blob: dcd6a0fc6ff91ec3f609665e68922a6b58d7f1a8 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
#
# 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 sys
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 xrange(5):
rddQueue += [ssc.sparkContext.parallelize([j for j in xrange(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)
|