Merge branch 'main' into deps/pytz/optional

Author: mroeschke

.circleci/config.yml

@@ -15,15 +15,15 @@ jobs:
       - checkout
       - run:
           name: Install Environment and Run Tests
-          shell: /bin/bash -exuo pipefail
+          shell: /bin/bash -exo pipefail
           command: |
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
-            wget -q $MAMBA_URL -O minimamba.sh
-            chmod +x minimamba.sh
-            MAMBA_DIR="$HOME/miniconda3"
-            rm -rf $MAMBA_DIR
-            ./minimamba.sh -b -p $MAMBA_DIR
-            export PATH=$MAMBA_DIR/bin:$PATH
+            MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MINI_URL -O Miniforge3.sh
+            chmod +x Miniforge3.sh
+            MINI_DIR="$HOME/miniconda3"
+            rm -rf $MINI_DIR
+            ./Miniforge3.sh -b -p $MINI_DIR
+            export PATH=$MINI_DIR/bin:$PATH
             conda info -a
             conda env create -q -n pandas-dev -f $ENV_FILE
             conda list -n pandas-dev
@@ -97,21 +97,16 @@ jobs:
 
       - run:
           name: Install Anaconda Client & Upload Wheels
+          shell: /bin/bash -exo pipefail
           command: |
-            echo "Install Mambaforge"
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
-            echo "Downloading $MAMBA_URL"
-            wget -q $MAMBA_URL -O minimamba.sh
-            chmod +x minimamba.sh
-
-            MAMBA_DIR="$HOME/miniconda3"
-            rm -rf $MAMBA_DIR
-            ./minimamba.sh -b -p $MAMBA_DIR
-
-            export PATH=$MAMBA_DIR/bin:$PATH
-
-            mamba install -y -c conda-forge anaconda-client
-
+            MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MINI_URL -O Miniforge3.sh
+            chmod +x Miniforge3.sh
+            MINI_DIR="$HOME/miniconda3"
+            rm -rf $MINI_DIR
+            ./Miniforge3.sh -b -p $MINI_DIR
+            export PATH=$MINI_DIR/bin:$PATH
+            conda install -y -c conda-forge anaconda-client
             source ci/upload_wheels.sh
             set_upload_vars
             upload_wheels

.github/workflows/unit-tests.yml

@@ -59,7 +59,6 @@ jobs:
             extra_loc: "zh_CN"
           - name: "Future infer strings"
             env_file: actions-311.yaml
-            pattern: "not slow and not network and not single_cpu"
             pandas_future_infer_string: "1"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml

ci/code_checks.sh

@@ -70,16 +70,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.MultiIndex.append PR07,SA01" \
-        -i "pandas.MultiIndex.copy PR07,RT03,SA01" \
         -i "pandas.MultiIndex.get_level_values SA01" \
-        -i "pandas.MultiIndex.get_loc PR07" \
         -i "pandas.MultiIndex.get_loc_level PR07" \
-        -i "pandas.MultiIndex.levshape SA01" \
         -i "pandas.MultiIndex.names SA01" \
-        -i "pandas.MultiIndex.remove_unused_levels RT03,SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
-        -i "pandas.MultiIndex.set_levels RT03,SA01" \
         -i "pandas.MultiIndex.sortlevel PR07,SA01" \
         -i "pandas.MultiIndex.to_frame RT03" \
         -i "pandas.NA SA01" \
@@ -223,7 +217,6 @@ 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" \
@@ -328,7 +321,6 @@ 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" \
@@ -347,7 +339,6 @@ 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" \
@@ -362,7 +353,6 @@ 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" \

ci/run_tests.sh

@@ -16,11 +16,5 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
-# temporarily let pytest always succeed (many tests are not yet passing in the
-# build enabling the future string dtype)
-if [[ "$PANDAS_FUTURE_INFER_STRING" == "1" ]]; then
-  PYTEST_CMD="$PYTEST_CMD || true"
-fi
-
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"

doc/source/user_guide/style.ipynb

@@ -351,7 +351,7 @@
     "\n",
     "- Using [.set_table_styles()][table] to control broader areas of the table with specified internal CSS. Although table styles allow the flexibility to add CSS selectors and properties controlling all individual parts of the table, they are unwieldy for individual cell specifications. Also, note that table styles cannot be exported to Excel. \n",
     "- Using [.set_td_classes()][td_class] to directly link either external CSS classes to your data cells or link the internal CSS classes created by [.set_table_styles()][table]. See [here](#Setting-Classes-and-Linking-to-External-CSS). These cannot be used on column header rows or indexes, and also won't export to Excel. \n",
-    "- Using the [.apply()][apply] and [.map()][map] functions to add direct internal CSS to specific data cells. See [here](#Styler-Functions). As of v1.4.0 there are also methods that work directly on column header rows or indexes; [.apply_index()][applyindex] and [.map_index()][mapindex]. Note that only these methods add styles that will export to Excel. These methods work in a similar way to [DataFrame.apply()][dfapply] and [DataFrame.map()][dfmap].\n",
+    "- Using the [.apply()][apply] and [.map()][map] functions to add direct internal CSS to specific data cells. See [here](#Styler-Functions). As of v1.4.0 there are also methods that work directly on column header rows or indexes: [.apply_index()][applyindex] and [.map_index()][mapindex]. Note that only these methods add styles that will export to Excel. These methods work in a similar way to [DataFrame.apply()][dfapply] and [DataFrame.map()][dfmap].\n",
     "\n",
     "[table]: ../reference/api/pandas.io.formats.style.Styler.set_table_styles.rst\n",
     "[styler]: ../reference/api/pandas.io.formats.style.Styler.rst\n",

doc/source/whatsnew/v3.0.0.rst

@@ -35,6 +35,7 @@ Other enhancements
 - :meth:`DataFrame.agg` called with ``axis=1`` and a ``func`` which relabels the result index now raises a ``NotImplementedError`` (:issue:`58807`).
 - :meth:`Index.get_loc` now accepts also subclasses of ``tuple`` as keys (:issue:`57922`)
 - :meth:`Styler.set_tooltips` provides alternative method to storing tooltips by using title attribute of td elements. (:issue:`56981`)
+- Added missing parameter ``weights`` in :meth:`DataFrame.plot.kde` for the estimation of the PDF (:issue:`59337`)
 - Allow dictionaries to be passed to :meth:`pandas.Series.str.replace` via ``pat`` parameter (:issue:`51748`)
 - Support passing a :class:`Series` input to :func:`json_normalize` that retains the :class:`Series` :class:`Index` (:issue:`51452`)
 - Support reading value labels from Stata 108-format (Stata 6) and earlier files (:issue:`58154`)
@@ -617,10 +618,11 @@ 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
 ^^^^^^
--
+- Fixed error message when passing invalid period alias to :meth:`PeriodIndex.to_timestamp` (:issue:`58974`)
 -
 
 Plotting

pandas/_libs/lib.pyx

@@ -2702,7 +2702,7 @@ def maybe_convert_objects(ndarray[object] objects,
         if using_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(storage="pyarrow_numpy")
+            dtype = StringDtype(storage="pyarrow", 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/offsets.pyx

@@ -4752,20 +4752,16 @@ def _validate_to_offset_alias(alias: str, is_period: bool) -> None:
                 alias.lower() not in {"s", "ms", "us", "ns"} and
                 alias.upper().split("-")[0].endswith(("S", "E"))):
             raise ValueError(INVALID_FREQ_ERR_MSG.format(alias))
-    if (is_period and
-            alias.upper() in c_OFFSET_TO_PERIOD_FREQSTR and
-            alias != "ms" and
-            alias.upper().split("-")[0].endswith(("S", "E"))):
-        if (alias.upper().startswith("B") or
-                alias.upper().startswith("S") or
-                alias.upper().startswith("C")):
-            raise ValueError(INVALID_FREQ_ERR_MSG.format(alias))
-        else:
-            alias_msg = "".join(alias.upper().split("E", 1))
-            raise ValueError(
-                f"for Period, please use \'{alias_msg}\' "
-                f"instead of \'{alias}\'"
-            )
+    if (
+        is_period and
+        alias in c_OFFSET_TO_PERIOD_FREQSTR and
+        alias != c_OFFSET_TO_PERIOD_FREQSTR[alias]
+    ):
+        alias_msg = c_OFFSET_TO_PERIOD_FREQSTR.get(alias)
+        raise ValueError(
+            f"for Period, please use \'{alias_msg}\' "
+            f"instead of \'{alias}\'"
+        )
 
 
 # TODO: better name?

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')