diff --git a/.github/actions/azureml-test/action.yml b/.github/actions/azureml-test/action.yml index 91a437719..7c44abb37 100644 --- a/.github/actions/azureml-test/action.yml +++ b/.github/actions/azureml-test/action.yml @@ -15,9 +15,15 @@ inputs: TEST_KIND: required: true description: Type of test - unit or nightly - AZUREML_TEST_CREDENTIALS: + AZUREML_TEST_UMI_CLIENT_ID: required: true - description: Credentials for AzureML login + description: AzureML User-managed identity client ID + AZUREML_TEST_UMI_TENANT_ID: + required: true + description: AzureML User-managed identity tenant ID + AZUREML_TEST_UMI_SUB_ID: + required: true + description: AzureML User-managed identity subscription ID AZUREML_TEST_SUBID: required: true description: AzureML subscription ID @@ -53,7 +59,9 @@ runs: - name: Log in to Azure uses: azure/login@v2 with: - creds: ${{ inputs.AZUREML_TEST_CREDENTIALS }} + client-id: ${{ inputs.AZUREML_TEST_UMI_CLIENT_ID }} + tenant-id: ${{ inputs.AZUREML_TEST_UMI_TENANT_ID }} + subscription-id: ${{ inputs.AZUREML_TEST_UMI_SUB_ID }} - name: Submit tests to AzureML shell: bash run: | diff --git a/.github/workflows/azureml-cpu-nightly.yml b/.github/workflows/azureml-cpu-nightly.yml index 89fc64757..616707f7f 100644 --- a/.github/workflows/azureml-cpu-nightly.yml +++ b/.github/workflows/azureml-cpu-nightly.yml @@ -64,6 +64,8 @@ jobs: needs: get-test-groups name: ${{ join(matrix.*, ', ') }} runs-on: ubuntu-latest + permissions: + id-token: write # This is required for requesting the JWT strategy: max-parallel: 50 # Usage limits: https://docs.github.com/en/actions/learn-github-actions/usage-limits-billing-and-administration matrix: @@ -79,7 +81,9 @@ jobs: EXP_NAME: recommenders-nightly-${{ matrix.test-group }}-python${{ matrix.python-version }}-${{ github.ref }} ENV_NAME: recommenders-${{ github.sha }}-python${{ matrix.python-version }}${{ contains(matrix.test-group, 'gpu') && '-gpu' || '' }}${{ contains(matrix.test-group, 'spark') && '-spark' || '' }} TEST_KIND: 'nightly' - AZUREML_TEST_CREDENTIALS: ${{ secrets.AZUREML_TEST_CREDENTIALS }} + AZUREML_TEST_UMI_CLIENT_ID: ${{ secrets.AZUREML_TEST_UMI_CLIENT_ID }} + AZUREML_TEST_UMI_TENANT_ID: ${{ secrets.AZUREML_TEST_UMI_TENANT_ID }} + AZUREML_TEST_UMI_SUB_ID: ${{ secrets.AZUREML_TEST_UMI_SUB_ID }} AZUREML_TEST_SUBID: ${{ secrets.AZUREML_TEST_SUBID }} PYTHON_VERSION: ${{ matrix.python-version }} TEST_GROUP: ${{ matrix.test-group }} diff --git a/.github/workflows/azureml-gpu-nightly.yml b/.github/workflows/azureml-gpu-nightly.yml index 16e3e6ed2..23cffda0a 100644 --- a/.github/workflows/azureml-gpu-nightly.yml +++ b/.github/workflows/azureml-gpu-nightly.yml @@ -64,6 +64,8 @@ jobs: needs: get-test-groups name: ${{ join(matrix.*, ', ') }} runs-on: ubuntu-latest + permissions: + id-token: write # This is required for requesting the JWT strategy: max-parallel: 50 # Usage limits: https://docs.github.com/en/actions/learn-github-actions/usage-limits-billing-and-administration matrix: @@ -79,7 +81,9 @@ jobs: EXP_NAME: recommenders-nightly-${{ matrix.test-group }}-python${{ matrix.python-version }}-${{ github.ref }} ENV_NAME: recommenders-${{ github.sha }}-python${{ matrix.python-version }}${{ contains(matrix.test-group, 'gpu') && '-gpu' || '' }}${{ contains(matrix.test-group, 'spark') && '-spark' || '' }} TEST_KIND: 'nightly' - AZUREML_TEST_CREDENTIALS: ${{ secrets.AZUREML_TEST_CREDENTIALS }} + AZUREML_TEST_UMI_CLIENT_ID: ${{ secrets.AZUREML_TEST_UMI_CLIENT_ID }} + AZUREML_TEST_UMI_TENANT_ID: ${{ secrets.AZUREML_TEST_UMI_TENANT_ID }} + AZUREML_TEST_UMI_SUB_ID: ${{ secrets.AZUREML_TEST_UMI_SUB_ID }} AZUREML_TEST_SUBID: ${{ secrets.AZUREML_TEST_SUBID }} PYTHON_VERSION: ${{ matrix.python-version }} TEST_GROUP: ${{ matrix.test-group }} diff --git a/.github/workflows/azureml-release-pipeline.yml b/.github/workflows/azureml-release-pipeline.yml index d9899658e..983cce9db 100644 --- a/.github/workflows/azureml-release-pipeline.yml +++ b/.github/workflows/azureml-release-pipeline.yml @@ -37,7 +37,7 @@ jobs: - name: Setup python uses: actions/setup-python@v5 with: - python-version: "3.8" + python-version: "3.10" - name: Install wheel package run: pip install wheel - name: Create wheel from setup.py diff --git a/.github/workflows/azureml-spark-nightly.yml b/.github/workflows/azureml-spark-nightly.yml index 97789fccf..da508ebe4 100644 --- a/.github/workflows/azureml-spark-nightly.yml +++ b/.github/workflows/azureml-spark-nightly.yml @@ -63,6 +63,8 @@ jobs: needs: get-test-groups name: ${{ join(matrix.*, ', ') }} runs-on: ubuntu-latest + permissions: + id-token: write # This is required for requesting the JWT strategy: max-parallel: 50 # Usage limits: https://docs.github.com/en/actions/learn-github-actions/usage-limits-billing-and-administration matrix: @@ -78,7 +80,9 @@ jobs: EXP_NAME: recommenders-nightly-${{ matrix.test-group }}-python${{ matrix.python-version }}-${{ github.ref }} ENV_NAME: recommenders-${{ github.sha }}-python${{ matrix.python-version }}${{ contains(matrix.test-group, 'gpu') && '-gpu' || '' }}${{ contains(matrix.test-group, 'spark') && '-spark' || '' }} TEST_KIND: 'nightly' - AZUREML_TEST_CREDENTIALS: ${{ secrets.AZUREML_TEST_CREDENTIALS }} + AZUREML_TEST_UMI_CLIENT_ID: ${{ secrets.AZUREML_TEST_UMI_CLIENT_ID }} + AZUREML_TEST_UMI_TENANT_ID: ${{ secrets.AZUREML_TEST_UMI_TENANT_ID }} + AZUREML_TEST_UMI_SUB_ID: ${{ secrets.AZUREML_TEST_UMI_SUB_ID }} AZUREML_TEST_SUBID: ${{ secrets.AZUREML_TEST_SUBID }} PYTHON_VERSION: ${{ matrix.python-version }} TEST_GROUP: ${{ matrix.test-group }} diff --git a/.github/workflows/azureml-unit-tests.yml b/.github/workflows/azureml-unit-tests.yml index ed3b5a98d..0f7ed2a18 100644 --- a/.github/workflows/azureml-unit-tests.yml +++ b/.github/workflows/azureml-unit-tests.yml @@ -53,6 +53,8 @@ jobs: needs: get-test-groups name: ${{ join(matrix.*, ', ') }} runs-on: ubuntu-latest + permissions: + id-token: write # This is required for requesting the JWT strategy: max-parallel: 50 # Usage limits: https://docs.github.com/en/actions/learn-github-actions/usage-limits-billing-and-administration matrix: @@ -68,7 +70,9 @@ jobs: EXP_NAME: recommenders-unit-${{ matrix.test-group }}-python${{ matrix.python-version }}-${{ github.sha }} ENV_NAME: recommenders-${{ github.sha }}-python${{ matrix.python-version }}${{ contains(matrix.test-group, 'gpu') && '-gpu' || '' }}${{ contains(matrix.test-group, 'spark') && '-spark' || '' }} TEST_KIND: 'unit' - AZUREML_TEST_CREDENTIALS: ${{ secrets.AZUREML_TEST_CREDENTIALS }} + AZUREML_TEST_UMI_CLIENT_ID: ${{ secrets.AZUREML_TEST_UMI_CLIENT_ID }} + AZUREML_TEST_UMI_TENANT_ID: ${{ secrets.AZUREML_TEST_UMI_TENANT_ID }} + AZUREML_TEST_UMI_SUB_ID: ${{ secrets.AZUREML_TEST_UMI_SUB_ID }} AZUREML_TEST_SUBID: ${{ secrets.AZUREML_TEST_SUBID }} PYTHON_VERSION: ${{ matrix.python-version }} TEST_GROUP: ${{ matrix.test-group }} diff --git a/setup.py b/setup.py index 03df519ed..41b4c8aed 100644 --- a/setup.py +++ b/setup.py @@ -36,15 +36,15 @@ "nltk>=3.8.1,<4", # requires tqdm "notebook>=6.5.5,<8", # requires ipykernel, jinja2, jupyter, nbconvert, nbformat, packaging, requests "numba>=0.57.0,<1", - "numpy<2.0.0", # FIXME: Remove numpy<2.0.0 once cornac release a version newer than 2.2.1 that resolve ImportError: numpy.core.multiarray failed to import. "pandas>2.0.0,<3.0.0", # requires numpy "pandera[strategies]>=0.6.5,<0.18;python_version<='3.8'", # For generating fake datasets "pandera[strategies]>=0.15.0;python_version>='3.9'", "retrying>=1.3.4,<2", "scikit-learn>=1.2.0,<2", # requires scipy, and introduce breaking change affects feature_extraction.text.TfidfVectorizer.min_df "scikit-surprise>=1.1.3", - "scipy>=1.10.1,<=1.13.1", # FIXME: Remove scipy<=1.13.1 once cornac release a version newer than 2.2.1. See #2128 "seaborn>=0.13.0,<1", # requires matplotlib, packaging + "statsmodels<=0.14.1;python_version<='3.8'", + "statsmodels>=0.14.4;python_version>='3.9'", "transformers>=4.27.0,<5", # requires packaging, pyyaml, requests, tqdm ] @@ -52,7 +52,9 @@ extras_require = { "gpu": [ "fastai>=2.7.11,<3", + "numpy<1.25.0;python_version<='3.8'", "nvidia-ml-py>=11.525.84", + "spacy<=3.7.5;python_version<='3.8'", "tensorflow>=2.8.4,!=2.9.0.*,!=2.9.1,!=2.9.2,!=2.10.0.*,<2.16", # Fixed TF due to constant security problems and breaking changes #2073 "tf-slim>=1.1.0", # No python_requires in its setup.py "torch>=2.0.1,<3", diff --git a/tests/README.md b/tests/README.md index 4958cedd2..893df94c2 100644 --- a/tests/README.md +++ b/tests/README.md @@ -216,30 +216,46 @@ Then, follow the steps below to create the AzureML infrastructure: - Name: `azureml-test-workspace` - Resource group: `recommenders_project_resources` - Location: *Make sure you have enough quota in the location you choose* -2. Create two new clusters: `cpu-cluster` and `gpu-cluster`. Go to compute, then compute cluster, then new. +1. Create two new clusters: `cpu-cluster` and `gpu-cluster`. Go to compute, then compute cluster, then new. - Select the CPU VM base. Anything above 64GB of RAM, and 8 cores should be fine. - Select the GPU VM base. Anything above 56GB of RAM, and 6 cores, and an NVIDIA K80 should be fine. -3. Add the subscription ID to GitHub action secrets [here](https://github.com/recommenders-team/recommenders/settings/secrets/actions). Create a new repository secret called `AZUREML_TEST_SUBID` and add the subscription ID as the value. -4. Make sure you have installed [Azure CLI](https://learn.microsoft.com/en-us/cli/azure/install-azure-cli), and that you are logged in: `az login`. -5. Select your subscription: `az account set -s $AZURE_SUBSCRIPTION_ID`. -6. Create a Service Principal: `az ad sp create-for-rbac --name $SERVICE_PRINCIPAL_NAME --role "AzureML Compute Operator" --scopes /subscriptions/$AZURE_SUBSCRIPTION_ID --json-auth`. This will output a JSON blob with the credentials of the Service Principal: - ``` - { - "clientId": "XXXXXXXXXXXXXXXXXXXXX", - "clientSecret": "XXXXXXXXXXXXXXXXXXXXX", - "subscriptionId": "XXXXXXXXXXXXXXXXXXXXX", - "tenantId": "XXXXXXXXXXXXXXXXXXXXX", - "activeDirectoryEndpointUrl": "https://login.microsoftonline.com", - "resourceManagerEndpointUrl": "https://management.azure.com/", - "activeDirectoryGraphResourceId": "https://graph.windows.net/", - "sqlManagementEndpointUrl": "https://management.core.windows.net:8443/", - "galleryEndpointUrl": "https://gallery.azure.com/", - "managementEndpointUrl": "https://management.core.windows.net/" - } - ``` -7. Assign