GraphX中的mask函数理解

超、凢脫俗 2022-09-11 02:24 128阅读 0赞

做了一个关于mask函数的使用记录，以方便记忆

创建用于实验的图

import org.apache.spark._
    import org.apache.spark.graphx._
    // To make some of the examples work we will also need RDD
    import org.apache.spark.rdd.RDD
    
    // Create an RDD for the vertices
    val users: RDD[(VertexId, (String, String))] =
      sc.parallelize(Array((3L, ("rxin", "student")), (7L, ("jgonzal", "postdoc")),
                           (5L, ("franklin", "prof")), (2L, ("istoica", "prof")),
                           (4L, ("peter", "student"))))
    // Create an RDD for edges
    val relationships: RDD[Edge[String]] =
      sc.parallelize(Array(Edge(3L, 7L, "collab"),    Edge(5L, 3L, "advisor"),
                           Edge(2L, 5L, "colleague"), Edge(5L, 7L, "pi"),
                           Edge(4L, 0L, "student"),   Edge(5L, 0L, "colleague")))
    // Define a default user in case there are relationship with missing user
    val defaultUser = ("John Doe", "Missing")
    // Build the initial Graph
    val graph = Graph(users, relationships, defaultUser)
    /将生成的图的顶点输出展示一下
    scala> graph.vertices.collect.foreach(println(_))
    (0,(John Doe,Missing))
    (2,(istoica,prof))
    (3,(rxin,student))
    (4,(peter,student))
    (5,(franklin,prof))
    (7,(jgonzal,postdoc))
    /将生成的图的边输出展示一下
    scala> graph.edges.collect.foreach(println(_))
    Edge(3,7,collab)
    Edge(5,3,advisor)
    Edge(2,5,colleague)
    Edge(5,7,pi)

接下来进行mask操作

// Run Connected Components
    val ccGraph = graph.connectedComponents() // No longer contains missing field
    scala> ccGraph.vertices.collect.foreach(println(_))
    (0,0)
    (2,0)
    (3,0)
    (4,0)
    (5,0)
    (7,0)
    scala> ccGraph.edges.collect.foreach(println(_))
    Edge(3,7,collab)
    Edge(5,3,advisor)
    Edge(2,5,colleague)
    Edge(5,7,pi)
    Edge(4,0,student)
    Edge(5,0,colleague)
    
    // Remove missing vertices as well as the edges to connected to them
    val validGraph = graph.subgraph(vpred = (id, attr) => attr._2 != "Missing")
    scala> validGraph.vertices.collect.foreach(println(_))
    (2,(istoica,prof))                                                              
    (3,(rxin,student))
    (4,(peter,student))
    (5,(franklin,prof))
    (7,(jgonzal,postdoc))
    scala> validGraph.edges.collect.foreach(println(_))
    Edge(3,7,collab)
    Edge(5,3,advisor)
    Edge(2,5,colleague)
    Edge(5,7,pi)
    
    // Restrict the answer to the valid subgraph
    val validCCGraph = ccGraph.mask(validGraph)
    scala> validCCGraph.vertices.collect.foreach(println(_))//由下面输出可以看出，vertices是以ccGraph为主体进行操作
    (2,0)
    (3,0)
    (4,0)
    (5,0)
    (7,0)
    scala> validCCGraph.edges.collect.foreach(println(_))
    Edge(3,7,collab)
    Edge(5,3,advisor)
    Edge(2,5,colleague)
    Edge(5,7,pi)
    
    //咱们进行相反的mask操作
    
    val ccvalidGrap=validGraph.mask(ccGraph)
    scala> ccvalidGrap.vertices.collect.foreach(println(_))//由输出可看出这次的vertices是以validGraph为主体进行操作
    (2,(istoica,prof))
    (3,(rxin,student))
    (4,(peter,student))
    (5,(franklin,prof))
    (7,(jgonzal,postdoc))
    scala> ccvalidGrap.edges.collect.foreach(println(_))
    Edge(3,7,collab)
    Edge(5,3,advisor)
    Edge(2,5,colleague)
    Edge(5,7,pi)

记录完成