PERF: Add var to masked arrays

doc/source/whatsnew/v1.6.0.rst

@@ -103,6 +103,7 @@ Performance improvements
 - Performance improvement in :meth:`.GroupBy.median` for nullable dtypes (:issue:`37493`)
 - Performance improvement in :meth:`.GroupBy.mean` and :meth:`.GroupBy.var` for extension array dtypes (:issue:`37493`)
 - Performance improvement for :meth:`MultiIndex.unique` (:issue:`48335`)
+- Performance improvement in ``var`` for nullable dtypes (:issue:`48379`).
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/array_algos/masked_reductions.py

@@ -22,6 +22,7 @@ def _reductions(
     skipna: bool = True,
     min_count: int = 0,
     axis: int | None = None,
+    **kwargs,
 ):
     """
     Sum, mean or product for 1D masked array.
@@ -45,14 +46,14 @@ def _reductions(
         if mask.any(axis=axis) or check_below_min_count(values.shape, None, min_count):
             return libmissing.NA
         else:
-            return func(values, axis=axis)
+            return func(values, axis=axis, **kwargs)
     else:
         if check_below_min_count(values.shape, mask, min_count) and (
             axis is None or values.ndim == 1
         ):
             return libmissing.NA
 
-        return func(values, where=~mask, axis=axis)
+        return func(values, where=~mask, axis=axis, **kwargs)
 
 
 def sum(
@@ -149,3 +150,19 @@ def mean(
     if not values.size or mask.all():
         return libmissing.NA
     return _reductions(np.mean, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def var(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: int | None = None,
+    ddof: int = 1,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+
+    return _reductions(
+        np.var, values=values, mask=mask, skipna=skipna, axis=axis, **{"ddof": ddof}
+    )

pandas/core/arrays/masked.py

@@ -1037,7 +1037,7 @@ def _quantile(
     # Reductions
 
     def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
-        if name in {"any", "all", "min", "max", "sum", "prod", "mean"}:
+        if name in {"any", "all", "min", "max", "sum", "prod", "mean", "var"}:
             return getattr(self, name)(skipna=skipna, **kwargs)
 
         data = self._data
@@ -1115,6 +1115,19 @@ def mean(self, *, skipna=True, axis: int | None = 0, **kwargs):
             "mean", result, skipna=skipna, axis=axis, **kwargs
         )
 
+    def var(self, *, skipna=True, axis: int | None = 0, ddof: int = 1, **kwargs):
+        nv.validate_stat_ddof_func((), kwargs, fname="var")
+        result = masked_reductions.var(
+            self._data,
+            self._mask,
+            skipna=skipna,
+            axis=axis,
+            ddof=ddof,
+        )
+        return self._wrap_reduction_result(
+            "var", result, skipna=skipna, axis=axis, **kwargs
+        )
+
     def min(self, *, skipna=True, axis: int | None = 0, **kwargs):
         nv.validate_min((), kwargs)
         return masked_reductions.min(

pandas/tests/reductions/test_reductions.py

@@ -696,7 +696,7 @@ def test_empty_multi(self, method, unit):
         expected = Series([1, np.nan], index=["a", "b"])
         tm.assert_series_equal(result, expected)
 
-    @pytest.mark.parametrize("method", ["mean"])
+    @pytest.mark.parametrize("method", ["mean", "var"])
     @pytest.mark.parametrize("dtype", ["Float64", "Int64", "boolean"])
     def test_ops_consistency_on_empty_nullable(self, method, dtype):
 
@@ -787,6 +787,15 @@ def test_mean_masked_overflow(self):
         assert result_masked - result_numpy == 0
         assert result_masked == 1e17
 
+    def test_var_masked_array(self):
+        # GH#48379
+        ser = Series([1, 2, 3, 4, 5], dtype="Int64")
+        ser_numpy_dtype = Series([1, 2, 3, 4, 5], dtype="int64")
+        result = ser.var()
+        result_numpy_dtype = ser_numpy_dtype.var()
+        assert result == result_numpy_dtype
+        assert result == 2.5
+
     @pytest.mark.parametrize("dtype", ("m8[ns]", "m8[ns]", "M8[ns]", "M8[ns, UTC]"))
     @pytest.mark.parametrize("skipna", [True, False])
     def test_empty_timeseries_reductions_return_nat(self, dtype, skipna):