MLlib协同过滤ALS算法的示例分析

这期内容当中小编将会给大家带来有关MLlib协同过滤ALS算法的示例分析，文章内容丰富且以专业的角度为大家分析和叙述，阅读完这篇文章希望大家可以有所收获。

ALS算法做协同过滤大致就是建立用户商品矩阵，根据评分值以解数独的形式解出来

import java.text.SimpleDateFormatimport java.util.Dateimport org.apache.spark.mllib.recommendation.{ALS, Rating }import org.apache.spark.{SparkContext, SparkConf}/** * Created by hadoop on 2015/7/20. */object MLlibCF {  def main(args: Array[String]) {    val time = new SimpleDateFormat("MMddHHmm").format(new Date())    val sparkConf = new SparkConf().setAppName("MLlibCF-"+time)    sparkConf.set("mapreduce.framework.name", "yarn")    sparkConf.set("spark.rdd.compress", "true")//是否需要压缩序列化的rdd分区，牺牲cpu时间提高空间利用率    sparkConf.set("spark.serializer","org.apache.spark.serializer.KryoSerializer")//配置序列化的接口    sparkConf.set("spark.storage.memoryFraction", "0.2")    sparkConf.set("spark.scheduler.mode", "FAIR")    sparkConf.set("spark.ui.port", "4042")    sparkConf.set("spark.akka.frameSize", "100")    val sc = new SparkContext(sparkConf)    val data = sc.textFile("hdfs://namenode:9000/data/test_in/mahout1.txt", 1)    //对读取的文件进行预处理，并放入Rating容器中    val ratings = data.map(_.split(",") match{      case(Array(user, product, rate))        => Rating(user.toInt, product.toInt, rate.toDouble)    })    //需要求出的值    val user1 = sc.parallelize(List("1,105","1,106","2,105","2,107","3,102")).map(    _.split(",") match {      case (Array(user, product))      => (user.toInt, product.toInt)    })    val rank = 10    val numIterations = 20    //建立ALS模型    val model = ALS.train(ratings, rank, numIterations, 0.01)        //读取需要的值    val predictions = model.predict(user1).map{      case Rating(user, product, rate)        => ((user, product), rate)    }    predictions.saveAsTextFile("hdfs://10.207.0.217:9000/data/test_out/zk/MLlib-"+time)  }}

上述就是小编为大家分享的MLlib协同过滤ALS算法的示例分析了，如果刚好有类似的疑惑，不妨参照上述分析进行理解。如果想知道更多相关知识，欢迎关注行业资讯频道。