Update flake8 to 7.1.1.

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
         files: ^(python/.*|benchmarks/.*)$
         exclude: ^python/nx-cugraph/
   - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
+    rev: 7.1.1
     hooks:
       - id: flake8
         args: ["--config=.flake8"]
@@ -34,7 +34,7 @@ repos:
     hooks:
       - id: yesqa
         additional_dependencies:
-          - flake8==6.0.0
+          - flake8==7.1.1
   - repo: https://github.com/pre-commit/mirrors-clang-format
     rev: v16.0.6
     hooks:

benchmarks/cugraph-dgl/python-script/ogbn_mag_benchmark.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
@@ -126,4 +126,4 @@ def sampling_func(g, seed_nodes, labels, train_loader):
     st = time.time()
     sampling_func(g, subset_split_idx["train"], labels, train_loader)
     et = time.time()
-    print(f"Sampling time taken  = {et-st} s")
+    print(f"Sampling time taken  = {et - st} s")

python/cugraph-dgl/cugraph_dgl/nn/conv/base.py

@@ -129,15 +129,15 @@ def __init__(
         if csrc_ids is not None:
             if csrc_ids.numel() != self._num_src_nodes + 1:
                 raise RuntimeError(
-                    f"Size mismatch for 'csrc_ids': expected ({size[0]+1},), "
+                    f"Size mismatch for 'csrc_ids': expected ({size[0] + 1},), "
                     f"but got {tuple(csrc_ids.size())}"
                 )
             csrc_ids = csrc_ids.contiguous()
 
         if cdst_ids is not None:
             if cdst_ids.numel() != self._num_dst_nodes + 1:
                 raise RuntimeError(
-                    f"Size mismatch for 'cdst_ids': expected ({size[1]+1},), "
+                    f"Size mismatch for 'cdst_ids': expected ({size[1] + 1},), "
                     f"but got {tuple(cdst_ids.size())}"
                 )
             cdst_ids = cdst_ids.contiguous()

python/cugraph-dgl/examples/graphsage/node-classification-dask.py

@@ -205,7 +205,9 @@ def train(args, device, g, dataset, model):
 
         et = time.time()
 
-        print(f"Time taken for epoch {epoch} with batch_size {batch_size} = {et-st} s")
+        print(
+            f"Time taken for epoch {epoch} with batch_size {batch_size} = {et - st} s"
+        )
         acc = evaluate(model, g, val_dataloader)
         print(
             "Epoch {:05d} | Loss {:.4f} | Accuracy {:.4f} ".format(

python/cugraph-dgl/examples/graphsage/node-classification.py

@@ -215,7 +215,9 @@ def train(args, device, g, dataset, model, directory):
 
         et = time.time()
 
-        print(f"Time taken for epoch {epoch} with batch_size {batch_size} = {et-st} s")
+        print(
+            f"Time taken for epoch {epoch} with batch_size {batch_size} = {et - st} s"
+        )
         acc = evaluate(model, g, val_dataloader)
         print(
             "Epoch {:05d} | Loss {:.4f} | Accuracy {:.4f} ".format(

python/cugraph-dgl/examples/multi_trainer_MG_example/model.py

@@ -134,7 +134,7 @@ def train_model(model, g, opt, train_dataloader, num_epochs, rank, val_nid):
     et = time.time()
     print(
         f"Total time taken for num_epochs {num_epochs} "
-        f"with batch_size {train_dataloader._batch_size} = {et-st} s on rank ={rank}"
+        f"with batch_size {train_dataloader._batch_size} = {et - st} s on rank ={rank}"
     )
     if rank == 0:
         val_acc = layerwise_infer(g, val_nid, model, 1024 * 5, "cuda")

python/cugraph-dgl/examples/multi_trainer_MG_example/workflow_mnmg.py

@@ -234,7 +234,7 @@ def run_workflow(
     torch.distributed.barrier()
     total_et = time.time()
     print(
-        f"Total time taken on n_epochs {n_epochs} = {total_et-total_st} s",
+        f"Total time taken on n_epochs {n_epochs} = {total_et - total_st} s",
         f"measured by worker = {global_rank}",
     )
 

python/cugraph-dgl/examples/multi_trainer_MG_example/workflow_snmg.py

@@ -207,7 +207,7 @@ def run_workflow(rank, world_size, cugraph_id, dataset, temp_dir):
     torch.distributed.barrier()
     total_et = time.time()
     print(
-        f"Total time taken on n_epochs {n_epochs} = {total_et-total_st} s",
+        f"Total time taken on n_epochs {n_epochs} = {total_et - total_st} s",
         f"measured by worker = {rank}",
     )
 

python/cugraph-pyg/cugraph_pyg/data/dask_graph_store.py

@@ -150,7 +150,7 @@ def is_set(self, key):
         if key not in self.__dataclass_fields__:
             raise KeyError(key)
         attr = getattr(self, key)
-        return type(attr) != _field_status or attr != _field_status.UNSET
+        return type(attr) is not _field_status or attr != _field_status.UNSET
 
     def is_fully_specified(self):
         """

python/cugraph-pyg/cugraph_pyg/examples/gcn_dist_sg.py

@@ -66,7 +66,7 @@ def train(epoch: int):
     torch.cuda.synchronize()
     print(
         f"Average Training Iteration Time (s/iter): \
-            {(time.perf_counter() - start_avg_time)/(i-warmup_steps):.6f}"
+            {(time.perf_counter() - start_avg_time) / (i - warmup_steps):.6f}"
     )
 
 

python/cugraph-service/tests/test_e2e.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.
@@ -307,8 +307,8 @@ def test_load_call_unload_extension(client, extension1):
     assert len(results) == 2
     assert len(results[0]) == 33
     assert len(results[1]) == 21
-    assert type(results[0][0]) == int
-    assert type(results[1][0]) == float
+    assert type(results[0][0]) is int
+    assert type(results[1][0]) is float
     assert results[0][0] == 9
     assert results[1][0] == 9.0
 

python/cugraph-service/tests/test_mg_e2e.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.
@@ -413,8 +413,8 @@ def test_call_extension_result_on_device(
         assert len(results) == 2
         assert len(results[0]) == array1_len
         assert len(results[1]) == array2_len
-        assert type(results[0][0]) == int
-        assert type(results[1][0]) == float
+        assert type(results[0][0]) is int
+        assert type(results[1][0]) is float
         assert results[0][0] == 9
         assert results[1][0] == 9.0
     else:

python/cugraph/cugraph/tests/generators/test_rmat.py

@@ -27,7 +27,9 @@
 _scale_values = [2, 4, 16]
 _scale_test_ids = [f"scale={x}" for x in _scale_values]
 _graph_types = [cugraph.Graph, None, int]
-_graph_test_ids = [f"create_using={getattr(x,'__name__',str(x))}" for x in _graph_types]
+_graph_test_ids = [
+    f"create_using={getattr(x, '__name__', str(x))}" for x in _graph_types
+]
 _clip_and_flip = [False, True]
 _clip_and_flip_test_ids = [f"clip_and_flip={x}" for x in _clip_and_flip]
 _scramble_vertex_ids = [False, True]

python/cugraph/cugraph/tests/generators/test_rmat_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
@@ -34,7 +34,9 @@
 _scale_values = [2, 4, 16]
 _scale_test_ids = [f"scale={x}" for x in _scale_values]
 _graph_types = [cugraph.Graph, None, int]
-_graph_test_ids = [f"create_using={getattr(x,'__name__',str(x))}" for x in _graph_types]
+_graph_test_ids = [
+    f"create_using={getattr(x, '__name__', str(x))}" for x in _graph_types
+]
 
 
 def _call_rmat(scale, num_edges, create_using, mg=True):

python/cugraph/cugraph/tests/sampling/test_bulk_sampler.py

@@ -119,7 +119,7 @@ def test_bulk_sampler_remainder(scratch_dir):
         assert b in recovered_samples["batch_id"].values_host.tolist()
 
     for x in range(0, 6, 2):
-        subdir = f"{x}-{x+1}"
+        subdir = f"{x}-{x + 1}"
         df = cudf.read_parquet(os.path.join(samples_path, f"batch={subdir}.parquet"))
 
         assert ((df.batch_id == x) | (df.batch_id == (x + 1))).all()

python/cugraph/cugraph/tests/structure/test_graph_mg.py

@@ -303,7 +303,7 @@ def test_mg_graph_serializable(dask_client, input_combo):
     G = input_combo["MGGraph"]
     dask_client.publish_dataset(shared_g=G)
     shared_g = dask_client.get_dataset("shared_g")
-    assert type(shared_g) == type(G)
+    assert type(shared_g) is type(G)
     assert G.number_of_vertices() == shared_g.number_of_vertices()
     assert G.number_of_edges() == shared_g.number_of_edges()
     # cleanup
@@ -314,7 +314,7 @@ def test_mg_graph_serializable(dask_client, input_combo):
 def test_mg_graph_copy():
     G = cugraph.MultiGraph(directed=True)
     G_c = copy.deepcopy(G)
-    assert type(G) == type(G_c)
+    assert type(G) is type(G_c)
 
 
 @pytest.mark.mg

python/cugraph/cugraph/tests/traversal/test_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.
 # You may obtain a copy of the License at
@@ -486,7 +486,7 @@ def test_scipy_api_compat():
     distances = cugraph.shortest_path(
         input_coo_matrix, source=0, return_predecessors=False
     )
-    assert type(distances) != tuple
+    assert type(distances) is not tuple
 
     with pytest.raises(ValueError):
         cugraph.shortest_path(input_coo_matrix, source=0, unweighted=False)

python/cugraph/cugraph/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.
 # You may obtain a copy of the License at
@@ -36,7 +36,7 @@ def _ensure_args(
     # checks common to all input types
     if (method is not None) and (method != "auto"):
         raise ValueError("only 'auto' is currently accepted for method")
-    if (indices is not None) and (type(indices) == list):
+    if (indices is not None) and (type(indices) is list):
         raise ValueError("indices currently cannot be a list-like type")
     if (indices is not None) and (source is not None):
         raise TypeError("cannot specify both 'source' and 'indices'")
@@ -70,9 +70,11 @@ def _ensure_args(
 
     # Check for non-Graph-type inputs
     else:
-        if (directed is not None) and (type(directed) != bool):
+        if (directed is not None) and (type(directed) is not bool):
             raise ValueError("'directed' must be a bool")
-        if (return_predecessors is not None) and (type(return_predecessors) != bool):
+        if (return_predecessors is not None) and (
+            type(return_predecessors) is not bool
+        ):
             raise ValueError("'return_predecessors' must be a bool")
         if (unweighted is not None) and (unweighted is not True):
             raise ValueError("'unweighted' currently must be True if " "specified")