improve performance of Series.searchsorted

Author: tp

asv_bench/benchmarks/series_methods.py

@@ -124,6 +124,25 @@ 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):
 
     params = ['dict', 'Series']

doc/source/whatsnew/v0.25.0.rst

@@ -60,7 +60,8 @@ 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`)
 
 
 .. _whatsnew_0250.bug_fixes:

pandas/core/series.py

@@ -2390,9 +2390,11 @@ def __rmatmul__(self, other):
     def searchsorted(self, value, side='left', sorter=None):
         if sorter is not None:
             sorter = ensure_platform_int(sorter)
-        result = 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
 
+        result = self._values.searchsorted(value, side=side, sorter=sorter)
         return result[0] if is_scalar(value) else result
 
     # -------------------------------------------------------------------