|
||||
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 from operator import add 0022 0023 from pyspark.sql import SparkSession 0024 0025 0026 if __name__ == "__main__": 0027 if len(sys.argv) != 2: 0028 print("Usage: wordcount <file>", file=sys.stderr) 0029 sys.exit(-1) 0030 0031 spark = SparkSession\ 0032 .builder\ 0033 .appName("PythonWordCount")\ 0034 .getOrCreate() 0035 0036 lines = spark.read.text(sys.argv[1]).rdd.map(lambda r: r[0]) 0037 counts = lines.flatMap(lambda x: x.split(' ')) \ 0038 .map(lambda x: (x, 1)) \ 0039 .reduceByKey(add) 0040 output = counts.collect() 0041 for (word, count) in output: 0042 print("%s: %i" % (word, count)) 0043 0044 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 |