Skip to content

Instantly share code, notes, and snippets.

@Mwea
Last active December 22, 2017 13:54
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save Mwea/b434414d17f9e85b7d982ec7fc5a8cda to your computer and use it in GitHub Desktop.
Save Mwea/b434414d17f9e85b7d982ec7fc5a8cda to your computer and use it in GitHub Desktop.
#
# 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 __future__ import print_function
import sys
from operator import add
from pyspark.sql import SparkSession
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: wordcount <file>", file=sys.stderr)
exit(-1)
spark = SparkSession\
.builder\
.appName("PythonWordCount")\
.getOrCreate()
lines = spark.read.text(sys.argv[1]).rdd.map(lambda r: r[0])
counts = lines.flatMap(lambda x: x.split(' ')) \
.map(lambda x: (x, 1)) \
.reduceByKey(add)
output = counts.collect()
for (word, count) in output:
print("%s: %i" % (word, count))
spark.stop()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment