[SPARK-1267][SPARK-18129] Allow PySpark to be pip installed

## What changes were proposed in this pull request?

This PR aims to provide a pip installable PySpark package. This does a bunch of work to copy the jars over and package them with the Python code (to prevent challenges from trying to use different versions of the Python code with different versions of the JAR). It does not currently publish to PyPI but that is the natural follow up (SPARK-18129).

Done:
- pip installable on conda [manual tested]
- setup.py installed on a non-pip managed system (RHEL) with YARN [manual tested]
- Automated testing of this (virtualenv)
- packaging and signing with release-build*

Possible follow up work:
- release-build update to publish to PyPI (SPARK-18128)
- figure out who owns the pyspark package name on prod PyPI (is it someone with in the project or should we ask PyPI or should we choose a different name to publish with like ApachePySpark?)
- Windows support and or testing ( SPARK-18136 )
- investigate details of wheel caching and see if we can avoid cleaning the wheel cache during our test
- consider how we want to number our dev/snapshot versions

Explicitly out of scope:
- Using pip installed PySpark to start a standalone cluster
- Using pip installed PySpark for non-Python Spark programs

*I've done some work to test release-build locally but as a non-committer I've just done local testing.
## How was this patch tested?

Automated testing with virtualenv, manual testing with conda, a system wide install, and YARN integration.

release-build changes tested locally as a non-committer (no testing of upload artifacts to Apache staging websites)

Author: Holden Karau <holden@us.ibm.com>
Author: Juliet Hougland <juliet@cloudera.com>
Author: Juliet Hougland <not@myemail.com>

Closes #15659 from holdenk/SPARK-1267-pip-install-pyspark.

.gitignore

@@ -57,6 +57,8 @@ project/plugins/project/build.properties
 project/plugins/src_managed/
 project/plugins/target/
 python/lib/pyspark.zip
+python/deps
+python/pyspark/python
 reports/
 scalastyle-on-compile.generated.xml
 scalastyle-output.xml

bin/beeline

@@ -25,7 +25,7 @@ set -o posix
 
 # Figure out if SPARK_HOME is set
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 CLASS="org.apache.hive.beeline.BeeLine"

bin/find-spark-home

+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Attempts to find a proper value for SPARK_HOME. Should be included using "source" directive.
+
+FIND_SPARK_HOME_PYTHON_SCRIPT="$(cd "$(dirname "$0")"; pwd)/find_spark_home.py"
+
+# Short cirtuit if the user already has this set.
+if [ ! -z "${SPARK_HOME}" ]; then
+   exit 0
+elif [ ! -f "$FIND_SPARK_HOME_PYTHON_SCRIPT" ]; then
+  # If we are not in the same directory as find_spark_home.py we are not pip installed so we don't
+  # need to search the different Python directories for a Spark installation.
+  # Note only that, if the user has pip installed PySpark but is directly calling pyspark-shell or
+  # spark-submit in another directory we want to use that version of PySpark rather than the
+  # pip installed version of PySpark.
+  export SPARK_HOME="$(cd "$(dirname "$0")"/..; pwd)"
+else
+  # We are pip installed, use the Python script to resolve a reasonable SPARK_HOME
+  # Default to standard python interpreter unless told otherwise
+  if [[ -z "$PYSPARK_DRIVER_PYTHON" ]]; then
+     PYSPARK_DRIVER_PYTHON="${PYSPARK_PYTHON:-"python"}"
+  fi
+  export SPARK_HOME=$($PYSPARK_DRIVER_PYTHON "$FIND_SPARK_HOME_PYTHON_SCRIPT")
+fi

bin/load-spark-env.sh

@@ -23,7 +23,7 @@
 
 # Figure out where Spark is installed
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 if [ -z "$SPARK_ENV_LOADED" ]; then

bin/pyspark

@@ -18,7 +18,7 @@
 #
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 source "${SPARK_HOME}"/bin/load-spark-env.sh
@@ -46,7 +46,7 @@ WORKS_WITH_IPYTHON=$(python -c 'import sys; print(sys.version_info >= (2, 7, 0))
 
 # Determine the Python executable to use for the executors:
 if [[ -z "$PYSPARK_PYTHON" ]]; then
-  if [[ $PYSPARK_DRIVER_PYTHON == *ipython* && ! WORKS_WITH_IPYTHON ]]; then
+  if [[ $PYSPARK_DRIVER_PYTHON == *ipython* && ! $WORKS_WITH_IPYTHON ]]; then
     echo "IPython requires Python 2.7+; please install python2.7 or set PYSPARK_PYTHON" 1>&2
     exit 1
   else
@@ -68,7 +68,7 @@ if [[ -n "$SPARK_TESTING" ]]; then
   unset YARN_CONF_DIR
   unset HADOOP_CONF_DIR
   export PYTHONHASHSEED=0
-  exec "$PYSPARK_DRIVER_PYTHON" -m $1
+  exec "$PYSPARK_DRIVER_PYTHON" -m "$1"
   exit
 fi
 

bin/run-example

@@ -18,7 +18,7 @@
 #
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 export _SPARK_CMD_USAGE="Usage: ./bin/run-example [options] example-class [example args]"

bin/spark-class

@@ -18,7 +18,7 @@
 #
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 . "${SPARK_HOME}"/bin/load-spark-env.sh
@@ -27,7 +27,7 @@ fi
 if [ -n "${JAVA_HOME}" ]; then
   RUNNER="${JAVA_HOME}/bin/java"
 else
-  if [ `command -v java` ]; then
+  if [ "$(command -v java)" ]; then
     RUNNER="java"
   else
     echo "JAVA_HOME is not set" >&2
@@ -36,7 +36,7 @@ else
 fi
 
 # Find Spark jars.
-if [ -f "${SPARK_HOME}/RELEASE" ]; then
+if [ -d "${SPARK_HOME}/jars" ]; then
   SPARK_JARS_DIR="${SPARK_HOME}/jars"
 else
   SPARK_JARS_DIR="${SPARK_HOME}/assembly/target/scala-$SPARK_SCALA_VERSION/jars"

bin/spark-shell

@@ -21,7 +21,7 @@
 # Shell script for starting the Spark Shell REPL
 
 cygwin=false
-case "`uname`" in
+case "$(uname)" in
   CYGWIN*) cygwin=true;;
 esac
 
@@ -29,7 +29,7 @@ esac
 set -o posix
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 export _SPARK_CMD_USAGE="Usage: ./bin/spark-shell [options]"

bin/spark-sql

@@ -18,7 +18,7 @@
 #
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 export _SPARK_CMD_USAGE="Usage: ./bin/spark-sql [options] [cli option]"

bin/spark-submit

@@ -18,7 +18,7 @@
 #
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 # disable randomized hash for string in Python 3.3+

bin/sparkR

@@ -18,7 +18,7 @@
 #
 
 if [ -z "${SPARK_HOME}" ]; then
-  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
+  source "$(dirname "$0")"/find-spark-home
 fi
 
 source "${SPARK_HOME}"/bin/load-spark-env.sh

dev/create-release/release-build.sh

@@ -162,14 +162,35 @@ if [[ "$1" == "package" ]]; then
     export ZINC_PORT=$ZINC_PORT
     echo "Creating distribution: $NAME ($FLAGS)"
 
+    # Write out the NAME and VERSION to PySpark version info we rewrite the - into a . and SNAPSHOT
+    # to dev0 to be closer to PEP440. We use the NAME as a "local version".
+    PYSPARK_VERSION=`echo "$SPARK_VERSION+$NAME" |  sed -r "s/-/./" | sed -r "s/SNAPSHOT/dev0/"`
+    echo "__version__='$PYSPARK_VERSION'" > python/pyspark/version.py
+
     # Get maven home set by MVN
     MVN_HOME=`$MVN -version 2>&1 | grep 'Maven home' | awk '{print $NF}'`
 
-    ./dev/make-distribution.sh --name $NAME --mvn $MVN_HOME/bin/mvn --tgz $FLAGS \
+    echo "Creating distribution"
+    ./dev/make-distribution.sh --name $NAME --mvn $MVN_HOME/bin/mvn --tgz --pip $FLAGS \
       -DzincPort=$ZINC_PORT 2>&1 >  ../binary-release-$NAME.log
     cd ..
-    cp spark-$SPARK_VERSION-bin-$NAME/spark-$SPARK_VERSION-bin-$NAME.tgz .
 
