Merge branch 'develop' of github.com:oracle/accelerated-data-science into ODSC-29065/md_opctl

Author: Ziqun Ye

.coveragerc

@@ -1,42 +1,61 @@
-[paths]
-source =
-    ads/
-
 [run]
-branch = true
-parallel = true
-source =
-    ads
 omit =
-    docs/*
-    tests/*
+    **/__init__.py
+    **/__main__.py
+    **/_imports.py
+    **/cli.py
+    **/constants.py
+    **/extension.py
+    **/score.py
+    */.*
+    /private/*
+    /tmp/*
     ads/automl/*
+    ads/common/analyzer.py
     ads/common/artifact/*
+    ads/common/function/*
+    ads/dataflow/*
+    ads/dataset/dask_series.py
+    ads/dataset/factory.py
     ads/environment/*
     ads/experiments/*
+    ads/explanations/*
     ads/templates/*
-    */constants.py
-    */_imports.py
-    */__init__.py
-    */__main__.py
-    */.*
+    ads/type_discovery/*
+    docs/*
+    tests/*
 
 [report]
 exclude_lines =
     pragma: no cover
     def __repr__
     if __name__ == .__main__.:
+    @(abc\.)?abstractmethod
+    raise AssertionError
+    raise NotImplementedError
 omit =
+    **/__init__.py
+    **/__main__.py
+    **/_imports.py
+    **/cli.py
+    **/constants.py
+    **/extension.py
+    **/score.py
+    */.*
+    /private/*
+    /tmp/*
     ads/automl/*
+    ads/common/analyzer.py
     ads/common/artifact/*
+    ads/common/function/*
+    ads/dataflow/*
+    ads/dataset/dask_series.py
+    ads/dataset/factory.py
     ads/environment/*
     ads/experiments/*
+    ads/explanations/*
     ads/templates/*
-    */constants.py
-    */_imports.py
-    */__init__.py
-    */__main__.py
-    __init.py__
+    ads/type_discovery/*
 show_missing = true
 skip_empty = true
 precision = 2

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,58 @@
+name: Feature Request
+description: Feature and enhancement proposals in oracle-ads library
+title: "[FR]: "
+labels: [Task, Backlog]
+assignees:
+  - octocat
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Before proceeding, please review the [Contributing to this repository](https://github.com/oracle/accelerated-data-science/blob/main/CONTRIBUTING.md) and the [Code of Conduct](https://github.com/oracle/.github/blob/main/CODE_OF_CONDUCT.md).
+        
+        ---
+        
+        Thank you for submitting a feature request.
+  - type: dropdown
+    id: contribution
+    attributes:
+      label: Willingness to contribute
+      description: Would you or another member of your organization be willing to contribute an implementation of this feature?
+      options:
+        - Yes. I can contribute this feature independently.
+        - Yes. I would be willing to contribute this feature with guidance from the oracle-ads team.
+        - No. I cannot contribute this feature at this time.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Proposal Summary
+      description: |
+        In a few sentences, provide a clear, high-level description of the feature request
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Motivation
+      description: |
+        - What is the use case for this feature?
+        - Why is this use case valuable to support for OCI DataScience users in general?
+        - Why is this use case valuable to support for your project(s) or organization?
+        - Why is it currently difficult to achieve this use case?
+      value: |
+        > #### What is the use case for this feature?
+
+        > #### Why is this use case valuable to support for OCI DataScience users in general?
+
+        > #### Why is this use case valuable to support for your project(s) or organization?
+
+        > #### Why is it currently difficult to achieve this use case?
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Details
+      description: |
+        Use this section to include any additional information about the feature. If you have a proposal for how to implement this feature, please include it here. For implementation guidelines, please refer to the [Contributing to this repository](https://github.com/oracle/accelerated-data-science/blob/main/CONTRIBUTING.md).
+    validations:
+      required: false

.github/workflows/publish-to-pypi.yml

@@ -0,0 +1,42 @@
+name: "[DO NOT TRIGGER] Publish to PyPI"
+
+# To run this workflow manually from the Actions tab
+on: workflow_dispatch
+
+jobs:
+  build-n-publish:
+    name: Build and publish Python 🐍 distribution 📦 to PyPI
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.x"
+      - name: Build distribution 📦
+        run: |
+          pip install wheel
+          make dist
+      - name: Validate
+        run: |
+          pip install dist/*.whl
+          python -c "import ads;"
+## To run publish to test PyPI secret with token needs to be added,
+##    this one GH_ADS_TESTPYPI_TOKEN - removed after initial test.
+## Project name also needed to be updated in setup.py - setup(name="test_oracle_ads", ...),
+##    regular name is occupied by former developer and can't be used for testing
+#      - name: Publish distribution 📦 to Test PyPI
+#        env:
+#          TWINE_USERNAME: __token__
+#          TWINE_PASSWORD: ${{ secrets.GH_ADS_TESTPYPI_TOKEN }}
+#        run: |
+#          pip install twine
+#          twine upload -r testpypi dist/* -u $TWINE_USERNAME -p $TWINE_PASSWORD
+      - name: Publish distribution 📦 to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.GH_ADS_PYPI_TOKEN }}
+        run: |
+          pip install twine
+          twine upload dist/* -u $TWINE_USERNAME -p $TWINE_PASSWORD

