def Of(label, pcoll, n, compare, *args, **kwargs):
"""Obtain a list of the compare-most N elements in a PCollection.
This transform will retrieve the n greatest elements in the PCollection
to which it is applied, where "greatest" is determined by the comparator
function supplied as the compare argument.
compare should be an implementation of "a < b" taking at least two arguments
(a and b). Additional arguments and side inputs specified in the apply call
become additional arguments to the comparator.
Args:
label: display label for transform processes.
pcoll: PCollection to process.
n: number of elements to extract from pcoll.
compare: as described above.
*args: as described above.
**kwargs: as described above.
"""
return pcoll | core.CombineGlobally(label, TopCombineFn(n, compare), *
args, **kwargs)
def apply(self, pcoll):
return pcoll | core.CombineGlobally(CountCombineFn())
def apply(self, pcoll):
return pcoll | core.CombineGlobally(self.label, ToDictCombineFn())
def FixedSizeGlobally(label, pcoll, n):
return pcoll | core.CombineGlobally(label, SampleCombineFn(n))