+    echo "Copying and signing python distribution"
+    PYTHON_DIST_NAME=pyspark-$PYSPARK_VERSION.tar.gz
+    cp spark-$SPARK_VERSION-bin-$NAME/python/dist/$PYTHON_DIST_NAME .
+
+    echo $GPG_PASSPHRASE | $GPG --passphrase-fd 0 --armour \
+      --output $PYTHON_DIST_NAME.asc \
+      --detach-sig $PYTHON_DIST_NAME
+    echo $GPG_PASSPHRASE | $GPG --passphrase-fd 0 --print-md \
+      MD5 $PYTHON_DIST_NAME > \
+      $PYTHON_DIST_NAME.md5
+    echo $GPG_PASSPHRASE | $GPG --passphrase-fd 0 --print-md \
+      SHA512 $PYTHON_DIST_NAME > \
+      $PYTHON_DIST_NAME.sha
+
+    echo "Copying and signing regular binary distribution"
+    cp spark-$SPARK_VERSION-bin-$NAME/spark-$SPARK_VERSION-bin-$NAME.tgz .
     echo $GPG_PASSPHRASE | $GPG --passphrase-fd 0 --armour \
       --output spark-$SPARK_VERSION-bin-$NAME.tgz.asc \
       --detach-sig spark-$SPARK_VERSION-bin-$NAME.tgz
@@ -208,6 +229,7 @@ if [[ "$1" == "package" ]]; then
   # Re-upload a second time and leave the files in the timestamped upload directory:
   LFTP mkdir -p $dest_dir
   LFTP mput -O $dest_dir 'spark-*'
+  LFTP mput -O $dest_dir 'pyspark-*'
   exit 0
 fi
 

dev/create-release/release-tag.sh

@@ -65,6 +65,7 @@ sed -i".tmp1" 's/Version.*$/Version: '"$RELEASE_VERSION"'/g' R/pkg/DESCRIPTION
 # Set the release version in docs
 sed -i".tmp1" 's/SPARK_VERSION:.*$/SPARK_VERSION: '"$RELEASE_VERSION"'/g' docs/_config.yml
 sed -i".tmp2" 's/SPARK_VERSION_SHORT:.*$/SPARK_VERSION_SHORT: '"$RELEASE_VERSION"'/g' docs/_config.yml
+sed -i".tmp3" 's/__version__ = .*$/__version__ = "'"$RELEASE_VERSION"'"/' python/pyspark/version.py
 
 git commit -a -m "Preparing Spark release $RELEASE_TAG"
 echo "Creating tag $RELEASE_TAG at the head of $GIT_BRANCH"
@@ -74,12 +75,16 @@ git tag $RELEASE_TAG
 $MVN versions:set -DnewVersion=$NEXT_VERSION | grep -v "no value" # silence logs
 # Remove -SNAPSHOT before setting the R version as R expects version strings to only have numbers
 R_NEXT_VERSION=`echo $NEXT_VERSION | sed 's/-SNAPSHOT//g'`
-sed -i".tmp2" 's/Version.*$/Version: '"$R_NEXT_VERSION"'/g' R/pkg/DESCRIPTION
+sed -i".tmp4" 's/Version.*$/Version: '"$R_NEXT_VERSION"'/g' R/pkg/DESCRIPTION
+# Write out the R_NEXT_VERSION to PySpark version info we use dev0 instead of SNAPSHOT to be closer
+# to PEP440.
+sed -i".tmp5" 's/__version__ = .*$/__version__ = "'"$R_NEXT_VERSION.dev0"'"/' python/pyspark/version.py
+
 
 # Update docs with next version
-sed -i".tmp3" 's/SPARK_VERSION:.*$/SPARK_VERSION: '"$NEXT_VERSION"'/g' docs/_config.yml
+sed -i".tmp6" 's/SPARK_VERSION:.*$/SPARK_VERSION: '"$NEXT_VERSION"'/g' docs/_config.yml
 # Use R version for short version
-sed -i".tmp4" 's/SPARK_VERSION_SHORT:.*$/SPARK_VERSION_SHORT: '"$R_NEXT_VERSION"'/g' docs/_config.yml
+sed -i".tmp7" 's/SPARK_VERSION_SHORT:.*$/SPARK_VERSION_SHORT: '"$R_NEXT_VERSION"'/g' docs/_config.yml
 
 git commit -a -m "Preparing development version $NEXT_VERSION"
 

