openml · pre-commit-ci · Jun 30, 2025 · Jun 30, 2025
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -7,20 +7,20 @@ files: |
   )/.*\.py$
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.3
+    rev: v0.12.1
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix, --no-cache]
       - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.13.0
+    rev: v1.16.1
     hooks:
       - id: mypy
         additional_dependencies:
           - types-requests
           - types-python-dateutil
   - repo: https://github.com/python-jsonschema/check-jsonschema
-    rev: 0.29.4
+    rev: 0.33.1
     hooks:
       - id: check-github-workflows
         files: '^github/workflows/.*\.ya?ml$'

diff --git a/openml/__init__.py b/openml/__init__.py
@@ -91,33 +91,33 @@ def populate_cache(
 
 
 __all__ = [
-    "OpenMLDataset",
+    "OpenMLBenchmarkSuite",
+    "OpenMLClassificationTask",
+    "OpenMLClusteringTask",
     "OpenMLDataFeature",
-    "OpenMLRun",
-    "OpenMLSplit",
+    "OpenMLDataset",
     "OpenMLEvaluation",
-    "OpenMLSetup",
-    "OpenMLParameter",
-    "OpenMLTask",
-    "OpenMLSupervisedTask",
-    "OpenMLClusteringTask",
+    "OpenMLFlow",
     "OpenMLLearningCurveTask",
+    "OpenMLParameter",
     "OpenMLRegressionTask",
-    "OpenMLClassificationTask",
-    "OpenMLFlow",
+    "OpenMLRun",
+    "OpenMLSetup",
+    "OpenMLSplit",
     "OpenMLStudy",
-    "OpenMLBenchmarkSuite",
+    "OpenMLSupervisedTask",
+    "OpenMLTask",
+    "__version__",
+    "_api_calls",
+    "config",
     "datasets",
     "evaluations",
     "exceptions",
     "extensions",
-    "config",
-    "runs",
     "flows",
-    "tasks",
+    "runs",
     "setups",
     "study",
+    "tasks",
     "utils",
-    "_api_calls",
-    "__version__",
 ]
diff --git a/openml/config.py b/openml/config.py
@@ -256,8 +256,8 @@ def stop_using_configuration_for_example(cls) -> None:
         global server  # noqa: PLW0603
         global apikey  # noqa: PLW0603
 
-        server = cast(str, cls._last_used_server)
-        apikey = cast(str, cls._last_used_key)
+        server = cast("str", cls._last_used_server)
+        apikey = cast("str", cls._last_used_key)
         cls._start_last_called = False
 
 
@@ -514,10 +514,10 @@ def overwrite_config_context(config: dict[str, Any]) -> Iterator[_Config]:
 
 __all__ = [
     "get_cache_directory",
+    "get_config_as_dict",
     "set_root_cache_directory",
     "start_using_configuration_for_example",
     "stop_using_configuration_for_example",
-    "get_config_as_dict",
 ]
 
 _setup()
diff --git a/openml/datasets/__init__.py b/openml/datasets/__init__.py
@@ -17,17 +17,17 @@
 )
 
 __all__ = [
+    "OpenMLDataFeature",
+    "OpenMLDataset",
     "attributes_arff_from_df",
     "check_datasets_active",
     "create_dataset",
+    "delete_dataset",
+    "edit_dataset",
+    "fork_dataset",
     "get_dataset",
     "get_datasets",
     "list_datasets",
-    "OpenMLDataset",
-    "OpenMLDataFeature",
-    "status_update",
     "list_qualities",
-    "edit_dataset",
-    "fork_dataset",
-    "delete_dataset",
+    "status_update",
 ]
diff --git a/openml/datasets/data_feature.py b/openml/datasets/data_feature.py
@@ -51,8 +51,7 @@ def __init__(  # noqa: PLR0913
         if data_type == "nominal":
             if nominal_values is None:
                 raise TypeError(
-                    "Dataset features require attribute `nominal_values` for nominal "
-                    "feature type.",
+                    "Dataset features require attribute `nominal_values` for nominal feature type.",
                 )
 
             if not isinstance(nominal_values, list):

diff --git a/openml/evaluations/__init__.py b/openml/evaluations/__init__.py
@@ -5,7 +5,7 @@
 
 __all__ = [
     "OpenMLEvaluation",
-    "list_evaluations",
     "list_evaluation_measures",
+    "list_evaluations",
     "list_evaluations_setups",
 ]
diff --git a/openml/evaluations/evaluation.py b/openml/evaluations/evaluation.py
@@ -123,7 +123,7 @@ def __repr__(self) -> str:
             "Run ID",
             "OpenML Run URL",
             "Task ID",
-            "OpenML Task URL" "Flow ID",
+            "OpenML Task URLFlow ID",
             "OpenML Flow URL",
             "Setup ID",
             "Data ID",

diff --git a/openml/evaluations/functions.py b/openml/evaluations/functions.py
@@ -228,7 +228,7 @@ def __list_evaluations(api_call: str) -> list[OpenMLEvaluation]:
     # Minimalistic check if the XML is useful
     if "oml:evaluations" not in evals_dict:
         raise ValueError(
-            "Error in return XML, does not contain " f'"oml:evaluations": {evals_dict!s}',
+            f'Error in return XML, does not contain "oml:evaluations": {evals_dict!s}',
         )
 
     assert isinstance(evals_dict["oml:evaluations"]["oml:evaluation"], list), type(

diff --git a/openml/extensions/__init__.py b/openml/extensions/__init__.py
@@ -10,7 +10,7 @@
 
