fixups

Author: MarcoGorelli

.pre-commit-config.yaml

@@ -181,15 +181,10 @@ repos:
         types: [rst]
         args: [--filename=*.rst]
         additional_dependencies: [flake8-rst==0.7.0, flake8==3.7.9]
-    -   id: frame-or-series-union
-        name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
-        entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]
-        language: pygrep
-        types: [python]
-        exclude: ^pandas/_typing\.py$
     -   id: inconsistent-namespace-usage
         name: 'Check for inconsistent use of pandas namespace'
         entry: python scripts/check_for_inconsistent_pandas_namespace.py
+        exclude: ^pandas/core/interchange/
         language: python
         types: [python]
     -   id: no-os-remove
@@ -200,9 +195,7 @@ repos:
         files: ^pandas/tests/
         exclude: |
             (?x)^
-            pandas/tests/io/excel/test_writers\.py
-            |pandas/tests/io/pytables/common\.py
-            |pandas/tests/io/pytables/test_store\.py$
+            pandas/tests/io/pytables/test_store\.py$
     -   id: unwanted-patterns
         name: Unwanted patterns
         language: pygrep
@@ -216,12 +209,8 @@ repos:
             |\.__class__
 
             # np.bool/np.object instead of np.bool_/np.object_
-            |np\.bool[^_8]
-            |np\.object[^_8]
-
-            # imports from pandas.core.common instead of `import pandas.core.common as com`
-            |from\ pandas\.core\.common\ import
-            |from\ pandas\.core\ import\ common
+            |np\.bool[^_8`]
+            |np\.object[^_8`]
 
             # imports from collections.abc instead of `from collections import abc`
             |from\ collections\.abc\ import
@@ -331,7 +320,10 @@ repos:
         language: python
         entry: python scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module"
         types: [python]
-        exclude: ^(asv_bench|pandas/tests|doc)/
+        exclude: |
+            (?x)
+            ^(asv_bench|pandas/tests|doc)/
+            |scripts/validate_min_versions_in_sync\.py$
     -   id: unwanted-patterns-strings-to-concatenate
         name: Check for use of not concatenated strings
         language: python

doc/scripts/eval_performance.py

@@ -6,8 +6,7 @@
 from pandas import DataFrame
 
 setup_common = """from pandas import DataFrame
-from numpy.random import randn
-df = DataFrame(randn(%d, 3), columns=list('abc'))
+df = DataFrame(np.random.randn(%d, 3), columns=list('abc'))
 %s"""
 
 setup_with = "s = 'a + b * (c ** 2 + b ** 2 - a) / (a * c) ** 3'"

doc/source/development/code_style.rst

@@ -320,7 +320,7 @@ Null-values are no longer coerced to NaN-value in value_counts and mode
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 :meth:`Series.value_counts` and :meth:`Series.mode` no longer coerce ``None``,
-``NaT`` and other null-values to a NaN-value for ``np.object``-dtype. This
+``NaT`` and other null-values to a NaN-value for ``np.object_``-dtype. This
 behavior is now consistent with ``unique``, ``isin`` and others
 (:issue:`42688`).
 

doc/source/whatsnew/v1.4.0.rst

@@ -135,7 +135,7 @@
 )
 
 from pandas import api, arrays, errors, io, plotting, tseries
-from pandas import testing  # noqa:PDF015
+from pandas import testing
 from pandas.util._print_versions import show_versions
 
 from pandas.io.api import (

pandas/__init__.py

@@ -1482,7 +1482,7 @@ def infer_dtype(value: object, skipna: bool = True) -> str:
         return val
 
     if values.descr.type_num != NPY_OBJECT:
-        # i.e. values.dtype != np.object
+        # i.e. values.dtype != np.object_
         # This should not be reached
         values = values.astype(object)
 

pandas/_libs/lib.pyx

@@ -14,7 +14,10 @@
 import sys
 
 from pandas._typing import F
-import pandas.compat._compressors
+from pandas.compat._compressors import (
+    LZMAFile,
+    has_lzma,
+)
 from pandas.compat._constants import (
     IS64,
     PY39,
@@ -131,7 +134,7 @@ def is_ci_environment() -> bool:
     return os.environ.get("PANDAS_CI", "0") == "1"
 
 
-def get_lzma_file() -> type[pandas.compat._compressors.LZMAFile]:
+def get_lzma_file() -> type[LZMAFile]:
     """
     Importing the `LZMAFile` class from the `lzma` module.
 
@@ -145,13 +148,13 @@ def get_lzma_file() -> type[pandas.compat._compressors.LZMAFile]:
     RuntimeError
         If the `lzma` module was not imported correctly, or didn't exist.
     """
-    if not pandas.compat._compressors.has_lzma:
+    if not has_lzma:
         raise RuntimeError(
             "lzma module not available. "
             "A Python re-install with the proper dependencies, "
             "might be required to solve this issue."
         )
-    return pandas.compat._compressors.LZMAFile
+    return LZMAFile
 
 
 __all__ = [

pandas/compat/__init__.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from collections.abc import Callable  # noqa: PDF001
+from collections import abc
 import re
 from typing import Union
 
@@ -302,7 +302,7 @@ def _str_endswith(self, pat: str, na=None):
     def _str_replace(
         self,
         pat: str | re.Pattern,
-        repl: str | Callable,
+        repl: str | abc.Callable,
         n: int = -1,
         case: bool = True,
         flags: int = 0,

pandas/core/arrays/string_arrow.py

@@ -133,11 +133,11 @@
 from pandas.core import (
     algorithms as algos,
     arraylike,
+    common,
     indexing,
     nanops,
     sample,
 )
-from pandas.core import common  # noqa: PDF018
 from pandas.core.array_algos.replace import should_use_regex
 from pandas.core.arrays import ExtensionArray
 from pandas.core.base import PandasObject

pandas/core/generic.py

@@ -7,8 +7,10 @@
 from pandas.core.interchange.dataframe_protocol import DataFrame as DataFrameXchg
 
 if TYPE_CHECKING:
-    import pandas as pd
-    from pandas import Index
+    from pandas import (
+        DataFrame,
+        Index,
+    )
 
 
 class PandasDataFrameXchg(DataFrameXchg):
@@ -21,7 +23,7 @@ class PandasDataFrameXchg(DataFrameXchg):
     """
 
     def __init__(
-        self, df: pd.DataFrame, nan_as_null: bool = False, allow_copy: bool = True
+        self, df: DataFrame, nan_as_null: bool = False, allow_copy: bool = True
     ) -> None:
         """
         Constructor - an instance of this (private) class is returned from