Fixed hooks

Author: tasfia8

.gitignore

@@ -140,4 +140,4 @@ doc/source/savefig/
 
 # Ignore virtual environments
 pandas-env/
-*.pyc
+*.pyc

pandas/core/arrays/string_arrow.py

@@ -5,8 +5,8 @@
 from typing import (
     TYPE_CHECKING,
     Union,
-    KeysView,
 )
+from collections.abc import KeysView
 import warnings
 
 import numpy as np
@@ -193,13 +193,12 @@ def _from_sequence(
         # handle explicit dtype "string" or "str"
         if dtype:
             if isinstance(dtype, str) and dtype == "str":
-            # Use StringDtype with Python storage explicitly
+                # Use StringDtype with Python storage explicitly
                 dtype = StringDtype(storage="python")
             else:
                 dtype = pandas_dtype(dtype)
                 assert isinstance(dtype, StringDtype) and dtype.storage == "pyarrow"
 
-
         if isinstance(scalars, BaseMaskedArray):
             # avoid costly conversion to object dtype in ensure_string_array and
             # numerical issues with Float32Dtype
@@ -210,9 +209,8 @@ def _from_sequence(
         elif isinstance(scalars, (pa.Array, pa.ChunkedArray)):
             return cls(pc.cast(scalars, pa.large_string()))
 
-
-        elif isinstance(scalars, KeysView): 
-            #Convert dict_keys to a NumPy array
+        elif isinstance(scalars, KeysView):
+            # Convert dict_keys to a NumPy array
             scalars = list(scalars)
 
         # convert non-na-likes to str

pandas/core/construction.py

@@ -11,8 +11,8 @@
     TYPE_CHECKING,
     cast,
     overload,
-    KeysView,
 )
+from collections.abc import KeysView
 
 import numpy as np
 from numpy import ma
@@ -664,13 +664,14 @@ def sanitize_array(
         # at this point we should have dtype be None or subarr.dtype == dtype
         dtype = cast(np.dtype, dtype)
         subarr = _sanitize_str_dtypes(subarr, data, dtype, copy)
-    
+
     from pandas.core.arrays.string_ import StringDtype
-    if dtype == "str": 
+
+    if dtype == "str":
         # Use StringDtype explicitly when dtype="str"
         dtype = StringDtype(storage="python")
-    
-    if isinstance(data, KeysView): 
+
+    if isinstance(data, KeysView):
         # Convert dict_keys to a list for processing
         data = list(data)
 

pandas/core/dtypes/common.py

@@ -180,8 +180,12 @@ def is_object_dtype(arr_or_dtype) -> bool:
     False
     """
     from pandas.core.arrays.string_ import StringDtype
-    return isinstance(arr_or_dtype, np.dtype) and arr_or_dtype == "object" or isinstance(arr_or_dtype, StringDtype)
 
+    return (
+        isinstance(arr_or_dtype, np.dtype)
+        and arr_or_dtype == "object"
+        or isinstance(arr_or_dtype, StringDtype)
+    )
 
 
 def is_sparse(arr) -> bool:

pandas/core/indexers/utils.py

@@ -10,8 +10,6 @@
 )
 
 import numpy as np
-import pandas as pd
-
 
 from pandas._libs import lib
 
@@ -28,6 +26,8 @@
     ABCSeries,
 )
 
+import pandas as pd
+
 if TYPE_CHECKING:
     from pandas._typing import AnyArrayLike
 
@@ -536,7 +536,7 @@ def check_array_indexer(array: AnyArrayLike, indexer: Any) -> Any:
             indexer = indexer.to_numpy(dtype=bool, na_value=False)
         else:
             indexer = np.asarray(indexer, dtype=bool)
-        
+
         # Allow empty boolean indexer for StringArray (string[python] dtype)
         if len(indexer) == 0 and isinstance(array, pd.arrays.StringArray):
             return indexer

pandas/core/indexes/base.py

@@ -482,16 +482,16 @@ def __new__(
         name=None,
         tupleize_cols: bool = True,
     ) -> Self:
+        from pandas.core.arrays.string_ import StringDtype
         from pandas.core.indexes.range import RangeIndex
-        from pandas.core.arrays.string_ import StringDtype 
 
         name = maybe_extract_name(name, data, cls)
 
         if dtype is not None:
-            if dtype == "str": 
+            if dtype == "str":
                 dtype = StringDtype(storage="python")
             dtype = pandas_dtype(dtype)
-        
+
         data_dtype = getattr(data, "dtype", None)
 
         refs = None
@@ -569,7 +569,7 @@ def __new__(
 
         try:
             arr = sanitize_array(data, None, dtype=dtype, copy=copy)
-            #print(f"sanitize_array received dtype: {dtype}") 
+            # print(f"sanitize_array received dtype: {dtype}")
         except ValueError as err:
             if "index must be specified when data is not list-like" in str(err):
                 raise cls._raise_scalar_data_error(data) from err

