diff options
Diffstat (limited to 'graphx')
15 files changed, 50 insertions, 46 deletions
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala b/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala index 058c8c8aa1..ce1054ed92 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala @@ -26,8 +26,8 @@ class EdgeDirection private (private val name: String) extends Serializable { * out becomes in and both and either remain the same. */ def reverse: EdgeDirection = this match { - case EdgeDirection.In => EdgeDirection.Out - case EdgeDirection.Out => EdgeDirection.In + case EdgeDirection.In => EdgeDirection.Out + case EdgeDirection.Out => EdgeDirection.In case EdgeDirection.Either => EdgeDirection.Either case EdgeDirection.Both => EdgeDirection.Both } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/EdgeTriplet.scala b/graphx/src/main/scala/org/apache/spark/graphx/EdgeTriplet.scala index c8790cac3d..65f82429d2 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/EdgeTriplet.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/EdgeTriplet.scala @@ -37,7 +37,7 @@ class EdgeTriplet[VD, ED] extends Edge[ED] { /** * Set the edge properties of this triplet. */ - protected[spark] def set(other: Edge[ED]): EdgeTriplet[VD,ED] = { + protected[spark] def set(other: Edge[ED]): EdgeTriplet[VD, ED] = { srcId = other.srcId dstId = other.dstId attr = other.attr diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala index 36dc7b0f86..db73a8abc5 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/Graph.scala @@ -316,7 +316,7 @@ abstract class Graph[VD: ClassTag, ED: ClassTag] protected () extends Serializab * satisfy the predicates */ def subgraph( - epred: EdgeTriplet[VD,ED] => Boolean = (x => true), + epred: EdgeTriplet[VD, ED] => Boolean = (x => true), vpred: (VertexId, VD) => Boolean = ((v, d) => true)) : Graph[VD, ED] diff --git a/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala b/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala index 7edd627b20..9451ff1e5c 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/GraphOps.scala @@ -124,18 +124,18 @@ class GraphOps[VD: ClassTag, ED: ClassTag](graph: Graph[VD, ED]) extends Seriali def collectNeighbors(edgeDirection: EdgeDirection): VertexRDD[Array[(VertexId, VD)]] = { val nbrs = edgeDirection match { case EdgeDirection.Either => - graph.aggregateMessages[Array[(VertexId,VD)]]( + graph.aggregateMessages[Array[(VertexId, VD)]]( ctx => { ctx.sendToSrc(Array((ctx.dstId, ctx.dstAttr))) ctx.sendToDst(Array((ctx.srcId, ctx.srcAttr))) }, (a, b) => a ++ b, TripletFields.All) case EdgeDirection.In => - graph.aggregateMessages[Array[(VertexId,VD)]]( + graph.aggregateMessages[Array[(VertexId, VD)]]( ctx => ctx.sendToDst(Array((ctx.srcId, ctx.srcAttr))), (a, b) => a ++ b, TripletFields.Src) case EdgeDirection.Out => - graph.aggregateMessages[Array[(VertexId,VD)]]( + graph.aggregateMessages[Array[(VertexId, VD)]]( ctx => ctx.sendToSrc(Array((ctx.dstId, ctx.dstAttr))), (a, b) => a ++ b, TripletFields.Dst) case EdgeDirection.Both => @@ -253,7 +253,7 @@ class GraphOps[VD: ClassTag, ED: ClassTag](graph: Graph[VD, ED]) extends Seriali def filter[VD2: ClassTag, ED2: ClassTag]( preprocess: Graph[VD, ED] => Graph[VD2, ED2], epred: (EdgeTriplet[VD2, ED2]) => Boolean = (x: EdgeTriplet[VD2, ED2]) => true, - vpred: (VertexId, VD2) => Boolean = (v:VertexId, d:VD2) => true): Graph[VD, ED] = { + vpred: (VertexId, VD2) => Boolean = (v: VertexId, d: VD2) => true): Graph[VD, ED] = { graph.mask(preprocess(graph).subgraph(epred, vpred)) } @@ -356,7 +356,7 @@ class GraphOps[VD: ClassTag, ED: ClassTag](graph: Graph[VD, ED]) extends Seriali maxIterations: Int = Int.MaxValue, activeDirection: EdgeDirection = EdgeDirection.Either)( vprog: (VertexId, VD, A) => VD, - sendMsg: EdgeTriplet[VD, ED] => Iterator[(VertexId,A)], + sendMsg: EdgeTriplet[VD, ED] => Iterator[(VertexId, A)], mergeMsg: (A, A) => A) : Graph[VD, ED] = { Pregel(graph, initialMsg, maxIterations, activeDirection)(vprog, sendMsg, mergeMsg) diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala b/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala