BUG: fixed formatting and small linting issues

Author: Jacob Austin

doc/source/whatsnew/v1.0.0.rst

@@ -125,6 +125,8 @@ Other enhancements
 - Roundtripping DataFrames with nullable integer or string data types to parquet
   (:meth:`~DataFrame.to_parquet` / :func:`read_parquet`) using the `'pyarrow'` engine
   now preserve those data types with pyarrow >= 1.0.0 (:issue:`20612`).
+- :meth:`DataFrame.sort_values`, :meth:`DataFrame.sort_index`, :meth:`Series.sort_index`, and :meth:`Series.sort_index`
+   now support the ``key`` argument which allows for custom sorting orders (:issue:`3942`)
 
 Build Changes
 ^^^^^^^^^^^^^

pandas/core/arrays/categorical.py

@@ -1603,7 +1603,7 @@ def argsort(self, ascending=True, kind="quicksort", *args, **kwargs):
         """
         return super().argsort(ascending=ascending, kind=kind, *args, **kwargs)
 
-    def sort_values(self, inplace=False, ascending=True, na_position="last"):
+    def sort_values(self, inplace=False, ascending=True, na_position="last", key=None):
         """
         Sort the Categorical by category value returning a new
         Categorical by default.
@@ -1682,7 +1682,9 @@ def sort_values(self, inplace=False, ascending=True, na_position="last"):
             msg = "invalid na_position: {na_position!r}"
             raise ValueError(msg.format(na_position=na_position))
 
-        sorted_idx = nargsort(self, ascending=ascending, na_position=na_position)
+        sorted_idx = nargsort(
+            self, ascending=ascending, na_position=na_position, key=key
+        )
 
         if inplace:
             self._codes = self._codes[sorted_idx]

pandas/core/frame.py

@@ -15,6 +15,7 @@
 import sys
 from textwrap import dedent
 from typing import (
+    Callable,
     FrozenSet,
     Hashable,
     Iterable,
@@ -25,7 +26,6 @@
     Tuple,
     Type,
     Union,
-    Callable
 )
 import warnings
 
@@ -4724,15 +4724,15 @@ def f(vals):
 
     @Substitution(**_shared_doc_kwargs)
     @Appender(NDFrame.sort_values.__doc__)
-    def sort_values(
+    def sort_values(  # type: ignore
         self,
         by,
         axis=0,
         ascending=True,
         inplace=False,
         kind="quicksort",
         na_position="last",
-        key : Union[Callable, None] = None
+        key: Optional[Callable] = None,
     ):
         inplace = validate_bool_kwarg(inplace, "inplace")
         axis = self._get_axis_number(axis)
@@ -4747,7 +4747,9 @@ def sort_values(
             from pandas.core.sorting import lexsort_indexer
 
             keys = [self._get_label_or_level_values(x, axis=axis) for x in by]
-            indexer = lexsort_indexer(keys, orders=ascending, na_position=na_position, key=key)
+            indexer = lexsort_indexer(
+                keys, orders=ascending, na_position=na_position, key=key
+            )
             indexer = ensure_platform_int(indexer)
         else:
             from pandas.core.sorting import nargsort
@@ -4773,7 +4775,7 @@ def sort_values(
 
     @Substitution(**_shared_doc_kwargs)
     @Appender(NDFrame.sort_index.__doc__)
-    def sort_index(
+    def sort_index(  # type: ignore
         self,
         axis=0,
         level=None,
@@ -4783,7 +4785,7 @@ def sort_index(
         na_position="last",
         sort_remaining=True,
         by=None,
-        key : Union[Callable, None] = None
+        key: Optional[Callable] = None,
     ):
 
         # TODO: this can be combined with Series.sort_index impl as

pandas/core/indexes/base.py

@@ -1,8 +1,7 @@
 from datetime import datetime
 import operator
 from textwrap import dedent
-
-from typing import FrozenSet, Union, Callable
+from typing import Callable, FrozenSet, Optional, Union
 import warnings
 
 import numpy as np
@@ -4425,7 +4424,9 @@ def asof_locs(self, where, mask):
 
         return result
 
-    def sort_values(self, return_indexer=False, ascending=True, key : Callable = None):
+    def sort_values(
+        self, return_indexer=False, ascending=True, key: Optional[Callable] = None
+    ):
         """
         Return a sorted copy of the index.
 
@@ -4439,7 +4440,7 @@ def sort_values(self, return_indexer=False, ascending=True, key : Callable = Non
         ascending : bool, default True
             Should the index values be sorted in an ascending order.
         key : Callable, default None
-            Apply a key function to the indices before sorting, like 
+            Apply a key function to the indices before sorting, like
             built-in sorted function.
 
