df1= sqlContext.createDataFrame([("A001","RED, WHITE, BLUE"),("A002","RED, YELLOW"),("A003","GREEN,RED"),("A004","WHITE,YELLOW")], ["id","csv_column"])
df1.show()


df2= sqlContext.createDataFrame([("C1","RED"),("C2","WHITE"),("C3","BLUE"),("C4","YELLOW"),("C5","RED"),("C6","GREEN"),("C7","BLUE")], ["CLRCODE","COLOR"])
df2.show()

+----+----------------+
| id | csv_column     |
+----+----------------+
|A001|RED, WHITE, BLUE|
|A002|RED, YELLOW     |
|A003|GREEN, RED      |
|A004|WHITE, YELLOW   |
 +----+----------------+

+-------+-------+
|CLRCODE| COLOR |
+-------+-------+
| C1    | RED   |
| C2    | WHITE |
| C3    | BLUE  |
| C4    | YELLOW|
| C5    | RED   |
| C6    | GREEN |
| C7    | BLUE  |
+-------+-------+

+-------+
|df1.id |
+-------+
|A001   |
|A002   |
|A003   |
+-------+
|A001   |
|A004   |
+-------+
|A001   |
+-------+
|A002   |
|A004   |
+-------+
|A001   |
|A002   |
|A003   |
+-------+
|A003   |
+-------+
|A001   |
+-------+