 __all__ = [
     "Extension",
-    "register_extension",
-    "get_extension_by_model",
     "get_extension_by_flow",
+    "get_extension_by_model",
+    "register_extension",
 ]
diff --git a/openml/flows/__init__.py b/openml/flows/__init__.py
@@ -12,10 +12,10 @@
 
 __all__ = [
     "OpenMLFlow",
-    "get_flow",
-    "list_flows",
-    "get_flow_id",
-    "flow_exists",
     "assert_flows_equal",
     "delete_flow",
+    "flow_exists",
+    "get_flow",
+    "get_flow_id",
+    "list_flows",
 ]
diff --git a/openml/flows/flow.py b/openml/flows/flow.py
@@ -169,7 +169,7 @@ def extension(self) -> Extension:
         """The extension of the flow (e.g., sklearn)."""
         if self._extension is None:
             self._extension = cast(
-                Extension, get_extension_by_flow(self, raise_if_no_extension=True)
+                "Extension", get_extension_by_flow(self, raise_if_no_extension=True)
             )
 
         return self._extension
@@ -435,7 +435,7 @@ def publish(self, raise_error_if_exists: bool = False) -> OpenMLFlow:  # noqa: F
         if not flow_id:
             if self.flow_id:
                 raise openml.exceptions.PyOpenMLError(
-                    "Flow does not exist on the server, " "but 'flow.flow_id' is not None.",
+                    "Flow does not exist on the server, but 'flow.flow_id' is not None.",
                 )
             super().publish()
             assert self.flow_id is not None  # for mypy
@@ -445,7 +445,7 @@ def publish(self, raise_error_if_exists: bool = False) -> OpenMLFlow:  # noqa: F
             raise openml.exceptions.PyOpenMLError(error_message)
         elif self.flow_id is not None and self.flow_id != flow_id:
             raise openml.exceptions.PyOpenMLError(
-                "Local flow_id does not match server flow_id: " f"'{self.flow_id}' vs '{flow_id}'",
+                f"Local flow_id does not match server flow_id: '{self.flow_id}' vs '{flow_id}'",
             )
 
         flow = openml.flows.functions.get_flow(flow_id)
@@ -517,7 +517,7 @@ def get_subflow(self, structure: list[str]) -> OpenMLFlow:
         sub_identifier = structure[0]
         if sub_identifier not in self.components:
             raise ValueError(
-                f"Flow {self.name} does not contain component with " f"identifier {sub_identifier}",
+                f"Flow {self.name} does not contain component with identifier {sub_identifier}",
             )
         if len(structure) == 1:
             return self.components[sub_identifier]  # type: ignore

diff --git a/openml/flows/functions.py b/openml/flows/functions.py
@@ -456,9 +456,9 @@ def assert_flows_equal(  # noqa: C901, PLR0912, PLR0913, PLR0915
                         )
 
                 if ignore_parameter_values_on_older_children:
-                    assert (
-                        flow1.upload_date is not None
-                    ), "Flow1 has no upload date that allows us to compare age of children."
+                    assert flow1.upload_date is not None, (
+                        "Flow1 has no upload date that allows us to compare age of children."
+                    )
                     upload_date_current_flow = dateutil.parser.parse(flow1.upload_date)
                     upload_date_parent_flow = dateutil.parser.parse(
                         ignore_parameter_values_on_older_children,

diff --git a/openml/runs/__init__.py b/openml/runs/__init__.py
@@ -19,14 +19,14 @@
     "OpenMLRun",
     "OpenMLRunTrace",
     "OpenMLTraceIteration",
-    "run_model_on_task",
-    "run_flow_on_task",
+    "delete_run",
     "get_run",
-    "list_runs",
-    "get_runs",
     "get_run_trace",
-    "run_exists",
+    "get_runs",
     "initialize_model_from_run",
     "initialize_model_from_trace",
-    "delete_run",
+    "list_runs",
+    "run_exists",
+    "run_flow_on_task",
+    "run_model_on_task",
 ]
diff --git a/openml/runs/run.py b/openml/runs/run.py
@@ -365,7 +365,7 @@ def to_filesystem(
             model.
         """
         if self.data_content is None or self.model is None:
-            raise ValueError("Run should have been executed (and contain " "model / predictions)")
+            raise ValueError("Run should have been executed (and contain model / predictions)")
         directory = Path(directory)
         directory.mkdir(exist_ok=True, parents=True)
 
