BUG: DataFrame sort_values and multiple "by" columns fails to order NaT correctly

closes #16836

Author: Jean-Mathieu Deschenes <[email protected]>

This patch had conflicts when merged, resolved by
Committer: Jeff Reback <[email protected]>

Closes #16995 from jdeschenes/datetime_sort_issues and squashes the following commits:

257e10a [Jean-Mathieu Deschenes] Changes requested by @jreback
c6d55e2 [Jean-Mathieu Deschenes] Fix for #16836

Author: Jean-Mathieu Deschenes

doc/source/whatsnew/v0.21.0.txt

@@ -648,6 +648,7 @@ Reshaping
 - :func:`Series.argmin`, :func:`Series.argmax`, and their counterparts on ``DataFrame`` and groupby objects work correctly with floating point data that contains infinite values (:issue:`13595`).
 - Bug in :func:`unique` where checking a tuple of strings raised a ``TypeError`` (:issue:`17108`)
 - Bug in :func:`concat` where order of result index was unpredictable if it contained non-comparable elements (:issue:`17344`)
+- Fixes regression when sorting by multiple columns on a ``datetime64`` dtype ``Series`` with ``NaT`` values (:issue:`16836`)
 
 Numeric
 ^^^^^^^

pandas/core/frame.py

@@ -3453,18 +3453,13 @@ def sort_values(self, by, axis=0, ascending=True, inplace=False,
         if len(by) > 1:
             from pandas.core.sorting import lexsort_indexer
 
-            def trans(v):
-                if needs_i8_conversion(v):
-                    return v.view('i8')
-                return v
-
             keys = []
             for x in by:
                 k = self.xs(x, axis=other_axis).values
                 if k.ndim == 2:
                     raise ValueError('Cannot sort by duplicate column %s' %
                                      str(x))
-                keys.append(trans(k))
+                keys.append(k)
             indexer = lexsort_indexer(keys, orders=ascending,
                                       na_position=na_position)
             indexer = _ensure_platform_int(indexer)

pandas/tests/frame/test_sorting.py

@@ -269,6 +269,11 @@ def test_sort_datetimes(self):
         df2 = df.sort_values(by=['B'])
         assert_frame_equal(df1, df2)
 
+        df1 = df.sort_values(by='B')
+
+        df2 = df.sort_values(by=['C', 'B'])
+        assert_frame_equal(df1, df2)
+
     def test_frame_column_inplace_sort_exception(self):
         s = self.frame['A']
         with tm.assert_raises_regex(ValueError, "This Series is a view"):
@@ -321,7 +326,29 @@ def test_sort_nat_values_in_int_column(self):
         assert_frame_equal(df_sorted, df_reversed)
 
         df_sorted = df.sort_values(["datetime", "float"], na_position="last")
-        assert_frame_equal(df_sorted, df_reversed)
+        assert_frame_equal(df_sorted, df)
+
+        # Ascending should not affect the results.
+        df_sorted = df.sort_values(["datetime", "float"], ascending=False)
+        assert_frame_equal(df_sorted, df)
+
+    def test_sort_nat(self):
+
+        # GH 16836
+
+        d1 = [Timestamp(x) for x in ['2016-01-01', '2015-01-01',
+                                     np.nan, '2016-01-01']]
+        d2 = [Timestamp(x) for x in ['2017-01-01', '2014-01-01',
+                                     '2016-01-01', '2015-01-01']]
+        df = pd.DataFrame({'a': d1, 'b': d2}, index=[0, 1, 2, 3])
+
+        d3 = [Timestamp(x) for x in ['2015-01-01', '2016-01-01',
+                                     '2016-01-01', np.nan]]
+        d4 = [Timestamp(x) for x in ['2014-01-01', '2015-01-01',
+                                     '2017-01-01', '2016-01-01']]
+        expected = pd.DataFrame({'a': d3, 'b': d4}, index=[1, 3, 0, 2])
+        sorted_df = df.sort_values(by=['a', 'b'], )
+        tm.assert_frame_equal(sorted_df, expected)
 
 
 class TestDataFrameSortIndexKinds(TestData):