.com/en/free-pro-team@latest/actions/reference/workflow-commands-for-github-actions#setting-an-environment-variable
id: set_package_version
run: |
echo "::set-output name=PACKAGE_VERSION::$(cat $PYTHON_PACKAGE/__init__.py | grep -Po '\d+\.\d+\.\d+')"
- name: Create temporary file with the body content for the release
run: |
grep -Poz "## \[${{steps.set_package_version.outputs.PACKAGE_VERSION}}] - \d{4}-\d{2}-\d{2}[\S\s]+?(?=## \[\d+\.\d+\.\d+\]|\[.+\]:)" CHANGELOG.md > release_body.md
- name: Create Release # https://github.com/actions/create-release
id: create_release
uses: actions/[email protected]
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # This token is provided by Actions, you do not need to create your own token
with:
tag_name: ${{ steps.set_package_version.outputs.PACKAGE_VERSION }}
release_name: Release ${{ steps.set_package_version.outputs.PACKAGE_VERSION }}
body_path: ./release_body.md
draft: false
prerelease: false
- name: Rollback Release in case of run failure
if: failure() && steps.create_release.outputs.id != ''
uses: author/action-rollback@stable
with:
# Using a known release ID
release_id: ${{ steps.create_release.outputs.id }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Publish distribution to PyPI # official action from python maintainers
uses: pypa/gh-action-pypi-publish@master
with:
user: __token__
password: ${{ secrets.PYPI_PASSWORD }}
verbose: true # trace if the upload fails