SPARK

Building a Recommendation Engine

import org.apache.spark.mllib.recommendation.ALS
import org.apache.spark.mllib.recommendation.Rating
import org.apache.spark.SparkConf
//Import other necessary packages
object Movie {
def main(args: Array[String]) {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("Movie").setMaster("local[2]")
val sc = new SparkContext(conf)
val rawData = sc.textFile("/home/mouli/Downloads/ml-100k/u.data")
//rawData.first()
val rawRatings = rawData.map(_.split("\t").take(3))
val ratings = rawRatings.map { case Array(user, movie, rating) => Rating(user.toInt, movie.toInt, rating.toDouble) }
//Training the data
//rank = 50, iteration = 10, lambda = 0.0.1
val model = ALS.train(ratings, 50, 5, 0.01)
model.userFeatures
model.userFeatures.count
model.productFeatures.count
//test the model
val predictedRating = model.predict(789, 123)
//generate recommendations
val userId = 789
val K = 10
val topKRecs = model.recommendProducts(userId, K)
println(topKRecs.mkString("\n"))
val movies = sc.textFile("/home/mouli/Downloads/ml-100k/u.item")
val titles = movies.map(line => line.split("\\|").take(2)).map(array => (array(0).toInt,array(1))).collectAsMap()
titles(123)
val moviesForUser = ratings.keyBy(_.user).lookup(789)
println(moviesForUser.size)
moviesForUser.sortBy(-_.rating).take(10).map(rating => (titles(rating.product), rating.rating)).foreach(println)
}