Merge pull request #40 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

ci/code_checks.sh

@@ -305,6 +305,10 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
         pandas/core/arrays/boolean.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Doctests dtypes'; echo $MSG
+    pytest -q --doctest-modules pandas/core/dtypes/
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     MSG='Doctests arrays/boolean.py' ; echo $MSG
     pytest -q --doctest-modules pandas/core/arrays/boolean.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"

doc/source/user_guide/boolean.rst

@@ -9,7 +9,7 @@
 .. _boolean:
 
 **************************
-Nullable Boolean Data Type
+Nullable Boolean data type
 **************************
 
 .. versionadded:: 1.0.0

doc/source/whatsnew/v1.0.2.rst

@@ -17,6 +17,7 @@ Fixed regressions
 
 - Fixed regression in :meth:`DataFrame.to_excel` when ``columns`` kwarg is passed (:issue:`31677`)
 - Fixed regression in :meth:`Series.align` when ``other`` is a DataFrame and ``method`` is not None (:issue:`31785`)
+- Fixed regression in :meth:`pandas.core.groupby.RollingGroupby.apply` where the ``raw`` parameter was ignored (:issue:`31754`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/arrays/interval.py

@@ -1175,7 +1175,7 @@ def __arrow_array__(self, type=None):
 
         Parameters
         ----------
-        na_tuple : boolean, default True
+        na_tuple : bool, default True
             Returns NA as a tuple if True, ``(nan, nan)``, or just as the NA
             value itself if False, ``nan``.
 

pandas/core/dtypes/base.py

@@ -1,4 +1,7 @@
-"""Extend pandas with custom array types"""
+"""
+Extend pandas with custom array types.
+"""
+
 from typing import Any, List, Optional, Tuple, Type
 
 import numpy as np
@@ -231,8 +234,9 @@ def construct_from_string(cls, string: str):
         ...     if match:
         ...         return cls(**match.groupdict())
         ...     else:
-        ...         raise TypeError(f"Cannot construct a '{cls.__name__}' from
-        ...             " "'{string}'")
+        ...         raise TypeError(
+        ...             f"Cannot construct a '{cls.__name__}' from '{string}'"
+        ...         )
         """
         if not isinstance(string, str):
             raise TypeError(

pandas/core/dtypes/cast.py

@@ -1,4 +1,6 @@
-""" routings for casting """
+"""
+Routines for casting.
+"""
 
 from datetime import date, datetime, timedelta
 
@@ -269,12 +271,12 @@ def maybe_upcast_putmask(result: np.ndarray, mask: np.ndarray, other):
 
     Examples
     --------
-    >>> result, _ = maybe_upcast_putmask(np.arange(1,6),
-    np.array([False, True, False, True, True]), np.arange(21,23))
+    >>> arr = np.arange(1, 6)
+    >>> mask = np.array([False, True, False, True, True])
+    >>> result, _ = maybe_upcast_putmask(arr, mask, False)
     >>> result
-    array([1, 21, 3, 22, 21])
+    array([1, 0, 3, 0, 0])
     """
-
     if not isinstance(result, np.ndarray):
         raise ValueError("The result input must be a ndarray.")
     if not is_scalar(other):
@@ -662,9 +664,8 @@ def infer_dtype_from_array(arr, pandas_dtype: bool = False):
     array(['1', '1'], dtype='<U21')
 
     >>> infer_dtype_from_array([1, '1'])
-    (numpy.object_, [1, '1'])
+    (<class 'numpy.object_'>, [1, '1'])
     """
-
     if isinstance(arr, np.ndarray):
         return arr.dtype, arr
 
@@ -709,7 +710,7 @@ def maybe_infer_dtype_type(element):
     >>> from collections import namedtuple
     >>> Foo = namedtuple("Foo", "dtype")
     >>> maybe_infer_dtype_type(Foo(np.dtype("i8")))
-    numpy.int64
+    dtype('int64')
     """
     tipo = None
     if hasattr(element, "dtype"):
@@ -1555,8 +1556,8 @@ def maybe_cast_to_integer_array(arr, dtype, copy: bool = False):
 
     Returns
     -------
-    int_arr : ndarray
-        An array of integer or unsigned integer dtype
+    ndarray
+        Array of integer or unsigned integer dtype.
 
