improve performance of Series.searchsorted

Author: tp

asv_bench/benchmarks/series_methods.py

@@ -130,6 +130,25 @@ def time_dropna(self, dtype):
         self.s.dropna()
 
 
+class SearchSorted(object):
+
+    goal_time = 0.2
+    params = ['int8', 'int16', 'int32', 'int64',
+              'uint8', 'uint16', 'uint32', 'uint64',
+              'float16', 'float32', 'float64',
+              'str']
+    param_names = ['dtype']
+
+    def setup(self, dtype):
+        N = 10**5
+        data = np.array([1] * N + [2] * N + [3] * N).astype(dtype)
+        self.s = Series(data)
+
+    def time_searchsorted(self, dtype):
+        key = '2' if dtype == 'str' else 2
+        self.s.searchsorted(key)
+
+
 class Map(object):
 
     goal_time = 0.2

doc/source/whatsnew/v0.24.0.txt

@@ -499,7 +499,8 @@ Performance Improvements
 - Very large improvement in performance of slicing when the index is a :class:`CategoricalIndex`,
   both when indexing by label (using .loc) and position(.iloc).
   Likewise, slicing a ``CategoricalIndex`` itself (i.e. ``ci[100:200]``) shows similar speed improvements (:issue:`21659`)
-- Improved performance of :func:`Series.describe` in case of numeric dtpyes (:issue:`21274`)
+- Improved performance of :func:`Series.searchsorted` (:issue:`22034`)
+- Improved performance of :func:`Series.describe` in case of numeric dtypes (:issue:`21274`)
 - Improved performance of :func:`pandas.core.groupby.GroupBy.rank` when dealing with tied rankings (:issue:`21237`)
 - Improved performance of :func:`DataFrame.set_index` with columns consisting of :class:`Period` objects (:issue:`21582`,:issue:`21606`)
 - Improved performance of membership checks in :class:`Categorical` and :class:`CategoricalIndex`

pandas/core/series.py

@@ -2082,8 +2082,11 @@ def __rmatmul__(self, other):
     def searchsorted(self, value, side='left', sorter=None):
         if sorter is not None:
             sorter = ensure_platform_int(sorter)
-        return self._values.searchsorted(Series(value)._values,
-                                         side=side, sorter=sorter)
+        if not is_extension_type(self._values):
+            value = np.asarray(value, dtype=self._values.dtype)
+            value = value[..., np.newaxis] if value.ndim == 0 else value
+
+        return self._values.searchsorted(value, side=side, sorter=sorter)
 
     # -------------------------------------------------------------------
     # Combination