Skip to content

fix: resolve AttributeError in pageRank on Spark Connect (issue #889) #890

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
Aug 26, 2026
Merged

fix: resolve AttributeError in pageRank on Spark Connect (issue #889) #890

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
8 changes: 7 additions & 1 deletion python/graphframes/connect/graphframes_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -352,6 +352,12 @@ def plan(self, session: SparkConnectClient) -> proto.Relation:
def pregel(self):
return PregelConnect(self)

@property
def outDegrees(self) -> DataFrame:
return self._edges.groupBy(F.col(self._SRC).alias(self._ID)).agg(
F.count("*").alias("outDegree")
)

def find(self, pattern: str) -> DataFrame:
@final
class Find(LogicalPlan):
Expand Down Expand Up @@ -913,7 +919,7 @@ def plan(self, session: SparkConnectClient) -> proto.Relation:
)

def _update_page_rank_edge_weights(self, new_vertices: DataFrame) -> "GraphFrameConnect":
cols2select = self.edges.columns + ["weight"]
cols2select = self._edges.columns + ["weight"]
new_edges = (
self._edges.join(
new_vertices.withColumn(self._SRC, F.col(self._ID)),
Expand Down
26 changes: 26 additions & 0 deletions python/tests/test_graphframes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,6 +457,32 @@ def test_page_rank(spark: SparkSession, args: PregelArguments) -> None:
_ = ranks.unpersist()


def test_graphframes_pagerank(spark: SparkSession) -> None:
"""Regression test for issue #889: pageRank fails on Spark Connect due to
AttributeError accessing self.edges and self.outDegrees on GraphFrameConnect."""
edges = spark.createDataFrame(
[
[0, 1],
[1, 2],
[2, 4],
[2, 0],
[3, 4],
[4, 0],
[4, 2],
],
["src", "dst"],
)
vertices = spark.createDataFrame([[0], [1], [2], [3], [4]], ["id"])
g = GraphFrame(vertices, edges)

result = g.pageRank(resetProbability=0.15, maxIter=3)

assert "pagerank" in result.vertices.columns
assert "weight" in result.edges.columns
assert result.vertices.count() == 5
assert result.edges.count() == edges.count()


@pytest.mark.parametrize("args", PREGEL_ARGUMENTS, ids=PREGEL_IDS)
def test_pregel_early_stopping(spark: SparkSession, args: PregelArguments) -> None:
edges = spark.createDataFrame(
Expand Down
Loading