Merge branch 'main' into groupby_describe_empty_dataset

Author: Khor Chean Wei

.github/workflows/code-checks.yml

@@ -80,6 +80,10 @@ jobs:
       id: build
       uses: ./.github/actions/build_pandas
 
+    - name: Check for no warnings when building single-page docs
+      run: ci/code_checks.sh single-docs
+      if: ${{ steps.build.outcome == 'success' }}
+
     - name: Run checks on imported code
       run: ci/code_checks.sh code
       if: ${{ steps.build.outcome == 'success' }}

.github/workflows/docbuild-and-upload.yml

@@ -37,6 +37,7 @@ jobs:
       run: |
         source activate pandas-dev
         python web/pandas_web.py web/pandas --target-path=web/build
+
     - name: Build documentation
       run: |
         source activate pandas-dev

.pre-commit-config.yaml

@@ -26,7 +26,7 @@ repos:
         types_or: [python, rst, markdown]
         files: ^(pandas|doc)/
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.1.0
+    rev: v4.2.0
     hooks:
     -   id: debug-statements
     -   id: end-of-file-fixer
@@ -56,7 +56,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.31.1
+    rev: v2.32.0
     hooks:
     -   id: pyupgrade
         args: [--py38-plus]
@@ -71,7 +71,7 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v0.2
+    rev: v0.4.1
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/asottile/yesqa

ci/code_checks.sh

@@ -12,8 +12,9 @@
 #   $ ./ci/code_checks.sh doctests      # run doctests
 #   $ ./ci/code_checks.sh docstrings    # validate docstring errors
 #   $ ./ci/code_checks.sh typing        # run static type analysis
+#   $ ./ci/code_checks.sh single-docs   # check single-page docs build warning-free
 
-[[ -z "$1" || "$1" == "code" || "$1" == "doctests" || "$1" == "docstrings" || "$1" == "typing" ]] || \
+[[ -z "$1" || "$1" == "code" || "$1" == "doctests" || "$1" == "docstrings" || "$1" == "typing" || "$1" == "single-docs" ]] || \
     { echo "Unknown command $1. Usage: $0 [code|doctests|docstrings|typing]"; exit 9999; }
 
 BASE_DIR="$(dirname $0)/.."
@@ -102,4 +103,11 @@ if [[ -z "$CHECK" || "$CHECK" == "typing" ]]; then
     fi
 fi
 
+### SINGLE-PAGE DOCS ###
+if [[ -z "$CHECK" || "$CHECK" == "single-docs" ]]; then
+    python doc/make.py --warnings-are-errors --single pandas.Series.value_counts
+    python doc/make.py --warnings-are-errors --single pandas.Series.str.split
+    python doc/make.py clean
+fi
+
 exit $RET

doc/source/index.rst.template

@@ -26,6 +26,7 @@ pandas documentation
 easy-to-use data structures and data analysis tools for the `Python <https://www.python.org/>`__
 programming language.
 
+{% if not single_doc -%}
 .. panels::
     :card: + intro-card text-center
     :column: col-lg-6 col-md-6 col-sm-6 col-xs-12 d-flex
@@ -96,16 +97,22 @@ programming language.
             :text: To the development guide
             :classes: btn-block btn-secondary stretched-link
 
-
+{% endif %}
 {% if single_doc and single_doc.endswith('.rst') -%}
 .. toctree::
     :maxdepth: 3
     :titlesonly:
 
     {{ single_doc[:-4] }}
+{% elif single_doc and single_doc.count('.') <= 1 %}
+.. autosummary::
+    :toctree: reference/api/
+
+    {{ single_doc }}
 {% elif single_doc %}
 .. autosummary::
     :toctree: reference/api/
+    :template: autosummary/accessor_method.rst
 
     {{ single_doc }}
 {% else -%}

doc/source/whatsnew/v1.5.0.rst

@@ -37,10 +37,17 @@ The protocol consists of two parts:
 Styler
 ^^^^^^
 
-  - New method :meth:`.Styler.to_string` for alternative customisable output methods (:issue:`44502`)
-  - Added the ability to render ``border`` and ``border-{side}`` CSS properties in Excel (:issue:`42276`)
-  - Added a new method :meth:`.Styler.concat` which allows adding customised footer rows to visualise additional calculations on the data, e.g. totals and counts etc. (:issue:`43875`, :issue:`46186`)
-  - :meth:`.Styler.highlight_null` now accepts ``color`` consistently with other builtin methods and deprecates ``null_color`` although this remains backwards compatible (:issue:`45907`)
+The most notable development is the new method :meth:`.Styler.concat` which
+allows adding customised footer rows to visualise additional calculations on the data,
+e.g. totals and counts etc. (:issue:`43875`, :issue:`46186`)
+
+Additionally there is an alternative output method :meth:`.Styler.to_string`,
+which allows using the Styler's formatting methods to create, for example, CSVs (:issue:`44502`).
+
+Minor feature improvements are:
+
+  - Adding the ability to render ``border`` and ``border-{side}`` CSS properties in Excel (:issue:`42276`)
+  - Making keyword arguments consist: :meth:`.Styler.highlight_null` now accepts ``color`` and deprecates ``null_color`` although this remains backwards compatible (:issue:`45907`)
 
 .. _whatsnew_150.enhancements.resample_group_keys:
 
@@ -113,7 +120,7 @@ Other enhancements
 - :meth:`DataFrame.reset_index` now accepts a ``names`` argument which renames the index names (:issue:`6878`)
 - :meth:`pd.concat` now raises when ``levels`` is given but ``keys`` is None (:issue:`46653`)
 - :meth:`pd.concat` now raises when ``levels`` contains duplicate values (:issue:`46653`)
-- Added ``numeric_only`` argument to :meth:`DataFrame.corr`, :meth:`DataFrame.corrwith`, and :meth:`DataFrame.cov` (:issue:`46560`)
+- Added ``numeric_only`` argument to :meth:`DataFrame.corr`, :meth:`DataFrame.corrwith`, :meth:`DataFrame.cov`, :meth:`DataFrame.idxmin`, :meth:`DataFrame.idxmax`, :meth:`.GroupBy.idxmin`, :meth:`.GroupBy.idxmax`, :meth:`.GroupBy.var`, :meth:`.GroupBy.std`, :meth:`.GroupBy.sem`, and :meth:`.GroupBy.quantile` (:issue:`46560`)
 - A :class:`errors.PerformanceWarning` is now thrown when using ``string[pyarrow]`` dtype with methods that don't dispatch to ``pyarrow.compute`` methods (:issue:`42613`, :issue:`46725`)
 - Added ``validate`` argument to :meth:`DataFrame.join` (:issue:`46622`)
 - A :class:`errors.PerformanceWarning` is now thrown when using ``string[pyarrow]`` dtype with methods that don't dispatch to ``pyarrow.compute`` methods (:issue:`42613`)
@@ -127,13 +134,6 @@ Notable bug fixes
 
 These are bug fixes that might have notable behavior changes.
 
-.. _whatsnew_150.notable_bug_fixes.notable_bug_fix1:
-
-Styler
-^^^^^^
-
-- Fixed bug in :class:`CSSToExcelConverter` leading to ``TypeError`` when border color provided without border style for ``xlsxwriter`` engine (:issue:`42276`)
-
 .. _whatsnew_150.notable_bug_fixes.groupby_transform_dropna:
 
 Using ``dropna=True`` with ``groupby`` transforms
@@ -194,13 +194,6 @@ did not have the same index as the input.
     df.groupby('a', dropna=True).transform('ffill')
     df.groupby('a', dropna=True).transform(lambda x: x)
 
-.. _whatsnew_150.notable_bug_fixes.visualization:
-
-Styler
-^^^^^^
-
-- Fix showing "None" as ylabel in :meth:`Series.plot` when not setting ylabel (:issue:`46129`)
-
 .. _whatsnew_150.notable_bug_fixes.notable_bug_fix2:
 
 notable_bug_fix2
@@ -615,6 +608,7 @@ Plotting
 - Bug in :meth:`DataFrame.boxplot` that prevented specifying ``vert=False`` (:issue:`36918`)
 - Bug in :meth:`DataFrame.plot.scatter` that prevented specifying ``norm`` (:issue:`45809`)
 - The function :meth:`DataFrame.plot.scatter` now accepts ``color`` as an alias for ``c`` and ``size`` as an alias for ``s`` for consistency to other plotting functions (:issue:`44670`)
+- Fix showing "None" as ylabel in :meth:`Series.plot` when not setting ylabel (:issue:`46129`)
 
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
@@ -660,7 +654,7 @@ ExtensionArray
 Styler
 ^^^^^^
 - Bug when attempting to apply styling functions to an empty DataFrame subset (:issue:`45313`)
--
+- Bug in :class:`CSSToExcelConverter` leading to ``TypeError`` when border color provided without border style for ``xlsxwriter`` engine (:issue:`42276`)
 
 Metadata
 ^^^^^^^^

pandas/_libs/tslibs/conversion.pyx

@@ -52,12 +52,8 @@ from pandas._libs.tslibs.np_datetime import (
 )
 
 from pandas._libs.tslibs.timezones cimport (
-    get_dst_info,
     get_utcoffset,
-    is_fixed_offset,
-    is_tzlocal,
     is_utc,
-    is_zoneinfo,
     maybe_get_tz,
     tz_compare,
     utc_pytz as UTC,
@@ -77,10 +73,7 @@ from pandas._libs.tslibs.nattype cimport (
     checknull_with_nat,
 )
 from pandas._libs.tslibs.tzconversion cimport (
-    bisect_right_i8,
-    infer_dateutil_fold,
-    localize_tzinfo_api,
-    tz_convert_from_utc_single,
+    Localizer,
     tz_localize_to_utc_single,
 )
 
@@ -518,9 +511,7 @@ cdef _TSObject _create_tsobject_tz_using_offset(npy_datetimestruct dts,
         _TSObject obj = _TSObject()
         int64_t value  # numpy dt64
         datetime dt
-        ndarray[int64_t] trans
-        int64_t* tdata
-        int64_t[::1] deltas
+        Py_ssize_t pos
 
     value = dtstruct_to_dt64(&dts)
     obj.dts = dts
@@ -530,19 +521,18 @@ cdef _TSObject _create_tsobject_tz_using_offset(npy_datetimestruct dts,
         check_overflows(obj)
         return obj
 
+    cdef:
+        Localizer info = Localizer(tz)
+
     # Infer fold from offset-adjusted obj.value
     # see PEP 495 https://www.python.org/dev/peps/pep-0495/#the-fold-attribute
-    if is_utc(tz):
+    if info.use_utc:
         pass
-    elif is_tzlocal(tz) or is_zoneinfo(tz):
-        localize_tzinfo_api(obj.value, tz, &obj.fold)
-    else:
-        trans, deltas, typ = get_dst_info(tz)
-
-        if typ == 'dateutil':
-            tdata = <int64_t*>cnp.PyArray_DATA(trans)
-            pos = bisect_right_i8(tdata, obj.value, trans.shape[0]) - 1
-            obj.fold = infer_dateutil_fold(obj.value, trans, deltas, pos)
+    elif info.use_tzlocal:
+        info.utc_val_to_local_val(obj.value, &pos, &obj.fold)
+    elif info.use_dst and not info.use_pytz:
+        # i.e. dateutil
+        info.utc_val_to_local_val(obj.value, &pos, &obj.fold)
 
     # Keep the converter same as PyDateTime's
     dt = datetime(obj.dts.year, obj.dts.month, obj.dts.day,
@@ -700,18 +690,19 @@ cdef inline void _localize_tso(_TSObject obj, tzinfo tz):
     cdef:
         int64_t local_val
         Py_ssize_t outpos = -1
+        Localizer info = Localizer(tz)
 
     assert obj.tzinfo is None
 
-    if is_utc(tz):
+    if info.use_utc:
         pass
     elif obj.value == NPY_NAT:
         pass
     else:
-        local_val = tz_convert_from_utc_single(obj.value, tz, &obj.fold, &outpos)
+        local_val = info.utc_val_to_local_val(obj.value, &outpos, &obj.fold)
 
-        if outpos != -1:
-            # infer we went through a pytz path
+        if info.use_pytz:
+            # infer we went through a pytz path, will have outpos!=-1
             tz = tz._tzinfos[tz._transition_info[outpos]]
 
         dt64_to_dtstruct(local_val, &obj.dts)

pandas/_libs/tslibs/timestamps.pyi

@@ -199,10 +199,14 @@ class Timestamp(datetime):
     @property
     def day_of_week(self) -> int: ...
     @property
+    def dayofweek(self) -> int: ...
+    @property
     def day_of_month(self) -> int: ...
     @property
     def day_of_year(self) -> int: ...
     @property
+    def dayofyear(self) -> int: ...
+    @property
     def quarter(self) -> int: ...
     @property
     def week(self) -> int: ...
@@ -211,3 +215,7 @@ class Timestamp(datetime):
     ) -> np.datetime64: ...
     @property
     def _date_repr(self) -> str: ...
+    @property
+    def days_in_month(self) -> int: ...
+    @property
+    def daysinmonth(self) -> int: ...

pandas/_libs/tslibs/tzconversion.pxd

@@ -2,6 +2,7 @@ from cpython.datetime cimport tzinfo
 from numpy cimport (
     int64_t,
     intp_t,
+    ndarray,
 )
 
 
@@ -21,5 +22,23 @@ cdef bint infer_dateutil_fold(
     int64_t value,
     const int64_t[::1] trans,
     const int64_t[::1] deltas,
-    intp_t pos,
+    Py_ssize_t pos,
 )
+
+
+cdef class Localizer:
+    cdef:
+        tzinfo tz
+        bint use_utc, use_fixed, use_tzlocal, use_dst, use_pytz
+        ndarray trans
+        Py_ssize_t ntrans
+        const int64_t[::1] deltas
+        int64_t delta
+        int64_t* tdata
+
+    cdef inline int64_t utc_val_to_local_val(
+        self,
+        int64_t utc_val,
+        Py_ssize_t* pos,
+        bint* fold=?,
+    ) except? -1