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

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

Author: pre-commit-ci[bot]

openml/_api_calls.py

@@ -12,7 +12,6 @@
 import xml
 import zipfile
 from pathlib import Path
-from typing import Dict, Tuple, Union
 
 import minio
 import requests
@@ -33,8 +32,8 @@
 
 _HEADERS = {"user-agent": f"openml-python/{__version__}"}
 
-DATA_TYPE = Dict[str, Union[str, int]]
-FILE_ELEMENTS_TYPE = Dict[str, Union[str, Tuple[str, str]]]
+DATA_TYPE = dict[str, str | int]
+FILE_ELEMENTS_TYPE = dict[str, str | tuple[str, str]]
 DATABASE_CONNECTION_ERRCODE = 107
 
 API_TOKEN_HELP_LINK = "https://openml.github.io/openml-python/latest/examples/Basics/introduction_tutorial/#authentication"  # noqa: S105

openml/base.py

@@ -4,7 +4,7 @@
 import re
 import webbrowser
 from abc import ABC, abstractmethod
-from typing import Iterable, Sequence
+from collections.abc import Iterable, Sequence
 
 import xmltodict
 

openml/cli.py

@@ -5,8 +5,8 @@
 import argparse
 import string
 import sys
+from collections.abc import Callable
 from pathlib import Path
-from typing import Callable
 from urllib.parse import urlparse
 
 from openml import config

openml/config.py

@@ -10,11 +10,12 @@
 import platform
 import shutil
 import warnings
+from collections.abc import Iterator
 from contextlib import contextmanager
 from io import StringIO
 from pathlib import Path
-from typing import Any, Iterator, cast
-from typing_extensions import Literal, TypedDict
+from typing import Any, Literal, cast
+from typing_extensions import TypedDict
 from urllib.parse import urlparse
 
 logger = logging.getLogger(__name__)

openml/datasets/data_feature.py

@@ -1,7 +1,8 @@
 # License: BSD 3-Clause
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Any, ClassVar, Sequence
+from collections.abc import Sequence
+from typing import TYPE_CHECKING, Any, ClassVar
 
 if TYPE_CHECKING:
     from IPython.lib import pretty

openml/datasets/dataset.py

@@ -7,9 +7,9 @@
 import pickle
 import re
 import warnings
+from collections.abc import Iterable, Sequence
 from pathlib import Path
-from typing import Any, Iterable, Sequence
-from typing_extensions import Literal
+from typing import Any, Literal
 
 import arff
 import numpy as np
@@ -766,8 +766,8 @@ def get_data(  # noqa: C901
             logger.info(f"Going to remove the following attributes: {to_exclude}")
             keep = np.array([column not in to_exclude for column in attribute_names])
             data = data.drop(columns=to_exclude)
-            categorical_mask = [cat for cat, k in zip(categorical_mask, keep) if k]
-            attribute_names = [att for att, k in zip(attribute_names, keep) if k]
+            categorical_mask = [cat for cat, k in zip(categorical_mask, keep, strict=False) if k]
+            attribute_names = [att for att, k in zip(attribute_names, keep, strict=False) if k]
 
         if target is None:
             return data, None, categorical_mask, attribute_names

openml/datasets/functions.py

@@ -9,8 +9,7 @@
 from functools import partial
 from pathlib import Path
 from pyexpat import ExpatError
-from typing import TYPE_CHECKING, Any
-from typing_extensions import Literal
+from typing import TYPE_CHECKING, Any, Literal
 
 import arff
 import minio.error

openml/evaluations/functions.py

@@ -5,8 +5,8 @@
 import json
 from functools import partial
 from itertools import chain
-from typing import Any
-from typing_extensions import Literal, overload
+from typing import Any, Literal
+from typing_extensions import overload
 
 import numpy as np
 import pandas as pd

openml/flows/flow.py

@@ -3,8 +3,9 @@
 
 import logging
 from collections import OrderedDict
+from collections.abc import Hashable, Sequence
 from pathlib import Path
-from typing import Any, Hashable, Sequence, cast
+from typing import Any, cast
 
 import xmltodict
 

openml/flows/functions.py

@@ -5,7 +5,7 @@
 import re
 from collections import OrderedDict
 from functools import partial
-from typing import Any, Dict
+from typing import Any
 
 import dateutil.parser
 import pandas as pd
@@ -417,7 +417,7 @@ def assert_flows_equal(  # noqa: C901, PLR0912, PLR0913, PLR0915
         attr1 = getattr(flow1, key, None)
         attr2 = getattr(flow2, key, None)
         if key == "components":
-            if not (isinstance(attr1, Dict) and isinstance(attr2, Dict)):
+            if not (isinstance(attr1, dict) and isinstance(attr2, dict)):
                 raise TypeError("Cannot compare components because they are not dictionary.")
 
             for name in set(attr1.keys()).union(attr2.keys()):
@@ -493,8 +493,8 @@ def assert_flows_equal(  # noqa: C901, PLR0912, PLR0913, PLR0915
                 # iterating over the parameter's meta info list
                 for param in params1:
                     if (
-                        isinstance(flow1.parameters_meta_info[param], Dict)
-                        and isinstance(flow2.parameters_meta_info[param], Dict)
+                        isinstance(flow1.parameters_meta_info[param], dict)
+                        and isinstance(flow2.parameters_meta_info[param], dict)
                         and "data_type" in flow1.parameters_meta_info[param]
                         and "data_type" in flow2.parameters_meta_info[param]
                     ):