cleanups

Author: topper-123

doc/source/whatsnew/v0.25.0.rst

@@ -65,7 +65,7 @@ Performance Improvements
 - Significant speedup in `SparseArray` initialization that benefits most operations, fixing performance regression introduced in v0.20.0 (:issue:`24985`)
 - `DataFrame.to_stata()` is now faster when outputting data with any string or non-native endian columns (:issue:`25045`)
 - Improved performance of :meth:`Series.searchsorted`. The speedup is especially large when the dtype is
- int8/int16/int32 and the searched key is within the integer bounds for the dtype(:issue:`22034`)
+ int8/int16/int32 and the searched key is within the integer bounds for the dtype (:issue:`22034`)
 
 
 .. _whatsnew_0250.bug_fixes:

pandas/core/algorithms.py

@@ -1734,24 +1734,25 @@ def searchsorted(arr, value, side="left", sorter=None):
 
  .. versionadded:: 0.25.0
 
- Find the indices into a sorted array `self` (a) such that, if the
+ Find the indices into a sorted array `arr` (a) such that, if the
  corresponding elements in `value` were inserted before the indices,
- the order of `self` would be preserved.
+ the order of `arr` would be preserved.
 
- Assuming that `self` is sorted:
+ Assuming that `arr` is sorted:
 
  ====== ================================
  `side` returned index `i` satisfies
  ====== ================================
- left ``self[i-1] < value <= self[i]``
- right ``self[i-1] <= value < self[i]``
+ left ``arr[i-1] < value <= self[i]``
+ right ``arr[i-1] <= value < self[i]``
  ====== ================================
 
  Parameters
  ----------
- arr: numpy.array or ExtensionArray
- array to search in. Cannot be Index, Series or PandasArray, as that
- would cause a RecursionError.
+ arr: array-like
+ Input array. If `sorter` is None, then it must be sorted in
+ ascending order, otherwise `sorter` must be an array of indices
+ that sort it.
  value : array_like
  Values to insert into `arr`.
  side : {'left', 'right'}, optional

pandas/tests/arrays/test_array.py

@@ -285,9 +285,15 @@ def test_searchsorted_numeric_dtypes_vector(self, any_real_dtype):
  expected = np.array([1, 2], dtype=np.intp)
  tm.assert_numpy_array_equal(result, expected)
 
- def test_search_sorted_datetime64_scalar(self):
- arr = pd.array(pd.date_range('20120101', periods=10, freq='2D'))
- val = pd.Timestamp('20120102')
+ @pytest.mark.parametrize('arr, val', [
+ [pd.date_range('20120101', periods=10, freq='2D'),
+ pd.Timestamp('20120102')],
+ [pd.date_range('20120101', periods=10, freq='2D', tz='Asia/Hong_Kong'),
+ pd.Timestamp('20120102', tz='Asia/Hong_Kong')],
+ [pd.timedelta_range(start='1 day', end='10 days', periods=10),
+ pd.Timedelta('2 days')]])
+ def test_search_sorted_datetime64_scalar(self, arr, val):
+ arr = pd.array(arr)
  result = arr.searchsorted(val)
  assert is_scalar(result)
  assert result == 1