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
51
52
53
54
55
56
57
58
59
60
61
|
#
# 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.
#
"""
Counts words in UTF8 encoded, '\n' delimited text received from the
network every second.
Usage: stateful_network_wordcount.py <hostname> <port>
<hostname> and <port> describe the TCP server that Spark Streaming
would connect to receive data.
To run this on your local machine, you need to first run a Netcat server
`$ nc -lk 9999`
and then run the example
`$ bin/spark-submit examples/src/main/python/streaming/stateful_network_wordcount.py \
localhost 9999`
"""
from __future__ import print_function
import sys
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
if __name__ == "__main__":
if len(sys.argv) != 3:
print("Usage: stateful_network_wordcount.py <hostname> <port>", file=sys.stderr)
exit(-1)
sc = SparkContext(appName="PythonStreamingStatefulNetworkWordCount")
ssc = StreamingContext(sc, 1)
ssc.checkpoint("checkpoint")
# RDD with initial state (key, value) pairs
initialStateRDD = sc.parallelize([(u'hello', 1), (u'world', 1)])
def updateFunc(new_values, last_sum):
return sum(new_values) + (last_sum or 0)
lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2]))
running_counts = lines.flatMap(lambda line: line.split(" "))\
.map(lambda word: (word, 1))\
.updateStateByKey(updateFunc, initialRDD=initialStateRDD)
running_counts.pprint()
ssc.start()
ssc.awaitTermination()
|
