x=sc.textFile("/home/amel/1MB").filter(!_.contains("NULL"))
.filter(!_.contains("Null"))
val re = x.map(row => {
val cols = row.split(",")
val Cycle = cols(2)
val Duration = Cycle match {
case "Licence" => "3 years"
case "Master" => "2 years"
case "Ingéniorat" => "5 years"
case "Ingeniorat" => "5 years"
case "Doctorat" => "3 years"
case _ => "NULL"
}
(cols(1).split("-")(0) + "," + Cycle + "," + Duration + "," +
cols(3), 1)
}).reduceByKey(_ + _)
re.collect.foreach(println)
}