Skip to content

feat: more tests for fromEdges #778

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SemyonSinchenko merged 1 commit into from
Jan 23, 2026
Merged

feat: more tests for fromEdges #778

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 23 additions & 2 deletions core/src/main/scala/org/graphframes/GraphFrame.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1081,10 +1081,31 @@ object GraphFrame extends Serializable with Logging {
* @group conversions
*/
def fromEdges(e: DataFrame): GraphFrame = {
fromEdges(e, StorageLevel.MEMORY_AND_DISK)
}

/**
* Create a new [[GraphFrame]] from an edge `DataFrame`. The resulting [[GraphFrame]] will have
* [[GraphFrame.vertices]] with a single "id" column.
*
* Note: The [[GraphFrame.vertices]] DataFrame will be persisted at level
* `StorageLevel.MEMORY_AND_DISK`.
* @param e
* Edge DataFrame. This must include columns "src" and "dst" containing source and destination
* vertex IDs. All other columns are treated as edge attributes.
* @param storageLevel
* StorageLevel to persist the graph vertices
* @return
* New [[GraphFrame]] instance
*
* @group conversions
*/
def fromEdges(e: DataFrame, storageLevel: StorageLevel): GraphFrame = {
logWarn(
s"this method persists graph vertices with storage level ${storageLevel.toString()}, users should manually unpersist it when the graph is not needed!")
val srcs = e.select(e("src").as("id"))
val dsts = e.select(e("dst").as("id"))
val v = srcs.unionAll(dsts).distinct()
v.persist(StorageLevel.MEMORY_AND_DISK)
val v = srcs.unionAll(dsts).distinct().persist(storageLevel)
apply(v, e)
}

Expand Down
39 changes: 39 additions & 0 deletions core/src/test/scala/org/graphframes/GraphFrameSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,6 +157,45 @@ class GraphFrameSuite extends SparkFunSuite with GraphFrameTestSparkContext {
.collect()
.toSet
assert(idsFromVerticesSet === idsFromEdgesSet)
g.vertices.unpersist()
}

test("construction from edges DataFrame, string IDs") {
val edges = spark
.createDataFrame(Seq(("a", "b", "love"), ("b", "a", "hate"), ("b", "c", "follow")))
.toDF("src", "dst", "action")

val g = GraphFrame.fromEdges(edges)
assert(g.vertices.columns === Array("id"))
val idsFromVertices = g.vertices.select("id").rdd.map(_.getString(0)).collect()
val idsFromVerticesSet = idsFromVertices.toSet
assert(idsFromVertices.length === idsFromVerticesSet.size)
val idsFromEdgesSet = g.edges
.select("src", "dst")
.rdd
.flatMap {
case Row(src: String, dst: String) =>
Seq(src, dst)
case _: Row => throw new GraphFramesUnreachableException()
}
.collect()
.toSet
assert(idsFromVerticesSet === idsFromEdgesSet)
g.vertices.unpersist()
}

test("construction from edges DataFrame, different storage level") {
val edges = spark
.createDataFrame(Seq((1L, 2L, "love"), (2L, 1L, "hate"), (2L, 3L, "follow")))
.toDF("src", "dst", "action")

var g = GraphFrame.fromEdges(edges)
assert(g.vertices.storageLevel === StorageLevel.MEMORY_AND_DISK)
g.vertices.unpersist()

g = GraphFrame.fromEdges(edges, StorageLevel.MEMORY_AND_DISK_SER)
assert(g.vertices.storageLevel === StorageLevel.MEMORY_AND_DISK_SER)
g.vertices.unpersist()
}

test("construction from GraphX") {
Expand Down