Merge remote-tracking branch 'upstream/main' into string-dtype-object

Author: jorisvandenbossche

.github/workflows/unit-tests.yml

@@ -57,6 +57,9 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
+          - name: "Future infer strings"
+            env_file: actions-311.yaml
+            pandas_future_infer_string: "1"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -75,6 +78,7 @@ 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' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}

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

@@ -223,7 +223,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.fromordinal SA01" \
         -i "pandas.Timestamp.fromtimestamp PR01,SA01" \
         -i "pandas.Timestamp.hour GL08" \
-        -i "pandas.Timestamp.isoweekday SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.microsecond GL08" \
         -i "pandas.Timestamp.min PR02" \
@@ -306,7 +305,6 @@ 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" \
@@ -329,7 +327,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.max SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.median SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.min SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
@@ -348,7 +345,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.max SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.median SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.min SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
@@ -363,7 +359,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.indices SA01" \
         -i "pandas.core.resample.Resampler.max PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.mean SA01" \
-        -i "pandas.core.resample.Resampler.median SA01" \
         -i "pandas.core.resample.Resampler.min PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.ohlc SA01" \
         -i "pandas.core.resample.Resampler.prod 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
 
@@ -2699,10 +2699,10 @@ 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()
+            dtype = StringDtype(na_value=np.nan)
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
         elif convert_to_nullable_dtype and is_string_array(objects, skipna=True):

pandas/_libs/tslibs/nattype.pyx

@@ -441,6 +441,13 @@ class NaTType(_NaT):
 
         Monday == 1 ... Sunday == 7.
 
+        See Also
+        --------
+        Timestamp.weekday : Return the day of the week with Monday=0, Sunday=6.
+        Timestamp.isocalendar : Return a tuple containing ISO year, week number
+            and weekday.
+        datetime.date.isoweekday : Equivalent method in datetime module.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00')

pandas/_libs/tslibs/timestamps.pyx

@@ -2775,6 +2775,13 @@ default 'raise'
 
         Monday == 1 ... Sunday == 7.
 
+        See Also
+        --------
+        Timestamp.weekday : Return the day of the week with Monday=0, Sunday=6.
+        Timestamp.isocalendar : Return a tuple containing ISO year, week number
+            and weekday.
+        datetime.date.isoweekday : Equivalent method in datetime module.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00')

pandas/_testing/__init__.py

@@ -509,14 +509,14 @@ def shares_memory(left, right) -> bool:
     if (
         isinstance(left, ExtensionArray)
         and is_string_dtype(left.dtype)
-        and left.dtype.storage in ("pyarrow", "pyarrow_numpy")  # type: ignore[attr-defined]
+        and left.dtype.storage == "pyarrow"  # type: ignore[attr-defined]
     ):
         # https://github.com/pandas-dev/pandas/pull/43930#discussion_r736862669
         left = cast("ArrowExtensionArray", left)
         if (
             isinstance(right, ExtensionArray)
             and is_string_dtype(right.dtype)
-            and right.dtype.storage in ("pyarrow", "pyarrow_numpy")  # type: ignore[attr-defined]
+            and right.dtype.storage == "pyarrow"  # type: ignore[attr-defined]
         ):
             right = cast("ArrowExtensionArray", right)
             left_pa_data = left._pa_array

pandas/core/arrays/arrow/array.py

@@ -575,10 +575,8 @@ def __getitem__(self, item: PositionalIndexer):
         if isinstance(item, np.ndarray):
             if not len(item):
                 # Removable once we migrate StringDtype[pyarrow] to ArrowDtype[string]
-                if self._dtype.name == "string" and self._dtype.storage in (
-                    "pyarrow",
-                    "pyarrow_numpy",
-                ):
+                if self._dtype.name == "string" and self._dtype.storage == "pyarrow":
+                    # TODO(infer_string) should this be large_string?
                     pa_dtype = pa.string()
                 else:
                     pa_dtype = self._dtype.pyarrow_dtype