Update buildspec; Freeze protobuf and pyarrow

ci/buildspec.yml

@@ -1,9 +1,4 @@
 version: 0.2
-
-env:
-  variables:
-    FRAMEWORK_VERSION: "0.23-1"
-
 phases:
   install:
     runtime-versions:
@@ -13,28 +8,49 @@ phases:
     commands:
     - echo Logging in to Amazon ECR...
     - $(aws ecr get-login --no-include-email --region $AWS_DEFAULT_REGION)
+    - echo Installing dependencies...
+    - curl -LO http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
+    - bash Miniconda3-latest-Linux-x86_64.sh -bfp /miniconda3
+    - export PATH=/miniconda3/bin:${PATH}
+    - conda install python=3.7
+    - conda update -y conda
+    - python3 -m pip install pip==20.1  # Pip dependency resolver in 20.2+ can't resolve some dependencies
+    - python3 -m pip install .[test]
   build:
     commands:
     - echo Build started on `date`
-    - echo Building the Docker image...
+    - echo Building base container...
     - docker login -u $dockerhub_username -p $dockerhub_password
     - docker build -t sklearn-base:$FRAMEWORK_VERSION-cpu-py3  -f docker/$FRAMEWORK_VERSION/base/Dockerfile.cpu .
     - pip install wheel setuptools
     - python setup.py bdist_wheel
+    - echo Building final container...
     - docker build -t preprod-sklearn:$FRAMEWORK_VERSION-cpu-py3 -f docker/$FRAMEWORK_VERSION/final/Dockerfile.cpu .
-    - docker tag preprod-sklearn:$FRAMEWORK_VERSION-cpu-py3 515193369038.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:$FRAMEWORK_VERSION-cpu-py3
+    - echo Building test container...
+    - printf "FROM preprod-sklearn:$FRAMEWORK_VERSION-cpu-py3\nADD . /app\nWORKDIR /app\nRUN python3 -m pip install .[test]" > Dockerfile.test
+    - docker build -t test-sklearn -f Dockerfile.test .
+    - echo Running tox...
+    - docker run --rm --entrypoint /bin/bash test-sklearn -c "tox -e ALL"
+    - echo Running container tests...
+    - pytest test/integration --docker-base-name preprod-sklearn --tag $FRAMEWORK_VERSION-cpu-py3 --py-version 3 --framework-version $FRAMEWORK_VERSION
   post_build:
     commands:
     - echo Build completed on `date`
-    - echo Pushing the Docker image...
     - |
       case $CODEBUILD_WEBHOOK_EVENT in
-        PUSH)
-          docker push 515193369038.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:$FRAMEWORK_VERSION-cpu-py3 | grep -v -E "[0-9]{12}.dkr.ecr.\S+.amazonaws.com"
+        PULL_REQUEST_MERGED)
+          echo Logging in to Amazon ECR...
+          $(aws ecr get-login --no-include-email --region $AWS_DEFAULT_REGION)
+          echo Pushing the Docker image...
+          docker push $SM_ALPHA.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:$FRAMEWORK_VERSION-cpu-py3 | grep -v -E "[0-9]{12}.dkr.ecr.\S+.amazonaws.com"
+          docker push $SM_ALPHA.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:$FRAMEWORK_VERSION | grep -v -E "[0-9]{12}.dkr.ecr.\S+.amazonaws.com"
           ;;
-        PULL_REQUEST_MERGED | PULL_REQUEST_CREATED | PULL_REQUEST_UPDATED | PULL_REQUEST_REOPENED)
+        PULL_REQUEST_CREATED | PULL_REQUEST_UPDATED | PULL_REQUEST_REOPENED)
+          echo Logging in to Amazon ECR...
+          $(aws ecr get-login --no-include-email --region $AWS_DEFAULT_REGION)
+          echo Pushing the Docker image...
           # pushes test tag for manual verification, requires cleanup in ECR every once in a while though
-          TEST_TAG=515193369038.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:$FRAMEWORK_VERSION-cpu-py3-test
+          TEST_TAG=$SM_ALPHA.dkr.ecr.us-west-2.amazonaws.com/sagemaker-scikit-learn:${FRAMEWORK_VERSION}-cpu-py3-test
           docker tag preprod-sklearn:$FRAMEWORK_VERSION-cpu-py3 ${TEST_TAG}
           docker push ${TEST_TAG} | grep -v -E "[0-9]{12}.dkr.ecr.\S+.amazonaws.com"
           ;;

docker/0.23-1/base/Dockerfile.cpu

@@ -7,7 +7,7 @@ ARG MINICONDA_VERSION=4.8.3
 ARG CONDA_PY_VERSION=37
 ARG CONDA_PKG_VERSION=4.9.0
 ARG PYTHON_VERSION=3.7.10
-ARG PYARROW_VERSION=3.0.0
+ARG PYARROW_VERSION=1.0.0
 ARG MLIO_VERSION=0.6.0
 
 # Install python and other scikit-learn runtime dependencies

requirements.txt

@@ -2,22 +2,23 @@ boto3==1.24.17
 botocore==1.27.18
 cryptography==35.0.0
 Flask==1.1.1
-itsdangerous==2.0.1
 gunicorn==20.0.4
+itsdangerous==2.0.1
+jinja2==3.0.3
+MarkupSafe==2.1.1
 model-archiver==1.0.3
 multi-model-server==1.1.1
 numpy==1.19.2
 pandas==1.1.3
+protobuf==3.20.1
 psutil==5.7.2
+pyarrow==1.0.0
 python-dateutil==2.8.1
-sagemaker-inference==1.2.0
 retrying==1.3.3
 sagemaker-containers==2.8.6.post2
 sagemaker-inference==1.2.0
 sagemaker-training==4.0.1
 scikit-learn==0.23.2
 scipy==1.5.3
 six==1.15.0
-jinja2==3.0.3
-MarkupSafe==2.1.1
 Werkzeug==0.15.6

tox.ini

@@ -10,8 +10,8 @@ deps =
     -r{toxinidir}/requirements.txt
     -r{toxinidir}/test-requirements.txt
 conda_deps=
-    pyarrow=3.0.0
-    mlio-py=0.5
+    pyarrow=1.0.0
+    mlio-py=0.6
 conda_channels=
     conda-forge
     mlio