Skip to content

Commit

Permalink
Skip deleting copied dask dataframe to avoid crash
Browse files Browse the repository at this point in the history
  • Loading branch information
naimnv committed Sep 22, 2023
1 parent 12c0675 commit bd85881
Showing 1 changed file with 2 additions and 5 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,6 @@
import gc
from typing import Union
import warnings
import random

import cudf
import cupy as cp
Expand Down Expand Up @@ -183,9 +182,7 @@ def __from_edgelist(
# Repartition to 2 partitions per GPU for memory efficient process
input_ddf = input_ddf.repartition(npartitions=len(workers) * 2)
# FIXME: Make a copy of the input ddf before implicitly altering it.
input_ddf = input_ddf.map_partitions(
lambda df: df.copy(), token="custom-" + str(random.random())
)
input_ddf = input_ddf.map_partitions(lambda df: df.copy())
# The dataframe will be symmetrized iff the graph is undirected
# otherwise, the inital dataframe will be returned
if edge_attr is not None:
Expand Down Expand Up @@ -337,7 +334,7 @@ def __from_edgelist(
)
for w, edata in ddf.items()
}
del ddf
# FIXME: For now, don't delete the copied dataframe to avoid crash
self._plc_graph = {
w: _client.compute(delayed_task, workers=w, allow_other_workers=False)
for w, delayed_task in delayed_tasks_d.items()
Expand Down

0 comments on commit bd85881

Please sign in to comment.