DataAnalysisIntro2.scala

DataAnalysisIntro2.scala

//CODE:
//The most popular category.
dataAov.map { x => x.categoryId } // select the categoryId field
    .countByValue()  // calculate how often each categoryId appears
    .toSeq
    .sortBy( - _._2) // sort by frequency in descending order
    .take(10) //take the top 10 records

//OUT:
//format: (categoryId, count)
ArrayBuffer(
(314,3068), 
(132,2229), 
(128,1770), // use this categoryid (128)
(270,1483), 
(139,1379), 
(107,1366), 
(177,1311), 
(226,1268), 
(103,1259),
(127,1204))