     Raises
     ------
@@ -1567,19 +1568,18 @@ def maybe_cast_to_integer_array(arr, dtype, copy: bool = False):
     --------
     If you try to coerce negative values to unsigned integers, it raises:
 
-    >>> Series([-1], dtype="uint64")
+    >>> pd.Series([-1], dtype="uint64")
     Traceback (most recent call last):
         ...
     OverflowError: Trying to coerce negative values to unsigned integers
 
     Also, if you try to coerce float values to integers, it raises:
 
-    >>> Series([1, 2, 3.5], dtype="int64")
+    >>> pd.Series([1, 2, 3.5], dtype="int64")
     Traceback (most recent call last):
         ...
     ValueError: Trying to coerce float values to integers
     """
-
     try:
         if not hasattr(arr, "astype"):
             casted = np.array(arr, dtype=dtype, copy=copy)

pandas/core/dtypes/common.py

@@ -1,4 +1,7 @@
-""" common type operations """
+"""
+Common type operations.
+"""
+
 from typing import Any, Callable, Union
 import warnings
 
@@ -705,7 +708,7 @@ def is_dtype_equal(source, target) -> bool:
     False
     >>> is_dtype_equal(CategoricalDtype(), "category")
     True
-    >>> is_dtype_equal(DatetimeTZDtype(), "datetime64")
+    >>> is_dtype_equal(DatetimeTZDtype(tz="UTC"), "datetime64")
     False
     """
 
@@ -862,7 +865,7 @@ def is_signed_integer_dtype(arr_or_dtype) -> bool:
     True
     >>> is_signed_integer_dtype('Int8')
     True
-    >>> is_signed_dtype(pd.Int8Dtype)
+    >>> is_signed_integer_dtype(pd.Int8Dtype)
     True
     >>> is_signed_integer_dtype(np.datetime64)
     False
@@ -994,7 +997,7 @@ def is_datetime64_any_dtype(arr_or_dtype) -> bool:
 
     Returns
     -------
-    boolean
+    bool
         Whether or not the array or dtype is of the datetime64 dtype.
 
     Examples
@@ -1011,13 +1014,11 @@ def is_datetime64_any_dtype(arr_or_dtype) -> bool:
     False
     >>> is_datetime64_any_dtype(np.array([1, 2]))
     False
-    >>> is_datetime64_any_dtype(np.array([], dtype=np.datetime64))
+    >>> is_datetime64_any_dtype(np.array([], dtype="datetime64[ns]"))
     True
-    >>> is_datetime64_any_dtype(pd.DatetimeIndex([1, 2, 3],
-                                dtype=np.datetime64))
+    >>> is_datetime64_any_dtype(pd.DatetimeIndex([1, 2, 3], dtype="datetime64[ns]"))
     True
     """
-
     if arr_or_dtype is None:
         return False
     return is_datetime64_dtype(arr_or_dtype) or is_datetime64tz_dtype(arr_or_dtype)
@@ -1034,7 +1035,7 @@ def is_datetime64_ns_dtype(arr_or_dtype) -> bool:
 
     Returns
     -------
-    boolean
+    bool
         Whether or not the array or dtype is of the datetime64[ns] dtype.
 
     Examples
@@ -1051,16 +1052,13 @@ def is_datetime64_ns_dtype(arr_or_dtype) -> bool:
     False
     >>> is_datetime64_ns_dtype(np.array([1, 2]))
     False
-    >>> is_datetime64_ns_dtype(np.array([], dtype=np.datetime64))  # no unit
+    >>> is_datetime64_ns_dtype(np.array([], dtype="datetime64"))  # no unit
     False
-    >>> is_datetime64_ns_dtype(np.array([],
-                               dtype="datetime64[ps]"))  # wrong unit
+    >>> is_datetime64_ns_dtype(np.array([], dtype="datetime64[ps]"))  # wrong unit
     False
-    >>> is_datetime64_ns_dtype(pd.DatetimeIndex([1, 2, 3],
-                               dtype=np.datetime64))  # has 'ns' unit
+    >>> is_datetime64_ns_dtype(pd.DatetimeIndex([1, 2, 3], dtype="datetime64[ns]"))
     True
     """
-
     if arr_or_dtype is None:
         return False
     try:
@@ -1240,7 +1238,8 @@ def is_datetimelike_v_numeric(a, b):
 
     Examples
     --------
-    >>> dt = np.datetime64(pd.datetime(2017, 1, 1))
+    >>> from datetime import datetime
+    >>> dt = np.datetime64(datetime(2017, 1, 1))
     >>>
     >>> is_datetimelike_v_numeric(1, 1)
     False

pandas/core/dtypes/concat.py

@@ -1,5 +1,5 @@
 """
-Utility functions related to concat
+Utility functions related to concat.
 """
 
 import numpy as np
@@ -261,6 +261,8 @@ def union_categoricals(
     >>> a = pd.Categorical(["a", "b"], ordered=True)
     >>> b = pd.Categorical(["a", "b", "c"], ordered=True)
     >>> union_categoricals([a, b])
+    Traceback (most recent call last):
+        ...
     TypeError: to union ordered Categoricals, all categories must be the same
 
     New in version 0.20.0

pandas/core/dtypes/dtypes.py

@@ -1,4 +1,7 @@
-""" define extension dtypes """
+"""
+Define extension dtypes.
+"""
+
 import re
 from typing import Any, Dict, List, MutableMapping, Optional, Tuple, Type, Union, cast
 
