Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/20473#discussion_r165869377 --- Diff: python/run-tests.py --- @@ -151,6 +152,67 @@ def parse_opts(): return opts +def _check_dependencies(python_exec, modules_to_test): + if "COVERAGE_PROCESS_START" in os.environ: + # Make sure if coverage is installed. + try: + subprocess_check_output( + [python_exec, "-c", "import coverage"], + stderr=open(os.devnull, 'w')) + except: + print_red("Coverage is not installed in Python executable '%s' " + "but 'COVERAGE_PROCESS_START' environment variable is set, " + "exiting." % python_exec) + sys.exit(-1) + + # If we should test 'pyspark-sql', it checks if PyArrow and Pandas are installed and + # explicitly prints out. See SPARK-23300. + if pyspark_sql in modules_to_test: + # TODO(HyukjinKwon): Relocate and deduplicate these version specifications. + minimum_pyarrow_version = '0.8.0' + minimum_pandas_version = '0.19.2' --- End diff -- In the last commit, - I only replaced `minimal_pyarrow_version` -> `minimum_pyarrow_version` and `minimal_pandas_version` -> `minimum_pandas_version` - Replaced the comment to `# TODO(HyukjinKwon): Relocate and deduplicate these version specifications.`, to match it to https://github.com/apache/spark/pull/20487.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org