Issue with ks.merge to Series

databricks/koalas/frame.py

@@ -5093,33 +5093,34 @@ def merge(self, right: 'DataFrame', how: str = 'inner',
         Parameters
         ----------
         right: Object to merge with.
+            DataFrame or named Series
         how: Type of merge to be performed.
             {'left', 'right', 'outer', 'inner'}, default 'inner'
 
-            left: use only keys from left frame, similar to a SQL left outer join; preserve key
-                order.
-            right: use only keys from right frame, similar to a SQL right outer join; preserve key
-                order.
-            outer: use union of keys from both frames, similar to a SQL full outer join; sort keys
-                lexicographically.
-            inner: use intersection of keys from both frames, similar to a SQL inner join;
-                preserve the order of the left keys.
-        on: Column or index level names to join on. These must be found in both DataFrames. If on
-            is None and not merging on indexes then this defaults to the intersection of the
+            left: use only keys from left frame, similar to a SQL left outer join;
+                preserve key order.
+            right: use only keys from right frame, similar to a SQL right outer join;
+                preserve key order.
+            outer: use union of keys from both frames, similar to a SQL full outer
+                join; sort keys lexicographically.
+            inner: use intersection of keys from both frames, similar to a SQL inner
+                join; preserve the order of the left keys.
+        on: Column or index level names to join on.
+            These must be found in both DataFrames. If on is None and not merging on
+            indexes then this defaults to the intersection of the
             columns in both DataFrames.
-        left_on: Column or index level names to join on in the left DataFrame. Can also
-            be an array or list of arrays of the length of the left DataFrame.
+        left_on: Column or index level names to join on in the left DataFrame.
+            Can also be an array or list of arrays of the length of the left DataFrame.
             These arrays are treated as if they are columns.
-        right_on: Column or index level names to join on in the right DataFrame. Can also
-            be an array or list of arrays of the length of the right DataFrame.
+        right_on: Column or index level names to join on in the right DataFrame.
+            Can also be an array or list of arrays of the length of the right DataFrame.
             These arrays are treated as if they are columns.
-        left_index: Use the index from the left DataFrame as the join key(s). If it is a
-            MultiIndex, the number of keys in the other DataFrame (either the index or a number of
-            columns) must match the number of levels.
-        right_index: Use the index from the right DataFrame as the join key. Same caveats as
-            left_index.
-        suffixes: Suffix to apply to overlapping column names in the left and right side,
-            respectively.
+        left_index: Use the index from the left DataFrame as the join key(s).
+            If it is a MultiIndex, the number of keys in the other DataFrame (either the
+            index or a number of columns) must match the number of levels.
+        right_index: Use the index from the right DataFrame as the join key.
+            Same caveats as left_index.
+        suffixes: Suffix to apply to overlapping column names in the left and right side, respectively.
 
         Returns
         -------

databricks/koalas/tests/test_dataframe.py

@@ -16,6 +16,7 @@
 
 from datetime import date, datetime
 import inspect
+from distutils.version import LooseVersion
 
 import numpy as np
 import pandas as pd
@@ -767,21 +768,23 @@ def check(op, right_kdf=right_kdf, right_pdf=right_pdf):
                                              suffixes=['_left', '_right']))
 
         # Test Series on the right
-        check(lambda left, right: left.merge(right), right_ks, right_ps)
-        check(lambda left, right: left.merge(right, left_on='x', right_on='x'),
-              right_ks, right_ps)
-        check(lambda left, right: left.set_index('x').merge(right, left_index=True, right_on='x'),
-              right_ks, right_ps)
-
-        # Test join types with Series
-        for how in ['inner', 'left', 'right', 'outer']:
-            check(lambda left, right: left.merge(right, how=how), right_ks, right_ps)
-            check(lambda left, right: left.merge(right, left_on='x', right_on='x', how=how),
+        # pd.DataFrame.merge with Series is implemented since version 0.24.0
+        if LooseVersion(pd.__version__) > LooseVersion("0.24.2"):
+            check(lambda left, right: left.merge(right), right_ks, right_ps)
+            check(lambda left, right: left.merge(right, left_on='x', right_on='x'),
+                  right_ks, right_ps)
+            check(lambda left, right: left.set_index('x').merge(right, left_index=True, right_on='x'),
                   right_ks, right_ps)
 
-        # suffix
-        check(lambda left, right: left.merge(right, suffixes=['_left', '_right'], how='outer',
-                                             left_index=True, right_index=True), right_ks, right_ps)
+            # Test join types with Series
+            for how in ['inner', 'left', 'right', 'outer']:
+                check(lambda left, right: left.merge(right, how=how), right_ks, right_ps)
+                check(lambda left, right: left.merge(right, left_on='x', right_on='x', how=how),
+                      right_ks, right_ps)
+
+            # suffix with Series
+            check(lambda left, right: left.merge(right, suffixes=['_left', '_right'], how='outer',
+                                                 left_index=True, right_index=True), right_ks, right_ps)
 
     def test_merge_retains_indices(self):
         left_pdf = pd.DataFrame({'A': [0, 1]})
@@ -1029,11 +1032,15 @@ def test_join(self):
 
         self.assert_eq(join_pdf, join_kdf)
 
-        # join with duplicated columns in Series and DataFrame
+        # join with duplicated columns in Series
         with self.assertRaisesRegex(ValueError,
                                     "columns overlap but no suffix specified"):
             kdf1.join(ks1, how='outer')
+        # join with duplicated columns in DataFrame
+        with self.assertRaisesRegex(ValueError,
+                                    "columns overlap but no suffix specified"):
             kdf1.join(kdf2, how='outer')
+
         # check `on` parameter
         join_pdf = pdf1.join(pdf2.set_index('key'), on='key', lsuffix='_left', rsuffix='_right')
         join_pdf.sort_values(by=list(join_pdf.columns), inplace=True)