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_r326890118
########## File path: python/pyspark/sql/cogroup.py ########## @@ -0,0 +1,98 @@ +# +# 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 pyspark import since +from pyspark.rdd import PythonEvalType +from pyspark.sql.column import Column +from pyspark.sql.dataframe import DataFrame + + +class CoGroupedData(object): + """ + A logical grouping of two :class:`GroupedData`, + created by :func:`GroupedData.cogroup`. + + .. note:: Experimental + + .. versionadded:: 3.0 + """ + + def __init__(self, gd1, gd2): + self._gd1 = gd1 + self._gd2 = gd2 + self.sql_ctx = gd1.sql_ctx + + @since(3.0) + def apply(self, udf): + """ + Applies a function to each cogroup using a pandas udf and returns the result + as a `DataFrame`. + + The user-defined function should take two `pandas.DataFrame` and return another + `pandas.DataFrame`. For each side of the cogroup, all columns are passed together + as a `pandas.DataFrame` to the user-function and the returned `pandas.DataFrame` + are combined as a :class:`DataFrame`. + + The returned `pandas.DataFrame` can be of arbitrary length and its schema must match the + returnType of the pandas udf. + + .. note:: This function requires a full shuffle. All the data of a cogroup will be loaded + into memory, so the user should be aware of the potential OOM risk if data is skewed + and certain groups are too large to fit in memory. + + .. note:: Experimental + + :param udf: a cogrouped map user-defined function returned by + :func:`pyspark.sql.functions.pandas_udf`. + + >>> from pyspark.sql.functions import pandas_udf, PandasUDFType + >>> df1 = spark.createDataFrame( + ... [(20000101, 1, 1.0), (20000101, 2, 2.0), (20000102, 1, 3.0), (20000102, 2, 4.0)], + ... ("time", "id", "v1")) + >>> df2 = spark.createDataFrame( + ... [(20000101, 1, "x"), (20000101, 2, "y")], + ... ("time", "id", "v2")) + >>> @pandas_udf("time int, id int, v1 double, v2 string", PandasUDFType.COGROUPED_MAP) Review comment: We should skip this test and run the doctests 1. add this to `dev/sparktestsupport/modules.py` at `pyspark_sql` 2. add: ```python def main(): doctest.testmod(...) ... ``` ---------------------------------------------------------------- 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]
