GraphX 的属性图

Posted 2020-08-09 见贤思小齐，知足常乐呵

package main.scala

import org.apache.spark.graphx.{Edge, Graph, VertexId}
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

object graph_test {
  
  // define hadoop_home directory
  System.setProperty("hadoop.home.dir","E:/zhuangji/winutil/")

  def main(args:Array[String]):Unit={

    val conf=new SparkConf().setMaster("local[2]").setAppName("graph_test")
    val sc=new SparkContext(conf)

    // VertexRDD & EdgeRDD to build graph
    val users:RDD[(VertexId,(String,String))]=
      sc.parallelize(Array((3L,("rxin","student")),(7L,("jgonzal","postdoc")),
                          (5L,("franklin","prof")),(2L,("istoica","prof"))))
    val relationships:RDD[Edge[String]]=
      sc.parallelize(Array(Edge(3L,7L,"collab"),Edge(5L,3L,"advisor"),
                           Edge(2L,5L,"colleague"),Edge(5L,7L,"pi")))

    val defaultUser=("John Doe","Missing")

    val graph=Graph(users,relationships,defaultUser)

    // graph.vertices & graph.edges to query graph
    println(graph.vertices.filter{case (id,(name,pos))=>pos=="prof"}.count)

    println(graph.edges.filter{case Edge(s,d,r)=>s<d}.count)  // 两者
    println(graph.edges.filter(e=>e.srcId<e.dstId).count)  // 等价
    
    // 三元组视图 graph.triplets could also query a graph
    val facts:RDD[String]=
      graph.triplets.map(triplet=>
         triplet.srcAttr._1 + " is the " + triplet.attr + " of " + triplet.dstAttr._1)
    facts.collect.foreach(println(_))

  }

}