convert an indicator matrix to a set of class labels based on the internal mappings for the supplied feature name
partition the data into the training set, the cross validation set and the test set.
make a random selection of the data for the supplied number of rows.
reference the random permutation of the data before partitioning.
The data set class contains the full dataset the number of continuous colums and number of discrete columns.
The data set contains the continuous data first, followed by the discrete data.
Created by cd on 7/05/2016.