Address dask_cudf.read_csv chunksize deprecation (rapidsai#4379)

xref rapidsai#4271

`chunksize` was deprecated in favor of `blocksize`

Also removed an unsupported `chunksize` in a `cudf.read_csv` call

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)

Approvers:
  - Don Acosta (https://github.com/acostadon)
  - Rick Ratzel (https://github.com/rlratzel)

URL: rapidsai#4379

benchmarks/cugraph/standalone/cugraph_dask_funcs.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2023, NVIDIA CORPORATION.
+# Copyright (c) 2021-2024, 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
@@ -44,7 +44,7 @@ def read_csv(input_csv_file, scale):
     chunksize = cugraph.dask.get_chunksize(input_csv_file)
     return dask_cudf.read_csv(
         input_csv_file,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         # names=names,
         dtype=dtypes,

benchmarks/cugraph/standalone/cugraph_funcs.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2023, NVIDIA CORPORATION.
+# Copyright (c) 2021-2024, 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
@@ -75,10 +75,8 @@ def read_csv(input_csv_file, scale):
     dtypes = [vertex_t, vertex_t, "float32"]
     names = (["src", "dst", "weight"],)
 
-    chunksize = cugraph.dask.get_chunksize(input_csv_file)
     return cudf.read_csv(
         input_csv_file,
-        chunksize=chunksize,
         delimiter=" ",
         # names=names,
         dtype=dtypes,

docs/cugraph/source/api_docs/cugraph/dask-cugraph.rst

@@ -54,7 +54,7 @@ Example
     # multi-GPU CSV reader
     e_list = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         names=['src', 'dst'],
         dtype=['int32', 'int32'],
     )

python/cugraph/cugraph/dask/centrality/betweenness_centrality.py

@@ -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.
@@ -204,7 +204,7 @@ def betweenness_centrality(
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)
@@ -362,7 +362,7 @@ def edge_betweenness_centrality(
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)

python/cugraph/cugraph/dask/centrality/eigenvector_centrality.py

@@ -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.
@@ -104,7 +104,7 @@ def eigenvector_centrality(input_graph, max_iter=100, tol=1.0e-6):
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph()

python/cugraph/cugraph/dask/centrality/katz_centrality.py

@@ -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.
@@ -133,7 +133,7 @@ def katz_centrality(
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)

python/cugraph/cugraph/dask/community/leiden.py

@@ -132,7 +132,7 @@ def leiden(
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph()

python/cugraph/cugraph/dask/community/louvain.py

@@ -136,7 +136,7 @@ def louvain(
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph()

python/cugraph/cugraph/dask/components/connectivity.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2023, NVIDIA CORPORATION.
+# Copyright (c) 2021-2024, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -78,7 +78,7 @@ def weakly_connected_components(input_graph):
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=False)

python/cugraph/cugraph/dask/cores/k_core.py

@@ -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.
@@ -109,7 +109,7 @@ def k_core(input_graph, k=None, core_number=None, degree_type="bidirectional"):
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=False)

python/cugraph/cugraph/dask/link_analysis/hits.py

@@ -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.
@@ -118,7 +118,7 @@ def hits(input_graph, tol=1.0e-5, max_iter=100, nstart=None, normalized=True):
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)

python/cugraph/cugraph/dask/link_analysis/pagerank.py

@@ -295,7 +295,7 @@ def pagerank(
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)

python/cugraph/cugraph/dask/traversal/bfs.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2019-2023, NVIDIA CORPORATION.
+# Copyright (c) 2019-2024, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -106,7 +106,7 @@ def bfs(input_graph, start, depth_limit=None, return_distances=True, check_start
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)

python/cugraph/cugraph/dask/traversal/sssp.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2019-2023, NVIDIA CORPORATION.
+# Copyright (c) 2019-2024, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -89,7 +89,7 @@ def sssp(input_graph, source, cutoff=None, check_source=True):
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> chunksize = dcg.get_chunksize(datasets_path / "karate.csv")
     >>> ddf = dask_cudf.read_csv(datasets_path / "karate.csv",
-    ...                          chunksize=chunksize, delimiter=" ",
+    ...                          blocksize=chunksize, delimiter=" ",
     ...                          names=["src", "dst", "value"],
     ...                          dtype=["int32", "int32", "float32"])
     >>> dg = cugraph.Graph(directed=True)