@@ -517,7 +517,7 @@ def get_metric_fn(self, sklearn_fn: Callable, kwargs: dict | None = None) -> np.
             # TODO: make this a stream reader
         else:
             raise ValueError(
-                "Run should have been locally executed or " "contain outputfile reference.",
+                "Run should have been locally executed or contain outputfile reference.",
             )
 
         # Need to know more about the task to compute scores correctly
@@ -528,11 +528,11 @@ def get_metric_fn(self, sklearn_fn: Callable, kwargs: dict | None = None) -> np.
             task.task_type_id in [TaskType.SUPERVISED_CLASSIFICATION, TaskType.LEARNING_CURVE]
             and "correct" not in attribute_names
         ):
-            raise ValueError('Attribute "correct" should be set for ' "classification task runs")
+            raise ValueError('Attribute "correct" should be set for classification task runs')
         if task.task_type_id == TaskType.SUPERVISED_REGRESSION and "truth" not in attribute_names:
-            raise ValueError('Attribute "truth" should be set for ' "regression task runs")
+            raise ValueError('Attribute "truth" should be set for regression task runs')
         if task.task_type_id != TaskType.CLUSTERING and "prediction" not in attribute_names:
-            raise ValueError('Attribute "predict" should be set for ' "supervised task runs")
+            raise ValueError('Attribute "predict" should be set for supervised task runs')
 
         def _attribute_list_to_dict(attribute_list):  # type: ignore
             # convenience function: Creates a mapping to map from the name of
@@ -566,7 +566,7 @@ def _attribute_list_to_dict(attribute_list):  # type: ignore
             pred = predictions_arff["attributes"][predicted_idx][1]
             corr = predictions_arff["attributes"][correct_idx][1]
             raise ValueError(
-                "Predicted and Correct do not have equal values:" f" {pred!s} Vs. {corr!s}",
+                f"Predicted and Correct do not have equal values: {pred!s} Vs. {corr!s}",
             )
 
         # TODO: these could be cached

diff --git a/openml/runs/trace.py b/openml/runs/trace.py
@@ -185,8 +185,7 @@ def generate(
             raise ValueError("Trace content is empty.")
         if len(attributes) != len(content[0]):
             raise ValueError(
-                "Trace_attributes and trace_content not compatible:"
-                f" {attributes} vs {content[0]}",
+                f"Trace_attributes and trace_content not compatible: {attributes} vs {content[0]}",
             )
 
         return cls._trace_from_arff_struct(

diff --git a/openml/setups/__init__.py b/openml/setups/__init__.py
@@ -4,10 +4,10 @@
 from .setup import OpenMLParameter, OpenMLSetup
 
 __all__ = [
-    "OpenMLSetup",
     "OpenMLParameter",
+    "OpenMLSetup",
     "get_setup",
+    "initialize_model",
     "list_setups",
     "setup_exists",
-    "initialize_model",
 ]
diff --git a/openml/study/__init__.py b/openml/study/__init__.py
@@ -19,8 +19,8 @@
 from .study import OpenMLBenchmarkSuite, OpenMLStudy
 
 __all__ = [
-    "OpenMLStudy",
     "OpenMLBenchmarkSuite",
+    "OpenMLStudy",
     "attach_to_study",
     "attach_to_suite",
     "create_benchmark_suite",
@@ -33,6 +33,6 @@
     "get_suite",
     "list_studies",
     "list_suites",
-    "update_suite_status",
     "update_study_status",
+    "update_suite_status",
 ]
diff --git a/openml/study/functions.py b/openml/study/functions.py
@@ -1,5 +1,4 @@
 # License: BSD 3-Clause
-# ruff: noqa: PLR0913
 from __future__ import annotations
 
 import warnings

diff --git a/openml/tasks/__init__.py b/openml/tasks/__init__.py
@@ -19,17 +19,17 @@
 )
 
 __all__ = [
-    "OpenMLTask",
-    "OpenMLSupervisedTask",
-    "OpenMLClusteringTask",
-    "OpenMLRegressionTask",
     "OpenMLClassificationTask",
+    "OpenMLClusteringTask",
     "OpenMLLearningCurveTask",
+    "OpenMLRegressionTask",
+    "OpenMLSplit",
+    "OpenMLSupervisedTask",
+    "OpenMLTask",
+    "TaskType",
     "create_task",
+    "delete_task",
     "get_task",
     "get_tasks",
     "list_tasks",
-    "OpenMLSplit",
-    "TaskType",
-    "delete_task",
 ]
diff --git a/openml/testing.py b/openml/testing.py
@@ -343,9 +343,9 @@ def create_request_response(
 
 
 __all__ = [
-    "TestBase",
-    "SimpleImputer",
     "CustomImputer",
+    "SimpleImputer",
+    "TestBase",
     "check_task_existence",
     "create_request_response",
 ]