dev/lint-python

@@ -20,7 +20,9 @@
 SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )"
 SPARK_ROOT_DIR="$(dirname "$SCRIPT_DIR")"
 PATHS_TO_CHECK="./python/pyspark/ ./examples/src/main/python/ ./dev/sparktestsupport"
-PATHS_TO_CHECK="$PATHS_TO_CHECK ./dev/run-tests.py ./python/run-tests.py ./dev/run-tests-jenkins.py"
+# TODO: fix pep8 errors with the rest of the Python scripts under dev
+PATHS_TO_CHECK="$PATHS_TO_CHECK ./dev/run-tests.py ./python/*.py ./dev/run-tests-jenkins.py"
+PATHS_TO_CHECK="$PATHS_TO_CHECK ./dev/pip-sanity-check.py"
 PEP8_REPORT_PATH="$SPARK_ROOT_DIR/dev/pep8-report.txt"
 PYLINT_REPORT_PATH="$SPARK_ROOT_DIR/dev/pylint-report.txt"
 PYLINT_INSTALL_INFO="$SPARK_ROOT_DIR/dev/pylint-info.txt"

dev/make-distribution.sh

@@ -33,6 +33,7 @@ SPARK_HOME="$(cd "`dirname "$0"`/.."; pwd)"
 DISTDIR="$SPARK_HOME/dist"
 
 MAKE_TGZ=false
+MAKE_PIP=false
 NAME=none
 MVN="$SPARK_HOME/build/mvn"
 
@@ -40,7 +41,7 @@ function exit_with_usage {
   echo "make-distribution.sh - tool for making binary distributions of Spark"
   echo ""
   echo "usage:"
-  cl_options="[--name] [--tgz] [--mvn <mvn-command>]"
+  cl_options="[--name] [--tgz] [--pip] [--mvn <mvn-command>]"
   echo "make-distribution.sh $cl_options <maven build options>"
   echo "See Spark's \"Building Spark\" doc for correct Maven options."
   echo ""
@@ -67,6 +68,9 @@ while (( "$#" )); do
     --tgz)
       MAKE_TGZ=true
       ;;
+    --pip)
+      MAKE_PIP=true
+      ;;
     --mvn)
       MVN="$2"
       shift
@@ -201,6 +205,16 @@ fi
 # Copy data files
 cp -r "$SPARK_HOME/data" "$DISTDIR"
 
+# Make pip package
+if [ "$MAKE_PIP" == "true" ]; then
+  echo "Building python distribution package"
+  cd $SPARK_HOME/python
+  python setup.py sdist
+  cd ..
+else
+  echo "Skipping creating pip installable PySpark"
+fi
+
 # Copy other things
 mkdir "$DISTDIR"/conf
 cp "$SPARK_HOME"/conf/*.template "$DISTDIR"/conf

dev/pip-sanity-check.py

+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+from __future__ import print_function
+
+from pyspark.sql import SparkSession
+import sys
+
+if __name__ == "__main__":
+    spark = SparkSession\
+        .builder\
+        .appName("PipSanityCheck")\
+        .getOrCreate()
+    sc = spark.sparkContext
+    rdd = sc.parallelize(range(100), 10)
+    value = rdd.reduce(lambda x, y: x + y)
+    if (value != 4950):
+        print("Value {0} did not match expected value.".format(value), file=sys.stderr)
+        sys.exit(-1)
+    print("Successfully ran pip sanity check")
+
+    spark.stop()

