Remove Scala Docs Page, keep backup (#155)

* Remove Scala Docs Page, keep backup


---------

Co-authored-by: Mufaddal Rohawala <mufi@amazon.com>

buildspec-release.yml

@@ -32,7 +32,7 @@ phases:
       - tox -e flake8,twine,sphinx
 
       # pyspark unit tests (no coverage)
-      - tox -e py37 -- tests/
+      - tox -e py38 -- tests/
 
       # todo consider adding subset of integration tests
 

buildspec.yml

@@ -41,7 +41,7 @@ phases:
       # pyspark linters and unit tests
       - cd $CODEBUILD_SRC_DIR/sagemaker-pyspark-sdk
       - tox -e flake8,twine,sphinx
-      - tox -e py37,stats -- tests/
+      - tox -e py38,stats -- tests/
 
       # spark integration tests
       - cd $CODEBUILD_SRC_DIR/integration-tests/sagemaker-spark-sdk
@@ -51,6 +51,6 @@ phases:
 
       # pyspark integration tests
       - cd $CODEBUILD_SRC_DIR/sagemaker-pyspark-sdk
-      - IGNORE_COVERAGE=- tox -e py37 -- $CODEBUILD_SRC_DIR/integration-tests/sagemaker-pyspark-sdk/tests/ -n 10 --boxed --reruns 2
-        # - test_cmd="IGNORE_COVERAGE=- tox -e py37 -- $CODEBUILD_SRC_DIR/integration-tests/sagemaker-pyspark-sdk/tests/ -n 10 --boxed --reruns 2"
+      - IGNORE_COVERAGE=- tox -e py38 -- $CODEBUILD_SRC_DIR/integration-tests/sagemaker-pyspark-sdk/tests/ -n 10 --boxed --reruns 2
+        # - test_cmd="IGNORE_COVERAGE=- tox -e py38 -- $CODEBUILD_SRC_DIR/integration-tests/sagemaker-pyspark-sdk/tests/ -n 10 --boxed --reruns 2"
         # - execute-command-if-has-matching-changes "$test_cmd" "src/" "tests/" "setup.*" "requirements.txt" "tox.ini" "buildspec.yml"

sagemaker-pyspark-sdk/src/sagemaker_pyspark/algorithms/PCASageMakerEstimator.py

@@ -33,10 +33,10 @@ class PCASageMakerEstimator(SageMakerEstimatorBase):
     dictionary with entries in trainingSparkDataFormatOptions with key "labelColumnName" or
     "featuresColumnName", with values corresponding to the desired label and features columns.
 
-    PCASageMakerEstimator uses
-    :class:`~sagemaker_pyspark.transformation.serializers.ProtobufRequestRowSerializer` to serialize
-     Rows into RecordIO-encoded Amazon Record protobuf messages for inference, by default selecting
-    the column named "features" expected to contain a Vector of Doubles.
+    :class:`~sagemaker_pyspark.transformation.serializers.ProtobufRequestRowSerializer` is used
+    by PCASageMakerEstimator to serialize Rows into RecordIO-encoded Amazon Record protobuf
+    messages for inference, by default selecting the column named "features" expected to contain
+    a Vector of Doubles.
 
     Inferences made against an Endpoint hosting a PCA model contain a "projection" field appended
     to the input DataFrame as a Dense Vector of Doubles.

sagemaker-pyspark-sdk/tox.ini

@@ -1,14 +1,14 @@
 [tox]
-envlist = flake8,twine,sphinx,py37,stats
+envlist = flake8,twine,sphinx,py38,stats
 skip_missing_interpreters = False
 
 [testenv]
 deps =
-    coverage == 4.4
-    pytest
-    pytest-cov
-    pytest-rerunfailures
-    pytest-xdist
+    coverage>=5.2, <6.2
+    pytest==6.2.5
+    pytest-cov==3.0.0
+    pytest-rerunfailures==10.2
+    pytest-xdist==2.4.0
 
 LANG=en_US.UTF-8
 LANGUAGE=en_US:en
@@ -28,8 +28,8 @@ passenv =
 [testenv:sphinx]
 basepython=python3
 deps =
-    sphinx
-    sphinx_rtd_theme
+    sphinx==5.1.1
+    sphinx-rtd-theme==0.5.0
 
 commands = sphinx-build -b html docs html
 
@@ -44,8 +44,8 @@ commands =
 [testenv:flake8]
 basepython=python3
 deps =
-    flake8
-    flake8_formatter_abspath
+    flake8==4.0.1
+    flake8_formatter_abspath==1.0.1
 
 skip_install = true
 commands=flake8 src/sagemaker_pyspark/ tests/ setup.py