Optimising Series.nunique for Nan values pandas-dev#40865 (pandas-dev…

…#41236)
ricoyudog · May 3, 2021 · c61e66e · c61e66e
1 parent 6b57a69
commit c61e66e
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 3 deletions.
diff --git a/asv_bench/benchmarks/frame_methods.py b/asv_bench/benchmarks/frame_methods.py
@@ -563,6 +563,14 @@ def time_frame_nunique(self):
         self.df.nunique()
 
 
+class SeriesNuniqueWithNan:
+    def setup(self):
+        self.ser = Series(100000 * (100 * [np.nan] + list(range(100)))).astype(float)
+
+    def time_series_nunique_nan(self):
+        self.ser.nunique()
+
+
 class Duplicated:
     def setup(self):
         n = 1 << 20

diff --git a/doc/source/whatsnew/v1.3.0.rst b/doc/source/whatsnew/v1.3.0.rst
@@ -665,7 +665,7 @@ Performance improvements
 - Performance improvement in the conversion of pyarrow boolean array to a pandas nullable boolean array (:issue:`41051`)
 - Performance improvement for concatenation of data with type :class:`CategoricalDtype` (:issue:`40193`)
 - Performance improvement in :meth:`.GroupBy.cummin` and :meth:`.GroupBy.cummax` with nullable data types (:issue:`37493`)
--
+- Performance improvement in :meth:`Series.nunique` with nan values (:issue:`40865`)
 
 .. ---------------------------------------------------------------------------
 

diff --git a/pandas/core/base.py b/pandas/core/base.py
@@ -1041,8 +1041,10 @@ def nunique(self, dropna: bool = True) -> int:
         >>> s.nunique()
         4
         """
-        obj = remove_na_arraylike(self) if dropna else self
-        return len(obj.unique())
+        uniqs = self.unique()
+        if dropna:
+            uniqs = remove_na_arraylike(uniqs)
+        return len(uniqs)
 
     @property
     def is_unique(self) -> bool: