|
||||
0001 # 0002 # Licensed to the Apache Software Foundation (ASF) under one or more 0003 # contributor license agreements. See the NOTICE file distributed with 0004 # this work for additional information regarding copyright ownership. 0005 # The ASF licenses this file to You under the Apache License, Version 2.0 0006 # (the "License"); you may not use this file except in compliance with 0007 # the License. You may obtain a copy of the License at 0008 # 0009 # http://www.apache.org/licenses/LICENSE-2.0 0010 # 0011 # Unless required by applicable law or agreed to in writing, software 0012 # distributed under the License is distributed on an "AS IS" BASIS, 0013 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 0014 # See the License for the specific language governing permissions and 0015 # limitations under the License. 0016 # 0017 0018 from __future__ import print_function 0019 0020 import sys 0021 0022 from pyspark.sql import SparkSession 0023 0024 0025 if __name__ == "__main__": 0026 if len(sys.argv) != 2: 0027 print("Usage: sort <file>", file=sys.stderr) 0028 sys.exit(-1) 0029 0030 spark = SparkSession\ 0031 .builder\ 0032 .appName("PythonSort")\ 0033 .getOrCreate() 0034 0035 lines = spark.read.text(sys.argv[1]).rdd.map(lambda r: r[0]) 0036 sortedCount = lines.flatMap(lambda x: x.split(' ')) \ 0037 .map(lambda x: (int(x), 1)) \ 0038 .sortByKey() 0039 # This is just a demo on how to bring all the sorted data back to a single node. 0040 # In reality, we wouldn't want to collect all the data to the driver node. 0041 output = sortedCount.collect() 0042 for (num, unitcount) in output: 0043 print(num) 0044 0045 spark.stop()
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated by the 2.1.0 LXR engine. The LXR team |