OSSEVALML-80 Python 3.10 audit (#3609)

* OSSEVALML-80_python-3-10

* OSSEVALML-80 Added Dockerfile, .dockerignore

* OSSEVALML-80 small update to Dockerfile

* OSSEVALML-80 release notes

* OSSEVALML-80 updated release notes with PR

* OSSEVALML-80 format fix

* OSSEVALML-80 updated release notes

* OSSEVALML-80 update install.md
- Dockerfile.arm reference for M1

* Lint.

Co-authored-by: Karsten Chu <[email protected]>
Co-authored-by: chukarsten <[email protected]>

Author: cp2boston

.dockerignore

@@ -0,0 +1,19 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env
+pip-log.txt
+pip-delete-this-directory.txt
+.tox
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.mypy_cache
+.pytest_cache
+.hypothesis

Dockerfile.arm

@@ -0,0 +1,32 @@
+# Dockerfile for creating an image for testing python versions
+#
+# Notes:
+# - this is not an optimized Dockerfile
+# - it was built to provide a clean environment for running
+#   tests on a mac M1, but could probably work on an older mac as well
+# - when running the tests, the makefile never exits at the end.  For now,
+#   just kill the container
+# Build: docker build --rm -t evalml_test . -f Dockerfile.arm
+# Test: docker run --rm -it evalml_test make test
+ARG VERSION=3.10-buster
+FROM --platform=linux/x86_64 python:$VERSION
+
+ARG DOCKER_ARM=1
+ARG TIMEOUT=1200
+
+RUN apt-get update && apt-get install -y git graphviz && rm -rf /var/lib/apt/lists/*
+
+# Referenced in test_gen_utils.py to create a fixture, limiting chromium to a
+# single process.  This is needed for kaleido in a container on an M1
+ENV DOCKER_ARM=$DOCKER_ARM
+
+# Set the test timeout
+ENV TIMEOUT=$TIMEOUT
+
+WORKDIR /workspace
+
+COPY . .
+
+RUN make installdeps-dev && make installdeps-prophet
+
+CMD ['bin/bash']

Makefile

@@ -1,3 +1,5 @@
+TIMEOUT ?= 300
+
 .PHONY: clean
 clean:
 	find . -name '*.pyo' -delete
@@ -24,44 +26,44 @@ lint-fix:
 
 .PHONY: test
 test:
-	pytest evalml/ --doctest-modules --doctest-continue-on-failure  --timeout 300
+	pytest evalml/ --doctest-modules --doctest-continue-on-failure  --timeout $(TIMEOUT)
 
 .PHONY: test-no-parallel
 test-no-parallel:
-	pytest evalml/ --doctest-modules --doctest-continue-on-failure --ignore=evalml/tests/automl_tests/parallel_tests  --timeout 300
+	pytest evalml/ --doctest-modules --doctest-continue-on-failure --ignore=evalml/tests/automl_tests/parallel_tests  --timeout $(TIMEOUT)
 
 .PHONY: test-parallel
 test-parallel:
-	pytest evalml/tests/automl_tests/parallel_tests/ --timeout 300 --durations 0
+	pytest evalml/tests/automl_tests/parallel_tests/ --timeout $(TIMEOUT) --durations 0
 
 .PHONY: doctests
 doctests:
 	pytest evalml --ignore evalml/tests -n 2 --durations 0 --doctest-modules --doctest-continue-on-failure
 
 .PHONY: git-test-parallel
 git-test-parallel:
-	pytest evalml/tests/automl_tests/parallel_tests/ -n 1 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-parallel-junit.xml --timeout 300 --durations 0
+	pytest evalml/tests/automl_tests/parallel_tests/ -n 1 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-parallel-junit.xml --timeout $(TIMEOUT) --durations 0
 
 .PHONY: git-test-automl
 git-test-automl:
-	pytest evalml/tests/automl_tests evalml/tests/tuner_tests -n 2 --ignore=evalml/tests/automl_tests/parallel_tests --durations 0 --timeout 300 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-automl-junit.xml
+	pytest evalml/tests/automl_tests evalml/tests/tuner_tests -n 2 --ignore=evalml/tests/automl_tests/parallel_tests --durations 0 --timeout $(TIMEOUT) --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-automl-junit.xml
 
 .PHONY: git-test-modelunderstanding
 git-test-modelunderstanding:
-	pytest evalml/tests/model_understanding_tests -n 2 --durations 0 --timeout 300 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-modelunderstanding-junit.xml
+	pytest evalml/tests/model_understanding_tests -n 2 --durations 0 --timeout $(TIMEOUT) --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-modelunderstanding-junit.xml
 
 .PHONY: git-test-other
 git-test-other:
-	pytest evalml/tests --ignore evalml/tests/automl_tests/ --ignore evalml/tests/tuner_tests/ --ignore evalml/tests/model_understanding_tests/ --ignore evalml/tests/pipeline_tests/ --ignore evalml/tests/utils_tests/ --ignore evalml/tests/component_tests/test_prophet_regressor.py --ignore evalml/tests/component_tests/test_components.py --ignore evalml/tests/component_tests/test_utils.py --ignore evalml/tests/integration_tests/ -n 2 --durations 0 --timeout 300 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-other-junit.xml
+	pytest evalml/tests --ignore evalml/tests/automl_tests/ --ignore evalml/tests/tuner_tests/ --ignore evalml/tests/model_understanding_tests/ --ignore evalml/tests/pipeline_tests/ --ignore evalml/tests/utils_tests/ --ignore evalml/tests/component_tests/test_prophet_regressor.py --ignore evalml/tests/component_tests/test_components.py --ignore evalml/tests/component_tests/test_utils.py --ignore evalml/tests/integration_tests/ -n 2 --durations 0 --timeout $(TIMEOUT) --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-other-junit.xml
 	make doctests
 
 .PHONY: git-test-prophet
 git-test-prophet:
-	pytest evalml/tests/component_tests/test_prophet_regressor.py evalml/tests/component_tests/test_components.py evalml/tests/component_tests/test_utils.py evalml/tests/pipeline_tests/ evalml/tests/utils_tests/ -n 2 --durations 0 --timeout 300 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-prophet-junit.xml
+	pytest evalml/tests/component_tests/test_prophet_regressor.py evalml/tests/component_tests/test_components.py evalml/tests/component_tests/test_utils.py evalml/tests/pipeline_tests/ evalml/tests/utils_tests/ -n 2 --durations 0 --timeout $(TIMEOUT) --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-prophet-junit.xml
 
 .PHONY: git-test-integration
 git-test-integration:
-	pytest evalml/tests/integration_tests -n 2 --durations 0 --timeout 300 --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-integration-junit.xml
+	pytest evalml/tests/integration_tests -n 2 --durations 0 --timeout $(TIMEOUT) --cov=evalml --cov-config=pyproject.toml --junitxml=test-reports/git-test-integration-junit.xml
 
 
 .PHONY: installdeps

docs/source/install.md

@@ -93,7 +93,7 @@ $ conda install -c conda-forge alteryx-open-src-update-checker
 ```
 ````
 
-## Time Series support with Facebook's Prophet 
+## Time Series support with Facebook's Prophet
 
 To support the `Prophet` time series estimator, be sure to install it as an extra requirement. Please note that this may take a few minutes.
 Prophet is currently only supported via pip installation in EvalML for Mac with CmdStan as a backend.
@@ -152,8 +152,10 @@ brew install graphviz
 
 Not all of EvalML's dependencies support Apple's new M1 chip. For this reason, `pip` or `conda` installing EvalML will
 fail. The core set of EvalML dependencies can be installed in the M1 chip, so we recommend you install EvalML with core
-dependencies. 
+dependencies.
 
 Alternatively, there is experimental support for M1 chips with the Rosetta terminal. After setting up a Rosetta terminal, you should be able to `pip` or `conda` install EvalML.
 
+For Docker fans, an included `Dockerfile.arm` can be built and run to provide an environment for testing.  Details are included within.
+
 +++

docs/source/release_notes.rst

@@ -29,12 +29,15 @@ Release Notes
         * Added the option to set the ``sp`` parameter for ARIMA models :pr:`3597`
         * Updated the CV split size of time series problems to match forecast horizon for improved performance :pr:`3616`
         * Added holdout set evaluation as part of AutoML search and pipeline ranking :pr:`3499`
+        * Added Dockerfile.arm and .dockerignore for python version and M1 testing :pr:`3609`
+        * Added ``test_gen_utils::in_container_arm64()`` fixture :pr:`3609`
     * Fixes
         * Fixed iterative graphs not appearing in documentation :pr:`3592`
         * Updated the ``load_diabetes()`` method to account for scikit-learn 1.1.1 changes to the dataset :pr:`3591`
         * Capped woodwork version at < 0.17.0 :pr:`3612`
         * Bump minimum scikit-optimize version to 0.9.0 `:pr:`3614`
         * Invalid target data checks involving regression and unsupported data types now produce a different ``DataCheckMessageCode`` :pr:`3630`
+        * Updated ``test_data_checks.py::test_data_checks_raises_value_errors_on_init`` - more lenient text check :pr:`3609`
     * Changes
         * Add pre-commit hooks for linting :pr:`3608`
         * Implemented a lower threshold and window size for the ``TimeSeriesRegularizer`` and ``DatetimeFormatDataCheck`` :pr:`3627`
@@ -43,6 +46,13 @@ Release Notes
     * Testing Changes
         * Pinned GraphViz version for Windows CI Test :pr:`3596`
         * Removed ``pytest.mark.skip_if_39`` pytest marker :pr:`3602` :pr:`3607`
+        * Updated pytest==7.1.2 :pr:`3609`
+        * Added Dockerfile.arm and .dockerignore for python version and M1 testing :pr:`3609`
+        * Added ``test_gen_utils::in_container_arm64()`` fixture :pr:`3609`
+
+.. warning::
+
+    **Breaking Changes**
         * Refactored test cases that iterate over all components to use ``pytest.mark.parametrise`` and changed the corresponding ``if...continue`` blocks to ``pytest.mark.xfail`` :pr:`3622`
 
 

evalml/tests/data_checks_tests/test_data_checks.py

@@ -638,19 +638,19 @@ def validate(self, X, y=None):
             [MockCheck],
             {"mock_check": {"foo": 1}},
             DataCheckInitError,
-            r"Encountered the following error while initializing mock_check: __init__\(\) missing 1 required positional argument: 'bar'",
+            r"Encountered the following error while initializing mock_check: .*__init__\(\) missing 1 required positional argument: 'bar'",
         ),
         (
             [MockCheck],
             {"mock_check": {"Bar": 2}},
             DataCheckInitError,
-            r"Encountered the following error while initializing mock_check: __init__\(\) got an unexpected keyword argument 'Bar'",
+            r"Encountered the following error while initializing mock_check: .*__init__\(\) got an unexpected keyword argument 'Bar'",
         ),
         (
             [MockCheck],
             {"mock_check": {"fo": 3, "ba": 4}},
             DataCheckInitError,
-            r"Encountered the following error while initializing mock_check: __init__\(\) got an unexpected keyword argument 'fo'",
+            r"Encountered the following error while initializing mock_check: .*__init__\(\) got an unexpected keyword argument 'fo'",
         ),
         (
             [MockCheck],

evalml/tests/dependency_update_check/minimum_test_requirements.txt

@@ -26,7 +26,7 @@ pmdarima==1.8.1
 pytest-cov==2.10.1
 pytest-timeout==1.4.2
 pytest-xdist==2.1.0
-pytest==6.0.1
+pytest==7.1.2
 pyzmq==20.0.0
 requirements-parser==0.2.0
 scikit-learn==1.1.2

evalml/tests/utils_tests/test_gen_utils.py

@@ -30,6 +30,19 @@
 )
 
 
+@pytest.fixture(scope="module")
+def in_container_arm64():
+    """Helper fixture to run chromium as a single process for kaleido.
+
+    The env var is set in the Dockerfile.arm for the purposes of local
+    testing in a container on a mac M1, otherwise it's a noop.
+    """
+    if os.getenv("DOCKER_ARM", None):
+        import plotly.io as pio
+
+        pio.kaleido.scope.chromium_args += ("--single-process",)
+
+
 @patch("importlib.import_module")
 def test_import_or_raise_errors(dummy_importlib):
     def _mock_import_function(library_str):
@@ -345,6 +358,7 @@ def test_rename_column_names_to_numeric():
     ],
 )
 def test_save_plotly_static_default_format(
+    in_container_arm64,
     file_name,
     format,
     interactive,

setup.cfg

@@ -87,7 +87,7 @@ dev =
     %(docs)s
 
 test =
-    pytest == 6.0.1
+    pytest == 7.1.2
     pytest-xdist == 2.1.0
     pytest-timeout == 1.4.2
     pytest-cov == 2.10.1