pyspark 对用户的购买商品记录作出统计

统计一共售出多少个商品，一共有多少个顾客，所有商品的累加和，售卖最流行的商品

数据UserPurchaseHistory.csv

用户名称，商品名称，价格

John,iPhone Cover,9.99
John,Headphones,5.49
Jack,iPhone Cover,9.99
Jill,Samsung Galaxy Cover,8.95
Bob,iPad Cover,5.49

"""A simple Spark app in Python"""
from pyspark import SparkContext

sc = SparkContext("local[2]", "First Spark App")
# we take the raw data in CSV format and convert it into a set of records of the form (user, product, price)
data = sc.textFile("data/UserPurchaseHistory.csv").map(lambda line: line.split(",")).map(lambda record: (record[0], record[1], record[2]))
# let's count the number of purchases
numPurchases = data.count()
# let's count how many unique users made purchases
uniqueUsers = data.map(lambda record: record[0]).distinct().count()
# let's sum up our total revenue
totalRevenue = data.map(lambda record: float(record[2])).sum()
# let's find our most popular product
products = data.map(lambda record: (record[1], 1.0)).reduceByKey(lambda a, b: a + b).collect()
mostPopular = sorted(products, key=lambda x: x[1], reverse=True)[0]
print mostPopular

# Finally, print everything out
print "Total purchases: %d" % numPurchases
print "Unique users: %d" % uniqueUsers
print "Total revenue: %2.2f" % totalRevenue
print "Most popular product: %s with %d purchases" % (mostPopular[0], mostPopular[1])

# stop the SparkContext
sc.stop()