Merge branch 'master' of https://github.com/pandas-dev/pandas into Tdtype

Author: jbrockmendel

doc/source/conf.py

@@ -315,7 +315,6 @@
    import numpy as np
    import pandas as pd
 
-   randn = np.random.randn
    np.random.seed(123456)
    np.set_printoptions(precision=4, suppress=True)
    pd.options.display.max_rows = 15

doc/source/whatsnew/index.rst

@@ -24,6 +24,7 @@ Version 0.25
 .. toctree::
    :maxdepth: 2
 
+   v0.25.2
    v0.25.1
    v0.25.0
 

doc/source/whatsnew/v0.10.0.rst

@@ -498,7 +498,7 @@ Here is a taste of what to expect.
 
 .. code-block:: ipython
 
-  In [58]: p4d = Panel4D(randn(2, 2, 5, 4),
+  In [58]: p4d = Panel4D(np.random.randn(2, 2, 5, 4),
     ....:       labels=['Label1','Label2'],
     ....:       items=['Item1', 'Item2'],
     ....:       major_axis=date_range('1/1/2000', periods=5),

doc/source/whatsnew/v0.25.1.rst

@@ -85,6 +85,7 @@ Plotting
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
 
+- Fixed regression in :meth:`pands.core.groupby.DataFrameGroupBy.quantile` raising when multiple quantiles are given (:issue:`27526`)
 - Bug in :meth:`pandas.core.groupby.DataFrameGroupBy.transform` where applying a timezone conversion lambda function would drop timezone information (:issue:`27496`)
 - Bug in :meth:`pandas.core.groupby.GroupBy.nth` where ``observed=False`` was being ignored for Categorical groupers (:issue:`26385`)
 - Bug in windowing over read-only arrays (:issue:`27766`)
@@ -94,6 +95,7 @@ Reshaping
 ^^^^^^^^^
 
 - A ``KeyError`` is now raised if ``.unstack()`` is called on a :class:`Series` or :class:`DataFrame` with a flat :class:`Index` passing a name which is not the correct one (:issue:`18303`)
+- Bug :meth:`merge_asof` could not merge :class:`Timedelta` objects when passing `tolerance` kwarg (:issue:`27642`)
 - Bug in :meth:`DataFrame.crosstab` when ``margins`` set to ``True`` and ``normalize`` is not ``False``, an error is raised. (:issue:`27500`)
 - :meth:`DataFrame.join` now suppresses the ``FutureWarning`` when the sort parameter is specified (:issue:`21952`)
 - Bug in :meth:`DataFrame.join` raising with readonly arrays (:issue:`27943`)
@@ -107,6 +109,7 @@ Other
 ^^^^^
 
 - Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` when replacing timezone-aware timestamps using a dict-like replacer (:issue:`27720`)
+- Bug in :meth:`Series.rename` when using a custom type indexer. Now any value that isn't callable or dict-like is treated as a scalar. (:issue:`27814`)
 
 .. _whatsnew_0.251.contributors:
 

doc/source/whatsnew/v0.25.2.rst

@@ -0,0 +1,110 @@
+.. _whatsnew_0252:
+
+What's new in 0.25.2 (October XX, 2019)
+---------------------------------------
+
+These are the changes in pandas 0.25.2. See :ref:`release` for a full changelog
+including other versions of pandas.
+
+.. _whatsnew_0252.bug_fixes:
+
+Bug fixes
+~~~~~~~~~
+
+Categorical
+^^^^^^^^^^^
+
+-
+
+Datetimelike
+^^^^^^^^^^^^
+
+-
+-
+-
+
+Timezones
+^^^^^^^^^
+
+-
+
+Numeric
+^^^^^^^
+
+-
+-
+-
+-
+
+Conversion
+^^^^^^^^^^
+
+-
+
+Interval
+^^^^^^^^
+
+-
+
+Indexing
+^^^^^^^^
+
+-
+-
+-
+-
+
+Missing
+^^^^^^^
+
+-
+
+I/O
+^^^
+
+-
+-
+-
+
+Plotting
+^^^^^^^^
+
+-
+-
+-
+
+Groupby/resample/rolling
+^^^^^^^^^^^^^^^^^^^^^^^^
+
+-
+-
+-
+-
+-
+
+Reshaping
+^^^^^^^^^
+
+-
+-
+-
+-
+-
+
+Sparse
+^^^^^^
+
+-
+
+Other
+^^^^^
+
+-
+-
+
+.. _whatsnew_0.252.contributors:
+
+Contributors
+~~~~~~~~~~~~
+
+.. contributors:: v0.25.1..HEAD

pandas/core/arrays/base.py

@@ -514,7 +514,7 @@ def fillna(self, value=None, method=None, limit=None):
 
     def dropna(self):
         """
-        Return ExtensionArray without NA values
+        Return ExtensionArray without NA values.
 
         Returns
         -------
@@ -957,7 +957,7 @@ def _concat_same_type(
         cls, to_concat: Sequence[ABCExtensionArray]
     ) -> ABCExtensionArray:
         """
-        Concatenate multiple array
+        Concatenate multiple array.
 
         Parameters
         ----------

pandas/core/arrays/datetimes.py

@@ -1158,7 +1158,7 @@ def tz_localize(self, tz, ambiguous="raise", nonexistent="raise", errors=None):
     def to_pydatetime(self):
         """
         Return Datetime Array/Index as object ndarray of datetime.datetime
-        objects
+        objects.
 
         Returns
         -------
@@ -1283,7 +1283,7 @@ def to_perioddelta(self, freq):
         """
         Calculate TimedeltaArray of difference between index
         values and index converted to PeriodArray at specified
-        freq. Used for vectorized offsets
+        freq. Used for vectorized offsets.
 
         Parameters
         ----------

pandas/core/arrays/period.py

@@ -426,7 +426,7 @@ def __array__(self, dtype=None):
     @property
     def is_leap_year(self):
         """
-        Logical indicating if the date belongs to a leap year
+        Logical indicating if the date belongs to a leap year.
         """
         return isleapyear_arr(np.asarray(self.year))
 

pandas/core/frame.py

@@ -3098,7 +3098,7 @@ def _ensure_valid_index(self, value):
         passed value.
         """
         # GH5632, make sure that we are a Series convertible
-        if not len(self.index) and is_list_like(value):
+        if not len(self.index) and is_list_like(value) and len(value):
             try:
                 value = Series(value)
             except (ValueError, NotImplementedError, TypeError):

pandas/core/groupby/groupby.py

@@ -1874,6 +1874,7 @@ def quantile(self, q=0.5, interpolation="linear"):
         a    2.0
         b    3.0
         """
+        from pandas import concat
 
         def pre_processor(vals: np.ndarray) -> Tuple[np.ndarray, Optional[Type]]:
             if is_object_dtype(vals):
@@ -1901,18 +1902,57 @@ def post_processor(vals: np.ndarray, inference: Optional[Type]) -> np.ndarray:
 
             return vals
 
-        return self._get_cythonized_result(
-            "group_quantile",
-            self.grouper,
-            aggregate=True,
-            needs_values=True,
-            needs_mask=True,
-            cython_dtype=np.float64,
-            pre_processing=pre_processor,
-            post_processing=post_processor,
-            q=q,
-            interpolation=interpolation,
-        )
+        if is_scalar(q):
+            return self._get_cythonized_result(
+                "group_quantile",
+                self.grouper,
+                aggregate=True,
+                needs_values=True,
+                needs_mask=True,
+                cython_dtype=np.float64,
+                pre_processing=pre_processor,
+                post_processing=post_processor,
+                q=q,
+                interpolation=interpolation,
+            )
+        else:
+            results = [
+                self._get_cythonized_result(
+                    "group_quantile",
+                    self.grouper,
+                    aggregate=True,
+                    needs_values=True,
+                    needs_mask=True,
+                    cython_dtype=np.float64,
+                    pre_processing=pre_processor,
+                    post_processing=post_processor,
+                    q=qi,
+                    interpolation=interpolation,
+                )
+                for qi in q
+            ]
+            result = concat(results, axis=0, keys=q)
+            # fix levels to place quantiles on the inside
+            # TODO(GH-10710): Ideally, we could write this as
+            #  >>> result.stack(0).loc[pd.IndexSlice[:, ..., q], :]
+            #  but this hits https://github.com/pandas-dev/pandas/issues/10710
+            #  which doesn't reorder the list-like `q` on the inner level.
+            order = np.roll(list(range(result.index.nlevels)), -1)
+            result = result.reorder_levels(order)
+            result = result.reindex(q, level=-1)
+
+            # fix order.
+            hi = len(q) * self.ngroups
+            arr = np.arange(0, hi, self.ngroups)
+            arrays = []
+
+            for i in range(self.ngroups):
+                arr = arr + i
+                arrays.append(arr)
+
+            indices = np.concatenate(arrays)
+            assert len(indices) == len(result)
+            return result.take(indices)
 
     @Substitution(name="groupby")
     def ngroup(self, ascending=True):
@@ -2330,8 +2370,9 @@ def head(self, n=5):
         """
         Return first n rows of each group.
 
-        Essentially equivalent to ``.apply(lambda x: x.head(n))``,
-        except ignores as_index flag.
+        Similar to ``.apply(lambda x: x.head(n))``, but it returns a subset of rows
+        from the original DataFrame with original index and order preserved
+        (``as_index`` flag is ignored).
 
         Returns
         -------
@@ -2342,10 +2383,6 @@ def head(self, n=5):
 
         >>> df = pd.DataFrame([[1, 2], [1, 4], [5, 6]],
         ...                   columns=['A', 'B'])
-        >>> df.groupby('A', as_index=False).head(1)
-           A  B
-        0  1  2
-        2  5  6
         >>> df.groupby('A').head(1)
            A  B
         0  1  2
@@ -2361,8 +2398,9 @@ def tail(self, n=5):
         """
         Return last n rows of each group.
 
-        Essentially equivalent to ``.apply(lambda x: x.tail(n))``,
-        except ignores as_index flag.
+        Similar to ``.apply(lambda x: x.tail(n))``, but it returns a subset of rows
+        from the original DataFrame with original index and order preserved
+        (``as_index`` flag is ignored).
 
         Returns
         -------
@@ -2377,10 +2415,6 @@ def tail(self, n=5):
            A  B
         1  a  2
         3  b  2
-        >>> df.groupby('A').head(1)
-           A  B
-        0  a  1
-        2  b  1
         """
         self._reset_group_selection()
         mask = self._cumcount_array(ascending=False) < n

pandas/core/indexes/datetimes.py

@@ -661,7 +661,7 @@ def _get_time_micros(self):
     def to_series(self, keep_tz=None, index=None, name=None):
         """
         Create a Series with both index and values equal to the index keys
-        useful with map for returning an indexer based on an index
+        useful with map for returning an indexer based on an index.
 
         Parameters
         ----------
@@ -687,10 +687,10 @@ def to_series(self, keep_tz=None, index=None, name=None):
                 behaviour and silence the warning.
 
         index : Index, optional
-            index of resulting Series. If None, defaults to original index
-        name : string, optional
-            name of resulting Series. If None, defaults to name of original
-            index
+            Index of resulting Series. If None, defaults to original index.
+        name : str, optional
+            Name of resulting Series. If None, defaults to name of original
+            index.
 
         Returns
         -------
@@ -735,7 +735,7 @@ def to_series(self, keep_tz=None, index=None, name=None):
 
     def snap(self, freq="S"):
         """
-        Snap time stamps to nearest occurring frequency
+        Snap time stamps to nearest occurring frequency.
 
         Returns
         -------

pandas/core/indexes/multi.py

@@ -1250,7 +1250,7 @@ def _set_names(self, names, level=None, validate=True):
             self.levels[l].rename(name, inplace=True)
 
     names = property(
-        fset=_set_names, fget=_get_names, doc="""\nNames of levels in MultiIndex\n"""
+        fset=_set_names, fget=_get_names, doc="""\nNames of levels in MultiIndex.\n"""
     )
 
     @Appender(_index_shared_docs["_get_grouper_for_level"])
@@ -1762,7 +1762,7 @@ def is_all_dates(self):
 
     def is_lexsorted(self):
         """
-        Return True if the codes are lexicographically sorted
+        Return True if the codes are lexicographically sorted.
 
         Returns
         -------
@@ -2246,7 +2246,7 @@ def swaplevel(self, i=-2, j=-1):
 
     def reorder_levels(self, order):
         """
-        Rearrange levels using input order. May not drop or duplicate levels
+        Rearrange levels using input order. May not drop or duplicate levels.
 
         Parameters
         ----------