path = "/public/retail_db"
products = sc.textFile(path + "/products")
minPricedProductsByCategory = products.\
filter(lambda product: product.split(",")[4] != "").\
map(lambda p:
(int(p.split(",")[1]), p)
).\
reduceByKey(lambda agg, product:
agg if(float(agg.split(",")[4]) < float(product.split(",")[4])) else product
).\
map(lambda rec: rec[1])
for i in minPricedProductsByCategory.collect(): print(i)