Yikun commented on code in PR #37923:
URL: https://github.com/apache/spark/pull/37923#discussion_r974808692
##########
python/pyspark/pandas/groupby.py:
##########
@@ -993,6 +994,101 @@ def nth(self, n: int) -> FrameLike:
return self._prepare_return(DataFrame(internal))
+ def prod(self, numeric_only: Optional[bool] = True, min_count: int = 0):
Review Comment:
```suggestion
def prod(self, numeric_only: Optional[bool] = True, min_count: int = 0)
-> FrameLike:
```
##########
python/pyspark/pandas/groupby.py:
##########
@@ -18,7 +18,6 @@
"""
A wrapper for GroupedData to behave similar to pandas GroupBy.
"""
-
Review Comment:
unrelated change
##########
python/pyspark/pandas/groupby.py:
##########
@@ -993,6 +994,101 @@ def nth(self, n: int) -> FrameLike:
return self._prepare_return(DataFrame(internal))
+ def prod(self, numeric_only: Optional[bool] = True, min_count: int = 0):
+ """
+ Compute prod of groups.
+
+ .. versionadded:: 3.4.0
+
+ Parameters
+ ----------
+ numeric_only : bool, default False
+ Include only float, int, boolean columns. If None, will attempt to
use
+ everything, then use only numeric data.
+
+ min_count: int, default 0
+ The required number of valid values to perform the operation.
+ If fewer than min_count non-NA values are present the result will
be NA.
+
+ Returns
+ -------
+ pyspark.pandas.Series or pyspark.pandas.DataFrame
+
+ See Also
+ --------
+ pyspark.pandas.Series.groupby
+ pyspark.pandas.DataFrame.groupby
+
+ Examples
+ --------
+ >>> df = ps.DataFrame({'A': [1, 1, 2, 1, 2],
+ ... 'B': [np.nan, 2, 3, 4, 5],
+ ... 'C': [1, 2, 1, 1, 2],
+ ... 'D': [True, False, True, False, True]})
+
+ Groupby one column and return the prod of the remaining columns in
+ each group.
+
+ >>> df.groupby('A').prod().sort_index()
+ B C D
+ A
+ 1 8.0 2 0
+ 2 15.0 2 1
+
+ >>> df.groupby('A').prod(min_count=3).sort_index()
+ B C D
+ A
+ 1 NaN 2.0 0.0
+ 2 NaN NaN NaN
+ """
+
+ self._validate_agg_columns(numeric_only=numeric_only,
function_name="prod")
+
+ 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=(NumericType, BooleanType),
+ bool_to_numeric=True,
+ )
+
+ psdf: DataFrame = DataFrame(internal)
+ if len(psdf._internal.column_labels) > 0:
+ tmp_count_column = "__tmp_%s_count_col__"
Review Comment:
```suggestion
tmp_count_column = verify_temp_column_name(psdf,
"__tmp_%s_count_col__")
```
You might want to verify column to aovid pontential column name conflict.
--
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]
