def predict(tr_data_arr, tr_label_arr, test_data_arr, test_label_arr):
data_arr = np.mat(tr_data_arr)
f_label_arr = []
for i in tr_label_arr:
if i == 1:
f_label_arr.append(i)
else:
f_label_arr.append(-1)
classifier_arr, agg_class_est = ada_boost_train_ds(
data_arr, f_label_arr, 30)
test_label_arr = np.mat([[i] for i in test_label_arr])
test_label_arr[test_label_arr == 0] = -1
pred_arr = ada_classify(test_data_arr, classifier_arr)
diff = test_label_arr - pred_arr
error = (diff != [0]).sum()
test_data_len = len(test_data_arr)
accuracy = (test_data_len - error) * 100.0 / test_data_len
return test_data_len, error, accuracy
return best_stump, min_error, best_class_est
def ada_classify(dat_to_class, classifier_arr):
data_mat = np.mat(dat_to_class)
m = data_mat.shape[0]
agg_class_est = np.mat(np.zeros((m, 1)))
for i in xrange(len(classifier_arr)):
class_est = stump_classify(data_mat, classifier_arr[i]['dim'],
classifier_arr[i]['thresh'],
classifier_arr[i]['ineq'])
agg_class_est += classifier_arr[i]['alpha'] * class_est
"""
随着迭代进行，分类的结果会越来越强。
即小于0的分类越来越小，大于0的越来越大
"""
print("agg_class_est:", agg_class_est)
return np.sign(agg_class_est)
if __name__ == '__main__':
from adaboost import load_simp_data, ada_boost_train_ds
data_mat, class_labels = load_simp_data()
# D = np.mat(np.ones((5, 1)) / 5)
# best_stump, min_error, best_class_est = build_stump(data_mat, class_labels, D)
# print best_stump
classifier_arr = ada_boost_train_ds(data_mat, class_labels, 30)
res = ada_classify([1.3, 1.2], classifier_arr)
print("res: ", res)