Implement Series.swapaxes

databricks/koalas/frame.py

@@ -6448,68 +6448,6 @@ def swaplevel(self, i=-2, j=-1, axis=0) -> "DataFrame":
 
         return DataFrame(internal)
 
-    def swapaxes(
-        self, i: Union[str, int] = 0, j: Union[str, int] = 1, copy: bool = True
-    ) -> "DataFrame":
-        """
-        Interchange axes and swap values axes appropriately.
-
-        .. note:: This method is based on an expensive operation due to the nature
-            of big data. Internally it needs to generate each row for each value, and
-            then group twice - it is a huge operation. To prevent misusage, this method
-            has the 'compute.max_rows' default limit of input length, and raises a ValueError.
-
-                >>> from databricks.koalas.config import option_context
-                >>> with option_context('compute.max_rows', 1000):  # doctest: +NORMALIZE_WHITESPACE
-                ...     ks.DataFrame({'a': range(1001)}).swapaxes()
-                Traceback (most recent call last):
-                  ...
-                ValueError: Current DataFrame has more then the given limit 1000 rows.
-                Please set 'compute.max_rows' by using 'databricks.koalas.config.set_option'
-                to retrieve to retrieve more than 1000 rows. Note that, before changing the
-                'compute.max_rows', this operation is considerably expensive.
-
-        Parameters
-        ----------
-        i: {0 or 'index', 1 or 'columns'}, default 0. The axis to swap.
-        j: {0 or 'index', 1 or 'columns'}, default 1. The axis to swap.
-
-        Returns
-        -------
-        DataFrame
-
-        Examples
-        --------
-        >>> kdf = ks.DataFrame(
-        ...     [[1, 2, 3], [4, 5, 6], [7, 8, 9]], index=['x', 'y', 'z'], columns=['a', 'b', 'c']
-        ... )
-        >>> kdf
-           a  b  c
-        x  1  2  3
-        y  4  5  6
-        z  7  8  9
-        >>> kdf.swapaxes()
-           x  y  z
-        a  1  4  7
-        b  2  5  8
-        c  3  6  9
-        >>> kdf.swapaxes(i=1, j=0)
-           x  y  z
-        a  1  4  7
-        b  2  5  8
-        c  3  6  9
-        >>> kdf.swapaxes(i=1, j=1)
-           a  b  c
-        x  1  2  3
-        y  4  5  6
-        z  7  8  9
-        """
-        assert copy is True
-        i = validate_axis(i)
-        j = validate_axis(j)
-
-        return self if i == j else self.transpose()
-
     def _swaplevel_columns(self, i, j) -> InternalFrame:
         assert isinstance(self.columns, pd.MultiIndex)
         for index in (i, j):

databricks/koalas/generic.py

@@ -1178,6 +1178,85 @@ def sum(self, axis=None, numeric_only=True) -> Union[Scalar, "Series"]:
             F.sum, name="sum", numeric_only=numeric_only, axis=axis
         )
 
