好,所以我必须从文件中找到最大数量,并且我有2行数字
line 1- 2,2,3
line 2- 4,3
现在我想找到最大数量,我的代码也可以正常工作,但问题是它显示了我想找到整个文件最大数量的每一行的最大数量
from mrjob.job import MRJob
class MRNumberCounter(MRJob):
def mapper(self, key, line):
for number in line.split():
yield number, 1
def reducer(self, number, occurrences):
yield max(number), number
if __name__ == '__main__':
MRNumberCounter.run()
我希望输出为4
from mrjob.job import MRJob
class MRNumberCounter(MRJob):
def mapper(self, key, line):
for number in line.split():
yield number, 1
def combiner(self, number, occurrences):
yield number, sum(occurrences)
def reducer(self, number, occurrences):
yield number, sum(occurrences)
if __name__ == '__main__':
MRNumberCounter.run()