Question

From the below code. what is the most appropriate next step in ML process?

val uniionRatingsRDD = ratingsRDD.union(newRatingsRDD)
val model = (new ALS.setRank(20).setIterations(10).run(unionRatingsRDD))

1. val predictionsForTestRDD = model.predict(ratingsRDD)
2. val model = ratingsRDD.split(userid,20)
3.val splits = ratingsRDD.randomSplit(Array(0.8,0.2),0L)
4. val topRecsForUser = model.recommendProducts(userid,5)

Answer 1

Hi@ritu,
The most appropriate step according to me is to do random split of your data set. After that you can train your model. So that it can find accurate parameters.