The file “RandomData_Final.csv” contains four variables.
PID = the unique identifying number in Amazon for each DVD.
Amazon = a dummy variable, equals 0 if Amazon does not itself sell the item and 1 if Amazon sells the item.
Sale_Rank = Amazon’s listed sales rank in the category “Movies & TV”. If no sales rank recorded, it equals 0.
Sale_Rank_Adj = The same as Sale_Rank unless Sale_Rank=0, in which case it equals one plus the maximum reported sales ranks over the 583,779 DVDs.