okaram · August 29, 2015 14:05
diff --git a/sales.py b/sales.py
 sales=sc.textFile("sales_*.txt").map(lambda x:x.split('\t'))
diff --git a/sales1.txt b/sales1.txt
 2014-01-01	1	1	100
 2014-01-01	1	2	37
 2014-01-01	1	3	54
 2014-01-01	2	1	50
 2014-01-01	2	2	40
 2014-01-01	3	1	75
diff --git a/sales_by_product.py b/sales_by_product.py
 sales_by_product=sales.map(lambda x : (x[0],int(x[2])) ).reduceByKey(lambda x,y:x+y)
	2014-01-01 1 1 100
	2014-01-01 1 2 37
	2014-01-01 1 3 54
	2014-01-01 2 1 50
	2014-01-01 2 2 40
	2014-01-01 3 1 75