Updated .pre-commit-config.yaml file and reformatted few files for better readability. (#1211)

* Used pylint automated tool to update from .format to f-strings.

* Updated the pre-commit configuration file.

* Reformatted 2 more files to use f-strings.

* Added new check that verifies .toml files in the repo, and updated black repo link.

---------

Co-authored-by: Claudia Comito <[email protected]>

Author: Sai-Suraj-27

.pre-commit-config.yaml

@@ -2,17 +2,21 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.0.0
+    rev: v4.4.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
     -   id: check-yaml
     -   id: check-added-large-files
-    -   id: flake8
--   repo: https://github.com/psf/black
+    -   id: check-toml
+-   repo: https://github.com/psf/black-pre-commit-mirror
     rev: 23.9.1
     hooks:
     -   id: black
+-   repo: https://github.com/PyCQA/flake8
+    rev: 6.1.0
+    hooks:
+      - id: flake8
 -   repo: https://github.com/pycqa/pydocstyle
     rev: 6.3.0  # pick a git hash / tag to point to
     hooks:

benchmarks/2020/distance_matrix/dask-chunks-cpu.py

@@ -31,4 +31,4 @@
         start = time.perf_counter()
         dist = dmm.euclidean_distances(data, data).compute()
         end = time.perf_counter()
-        print("\t{}s".format(end - start))
+        print(f"\t{end - start}s")

benchmarks/2020/generate_jobscripts.py

@@ -76,7 +76,7 @@ def jobscripts_from(
         if key in SKIP:
             continue
 
-        parameters.append("--{}".format(key))
+        parameters.append(f"--{key}")
         parameters.append(str(value))
 
     for script, benchmark in configuration["benchmarks"].items():

examples/nn/imagenet-DASO.py

@@ -330,8 +330,8 @@ def main():
         print0("Test mode - no DDP, no apex, RN50, 10 iterations")
 
     args.distributed = True  # TODO: DDDP: if ht.MPI_WORLD.size > 1 else False
-    print0("loss_scale = {}".format(args.loss_scale), type(args.loss_scale))
-    print0("\nCUDNN VERSION: {}\n".format(torch.backends.cudnn.version()))
+    print0(f"loss_scale = {args.loss_scale}", type(args.loss_scale))
+    print0(f"\nCUDNN VERSION: {torch.backends.cudnn.version()}\n")
 
     cudnn.benchmark = True
     best_prec1 = 0
@@ -379,10 +379,10 @@ def main():
 
     # create model
     if args.pretrained:
-        print0("=> using pre-trained model '{}'".format(args.arch))
+        print0(f"=> using pre-trained model '{args.arch}'")
         model = models.__dict__[args.arch](pretrained=True)
     else:
-        print0("=> creating model '{}'".format(args.arch))
+        print0(f"=> creating model '{args.arch}'")
         model = models.__dict__[args.arch]()
 
     if (
@@ -426,7 +426,7 @@ def main():
         # Use a local scope to avoid dangling references
         def resume():
             if os.path.isfile(args.resume):
-                print0("=> loading checkpoint '{}'".format(args.resume))
+                print0(f"=> loading checkpoint '{args.resume}'")
                 checkpoint = torch.load(
                     args.resume, map_location=lambda storage, loc: storage.cuda(args.gpu)
                 )
@@ -440,7 +440,7 @@ def resume():
             else:
                 try:
                     resfile = "imgnet-checkpoint-" + str(args.world_size) + ".pth.tar"
-                    print0("=> loading checkpoint '{}'".format(resfile))
+                    print0(f"=> loading checkpoint '{resfile}'")
                     checkpoint = torch.load(
                         resfile, map_location=lambda storage, loc: storage.cuda(args.gpu)
                     )
@@ -636,11 +636,11 @@ def train(dev, train_loader, model, criterion, optimizer, epoch):
         target = data[0]["label"].squeeze().cuda(dev).long()
 
         if 0 <= args.prof == i:
-            print("Profiling begun at iteration {}".format(i))
+            print(f"Profiling begun at iteration {i}")
             torch.cuda.cudart().cudaProfilerStart()
 
         if args.prof >= 0:
-            torch.cuda.nvtx.range_push("Body of iteration {}".format(i))
+            torch.cuda.nvtx.range_push(f"Body of iteration {i}")
 
         lr_warmup(optimizer, epoch, i, train_loader_len)
 
