In [8]:
from collections import namedtuple
from random import randint
LogLine = namedtuple('LogLine', ['ts', 'msg',
'processed', 'dictionary', 'supportId'])
logList = list()
for i in range(1000):
a = LogLine(int(i),'message=%i'%i,None,None,int(randint(1,5)))
logList.append(a)
rddlogLines= sc.parallelize(logList)
In [5]:
sc.addPyFile('magichour.zip')
In [7]:
from magichour.api.dist.events.eventEval import eventEvalRDD
In [9]:
eventDefs = 'hdfs://namenode/magichour/eventDefs'
windowSeconds = 500
testing = eventEvalRDD(sc,rddlogLines,eventDefs,windowSeconds)
In [10]:
testing.collect()
In [ ]: