allisonwang-db commented on code in PR #42272: URL: https://github.com/apache/spark/pull/42272#discussion_r1302303763
########## examples/src/main/python/sql/udtf.py: ########## @@ -0,0 +1,230 @@ +# +# 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. +# + +""" +A simple example demonstrating Python UDTFs in Spark +Run with: + ./bin/spark-submit examples/src/main/python/sql/udtf.py +""" + +# NOTE that this file is imported in the User Guides in PySpark documentation. +# The codes are referred via line numbers. See also `literalinclude` directive in Sphinx. +from pyspark.sql import SparkSession +from pyspark.sql.pandas.utils import require_minimum_pandas_version, require_minimum_pyarrow_version + +# Python UDTFs use Arrow by default. +require_minimum_pandas_version() +require_minimum_pyarrow_version() + + +def python_udtf_simple_example(spark: SparkSession) -> None: + + # Define the UDTF class and implement the required `eval` method. + class SquareNumbers: + def eval(self, start: int, end: int): # type: ignore[no-untyped-def] + for num in range(start, end + 1): + yield (num, num * num) + + from pyspark.sql.functions import lit, udtf + + # Create a UDTF using the class definition and the `udtf` function. + square_num = udtf(SquareNumbers, returnType="num: int, squared: int") + + # Invoke the UDTF in PySpark. + square_num(lit(1), lit(3)).show() # type: ignore + # +---+------+ + # |num|squred| Review Comment: Good catch! Updated. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