index 01b013ff71..cfcf7244ea 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala @@ -147,10 +147,10 @@ object Pregel extends Logging { logInfo("Pregel finished iteration " + i) // Unpersist the RDDs hidden by newly-materialized RDDs - oldMessages.unpersist(blocking=false) - newVerts.unpersist(blocking=false) - prevG.unpersistVertices(blocking=false) - prevG.edges.unpersist(blocking=false) + oldMessages.unpersist(blocking = false) + newVerts.unpersist(blocking = false) + prevG.unpersistVertices(blocking = false) + prevG.edges.unpersist(blocking = false) // count the iteration i += 1 } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala index c561570809..ab021a252e 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/impl/EdgePartition.scala @@ -156,8 +156,8 @@ class EdgePartition[ val size = data.size var i = 0 while (i < size) { - edge.srcId = srcIds(i) - edge.dstId = dstIds(i) + edge.srcId = srcIds(i) + edge.dstId = dstIds(i) edge.attr = data(i) newData(i) = f(edge) i += 1 diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala b/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala index bc974b2f04..8c0a461e99 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala @@ -116,7 +116,7 @@ object PageRank extends Logging { val personalized = srcId isDefined val src: VertexId = srcId.getOrElse(-1L) - def delta(u: VertexId, v: VertexId):Double = { if (u == v) 1.0 else 0.0 } + def delta(u: VertexId, v: VertexId): Double = { if (u == v) 1.0 else 0.0 } var iteration = 0 var prevRankGraph: Graph[Double, Double] = null @@ -133,13 +133,13 @@ object PageRank extends Logging { // edge partitions. prevRankGraph = rankGraph val rPrb = if (personalized) { - (src: VertexId ,id: VertexId) => resetProb * delta(src,id) + (src: VertexId , id: VertexId) => resetProb * delta(src, id) } else { (src: VertexId, id: VertexId) => resetProb } rankGraph = rankGraph.joinVertices(rankUpdates) { - (id, oldRank, msgSum) => rPrb(src,id) + (1.0 - resetProb) * msgSum + (id, oldRank, msgSum) => rPrb(src, id) + (1.0 - resetProb) * msgSum }.cache() rankGraph.edges.foreachPartition(x => {}) // also materializes rankGraph.vertices @@ -243,7 +243,7 @@ object PageRank extends Logging { // Execute a dynamic version of Pregel. val vp = if (personalized) { - (id: VertexId, attr: (Double, Double),msgSum: Double) => + (id: VertexId, attr: (Double, Double), msgSum: Double) => personalizedVertexProgram(id, attr, msgSum) } else { (id: VertexId, attr: (Double, Double), msgSum: Double) => diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/SVDPlusPlus.scala b/graphx/src/main/scala/org/apache/spark/graphx/lib/SVDPlusPlus.scala index 3b0e1628d8..9cb24ed080 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/lib/SVDPlusPlus.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/SVDPlusPlus.scala @@ -210,7 +210,7 @@ object SVDPlusPlus { /** * Forces materialization of a Graph by count()ing its RDDs. */ - private def materialize(g: Graph[_,_]): Unit = { + private def materialize(g: Graph[_, _]): Unit = { g.vertices.count() g.edges.count() } diff --git a/graphx/src/main/scala/org/apache/spark/graphx/lib/TriangleCount.scala b/graphx/src/main/scala/org/apache/spark/graphx/lib/TriangleCount.scala index daf162085e..a5d598053f 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/lib/TriangleCount.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/lib/TriangleCount.scala @@ -38,7 +38,7 @@ import org.apache.spark.graphx._ */ object TriangleCount { - def run[VD: ClassTag, ED: ClassTag](graph: Graph[VD,ED]): Graph[Int, ED] = { + def run[VD: ClassTag, ED: ClassTag](graph: Graph[VD, ED]): Graph[Int, ED] = { // Remove redundant edges val g = graph.groupEdges((a, b) => a).cache() @@ -49,7 +49,7 @@ object TriangleCount { var i = 0 while (i < nbrs.size) { // prevent self cycle - if(nbrs(i) != vid) { + if (nbrs(i) != vid) { set.add(nbrs(i)) } i += 1 diff --git a/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala b/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala index 2d6a825b61..9591c4e9b8 100644 --- a/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala +++ b/graphx/src/main/scala/org/apache/spark/graphx/util/GraphGenerators.scala @@ -243,14 +243,15 @@ object GraphGenerators { * @return A graph containing vertices with the row and column ids * as their attributes and edge values as 1.0. */ - def gridGraph(sc: SparkContext, rows: Int, cols: Int): Graph[(Int,Int), Double] = { + def gridGraph(sc: SparkContext, rows: Int, cols: Int): Graph[(Int, Int), Double] = { // Convert row column address into vertex ids (row major order) def sub2ind(r: Int, c: Int): VertexId = r * cols + c - val vertices: RDD[(VertexId, (Int,Int))] = - sc.parallelize(0 until rows).flatMap( r => (0 until cols).map( c => (sub2ind(r,c), (r,c)) ) ) + val vertices: RDD[(VertexId, (Int, Int))] = sc.parallelize(0 until rows).flatMap { r => + (0 until cols).map( c => (sub2ind(r, c), (r, c)) ) + } val edges: RDD[Edge[Double]] = - vertices.flatMap{ case (vid, (r,c)) => + vertices.flatMap{ case (vid, (r, c)) => (if (r + 1 < rows) { Seq( (sub2ind(r, c), sub2ind(r + 1, c))) } else { Seq.empty }) ++ (if (c + 1 < cols) { Seq( (sub2ind(r, c), sub2ind(r, c + 1))) } else { Seq.empty }) }.map{ case (src, dst) => Edge(src, dst, 1.0) } diff --git a/graphx/src/test/scala/org/apache/spark/graphx/GraphOpsSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/GraphOpsSuite.scala index 9bc8007ce4..68fe83739e 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/GraphOpsSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/GraphOpsSuite.scala @@ -59,7 +59,7 @@ class GraphOpsSuite extends FunSuite with LocalSparkContext { test ("filter") { withSpark { sc => val n = 5 - val vertices = sc.parallelize((0 to n).map(x => (x:VertexId, x))) + val vertices = sc.parallelize((0 to n).map(x => (x: VertexId, x))) val edges = sc.parallelize((1 to n).map(x => Edge(0, x, x))) val graph: Graph[Int, Int] = Graph(vertices, edges).cache() val filteredGraph = graph.filter( @@ -67,11 +67,11 @@ class GraphOpsSuite extends FunSuite with LocalSparkContext { val degrees: VertexRDD[Int] = graph.outDegrees graph.outerJoinVertices(degrees) {(vid, data, deg) => deg.getOrElse(0)} }, - vpred = (vid: VertexId, deg:Int) => deg > 0 + vpred = (vid: VertexId, deg: Int) => deg > 0 ).cache() val v = filteredGraph.vertices.collect().toSet - assert(v === Set((0,0))) + assert(v === Set((0, 0))) // the map is necessary because of object-reuse in the edge iterator val e = filteredGraph.edges.map(e => Edge(e.srcId, e.dstId, e.attr)).collect().toSet diff --git a/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala index a570e4ed75..2b1d8e4732 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/GraphSuite.scala @@ -248,7 +248,7 @@ class GraphSuite extends FunSuite with LocalSparkContext { test("mask") { withSpark { sc => val n = 5 - val vertices = sc.parallelize((0 to n).map(x => (x:VertexId, x))) + val vertices = sc.parallelize((0 to n).map(x => (x: VertexId, x))) val edges = sc.parallelize((1 to n).map(x => Edge(0, x, x))) val graph: Graph[Int, Int] = Graph(vertices, edges).cache() @@ -260,11 +260,11 @@ class GraphSuite extends FunSuite with LocalSparkContext { val projectedGraph = graph.mask(subgraph) val v = projectedGraph.vertices.collect().toSet - assert(v === Set((0,0), (1,1), (2,2), (4,4), (5,5))) + assert(v === Set((0, 0), (1, 1), (2, 2), (4, 4), (5, 5))) // the map is necessary because of object-reuse in the edge iterator val e = projectedGraph.edges.map(e => Edge(e.srcId, e.dstId, e.attr)).collect().toSet - assert(e === Set(Edge(0,1,1), Edge(0,2,2), Edge(0,5,5))) + assert(e === Set(Edge(0, 1, 1), Edge(0, 2, 2), Edge(0, 5, 5))) } } diff --git a/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala index 4cc30a9640..accccfc232 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/lib/ConnectedComponentsSuite.scala @@ -52,13 +52,16 @@ class ConnectedComponentsSuite extends FunSuite with LocalSparkContext { withSpark { sc => val chain1 = (0 until 9).map(x => (x, x + 1)) val chain2 = (10 until 20).map(x => (x, x + 1)) - val rawEdges = sc.parallelize(chain1 ++ chain2, 3).map { case (s,d) => (s.toLong, d.toLong) } + val rawEdges = sc.parallelize(chain1 ++ chain2, 3).map { case (s, d) => (s.toLong, d.toLong) } val