ENH/PERF: add ExtensionArray.duplicated

asv_bench/benchmarks/algorithms.py

@@ -72,7 +72,16 @@ class Duplicated:
     params = [
         [True, False],
         ["first", "last", False],
-        ["int", "uint", "float", "string", "datetime64[ns]", "datetime64[ns, tz]"],
+        [
+            "int",
+            "uint",
+            "float",
+            "string",
+            "datetime64[ns]",
+            "datetime64[ns, tz]",
+            "timestamp[ms][pyarrow]",
+            "duration[s][pyarrow]",
+        ],
     ]
     param_names = ["unique", "keep", "dtype"]
 
@@ -87,6 +96,12 @@ def setup(self, unique, keep, dtype):
             "datetime64[ns, tz]": pd.date_range(
                 "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
             ),
+            "timestamp[ms][pyarrow]": pd.Index(
+                np.arange(N), dtype="timestamp[ms][pyarrow]"
+            ),
+            "duration[s][pyarrow]": pd.Index(
+                np.arange(N), dtype="duration[s][pyarrow]"
+            ),
         }[dtype]
         if not unique:
             data = data.repeat(5)

doc/source/whatsnew/v2.2.0.rst

@@ -239,6 +239,7 @@ Performance improvements
 - Performance improvement in :meth:`DataFrame.groupby` when aggregating pyarrow timestamp and duration dtypes (:issue:`55031`)
 - Performance improvement in :meth:`DataFrame.sort_index` and :meth:`Series.sort_index` when indexed by a :class:`MultiIndex` (:issue:`54835`)
 - Performance improvement in :meth:`Index.difference` (:issue:`55108`)
+- Performance improvement in :meth:`Series.duplicated` for pyarrow timestamp and duration dtypes (:issue:`55255`)
 - Performance improvement when indexing with more than 4 keys (:issue:`54550`)
 - Performance improvement when localizing time to UTC (:issue:`55241`)
 

pandas/core/algorithms.py

@@ -1000,9 +1000,13 @@ def duplicated(
     duplicated : ndarray[bool]
     """
     if hasattr(values, "dtype"):
-        if isinstance(values.dtype, ArrowDtype) and values.dtype.kind in "ifub":
-            values = values._to_masked()  # type: ignore[union-attr]
-
+        if isinstance(values.dtype, ArrowDtype):
+            if values.dtype.kind in "ifub":
+                values = values._to_masked()  # type: ignore[union-attr]
+            else:
+                values = (
+                    values._maybe_convert_datelike_array()  # type: ignore[union-attr]
+                )
         if isinstance(values.dtype, BaseMaskedDtype):
             values = cast("BaseMaskedArray", values)
             return htable.duplicated(values._data, keep=keep, mask=values._mask)