spark-instrumented-optimizer/python/examples/wordcount.py

36 lines
1.3 KiB
Python
Executable file

#
# 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 sys
from operator import add
from pyspark import SparkContext
if __name__ == "__main__":
if len(sys.argv) < 3:
print >> sys.stderr, "Usage: wordcount <master> <file>"
exit(-1)
sc = SparkContext(sys.argv[1], "PythonWordCount")
lines = sc.textFile(sys.argv[2], 1)
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)