Apache Spark 2.2.0 中文文档 - GraphX Programming Guide | ApacheCN

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

class VertexProperty()
case class UserProperty(val name: String) extends VertexProperty
case class ProductProperty(val name: String, val price: Double) extends VertexProperty
// The graph might then have the type:
var graph: Graph[VertexProperty, String] = null

class Graph[VD, ED] {
  val vertices: VertexRDD[VD]
  val edges: EdgeRDD[ED]
}

val userGraph: Graph[(String, String), String]

// Assume the SparkContext has already been constructed
val sc: SparkContext
// 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"))))
// 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")))
// 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)

val graph: Graph[(String, String), String] // Constructed from above
// Count all users which are postdocs
graph.vertices.filter { case (id, (name, pos)) => pos == "postdoc" }.count
// Count all the edges where src > dst
graph.edges.filter(e => e.srcId > e.dstId).count

graph.edges.filter { case Edge(src, dst, prop) => src > dst }.count

SELECT src.id, dst.id, src.attr, e.attr, dst.attr
FROM edges AS e LEFT JOIN vertices AS src, vertices AS dst
ON e.srcId = src.Id AND e.dstId = dst.Id

val graph: Graph[(String, String), String] // Constructed from above
// Use the triplets view to create an RDD of facts.
val facts: RDD[String] =
  graph.triplets.map(triplet =>
    triplet.srcAttr._1 + " is the " + triplet.attr + " of " + triplet.dstAttr._1)
facts.collect.foreach(println(_))

val graph: Graph[(String, String), String]
// Use the implicit GraphOps.inDegrees operator
val inDegrees: VertexRDD[Int] = graph.inDegrees

/** Summary of the functionality in the property graph */
class Graph[VD, ED] {
  // Information about the Graph ===================================================================
  val numEdges: Long
  val numVertices: Long
  val inDegrees: VertexRDD[Int]
  val outDegrees: VertexRDD[Int]
  val degrees: VertexRDD[Int]
  // Views of the graph as collections =============================================================
  val vertices: VertexRDD[VD]
  val edges: EdgeRDD[ED]
  val triplets: RDD[EdgeTriplet[VD, ED]]
  // Functions for caching graphs ==================================================================
  def persist(newLevel: StorageLevel = StorageLevel.MEMORY_ONLY): Graph[VD, ED]
  def cache(): Graph[VD, ED]
  def unpersistVertices(blocking: Boolean = true): Graph[VD, ED]
  // Change the partitioning heuristic  ============================================================
  def partitionBy(partitionStrategy: PartitionStrategy): Graph[VD, ED]
  // Transform vertex and edge attributes ==========================================================
  def mapVertices[VD2](map: (VertexId, VD) => VD2): Graph[VD2, ED]
  def mapEdges[ED2](map: Edge[ED] => ED2): Graph[VD, ED2]
  def mapEdges[ED2](map: (PartitionID, Iterator[Edge[ED]]) => Iterator[ED2]): Graph[VD, ED2]
  def mapTriplets[ED2](map: EdgeTriplet[VD, ED] => ED2): Graph[VD, ED2]
  def mapTriplets[ED2](map: (PartitionID, Iterator[EdgeTriplet[VD, ED]]) => Iterator[ED2])
    : Graph[VD, ED2]
  // Modify the graph structure ====================================================================
  def reverse: Graph[VD, ED]
  def subgraph(
      epred: EdgeTriplet[VD,ED] => Boolean = (x => true),
      vpred: (VertexId, VD) => Boolean = ((v, d) => true))
    : Graph[VD, ED]
  def mask[VD2, ED2](other: Graph[VD2, ED2]): Graph[VD, ED]
  def groupEdges(merge: (ED, ED) => ED): Graph[VD, ED]
  // Join RDDs with the graph ======================================================================
  def joinVertices[U](table: RDD[(VertexId, U)])(mapFunc: (VertexId, VD, U) => VD): Graph[VD, ED]
  def outerJoinVertices[U, VD2](other: RDD[(VertexId, U)])
      (mapFunc: (VertexId, VD, Option[U]) => VD2)
    : Graph[VD2, ED]
  // Aggregate information about adjacent triplets =================================================
  def collectNeighborIds(edgeDirection: EdgeDirection): VertexRDD[Array[VertexId]]
  def collectNeighbors(edgeDirection: EdgeDirection): VertexRDD[Array[(VertexId, VD)]]
  def aggregateMessages[Msg: ClassTag](
      sendMsg: EdgeContext[VD, ED, Msg] => Unit,
      mergeMsg: (Msg, Msg) => Msg,
      tripletFields: TripletFields = TripletFields.All)
    : VertexRDD[A]
  // Iterative graph-parallel computation ==========================================================
  def pregel[A](initialMsg: A, maxIterations: Int, activeDirection: EdgeDirection)(
      vprog: (VertexId, VD, A) => VD,
      sendMsg: EdgeTriplet[VD, ED] => Iterator[(VertexId,A)],
      mergeMsg: (A, A) => A)
    : Graph[VD, ED]
  // Basic graph algorithms ========================================================================
  def pageRank(tol: Double, resetProb: Double = 0.15): Graph[Double, Double]
  def connectedComponents(): Graph[VertexId, ED]
  def triangleCount(): Graph[Int, ED]
  def stronglyConnectedComponents(numIter: Int): Graph[VertexId, ED]
}

class Graph[VD, ED] {
  def mapVertices[VD2](map: (VertexId, VD) => VD2): Graph[VD2, ED]
  def mapEdges[ED2](map: Edge[ED] => ED2): Graph[VD, ED2]
  def mapTriplets[ED2](map: EdgeTriplet[VD, ED] => ED2): Graph[VD, ED2]
}

val newVertices = graph.vertices.map { case (id, attr) => (id, mapUdf(id, attr)) }
val newGraph = Graph(newVertices, graph.edges)

val newGraph = graph.mapVertices((id, attr) => mapUdf(id, attr))

// Given a graph where the vertex property is the out degree
val inputGraph: Graph[Int, String] =
  graph.outerJoinVertices(graph.outDegrees)((vid, _, degOpt) => degOpt.getOrElse(0))
// Construct a graph where each edge contains the weight
// and each vertex is the initial PageRank
val outputGraph: Graph[Double, Double] =
  inputGraph.mapTriplets(triplet => 1.0 / triplet.srcAttr).mapVertices((id, _) => 1.0)

class Graph[VD, ED] {
  def reverse: Graph[VD, ED]
  def subgraph(epred: EdgeTriplet[VD,ED] => Boolean,
               vpred: (VertexId, VD) => Boolean): Graph[VD, ED]
  def mask[VD2, ED2](other: Graph[VD2, ED2]): Graph[VD, ED]
  def groupEdges(merge: (ED, ED) => ED): Graph[VD,ED]
}

// 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)
// Notice that there is a user 0 (for which we have no information) connected to users
// 4 (peter) and 5 (franklin).
graph.triplets.map(
  triplet => triplet.srcAttr._1 + " is the " + triplet.attr + " of " + triplet.dstAttr._1
).collect.foreach(println(_))
// Remove missing vertices as well as the edges to connected to them
val validGraph = graph.subgraph(vpred = (id, attr) => attr._2 != "Missing")
// The valid subgraph will disconnect users 4 and 5 by removing user 0
validGraph.vertices.collect.foreach(println(_))
validGraph.triplets.map(
  triplet => triplet.srcAttr._1 + " is the " + triplet.attr + " of " + triplet.dstAttr._1
).collect.foreach(println(_))

// Run Connected Components
val ccGraph = graph.connectedComponents() // No longer contains missing field
// Remove missing vertices as well as the edges to connected to them
val validGraph = graph.subgraph(vpred = (id, attr) => attr._2 != "Missing")
// Restrict the answer to the valid subgraph
val validCCGraph = ccGraph.mask(validGraph)

class Graph[VD, ED] {
  def joinVertices[U](table: RDD[(VertexId, U)])(map: (VertexId, VD, U) => VD)
    : Graph[VD, ED]
  def outerJoinVertices[U, VD2](table: RDD[(VertexId, U)])(map: (VertexId, VD, Option[U]) => VD2)
    : Graph[VD2, ED]
}