twoChains = Graph.fromEdgeTuples(rawEdges, 1.0) val ccGraph = twoChains.connectedComponents() val vertices = ccGraph.vertices.collect() for ( (id, cc) <- vertices ) { - if(id < 10) { assert(cc === 0) } - else { assert(cc === 10) } + if (id < 10) { + assert(cc === 0) + } else { + assert(cc === 10) + } } val ccMap = vertices.toMap for (id <- 0 until 20) { @@ -75,7 +78,7 @@ class ConnectedComponentsSuite extends FunSuite with LocalSparkContext { withSpark { sc => val chain1 = (0 until 9).map(x => (x, x + 1)) val chain2 = (10 until 20).map(x => (x, x + 1)) - val rawEdges = sc.parallelize(chain1 ++ chain2, 3).map { case (s,d) => (s.toLong, d.toLong) } + val rawEdges = sc.parallelize(chain1 ++ chain2, 3).map { case (s, d) => (s.toLong, d.toLong) } val twoChains = Graph.fromEdgeTuples(rawEdges, true).reverse val ccGraph = twoChains.connectedComponents() val vertices = ccGraph.vertices.collect() @@ -106,9 +109,9 @@ class ConnectedComponentsSuite extends FunSuite with LocalSparkContext { (4L, ("peter", "student")))) // Create an RDD for edges val relationships: RDD[Edge[String]] = - sc.parallelize(Array(Edge(3L, 7L, "collab"), Edge(5L, 3L, "advisor"), + 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"))) + Edge(4L, 0L, "student"), Edge(5L, 0L, "colleague"))) // Edges are: // 2 ---> 5 ---> 3 // | \ diff --git a/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala index 3f3c9dfd7b..39c6ace912 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/lib/PageRankSuite.scala @@ -31,14 +31,14 @@ object GridPageRank { def sub2ind(r: Int, c: Int): Int = r * nCols + c // Make the grid graph for (r <- 0 until nRows; c <- 0 until nCols) { - val ind = sub2ind(r,c) + val ind = sub2ind(r, c) if (r + 1 < nRows) { outDegree(ind) += 1 - inNbrs(sub2ind(r + 1,c)) += ind + inNbrs(sub2ind(r + 1, c)) += ind } if (c + 1 < nCols) { outDegree(ind) += 1 - inNbrs(sub2ind(r,c + 1)) += ind + inNbrs(sub2ind(r, c + 1)) += ind } } // compute the pagerank @@ -99,8 +99,8 @@ class PageRankSuite extends FunSuite with LocalSparkContext { val resetProb = 0.15 val errorTol = 1.0e-5 - val staticRanks1 = starGraph.staticPersonalizedPageRank(0,numIter = 1, resetProb).vertices - val staticRanks2 = starGraph.staticPersonalizedPageRank(0,numIter = 2, resetProb) + val staticRanks1 = starGraph.staticPersonalizedPageRank(0, numIter = 1, resetProb).vertices + val staticRanks2 = starGraph.staticPersonalizedPageRank(0, numIter = 2, resetProb) .vertices.cache() // Static PageRank should only take 2 iterations to converge @@ -117,7 +117,7 @@ class PageRankSuite extends FunSuite with LocalSparkContext { } assert(staticErrors.sum === 0) - val dynamicRanks = starGraph.personalizedPageRank(0,0, resetProb).vertices.cache() + val dynamicRanks = starGraph.personalizedPageRank(0, 0, resetProb).vertices.cache() assert(compareRanks(staticRanks2, dynamicRanks) < errorTol) } } // end of test Star PageRank @@ -162,7 +162,7 @@ class PageRankSuite extends FunSuite with LocalSparkContext { test("Chain PersonalizedPageRank") { withSpark { sc => val chain1 = (0 until 9).map(x => (x, x + 1) ) - val rawEdges = sc.parallelize(chain1, 1).map { case (s,d) => (s.toLong, d.toLong) } + val rawEdges = sc.parallelize(chain1, 1).map { case (s, d) => (s.toLong, d.toLong) } val chain = Graph.fromEdgeTuples(rawEdges, 1.0).cache() val resetProb = 0.15 val tol = 0.0001 diff --git a/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala b/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala index 293c7f3ba4..79bf4e6cd1 100644 --- a/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala +++ b/graphx/src/test/scala/org/apache/spark/graphx/lib/TriangleCountSuite.scala @@ -58,7 +58,7 @@ class TriangleCountSuite extends FunSuite with LocalSparkContext { val triangles = Array(0L -> 1L, 1L -> 2L, 2L -> 0L) ++ Array(0L -> -1L, -1L -> -2L, -2L -> 0L) - val revTriangles = triangles.map { case (a,b) => (b,a) } + val revTriangles = triangles.map { case (a, b) => (b, a) } val rawEdges = sc.parallelize(triangles ++ revTriangles, 2) val graph = Graph.fromEdgeTuples(rawEdges, true).cache() val triangleCount = graph.triangleCount() |