@@ -286,23 +289,27 @@ def _from_values_or_dtype(
 
         Examples
         --------
-        >>> CategoricalDtype._from_values_or_dtype()
+        >>> pd.CategoricalDtype._from_values_or_dtype()
         CategoricalDtype(categories=None, ordered=None)
-        >>> CategoricalDtype._from_values_or_dtype(categories=['a', 'b'],
-        ...                                        ordered=True)
+        >>> pd.CategoricalDtype._from_values_or_dtype(
+        ...     categories=['a', 'b'], ordered=True
+        ... )
         CategoricalDtype(categories=['a', 'b'], ordered=True)
-        >>> dtype1 = CategoricalDtype(['a', 'b'], ordered=True)
-        >>> dtype2 = CategoricalDtype(['x', 'y'], ordered=False)
-        >>> c = Categorical([0, 1], dtype=dtype1, fastpath=True)
-        >>> CategoricalDtype._from_values_or_dtype(c, ['x', 'y'], ordered=True,
-        ...                                        dtype=dtype2)
+        >>> dtype1 = pd.CategoricalDtype(['a', 'b'], ordered=True)
+        >>> dtype2 = pd.CategoricalDtype(['x', 'y'], ordered=False)
+        >>> c = pd.Categorical([0, 1], dtype=dtype1, fastpath=True)
+        >>> pd.CategoricalDtype._from_values_or_dtype(
+        ...     c, ['x', 'y'], ordered=True, dtype=dtype2
+        ... )
+        Traceback (most recent call last):
+            ...
         ValueError: Cannot specify `categories` or `ordered` together with
         `dtype`.
 
         The supplied dtype takes precedence over values' dtype:
 
-        >>> CategoricalDtype._from_values_or_dtype(c, dtype=dtype2)
-        CategoricalDtype(['x', 'y'], ordered=False)
+        >>> pd.CategoricalDtype._from_values_or_dtype(c, dtype=dtype2)
+        CategoricalDtype(categories=['x', 'y'], ordered=False)
         """
         from pandas.core.dtypes.common import is_categorical
 

pandas/core/dtypes/inference.py

@@ -117,7 +117,8 @@ def is_file_like(obj) -> bool:
 
     Examples
     --------
-    >>> buffer(StringIO("data"))
+    >>> import io
+    >>> buffer = io.StringIO("data")
     >>> is_file_like(buffer)
     True
     >>> is_file_like([1, 2, 3])
@@ -311,6 +312,7 @@ def is_named_tuple(obj) -> bool:
 
     Examples
     --------
+    >>> from collections import namedtuple
     >>> Point = namedtuple("Point", ["x", "y"])
     >>> p = Point(1, 2)
     >>>
@@ -339,6 +341,7 @@ def is_hashable(obj) -> bool:
 
     Examples
     --------
+    >>> import collections
     >>> a = ([],)
     >>> isinstance(a, collections.abc.Hashable)
     True

pandas/core/frame.py

@@ -2933,12 +2933,12 @@ def __setitem__(self, key, value):
             # set column
             self._set_item(key, value)
 
-    def _setitem_slice(self, key, value):
+    def _setitem_slice(self, key: slice, value):
         # NB: we can't just use self.loc[key] = value because that
         #  operates on labels and we need to operate positional for
         #  backwards-compat, xref GH#31469
         self._check_setitem_copy()
-        self.loc._setitem_with_indexer(key, value)
+        self.iloc._setitem_with_indexer(key, value)
 
     def _setitem_array(self, key, value):
         # also raises Exception if object array with NA values
@@ -2950,7 +2950,7 @@ def _setitem_array(self, key, value):
             key = check_bool_indexer(self.index, key)
             indexer = key.nonzero()[0]
             self._check_setitem_copy()
-            self.loc._setitem_with_indexer(indexer, value)
+            self.iloc._setitem_with_indexer(indexer, value)
         else:
             if isinstance(value, DataFrame):
                 if len(value.columns) != len(key):
@@ -2962,7 +2962,7 @@ def _setitem_array(self, key, value):
                     key, axis=1, raise_missing=False
                 )[1]
                 self._check_setitem_copy()
-                self.loc._setitem_with_indexer((slice(None), indexer), value)
+                self.iloc._setitem_with_indexer((slice(None), indexer), value)
 
     def _setitem_frame(self, key, value):
         # support boolean setting with DataFrame input, e.g.

pandas/core/groupby/groupby.py

@@ -2336,7 +2336,8 @@ def shift(self, periods=1, freq=None, axis=0, fill_value=None):
         ----------
         periods : int, default 1
             Number of periods to shift.
-        freq : frequency string
+        freq : str, optional
+            Frequency string
         axis : axis to shift, default 0
         fill_value : optional