Merge branch 'master' into ref-quantile

Author: jbrockmendel

asv_bench/benchmarks/rolling.py

@@ -140,8 +140,11 @@ class Pairwise:
 
     def setup(self, window, method, pairwise):
         N = 10 ** 4
+        n_groups = 20
+        groups = [i for _ in range(N // n_groups) for i in range(n_groups)]
         arr = np.random.random(N)
         self.df = pd.DataFrame(arr)
+        self.df_group = pd.DataFrame({"A": groups, "B": arr}).groupby("A")
 
     def time_pairwise(self, window, method, pairwise):
         if window is None:
@@ -150,6 +153,13 @@ def time_pairwise(self, window, method, pairwise):
             r = self.df.rolling(window=window)
         getattr(r, method)(self.df, pairwise=pairwise)
 
+    def time_groupby(self, window, method, pairwise):
+        if window is None:
+            r = self.df_group.expanding()
+        else:
+            r = self.df_group.rolling(window=window)
+        getattr(r, method)(self.df, pairwise=pairwise)
+
 
 class Quantile:
     params = (

doc/source/user_guide/style.ipynb

@@ -180,8 +180,7 @@
     "\n",
     "styles = [\n",
     "    hover(),\n",
-    "    {'selector': \"th\", 'props': [(\"font-size\", \"150%\"),\n",
-    "                                 (\"text-align\", \"center\")]}\n",
+    "    {'selector': \"th\", 'props': [(\"font-size\", \"150%\"), (\"text-align\", \"center\")]}\n",
     "]\n",
     "\n",
     "df.style.set_table_styles(styles)"
@@ -224,7 +223,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can also chain all of the above by setting the `overwrite` argument to `False` so that it preserves previous settings."
+    "We can also chain all of the above by setting the `overwrite` argument to `False` so that it preserves previous settings. We also show the CSS string input rather than the list of tuples."
    ]
   },
   {
@@ -238,13 +237,13 @@
     "    set_table_styles(styles).\\\n",
     "    set_table_styles({\n",
     "        'A': [{'selector': '',\n",
-    "               'props': [('color', 'red')]}],\n",
+    "               'props': 'color:red;'}],\n",
     "        'B': [{'selector': 'td',\n",
-    "               'props': [('color', 'blue')]}]\n",
+    "               'props': 'color:blue;'}]\n",
     "    }, axis=0, overwrite=False).\\\n",
     "    set_table_styles({\n",
     "        3: [{'selector': 'td',\n",
-    "             'props': [('color', 'green')]}]\n",
+    "             'props': 'color:green;font-weight:bold;'}]\n",
     "    }, axis=1, overwrite=False)\n",
     "s"
    ]

doc/source/whatsnew/v1.2.2.rst

@@ -31,6 +31,7 @@ Bug fixes
 ~~~~~~~~~
 
 - :func:`pandas.read_excel` error message when a specified ``sheetname`` does not exist is now uniform across engines (:issue:`39250`)
+- Fixed bug in :func:`pandas.read_excel` producing incorrect results when the engine ``openpyxl`` is used and the excel file is missing or has incorrect dimension information; the fix requires ``openpyxl`` >= 3.0.0, prior versions may still fail (:issue:`38956`, :issue:`39001`)
 -
 
 .. ---------------------------------------------------------------------------

doc/source/whatsnew/v1.3.0.rst

@@ -53,10 +53,12 @@ Other enhancements
 - :meth:`DataFrame.apply` can now accept non-callable DataFrame properties as strings, e.g. ``df.apply("size")``, which was already the case for :meth:`Series.apply` (:issue:`39116`)
 - :meth:`Series.apply` can now accept list-like or dictionary-like arguments that aren't lists or dictionaries, e.g. ``ser.apply(np.array(["sum", "mean"]))``, which was already the case for :meth:`DataFrame.apply` (:issue:`39140`)
 - :meth:`DataFrame.plot.scatter` can now accept a categorical column as the argument to ``c`` (:issue:`12380`, :issue:`31357`)
-- :meth:`.Styler.set_tooltips` allows on hover tooltips to be added to styled HTML dataframes.
+- :meth:`.Styler.set_tooltips` allows on hover tooltips to be added to styled HTML dataframes (:issue:`35643`)
+- :meth:`.Styler.set_tooltips_class` and :meth:`.Styler.set_table_styles` amended to optionally allow certain css-string input arguments (:issue:`39564`)
 - :meth:`Series.loc.__getitem__` and :meth:`Series.loc.__setitem__` with :class:`MultiIndex` now raising helpful error message when indexer has too many dimensions (:issue:`35349`)
 - :meth:`pandas.read_stata` and :class:`StataReader` support reading data from compressed files.
 
+
 .. ---------------------------------------------------------------------------
 
 .. _whatsnew_130.notable_bug_fixes:
@@ -249,7 +251,8 @@ Performance improvements
 - Performance improvement in :meth:`Series.mean` for nullable data types (:issue:`34814`)
 - Performance improvement in :meth:`Series.isin` for nullable data types (:issue:`38340`)
 - Performance improvement in :meth:`DataFrame.corr` for method=kendall (:issue:`28329`)
-- Performance improvement in :meth:`core.window.Rolling.corr` and :meth:`core.window.Rolling.cov` (:issue:`39388`)
+- Performance improvement in :meth:`core.window.rolling.Rolling.corr` and :meth:`core.window.rolling.Rolling.cov` (:issue:`39388`)
+- Performance improvement in :meth:`core.window.rolling.RollingGroupby.corr`, :meth:`core.window.expanding.ExpandingGroupby.corr`, :meth:`core.window.expanding.ExpandingGroupby.corr` and :meth:`core.window.expanding.ExpandingGroupby.cov` (:issue:`39591`)
 
 .. ---------------------------------------------------------------------------
 
@@ -279,6 +282,7 @@ Datetimelike
 - Bug in :class:`Categorical` incorrectly typecasting ``datetime`` object to ``Timestamp`` (:issue:`38878`)
 - Bug in comparisons between :class:`Timestamp` object and ``datetime64`` objects just outside the implementation bounds for nanosecond ``datetime64`` (:issue:`39221`)
 - Bug in :meth:`Timestamp.round`, :meth:`Timestamp.floor`, :meth:`Timestamp.ceil` for values near the implementation bounds of :class:`Timestamp` (:issue:`39244`)
+- Bug in :meth:`Timedelta.round`, :meth:`Timedelta.floor`, :meth:`Timedelta.ceil` for values near the implementation bounds of :class:`Timedelta` (:issue:`38964`)
 - Bug in :func:`date_range` incorrectly creating :class:`DatetimeIndex` containing ``NaT`` instead of raising ``OutOfBoundsDatetime`` in corner cases (:issue:`24124`)
 
 Timedelta
@@ -341,6 +345,8 @@ Indexing
 - Bug in incorrectly raising in :meth:`Index.insert`, when setting a new column that cannot be held in the existing ``frame.columns``, or in :meth:`Series.reset_index` or :meth:`DataFrame.reset_index` instead of casting to a compatible dtype (:issue:`39068`)
 - Bug in :meth:`RangeIndex.append` where a single object of length 1 was concatenated incorrectly (:issue:`39401`)
 - Bug in setting ``numpy.timedelta64`` values into an object-dtype :class:`Series` using a boolean indexer (:issue:`39488`)
+- Bug in setting numeric values into a into a boolean-dtypes :class:`Series` using ``at`` or ``iat`` failing to cast to object-dtype (:issue:`39582`)
+-
 
 Missing
 ^^^^^^^
@@ -404,6 +410,8 @@ Groupby/resample/rolling
 - Bug in :meth:`.Resampler.aggregate` and :meth:`DataFrame.transform` raising ``TypeError`` instead of ``SpecificationError`` when missing keys had mixed dtypes (:issue:`39025`)
 - Bug in :meth:`.DataFrameGroupBy.idxmin` and :meth:`.DataFrameGroupBy.idxmax` with ``ExtensionDtype`` columns (:issue:`38733`)
 - Bug in :meth:`Series.resample` would raise when the index was a :class:`PeriodIndex` consisting of ``NaT`` (:issue:`39227`)
+- Bug in :meth:`core.window.rolling.RollingGroupby.corr` and :meth:`core.window.expanding.ExpandingGroupby.corr` where the groupby column would return 0 instead of ``np.nan`` when providing ``other`` that was longer than each group (:issue:`39591`)
+- Bug in :meth:`core.window.expanding.ExpandingGroupby.corr` and :meth:`core.window.expanding.ExpandingGroupby.cov` where 1 would be returned instead of ``np.nan`` when providing ``other`` that was longer than each group (:issue:`39591`)
 
 Reshaping
 ^^^^^^^^^
@@ -413,7 +421,9 @@ Reshaping
 - :meth:`merge_asof` raises ``ValueError`` instead of cryptic ``TypeError`` in case of non-numerical merge columns (:issue:`29130`)
 - Bug in :meth:`DataFrame.join` not assigning values correctly when having :class:`MultiIndex` where at least one dimension is from dtype ``Categorical`` with non-alphabetically sorted categories (:issue:`38502`)
 - :meth:`Series.value_counts` and :meth:`Series.mode` return consistent keys in original order (:issue:`12679`, :issue:`11227` and :issue:`39007`)
+- Bug in :meth:`DataFrame.stack` not handling ``NaN`` in :class:`MultiIndex` columns correct (:issue:`39481`)
 - Bug in :meth:`DataFrame.apply` would give incorrect results when used with a string argument and ``axis=1`` when the axis argument was not supported and now raises a ``ValueError`` instead (:issue:`39211`)
+- Bug in :meth:`DataFrame.sort_values` not reshaping index correctly after sorting on columns, when ``ignore_index=True`` (:issue:`39464`)
 - Bug in :meth:`DataFrame.append` returning incorrect dtypes with combinations of ``ExtensionDtype`` dtypes (:issue:`39454`)
 
 Sparse
@@ -437,6 +447,8 @@ Other
 - Bug in :class:`Styler` which caused CSS to duplicate on multiple renders. (:issue:`39395`)
 - :meth:`Index.where` behavior now mirrors :meth:`Index.putmask` behavior, i.e. ``index.where(mask, other)`` matches ``index.putmask(~mask, other)`` (:issue:`39412`)
 - Bug in :func:`pandas.testing.assert_series_equal`, :func:`pandas.testing.assert_frame_equal`, :func:`pandas.testing.assert_index_equal` and :func:`pandas.testing.assert_extension_array_equal` incorrectly raising when an attribute has an unrecognized NA type (:issue:`39461`)
+- Bug in :class:`Styler` where ``subset`` arg in methods raised an error for some valid multiindex slices (:issue:`33562`)
+-
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/tslibs/fields.pyx

@@ -636,3 +636,154 @@ def get_locale_names(name_type: str, locale: object = None):
     """
     with set_locale(locale, LC_TIME):
         return getattr(LocaleTime(), name_type)
+
+
+# ---------------------------------------------------------------------
+# Rounding
+
+
+class RoundTo:
+    """
+    enumeration defining the available rounding modes
+
+    Attributes
+    ----------
+    MINUS_INFTY
+        round towards -∞, or floor [2]_
+    PLUS_INFTY
+        round towards +∞, or ceil [3]_
+    NEAREST_HALF_EVEN
+        round to nearest, tie-break half to even [6]_
+    NEAREST_HALF_MINUS_INFTY
+        round to nearest, tie-break half to -∞ [5]_
+    NEAREST_HALF_PLUS_INFTY
+        round to nearest, tie-break half to +∞ [4]_
+
+
+    References
+    ----------
+    .. [1] "Rounding - Wikipedia"
+           https://en.wikipedia.org/wiki/Rounding
+    .. [2] "Rounding down"
+           https://en.wikipedia.org/wiki/Rounding#Rounding_down
+    .. [3] "Rounding up"
+           https://en.wikipedia.org/wiki/Rounding#Rounding_up
+    .. [4] "Round half up"
+           https://en.wikipedia.org/wiki/Rounding#Round_half_up
+    .. [5] "Round half down"
+           https://en.wikipedia.org/wiki/Rounding#Round_half_down
+    .. [6] "Round half to even"
+           https://en.wikipedia.org/wiki/Rounding#Round_half_to_even
+    """
+    @property
+    def MINUS_INFTY(self) -> int:
+        return 0
+
+    @property
+    def PLUS_INFTY(self) -> int:
+        return 1
+
+    @property
+    def NEAREST_HALF_EVEN(self) -> int:
+        return 2
+
+    @property
+    def NEAREST_HALF_PLUS_INFTY(self) -> int:
+        return 3
+
+    @property
+    def NEAREST_HALF_MINUS_INFTY(self) -> int:
+        return 4
+
+
+cdef inline ndarray[int64_t] _floor_int64(int64_t[:] values, int64_t unit):
+    cdef:
+        Py_ssize_t i, n = len(values)
+        ndarray[int64_t] result = np.empty(n, dtype="i8")
+        int64_t res, value
+
+    with cython.overflowcheck(True):
+        for i in range(n):
+            value = values[i]
+            if value == NPY_NAT:
+                res = NPY_NAT
+            else:
+                res = value - value % unit
+            result[i] = res
+
+    return result
+
+
+cdef inline ndarray[int64_t] _ceil_int64(int64_t[:] values, int64_t unit):
+    cdef:
+        Py_ssize_t i, n = len(values)
+        ndarray[int64_t] result = np.empty(n, dtype="i8")
+        int64_t res, value
+
+    with cython.overflowcheck(True):
+        for i in range(n):
+            value = values[i]
+
+            if value == NPY_NAT:
+                res = NPY_NAT
+            else:
+                remainder = value % unit
+                if remainder == 0:
+                    res = value
+                else:
+                    res = value + (unit - remainder)
+
+            result[i] = res
+
+    return result
+
+
+cdef inline ndarray[int64_t] _rounddown_int64(values, int64_t unit):
+    return _ceil_int64(values - unit // 2, unit)
+
+
+cdef inline ndarray[int64_t] _roundup_int64(values, int64_t unit):
+    return _floor_int64(values + unit // 2, unit)
+
+
+def round_nsint64(values: np.ndarray, mode: RoundTo, nanos) -> np.ndarray:
+    """
+    Applies rounding mode at given frequency
+
+    Parameters
+    ----------
+    values : np.ndarray[int64_t]`
+    mode : instance of `RoundTo` enumeration
+    nanos : np.int64
+        Freq to round to, expressed in nanoseconds
+
+    Returns
+    -------
+    np.ndarray[int64_t]
+    """
+    cdef:
+        int64_t unit = nanos
+
+    if mode == RoundTo.MINUS_INFTY:
+        return _floor_int64(values, unit)
+    elif mode == RoundTo.PLUS_INFTY:
+        return _ceil_int64(values, unit)
+    elif mode == RoundTo.NEAREST_HALF_MINUS_INFTY:
+        return _rounddown_int64(values, unit)
+    elif mode == RoundTo.NEAREST_HALF_PLUS_INFTY:
+        return _roundup_int64(values, unit)
+    elif mode == RoundTo.NEAREST_HALF_EVEN:
+        # for odd unit there is no need of a tie break
+        if unit % 2:
+            return _rounddown_int64(values, unit)
+        quotient, remainder = np.divmod(values, unit)
+        mask = np.logical_or(
+            remainder > (unit // 2),
+            np.logical_and(remainder == (unit // 2), quotient % 2)
+        )
+        quotient[mask] += 1
+        return quotient * unit
+
+    # if/elif above should catch all rounding modes defined in enum 'RoundTo':
+    # if flow of control arrives here, it is a bug
+    raise ValueError("round_nsint64 called with an unrecognized rounding mode")

pandas/_libs/tslibs/timedeltas.pyx

@@ -47,6 +47,7 @@ from pandas._libs.tslibs.util cimport (
     is_integer_object,
     is_timedelta64_object,
 )
+from pandas._libs.tslibs.fields import RoundTo, round_nsint64
 
 # ----------------------------------------------------------------------
 # Constants
@@ -1297,14 +1298,18 @@ class Timedelta(_Timedelta):
         object_state = self.value,
         return (Timedelta, object_state)
 
-    def _round(self, freq, rounder):
+    @cython.cdivision(True)
+    def _round(self, freq, mode):
         cdef:
-            int64_t result, unit
+            int64_t result, unit, remainder
+            ndarray[int64_t] arr
 
         from pandas._libs.tslibs.offsets import to_offset
         unit = to_offset(freq).nanos
-        result = unit * rounder(self.value / float(unit))
-        return Timedelta(result, unit='ns')
+
+        arr = np.array([self.value], dtype="i8")
+        result = round_nsint64(arr, mode, unit)[0]
+        return Timedelta(result, unit="ns")
 
     def round(self, freq):
         """
@@ -1323,7 +1328,7 @@ class Timedelta(_Timedelta):
         ------
         ValueError if the freq cannot be converted
         """
-        return self._round(freq, np.round)
+        return self._round(freq, RoundTo.NEAREST_HALF_EVEN)
 
     def floor(self, freq):
         """
@@ -1334,7 +1339,7 @@ class Timedelta(_Timedelta):
         freq : str
             Frequency string indicating the flooring resolution.
         """
-        return self._round(freq, np.floor)
+        return self._round(freq, RoundTo.MINUS_INFTY)
 
     def ceil(self, freq):
         """
@@ -1345,7 +1350,7 @@ class Timedelta(_Timedelta):
         freq : str
             Frequency string indicating the ceiling resolution.
         """
-        return self._round(freq, np.ceil)
+        return self._round(freq, RoundTo.PLUS_INFTY)
 
     # ----------------------------------------------------------------
     # Arithmetic Methods