X_train = (((X_tr[:, None] & (1 << np.arange(8)))) > 0).astype(
int) # vector-> binary matrix
Y_train = np.array(Y_train)
# X_test = np.array(X_test).reshape(-1,1)
X_te = np.array(X_test)
X_test = (((X_te[:, None] & (1 << np.arange(8)))) > 0).astype(int)
Y_test = np.array(Y_test)
return [X_train, X_test, Y_train, Y_test]
data = load_dataset()
kf = SequenceKFold(seq_lengths(data[1]), 2)
for tuple in kf:
train_len = tuple[1]
test_len = tuple[3]
split = dataset_split(tuple[0], tuple[2])
#train the model
clf = MultinomialHMM()
clf.fit(split[0], split[2], train_len)
#evaluate the model
Y_pred = clf.predict(split[1], test_len)
print('Accuracy:')
print(clf.score(split[1], split[3], test_len))
print('Confusion matrix:')
labels = list(data[2].values())
print(confusion_matrix(split[3], Y_pred, labels))
print('Report:')
target_names = list(data[2].keys())
print(classification_report(split[3], Y_pred, target_names=target_names))