         Returns

pandas/core/indexes/datetimelike.py

@@ -2,7 +2,7 @@
 Base and utility classes for tseries type pandas objects.
 """
 import operator
-from typing import Set
+from typing import Callable, Optional, Set
 import warnings
 
 import numpy as np
@@ -279,19 +279,26 @@ def map(self, mapper, na_action=None):
         except Exception:
             return self.astype(object).map(mapper)
 
-    def sort_values(self, return_indexer=False, ascending=True):
+    def sort_values(
+        self, return_indexer=False, ascending=True, key: Optional[Callable] = None
+    ):
         """
         Return sorted copy of Index.
         """
+        if key:
+            idx = self.map(key, na_action="ignore")
+        else:
+            idx = self
+
         if return_indexer:
-            _as = self.argsort()
+            _as = idx.argsort()
             if not ascending:
                 _as = _as[::-1]
             sorted_index = self.take(_as)
             return sorted_index, _as
         else:
-            sorted_values = np.sort(self._ndarray_values)
-            attribs = self._get_attributes_dict()
+            sorted_values = np.sort(idx._ndarray_values)
+            attribs = self._get_attributes_dict()  # type: ignore
             freq = attribs["freq"]
 
             if freq is not None and not is_period_dtype(self):
@@ -304,7 +311,7 @@ def sort_values(self, return_indexer=False, ascending=True):
             if not ascending:
                 sorted_values = sorted_values[::-1]
 
-            return self._simple_new(sorted_values, **attribs)
+            return self._simple_new(sorted_values, **attribs)  # type: ignore
 
     @Appender(_index_shared_docs["take"] % _index_doc_kwargs)
     def take(self, indices, axis=0, allow_fill=True, fill_value=None, **kwargs):

pandas/core/series.py

@@ -2883,14 +2883,14 @@ def update(self, other):
     # ----------------------------------------------------------------------
     # Reindexing, sorting
 
-    def sort_values(
+    def sort_values(  # type: ignore
         self,
         axis=0,
         ascending=True,
         inplace=False,
         kind="quicksort",
         na_position="last",
-        key: Callable = None
+        key: Optional[Callable] = None,
     ):
         """
         Sort by the values.
@@ -3081,7 +3081,7 @@ def _try_kind_sort(arr):
         else:
             return result.__finalize__(self)
 
-    def sort_index(
+    def sort_index(  # type: ignore
         self,
         axis=0,
         level=None,
@@ -3090,7 +3090,7 @@ def sort_index(
         kind="quicksort",
         na_position="last",
         sort_remaining=True,
-        key : Callable = None
+        key: Optional[Callable] = None,
     ):
         """
         Sort Series by index labels.

pandas/core/sorting.py

@@ -1,5 +1,5 @@
 """ miscellaneous sorting / groupby utilities """
-from typing import Callable, Union
+from typing import Callable, Optional
 
 import numpy as np
 
@@ -189,7 +189,8 @@ def indexer_from_factorized(labels, shape, compress: bool = True):
     return get_group_index_sorter(ids, ngroups)
 
 
-def lexsort_indexer(keys, orders=None, na_position="last", key : Union[Callable, None] = None):
+def lexsort_indexer(keys, orders=None, na_position="last", key=None):
+
     from pandas.core.arrays import Categorical
 
     labels = []
@@ -239,7 +240,13 @@ def lexsort_indexer(keys, orders=None, na_position="last", key : Union[Callable,
     return indexer_from_factorized(labels, shape)
 
 
-def nargsort(items, kind="quicksort", ascending=True, na_position="last", key: Union[Callable, None] = None):
+def nargsort(
+    items,
+    kind="quicksort",
+    ascending: bool = True,
+    na_position="last",
+    key: Optional[Callable] = None,
+):
     """
     This is intended to be a drop-in replacement for np.argsort which
     handles NaNs. It adds ascending and na_position parameters.
@@ -260,9 +267,11 @@ def nargsort(items, kind="quicksort", ascending=True, na_position="last", key: U
         if masked.size == 0:
             vals = np.array([])  # vectorize fails on empty object arrays
         else:
-            vals = np.asarray(key_func(masked))   # revert from masked
+            vals = np.asarray(key_func(masked))  # revert from masked
 
-        return nargsort(vals, kind=kind, ascending=ascending, na_position=na_position, key=None)
+        return nargsort(
+            vals, kind=kind, ascending=ascending, na_position=na_position, key=None
+        )
 
     idx = np.arange(len(items))
     non_nans = items[~mask]

pandas/tests/frame/test_sorting.py

@@ -81,7 +81,7 @@ def test_sort_values(self):
         with pytest.raises(ValueError, match=msg):
             frame.sort_values(by=["A", "B"], axis=0, ascending=[True] * 5)
 
-    @pytest.fixture(params=[None, lambda x : x])
+    @pytest.fixture(params=[None, lambda x: x])
     def key(self, request):
         return request.param
 
@@ -93,22 +93,22 @@ def test_sort_values_inplace(self, key):
         sorted_df = frame.copy()
         sorted_df.sort_values(by="A", inplace=True, key=key)
         expected = frame.sort_values(by="A", key=key)
-        assert_frame_equal(sorted_df, expected)
+        tm.assert_frame_equal(sorted_df, expected)
 
         sorted_df = frame.copy()
         sorted_df.sort_values(by=1, axis=1, inplace=True, key=key)
         expected = frame.sort_values(by=1, axis=1, key=key)
-        assert_frame_equal(sorted_df, expected)
+        tm.assert_frame_equal(sorted_df, expected)
 
         sorted_df = frame.copy()
         sorted_df.sort_values(by="A", ascending=False, inplace=True, key=key)
         expected = frame.sort_values(by="A", ascending=False, key=key)
-        assert_frame_equal(sorted_df, expected)
+        tm.assert_frame_equal(sorted_df, expected)
 
         sorted_df = frame.copy()
         sorted_df.sort_values(by=["A", "B"], ascending=False, inplace=True, key=key)
         expected = frame.sort_values(by=["A", "B"], ascending=False, key=key)
-        assert_frame_equal(sorted_df, expected)
+        tm.assert_frame_equal(sorted_df, expected)
 
     def test_sort_nan(self):
         # GH3917
@@ -256,15 +256,20 @@ def test_sort_multi_index_key(self):
         df = DataFrame(
             {"a": [3, 1, 2], "b": [0, 0, 0], "c": [0, 1, 2], "d": list("abc")}
         )
-        result = df.set_index(list("abc")).sort_index(level=list("ba"), key=lambda x : x[0])
+        result = df.set_index(list("abc")).sort_index(
+            level=list("ba"), key=lambda x: x[0]
+        )
 
         expected = DataFrame(
             {"a": [1, 2, 3], "b": [0, 0, 0], "c": [1, 2, 0], "d": list("bca")}
         )
         expected = expected.set_index(list("abc"))
         tm.assert_frame_equal(result, expected)
 
-        result = df.set_index(list("abc")).sort_index(level=list("ba"), key=lambda x : x[2])
+        result = df.set_index(list("abc")).sort_index(
+            level=list("ba"), key=lambda x: x[2]
+        )
+
         expected = df.set_index(list("abc"))
         tm.assert_frame_equal(result, expected)
 
@@ -594,63 +599,63 @@ def test_sort_index_key(self):
 
         result = df.sort_index()
         expected = df.iloc[[2, 3, 0, 1, 5, 4]]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
         result = df.sort_index(key=str.lower)
         expected = df.iloc[[0, 1, 5, 2, 3, 4]]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
         result = df.sort_index(key=str.lower, ascending=False)
         expected = df.iloc[[4, 2, 3, 0, 1, 5]]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.parametrize('dtype', ['int8', 'int16', 'int32', 'int64', 'float32', 'float64'])
+    @pytest.mark.parametrize("dtype", ["int8", "int64", "float64"])
     def test_sort_index_key_int(self, dtype):
         df = DataFrame(np.arange(6, dtype=dtype), index=np.arange(6, dtype=dtype))
 
         result = df.sort_index()
-        assert_frame_equal(result, df)
+        tm.assert_frame_equal(result, df)
 
-        result = df.sort_index(key=lambda x : -x)
+        result = df.sort_index(key=lambda x: -x)
         expected = df.sort_index(ascending=False)
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
-        result = df.sort_index(key=lambda x : 2 * x)
-        assert_frame_equal(result, df)
+        result = df.sort_index(key=lambda x: 2 * x)
+        tm.assert_frame_equal(result, df)
 
     def test_sort_value_key(self):
         df = DataFrame(np.array([0, 5, np.nan, 3, 2, np.nan]))
 
         result = df.sort_values(0)
         expected = df.iloc[[0, 4, 3, 1, 2, 5]]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
-        result = df.sort_values(0, key=lambda x : x + 5)
+        result = df.sort_values(0, key=lambda x: x + 5)
         expected = df.iloc[[0, 4, 3, 1, 2, 5]]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
-        result = df.sort_values(0, key=lambda x : -x, ascending=False)
+        result = df.sort_values(0, key=lambda x: -x, ascending=False)
         expected = df.iloc[[0, 4, 3, 1, 2, 5]]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
     def test_sort_value_key_nan(self):
         df = DataFrame(np.array([["hello", "goodbye"], ["hello", "Hello"]]))
 
         result = df.sort_values(1)
         expected = df[::-1]
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
         result = df.sort_values([0, 1], key=str.lower)
-        assert_frame_equal(result, df)
+        tm.assert_frame_equal(result, df)
 
         result = df.sort_values([0, 1], key=str.lower, ascending=False)
         expected = df.sort_values(1, key=str.lower, ascending=False)
-        assert_frame_equal(result, expected)
+        tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.parametrize('key', [None, lambda x : x])
+    @pytest.mark.parametrize("key", [None, lambda x: x])
     def test_sort_value_key_empty(self, key):
         df = DataFrame(np.array([]))
- 
+
         df.sort_values(0, key=key)
         df.sort_index(key=key)