examples/src/main/python/streaming/queue_stream.py - master - githubmirror/spark

examples/src/main/python/streaming/queue_stream.py

49 строк2 KB

Bryan Cutler

[SPARK-16403][EXAMPLES] Cleanup to remove unused imports, consistent style, minor fixes

14 июл 2016, 11:12

14 июл 2016, 11:12e3f8a03

#
# 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.
#

"""
 Create a queue of RDDs that will be mapped/reduced one at a time in
 1 second intervals.

 To run this example use
    `$ bin/spark-submit examples/src/main/python/streaming/queue_stream.py
"""
import time

from pyspark import SparkContext
from pyspark.streaming import StreamingContext

if __name__ == "__main__":

    sc = SparkContext(appName="PythonStreamingQueueStream")
    ssc = StreamingContext(sc, 1)

    # Create the queue through which RDDs can be pushed to
    # a QueueInputDStream
    rddQueue = []
    for i in range(5):
        rddQueue += [ssc.sparkContext.parallelize([j for j in range(1, 1001)], 10)]

    # Create the QueueInputDStream and use it do some processing
    inputStream = ssc.queueStream(rddQueue)
    mappedStream = inputStream.map(lambda x: (x % 10, 1))
    reducedStream = mappedStream.reduceByKey(lambda a, b: a + b)
    reducedStream.pprint()

    ssc.start()
    time.sleep(6)
    ssc.stop(stopSparkContext=True, stopGraceFully=True)