dev/run-pip-tests

+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Stop on error
+set -e
+# Set nullglob for when we are checking existence based on globs
+shopt -s nullglob
+
+FWDIR="$(cd "$(dirname "$0")"/..; pwd)"
+cd "$FWDIR"
+
+echo "Constucting virtual env for testing"
+VIRTUALENV_BASE=$(mktemp -d)
+
+# Clean up the virtual env enviroment used if we created one.
+function delete_virtualenv() {
+  echo "Cleaning up temporary directory - $VIRTUALENV_BASE"
+  rm -rf "$VIRTUALENV_BASE"
+}
+trap delete_virtualenv EXIT
+
+# Some systems don't have pip or virtualenv - in those cases our tests won't work.
+if ! hash virtualenv 2>/dev/null; then
+  echo "Missing virtualenv skipping pip installability tests."
+  exit 0
+fi
+if ! hash pip 2>/dev/null; then
+  echo "Missing pip, skipping pip installability tests."
+  exit 0
+fi
+
+# Figure out which Python execs we should test pip installation with
+PYTHON_EXECS=()
+if hash python2 2>/dev/null; then
+  # We do this since we are testing with virtualenv and the default virtual env python
+  # is in /usr/bin/python
+  PYTHON_EXECS+=('python2')
+elif hash python 2>/dev/null; then
+  # If python2 isn't installed fallback to python if available
+  PYTHON_EXECS+=('python')
+fi
+if hash python3 2>/dev/null; then
+  PYTHON_EXECS+=('python3')
+fi
+
+# Determine which version of PySpark we are building for archive name
+PYSPARK_VERSION=$(python -c "exec(open('python/pyspark/version.py').read());print __version__")
+PYSPARK_DIST="$FWDIR/python/dist/pyspark-$PYSPARK_VERSION.tar.gz"
+# The pip install options we use for all the pip commands
+PIP_OPTIONS="--upgrade --no-cache-dir --force-reinstall "
+# Test both regular user and edit/dev install modes.
+PIP_COMMANDS=("pip install $PIP_OPTIONS $PYSPARK_DIST"
+	      "pip install $PIP_OPTIONS -e python/")
+
+for python in "${PYTHON_EXECS[@]}"; do
+  for install_command in "${PIP_COMMANDS[@]}"; do
+    echo "Testing pip installation with python $python"
+    # Create a temp directory for us to work in and save its name to a file for cleanup
+    echo "Using $VIRTUALENV_BASE for virtualenv"
+    VIRTUALENV_PATH="$VIRTUALENV_BASE"/$python
+    rm -rf "$VIRTUALENV_PATH"
+    mkdir -p "$VIRTUALENV_PATH"
+    virtualenv --python=$python "$VIRTUALENV_PATH"
+    source "$VIRTUALENV_PATH"/bin/activate
+    # Upgrade pip
+    pip install --upgrade pip
+
+    echo "Creating pip installable source dist"
+    cd "$FWDIR"/python
+    $python setup.py sdist
+
+
+    echo "Installing dist into virtual env"
+    cd dist
+    # Verify that the dist directory only contains one thing to install
+    sdists=(*.tar.gz)
+    if [ ${#sdists[@]} -ne 1 ]; then
+      echo "Unexpected number of targets found in dist directory - please cleanup existing sdists first."
+      exit -1
+    fi
+    # Do the actual installation
+    cd "$FWDIR"
+    $install_command
+
+    cd /
+
+    echo "Run basic sanity check on pip installed version with spark-submit"
+    spark-submit "$FWDIR"/dev/pip-sanity-check.py
+    echo "Run basic sanity check with import based"
+    python "$FWDIR"/dev/pip-sanity-check.py
+    echo "Run the tests for context.py"
+    python "$FWDIR"/python/pyspark/context.py
+
+    cd "$FWDIR"
+
+  done
+done
+
+exit 0

dev/run-tests-jenkins.py

@@ -128,6 +128,7 @@ def run_tests(tests_timeout):
         ERROR_CODES["BLOCK_MIMA"]: 'MiMa tests',
         ERROR_CODES["BLOCK_SPARK_UNIT_TESTS"]: 'Spark unit tests',
         ERROR_CODES["BLOCK_PYSPARK_UNIT_TESTS"]: 'PySpark unit tests',
+        ERROR_CODES["BLOCK_PYSPARK_PIP_TESTS"]: 'PySpark pip packaging tests',
         ERROR_CODES["BLOCK_SPARKR_UNIT_TESTS"]: 'SparkR unit tests',
         ERROR_CODES["BLOCK_TIMEOUT"]: 'from timeout after a configured wait of \`%s\`' % (
             tests_timeout)

dev/run-tests.py

@@ -432,6 +432,12 @@ def run_python_tests(test_modules, parallelism):
     run_cmd(command)
 
 
+def run_python_packaging_tests():
+    set_title_and_block("Running PySpark packaging tests", "BLOCK_PYSPARK_PIP_TESTS")
+    command = [os.path.join(SPARK_HOME, "dev", "run-pip-tests")]
+    run_cmd(command)
+
+
 def run_build_tests():
     set_title_and_block("Running build tests", "BLOCK_BUILD_TESTS")
     run_cmd([os.path.join(SPARK_HOME, "dev", "test-dependencies.sh")])
@@ -583,6 +589,7 @@ def main():
     modules_with_python_tests = [m for m in test_modules if m.python_test_goals]
     if modules_with_python_tests:
         run_python_tests(modules_with_python_tests, opts.parallelism)
+        run_python_packaging_tests()
     if any(m.should_run_r_tests for m in test_modules):
         run_sparkr_tests()
 

dev/sparktestsupport/__init__.py

@@ -33,5 +33,6 @@ ERROR_CODES = {
     "BLOCK_SPARKR_UNIT_TESTS": 20,
     "BLOCK_JAVA_STYLE": 21,
     "BLOCK_BUILD_TESTS": 22,
+    "BLOCK_PYSPARK_PIP_TESTS": 23,
     "BLOCK_TIMEOUT": 124
 }