pandas/tests/indexes/categorical/test_formats.py

@@ -54,7 +54,7 @@ def test_string_categorical_index_repr(self):
         expected = """CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
                   'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""  # noqa: E501
+                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""egory')"""  # noqa: E501
 
         assert repr(idx) == expected
 
@@ -63,15 +63,15 @@ def test_string_categorical_index_repr(self):
         expected = """CategoricalIndex(['あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ',
                   ...
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""  # noqa: E501
+                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""length=300)"""  # noqa: E501
 
         assert repr(idx) == expected
 
         # larger categories
         idx = CategoricalIndex(list("あいうえおかきくけこさしすせそ"))
         expected = """CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ', 'さ', 'し',
                   'す', 'せ', 'そ'],
-                 categories=['あ', 'い', 'う', 'え', ..., 'し', 'す', 'せ', 'そ'], ordered=False, dtype='category')"""  # noqa: E501
+                 categories=['あ', 'い', 'う', 'え', ..., 'し', 'す', 'せ', 'そ'], ordered=False, dtype='category')"""ory')"""  # noqa: E501
 
         assert repr(idx) == expected
 
@@ -88,7 +88,7 @@ def test_string_categorical_index_repr(self):
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
                   'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい',
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""  # noqa: E501
+                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category')"""ory')"""  # noqa: E501
 
             assert repr(idx) == expected
 
@@ -99,14 +99,14 @@ def test_string_categorical_index_repr(self):
                   ...
                   'ううう', 'あ', 'いい', 'ううう', 'あ', 'いい', 'ううう',
                   'あ', 'いい', 'ううう'],
-                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""  # noqa: E501
+                 categories=['あ', 'いい', 'ううう'], ordered=False, dtype='category', length=300)"""ength=300)"""  # noqa: E501
 
             assert repr(idx) == expected
 
             # larger categories
             idx = CategoricalIndex(list("あいうえおかきくけこさしすせそ"))
             expected = """CategoricalIndex(['あ', 'い', 'う', 'え', 'お', 'か', 'き', 'く', 'け', 'こ',
                   'さ', 'し', 'す', 'せ', 'そ'],
-                 categories=['あ', 'い', 'う', 'え', ..., 'し', 'す', 'せ', 'そ'], ordered=False, dtype='category')"""  # noqa: E501
+                 categories=['あ', 'い', 'う', 'え', ..., 'し', 'す', 'せ', 'そ'], ordered=False, dtype='category')""")"""  # noqa: E501
 
             assert repr(idx) == expected

pandas/tests/indexes/test_base.py

@@ -69,15 +69,14 @@ def test_constructor_casting(self, index):
         arr = np.array(index)
         new_index = Index(arr)
         tm.assert_contains_all(arr, new_index)
-        
+
         if index.dtype.name == "string":
-        # Allow conversion to object when casting back through NumPy array
+            # Allow conversion to object when casting back through NumPy array
             assert new_index.dtype.name == "object"
             tm.assert_index_equal(index.astype("object"), new_index)
         else:
             tm.assert_index_equal(index, new_index)
 
-
     def test_constructor_copy(self, using_infer_string):
         index = Index(list("abc"), name="name")
         arr = np.array(index)
@@ -486,7 +485,6 @@ def test_empty_fancy(self, index, dtype, request, using_infer_string):
 
         assert index[[]].identical(empty_index)
         if dtype == np.bool_:
-
             if index.dtype.name == "string":
                 # `string[python]` allows empty boolean indexing
                 assert index[empty_arr].identical(empty_index)
@@ -692,17 +690,18 @@ def test_is_numeric(self, index, expected):
     def test_is_object(self, index, expected, using_infer_string):
         if using_infer_string and index.dtype == "string" and expected:
             expected = False
-        #Bug fix 
+        # Bug fix
         if index.dtype.name == "string":
             assert not is_object_dtype(index)  # string[python] is not an object dtype
         elif index.dtype.name == "object":
             # Ensure object dtype behaves as expected
-            assert index.dtype.name == "object", "Index with dtype='object' should be recognized as such"
+            assert (
+                index.dtype.name == "object"
+            ), "Index with dtype='object' should be recognized as such"
         else:
             # For other dtypes, use the expected value
             assert is_object_dtype(index) is expected
 
-
     def test_summary(self, index):
         index._summary()
 
@@ -1743,7 +1742,8 @@ def test_is_monotonic_pyarrow_list_type():
     assert not idx.is_monotonic_increasing
     assert not idx.is_monotonic_decreasing
 
-def test_index_from_dict_keys_with_dtype():  
+
+def test_index_from_dict_keys_with_dtype():
     d = {"a": 1, "b": 2}
 
     # Test without dtype (default inference)

pandas/tests/io/parser/usecols/test_strings.py

@@ -79,7 +79,7 @@ def test_usecols_with_multi_byte_characters(all_parsers):
     data = """あああ,いい,ううう,ええええ
 0.056674973,8,True,a
 2.613230982,2,False,b
-3.568935038,7,False,a"""
+3.568935038,7,False,a"""e,a"""
     parser = all_parsers
 
     exp_data = {