Merge remote-tracking branch 'upstream/main' into issue-61319

Author: HoqueUM

.pre-commit-config.yaml

@@ -1,4 +1,4 @@
-minimum_pre_commit_version: 2.15.0
+minimum_pre_commit_version: 4.0.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
@@ -19,13 +19,13 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.9
+    rev: v0.11.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
         exclude: ^pandas/tests/frame/test_query_eval.py
     -   id: ruff
-        # TODO: remove autofixe-only rules when they are checked by ruff
+        # TODO: remove autofix only rules when they are checked by ruff
         name: ruff-selected-autofixes
         alias: ruff-selected-autofixes
         files: ^pandas
@@ -34,7 +34,7 @@ repos:
     -   id: ruff-format
         exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.14'
+    rev: v2.14
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -95,14 +95,14 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.7
+    rev: v20.1.0
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.7.0
+    rev: v1.7.2
     hooks:
     - id: meson-fmt
       args: ['--inplace']

asv_bench/benchmarks/frame_methods.py

@@ -517,7 +517,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(1000, 100))
 
         self.s = Series(np.arange(1028.0))
-        self.df2 = DataFrame({i: self.s for i in range(1028)})
+        self.df2 = DataFrame(dict.fromkeys(range(1028), self.s))
         self.df3 = DataFrame(np.random.randn(1000, 3), columns=list("ABC"))
 
     def time_apply_user_func(self):

asv_bench/benchmarks/indexing_engines.py

@@ -67,6 +67,14 @@ class NumericEngineIndexing:
     def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in [np.int16, np.int8, np.uint8]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)
@@ -115,6 +123,14 @@ def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
         dtype = dtype.lower()
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in ["int16", "int8", "uint8"]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)

ci/code_checks.sh

@@ -72,9 +72,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Timestamp.max PR02" \
-        -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \

doc/source/getting_started/comparison/comparison_with_r.rst

@@ -383,7 +383,7 @@ In Python, since ``a`` is a list, you can simply use list comprehension.
 
 .. ipython:: python
 
-   a = np.array(list(range(1, 24)) + [np.NAN]).reshape(2, 3, 4)
+   a = np.array(list(range(1, 24)) + [np.nan]).reshape(2, 3, 4)
    pd.DataFrame([tuple(list(x) + [val]) for x, val in np.ndenumerate(a)])
 
 meltlist
@@ -402,7 +402,7 @@ In Python, this list would be a list of tuples, so
 
 .. ipython:: python
 
-   a = list(enumerate(list(range(1, 5)) + [np.NAN]))
+   a = list(enumerate(list(range(1, 5)) + [np.nan]))
    pd.DataFrame(a)
 
 For more details and examples see :ref:`the Intro to Data Structures

doc/source/reference/groupby.rst

@@ -79,6 +79,8 @@ Function application
    DataFrameGroupBy.cumsum
    DataFrameGroupBy.describe
    DataFrameGroupBy.diff
+   DataFrameGroupBy.ewm
+   DataFrameGroupBy.expanding
    DataFrameGroupBy.ffill
    DataFrameGroupBy.first
    DataFrameGroupBy.head
@@ -130,6 +132,8 @@ Function application
    SeriesGroupBy.cumsum
    SeriesGroupBy.describe
    SeriesGroupBy.diff
+   SeriesGroupBy.ewm
+   SeriesGroupBy.expanding
    SeriesGroupBy.ffill
    SeriesGroupBy.first
    SeriesGroupBy.head

doc/source/user_guide/basics.rst

@@ -2064,12 +2064,12 @@ different numeric dtypes will **NOT** be combined. The following example will gi
 
 .. ipython:: python
 
-   df1 = pd.DataFrame(np.random.randn(8, 1), columns=["A"], dtype="float32")
+   df1 = pd.DataFrame(np.random.randn(8, 1), columns=["A"], dtype="float64")
    df1
    df1.dtypes
    df2 = pd.DataFrame(
        {
-           "A": pd.Series(np.random.randn(8), dtype="float16"),
+           "A": pd.Series(np.random.randn(8), dtype="float32"),
            "B": pd.Series(np.random.randn(8)),
            "C": pd.Series(np.random.randint(0, 255, size=8), dtype="uint8"),  # [0,255] (range of uint8)
        }

doc/source/user_guide/enhancingperf.rst

@@ -171,6 +171,7 @@ can be improved by passing an ``np.ndarray``.
    In [4]: %%cython
       ...: cimport numpy as np
       ...: import numpy as np
+      ...: np.import_array()
       ...: cdef double f_typed(double x) except? -2:
       ...:     return x * (x - 1)
       ...: cpdef double integrate_f_typed(double a, double b, int N):
@@ -225,6 +226,7 @@ and ``wraparound`` checks can yield more performance.
       ...: cimport cython
       ...: cimport numpy as np
       ...: import numpy as np
+      ...: np.import_array()
       ...: cdef np.float64_t f_typed(np.float64_t x) except? -2:
       ...:     return x * (x - 1)
       ...: cpdef np.float64_t integrate_f_typed(np.float64_t a, np.float64_t b, np.int64_t N):

doc/source/whatsnew/v0.11.0.rst

@@ -74,10 +74,10 @@ Numeric dtypes will propagate and can coexist in DataFrames. If a dtype is passe
 
 .. ipython:: python
 
-   df1 = pd.DataFrame(np.random.randn(8, 1), columns=['A'], dtype='float32')
+   df1 = pd.DataFrame(np.random.randn(8, 1), columns=['A'], dtype='float64')
    df1
    df1.dtypes
-   df2 = pd.DataFrame({'A': pd.Series(np.random.randn(8), dtype='float16'),
+   df2 = pd.DataFrame({'A': pd.Series(np.random.randn(8), dtype='float32'),
                        'B': pd.Series(np.random.randn(8)),
                        'C': pd.Series(range(8), dtype='uint8')})
    df2

doc/source/whatsnew/v2.3.0.rst

@@ -119,6 +119,7 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`.DataFrameGroupBy.min`, :meth:`.DataFrameGroupBy.max`, :meth:`.Resampler.min`, :meth:`.Resampler.max` on string input of all NA values would return float dtype; now returns string (:issue:`60810`)
 - Bug in :meth:`DataFrame.sum` with ``axis=1``, :meth:`.DataFrameGroupBy.sum` or :meth:`.SeriesGroupBy.sum` with ``skipna=True``, and :meth:`.Resampler.sum` on :class:`StringDtype` with all NA values resulted in ``0`` and is now the empty string ``""`` (:issue:`60229`)
 - Bug in :meth:`Series.__pos__` and :meth:`DataFrame.__pos__` did not raise for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`60710`)
 - Bug in :meth:`Series.rank` for :class:`StringDtype` with ``storage="pyarrow"`` incorrectly returning integer results in case of ``method="average"`` and raising an error if it would truncate results (:issue:`59768`)