val nonUniqueCosts: RDD[(VertexId, Double)]
val uniqueCosts: VertexRDD[Double] =
  graph.vertices.aggregateUsingIndex(nonUnique, (a,b) => a + b)
val joinedGraph = graph.joinVertices(uniqueCosts)(
  (id, oldCost, extraCost) => oldCost + extraCost)

val outDegrees: VertexRDD[Int] = graph.outDegrees
val degreeGraph = graph.outerJoinVertices(outDegrees) { (id, oldAttr, outDegOpt) =>
  outDegOpt match {
    case Some(outDeg) => outDeg
    case None => 0 // No outDegree means zero outDegree
  }
}

val joinedGraph = graph.joinVertices(uniqueCosts,
  (id: VertexId, oldCost: Double, extraCost: Double) => oldCost + extraCost)

class Graph[VD, ED] {
  def aggregateMessages[Msg: ClassTag](
      sendMsg: EdgeContext[VD, ED, Msg] => Unit,
      mergeMsg: (Msg, Msg) => Msg,
      tripletFields: TripletFields = TripletFields.All)
    : VertexRDD[Msg]
}

import org.apache.spark.graphx.{Graph, VertexRDD}
import org.apache.spark.graphx.util.GraphGenerators

// Create a graph with "age" as the vertex property.
// Here we use a random graph for simplicity.
val graph: Graph[Double, Int] =
  GraphGenerators.logNormalGraph(sc, numVertices = 100).mapVertices( (id, _) => id.toDouble )
// Compute the number of older followers and their total age
val olderFollowers: VertexRDD[(Int, Double)] = graph.aggregateMessages[(Int, Double)](
  triplet => { // Map Function
    if (triplet.srcAttr > triplet.dstAttr) {
      // Send message to destination vertex containing counter and age
      triplet.sendToDst(1, triplet.srcAttr)
    }
  },
  // Add counter and age
  (a, b) => (a._1 + b._1, a._2 + b._2) // Reduce Function
)
// Divide total age by number of older followers to get average age of older followers
val avgAgeOfOlderFollowers: VertexRDD[Double] =
  olderFollowers.mapValues( (id, value) =>
    value match { case (count, totalAge) => totalAge / count } )
// Display the results
avgAgeOfOlderFollowers.collect.foreach(println(_))

class Graph[VD, ED] {
  def mapReduceTriplets[Msg](
      map: EdgeTriplet[VD, ED] => Iterator[(VertexId, Msg)],
      reduce: (Msg, Msg) => Msg)
    : VertexRDD[Msg]
}

val graph: Graph[Int, Float] = ...
def msgFun(triplet: Triplet[Int, Float]): Iterator[(Int, String)] = {
  Iterator((triplet.dstId, "Hi"))
}
def reduceFun(a: String, b: String): String = a + " " + b
val result = graph.mapReduceTriplets[String](msgFun, reduceFun)

val graph: Graph[Int, Float] = ...
def msgFun(triplet: EdgeContext[Int, Float, String]) {
  triplet.sendToDst("Hi")
}
def reduceFun(a: String, b: String): String = a + " " + b
val result = graph.aggregateMessages[String](msgFun, reduceFun)

// Define a reduce operation to compute the highest degree vertex
def max(a: (VertexId, Int), b: (VertexId, Int)): (VertexId, Int) = {
  if (a._2 > b._2) a else b
}
// Compute the max degrees
val maxInDegree: (VertexId, Int)  = graph.inDegrees.reduce(max)
val maxOutDegree: (VertexId, Int) = graph.outDegrees.reduce(max)
val maxDegrees: (VertexId, Int)   = graph.degrees.reduce(max)

class GraphOps[VD, ED] {
  def collectNeighborIds(edgeDirection: EdgeDirection): VertexRDD[Array[VertexId]]
  def collectNeighbors(edgeDirection: EdgeDirection): VertexRDD[ Array[(VertexId, VD)] ]
}

class GraphOps[VD, ED] {
  def pregel[A]
      (initialMsg: A,
       maxIter: Int = Int.MaxValue,
       activeDir: EdgeDirection = EdgeDirection.Out)
      (vprog: (VertexId, VD, A) => VD,
       sendMsg: EdgeTriplet[VD, ED] => Iterator[(VertexId, A)],
       mergeMsg: (A, A) => A)
    : Graph[VD, ED] = {
    // Receive the initial message at each vertex
    var g = mapVertices( (vid, vdata) => vprog(vid, vdata, initialMsg) ).cache()

