gistfile1.py

def get_reporting(data):
	if not data:
		return (0, 0)

	unique_ids = list(set(data))
	num_unique_vistors = len(unique_ids)

	# create frequency of visits by user id dict
	frequency = dict((key, len([k for k in data if k == key])) for key in unique_ids)

	# get average page views per user
	avg = sum(frequency.values())/float(num_unique_vistors)

	return (num_unique_vistors, avg)


dataset1 = [8, 8, 2, 2]
assert get_reporting(dataset1) == (2, 2.0)

dataset2 = [9, 8, 9]
assert get_reporting(dataset2) == (2, 1.5)