Group multiple conditions in PyMVPA


I am using PyMVPA for my analysis and I have a question about it.

In my experiment, I have 4 conditions (male_faces, female_faces, cars, bikes). I am running my analysis on the 4 condition, but I would also like to run it again by grouping multiple conditions together (e.g., faces vs. vehicles). Is this something possible, and would it make sense to do it in PyMVPA, or should I generate new event files with these two conditions rather than four?