    // compute the messages
    var messages = g.mapReduceTriplets(sendMsg, mergeMsg)
    var activeMessages = messages.count()
    // Loop until no messages remain or maxIterations is achieved
    var i = 0
    while (activeMessages > 0 && i < maxIterations) {
      // Receive the messages and update the vertices.
      g = g.joinVertices(messages)(vprog).cache()
      val oldMessages = messages
      // Send new messages, skipping edges where neither side received a message. We must cache
      // messages so it can be materialized on the next line, allowing us to uncache the previous
      // iteration.
      messages = GraphXUtils.mapReduceTriplets(
        g, sendMsg, mergeMsg, Some((oldMessages, activeDirection))).cache()
      activeMessages = messages.count()
      i += 1
    }
    g
  }
}

import org.apache.spark.graphx.{Graph, VertexId}
import org.apache.spark.graphx.util.GraphGenerators

// A graph with edge attributes containing distances
val graph: Graph[Long, Double] =
  GraphGenerators.logNormalGraph(sc, numVertices = 100).mapEdges(e => e.attr.toDouble)
val sourceId: VertexId = 42 // The ultimate source
// Initialize the graph such that all vertices except the root have distance infinity.
val initialGraph = graph.mapVertices((id, _) =>
    if (id == sourceId) 0.0 else Double.PositiveInfinity)
val sssp = initialGraph.pregel(Double.PositiveInfinity)(
  (id, dist, newDist) => math.min(dist, newDist), // Vertex Program
  triplet => {  // Send Message
    if (triplet.srcAttr + triplet.attr < triplet.dstAttr) {
      Iterator((triplet.dstId, triplet.srcAttr + triplet.attr))
    } else {
      Iterator.empty
    }
  },
  (a, b) => math.min(a, b) // Merge Message
)
println(sssp.vertices.collect.mkString("\n"))

object GraphLoader {
  def edgeListFile(
      sc: SparkContext,
      path: String,
      canonicalOrientation: Boolean = false,
      minEdgePartitions: Int = 1)
    : Graph[Int, Int]
}

# This is a comment
2 1
4 1
1 2

object Graph {
  def apply[VD, ED](
      vertices: RDD[(VertexId, VD)],
      edges: RDD[Edge[ED]],
      defaultVertexAttr: VD = null)
    : Graph[VD, ED]

  def fromEdges[VD, ED](
      edges: RDD[Edge[ED]],
      defaultValue: VD): Graph[VD, ED]

  def fromEdgeTuples[VD](
      rawEdges: RDD[(VertexId, VertexId)],
      defaultValue: VD,
      uniqueEdges: Option[PartitionStrategy] = None): Graph[VD, Int]

}

class VertexRDD[VD] extends RDD[(VertexId, VD)] {
  // Filter the vertex set but preserves the internal index
  def filter(pred: Tuple2[VertexId, VD] => Boolean): VertexRDD[VD]
  // Transform the values without changing the ids (preserves the internal index)
  def mapValues[VD2](map: VD => VD2): VertexRDD[VD2]
  def mapValues[VD2](map: (VertexId, VD) => VD2): VertexRDD[VD2]
  // Show only vertices unique to this set based on their VertexId's
  def minus(other: RDD[(VertexId, VD)])
  // Remove vertices from this set that appear in the other set
  def diff(other: VertexRDD[VD]): VertexRDD[VD]
  // Join operators that take advantage of the internal indexing to accelerate joins (substantially)
  def leftJoin[VD2, VD3](other: RDD[(VertexId, VD2)])(f: (VertexId, VD, Option[VD2]) => VD3): VertexRDD[VD3]
  def innerJoin[U, VD2](other: RDD[(VertexId, U)])(f: (VertexId, VD, U) => VD2): VertexRDD[VD2]
  // Use the index on this RDD to accelerate a `reduceByKey` operation on the input RDD.
  def aggregateUsingIndex[VD2](other: RDD[(VertexId, VD2)], reduceFunc: (VD2, VD2) => VD2): VertexRDD[VD2]
}

val setA: VertexRDD[Int] = VertexRDD(sc.parallelize(0L until 100L).map(id => (id, 1)))
val rddB: RDD[(VertexId, Double)] = sc.parallelize(0L until 100L).flatMap(id => List((id, 1.0), (id, 2.0)))
// There should be 200 entries in rddB
rddB.count
val setB: VertexRDD[Double] = setA.aggregateUsingIndex(rddB, _ + _)
// There should be 100 entries in setB
setB.count
// Joining A and B should now be fast!
val setC: VertexRDD[Double] = setA.innerJoin(setB)((id, a, b) => a + b)

