PageRank 算法

package com.sdcet

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * Created by Administrator on 2017/2/10.
  */
object PageRank {
  def main(args: Array[String]) {
    System.setProperty("hadoop.home.dir", "E:\\winutils-hadoop-2.6.4\\hadoop-2.6.4")
    val conf = new SparkConf().setAppName("PageRank").setMaster("local")
    val sc = new SparkContext(conf)
    val links: RDD[(String, Array[String])] = sc.parallelize(Array(("A", Array("d")), ("B", Array("A")), ("C", Array("A", "B")), ("D", Array("A", "C"))), 2)
    var rank: RDD[(String, Double)] = sc.parallelize(Array(("A", 1.0), ("B", 1.0), ("C", 1.0), ("D", 1.0)), 2)
    for (i <- 1 to 10) {
      val contribs = links.join(rank, 2).flatMap {
        case (url, (links, rank)) => links.map(dest => (dest, rank / links.size))
      }
      rank = contribs.reduceByKey(_ + _, 2).mapValues(0.15 + 0.85 * _)
    }
    println("rank:"+rank)
    rank.saveAsTextFile("hdfs://hadoop1:9000/pageRank")
  }
}