Merge remote-tracking branch 'upstream/main' into read-csv-from-directory

Author: fangchenli

.github/workflows/unit-tests.yml

@@ -91,7 +91,7 @@ jobs:
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_CI: '1'
-      PANDAS_FUTURE_INFER_STRING: ${{ matrix.pandas_future_infer_string || '0' }}
+      PANDAS_FUTURE_INFER_STRING: ${{ matrix.pandas_future_infer_string || '1' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}

doc/source/whatsnew/v3.0.0.rst

@@ -457,6 +457,7 @@ Other Deprecations
 - Deprecated :meth:`.DataFrameGroupby.corrwith` (:issue:`57158`)
 - Deprecated :meth:`Timestamp.utcfromtimestamp`, use ``Timestamp.fromtimestamp(ts, "UTC")`` instead (:issue:`56680`)
 - Deprecated :meth:`Timestamp.utcnow`, use ``Timestamp.now("UTC")`` instead (:issue:`56680`)
+- Deprecated ``pd.core.internals.api.maybe_infer_ndim`` (:issue:`40226`)
 - Deprecated allowing non-keyword arguments in :meth:`DataFrame.all`, :meth:`DataFrame.min`, :meth:`DataFrame.max`, :meth:`DataFrame.sum`, :meth:`DataFrame.prod`, :meth:`DataFrame.mean`, :meth:`DataFrame.median`, :meth:`DataFrame.sem`, :meth:`DataFrame.var`, :meth:`DataFrame.std`, :meth:`DataFrame.skew`, :meth:`DataFrame.kurt`, :meth:`Series.all`,  :meth:`Series.min`, :meth:`Series.max`, :meth:`Series.sum`, :meth:`Series.prod`, :meth:`Series.mean`, :meth:`Series.median`, :meth:`Series.sem`, :meth:`Series.var`, :meth:`Series.std`, :meth:`Series.skew`, and :meth:`Series.kurt`. (:issue:`57087`)
 - Deprecated allowing non-keyword arguments in :meth:`Series.to_markdown` except ``buf``. (:issue:`57280`)
 - Deprecated allowing non-keyword arguments in :meth:`Series.to_string` except ``buf``. (:issue:`57280`)

pandas/_libs/internals.pyx

@@ -709,9 +709,9 @@ cdef class Block:
             self.ndim = state[2]
         else:
             # older pickle
-            from pandas.core.internals.api import maybe_infer_ndim
+            from pandas.core.internals.api import _maybe_infer_ndim
 
-            ndim = maybe_infer_ndim(self.values, self.mgr_locs)
+            ndim = _maybe_infer_ndim(self.values, self.mgr_locs)
             self.ndim = ndim
 
     cpdef Block slice_block_rows(self, slice slicer):

pandas/core/generic.py

@@ -1918,7 +1918,7 @@ def keys(self) -> Index:
         b  2  4
         c  3  8
         >>> d.keys()
-        Index(['A', 'B'], dtype='object')
+        Index(['A', 'B'], dtype='str')
         """
         return self._info_axis
 
@@ -6276,7 +6276,7 @@ def dtypes(self):
         float              float64
         int                  int64
         datetime    datetime64[s]
-        string              object
+        string              str
         dtype: object
         """
         data = self._mgr.get_dtypes()
@@ -6838,7 +6838,7 @@ def convert_dtypes(
         0      a
         1      b
         2    NaN
-        dtype: object
+        dtype: str
 
         Obtain a Series with dtype ``StringDtype``.
 