python/cugraph/cugraph/structure/symmetrize.py

@@ -159,7 +159,7 @@ def symmetrize_ddf(
     >>> # Init a DASK Cluster
     >>> # Download dataset from https://github.com/rapidsai/cugraph/datasets/..
     >>> # chunksize = dcg.get_chunksize(datasets / 'karate.csv')
-    >>> # ddf = dask_cudf.read_csv(datasets/'karate.csv', chunksize=chunksize,
+    >>> # ddf = dask_cudf.read_csv(datasets/'karate.csv', blocksize=chunksize,
     >>> #                          delimiter=' ',
     >>> #                          names=['src', 'dst', 'weight'],
     >>> #                          dtype=['int32', 'int32', 'float32'])

python/cugraph/cugraph/testing/utils.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, 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
@@ -245,7 +245,7 @@ def read_dask_cudf_csv_file(csv_file, read_weights_in_sp=True, single_partition=
             chunksize = os.path.getsize(csv_file)
             return dask_cudf.read_csv(
                 csv_file,
-                chunksize=chunksize,
+                blocksize=chunksize,
                 delimiter=" ",
                 names=["src", "dst", "weight"],
                 dtype=["int32", "int32", "float32"],
@@ -264,7 +264,7 @@ def read_dask_cudf_csv_file(csv_file, read_weights_in_sp=True, single_partition=
             chunksize = os.path.getsize(csv_file)
             return dask_cudf.read_csv(
                 csv_file,
-                chunksize=chunksize,
+                blocksize=chunksize,
                 delimiter=" ",
                 names=["src", "dst", "weight"],
                 dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/comms/test_comms_mg.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, 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
@@ -53,7 +53,7 @@ def test_dask_mg_pagerank(dask_client, directed):
 
     ddf1 = dask_cudf.read_csv(
         input_data_path1,
-        chunksize=chunksize1,
+        blocksize=chunksize1,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],
@@ -66,7 +66,7 @@ def test_dask_mg_pagerank(dask_client, directed):
 
     ddf2 = dask_cudf.read_csv(
         input_data_path2,
-        chunksize=chunksize2,
+        blocksize=chunksize2,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/community/test_leiden_mg.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, 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
@@ -67,7 +67,7 @@ def daskGraphFromDataset(request, dask_client):
     chunksize = dcg.get_chunksize(dataset)
     ddf = dask_cudf.read_csv(
         dataset,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],
@@ -96,7 +96,7 @@ def uddaskGraphFromDataset(request, dask_client):
     chunksize = dcg.get_chunksize(dataset)
     ddf = dask_cudf.read_csv(
         dataset,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/community/test_louvain_mg.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, 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
@@ -67,7 +67,7 @@ def daskGraphFromDataset(request, dask_client):
     chunksize = dcg.get_chunksize(dataset)
     ddf = dask_cudf.read_csv(
         dataset,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],
@@ -96,7 +96,7 @@ def uddaskGraphFromDataset(request, dask_client):
     chunksize = dcg.get_chunksize(dataset)
     ddf = dask_cudf.read_csv(
         dataset,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/community/test_triangle_count_mg.py

@@ -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
@@ -88,7 +88,7 @@ def input_expected_output(dask_client, input_combo):
     chunksize = dcg.get_chunksize(input_data_path)
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/components/test_connectivity_mg.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2023, NVIDIA CORPORATION.
+# Copyright (c) 2020-2024, 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
@@ -48,7 +48,7 @@ def test_dask_mg_wcc(dask_client, directed):
 
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/core/test_core_number_mg.py

@@ -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
@@ -78,7 +78,7 @@ def input_expected_output(dask_client, input_combo):
     chunksize = dcg.get_chunksize(input_data_path)
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],
@@ -143,7 +143,7 @@ def test_core_number_invalid_input(input_expected_output):
     chunksize = dcg.get_chunksize(input_data_path)
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/core/test_k_core_mg.py

@@ -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
@@ -98,7 +98,7 @@ def input_expected_output(dask_client, input_combo):
     chunksize = dcg.get_chunksize(input_data_path)
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],
@@ -164,7 +164,7 @@ def test_dask_mg_k_core_invalid_input(dask_client):
     chunksize = dcg.get_chunksize(input_data_path)
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],

python/cugraph/cugraph/tests/data_store/test_property_graph_mg.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2023, NVIDIA CORPORATION.
+# Copyright (c) 2021-2024, 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
@@ -372,7 +372,7 @@ def net_MGPropertyGraph(dask_client):
     chunksize = dcg.get_chunksize(input_data_path)
     ddf = dask_cudf.read_csv(
         input_data_path,
-        chunksize=chunksize,
+        blocksize=chunksize,
         delimiter=" ",
         names=["src", "dst", "value"],
         dtype=["int32", "int32", "float32"],