Merge branch 'main' into categorical

Author: jahn96

README.md

@@ -96,7 +96,7 @@ The source code is currently hosted on GitHub at:
 https://github.com/pandas-dev/pandas
 
 Binary installers for the latest released version are available at the [Python
-Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://docs.conda.io/en/latest/).
+Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://anaconda.org/conda-forge/pandas).
 
 ```sh
 # conda

ci/code_checks.sh

@@ -306,7 +306,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_sparse SA01" \
         -i "pandas.api.types.is_timedelta64_ns_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
-        -i "pandas.api.types.union_categoricals RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.BooleanArray SA01" \
         -i "pandas.arrays.DatetimeArray SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -584,6 +584,7 @@ I/O
 - Bug in :meth:`read_json` not validating the ``typ`` argument to not be exactly ``"frame"`` or ``"series"`` (:issue:`59124`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
 - Bug in :meth:`read_stata` where extreme value integers were incorrectly interpreted as missing for format versions 111 and prior (:issue:`58130`)
+- Bug in :meth:`read_stata` where the missing code for double was not recognised for format versions 105 and prior (:issue:`58149`)
 
 Period
 ^^^^^^

pandas/_config/__init__.py

@@ -30,6 +30,6 @@
 from pandas._config.display import detect_console_encoding
 
 
-def using_pyarrow_string_dtype() -> bool:
+def using_string_dtype() -> bool:
     _mode_options = _global_config["future"]
     return _mode_options["infer_string"]

pandas/_libs/lib.pyx

@@ -37,7 +37,7 @@ from cython cimport (
     floating,
 )
 
-from pandas._config import using_pyarrow_string_dtype
+from pandas._config import using_string_dtype
 
 from pandas._libs.missing import check_na_tuples_nonequal
 
@@ -2699,7 +2699,7 @@ def maybe_convert_objects(ndarray[object] objects,
         seen.object_ = True
 
     elif seen.str_:
-        if using_pyarrow_string_dtype() and is_string_array(objects, skipna=True):
+        if using_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
             dtype = StringDtype(storage="pyarrow_numpy")

pandas/core/construction.py

@@ -16,7 +16,7 @@
 import numpy as np
 from numpy import ma
 
-from pandas._config import using_pyarrow_string_dtype
+from pandas._config import using_string_dtype
 
 from pandas._libs import lib
 from pandas._libs.tslibs import (
@@ -571,11 +571,7 @@ def sanitize_array(
     if not is_list_like(data):
         if index is None:
             raise ValueError("index must be specified when data is not list-like")
-        if (
-            isinstance(data, str)
-            and using_pyarrow_string_dtype()
-            and original_dtype is None
-        ):
+        if isinstance(data, str) and using_string_dtype() and original_dtype is None:
             from pandas.core.arrays.string_ import StringDtype
 
             dtype = StringDtype("pyarrow_numpy")
@@ -609,7 +605,7 @@ def sanitize_array(
             subarr = data
             if data.dtype == object and infer_object:
                 subarr = maybe_infer_to_datetimelike(data)
-            elif data.dtype.kind == "U" and using_pyarrow_string_dtype():
+            elif data.dtype.kind == "U" and using_string_dtype():
                 from pandas.core.arrays.string_ import StringDtype
 
                 dtype = StringDtype(storage="pyarrow_numpy")

pandas/core/dtypes/cast.py

@@ -18,7 +18,7 @@
 
 import numpy as np
 
-from pandas._config import using_pyarrow_string_dtype
+from pandas._config import using_string_dtype
 
 from pandas._libs import (
     Interval,
@@ -798,7 +798,7 @@ def infer_dtype_from_scalar(val) -> tuple[DtypeObj, Any]:
         # coming out as np.str_!
 
         dtype = _dtype_obj
-        if using_pyarrow_string_dtype():
+        if using_string_dtype():
             from pandas.core.arrays.string_ import StringDtype
 
             dtype = StringDtype(storage="pyarrow_numpy")

pandas/core/dtypes/concat.py

@@ -190,6 +190,7 @@ def union_categoricals(
     Returns
     -------
     Categorical
+        The union of categories being combined.
 
     Raises
     ------
@@ -201,6 +202,11 @@ def union_categoricals(
     ValueError
         Empty list of categoricals passed
 
+    See Also
+    --------
+    CategoricalDtype : Type for categorical data with the categories and orderedness.
+    Categorical : Represent a categorical variable in classic R / S-plus fashion.
+
     Notes
     -----
     To learn more about categories, see `link

pandas/core/frame.py

@@ -901,6 +901,14 @@ def __dataframe__(
         """
         Return the dataframe interchange object implementing the interchange protocol.
 
+        .. warning::
+
+            Due to severe implementation issues, we recommend only considering using the
+            interchange protocol in the following cases:
+
+            - converting to pandas: for pandas >= 2.0.3
+            - converting from pandas: for pandas >= 3.0.0
+
         Parameters
         ----------
         nan_as_null : bool, default False

pandas/core/interchange/from_dataframe.py

@@ -36,6 +36,14 @@ def from_dataframe(df, allow_copy: bool = True) -> pd.DataFrame:
     """
     Build a ``pd.DataFrame`` from any DataFrame supporting the interchange protocol.
 
+    .. warning::
+
+        Due to severe implementation issues, we recommend only considering using the
+        interchange protocol in the following cases:
+
+        - converting to pandas: for pandas >= 2.0.3
+        - converting from pandas: for pandas >= 3.0.0
+
     Parameters
     ----------
     df : DataFrameXchg