Merge pull request #80 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

pandas/core/base.py

@@ -927,16 +927,17 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
         nv.validate_max(args, kwargs)
         return nanops.nanmax(self._values, skipna=skipna)
 
+    @doc(op="max", oppose="min", value="largest")
     def argmax(self, axis=None, skipna=True, *args, **kwargs):
         """
-        Return int position of the largest value in the Series.
+        Return int position of the {value} value in the Series.
 
-        If the maximum is achieved in multiple locations,
+        If the {op}imum is achieved in multiple locations,
         the first row position is returned.
 
         Parameters
         ----------
-        axis : {None}
+        axis : {{None}}
             Dummy argument for consistency with Series.
         skipna : bool, default True
             Exclude NA/null values when showing the result.
@@ -946,21 +947,22 @@ def argmax(self, axis=None, skipna=True, *args, **kwargs):
         Returns
         -------
         int
-            Row position of the maximum values.
+            Row position of the {op}imum value.
 
         See Also
         --------
-        numpy.ndarray.argmax : Equivalent method for numpy arrays.
-        Series.argmin : Similar method, but returning the minimum.
+        Series.arg{op} : Return position of the {op}imum value.
+        Series.arg{oppose} : Return position of the {oppose}imum value.
+        numpy.ndarray.arg{op} : Equivalent method for numpy arrays.
         Series.idxmax : Return index label of the maximum values.
         Series.idxmin : Return index label of the minimum values.
 
         Examples
         --------
         Consider dataset containing cereal calories
 
-        >>> s = pd.Series({'Corn Flakes': 100.0, 'Almond Delight': 110.0,
-        ...                'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0})
+        >>> s = pd.Series({{'Corn Flakes': 100.0, 'Almond Delight': 110.0,
+        ...                'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0}})
         >>> s
         Corn Flakes              100.0
         Almond Delight           110.0
@@ -970,8 +972,11 @@ def argmax(self, axis=None, skipna=True, *args, **kwargs):
 
         >>> s.argmax()
         2
+        >>> s.argmin()
+        0
 
-        The maximum cereal calories is in the third element,
+        The maximum cereal calories is the third element and
+        the minimum cereal calories is the first element,
         since series is zero-indexed.
         """
         nv.validate_minmax_axis(axis)
@@ -1019,25 +1024,8 @@ def min(self, axis=None, skipna=True, *args, **kwargs):
         nv.validate_min(args, kwargs)
         return nanops.nanmin(self._values, skipna=skipna)
 
+    @doc(argmax, op="min", oppose="max", value="smallest")
     def argmin(self, axis=None, skipna=True, *args, **kwargs):
-        """
-        Return a ndarray of the minimum argument indexer.
-
-        Parameters
-        ----------
-        axis : {None}
-            Dummy argument for consistency with Series.
-        skipna : bool, default True
-
-        Returns
-        -------
-        numpy.ndarray
-
-        See Also
-        --------
-        numpy.ndarray.argmin : Return indices of the minimum values along
-            the given axis.
-        """
         nv.validate_minmax_axis(axis)
         nv.validate_argmax_with_skipna(skipna, args, kwargs)
         return nanops.nanargmin(self._values, skipna=skipna)

pandas/core/frame.py

@@ -890,7 +890,7 @@ def style(self) -> "Styler":
         """
 
     @Appender(_shared_docs["items"])
-    def items(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
+    def items(self) -> Iterable[Tuple[Label, Series]]:
         if self.columns.is_unique and hasattr(self, "_item_cache"):
             for k in self.columns:
                 yield k, self._get_item_cache(k)
@@ -899,10 +899,10 @@ def items(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
                 yield k, self._ixs(i, axis=1)
 
     @Appender(_shared_docs["items"])
-    def iteritems(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
+    def iteritems(self) -> Iterable[Tuple[Label, Series]]:
         yield from self.items()
 
-    def iterrows(self) -> Iterable[Tuple[Optional[Hashable], Series]]:
+    def iterrows(self) -> Iterable[Tuple[Label, Series]]:
         """
         Iterate over DataFrame rows as (index, Series) pairs.
 
@@ -4043,7 +4043,7 @@ def set_index(
             "one-dimensional arrays."
         )
 
-        missing: List[Optional[Hashable]] = []
+        missing: List[Label] = []
         for col in keys:
             if isinstance(
                 col, (ABCIndexClass, ABCSeries, np.ndarray, list, abc.Iterator)
@@ -4082,7 +4082,7 @@ def set_index(
             else:
                 arrays.append(self.index)
 
-        to_remove: List[Optional[Hashable]] = []
+        to_remove: List[Label] = []
         for col in keys:
             if isinstance(col, ABCMultiIndex):
                 for n in range(col.nlevels):
@@ -4137,7 +4137,7 @@ def reset_index(
         drop: bool = False,
         inplace: bool = False,
         col_level: Hashable = 0,
-        col_fill: Optional[Hashable] = "",
+        col_fill: Label = "",
     ) -> Optional["DataFrame"]:
         """
         Reset the index, or a level of it.

pandas/core/generic.py

@@ -9729,7 +9729,7 @@ def describe_1d(data):
 
         ldesc = [describe_1d(s) for _, s in data.items()]
         # set a convenient order for rows
-        names: List[Optional[Hashable]] = []
+        names: List[Label] = []
         ldesc_indexes = sorted((x.index for x in ldesc), key=len)
         for idxnames in ldesc_indexes:
             for name in idxnames:

pandas/core/indexes/base.py

@@ -1,7 +1,7 @@
 from datetime import datetime
 import operator
 from textwrap import dedent
-from typing import TYPE_CHECKING, Any, FrozenSet, Hashable, Optional, Union
+from typing import TYPE_CHECKING, Any, FrozenSet, Hashable, Union
 import warnings
 
 import numpy as np
@@ -2163,7 +2163,7 @@ def dropna(self, how="any"):
 
         Returns
         -------
-        valid : Index
+        Index
         """
         if how not in ("any", "all"):
             raise ValueError(f"invalid how option: {how}")
@@ -5546,7 +5546,7 @@ def default_index(n):
     return RangeIndex(0, n, name=None)
 
 
-def maybe_extract_name(name, obj, cls) -> Optional[Hashable]:
+def maybe_extract_name(name, obj, cls) -> Label:
     """
     If no name is passed, then extract it from data, validating hashability.
     """

pandas/core/reshape/concat.py

@@ -2,11 +2,11 @@
 Concat routines.
 """
 
-from typing import Hashable, Iterable, List, Mapping, Optional, Union, overload
+from typing import Iterable, List, Mapping, Union, overload
 
 import numpy as np
 
-from pandas._typing import FrameOrSeriesUnion
+from pandas._typing import FrameOrSeriesUnion, Label
 
 from pandas.core.dtypes.generic import ABCDataFrame, ABCSeries
 
@@ -32,7 +32,7 @@
 
 @overload
 def concat(
-    objs: Union[Iterable["DataFrame"], Mapping[Optional[Hashable], "DataFrame"]],
+    objs: Union[Iterable["DataFrame"], Mapping[Label, "DataFrame"]],
     axis=0,
     join: str = "outer",
     ignore_index: bool = False,
@@ -48,9 +48,7 @@ def concat(
 
 @overload
 def concat(
-    objs: Union[
-        Iterable[FrameOrSeriesUnion], Mapping[Optional[Hashable], FrameOrSeriesUnion]
-    ],
+    objs: Union[Iterable[FrameOrSeriesUnion], Mapping[Label, FrameOrSeriesUnion]],
     axis=0,
     join: str = "outer",
     ignore_index: bool = False,
@@ -65,9 +63,7 @@ def concat(
 
 
 def concat(
-    objs: Union[
-        Iterable[FrameOrSeriesUnion], Mapping[Optional[Hashable], FrameOrSeriesUnion]
-    ],
+    objs: Union[Iterable[FrameOrSeriesUnion], Mapping[Label, FrameOrSeriesUnion]],
     axis=0,
     join="outer",
     ignore_index: bool = False,
@@ -536,7 +532,7 @@ def _get_concat_axis(self) -> Index:
                 idx = ibase.default_index(len(self.objs))
                 return idx
             elif self.keys is None:
-                names: List[Optional[Hashable]] = [None] * len(self.objs)
+                names: List[Label] = [None] * len(self.objs)
                 num = 0
                 has_names = False
                 for i, x in enumerate(self.objs):

pandas/core/series.py

@@ -692,11 +692,7 @@ def __array_ufunc__(
         inputs = tuple(extract_array(x, extract_numpy=True) for x in inputs)
         result = getattr(ufunc, method)(*inputs, **kwargs)
 