.github/workflows/run-unittests-default_setup.yml

@@ -29,7 +29,7 @@ env:
 
 jobs:
   test:
-    name: python ${{ matrix.python-version }}, tests/unitary/default_setup
+    name: python ${{ matrix.python-version }}, default_setup
     runs-on: ubuntu-latest
     timeout-minutes: 20
 

.github/workflows/run-unittests.yml

@@ -22,14 +22,15 @@ concurrency:
 
 permissions:
   contents: read
+  pull-requests: write
 
 # hack for https://github.com/actions/cache/issues/810#issuecomment-1222550359
 env:
   SEGMENT_DOWNLOAD_TIMEOUT_MINS: 5
 
 jobs:
   test:
-    name: python ${{ matrix.python-version }}, ${{ matrix.test-path }}, ignore ${{ matrix.ignore-path }}
+    name: python ${{ matrix.python-version }}, ${{ matrix.name }}
     runs-on: ubuntu-latest
     timeout-minutes: 90
 
@@ -41,6 +42,11 @@ jobs:
         include:
           - test-path: "tests/unitary"
             ignore-path: "tests/unitary/with_extras/model"
+            name: "unitary"
+          - test-path: "tests/unitary/with_extras/model"
+            name: "model"
+          - python-version: "3.8"
+            cov-reports: --cov=ads --cov-report=xml --cov-report=html
 
     steps:
       - uses: actions/checkout@v3
@@ -82,10 +88,11 @@ jobs:
         shell: bash
         run: |
           set -x # print commands that are executed
+          
           sudo apt-get install libkrb5-dev graphviz
           $CONDA/bin/conda init
           source /home/runner/.bashrc
-          pip install setuptools
+          
           pip install -r dev-requirements.txt
 
