def voting():
print("----------------voting------------------")
mat = Arff("./voting.arff", label_count=1)
# data = mat.data[:, 0:-1]
# labels = mat.data[:, -1]#.reshape(-1, 1)
splits = 10
kfolder = KFold(n_splits=splits)
scores = [[], []]
data, tData, labels, tLabels = train_test_split(mat.data[:, :-1],
mat.data[:, -1].reshape(
-1, 1),
test_size=.25)
best_tree = (0, None)
for train, validate in kfolder.split(data, labels):
# print(train, validate)
dtree = DTClassifier(features=mat.get_attr_names())
dtree.fit(data[train], labels[train])
scores[0].append(dtree.score(data[validate], labels[validate]))
scores[1].append(dtree.score(data[train], labels[train]))
if scores[0][-1] > best_tree[0]:
best_tree = (scores[0][-1], dtree)
average = np.sum(scores, axis=1) / splits
scores[0].append(average[0])
scores[1].append(average[1])
header_text = ''
for x in range(splits):
header_text = header_text + str(x) + ' '
np.savetxt("voting.csv",
scores,
header=header_text + 'average',
delimiter=',')
print(scores)
print('Average CV accuracy: {:.2f}'.format(scores[0][-1]))
print('Best tree accuracy: {:.2f}'.format(best_tree[1].score(
tData, tLabels)))
f = open("voting_tree", "w")
f.write(dtree.graph(class_translator=lambda x: mat.attr_value(-1, x)))
f.close()