@@ -719,7 +719,7 @@ def train(dev, train_loader, model, criterion, optimizer, epoch):
             torch.cuda.nvtx.range_pop()
 
         if args.prof >= 0 and i == args.prof + 10:
-            print0("Profiling ended at iteration {}".format(i))
+            print0(f"Profiling ended at iteration {i}")
             torch.cuda.cudart().cudaProfilerStop()
             quit()
     # todo average loss, and top1 and top5

examples/nn/imagenet.py

@@ -324,7 +324,7 @@ def validate(val_loader, model, criterion, args):
                 progress.display(i)
 
         # TODO: this should also be done with the ProgressMeter
-        print(" * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}".format(top1=top1, top5=top5))
+        print(f" * Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}")
 
     return top1.avg
 

heat/cluster/_kcluster.py

@@ -132,7 +132,7 @@ def _initialize_cluster_centers(self, x: DNDarray):
         elif isinstance(self.init, DNDarray):
             if len(self.init.shape) != 2:
                 raise ValueError(
-                    "passed centroids need to be two-dimensional, but are {}".format(len(self.init))
+                    f"passed centroids need to be two-dimensional, but are {len(self.init)}"
                 )
             if self.init.shape[0] != self.n_clusters or self.init.shape[1] != x.shape[1]:
                 raise ValueError("passed centroids do not match cluster count or data shape")

heat/core/base.py

@@ -63,7 +63,7 @@ def __repr__(self, indent: int = 1) -> str:
         indent : int, default: 1
             Indicates the indentation for the top-level output.
         """
-        return "{}({})".format(self.__class__.__name__, json.dumps(self.get_params(), indent=4))
+        return f"{self.__class__.__name__}({json.dumps(self.get_params(), indent=4)})"
 
     def set_params(self, **params: Dict[str, object]) -> self:
         """

heat/core/factories.py

@@ -323,7 +323,7 @@ def array(
                     else devices.get_device().torch_device,
                 )
             except RuntimeError:
-                raise TypeError("invalid data of type {}".format(type(obj)))
+                raise TypeError(f"invalid data of type {type(obj)}")
     else:
         if copy is False and not np.isscalar(obj) and not isinstance(obj, (Tuple, List)):
             # Python array-API compliance, cf. https://data-apis.org/array-api/2022.12/API_specification/generated/array_api.asarray.html
@@ -346,7 +346,7 @@ def array(
                 else devices.get_device().torch_device,
             )
         except RuntimeError:
-            raise TypeError("invalid data of type {}".format(type(obj)))
+            raise TypeError(f"invalid data of type {type(obj)}")
 
     # infer dtype from obj if not explicitly given
     if dtype is None:

heat/core/io.py

@@ -110,7 +110,7 @@ def load_hdf5(
         if not isinstance(path, str):
             raise TypeError(f"path must be str, not {type(path)}")
         elif not isinstance(dataset, str):
-            raise TypeError("dataset must be str, not {}".format(type(dataset)))
+            raise TypeError(f"dataset must be str, not {type(dataset)}")
         elif split is not None and not isinstance(split, int):
             raise TypeError(f"split must be None or int, not {type(split)}")
 
