Implement Index.drop_duplicates

databricks/koalas/indexes.py

@@ -390,6 +390,40 @@ def fillna(self, value):
         result = DataFrame(self._kdf._internal.copy(sdf=sdf)).index
         return result
 
+    # TODO: ADD keep parameter
+    def drop_duplicates(self):
+        """
+        Return Index with duplicate values removed.
+
+        Returns
+        -------
+        deduplicated : Index
+
+        See Also
+        --------
+        Series.drop_duplicates : Equivalent method on Series.
+        DataFrame.drop_duplicates : Equivalent method on DataFrame.
+
+        Examples
+        --------
+        Generate an pandas.Index with duplicate values.
+
+        >>> idx = ks.Index(['lama', 'cow', 'lama', 'beetle', 'lama', 'hippo'])
+
+        >>> idx.drop_duplicates() # doctest: +SKIP
+        Index(['lama', 'cow', 'beetle', 'hippo'], dtype='object')
+        """
+        kdf = self._kdf.copy()
+        sdf = kdf._internal.sdf.select(self._internal.index_scols).drop_duplicates()
+        internal = _InternalFrame(sdf=sdf, index_map=self._internal.index_map)
+        result = DataFrame(internal).index
+
+        if isinstance(self, MultiIndex):
+            result.names = self.names
+        else:
+            result.name = self.name
+        return result
+
     def to_series(self, name: Union[str, Tuple[str, ...]] = None) -> Series:
         """
         Create a Series with both index and values equal to the index keys

databricks/koalas/missing/indexes.py

@@ -49,7 +49,6 @@ class _MissingPandasLikeIndex(object):
     delete = unsupported_function('delete')
     difference = unsupported_function('difference')
     drop = unsupported_function('drop')
-    drop_duplicates = unsupported_function('drop_duplicates')
     droplevel = unsupported_function('droplevel')
     duplicated = unsupported_function('duplicated')
     equals = unsupported_function('equals')
@@ -137,7 +136,6 @@ class _MissingPandasLikeMultiIndex(object):
     delete = unsupported_function('delete')
     difference = unsupported_function('difference')
     drop = unsupported_function('drop')
-    drop_duplicates = unsupported_function('drop_duplicates')
     droplevel = unsupported_function('droplevel')
     duplicated = unsupported_function('duplicated')
     equal_levels = unsupported_function('equal_levels')

databricks/koalas/tests/test_indexes.py

@@ -334,3 +334,12 @@ def test_index_fillna(self):
 
         with self.assertRaisesRegex(TypeError, "Unsupported type <class 'list'>"):
             kidx.fillna([1, 2])
+
+    def test_index_drop_duplicates(self):
+        pidx = pd.Index([1, 1, 2])
+        kidx = ks.Index([1, 1, 2])
+        self.assert_eq(pidx.drop_duplicates(), kidx.drop_duplicates())
+
+        pidx = pd.MultiIndex.from_tuples([(1, 1), (1, 1), (2, 2)], names=['level1', 'level2'])
+        kidx = ks.MultiIndex.from_tuples([(1, 1), (1, 1), (2, 2)], names=['level1', 'level2'])
+        self.assert_eq(pidx.drop_duplicates(), kidx.drop_duplicates())

docs/source/reference/indexing.rst

@@ -40,6 +40,7 @@ Modifying and computations
    Index.is_interval
    Index.is_numeric
    Index.is_object
+   Index.drop_duplicates
    Index.value_counts
 
 Missing Values