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

Fixes for pandas 2, latest cudf, and wheel building #4144

Merged
merged 9 commits into from
Feb 6, 2024
Merged

Fixes for pandas 2, latest cudf, and wheel building #4144

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
0906c8d
Fix renumber map column name to not conflict with a method
vyasr Feb 5, 2024
4d67ddd
One more renumber map
vyasr Feb 5, 2024
b04c7cf
Fix when reading from file
vyasr Feb 5, 2024
e4a5aa5
Cast to float to ensure that it works when the frame is empty because…
vyasr Feb 5, 2024
338a431
Make dgl and pyg wheel tests download cugraph/pylibcugraph wheels bui…
vyasr Feb 5, 2024
f77bee5
Access map by name
vyasr Feb 5, 2024
8a0d386
Test a fix for the libcugraph_etl build issues from libcudf
vyasr Feb 5, 2024
ce53b00
Fix export name
vyasr Feb 5, 2024
37cd1c3
Fix last failure
vyasr Feb 6, 2024
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: 5 additions & 3 deletions python/cugraph/cugraph/gnn/data_loading/bulk_sampler_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
# Copyright (c) 2023-2024, NVIDIA CORPORATION.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Expand Down Expand Up @@ -181,7 +181,9 @@ def _write_samples_to_parquet_csr(
[
cudf.Series(minors_array[results_start:results_end], name="minors"),
cudf.Series(
renumber_map.map.values[renumber_map_start:renumber_map_end],
renumber_map.renumber_map.values[
renumber_map_start:renumber_map_end
],
name="map",
),
label_hop_offsets_current_partition,
Expand Down Expand Up @@ -299,7 +301,7 @@ def _write_samples_to_parquet_coo(
else:
renumber_map_end_ix = offsets_z.renumber_map_offsets.iloc[0]

renumber_map_p = renumber_map.map.iloc[
renumber_map_p = renumber_map.renumber_map.iloc[
renumber_map_start_ix:renumber_map_end_ix
]

Expand Down
8 changes: 4 additions & 4 deletions python/cugraph/cugraph/gnn/dgl_extensions/dgl_uniform_sampler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
# Copyright (c) 2023-2024, NVIDIA CORPORATION.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Expand Down Expand Up @@ -120,9 +120,9 @@ def sample_neighbors(
return self._get_edgeid_type_d(sampled_df)
else:
return (
sampled_df[src_n].values,
sampled_df[dst_n].values,
sampled_df["indices"].values,
sampled_df[src_n].astype("float").values,
sampled_df[dst_n].astype("float").values,
sampled_df["indices"].astype("float").values,
)

def _get_edgeid_type_d(self, df):
Expand Down
4 changes: 2 additions & 2 deletions python/cugraph/cugraph/sampling/sampling_utilities.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
# Copyright (c) 2023-2024, NVIDIA CORPORATION.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Expand Down Expand Up @@ -74,7 +74,7 @@ def sampling_results_from_cupy_array_dict(
if renumber:
renumber_df = cudf.DataFrame(
{
"map": cupy_array_dict["renumber_map"],
"renumber_map": cupy_array_dict["renumber_map"],
}
)

Expand Down
4 changes: 2 additions & 2 deletions python/cugraph/cugraph/tests/sampling/test_bulk_sampler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
# Copyright (c) 2023-2024, NVIDIA CORPORATION.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Expand Down Expand Up @@ -222,7 +222,7 @@ def test_bulk_sampler_partitions(scratch_dir):
]

recovered_samples = cudf.read_parquet(os.path.join(samples_path, file))
recovered_map = recovered_samples.map
recovered_map = recovered_samples["map"]
recovered_samples = recovered_samples.drop("map", axis=1).dropna()

for current_batch_id in range(start_batch_id, end_batch_id + 1):
Expand Down
4 changes: 2 additions & 2 deletions python/cugraph/cugraph/tests/sampling/test_bulk_sampler_mg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2023, NVIDIA CORPORATION.
# Copyright (c) 2023-2024, NVIDIA CORPORATION.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Expand Down Expand Up @@ -166,7 +166,7 @@ def test_bulk_sampler_partitions(dask_client, scratch_dir, mg_input):
]

recovered_samples = cudf.read_parquet(os.path.join(samples_path, file))
recovered_map = recovered_samples.map
recovered_map = recovered_samples["map"]
recovered_samples = recovered_samples.drop("map", axis=1).dropna()

for current_batch_id in range(start_batch_id, end_batch_id + 1):
Expand Down
18 changes: 11 additions & 7 deletions python/cugraph/cugraph/tests/sampling/test_uniform_neighbor_sample.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2022-2023, NVIDIA CORPORATION.
# Copyright (c) 2022-2024, NVIDIA CORPORATION.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
Expand Down Expand Up @@ -796,7 +796,9 @@ def test_uniform_neighbor_sample_renumber(hops):
expected_renumber_map = cudf.concat([sources_hop_0, destinations_hop]).unique()

assert sorted(expected_renumber_map.values_host.tolist()) == sorted(
renumber_map.map[0 : len(expected_renumber_map)].values_host.tolist()
renumber_map.renumber_map[
0 : len(expected_renumber_map)
].values_host.tolist()
)
assert (renumber_map.batch_id == 0).all()

