package com.test import org.apache.spark.graphx._ import org.apache.spark.rdd.RDD import org.apache.spark.sql.{SaveMode, SparkSession} import scala.collection.mutable.ListBuffer object GraphxDHDemo { def main(args: Array[String]): Unit = { val spark = SparkSession.builder().master("local[*]").appName("yy").getOrCreate() val sc = spark.sparkContext sc.setLogLevel("ERROR") val input_1 = ListBuffer( 1,2,3,4,5,6,7,8,9,10 ) val input_2 = ListBuffer( List(3,1) ,List(1,4) ,List(2,5) ,List(5,6) ,List(7,3) ,List(9,7) ,List(10,3) ,List(8,7) ) // 构建顶点的rdd val input1 = input_1.map(x => (x.toLong,(x.toString,1))) // 构建边的rdd val input2 = input_2.distinct.map(x => Edge(x(0).toLong, x(1).toLong, 1)) //创建顶点RDD val users: RDD[(VertexId, (String, PartitionID))] = sc.makeRDD(input1) //创建各顶点间关系的RDD val
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)