@@ -8138,7 +8138,7 @@ def isna(self) -> Self:
         ... )
         >>> df
            age       born    name        toy
-        0  5.0        NaT  Alfred       None
+        0  5.0        NaT  Alfred        NaN
         1  6.0 1939-05-27  Batman  Batmobile
         2  NaN 1940-04-25              Joker
 
@@ -8211,7 +8211,7 @@ def notna(self) -> Self:
         ... )
         >>> df
            age       born    name        toy
-        0  5.0        NaT  Alfred       None
+        0  5.0        NaT  Alfred        NaN
         1  6.0 1939-05-27  Batman  Batmobile
         2  NaN 1940-04-25              Joker
 
@@ -10401,7 +10401,7 @@ def truncate(
         2    b
         3    c
         4    d
-        Name: A, dtype: object
+        Name: A, dtype: str
 
         The index values in ``truncate`` can be datetimes or string
         dates.

pandas/core/internals/api.py

@@ -136,7 +136,7 @@ def make_block(
     if not isinstance(placement, BlockPlacement):
         placement = BlockPlacement(placement)
 
-    ndim = maybe_infer_ndim(values, placement, ndim)
+    ndim = _maybe_infer_ndim(values, placement, ndim)
     if isinstance(values.dtype, (PeriodDtype, DatetimeTZDtype)):
         # GH#41168 ensure we can pass 1D dt64tz values
         # More generally, any EA dtype that isn't is_1d_only_ea_dtype
@@ -148,7 +148,7 @@ def make_block(
     return klass(values, ndim=ndim, placement=placement)
 
 
-def maybe_infer_ndim(values, placement: BlockPlacement, ndim: int | None) -> int:
+def _maybe_infer_ndim(values, placement: BlockPlacement, ndim: int | None) -> int:
     """
     If `ndim` is not provided, infer it from placement and values.
     """
@@ -162,3 +162,15 @@ def maybe_infer_ndim(values, placement: BlockPlacement, ndim: int | None) -> int
         else:
             ndim = values.ndim
     return ndim
+
+
+def maybe_infer_ndim(values, placement: BlockPlacement, ndim: int | None) -> int:
+    """
+    If `ndim` is not provided, infer it from placement and values.
+    """
+    warnings.warn(
+        "maybe_infer_ndim is deprecated and will be removed in a future version.",
+        DeprecationWarning,
+        stacklevel=2,
+    )
+    return _maybe_infer_ndim(values, placement, ndim)

pandas/core/tools/numeric.py

@@ -55,7 +55,8 @@ def to_numeric(
     """
     Convert argument to a numeric type.
 
-    The default return dtype is `float64` or `int64`
+    If the input is already of a numeric dtype, the dtype will be preserved.
+    For non-numeric inputs, the default return dtype is `float64` or `int64`
     depending on the data supplied. Use the `downcast` parameter
     to obtain other dtypes.
 

pandas/tests/indexing/test_iloc.py

@@ -6,6 +6,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import pa_version_under16p0
 from pandas.errors import IndexingError
 
 from pandas import (
@@ -140,6 +141,9 @@ def test_is_scalar_access(self):
         df = ser.to_frame()
         assert df.iloc._is_scalar_access((1, 0))
 
+    @pytest.mark.skipif(
+        pa_version_under16p0, reason="https://github.com/apache/arrow/issues/40642"
+    )
     def test_iloc_exceeds_bounds(self):
         # GH6296
         # iloc should allow indexers that exceed the bounds

pandas/tests/internals/test_api.py

@@ -79,6 +79,15 @@ def test_create_block_manager_from_blocks_deprecated():
         internals.create_block_manager_from_blocks
 
 
+def test_maybe_infer_ndim_deprecated():
+    # GH#40226
+    msg = "maybe_infer_ndim is deprecated and will be removed in a future version."
+    arr = np.arange(5)
+    bp = pd._libs.internals.BlockPlacement([1])
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
+        internals.api.maybe_infer_ndim(arr, bp, 1)
+
+
 def test_create_dataframe_from_blocks(float_frame):
     block = float_frame._mgr.blocks[0]
     index = float_frame.index.copy()

pandas/tests/io/test_gcs.py

@@ -216,7 +216,6 @@ def test_to_parquet_gcs_new_file(monkeypatch, tmpdir):
         {
             "int": [1, 3],
             "float": [2.0, np.nan],
-            "str": ["t", "s"],
             "dt": date_range("2018-06-18", periods=2),
         }
     )