fix tz-aware unique

Author: jreback

doc/source/whatsnew/v0.20.0.txt

@@ -563,6 +563,58 @@ result. On the other hand, this might have backward incompatibilities: e.g.
 compared to numpy arrays, ``Index`` objects are not mutable. To get the original
 ndarray, you can always convert explicitly using ``np.asarray(idx.hour)``.
 
+.. _whatsnew_0200.api_breaking.unique:
+
+pd.unique will now be consistent with extension types
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+In prior versions, using ``Series.unique()`` and ``pd.unique(Series)`` on ``Categorical`` and tz-aware datatypes would yield different return types. These are now consistent to return the extension type.
+
+Previous behaviour:
+
+Datetime tz-aware
+
+.. code-block:: ipython
+
+   In [5]: Series(pd.Index([pd.Timestamp('20160101', tz='US/Eastern'),
+                            pd.Timestamp('20160101', tz='US/Eastern')])).unique()
+   Out[5]: array([Timestamp('2016-01-01 00:00:00-0500', tz='US/Eastern')], dtype=object)
+
+   In [7]: pd.unique(Series(pd.Index([pd.Timestamp('20160101', tz='US/Eastern'),
+                                      pd.Timestamp('20160101', tz='US/Eastern')])))
+   Out[7]: array(['2016-01-01T05:00:00.000000000'], dtype='datetime64[ns]')
+
+Categoricals
+
+.. code-block:: ipython
+
+
+   In [1]: pd.Series(pd.Categorical(list('aabc'))).unique()
+   Out[1]:
+   [a, b, c]
+   Categories (3, object): [a, b, c]
+
+   In [2]: pd.unique(pd.Series(pd.Categorical(list('aabc'))).unique())
+   Out[2]: array(['a', 'b', 'c'], dtype=object)
+
+New Behavior:
+
+Datetime tz-aware
+
+.. ipython:: python
+
+   Series(pd.Index([pd.Timestamp('20160101', tz='US/Eastern'),
+                    pd.Timestamp('20160101', tz='US/Eastern')])).unique()
+   pd.unique(Series(pd.Index([pd.Timestamp('20160101', tz='US/Eastern'),
+                              pd.Timestamp('20160101', tz='US/Eastern')])))
+
+Categoricals
+
+.. ipython:: python
+
+   pd.Series(pd.Categorical(list('aabc'))).unique()
+   pd.unique(pd.Series(pd.Categorical(list('aabc'))).unique())
+
 .. _whatsnew_0200.api_breaking.s3:
 
 S3 File Handling

pandas/core/algorithms.py

@@ -278,8 +278,10 @@ def unique(values):
 
     Returns
     -------
-    unique values. The returned type will be a pandas Index
-    if a pandas type is input, otherwise ndarray
+    unique values.
+    - If the input is a Categorical dtype, the return is a Categorical
+    - If the input is an Index, the return is an Index
+    - If the input is a Series/ndarray, the return will be an ndarray
 
     Examples
     --------
@@ -293,6 +295,11 @@ def unique(values):
     ...                   pd.Timestamp('20160101')]))
     array(['2016-01-01T00:00:00.000000000'], dtype='datetime64[ns]')
 
+    >>> pd.unique(pd.Series([pd.Timestamp('20160101', tz='US/Eastern'),
+    ...                      pd.Timestamp('20160101', tz='US/Eastern')]))
+    array([Timestamp('2016-01-01 00:00:00-0500', tz='US/Eastern')],
+          dtype=object)
+
     >>> pd.unique(pd.Index([pd.Timestamp('20160101', tz='US/Eastern'),
     ...                     pd.Timestamp('20160101', tz='US/Eastern')]))
     DatetimeIndex(['2016-01-01 00:00:00-05:00'],
@@ -309,6 +316,7 @@ def unique(values):
     Categories (3, object): [a, b, c]
 
     """
+
     values = _ensure_arraylike(values)
 
     # categorical is a fast-path
@@ -326,6 +334,13 @@ def unique(values):
     uniques = table.unique(values)
     uniques = _reconstruct_data(uniques, dtype, original)
 
+    if isinstance(original, ABCSeries) and is_datetime64tz_dtype(dtype):
+        # we are special casing datetime64tz_dtype
+        # to return an object array of tz-aware Timestamps
+
+        # TODO: it must return DatetimeArray with tz in pandas 2.0
+        uniques = uniques.asobject.values
+
     return uniques
 
 

pandas/core/base.py

@@ -873,6 +873,7 @@ def unique(self):
         else:
             from pandas.core.algorithms import unique1d
             result = unique1d(values)
+
         return result
 
     def nunique(self, dropna=True):

pandas/core/series.py

@@ -1204,10 +1204,14 @@ def mode(self):
     @Appender(base._shared_docs['unique'] % _shared_doc_kwargs)
     def unique(self):
         result = super(Series, self).unique()
+
         if is_datetime64tz_dtype(self.dtype):
-            # to return array of Timestamp with tz
-            # ToDo: it must return DatetimeArray with tz in pandas 2.0
-            return result.asobject.values
+            # we are special casing datetime64tz_dtype
+            # to return an object array of tz-aware Timestamps
+
+            # TODO: it must return DatetimeArray with tz in pandas 2.0
+            result = result.asobject.values
+
         return result
 
     @Appender(base._shared_docs['drop_duplicates'] % _shared_doc_kwargs)

pandas/tests/test_algos.py

@@ -401,6 +401,7 @@ def test_categorical(self):
 
     def test_datetime64tz_aware(self):
         # GH 15939
+
         result = Series(
             pd.Index([Timestamp('20160101', tz='US/Eastern'),
                       Timestamp('20160101', tz='US/Eastern')])).unique()
@@ -417,9 +418,9 @@ def test_datetime64tz_aware(self):
         result = pd.unique(
             Series(pd.Index([Timestamp('20160101', tz='US/Eastern'),
                              Timestamp('20160101', tz='US/Eastern')])))
-        expected = DatetimeIndex(['2016-01-01 00:00:00'],
-                                 dtype='datetime64[ns, US/Eastern]', freq=None)
-        tm.assert_index_equal(result, expected)
+        expected = np.array([Timestamp('2016-01-01 00:00:00-0500',
+                                       tz='US/Eastern')], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
 
         result = pd.unique(pd.Index([Timestamp('20160101', tz='US/Eastern'),
                                      Timestamp('20160101', tz='US/Eastern')]))