def decision_spambase_set_no_libs(): """ Solution for HW1 prob 1 """ print('Homework 1 problem 1 - No Libraries - Regression Decision tree') print('Spambase Dataset') spam_data = utils.load_and_normalize_spam_data() test, train = utils.split_test_and_train(spam_data) print str(len(train)) + " # in training set <--> # in test " + str(len(test)) node = mytree.Node(np.ones(len(train))) branch_node(node, train, 5, 'is_spam') #node.show_children_tree() node.show_children_tree(follow=False) model = mytree.Tree(node) model.print_leaves() print 'Trained model error is : ' + str(model.error()) node.presence = np.ones(len(test)) test_node(node, test, 'is_spam') test_tree = mytree.Tree(node) prediction = test_tree.predict_obj() test_tree.print_leaves_test() print 'predict sum: ' + str(sum(prediction)) print 'MSE:' + str(test_tree.error_test()) [tp, tn, fp, fn] = mystats.get_performance_stats(test['is_spam'].as_matrix(), prediction) print 'TP: {}\tFP: {}\nTN: {}\tFN: {}'.format(tp, fp, tn, fn) print 'Accuracy: ' + str(mystats.compute_accuracy(tp,tn, fp,fn)) print 'MSE: ' + str(mystats.compute_MSE_arrays(prediction, test['is_spam']))