SSC.py
1.05 KB
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
__author__ = 'chunk'
from ..common import *
from . import *
from .dependencies import *
from .SC import *
import sys
from pyspark import SparkConf, SparkContext
from pyspark.streaming import StreamingContext
class StreamSparker(Sparker):
def __init__(self, host='HPC-server', appname='NewPySparkStreamingApp', source='localhost', port=9999, **kwargs):
Sparker.__init__(self, host, appname)
self.source = source
self.port = port
self.ssc = StreamingContext(sparkContext=self.sc, batchDuration=1)
def start(self):
self.ssc.start()
self.ssc.awaitTermination()
def set_datasource(self, source='localhost', port=9999):
self.source = source
self.port = port
def _word_count(self):
lines = self.ssc.socketTextStream(self.source, self.port)
words = lines.flatMap(lambda line: line.split(" "))
pairs = words.map(lambda word: (word, 1))
wordCounts = pairs.reduceByKey(lambda x, y: x + y)
wordCounts.pprint()
self.start()