[pre-commit.ci] pre-commit autoupdate

.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: v0.11.0
     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: v1.15.0
     hooks:
       - id: mypy
         additional_dependencies:
           - types-requests
           - types-python-dateutil
   - repo: https://github.com/python-jsonschema/check-jsonschema
-    rev: 0.29.4
+    rev: 0.31.3
     hooks:
       - id: check-github-workflows
         files: '^github/workflows/.*\.ya?ml$'

openml/__init__.py

@@ -91,35 +91,35 @@ 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__",
 ]
 
 # Load the scikit-learn extension by default

openml/config.py

@@ -254,8 +254,8 @@ 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
 
 
@@ -513,10 +513,10 @@ 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()

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",
 ]

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):

openml/datasets/dataset.py

@@ -448,7 +448,7 @@ def _parse_data_from_arff(  # noqa: C901, PLR0912, PLR0915
             data = self._get_arff(self.format)
         except OSError as e:
             logger.critical(
-                f"Please check that the data file {arff_file_path} is " "there and can be read.",
+                f"Please check that the data file {arff_file_path} is there and can be read.",
             )
             raise e
 

openml/datasets/functions.py

@@ -72,7 +72,7 @@ def list_qualities() -> list[str]:
         raise ValueError('Error in return XML, does not contain "oml:data_qualities_list"')
 
     if not isinstance(qualities["oml:data_qualities_list"]["oml:quality"], list):
-        raise TypeError("Error in return XML, does not contain " '"oml:quality" as a list')
+        raise TypeError('Error in return XML, does not contain "oml:quality" as a list')
 
     return qualities["oml:data_qualities_list"]["oml:quality"]
 
@@ -177,7 +177,7 @@ def list_datasets(
     """
     if output_format not in ["dataframe", "dict"]:
         raise ValueError(
-            "Invalid output format selected. " "Only 'dict' or 'dataframe' applicable.",
+            "Invalid output format selected. Only 'dict' or 'dataframe' applicable.",
         )
 
     # TODO: [0.15]

openml/evaluations/__init__.py

@@ -5,7 +5,7 @@
 
 __all__ = [
     "OpenMLEvaluation",
-    "list_evaluations",
     "list_evaluation_measures",
+    "list_evaluations",
     "list_evaluations_setups",
 ]

openml/evaluations/evaluation.py

@@ -103,7 +103,7 @@ 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",

openml/evaluations/functions.py

@@ -234,7 +234,7 @@ def __list_evaluations(
     # 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(
@@ -321,9 +321,9 @@ def list_evaluation_measures() -> list[str]:
     qualities = xmltodict.parse(xml_string, force_list=("oml:measures"))
     # Minimalistic check if the XML is useful
     if "oml:evaluation_measures" not in qualities:
-        raise ValueError("Error in return XML, does not contain " '"oml:evaluation_measures"')
+        raise ValueError('Error in return XML, does not contain "oml:evaluation_measures"')
     if not isinstance(qualities["oml:evaluation_measures"]["oml:measures"][0]["oml:measure"], list):
-        raise TypeError("Error in return XML, does not contain " '"oml:measure" as a list')
+        raise TypeError('Error in return XML, does not contain "oml:measure" as a list')
     return qualities["oml:evaluation_measures"]["oml:measures"][0]["oml:measure"]
 
 
@@ -343,13 +343,13 @@ def list_estimation_procedures() -> list[str]:
 
     # Minimalistic check if the XML is useful
     if "oml:estimationprocedures" not in api_results:
-        raise ValueError("Error in return XML, does not contain " '"oml:estimationprocedures"')
+        raise ValueError('Error in return XML, does not contain "oml:estimationprocedures"')
     if "oml:estimationprocedure" not in api_results["oml:estimationprocedures"]:
-        raise ValueError("Error in return XML, does not contain " '"oml:estimationprocedure"')
+        raise ValueError('Error in return XML, does not contain "oml:estimationprocedure"')
 
     if not isinstance(api_results["oml:estimationprocedures"]["oml:estimationprocedure"], list):
         raise TypeError(
-            "Error in return XML, does not contain " '"oml:estimationprocedure" as a list',
+            'Error in return XML, does not contain "oml:estimationprocedure" as a list',
         )
 
     return [
@@ -415,7 +415,7 @@ def list_evaluations_setups(
     """
     if parameters_in_separate_columns and (flows is None or len(flows) != 1):
         raise ValueError(
-            "Can set parameters_in_separate_columns to true " "only for single flow_id",
+            "Can set parameters_in_separate_columns to true only for single flow_id",
         )
 