@@ -410,11 +410,11 @@ def save_netcdf(
         >>> ht.save_netcdf(x, 'data.nc', dataset='DATA')
         """
         if not isinstance(data, DNDarray):
-            raise TypeError("data must be heat tensor, not {}".format(type(data)))
+            raise TypeError(f"data must be heat tensor, not {type(data)}")
         if not isinstance(path, str):
-            raise TypeError("path must be str, not {}".format(type(path)))
+            raise TypeError(f"path must be str, not {type(path)}")
         if not isinstance(variable, str):
-            raise TypeError("variable must be str, not {}".format(type(path)))
+            raise TypeError(f"variable must be str, not {type(path)}")
         if dimension_names is None:
             dimension_names = [
                 __NETCDF_DIM_TEMPLATE.format(variable, dim) for dim, _ in enumerate(data.shape)
@@ -430,15 +430,11 @@ def save_netcdf(
                 )
             )
         elif not len(dimension_names) == len(data.shape):
-            raise ValueError(
-                "{0} names given for {1} dimensions".format(len(dimension_names), len(data.shape))
-            )
+            raise ValueError(f"{len(dimension_names)} names given for {len(data.shape)} dimensions")
 
         # we only support a subset of possible modes
         if mode not in __VALID_WRITE_MODES:
-            raise ValueError(
-                "mode was {}, not in possible modes {}".format(mode, __VALID_WRITE_MODES)
-            )
+            raise ValueError(f"mode was {mode}, not in possible modes {__VALID_WRITE_MODES}")
 
         failed = 0
         excep = None
@@ -468,9 +464,7 @@ def __get_expanded_split(
                 If resulting shapes do not match.
             """
             if np.prod(shape) != np.prod(expanded_shape):
-                raise ValueError(
-                    "Shapes %s and %s do not have the same size" % (shape, expanded_shape)
-                )
+                raise ValueError(f"Shapes {shape} and {expanded_shape} do not have the same size")
             if np.prod(shape) == 1:  # size 1 array
                 return split
             if len(shape) == len(expanded_shape):  # actually not expanded at all
@@ -484,7 +478,7 @@ def __get_expanded_split(
             ex_ind_nonempty, sq_ex = list(zip(*enumerated))  # transpose
             if not sq_shape == sq_ex:
                 raise ValueError(
-                    "Shapes %s and %s differ in non-empty dimensions" % (shape, expanded_shape)
+                    f"Shapes {shape} and {expanded_shape} differ in non-empty dimensions"
                 )
             if split in ind_nonempty:  # split along non-empty dimension
                 split_sq = ind_nonempty.index(split)  # split-axis in squeezed shape
@@ -664,7 +658,7 @@ def __merge_slices(
             raise excep
         elif failed:
             excep = data.comm.bcast(excep, root=failed - 1)
-            excep.args = "raised by process rank {}".format(failed - 1), *excep.args
+            excep.args = f"raised by process rank {failed - 1}", *excep.args
             raise excep from None  # raise the same error but without traceback
             # because that is on a different process
 

heat/core/linalg/svdtools.py

@@ -85,7 +85,7 @@ def hsvd_rank(
         [2] Himpe, Leibner, Rave. Hierarchical approximate proper orthogonal decomposition. SIAM J. Sci. Comput., 40 (5), 2018.
     """
     if not isinstance(A, DNDarray):
-        raise TypeError("Argument needs to be a DNDarray but is {}.".format(type(A)))
+        raise TypeError(f"Argument needs to be a DNDarray but is {type(A)}.")
     if not A.ndim == 2:
         raise ValueError("A needs to be a 2D matrix")
     if not A.dtype == types.float32 and not A.dtype == types.float64:
@@ -197,7 +197,7 @@ def hsvd_rtol(
         [2] Himpe, Leibner, Rave. Hierarchical approximate proper orthogonal decomposition. SIAM J. Sci. Comput., 40 (5), 2018.
     """
     if not isinstance(A, DNDarray):
-        raise TypeError("Argument needs to be a DNDarray but is {}.".format(type(A)))
+        raise TypeError(f"Argument needs to be a DNDarray but is {type(A)}.")
     if not A.ndim == 2:
         raise ValueError("A needs to be a 2D matrix")
     if not A.dtype == types.float32 and not A.dtype == types.float64: