BUG: right merge not preserve row order (#27453)

doc/source/whatsnew/v1.0.0.rst

@@ -274,6 +274,7 @@ New repr for :class:`~pandas.arrays.IntervalArray`
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 - :class:`pandas.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)
+- :class:`pandas.core.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)
 
 *pandas 0.25.x*
 
@@ -292,6 +293,32 @@ New repr for :class:`~pandas.arrays.IntervalArray`
 
    pd.arrays.IntervalArray.from_tuples([(0, 1), (2, 3)])
 
+- :meth:`DataFrame.merge` now preserves right frame's row order when executing a right merge (:issue:`27453`)
+
+.. ipython:: python
+
+    left_df = pd.DataFrame({"colors": ["blue", "red"]}, index=pd.Index([0, 1]))
+    right_df = pd.DataFrame({"hats": ["small", "big"]}, index=pd.Index([1, 0]))
+
+*pandas 0.25.x*
+
+.. ipython:: python
+    left_df.merge(right_df, left_index=True, right_index=True, how="right")
+        colors   hats
+    0    blue    big
+    1     red  small
+
+
+*pandas 1.0.0*
+
+.. ipython:: python
+
+    left_df.merge(right_df, left_index=True, right_index=True, how="right")
+      colors   hats
+    1    red  small
+    0   blue    big
+
+
 
 All :class:`SeriesGroupBy` aggregation methods now respect the ``observed`` keyword
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -949,6 +976,7 @@ Reshaping
 - Bug in :func:`melt` where supplying mixed strings and numeric values for ``id_vars`` or ``value_vars`` would incorrectly raise a ``ValueError`` (:issue:`29718`)
 - Dtypes are now preserved when transposing a ``DataFrame`` where each column is the same extension dtype (:issue:`30091`)
 - Bug in :func:`merge_asof` merging on a tz-aware ``left_index`` and ``right_on`` a tz-aware column (:issue:`29864`)
+- :meth:`DataFrame.merge` now preserves right frame's row order when executing a right merge (:issue:`27453`)
 -
 
 Sparse

pandas/core/reshape/merge.py

@@ -566,10 +566,10 @@ def __init__(
         indicator: bool = False,
         validate=None,
     ):
-        _left = _validate_operand(left)
-        _right = _validate_operand(right)
-        self.left = self.orig_left = _left
-        self.right = self.orig_right = _right
+        left = validate_operand(left)
+        right = validate_operand(right)
+        self.left = self.orig_left = left
+        self.right = self.orig_right = right
         self.how = how
         self.axis = axis
 
@@ -1301,6 +1301,9 @@ def _get_join_indexers(
         right_keys
     ), "left_key and right_keys must be the same length"
 
+    # bind `sort` arg. of _factorize_keys
+    fkeys = partial(_factorize_keys, sort=sort)
+
     # get left & right join labels and num. of levels at each location
     mapped = (
         _factorize_keys(left_keys[n], right_keys[n], sort=sort)
@@ -1315,15 +1318,20 @@ def _get_join_indexers(
     # factorize keys to a dense i8 space
     # `count` is the num. of unique keys
     # set(lkey) | set(rkey) == range(count)
-    lkey, rkey, count = _factorize_keys(lkey, rkey, sort=sort)
 
+    # flip left and right keys if performing a right merge
+    # to preserve right merge row order (GH 27453)
+    if how == "right":
+        factorized_rkey, factorized_lkey, count = fkeys(rkey, lkey)
+    else:
+        factorized_lkey, factorized_rkey, count = fkeys(lkey, rkey)
     # preserve left frame order if how == 'left' and sort == False
     kwargs = copy.copy(kwargs)
     if how == "left":
         kwargs["sort"] = sort
     join_func = _join_functions[how]
 
-    return join_func(lkey, rkey, count, **kwargs)
+    return join_func(factorized_lkey, factorized_rkey, count, **kwargs)
 
 
 def _restore_dropped_levels_multijoin(

pandas/tests/reshape/merge/test_merge.py

@@ -1289,17 +1289,17 @@ def test_merge_on_index_with_more_values(self, how, index, expected_index):
         # GH 24212
         # pd.merge gets [0, 1, 2, -1, -1, -1] as left_indexer, ensure that
         # -1 is interpreted as a missing value instead of the last element
-        df1 = pd.DataFrame({"a": [1, 2, 3], "key": [0, 2, 2]}, index=index)
-        df2 = pd.DataFrame({"b": [1, 2, 3, 4, 5]})
+        df1 = pd.DataFrame({"a": [0, 1, 2], "key": [0, 1, 2]}, index=index)
+        df2 = pd.DataFrame({"b": [0, 1, 2, 3, 4, 5]})
         result = df1.merge(df2, left_on="key", right_index=True, how=how)
         expected = pd.DataFrame(
             [
-                [1.0, 0, 1],
-                [2.0, 2, 3],
-                [3.0, 2, 3],
-                [np.nan, 1, 2],
-                [np.nan, 3, 4],
-                [np.nan, 4, 5],
+                [0, 0, 0],
+                [1, 1, 1],
+                [2, 2, 2],
+                [np.nan, 3, 3],
+                [np.nan, 4, 4],
+                [np.nan, 5, 5],
             ],
             columns=["a", "key", "b"],
         )
@@ -2153,3 +2153,35 @@ def test_merge_multiindex_columns():
     expected["id"] = ""
 
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize("how", ["left", "right"])
+def test_merge_preserves_row_order(how):
+    # GH 27453
+    population = [
+        ("Jenn", "Jamaica", 3),
+        ("Beth", "Bulgaria", 7),
+        ("Carl", "Canada", 30),
+    ]
+    columns = ["name", "country", "population"]
+    population_df = DataFrame(population, columns=columns)
+
+    people = [("Abe", "America"), ("Beth", "Bulgaria"), ("Carl", "Canada")]
+    columns = ["name", "country"]
+    people_df = DataFrame(people, columns=columns)
+
+    expected_data = [
+        ("Abe", "America", np.nan),
+        ("Beth", "Bulgaria", 7),
+        ("Carl", "Canada", 30),
+    ]
+    expected_cols = ["name", "country", "population"]
+    expected = DataFrame(expected_data, columns=expected_cols)
+
+    if how == "right":
+        left_df, right_df = population_df, people_df
+    elif how == "left":
+        left_df, right_df = people_df, population_df
+
+    result = left_df.merge(right_df, on=("name", "country"), how=how)
+    assert_frame_equal(expected, result)