groupByOrderItems.py

import itertools as it, sys
from functools import reduce
order_items = open("/data/retail_db/order_items/part-00000","r").read().splitlines()[:50]
order_subtotal = list(map(lambda x: (int(x.split(",")[1]),float(x.split(",")[4])),order_items))
#sorted values should be passed in groupby
iterator = it.groupby(sorted(order_subtotal),lambda x: x[0])

revenuePerOrder = map(lambda x: (x[0], reduce(lambda a,b: a + b, map(lambda v: v[1], x[1]))), iterator)
print(list(revenuePerOrder))