viirya commented on a change in pull request #27109: [SPARK-30434][PYTHON][SQL] Move pandas related functionalities into 'pandas' sub-package URL: https://github.com/apache/spark/pull/27109#discussion_r364036517
########## File path: python/pyspark/sql/pandas/functions.py ########## @@ -0,0 +1,539 @@ +# +# 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 functools +import sys + +from pyspark import since +from pyspark.rdd import PythonEvalType +from pyspark.sql.types import DataType +from pyspark.sql.udf import _create_udf + + +class PandasUDFType(object): + """Pandas UDF Types. See :meth:`pyspark.sql.functions.pandas_udf`. + """ + SCALAR = PythonEvalType.SQL_SCALAR_PANDAS_UDF + + SCALAR_ITER = PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF + + GROUPED_MAP = PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF + + COGROUPED_MAP = PythonEvalType.SQL_COGROUPED_MAP_PANDAS_UDF + + GROUPED_AGG = PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF + + MAP_ITER = PythonEvalType.SQL_MAP_PANDAS_ITER_UDF + + +@since(2.3) +def pandas_udf(f=None, returnType=None, functionType=None): + """ + Creates a vectorized user defined function (UDF). + + :param f: user-defined function. A python function if used as a standalone function + :param returnType: the return type of the user-defined function. The value can be either a + :class:`pyspark.sql.types.DataType` object or a DDL-formatted type string. + :param functionType: an enum value in :class:`pyspark.sql.functions.PandasUDFType`. + Default: SCALAR. + + The function type of the UDF can be one of the following: + + 1. SCALAR + + A scalar UDF defines a transformation: One or more `pandas.Series` -> A `pandas.Series`. + The length of the returned `pandas.Series` must be of the same as the input `pandas.Series`. + If the return type is :class:`StructType`, the returned value should be a `pandas.DataFrame`. + + :class:`MapType`, nested :class:`StructType` are currently not supported as output types. + + Scalar UDFs can be used with :meth:`pyspark.sql.DataFrame.withColumn` and + :meth:`pyspark.sql.DataFrame.select`. + + >>> from pyspark.sql.functions import pandas_udf, PandasUDFType Review comment: <del>There are similar imports below.</del> ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
