stat.py

# input data:

# a,1
# b,2
# a,3
# a,4
# a,7
# b,4
# b,0

# $ cat data.csv | python stat.py
# a {'count': 4, 'sum': 15.0, 'avg': 3.75}
# b {'count': 3, 'sum': 6.0, 'avg': 2.0}

import sys
import collections

class Stat(object):
    def __init__(self):
        self.sum = 0.0
        self.count = 0
    def update(self, value):
        self.count += 1
        self.sum += value

    def status(self):
        return {'sum': self.sum, 'count': self.count, 'avg': self.sum / self.count}

def stat_factory():
    return Stat()

objects = collections.defaultdict(stat_factory)

for line in sys.stdin:
    key, val = line.split(",")
    objects[key].update(float(val))

for k, v in objects.items():
    print k, v.status()