xgboost package has two files that must be used for ranking:
train.txtwith the data
train.txt.groupwith the group of each observation
I don't understand two things in each file:
- What should I use as positive/negative classes? In ranking, there is no such thing as a positive/negative class...
- What should I use as group? Say that I have observations x1 > x2 > x3. How do I express this lexicographical order using groups?