       - name: "Run unitary tests folder with maximum ADS dependencies"
@@ -95,16 +102,123 @@ jobs:
           NB_SESSION_COMPARTMENT_OCID: ocid1.compartment.oc1.<unique_ocid>
           CONDA_PREFIX: /usr/share/miniconda
         run: |
+          set -x # print commands that are executed
+          
+          # Setup project and tests folder for cov reports to not be overwritten by another parallel step
+          if [[ ! -z "${{ matrix.cov-reports }}" ]]; then
+            mkdir -p cov-${{ matrix.name }}
+            cd cov-${{ matrix.name }}
+            ln -s ../tests tests
+            ln -s ../ads ads
+            ln -s ../.coveragerc .coveragerc
+          fi
+          
+          # Run tests
           python -m pytest -v -p no:warnings --durations=5 \
+          -n auto --dist loadfile ${{ matrix.cov-reports }} \
           ${{ matrix.test-path }} \
-          --ignore "${{ matrix.ignore-path }}" \
-          --cov --cov-append --cov-report=html
+          --ignore "${{ matrix.ignore-path }}"
+
+      - name: "Save coverage files"
+        uses: actions/upload-artifact@v3
+        if: ${{ matrix.cov-reports }}
+        with:
+          name: cov-reports-${{ matrix.name }}
+          path: |
+            cov-${{ matrix.name }}/htmlcov/
+            cov-${{ matrix.name }}/.coverage
+            cov-${{ matrix.name }}/coverage.xml
+
+  coverage-report:
+    name: "Coverage report"
+    runs-on: ubuntu-latest
+    continue-on-error: true
+    needs: test
+    if: ${{ success() }} && ${{ github.event.issue.pull_request }}
+    env:
+      COMPARE_BRANCH: develop
+
+    steps:
+      - name: "Checkout current branch"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: "Download coverage files"
+        uses: actions/download-artifact@v3
+      - name: "Calculate overall coverage"
+        run: |
+          set -x # print commands that are executed
+          
+          # Prepare default cov body text 
+          COV_BODY_INTRO="📌 Overall coverage:\n\n"
+          echo COV_BODY="$COV_BODY_INTRO No success to gather report. 😿" >> $GITHUB_ENV
+          
+          # Combine coverage files
+          pip install coverage
+          coverage combine cov-reports-unitary/.coverage cov-reports-model/.coverage
+          
+          # Make html report
+          coverage html
+          
+          # Calculate overall coverage and update body message
+          COV=$(grep -E 'pc_cov' htmlcov/index.html | cut -d'>' -f 2 | cut -d'%' -f 1)
+          if [[ ! -z $COV ]]; then 
+            if [[ $COV < 50 ]]; then COLOR=red; elif [[ $COV < 80 ]]; then COLOR=yellow; else COLOR=green; fi
+            echo COV_BODY="$COV_BODY_INTRO ![Coverage-$COV%](https://img.shields.io/badge/coverage-$COV%25-$COLOR)" >> $GITHUB_ENV
+          fi
+
+      - name: "Calculate coverage diff"
+        if: always()
+        run: |
+          set -x # print commands that are executed
+          
+          # Prepare default diff body text 
+          DIFF_BODY_INTRO="📌 Cov diff with **${{ env.COMPARE_BRANCH }}**:\n\n"
+          echo DIFF_BODY="$BODY_INTRO No success to gather report. 😿" >> $GITHUB_ENV
+          
+          # Prepare file paths to coverage xml files
+          # Filenames taken from job.test last step with name - "Save coverage files"
+          FILE1="cov-reports-unitary/coverage.xml"; [[ ! -f $FILE1 ]] && FILE1="" 
+          FILE2="cov-reports-model/coverage.xml"; [[ ! -f $FILE2 ]] && FILE2=""
+          echo "FILE1=$FILE1" >> $GITHUB_ENV
+          echo "FILE2=$FILE2" >> $GITHUB_ENV
+          
+          # Calculate coverage diff and update body message
+          pip install diff_cover
+          diff-cover $FILE1 $FILE2 --compare-branch=origin/${{ env.COMPARE_BRANCH }} 
+          DIFF=$(diff-cover $FILE1 $FILE2 \
+            --compare-branch=origin/${{ env.COMPARE_BRANCH }} | grep Coverage: | cut -d' ' -f 2 | cut -d'%' -f 1)
+          if [[ -z $DIFF ]]; then 
+            DIFF_INFO=$(diff-cover $FILE1 $FILE2 \
+              --compare-branch=origin/${{ env.COMPARE_BRANCH }}  | grep "No lines");
+            echo DIFF_BODY="$DIFF_BODY_INTRO $DIFF_INFO">> $GITHUB_ENV
+          else
+            if [[ $DIFF < 50 ]]; then COLOR=red; elif [[ $DIFF < 80 ]]; then COLOR=yellow; else COLOR=green; fi
+            echo DIFF_BODY="$DIFF_BODY_INTRO ![Coverage-$DIFF%](https://img.shields.io/badge/coverage-$DIFF%25-$COLOR)" >> $GITHUB_ENV
+          fi
 
-#       Uploading test artifacts
-#       https://docs.github.com/en/actions/using-workflows/storing-workflow-data-as-artifacts#uploading-build-and-test-artifacts
-      - name: "Save html coverage report"
+      - name: "Add comment with cov diff to PR"
+        uses: actions/github-script@v6
+        if: always()
+        with:
+          github-token: ${{ github.token }}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: '${{ env.DIFF_BODY }}\n\n${{ env.COV_BODY }}'
+            })
+      - name: "Generate html difference report"
+        run: |
+          diff-cover ${{ env.FILE1 }} ${{ env.FILE2 }} \
+          --compare-branch=origin/${{ env.COMPARE_BRANCH }} \
+          --html-report=cov-diff.html
+      - name: "Save coverage difference report"
         uses: actions/upload-artifact@v3
         with:
-          name: code-coverage-report
-          path: htmlcov/
+          name: cov-html-reports
+          path: |
+            cov-diff.html
+            htmlcov/
           retention-days: 10

ads/bds/auth.py

@@ -14,7 +14,7 @@
 KRB5_CONFIG = "KRB5_CONFIG"
 
 
-class KRB5KinitError(Exception):
+class KRB5KinitError(Exception):   # pragma: no cover
     """KRB5KinitError class when kinit -kt command failed to generate cached ticket with the keytab file and the krb5 config file."""
 
     pass

ads/catalog/model.py

@@ -82,11 +82,11 @@
 _WORK_REQUEST_INTERVAL_IN_SEC = 3
 
 
-class ModelWithActiveDeploymentError(Exception):
+class ModelWithActiveDeploymentError(Exception):   # pragma: no cover
     pass
 
 
-class ModelArtifactSizeError(Exception):
+class ModelArtifactSizeError(Exception):   # pragma: no cover
     def __init__(self, max_artifact_size: str):
         super().__init__(
             f"The model artifacts size is greater than `{max_artifact_size}`. "

ads/common/decorator/deprecate.py

@@ -9,7 +9,7 @@
 from functools import wraps
 
 
-class NotSupportedError(Exception):
+class NotSupportedError(Exception):   # pragma: no cover
     pass