Test for Mtxslv Decision Trees

Create a dataset running the following lines:

import numpy as np

lista_features_coluna_1 = [[0],[0],[1],[1]]
lista_features_coluna_2 = [[0],[1],[0],[1]]
features_teste = np.concatenate((lista_features_coluna_1,lista_features_coluna_2), axis = 1)
labels_teste = np.array([[1],[1],[0],[1]])

print("features_teste = \n",features_teste)
print("labels_teste = \n",labels_teste)

Notice is the same thing as:

A	B	y
0	0	1
0	1	1
1	0	0
1	1	1

We can formulate the rule for y as: y = A and B or not(A). The decision tree can be seen as a disjunction of conjunctions, so this boolean rule can, at least, be represented by our hypothesis space.

In order to create the tree, run:

arvore = MtxslvDecisionTrees()
arvore.fit(features_teste, labels_teste, 0.05)