[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -1,13 +1,13 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
     -   id: trailing-whitespace
     -   id: end-of-file-fixer
     -   id: check-yaml
     -   id: check-added-large-files
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.11.5
+  rev: v0.16.5
   hooks:
     - id: ruff
       args: [ --fix ]
@@ -16,7 +16,7 @@ repos:
       types_or: ["python"]
 
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.15.0'
+    rev: 'v2.3.1'
     hooks:
     -   id: mypy
         additional_dependencies: ["types-tabulate", "types-requests"]

amlb/__init__.py

@@ -2,23 +2,23 @@
 amlb entrypoint package.
 """
 
-from .logger import app_logger as log
+from .__version__ import __version__
+from .benchmark import Benchmark, SetupMode
 from .errors import AutoMLError
+from .logger import app_logger as log
 from .resources import Resources
-from .benchmark import Benchmark, SetupMode
-from .runners import AWSBenchmark, DockerBenchmark, SingularityBenchmark
 from .results import TaskResult
-from .__version__ import __version__
+from .runners import AWSBenchmark, DockerBenchmark, SingularityBenchmark
 
 __all__ = [
-    "log",
+    "AWSBenchmark",
     "AutoMLError",
-    "Resources",
     "Benchmark",
     "DockerBenchmark",
-    "SingularityBenchmark",
-    "AWSBenchmark",
+    "Resources",
     "SetupMode",
+    "SingularityBenchmark",
     "TaskResult",
     "__version__",
+    "log",
 ]

amlb/benchmark.py

@@ -10,28 +10,32 @@
 
 from __future__ import annotations
 
-from copy import copy
-from enum import Enum
-from functools import cached_property
-from importlib import import_module, invalidate_caches
 import logging
 import math
 import os
 import re
 import signal
 import sys
+from copy import copy
+from enum import Enum
+from functools import cached_property
+from importlib import import_module, invalidate_caches
 
 import pandas as pd
 
-from .frameworks.definitions import load_framework_definition
-from .job import Job, JobError, SimpleJobRunner, MultiThreadingJobRunner
-from .datasets import DataLoader, DataSourceType
 from .data import DatasetType
+from .datasets import DataLoader, DataSourceType
 from .datautils import read_csv
-from .resources import get as rget, config as rconfig, output_dirs as routput_dirs
+from .frameworks.definitions import load_framework_definition
+from .job import Job, JobError, MultiThreadingJobRunner, SimpleJobRunner
+from .resources import config as rconfig
+from .resources import get as rget
+from .resources import output_dirs as routput_dirs
 from .results import ErrorResult, Scoreboard, TaskResult
 from .utils import (
     Namespace as ns,
+)
+from .utils import (
     OSMonitoring,
     as_list,
     datetime_iso,
@@ -51,7 +55,6 @@
     touch,
 )
 
-
 log = logging.getLogger(__name__)
 
 _setup_dir_ = ".setup"
@@ -187,7 +190,7 @@ def setup(self, mode: SetupMode):
         if mode == SetupMode.skip or mode == SetupMode.auto and self._is_setup_done():
             return
 
-        log.info("Setting up framework {}.".format(self.framework_name))
+        log.info(f"Setting up framework {self.framework_name}.")
 
         self._write_setup_env(
             self.framework_module.__path__[0], **dict(self.framework_def.setup_env)
@@ -235,9 +238,7 @@ def resolve_venv(cmd):
             )
 
         invalidate_caches()
-        log.info(
-            "Setup of framework {} completed successfully.".format(self.framework_name)
-        )
+        log.info(f"Setup of framework {self.framework_name} completed successfully.")
 
         self._mark_setup_done()
 
@@ -338,15 +339,17 @@ def on_interrupt(*_):
             # threading.Thread(target=self.cleanup)
 
         try:
-            with signal_handler(signal.SIGINT, on_interrupt):
-                with OSMonitoring(
+            with (
+                signal_handler(signal.SIGINT, on_interrupt),
+                OSMonitoring(
                     name=jobs[0].name if len(jobs) == 1 else None,
                     interval_seconds=rconfig().monitoring.interval_seconds,
                     check_on_exit=True,
                     statistics=rconfig().monitoring.statistics,
                     verbosity=rconfig().monitoring.verbosity,
-                ):
-                    self.job_runner.start()
+                ),
+            ):
+                self.job_runner.start()
         except (KeyboardInterrupt, InterruptedError):
             pass
         finally:
@@ -381,7 +384,7 @@ def _get_task_def(self, task_name, include_disabled=False, fail_on_missing=True)
             )
         except StopIteration:
             if fail_on_missing:
-                raise ValueError("Incorrect task name: {}.".format(task_name))
+                raise ValueError(f"Incorrect task name: {task_name}.")
             return None
         if not include_disabled and not Benchmark._is_task_enabled(task_def):
             raise ValueError(
@@ -563,7 +566,7 @@ def __init__(
         self.git_info = git_info
         self.measure_inference_time = measure_inference_time
         self.ext = ns()  # used if frameworks require extra config points
-        self.quantile_levels = list(sorted(quantile_levels))
+        self.quantile_levels = sorted(quantile_levels)
 
     def __setattr__(self, name, value):
         if name == "metrics":

amlb/benchmarks/file.py

@@ -1,8 +1,8 @@
 import logging
 import os
-from typing import List, Tuple, Optional
+from typing import List, Optional, Tuple
 
