Write a general matlab program for growing a binary tree and use it to train a tree fully
using the data from the three categories in the table, using an entropy impurity.
(a) Use the (unpruned) tree to classify the following patterns: {A,E, I, L,N},
{D,E, J,K,N}, {B,F, J,K,M}, a nd {C,D, J, L,N}.
(b) Prune one pair of leafs, increasing the entropy impurity as little as possible.
(c) Modify your program to allow for non-binary splits, where the branching ratio
B as is determined at each node during training. Train a new tree fully using a
gain ratio impurity and then classify the points in (a).