DataAnalysisIntro3.scala

DataAnalysisIntro3.scala

//CODE:
val interestedBrowsers = List("Android", "OS X", "iOS", "Linux", "Windows")
val osAov = dataAov.filter(x => interestedBrowsers.contains(x.osFamily)) //we leave only the desired OS
    .filter(_.categoryId == 128) // filter categories
    .map(x => (x.osFamily, (x.aov, 1.0))) // need to calculate average purchase amount
    .reduceByKey((x, y) => (x._1 + y._1, x._2 + y._2))
    .map{ case(osFamily, (revenue, orders)) => (osFamily, revenue/orders) }
    .collect()
 
//OUT
//The output is an array of tuples (tuple) in OS format, the average purchase amount:
Array(
(OS X,4859.827586206897), 
(Linux,3730.4347826086955), 
(iOS,3964.6153846153848), 
(Android,3670.8474576271187),
(Windows,3261.030993042378))