     # List evaluations

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",
 ]

openml/extensions/sklearn/extension.py

@@ -1254,8 +1254,7 @@ def _check_dependencies(
             else:
                 raise NotImplementedError(f"operation '{operation}' is not supported")
             message = (
-                "Trying to deserialize a model with dependency "
-                f"{dependency_string} not satisfied."
+                f"Trying to deserialize a model with dependency {dependency_string} not satisfied."
             )
             if not check:
                 if strict_version:
@@ -1497,7 +1496,7 @@ def _prevent_optimize_n_jobs(self, model):
             )
             if len(n_jobs_vals) > 0:
                 raise PyOpenMLError(
-                    "openml-python should not be used to " "optimize the n_jobs parameter.",
+                    "openml-python should not be used to optimize the n_jobs parameter.",
                 )
 
     ################################################################################################
@@ -1555,7 +1554,7 @@ def _seed_current_object(current_value):
 
             if current_value is not None:
                 raise ValueError(
-                    "Models should be seeded with int or None (this should never " "happen). ",
+                    "Models should be seeded with int or None (this should never happen). ",
                 )
 
             return True
@@ -1780,10 +1779,10 @@ def _prediction_to_probabilities(
             # to handle the case when dataset is numpy and categories are encoded
             # however the class labels stored in task are still categories
             if isinstance(y_train, np.ndarray) and isinstance(
-                cast(List, task.class_labels)[0],
+                cast("List", task.class_labels)[0],
                 str,
             ):
-                model_classes = [cast(List[str], task.class_labels)[i] for i in model_classes]
+                model_classes = [cast("List[str]", task.class_labels)[i] for i in model_classes]
 
         modelpredict_start_cputime = time.process_time()
         modelpredict_start_walltime = time.time()
@@ -2006,7 +2005,7 @@ def is_subcomponent_specification(values):
                         # (mixed)). OpenML replaces the subcomponent by an
                         # OpenMLFlow object.
                         if len(subcomponent) < 2 or len(subcomponent) > 3:
-                            raise ValueError("Component reference should be " "size {2,3}. ")
+                            raise ValueError("Component reference should be size {2,3}. ")
 
                         subcomponent_identifier = subcomponent[0]
                         subcomponent_flow = subcomponent[1]

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",
 ]

openml/flows/flow.py

@@ -438,7 +438,7 @@ 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
@@ -448,7 +448,7 @@ 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)
@@ -520,7 +520,7 @@ 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

openml/flows/functions.py

@@ -67,7 +67,7 @@ def _get_cached_flow(fid: int) -> OpenMLFlow:
             return _create_flow_from_xml(fh.read())
     except OSError as e:
         openml.utils._remove_cache_dir_for_id(FLOWS_CACHE_DIR_NAME, fid_cache_dir)
-        raise OpenMLCacheException("Flow file for fid %d not " "cached" % fid) from e
+        raise OpenMLCacheException("Flow file for fid %d not cached" % fid) from e
 
 
 @openml.utils.thread_safe_if_oslo_installed
@@ -217,7 +217,7 @@ def list_flows(
     """
     if output_format not in ["dataframe", "dict"]:
         raise ValueError(
-            "Invalid output format selected. " "Only 'dict' or 'dataframe' applicable.",
+            "Invalid output format selected. Only 'dict' or 'dataframe' applicable.",
         )
 
     # TODO: [0.15]
@@ -514,11 +514,11 @@ def assert_flows_equal(  # noqa: C901, PLR0912, PLR0913, PLR0915
             for name in set(attr1.keys()).union(attr2.keys()):
                 if name not in attr1:
                     raise ValueError(
-                        f"Component {name} only available in " "argument2, but not in argument1.",
+                        f"Component {name} only available in argument2, but not in argument1.",
                     )
                 if name not in attr2:
                     raise ValueError(
-                        f"Component {name} only available in " "argument2, but not in argument1.",
+                        f"Component {name} only available in argument2, but not in argument1.",
                     )
                 assert_flows_equal(
                     attr1[name],
@@ -547,9 +547,9 @@ 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,
@@ -579,7 +579,7 @@ def assert_flows_equal(  # noqa: C901, PLR0912, PLR0913, PLR0915
                 params2 = set(flow2.parameters_meta_info)
                 if params1 != params2:
                     raise ValueError(
-                        "Parameter list in meta info for parameters differ " "in the two flows.",
+                        "Parameter list in meta info for parameters differ in the two flows.",
                     )
                 # iterating over the parameter's meta info list
                 for param in params1: