Merge remote-tracking branch 'upstream/master' into issue-19860

Author: mariuspot

ci/doctests.sh

@@ -21,7 +21,7 @@ if [ "$DOCTEST" ]; then
 
     # DataFrame / Series docstrings
     pytest --doctest-modules -v pandas/core/frame.py \
-        -k"-assign -axes -combine -isin -itertuples -join -nlargest -nsmallest -nunique -pivot_table -quantile -query -reindex -reindex_axis -replace -round -set_index -stack -to_dict -to_records -to_stata -transform"
+        -k"-assign -axes -combine -isin -itertuples -join -nlargest -nsmallest -nunique -pivot_table -quantile -query -reindex -reindex_axis -replace -round -set_index -stack -to_dict -to_stata -transform"
 
     if [ $? -ne "0" ]; then
         RET=1

ci/lint.sh

@@ -20,14 +20,14 @@ if [ "$LINT" ]; then
 
     # pandas/_libs/src is C code, so no need to search there.
     echo "Linting *.py"
-    flake8 pandas --filename=*.py --exclude pandas/_libs/src --ignore=C406,C408,C409,C410,E402,E731,E741,W503
+    flake8 pandas --filename=*.py --exclude pandas/_libs/src --ignore=C406,C408,C409,E402,E731,E741,W503
     if [ $? -ne "0" ]; then
         RET=1
     fi
     echo "Linting *.py DONE"
 
     echo "Linting setup.py"
-    flake8 setup.py --ignore=C406,C408,C409,C410,E402,E731,E741,W503
+    flake8 setup.py --ignore=E402,E731,E741,W503
     if [ $? -ne "0" ]; then
         RET=1
     fi
@@ -41,21 +41,21 @@ if [ "$LINT" ]; then
     echo "Linting asv_bench/benchmarks/*.py DONE"
 
     echo "Linting scripts/*.py"
-    flake8 scripts --filename=*.py --ignore=C406,C408,C409,C410,E402,E731,E741,W503
+    flake8 scripts --filename=*.py --ignore=C408,E402,E731,E741,W503
     if [ $? -ne "0" ]; then
         RET=1
     fi
     echo "Linting scripts/*.py DONE"
 
     echo "Linting doc scripts"
-    flake8 doc/make.py doc/source/conf.py --ignore=C406,C408,C409,C410,E402,E731,E741,W503
+    flake8 doc/make.py doc/source/conf.py --ignore=E402,E731,E741,W503
     if [ $? -ne "0" ]; then
         RET=1
     fi
     echo "Linting doc scripts DONE"
 
     echo "Linting *.pyx"
-    flake8 pandas --filename=*.pyx --select=E501,E302,E203,E111,E114,E221,E303,E128,E231,E126,E265,E305,E301,E127,E261,E271,E129,W291,E222,E241,E123,F403,C400,C401,C402,C403,C404,C407,C411
+    flake8 pandas --filename=*.pyx --select=E501,E302,E203,E111,E114,E221,E303,E128,E231,E126,E265,E305,E301,E127,E261,E271,E129,W291,E222,E241,E123,F403,C400,C401,C402,C403,C404,C405,C406,C407,C408,C409,C410,C411
     if [ $? -ne "0" ]; then
         RET=1
     fi

doc/source/api.rst

@@ -2352,6 +2352,7 @@ Computations / Descriptive Stats
    Resampler.std
    Resampler.sum
    Resampler.var
+   Resampler.quantile
 
 Style
 -----

doc/source/groupby.rst

@@ -106,9 +106,8 @@ consider the following ``DataFrame``:
    .. versionadded:: 0.20
 
    A string passed to ``groupby`` may refer to either a column or an index level.
-   If a string matches both a column name and an index level name then a warning is
-   issued and the column takes precedence. This will result in an ambiguity error
-   in a future version.
+   If a string matches both a column name and an index level name, a
+   ``ValueError`` will be raised.
 
 .. ipython:: python
 
@@ -389,7 +388,7 @@ This is mainly syntactic sugar for the alternative and much more verbose:
 Additionally this method avoids recomputing the internal grouping information
 derived from the passed key.
 
-.. _groupby.iterating:
+.. _groupby.iterating-label:
 
 Iterating through groups
 ------------------------
@@ -415,8 +414,7 @@ In the case of grouping by multiple keys, the group name will be a tuple:
       ...:        print(group)
       ...:
 
-It's standard Python-fu but remember you can unpack the tuple in the for loop
-statement if you wish: ``for (k1, k2), group in grouped:``.
+See :ref:`timeseries.iterating-label`.
 
 Selecting a group
 -----------------

doc/source/timeseries.rst

@@ -703,6 +703,24 @@ regularity will result in a ``DatetimeIndex``, although frequency is lost:
 
    ts2[[0, 2, 6]].index
 
+.. _timeseries.iterating-label:
+
+Iterating through groups
+------------------------
+
+With the :ref:`Resampler` object in hand, iterating through the grouped data is very
+natural and functions similarly to :py:func:`itertools.groupby`:
+
+.. ipython:: python
+
+   resampled = df.resample('H')
+
+   for name, group in resampled:
+       print(name)
+       print(group)
+
+See :ref:`groupby.iterating-label`.
+
 .. _timeseries.components:
 
 Time/Date Components

doc/source/whatsnew/v0.24.0.txt

@@ -42,7 +42,7 @@ Pandas has gained the ability to hold integer dtypes with missing values. This l
 Here is an example of the usage.
 
 We can construct a ``Series`` with the specified dtype. The dtype string ``Int64`` is a pandas ``ExtensionDtype``. Specifying a list or array using the traditional missing value
-marker of ``np.nan`` will infer to integer dtype. The display of the ``Series`` will also use the ``NaN`` to indicate missing values in string outputs. (:issue:`20700`, :issue:`20747`)
+marker of ``np.nan`` will infer to integer dtype. The display of the ``Series`` will also use the ``NaN`` to indicate missing values in string outputs. (:issue:`20700`, :issue:`20747`, :issue:`22441`)
 
 .. ipython:: python
 
@@ -182,6 +182,8 @@ Other Enhancements
 - :func:`to_timedelta` now supports iso-formated timedelta strings (:issue:`21877`)
 - :class:`Series` and :class:`DataFrame` now support :class:`Iterable` in constructor (:issue:`2193`)
 - :class:`DatetimeIndex` gained :attr:`DatetimeIndex.timetz` attribute. Returns local time with timezone information. (:issue:`21358`)
+- :class:`Resampler` now is iterable like :class:`GroupBy` (:issue:`15314`).
+- :ref:`Series.resample` and :ref:`DataFrame.resample` have gained the :meth:`Resampler.quantile` (:issue:`15023`).
 
 .. _whatsnew_0240.api_breaking:
 
@@ -521,6 +523,7 @@ Removal of prior version deprecations/changes
 - :meth:`Series.repeat` has renamed the ``reps`` argument to ``repeats`` (:issue:`14645`)
 - Several private functions were removed from the (non-public) module ``pandas.core.common`` (:issue:`22001`)
 - Removal of the previously deprecated module ``pandas.core.datetools`` (:issue:`14105`, :issue:`14094`)
+- Strings passed into :meth:`DataFrame.groupby` that refer to both column and index levels will raise a ``ValueError`` (:issue:`14432`)
 -
 
 .. _whatsnew_0240.performance:
@@ -656,7 +659,11 @@ Indexing
 - Fixed ``DataFrame[np.nan]`` when columns are non-unique (:issue:`21428`)
 - Bug when indexing :class:`DatetimeIndex` with nanosecond resolution dates and timezones (:issue:`11679`)
 - Bug where indexing with a Numpy array containing negative values would mutate the indexer (:issue:`21867`)
+<<<<<<< HEAD
 - Bug where mixed indexes wouldn't allow integers for ``.at`` (:issue:`19860`)
+=======
+- ``Float64Index.get_loc`` now raises ``KeyError`` when boolean key passed. (:issue:`19087`)
+>>>>>>> upstream/master
 
 Missing
 ^^^^^^^
@@ -677,6 +684,7 @@ I/O
 
 - :func:`read_html()` no longer ignores all-whitespace ``<tr>`` within ``<thead>`` when considering the ``skiprows`` and ``header`` arguments. Previously, users had to decrease their ``header`` and ``skiprows`` values on such tables to work around the issue. (:issue:`21641`)
 - :func:`read_excel()` will correctly show the deprecation warning for previously deprecated ``sheetname`` (:issue:`17994`)
+- :func:`read_csv()` will correctly parse timezone-aware datetimes (:issue:`22256`)
 -
 
 Plotting
@@ -694,7 +702,7 @@ Groupby/Resample/Rolling
   ``SeriesGroupBy`` when the grouping variable only contains NaNs and numpy version < 1.13 (:issue:`21956`).
 - Multiple bugs in :func:`pandas.core.Rolling.min` with ``closed='left'` and a
   datetime-like index leading to incorrect results and also segfault. (:issue:`21704`)
--
+- Bug in :meth:`Resampler.apply` when passing postiional arguments to applied func (:issue:`14615`).
 
 Sparse
 ^^^^^^

pandas/_libs/index.pyx

@@ -50,23 +50,7 @@ cpdef get_value_at(ndarray arr, object loc, object tz=None):
 
 
 cpdef object get_value_box(ndarray arr, object loc):
-    cdef:
-        Py_ssize_t i, sz
-
-    if util.is_float_object(loc):
-        casted = int(loc)
-        if casted == loc:
-            loc = casted
-    i = <Py_ssize_t> loc
-    sz = cnp.PyArray_SIZE(arr)
-
-    if i < 0 and sz > 0:
-        i += sz
-
-    if i >= sz or sz == 0 or i < 0:
-        raise IndexError('index out of bounds')
-
-    return get_value_at(arr, i, tz=None)
+    return get_value_at(arr, loc, tz=None)
 
 
 # Don't populate hash tables in monotonic indexes larger than this

pandas/_libs/util.pxd

@@ -72,23 +72,50 @@ cdef inline void set_array_not_contiguous(ndarray ao) nogil:
                        (NPY_ARRAY_C_CONTIGUOUS | NPY_ARRAY_F_CONTIGUOUS))
 
 
-cdef inline object get_value_at(ndarray arr, object loc):
+cdef inline Py_ssize_t validate_indexer(ndarray arr, object loc) except -1:
+    """
+    Cast the given indexer `loc` to an integer.  If it is negative, i.e. a
+    python-style indexing-from-the-end indexer, translate it to a
+    from-the-front indexer.  Raise if this is not possible.
+
+    Parameters
+    ----------
+    arr : ndarray
+    loc : object
+
+    Returns
+    -------
+    idx : Py_ssize_t
+
+    Raises
+    ------
+    IndexError
+    """
     cdef:
-        Py_ssize_t i, sz
+        Py_ssize_t idx, size
         int casted
 
     if is_float_object(loc):
         casted = int(loc)
         if casted == loc:
             loc = casted
-    i = <Py_ssize_t> loc
-    sz = cnp.PyArray_SIZE(arr)
 
-    if i < 0 and sz > 0:
-        i += sz
-    elif i >= sz or sz == 0:
+    idx = <Py_ssize_t>loc
+    size = cnp.PyArray_SIZE(arr)
+
+    if idx < 0 and size > 0:
+        idx += size
+    if idx >= size or size == 0 or idx < 0:
         raise IndexError('index out of bounds')
 
+    return idx
+
+
+cdef inline object get_value_at(ndarray arr, object loc):
+    cdef:
+        Py_ssize_t i
+
+    i = validate_indexer(arr, loc)
     return get_value_1d(arr, i)
 
 
@@ -99,19 +126,9 @@ cdef inline set_value_at_unsafe(ndarray arr, object loc, object value):
     flag above the loop and then eschew the check on each iteration.
     """
     cdef:
-        Py_ssize_t i, sz
-    if is_float_object(loc):
-        casted = int(loc)
-        if casted == loc:
-            loc = casted
-    i = <Py_ssize_t> loc
-    sz = cnp.PyArray_SIZE(arr)
-
-    if i < 0:
-        i += sz
-    elif i >= sz:
-        raise IndexError('index out of bounds')
+        Py_ssize_t i
 
+    i = validate_indexer(arr, loc)
     assign_value_1d(arr, i, value)
 
 

pandas/core/arrays/integer.py

@@ -409,8 +409,7 @@ def astype(self, dtype, copy=True):
 
         # if we are astyping to an existing IntegerDtype we can fastpath
         if isinstance(dtype, _IntegerDtype):
-            result = self._data.astype(dtype.numpy_dtype,
-                                       casting='same_kind', copy=False)
+            result = self._data.astype(dtype.numpy_dtype, copy=False)
             return type(self)(result, mask=self._mask, copy=False)
 
         # coerce