AzureML Data Scientist role: `az role assignment create --assignee $SERVICE_PRINCIPAL_NAME --role "AzureML Data Scientist" --scope /subscriptions/$AZURE_SUBSCRIPTION_ID` -8. Assign Reader role: `az role assignment create --assignee $SERVICE_PRINCIPAL_NAME --role "Reader" --scope /subscriptions/$AZURE_SUBSCRIPTION_ID` -9. Add the output as github's action secret `AZUREML_TEST_CREDENTIALS` under repository's **Settings > Security > Secrets and variables > Actions**. +1. Add the subscription ID to GitHub action secrets + [here](https://github.com/recommenders-team/recommenders/settings/secrets/actions). + * Create a new repository secret called `AZUREML_TEST_SUBID` and + add the subscription ID as the value. +1. Set up [login with OpenID Connect + (OIDC)](https://github.com/marketplace/actions/azure-login#login-with-openid-connect-oidc-recommended) + for GitHub Actions. + 1. Create a user-assigned managed identity (UMI) and assign the + following 3 roles of the AzureML workspace created above to the + UMI (See [Create a user-assigned managed + identity](https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/how-manage-user-assigned-managed-identities?pivots=identity-mi-methods-azp#create-a-user-assigned-managed-identity)): + * AzureML Compute Operator + * AzureML Data Scientist + * Reader + 1. [Create a federated identiy credential on the + UMI](https://learn.microsoft.com/en-us/entra/workload-id/workload-identity-federation-create-trust-user-assigned-managed-identity?pivots=identity-wif-mi-methods-azp#github-actions-deploying-azure-resources) + with the following settings: + * Name: A unique name for the federated identity credential + within your application. + * Issuer: Set to `https://token.actions.githubusercontent.com` + for GitHub Actions. + * Subject: The subject claim format, e.g., + `repo:recommenders-team/recommenders:ref:refs/heads/`: + + `repo:recommenders-team/recommenders:pull_request` + + `repo:recommenders-team/recommenders:ref:refs/heads/staging` + + `repo:recommenders-team/recommenders:ref:refs/heads/main` + * Description: (Optional) A description of the credential. + * Audiences: Specifies who can use this credential; for GitHub + Actions, use `api://AzureADTokenExchange`. +1. Create 3 Actions secrets + * `AZUREML_TEST_UMI_TENANT_ID` + * `AZUREML_TEST_UMI_SUB_ID` + * `AZUREML_TEST_UMI_CLIENT_ID` + + and use the UMI's tenant ID, subscription ID and client ID as the + values of the secrets, respectively, under the repository's + **Settings > Security > Secrets and variables > Actions**. ## How to execute tests in your local environment diff --git a/tests/ci/azureml_tests/post_pytest.py b/tests/ci/azureml_tests/post_pytest.py index b457e709d..26472ea46 100644 --- a/tests/ci/azureml_tests/post_pytest.py +++ b/tests/ci/azureml_tests/post_pytest.py @@ -89,8 +89,12 @@ def parse_args(): run_id=run.info.run_id, dst_path=args.log_dir, ) - log_path = pathlib.Path("user_logs/std_log.txt") - with open(pathlib.Path(args.log_dir) / log_path, "r") as file: - print(f"\nDumping logs in {log_path}") - print("=====================================") - print(file.read()) + log_path = next( + (path for path in pathlib.Path(args.log_dir).rglob("std_log.txt")), + None + ) + if log_path is not None: + with open(log_path, "r") as file: + print(f"\nDumping logs in {log_path}") + print("=====================================") + print(file.read())