Pre commit ci update config (#719)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/pre-commit/pre-commit-hooks: v4.6.0 → v5.0.0](pre-commit/pre-commit-hooks@v4.6.0...v5.0.0)
- [github.com/astral-sh/ruff-pre-commit: v0.6.5 → v0.9.1](astral-sh/ruff-pre-commit@v0.6.5...v0.9.1)
- [github.com/pre-commit/mirrors-mypy: v1.11.2 → v1.14.1](pre-commit/mirrors-mypy@v1.11.2...v1.14.1)
- [github.com/nbQA-dev/nbQA: 1.8.7 → 1.9.1](nbQA-dev/nbQA@1.8.7...1.9.1)

* [pre-commit.ci] Add auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add lint fixes

* Update ruff version

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: amrit110

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0  # Use the ref you want to point at
+    rev: v5.0.0  # Use the ref you want to point at
     hooks:
     - id: trailing-whitespace
     - id: check-ast
@@ -16,7 +16,7 @@ repos:
     - id: check-toml
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.6.5'
+    rev: 'v0.9.2'
     hooks:
     - id: ruff
       args: [--fix, --exit-non-zero-on-fix]
@@ -25,7 +25,7 @@ repos:
       types_or: [python, jupyter]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.11.2
+    rev: v1.14.1
     hooks:
     - id: mypy
       entry: python3 -m mypy --config-file pyproject.toml
@@ -41,7 +41,7 @@ repos:
       entry: python3 -m nbstripout
 
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.7
+    rev: 1.9.1
     hooks:
     - id: nbqa-black
     - id: nbqa-ruff

cyclops/data/df/feature.py

@@ -60,7 +60,7 @@ def __init__(self, **kwargs: Any) -> None:
         if kwargs[FEATURE_TYPE_ATTR] not in FEATURE_TYPES:
             raise ValueError(
                 f"""Feature type '{kwargs[FEATURE_TYPE_ATTR]}'
-                not in {', '.join(FEATURE_TYPES)}.""",
+                not in {", ".join(FEATURE_TYPES)}.""",
             )
 
         # Set attributes

cyclops/data/features/medical_image.py

@@ -209,11 +209,14 @@ def decode_example(
                     use_auth_token = token_per_repo_id.get(repo_id)
                 except ValueError:
                     use_auth_token = None
-                with xopen(
-                    path,
-                    "rb",
-                    use_auth_token=use_auth_token,
-                ) as file_obj, BytesIO(file_obj.read()) as buffer:
+                with (
+                    xopen(
+                        path,
+                        "rb",
+                        use_auth_token=use_auth_token,
+                    ) as file_obj,
+                    BytesIO(file_obj.read()) as buffer,
+                ):
                     image, metadata = self._read_file_from_bytes(buffer)
                     metadata["filename_or_obj"] = path
 

cyclops/data/impute.py

@@ -304,7 +304,7 @@ def _process_imputefunc(
             if imputefunc not in IMPUTEFUNCS:
                 raise ValueError(
                     f"""Imputefunc string {imputefunc} not supported.
-                    Supporting: {','.join(IMPUTEFUNCS)}""",
+                    Supporting: {",".join(IMPUTEFUNCS)}""",
                 )
             func = IMPUTEFUNCS[imputefunc]
         elif callable(imputefunc):

cyclops/data/slicer.py

@@ -825,8 +825,7 @@ def filter_string_contains(
     example_values = pa.array(examples[column_name])
     if not pa.types.is_string(example_values.type):
         raise ValueError(
-            "Expected string feature, but got feature of type "
-            f"{example_values.type}.",
+            f"Expected string feature, but got feature of type {example_values.type}.",
         )
 
     # get all the values that contain the given substring

cyclops/evaluate/evaluator.py

@@ -170,8 +170,7 @@ def _load_data(
         if split is None:
             split = choose_split(dataset, **load_dataset_kwargs)
             LOGGER.warning(
-                "Got `split=None` but `dataset` is a string. "
-                "Using `split=%s` instead.",
+                "Got `split=None` but `dataset` is a string. Using `split=%s` instead.",
                 split,
             )
 

cyclops/evaluate/fairness/evaluator.py

@@ -150,7 +150,7 @@ def evaluate_fairness(  # noqa: PLR0912
     # input validation and formatting
     if not isinstance(dataset, Dataset):
         raise TypeError(
-            "Expected `dataset` to be of type `Dataset`, but got " f"{type(dataset)}.",
+            f"Expected `dataset` to be of type `Dataset`, but got {type(dataset)}.",
         )
     if array_lib not in _SUPPORTED_ARRAY_LIBS:
         raise NotImplementedError(f"The array library `{array_lib}` is not supported.")
@@ -520,8 +520,7 @@ def _validate_group_bins(
     for group, bins in group_bins.items():
         if not isinstance(bins, (list, int)):
             raise TypeError(
-                f"The bins for {group} must be a list or an integer. "
-                f"Got {type(bins)}.",
+                f"The bins for {group} must be a list or an integer. Got {type(bins)}.",
             )
 
         if isinstance(bins, int) and not 2 <= bins < len(unique_values[group]):

cyclops/evaluate/metrics/accuracy.py

@@ -339,19 +339,19 @@ def __new__(  # type: ignore # mypy expects a subclass of Accuracy
                 zero_division=zero_division,
             )
         if task == "multiclass":
-            assert (
-                isinstance(num_classes, int) and num_classes > 0
-            ), "Number of classes must be specified for multiclass classification."
+            assert isinstance(num_classes, int) and num_classes > 0, (
+                "Number of classes must be specified for multiclass classification."
+            )
             return MulticlassAccuracy(
                 num_classes=num_classes,
                 top_k=top_k,
                 average=average,
                 zero_division=zero_division,
             )
         if task == "multilabel":
-            assert (
-                isinstance(num_labels, int) and num_labels > 0
-            ), "Number of labels must be specified for multilabel classification."
+            assert isinstance(num_labels, int) and num_labels > 0, (
+                "Number of labels must be specified for multilabel classification."
+            )
             return MultilabelAccuracy(
                 num_labels=num_labels,
                 threshold=threshold,

cyclops/evaluate/metrics/auroc.py

@@ -336,18 +336,18 @@ def __new__(  # type: ignore # mypy expects a subclass of AUROC
         if task == "binary":
             return BinaryAUROC(max_fpr=max_fpr, thresholds=thresholds)
         if task == "multiclass":
-            assert (
-                isinstance(num_classes, int) and num_classes > 0
-            ), "Number of classes must be a positive integer."
+            assert isinstance(num_classes, int) and num_classes > 0, (
+                "Number of classes must be a positive integer."
+            )
             return MulticlassAUROC(
                 num_classes=num_classes,
                 thresholds=thresholds,
                 average=average,  # type: ignore
             )
         if task == "multilabel":
-            assert (
-                isinstance(num_labels, int) and num_labels > 0
-            ), "Number of labels must be a positive integer."
+            assert isinstance(num_labels, int) and num_labels > 0, (
+                "Number of labels must be a positive integer."
+            )
             return MultilabelAUROC(
                 num_labels=num_labels,
                 thresholds=thresholds,

cyclops/evaluate/metrics/experimental/utils/types.py

@@ -1,3 +1,5 @@
+# noqa: A005
+
 """Utilities for array-API compatibility."""
 
 import builtins