Skip to content
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

Jump to bottom

Persist more in MGPropertyGraph #2805

Merged
merged 3 commits into from
Oct 24, 2022
Merged

Persist more in MGPropertyGraph #2805

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d826be3
Persist more in MGPropertyGraph
eriknw Oct 13, 2022
23dd4b6
Merge branch 'branch-22.12' into pg_persist
eriknw Oct 18, 2022
273e54f
Add benchmark for adding edge data
eriknw Oct 18, 2022
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
37 changes: 18 additions & 19 deletions python/cugraph/cugraph/dask/structure/mg_property_graph.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -456,7 +456,7 @@ def add_vertex_data(
self.__vertex_prop_dtypes.update(new_col_info)

# Join on shared columns and the indices
tmp_df = tmp_df.set_index(self.vertex_col_name)
tmp_df = tmp_df.persist().set_index(self.vertex_col_name).persist()
cols = self.__vertex_prop_dataframe.columns.intersection(
tmp_df.columns
).to_list()
Expand All @@ -465,7 +465,9 @@ def add_vertex_data(
self.__vertex_prop_dataframe = (
self.__vertex_prop_dataframe.reset_index()
.merge(tmp_df.reset_index(), on=cols, how="outer")
.persist()
.set_index(self.vertex_col_name)
.persist()
)
# self.__vertex_prop_dataframe = \
# self.__vertex_prop_dataframe.merge(tmp_df, on=cols, how="outer")
Expand All @@ -479,8 +481,6 @@ def add_vertex_data(
self.__vertex_prop_eval_dict[
self.vertex_col_name
] = self.__vertex_prop_dataframe.index
# Should we persist?
# self.__vertex_prop_dataframe = self.__vertex_prop_dataframe.persist()

def get_vertex_data(self, vertex_ids=None, types=None, columns=None):
"""
Expand Down Expand Up @@ -666,16 +666,15 @@ def add_edge_data(
tmp_df[self.edge_id_col_name] = (
tmp_df[self.edge_id_col_name].cumsum() + starting_eid
)
tmp_df = tmp_df.persist()
tmp_df = tmp_df.set_index(self.edge_id_col_name)
tmp_df = tmp_df.persist()
tmp_df = tmp_df.persist().set_index(self.edge_id_col_name).persist()
self.__last_edge_id = starting_eid + len(tmp_df)
else:
tmp_df = tmp_df.persist()
tmp_df = tmp_df.rename(
columns={edge_id_col_name: self.edge_id_col_name}
).set_index(self.edge_id_col_name)
tmp_df = tmp_df.persist()
tmp_df = (
tmp_df.rename(columns={edge_id_col_name: self.edge_id_col_name})
.persist()
.set_index(self.edge_id_col_name)
.persist()
)

if property_columns:
# all columns
Expand All @@ -701,7 +700,9 @@ def add_edge_data(
self.__edge_prop_dataframe = (
self.__edge_prop_dataframe.reset_index()
.merge(tmp_df.reset_index(), on=cols, how="outer")
.persist()
.set_index(self.edge_id_col_name)
.persist()
)
# self.__edge_prop_dataframe = \
# self.__edge_prop_dataframe.merge(tmp_df, on=cols, how="outer")
Expand All @@ -717,8 +718,6 @@ def add_edge_data(
self.__edge_prop_eval_dict[
self.edge_id_col_name
] = self.__edge_prop_dataframe.index
# Should we persist?
# self.__edge_prop_dataframe = self.__edge_prop_dataframe.persist()

def get_edge_data(self, edge_ids=None, types=None, columns=None):
"""
Expand Down Expand Up @@ -1118,9 +1117,9 @@ def renumber_vertices_by_type(self):
df[self.vertex_col_name] = 1
df[self.vertex_col_name] = df[self.vertex_col_name].cumsum() - 1

self.__vertex_prop_dataframe = df.set_index(
self.vertex_col_name, sorted=True
).persist()
self.__vertex_prop_dataframe = (
df.persist().set_index(self.vertex_col_name, sorted=True).persist()
)

# FIXME DASK_CUDF: https://github.com/rapidsai/cudf/issues/11795
df = self._vertex_type_value_counts
Expand Down Expand Up @@ -1163,9 +1162,9 @@ def renumber_edges_by_type(self):

df[self.edge_id_col_name] = 1
df[self.edge_id_col_name] = df[self.edge_id_col_name].cumsum() - 1
self.__edge_prop_dataframe = df.set_index(
self.edge_id_col_name, sorted=True
).persist()
self.__edge_prop_dataframe = (
df.persist().set_index(self.edge_id_col_name, sorted=True).persist()
)

# FIXME DASK_CUDF: https://github.com/rapidsai/cudf/issues/11795
df = self._edge_type_value_counts
Expand Down