Expand Down Expand Up @@ -854,7 +856,9 @@ def test_uniform_neighbor_sample_offset_renumber(hops):
expected_renumber_map = cudf.concat([sources_hop_0, destinations_hop]).unique()

assert sorted(expected_renumber_map.values_host.tolist()) == sorted(
renumber_map.map[0 : len(expected_renumber_map)].values_host.tolist()
renumber_map.renumber_map[
0 : len(expected_renumber_map)
].values_host.tolist()
)

renumber_map_offsets = offsets_renumbered.renumber_map_offsets.dropna()
Expand Down Expand Up @@ -902,8 +906,8 @@ def test_uniform_neighbor_sample_csr_csc_global(hops, seed):
minors = sampling_results["minors"].dropna()
assert len(majors) == len(minors)

majors = renumber_map.map.iloc[majors]
minors = renumber_map.map.iloc[minors]
majors = renumber_map.renumber_map.iloc[majors]
minors = renumber_map.renumber_map.iloc[minors]

for i in range(len(majors)):
assert 1 == len(el[(el.src == majors.iloc[i]) & (el.dst == minors.iloc[i])])
Expand Down Expand Up @@ -952,8 +956,8 @@ def test_uniform_neighbor_sample_csr_csc_local(hops, seed):
majors = cudf.Series(cupy.arange(len(major_offsets) - 1))
majors = majors.repeat(cupy.diff(major_offsets))

majors = renumber_map.map.iloc[majors]
minors = renumber_map.map.iloc[minors]
majors = renumber_map.renumber_map.iloc[majors]
minors = renumber_map.renumber_map.iloc[minors]

for i in range(len(majors)):
assert 1 == len(el[(el.src == majors.iloc[i]) & (el.dst == minors.iloc[i])])
Expand Down
14 changes: 8 additions & 6 deletions python/cugraph/cugraph/tests/sampling/test_uniform_neighbor_sample_mg.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1015,7 +1015,7 @@ def test_uniform_neighbor_sample_renumber(dask_client, hops):

assert (renumber_map.batch_id == 0).all()
assert (
renumber_map.map.nunique()
renumber_map.renumber_map.nunique()
== cudf.concat(
[sources_hop_0, sampling_results_renumbered.destinations]
).nunique()
Expand Down Expand Up @@ -1091,7 +1091,9 @@ def test_uniform_neighbor_sample_offset_renumber(dask_client, hops):
expected_renumber_map = cudf.concat([sources_hop_0, destinations_hop]).unique()

assert sorted(expected_renumber_map.values_host.tolist()) == sorted(
renumber_map.map[0 : len(expected_renumber_map)].values_host.tolist()
renumber_map.renumber_map[
0 : len(expected_renumber_map)
].values_host.tolist()
)

renumber_map_offsets = offsets_renumbered.renumber_map_offsets.dropna()
Expand Down Expand Up @@ -1153,8 +1155,8 @@ def test_uniform_neighbor_sample_csr_csc_global(dask_client, hops, seed):
minors = sampling_results["minors"].dropna()
assert len(majors) == len(minors)

majors = renumber_map.map.iloc[majors]
minors = renumber_map.map.iloc[minors]
majors = renumber_map.renumber_map.iloc[majors]
minors = renumber_map.renumber_map.iloc[minors]

for i in range(len(majors)):
assert 1 == len(el[(el.src == majors.iloc[i]) & (el.dst == minors.iloc[i])])
Expand Down Expand Up @@ -1221,8 +1223,8 @@ def test_uniform_neighbor_sample_csr_csc_local(dask_client, hops, seed):
majors = cudf.Series(cupy.arange(len(major_offsets) - 1))
majors = majors.repeat(cupy.diff(major_offsets))

majors = renumber_map.map.iloc[majors]
minors = renumber_map.map.iloc[minors]
majors = renumber_map.renumber_map.iloc[majors]
minors = renumber_map.renumber_map.iloc[minors]

for i in range(len(majors)):
assert 1 == len(el[(el.src == majors.iloc[i]) & (el.dst == minors.iloc[i])])
Expand Down
Loading