+    def swapaxes(
+        self, i: Union[str, int], j: Union[str, int], copy: bool = True
+    ) -> Union["DataFrame", "Series"]:
+        """
+        Interchange axes and swap values axes appropriately.
+
+        .. note:: This method, if applied to a DataFrame, is based on an expensive operation due to
+            the nature of big data. Internally it needs to generate each row for each value, and
+            then group twice - it is a huge operation. To prevent misusage, this method
+            has the 'compute.max_rows' default limit of input length, and raises a ValueError.
+
+                >>> from databricks.koalas.config import option_context
+                >>> with option_context('compute.max_rows', 1000):  # doctest: +NORMALIZE_WHITESPACE
+                ...     ks.DataFrame({'a': range(1001)}).swapaxes()
+                Traceback (most recent call last):
+                  ...
+                ValueError: Current DataFrame has more then the given limit 1000 rows.
+                Please set 'compute.max_rows' by using 'databricks.koalas.config.set_option'
+                to retrieve to retrieve more than 1000 rows. Note that, before changing the
+                'compute.max_rows', this operation is considerably expensive.
+
+        Parameters
+        ----------
+        i: {0 or 'index', 1 or 'columns'}. The axis to swap.
+        j: {0 or 'index', 1 or 'columns'}. The axis to swap.
+        copy : bool, default True.
+
+        Returns
+        -------
+        DataFrame or Series
+
+        Examples
+        --------
+        On a DataFrame:
+
+        >>> kdf = ks.DataFrame(
+        ...     [[1, 2, 3], [4, 5, 6], [7, 8, 9]], index=['x', 'y', 'z'], columns=['a', 'b', 'c']
+        ... )
+        >>> kdf
+           a  b  c
+        x  1  2  3
+        y  4  5  6
+        z  7  8  9
+        >>> kdf.swapaxes(i=1, j=0)
+           x  y  z
+        a  1  4  7
+        b  2  5  8
+        c  3  6  9
+        >>> kdf.swapaxes(i=1, j=1)
+           a  b  c
+        x  1  2  3
+        y  4  5  6
+        z  7  8  9
+
+        On a Series:
+
+        >>> kser = ks.Series([1, 2, 3], index=["x", "y", "z"])
+        >>> kser
+        x    1
+        y    2
+        z    3
+        dtype: int64
+        >>>
+        >>> kser.swapaxes(0, 0)
+        x    1
+        y    2
+        z    3
+        dtype: int64
+        """
+        assert copy is True
+        i = validate_axis(i)
+        j = validate_axis(j)
+
+        if isinstance(self, ks.Series):
+            if not i == j == 0:
+                raise ValueError("Axis must be 0 for Series")
+
+        return self.copy() if i == j else cast(Union["DataFrame", "Series"], self).transpose()
+
     def skew(self, axis=None, numeric_only=True) -> Union[Scalar, "Series"]:
         """
         Return unbiased skew normalized by N-1.

databricks/koalas/missing/series.py

@@ -55,7 +55,6 @@ class MissingPandasLikeSeries(object):
     sem = _unsupported_function("sem")
     set_axis = _unsupported_function("set_axis")
     slice_shift = _unsupported_function("slice_shift")
-    swapaxes = _unsupported_function("swapaxes")
     to_hdf = _unsupported_function("to_hdf")
     to_period = _unsupported_function("to_period")
     to_sql = _unsupported_function("to_sql")

databricks/koalas/tests/test_dataframe.py

@@ -1453,6 +1453,7 @@ def test_swapaxes(self):
 
         self.assertRaises(AssertionError, lambda: kdf.swapaxes(0, 1, copy=False))
         self.assertRaises(ValueError, lambda: kdf.swapaxes(0, -1))
+        self.assertRaises(TypeError, lambda: kdf.swapaxes())
 
     def test_nlargest(self):
         pdf = pd.DataFrame(

databricks/koalas/tests/test_series.py

@@ -1853,6 +1853,19 @@ def test_swaplevel(self):
         self.assertRaises(KeyError, lambda: kser.swaplevel("not_number", "color"))
         self.assertRaises(AssertionError, lambda: kser.swaplevel(copy=False))
 
+    def test_swapaxes(self):
+        pser = pd.Series([1, 2, 3], index=["x", "y", "z"], name="ser")
+        kser = ks.from_pandas(pser)
+
+        self.assert_eq(kser.swapaxes(0, 0), pser.swapaxes(0, 0))
+        self.assert_eq(kser.swapaxes("index", "index"), pser.swapaxes("index", "index"))
+        self.assert_eq((kser + 1).swapaxes(0, 0), (pser + 1).swapaxes(0, 0))
+
+        self.assertRaises(AssertionError, lambda: kser.swapaxes(0, 1, copy=False))
+        self.assertRaises(ValueError, lambda: kser.swapaxes(0, 1))
+        self.assertRaises(ValueError, lambda: kser.swapaxes("index", "columns"))
+        self.assertRaises(TypeError, lambda: kser.swapaxes())
+
     def test_div_zero_and_nan(self):
         pser = pd.Series([100, None, -300, None, 500, -700, np.inf, -np.inf], name="Koalas")
         kser = ks.from_pandas(pser)

docs/source/reference/series.rst

@@ -176,6 +176,7 @@ Reindexing / Selection / Label manipulation
    Series.reset_index
    Series.sample
    Series.swaplevel
+   Series.swapaxes
    Series.take
    Series.tail
    Series.where