Add subcommand (like cv_split) to divide data into training set and test set for cross validation.
After converting MovieLens data to cpmf format,
$ python scripts/convert_movielens.py PATH/ml-1m/ratings.dat --separator :: > input/ml-1m
users will split the data into training set and test set by the following command.
$ ./mf cv_split input/ml-1m --training_size 0.8
or
$ ./mf cv_split input/ml-1m --test_size 0.2