wfaria

from pyspark import SparkContext
	
dataFile = "./sbin/start-master.sh"	
sc = SparkContext("spark://ip-XXX-XX-X-XX.sa-east-1.compute.internal:7077", "Simple App")	
textRdd = sc.textFile(dataFile)	
print "Number of lines: ", textRdd.count()	
print "Number of lines with 8080: ", textRdd.filter(lambda x : '8080' in x).count()
sc.stop()