HyukjinKwon commented on a change in pull request #24981: [SPARK-27463][PYTHON] Support Dataframe Cogroup via Pandas UDFs URL: https://github.com/apache/spark/pull/24981#discussion_r326890237
########## File path: python/pyspark/sql/tests/test_pandas_udf_cogrouped_map.py ########## @@ -0,0 +1,280 @@ +# +# 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. +# + +import unittest +import sys + +from pyspark.sql.functions import array, explode, col, lit, udf, sum, pandas_udf, PandasUDFType +from pyspark.sql.types import DoubleType, StructType, StructField +from pyspark.testing.sqlutils import ReusedSQLTestCase, have_pandas, have_pyarrow, \ + pandas_requirement_message, pyarrow_requirement_message +from pyspark.testing.utils import QuietTest + +if have_pandas: + import pandas as pd + from pandas.util.testing import assert_frame_equal, assert_series_equal + +if have_pyarrow: + import pyarrow as pa + + +""" +Tests below use pd.DataFrame.assign that will infer mixed types (unicode/str) for column names +from kwargs w/ Python 2, so need to set check_column_type=False and avoid this check +""" +if sys.version < '3': + _check_column_type = False Review comment: nit ```python _check_column_type = sys.version >= '3' ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
