Sandeep Giri girisandeep

## apache_log_topnlinks.scala
var accessLogs = sc.textFile("/data/spark/project/access/access.log.45.gz")

//Check whats in the RDD. Each record of accessLogs RDDs should be the line //from the files in folder
accessLogs.take(10)

//Keep only the lines which have IP
def containsIP(line:String):Boolean = return line matches "^([0-9\\.]+) .*$"
var ipaccesslogs = accessLogs.filter(containsIP)

//Extract only IP
	var accessLogs = sc.textFile("/data/spark/project/access/access.log.45.gz")

	//Check whats in the RDD. Each record of accessLogs RDDs should be the line //from the files in folder
	accessLogs.take(10)

	//Keep only the lines which have IP
	def containsIP(line:String):Boolean = return line matches "^([0-9\\.]+) .*$"
	var ipaccesslogs = accessLogs.filter(containsIP)

	//Extract only IP