javacaoyu commented on a change in pull request #19126:
URL: https://github.com/apache/flink/pull/19126#discussion_r831017538
##########
File path: flink-python/pyflink/datastream/data_stream.py
##########
@@ -1174,6 +1174,66 @@ def process_element(self, value, ctx:
'KeyedProcessFunction.Context'):
return self.process(FilterKeyedProcessFunctionAdapter(func),
self._original_data_type_info)\
.name("Filter")
+ def sum(self, position_to_sum: Union[int, str]) -> 'DataStream':
+ """
+ Applies an aggregation that gives a rolling sum of the data stream at
the
+ given position grouped by the given key. An independent aggregate is
kept
+ per key.
+
+ Example(Tuple data to sum):
+ ::
+
+ >>> ds = env.from_collection([('a', 1), ('a', 2), ('b', 1), ('b',
5)])
+ >>> ds.key_by(lambda x: x[0]).sum(1)
+
+ Example(Row data to sum):
+ ::
+
+ >>> ds = env.from_collection([('a', 1), ('a', 2), ('a', 3), ('b',
1), ('b', 2)],
+ ...
type_info=Types.ROW([Types.STRING(), Types.INT()]))
+ >>> ds.key_by(lambda x: x[0]).sum(1)
+
+ Example(Row data with fields name to sum):
+ ::
+
+ >>> ds = env.from_collection(
+ ... [('a', 1), ('a', 2), ('a', 3), ('b', 1), ('b', 2)],
+ ... type_info=Types.ROW_NAMED(["key", "value"],
[Types.STRING(), Types.INT()])
+ ... )
+ >>> ds.key_by(lambda x: x[0]).sum("value")
+
+ :param position_to_sum:
+ The field position in the data points to sum, type can be int or
str.
+ This is applicable to Tuple types, and :class:`pyflink.common.Row`
types.
+ :return: The transformed DataStream.
+ """
+ if not isinstance(position_to_sum, int) and not
isinstance(position_to_sum, str):
+ raise TypeError("The input must be of int or str type to locate
the value to sum")
+
+ class SumReduceFunction(ReduceFunction):
+
+ def __init__(self, position_to_sum):
+ self._pos = position_to_sum
+
+ def reduce(self, value1, value2):
+ from numbers import Number
+ if not isinstance(value1[self._pos], Number):
Review comment:
Yes, very thanks for your advice, let me be enlightened.
Sure, i only considered the normal situation, forget that when the user is
using it, there is any situation.
And let me know, in any situation, check the new input always better than
check the aggregated values, even that get same result in most situation.
I will to fixed that bug.
and very thanks to you, its let me programming skills up.
--
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]