// Transform the edge attributes while preserving the structure
def mapValues[ED2](f: Edge[ED] => ED2): EdgeRDD[ED2]
// Reverse the edges reusing both attributes and structure
def reverse: EdgeRDD[ED]
// Join two `EdgeRDD`s partitioned using the same partitioning strategy.
def innerJoin[ED2, ED3](other: EdgeRDD[ED2])(f: (VertexId, VertexId, ED, ED2) => ED3): EdgeRDD[ED3]

import org.apache.spark.graphx.GraphLoader

// Load the edges as a graph
val graph = GraphLoader.edgeListFile(sc, "data/graphx/followers.txt")
// Run PageRank
val ranks = graph.pageRank(0.0001).vertices
// Join the ranks with the usernames
val users = sc.textFile("data/graphx/users.txt").map { line =>
  val fields = line.split(",")
  (fields(0).toLong, fields(1))
}
val ranksByUsername = users.join(ranks).map {
  case (id, (username, rank)) => (username, rank)
}
// Print the result
println(ranksByUsername.collect().mkString("\n"))

import org.apache.spark.graphx.GraphLoader

// Load the graph as in the PageRank example
val graph = GraphLoader.edgeListFile(sc, "data/graphx/followers.txt")
// Find the connected components
val cc = graph.connectedComponents().vertices
// Join the connected components with the usernames
val users = sc.textFile("data/graphx/users.txt").map { line =>
  val fields = line.split(",")
  (fields(0).toLong, fields(1))
}
val ccByUsername = users.join(cc).map {
  case (id, (username, cc)) => (username, cc)
}
// Print the result
println(ccByUsername.collect().mkString("\n"))

import org.apache.spark.graphx.{GraphLoader, PartitionStrategy}

// Load the edges in canonical order and partition the graph for triangle count
val graph = GraphLoader.edgeListFile(sc, "data/graphx/followers.txt", true)
  .partitionBy(PartitionStrategy.RandomVertexCut)
// Find the triangle count for each vertex
val triCounts = graph.triangleCount().vertices
// Join the triangle counts with the usernames
val users = sc.textFile("data/graphx/users.txt").map { line =>
  val fields = line.split(",")
  (fields(0).toLong, fields(1))
}
val triCountByUsername = users.join(triCounts).map { case (id, (username, tc)) =>
  (username, tc)
}
// Print the result
println(triCountByUsername.collect().mkString("\n"))

import org.apache.spark.graphx.GraphLoader

// Load my user data and parse into tuples of user id and attribute list
val users = (sc.textFile("data/graphx/users.txt")
  .map(line => line.split(",")).map( parts => (parts.head.toLong, parts.tail) ))

// Parse the edge data which is already in userId -> userId format
val followerGraph = GraphLoader.edgeListFile(sc, "data/graphx/followers.txt")

// Attach the user attributes
val graph = followerGraph.outerJoinVertices(users) {
  case (uid, deg, Some(attrList)) => attrList
  // Some users may not have attributes so we set them as empty
  case (uid, deg, None) => Array.empty[String]
}

// Restrict the graph to users with usernames and names
val subgraph = graph.subgraph(vpred = (vid, attr) => attr.size == 2)

// Compute the PageRank
val pagerankGraph = subgraph.pageRank(0.001)

// Get the attributes of the top pagerank users
val userInfoWithPageRank = subgraph.outerJoinVertices(pagerankGraph.vertices) {
  case (uid, attrList, Some(pr)) => (pr, attrList.toList)
  case (uid, attrList, None) => (0.0, attrList.toList)
}

println(userInfoWithPageRank.vertices.top(5)(Ordering.by(_._2._1)).mkString("\n"))