Yikun commented on a change in pull request #35868:
URL: https://github.com/apache/spark/pull/35868#discussion_r830850186
##########
File path: python/pyspark/pandas/series.py
##########
@@ -3540,8 +3540,10 @@ def quantile(psser: Series) -> Column:
return self._reduce_for_stat_function(quantile, name="quantile")
- # TODO: add axis, numeric_only, pct, na_option parameter
- def rank(self, method: str = "average", ascending: bool = True) ->
"Series":
+ # TODO: add axis, pct, na_option parameter
+ def rank(
+ self, method: str = "average", ascending: bool = True, numeric_only:
Optional[bool] = None
Review comment:
same test on None explictly
##########
File path: python/pyspark/pandas/tests/test_series.py
##########
@@ -1333,6 +1333,17 @@ def test_rank(self):
self.assert_eq(pser.rank(method="first"),
psser.rank(method="first").sort_index())
self.assert_eq(pser.rank(method="dense"),
psser.rank(method="dense").sort_index())
+ non_numeric_pser = pd.Series(["a", "c", "b", "d"], name="x",
index=[10, 11, 12, 13])
+ non_numeric_psser = ps.from_pandas(non_numeric_pser)
+ self.assert_eq(
+ non_numeric_pser.rank(numeric_only=True).sort_index(),
+ non_numeric_psser.rank(numeric_only=True).sort_index(),
+ )
+ self.assert_eq(
+ (non_numeric_pser + "x").rank(numeric_only=True).sort_index(),
+ (non_numeric_psser + "x").rank(numeric_only=True).sort_index(),
+ )
Review comment:
```suggestion
self.assert_eq(
non_numeric_pser.rank(numeric_only=True),
non_numeric_psser.rank(numeric_only=True),
)
self.assert_eq(
(non_numeric_pser + "x").rank(numeric_only=True),
(non_numeric_psser + "x").rank(numeric_only=True),
)
```
I guess `sort.index` is useless in here, because we will get a empty series
##########
File path: python/pyspark/pandas/frame.py
##########
@@ -10239,8 +10239,10 @@ def any(self, axis: Axis = 0) -> "Series":
return first_series(DataFrame(internal))
- # TODO: add axis, numeric_only, pct, na_option parameter
- def rank(self, method: str = "average", ascending: bool = True) ->
"DataFrame":
+ # TODO: add axis, pct, na_option parameter
+ def rank(
+ self, method: str = "average", ascending: bool = True, numeric_only:
Optional[bool] = None
Review comment:
https://github.com/pandas-dev/pandas/blob/6033ed4b3383d874ee4a8a461724c0b8c2ca968d/pandas/core/generic.py#L8651-L8660
Consider rank=`None` would be deprecated in future in pandas, we might want
to add a test on this (set `rank=None` expilictly), to make sure protect some
behavior in future.
--
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]
