We have 36 classification datasets(arff file) from UCI Machine Learning Repository.
We will produce artificial datasets(200 datasets) from this 36 datasets.
(How can we produce the datasets?)
For example If one classification dataset have A B C D E classes, we can produce 10 artificial classification datasets which have A B, A C, A D, A E, B C, B D, B E, C D, C E, D E classes.
If one classification dataset have 10 classes, we can produce 45 datasets which have 2 classes.
This artificial datasets should contain only two classes.
This software will be used for defining classification dataset's meta features. These datasets should be appropriate for my Classification Meta Features project.
Max budget: $100