Merge branch 'main' into hotfix/cmp0xff/62063-def-of-scalar

Author: cmp0xff

doc/source/user_guide/migration-3-strings.rst

@@ -315,6 +315,37 @@ the :meth:`~pandas.Series.str.decode` method now has a ``dtype`` parameter to be
 able to specify object dtype instead of the default of string dtype for this use
 case.
 
+:meth:`Series.values` now returns an :class:`~pandas.api.extensions.ExtensionArray`
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+With object dtype, using ``.values`` on a Series will return the underlying NumPy array.
+
+.. code-block:: python
+
+   >>> ser = pd.Series(["a", "b", np.nan], dtype="object")
+   >>> type(ser.values)
+   <class 'numpy.ndarray'>
+
+However with the new string dtype, the underlying ExtensionArray is returned instead.
+
+.. code-block:: python
+
+   >>> ser = pd.Series(["a", "b", pd.NA], dtype="str")
+   >>> ser.values
+   <ArrowStringArray>
+   ['a', 'b', nan]
+   Length: 3, dtype: str
+
+If your code requires a NumPy array, you should use :meth:`Series.to_numpy`.
+
+.. code-block:: python
+
+   >>> ser = pd.Series(["a", "b", pd.NA], dtype="str")
+   >>> ser.to_numpy()
+   ['a' 'b' nan]
+
+In general, you should always prefer :meth:`Series.to_numpy` to get a NumPy array or :meth:`Series.array` to get an ExtensionArray over using :meth:`Series.values`.
+
 Notable bug fixes
 ~~~~~~~~~~~~~~~~~
 

pandas/tests/groupby/test_libgroupby.py

@@ -285,7 +285,7 @@ def test_cython_group_mean_not_datetimelike_but_has_NaT_values():
     )
 
 
-def test_cython_group_mean_Inf_at_begining_and_end():
+def test_cython_group_mean_Inf_at_beginning_and_end():
     # GH 50367
     actual = np.array([[np.nan, np.nan], [np.nan, np.nan]], dtype="float64")
     counts = np.array([0, 0], dtype="int64")
@@ -314,7 +314,7 @@ def test_cython_group_mean_Inf_at_begining_and_end():
         ([[np.inf], [-np.inf], [-np.inf]], [[np.inf], [-np.inf]]),
     ],
 )
-def test_cython_group_sum_Inf_at_begining_and_end(values, out):
+def test_cython_group_sum_Inf_at_beginning_and_end(values, out):
     # GH #53606
     actual = np.array([[np.nan], [np.nan]], dtype="float64")
     counts = np.array([0, 0], dtype="int64")

pandas/tests/reshape/test_from_dummies.py

@@ -100,7 +100,7 @@ def test_error_contains_non_dummies():
         from_dummies(dummies)
 
 
-def test_error_with_prefix_multiple_seperators():
+def test_error_with_prefix_multiple_separators():
     dummies = DataFrame(
         {
             "col1_a": [1, 0, 1],

scripts/tests/test_validate_min_versions_in_sync.py

@@ -10,34 +10,36 @@
     pin_min_versions_to_yaml_file,
 )
 
+DATA_PATH = pathlib.Path(__file__).parents[2] / "scripts/tests/data/"
+
 
 @pytest.mark.parametrize(
     "src_toml, src_yaml, expected_yaml",
     [
         (
-            pathlib.Path("scripts/tests/data/deps_minimum.toml"),
-            pathlib.Path("scripts/tests/data/deps_unmodified_random.yaml"),
-            pathlib.Path("scripts/tests/data/deps_expected_random.yaml"),
+            DATA_PATH / "deps_minimum.toml",
+            DATA_PATH / "deps_unmodified_random.yaml",
+            DATA_PATH / "deps_expected_random.yaml",
         ),
         (
-            pathlib.Path("scripts/tests/data/deps_minimum.toml"),
-            pathlib.Path("scripts/tests/data/deps_unmodified_same_version.yaml"),
-            pathlib.Path("scripts/tests/data/deps_expected_same_version.yaml"),
+            DATA_PATH / "deps_minimum.toml",
+            DATA_PATH / "deps_unmodified_same_version.yaml",
+            DATA_PATH / "deps_expected_same_version.yaml",
         ),
         (
-            pathlib.Path("scripts/tests/data/deps_minimum.toml"),
-            pathlib.Path("scripts/tests/data/deps_unmodified_duplicate_package.yaml"),
-            pathlib.Path("scripts/tests/data/deps_expected_duplicate_package.yaml"),
+            DATA_PATH / "deps_minimum.toml",
+            DATA_PATH / "deps_unmodified_duplicate_package.yaml",
+            DATA_PATH / "deps_expected_duplicate_package.yaml",
         ),
         (
-            pathlib.Path("scripts/tests/data/deps_minimum.toml"),
-            pathlib.Path("scripts/tests/data/deps_unmodified_no_version.yaml"),
-            pathlib.Path("scripts/tests/data/deps_expected_no_version.yaml"),
+            DATA_PATH / "deps_minimum.toml",
+            DATA_PATH / "deps_unmodified_no_version.yaml",
+            DATA_PATH / "deps_expected_no_version.yaml",
         ),
         (
-            pathlib.Path("scripts/tests/data/deps_minimum.toml"),
-            pathlib.Path("scripts/tests/data/deps_unmodified_range.yaml"),
-            pathlib.Path("scripts/tests/data/deps_expected_range.yaml"),
+            DATA_PATH / "deps_minimum.toml",
+            DATA_PATH / "deps_unmodified_range.yaml",
+            DATA_PATH / "deps_expected_range.yaml",
         ),
     ],
 )

scripts/tests/test_validate_unwanted_patterns.py

@@ -10,7 +10,7 @@ class TestStringsWithWrongPlacedWhitespace:
         "data",
         [
             (
-                """
+                r"""
     msg = (
         "foo\n"
         " bar"

scripts/validate_min_versions_in_sync.py

@@ -23,19 +23,20 @@
 
 from scripts.generate_pip_deps_from_conda import CONDA_TO_PIP
 
-DOC_PATH = pathlib.Path("doc/source/getting_started/install.rst").resolve()
+BASE_PATH = pathlib.Path(__file__).parents[1]
+DOC_PATH = (BASE_PATH / "doc/source/getting_started/install.rst").resolve()
 CI_PATH = next(
-    pathlib.Path("ci/deps").absolute().glob("actions-*-minimum_versions.yaml")
+    (BASE_PATH / "ci/deps").absolute().glob("actions-*-minimum_versions.yaml")
 )
-CODE_PATH = pathlib.Path("pandas/compat/_optional.py").resolve()
-SETUP_PATH = pathlib.Path("pyproject.toml").resolve()
-YAML_PATH = pathlib.Path("ci/deps")
-ENV_PATH = pathlib.Path("environment.yml")
+CODE_PATH = (BASE_PATH / "pandas/compat/_optional.py").resolve()
+SETUP_PATH = (BASE_PATH / "pyproject.toml").resolve()
+YAML_PATH = BASE_PATH / "ci/deps"
+ENV_PATH = BASE_PATH / "environment.yml"
 EXCLUDE_DEPS = {"tzdata", "pyqt", "pyqt5"}
 # pandas package is not available
 # in pre-commit environment
-sys.path.append("pandas/compat")
-sys.path.append("pandas/util")
+sys.path.append(str(BASE_PATH / "pandas/compat"))
+sys.path.append(str(BASE_PATH / "pandas/util"))
 import _exceptions
 import version