-from amlb.utils import config_load, Namespace
+from amlb.utils import Namespace, config_load
 
 log = logging.getLogger(__name__)
 

amlb/benchmarks/openml.py

@@ -6,11 +6,10 @@
 
 import openml
 import pandas as pd
-from openml import OpenMLTask, OpenMLDataset
+from openml import OpenMLDataset, OpenMLTask
 
 from amlb.utils import Namespace, str_sanitize
 
-
 log = logging.getLogger(__name__)
 
 
@@ -67,7 +66,7 @@ def load_openml_tasks_from_suite(domain: str, oml_id: int) -> list[Namespace]:
                 name=str_sanitize(datasets.loc[did]["name"]),
                 description=f"{domain}/d/{did}",
                 openml_task_id=tid,
-                id="{}.org/t/{}".format(domain, tid),
+                id=f"{domain}.org/t/{tid}",
             )
         )
     return tasks
@@ -81,7 +80,7 @@ def load_openml_task_as_definition(domain: str, oml_id: int) -> list[Namespace]:
             name=str_sanitize(data.name),
             description=data.description,
             openml_task_id=task.id,
-            id="{}.org/t/{}".format(domain, task.id),
+            id=f"{domain}.org/t/{task.id}",
         )
     ]
 

amlb/benchmarks/parser.py

@@ -2,9 +2,10 @@
 
 from typing import List, Tuple
 
-from .openml import is_openml_benchmark, load_oml_benchmark
+from amlb.utils import Namespace, str_sanitize
+
 from .file import load_file_benchmark
-from amlb.utils import str_sanitize, Namespace
+from .openml import is_openml_benchmark, load_oml_benchmark
 
 
 def benchmark_load(

amlb/data.py

@@ -13,11 +13,12 @@
 
 from __future__ import annotations
 
+import logging
 from abc import ABC, abstractmethod
+from collections.abc import Iterable
 from enum import Enum
 from functools import cached_property
-import logging
-from typing import List, Union, Iterable
+from typing import List, Union
 
 import numpy as np
 import pandas as pd
@@ -126,15 +127,13 @@ def data_path(self, format: str) -> str:
         :param format: the format requested for the data file. Currently supported formats are 'arff', 'csv'.
         :return: the path to the data-split file in the requested format.
         """
-        pass
 
     @cached_property
     @abstractmethod
     def data(self) -> DF:
         """
         :return: all the columns (predictors + target) as a pandas DataFrame.
         """
-        pass
 
     @cached_property
     @profile(logger=log)
@@ -199,31 +198,27 @@ def type(self) -> DatasetType:
         """
         :return: the problem type for the current dataset.
         """
-        pass
 
     @property
     @abstractmethod
     def train(self) -> Datasplit:
         """
         :return: the data subset used to train the model.
         """
-        pass
 
     @property
     @abstractmethod
     def test(self) -> Datasplit:
         """
         :return: the data subset used to score the model.
         """
-        pass
 
     @property
     @abstractmethod
     def features(self) -> List[Feature]:
         """
         :return: the list of all features available in the current dataset, target included.
         """
-        pass
 
     @property
     def predictors(self) -> List[Feature]:
@@ -238,7 +233,6 @@ def target(self) -> Feature:
         """
         :return: the target feature for the current dataset.
         """
-        pass
 
     @profile(logger=log)
     def release(self) -> None:

amlb/datasets/file.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
-from abc import abstractmethod
 import logging
 import os
 import re
 import tempfile
+from abc import abstractmethod
 from functools import cache, cached_property
 from typing import List
 
@@ -18,15 +18,16 @@
 from ..resources import config as rconfig
 from ..utils import (
     Namespace as ns,
+)
+from ..utils import (
     as_list,
     list_all_files,
     path_from_split,
     profile,
     repr_def,
     split_path,
 )
-
-from .fileutils import is_archive, is_valid_url, unarchive_file, get_file_handler
+from .fileutils import get_file_handler, is_archive, is_valid_url, unarchive_file
 
 log = logging.getLogger(__name__)
 

amlb/datasets/fileutils.py

@@ -2,12 +2,13 @@
 import os
 import shutil
 import tarfile
-import boto3
-from botocore.errorfactory import ClientError
+import zipfile
 from urllib.error import URLError
 from urllib.parse import urlparse
 from urllib.request import Request, urlopen
-import zipfile
+
+import boto3
+from botocore.errorfactory import ClientError
 
 from ..utils import touch