使用者定義的 Python 累加器

定義 AccumulatorParam

from pyspark import AccumulatorParam

class StringAccumulator(AccumulatorParam):
    def zero(self, s):
        return s
    def addInPlace(self, s1, s2):
        return s1 + s2

accumulator = sc.accumulator("", StringAccumulator())

def add(x): 
    global accumulator
    accumulator += x

sc.parallelize(["a", "b", "c"]).foreach(add)