zhengruifeng commented on code in PR #37801:
URL: https://github.com/apache/spark/pull/37801#discussion_r962859128
##########
python/pyspark/pandas/groupby.py:
##########
@@ -895,6 +895,89 @@ def sem(col: Column) -> Column:
bool_to_numeric=True,
)
+ # TODO: 1, 'n' accepts list and slice; 2, implement 'dropna' parameter
+ def nth(self, n: int) -> FrameLike:
+ """
+ Take the nth row from each group.
+
+ .. versionadded:: 3.4.0
+
+ Parameters
+ ----------
+ n : int
+ A single nth value for the row
+
+ Examples
+ --------
+
+ >>> df = ps.DataFrame({'A': [1, 1, 2, 1, 2],
+ ... 'B': [np.nan, 2, 3, 4, 5]}, columns=['A', 'B'])
+ >>> g = df.groupby('A')
+ >>> g.nth(0)
+ B
+ A
+ 1 NaN
+ 2 3.0
+ >>> g.nth(1)
+ B
+ A
+ 1 2.0
+ 2 5.0
+ >>> g.nth(-1)
+ B
+ A
+ 1 4.0
+ 2 5.0
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+ """
+ groupkey_names = [SPARK_INDEX_NAME_FORMAT(i) for i in
range(len(self._groupkeys))]
+ internal, agg_columns, sdf = self._prepare_reduce(
+ groupkey_names=groupkey_names,
+ accepted_spark_types=None,
+ bool_to_numeric=False,
+ )
+ psdf: DataFrame = DataFrame(internal)
+
+ if len(psdf._internal.column_labels) > 0:
+ window1 =
Window.partitionBy(*groupkey_names).orderBy(NATURAL_ORDER_COLUMN_NAME)
+ tmp_row_number_col = "__tmp_row_number_col__"
+ if n >= 0:
+ sdf = (
+ psdf._internal.spark_frame.withColumn(
+ tmp_row_number_col, F.row_number().over(window1)
+ )
+ .where(F.col(tmp_row_number_col) == n + 1)
+ .drop(tmp_row_number_col)
+ )
+ else:
+ window2 = Window.partitionBy(*groupkey_names).rowsBetween(
+ Window.unboundedPreceding, Window.unboundedFollowing
+ )
+ tmp_group_size_col = "__tmp_group_size_col__"
+ sdf = (
+ psdf._internal.spark_frame.withColumn(
+ tmp_group_size_col, F.count(F.lit(0)).over(window2)
+ )
+ .withColumn(tmp_row_number_col,
F.row_number().over(window1))
+ .where(F.col(tmp_row_number_col) ==
F.col(tmp_group_size_col) + 1 + n)
+ .drop(tmp_group_size_col, tmp_row_number_col)
+ )
+ else:
+ sdf = sdf.select(*groupkey_names).distinct()
Review Comment:
there seems a bug in Pandas' `GroupBy.nth`, its returned index varies with
`n`:
```
In [23]: pdf
Out[23]:
A B C D
0 1 3.1 a True
1 2 4.1 b False
2 1 4.1 b False
3 2 3.1 a True
In [24]: pdf.groupby(["A", "B", "C", "D"]).nth(0)
Out[24]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (1, 4.1, b, False), (2, 3.1, a, True), (2, 4.1,
b, False)]
In [25]: pdf.groupby(["A", "B", "C", "D"]).nth(0).index
Out[25]:
MultiIndex([(1, 3.1, 'a', True),
(1, 4.1, 'b', False),
(2, 3.1, 'a', True),
(2, 4.1, 'b', False)],
names=['A', 'B', 'C', 'D'])
In [26]: pdf.groupby(["A", "B", "C", "D"]).nth(1)
Out[26]:
Empty DataFrame
Columns: []
Index: []
In [27]: pdf.groupby(["A", "B", "C", "D"]).nth(1).index
Out[27]: MultiIndex([], names=['A', 'B', 'C', 'D'])
In [28]: pdf.groupby(["A", "B", "C", "D"]).nth(-1)
Out[28]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (1, 4.1, b, False), (2, 3.1, a, True), (2, 4.1,
b, False)]
In [29]: pdf.groupby(["A", "B", "C", "D"]).nth(-1).index
Out[29]:
MultiIndex([(1, 3.1, 'a', True),
(1, 4.1, 'b', False),
(2, 3.1, 'a', True),
(2, 4.1, 'b', False)],
names=['A', 'B', 'C', 'D'])
In [30]: pdf.groupby(["A", "B", "C", "D"]).nth(-2)
Out[30]:
Empty DataFrame
Columns: []
Index: []
In [31]: pdf.groupby(["A", "B", "C", "D"]).nth(-2).index
Out[31]: MultiIndex([], names=['A', 'B', 'C', 'D'])
```
while other functions' behavior in Pandas and PS are like this:
```
In [17]: pdf
Out[17]:
A B C D
0 1 3.1 a True
1 2 4.1 b False
2 1 4.1 b False
3 2 3.1 a True
In [18]: pdf.groupby(["A", "B", "C", "D"]).max()
Out[18]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (1, 4.1, b, False), (2, 3.1, a, True), (2, 4.1,
b, False)]
In [19]: pdf.groupby(["A", "B", "C", "D"]).mad()
Out[19]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (1, 4.1, b, False), (2, 3.1, a, True), (2, 4.1,
b, False)]
In [20]: psdf.groupby(["A", "B", "C", "D"]).max()
Out[20]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (2, 4.1, b, False), (1, 4.1, b, False), (2, 3.1,
a, True)]
In [21]: psdf.groupby(["A", "B", "C", "D"]).mad()
Out[21]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (2, 4.1, b, False), (1, 4.1, b, False), (2, 3.1,
a, True)]
In [22]:
In [22]: psdf.groupby(["A", "B", "C", "D"]).nth(0)
Out[22]:
Empty DataFrame
Columns: []
Index: [(1, 3.1, a, True), (2, 4.1, b, False), (1, 4.1, b, False), (2, 3.1,
a, True)]
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