-        name: Label
-        if len(set(names)) == 1:
-            name = names[0]
-        else:
-            name = None
+        name = names[0] if len(set(names)) == 1 else None
 
         def construct_return(result):
             if lib.is_scalar(result):

pandas/core/strings.py

@@ -572,7 +572,7 @@ def str_replace(arr, pat, repl, n=-1, case=None, flags=0, regex=True):
     r"""
     Replace occurrences of pattern/regex in the Series/Index with
     some other string. Equivalent to :meth:`str.replace` or
-    :func:`re.sub`.
+    :func:`re.sub`, depending on the regex value.
 
     Parameters
     ----------

pandas/core/tools/numeric.py

@@ -35,6 +35,7 @@ def to_numeric(arg, errors="raise", downcast=None):
     Parameters
     ----------
     arg : scalar, list, tuple, 1-d array, or Series
+        Argument to be converted.
     errors : {'ignore', 'raise', 'coerce'}, default 'raise'
         - If 'raise', then invalid parsing will raise an exception.
         - If 'coerce', then invalid parsing will be set as NaN.
@@ -61,7 +62,8 @@ def to_numeric(arg, errors="raise", downcast=None):
 
     Returns
     -------
-    ret : numeric if parsing succeeded.
+    ret
+        Numeric if parsing succeeded.
         Return type depends on input.  Series if Series, otherwise ndarray.
 
     See Also

pandas/io/excel/_base.py

@@ -1,5 +1,5 @@
 import abc
-from datetime import date, datetime, timedelta
+import datetime
 from io import BytesIO
 import os
 from textwrap import fill
@@ -28,7 +28,6 @@
     _pop_header_name,
     get_writer,
 )
-from pandas.io.formats.printing import pprint_thing
 from pandas.io.parsers import TextParser
 
 _read_excel_doc = (
@@ -742,11 +741,11 @@ def _value_with_fmt(self, val):
             val = float(val)
         elif is_bool(val):
             val = bool(val)
-        elif isinstance(val, datetime):
+        elif isinstance(val, datetime.datetime):
             fmt = self.datetime_format
-        elif isinstance(val, date):
+        elif isinstance(val, datetime.date):
             fmt = self.date_format
-        elif isinstance(val, timedelta):
+        elif isinstance(val, datetime.timedelta):
             val = val.total_seconds() / float(86400)
             fmt = "0"
         else:
@@ -763,9 +762,7 @@ def check_extension(cls, ext):
         if ext.startswith("."):
             ext = ext[1:]
         if not any(ext in extension for extension in cls.supported_extensions):
-            msg = "Invalid extension for engine"
-            f"'{pprint_thing(cls.engine)}': '{pprint_thing(ext)}'"
-            raise ValueError(msg)
+            raise ValueError(f"Invalid extension for engine '{cls.engine}': '{ext}'")
         else:
             return True
 

pandas/io/pytables.py

@@ -8,17 +8,7 @@
 import itertools
 import os
 import re
-from typing import (
-    TYPE_CHECKING,
-    Any,
-    Dict,
-    Hashable,
-    List,
-    Optional,
-    Tuple,
-    Type,
-    Union,
-)
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Type, Union
 import warnings
 
 import numpy as np
@@ -27,7 +17,7 @@
 
 from pandas._libs import lib, writers as libwriters
 from pandas._libs.tslibs import timezones
-from pandas._typing import ArrayLike, FrameOrSeries
+from pandas._typing import ArrayLike, FrameOrSeries, Label
 from pandas.compat._optional import import_optional_dependency
 from pandas.errors import PerformanceWarning
 from pandas.util._decorators import cache_readonly
@@ -2811,7 +2801,7 @@ def read_multi_index(
 
         levels = []
         codes = []
-        names: List[Optional[Hashable]] = []
+        names: List[Label] = []
         for i in range(nlevels):
             level_key = f"{key}_level{i}"
             node = getattr(self.group, level_key)
@@ -2976,7 +2966,7 @@ class SeriesFixed(GenericFixed):
     pandas_kind = "series"
     attributes = ["name"]
 
-    name: Optional[Hashable]
+    name: Label
 
     @property
     def shape(self):