Validate operand, parametrized tests, whatnew

GH21220

Author: KalyanGokhale

doc/source/whatsnew/v0.23.1.txt

@@ -16,6 +16,7 @@ New features
 ~~~~~~~~~~~~
 
 - :meth:`Index.droplevel` is now implemented also for flat indexes, for compatibility with MultiIndex (:issue:`21115`)
+- :func: merge now allows  a ``DataFrame`` and a ``Series`` with a name as inputs (:issue:`21220`)
 
 
 .. _whatsnew_0231.deprecations:

pandas/core/reshape/merge.py

@@ -492,10 +492,8 @@ def __init__(self, left, right, how='inner', on=None,
                  left_index=False, right_index=False, sort=True,
                  suffixes=('_x', '_y'), copy=True, indicator=False,
                  validate=None):
-        if isinstance(left, Series):
-            left = left.to_frame()
-        if isinstance(right, Series):
-            right = right.to_frame()
+        left = validate_operand(left)
+        right = validate_operand(right)
         self.left = self.orig_left = left
         self.right = self.orig_right = right
         self.how = how
@@ -522,13 +520,6 @@ def __init__(self, left, right, how='inner', on=None,
             raise ValueError(
                 'indicator option can only accept boolean or string arguments')
 
-        if not isinstance(left, DataFrame):
-            raise ValueError('can not merge DataFrame with instance of '
-                             'type {left}'.format(left=type(left)))
-        if not isinstance(right, DataFrame):
-            raise ValueError('can not merge DataFrame with instance of '
-                             'type {right}'.format(right=type(right)))
-
         if not is_bool(left_index):
             raise ValueError(
                 'left_index parameter must be of type bool, not '
@@ -1643,3 +1634,16 @@ def _should_fill(lname, rname):
 
 def _any(x):
     return x is not None and com._any_not_none(*x)
+
+
+def validate_operand(obj):
+    if isinstance(obj, DataFrame):
+        return obj
+    elif isinstance(obj, Series):
+        if obj.name is None:
+            raise ValueError('Cannot merge a Series without a name')
+        else:
+            return obj.to_frame()
+    else:
+        raise ValueError('Cannot merge a DataFrame or a Series with '
+                         'instance of type {obj}'.format(obj=type(obj)))

pandas/tests/reshape/merge/test_merge.py

@@ -1866,22 +1866,40 @@ def test_merge_index_types(index):
     assert_frame_equal(result, expected)
 
 
-def test_merge_series():
+@pytest.mark.parametrize("on,left_on,right_on,left_index,right_index,nms,nm", [
+                         (['outer', 'inner'], None, None, False, False,
+                          ['outer', 'inner'], 'B'),
+                         (None, None, None, True, True, ['outer', 'inner'],
+                          'B'),
+                         (None, ['outer', 'inner'], None, False, True, None,
+                          'B'),
+                         (None, None, ['outer', 'inner'], True, False, None,
+                          'B'),
+                         (['outer', 'inner'], None, None, False, False,
+                          ['outer', 'inner'], None),
+                         (None, None, None, True, True, ['outer', 'inner'],
+                          None),
+                         (None, ['outer', 'inner'], None, False, True, None,
+                          None),
+                         (None, None, ['outer', 'inner'], True, False, None,
+                          None),
+                         ])
+def test_merge_series(on, left_on, right_on, left_index, right_index, nms, nm):
     # GH 21220
     a = pd.DataFrame({"A": [1, 2, 3, 4]},
                      index=pd.MultiIndex.from_product([['a', 'b'], [0, 1]],
                      names=['outer', 'inner']))
     b = pd.Series([1, 2, 3, 4],
                   index=pd.MultiIndex.from_product([['a', 'b'], [1, 2]],
-                  names=['outer', 'inner']), name='B')
+                  names=['outer', 'inner']), name=nm)
     expected = pd.DataFrame({"A": [2, 4], "B": [1, 3]},
                             index=pd.MultiIndex.from_product([['a', 'b'], [1]],
-                            names=['outer', 'inner']))
-
-    # Test merge with a DataFrame and a Series 'converted-to-DataFrame' object
-    result = pd.merge(a, b.to_frame(), on=['outer', 'inner'])
-    tm.assert_frame_equal(result, expected)
-
-    # Test merge with a DataFrame and a Series object
-    result = pd.merge(a, b, on=['outer', 'inner'])
-    tm.assert_frame_equal(result, expected)
+                            names=nms))
+    if nm is not None:
+        result = pd.merge(a, b, on=on, left_on=left_on, right_on=right_on,
+                          left_index=left_index, right_index=right_index)
+        tm.assert_frame_equal(result, expected)
+    else:
+        with tm.assert_raises_regex(ValueError, 'a Series without a name'):
+            result = pd.merge(a, b, on=on, left_on=left_on, right_on=right_on,
+                              left_index=left_index, right_index=right_index)