Implements tail() for DataFrame & Series

databricks/koalas/frame.py

@@ -4229,6 +4229,63 @@ def head(self, n=5):
 
         return DataFrame(self._internal.copy(sdf=self._sdf.limit(n)))
 
+    def tail(self, n=5):
+        """
+        Return the last `n` rows.
+
+        This function returns the last `n` rows for the object based
+        on position. It is useful for quickly verifying data,
+        for example, after sorting or appending rows.
+
+        Parameters
+        ----------
+        n : int, default 5
+            Number of rows to select.
+
+        Returns
+        -------
+        obj_tail : same type as caller
+            The last `n` rows of the caller object.
+
+        Examples
+        --------
+        >>> df = ks.DataFrame({'animal':['alligator', 'bee', 'falcon', 'lion',
+        ...                    'monkey', 'parrot', 'shark', 'whale', 'zebra']})
+        >>> df
+              animal
+        0  alligator
+        1        bee
+        2     falcon
+        3       lion
+        4     monkey
+        5     parrot
+        6      shark
+        7      whale
+        8      zebra
+
+        Viewing the last 5 lines
+
+        >>> df.tail()
+           animal
+        8   zebra
+        7   whale
+        6   shark
+        5  parrot
+        4  monkey
+
+        Viewing the last `n` lines (three in this case)
+
+        >>> df.tail(3)
+          animal
+        8  zebra
+        7  whale
+        6  shark
+        """
+        tmp_col = '__order__'
+        sdf = self._sdf.withColumn(tmp_col, F.monotonically_increasing_id())
+
+        return DataFrame(self._internal.copy(sdf=sdf.orderBy(tmp_col, ascending=False).limit(n)))
+
     def pivot_table(self, values=None, index=None, columns=None,
                     aggfunc='mean', fill_value=None):
         """

databricks/koalas/missing/frame.py

@@ -86,7 +86,6 @@ class _MissingPandasLikeDataFrame(object):
     stack = unsupported_function('stack')
     swapaxes = unsupported_function('swapaxes')
     swaplevel = unsupported_function('swaplevel')
-    tail = unsupported_function('tail')
     take = unsupported_function('take')
     to_feather = unsupported_function('to_feather')
     to_gbq = unsupported_function('to_gbq')

databricks/koalas/missing/series.py

@@ -95,7 +95,6 @@ class _MissingPandasLikeSeries(object):
     squeeze = unsupported_function('squeeze')
     swapaxes = unsupported_function('swapaxes')
     swaplevel = unsupported_function('swaplevel')
-    tail = unsupported_function('tail')
     take = unsupported_function('take')
     to_hdf = unsupported_function('to_hdf')
     to_period = unsupported_function('to_period')

databricks/koalas/series.py

@@ -1736,6 +1736,32 @@ def head(self, n=5):
         """
         return _col(self.to_dataframe().head(n))
 
+    def tail(self, n=5):
+        """
+        Return the last n rows.
+
+        This function returns the last n rows for the object based on position.
+        It is useful for quickly verifying data,
+        for example, after sorting or appending rows.
+
+        Parameters
+        ----------
+        n : Integer, default =  5
+
+        Returns
+        -------
+        The last n rows of the caller object.
+
+        Examples
+        --------
+        >>> df = ks.DataFrame({'animal':['alligator', 'bee', 'falcon', 'lion']})
+        >>> df.animal.tail(2)  # doctest: +NORMALIZE_WHITESPACE
+        3      lion
+        2    falcon
+        Name: animal, dtype: object
+        """
+        return _col(self.to_dataframe().tail(n))
+
     # TODO: Categorical type isn't supported (due to PySpark's limitation) and
     # some doctests related with timestamps were not added.
     def unique(self):

docs/source/reference/frame.rst

@@ -148,6 +148,7 @@ Reindexing / Selection / Label manipulation
    DataFrame.set_index
    DataFrame.isin
    DataFrame.sample
+   DataFrame.tail
 
 .. _api.dataframe.missing:
 

docs/source/reference/series.rst

@@ -152,6 +152,7 @@ Reindexing / Selection / Label manipulation
    Series.rename
    Series.reset_index
    Series.sample
+   Series.tail
    Series.where
    Series.mask
    Series.truncate