def test_train(self):
print("Test Train:")
data_mat, labels_arr = adb.load_simple_data()
classifies_arr, est_agg = adb.train(data_mat, labels_arr, 9)
self.assertEqual(len(classifies_arr), 3)
self.assertEqual(0, classifies_arr[-1]['dim'])
self.assertEqual('lt', classifies_arr[-1]['ineq'])
self.assertEqual(0.9, classifies_arr[-1]['thresh'])
self.assertEqual(0.8958797346, round(classifies_arr[-1]['alpha'], 10))
def test_build_stump(self):
print("Test Build Stump:")
data_mat, labels_arr = adb.load_simple_data()
w_data = np.mat(np.ones((5, 1)) / 5)
best_stump, min_error, best_estimation = adb.build_stump(
data_mat, labels_arr, w_data)
self.assertEqual(best_stump, {'dim': 0, 'ineq': 'lt', 'thresh': 1.3})
self.assertEqual(min_error, np.matrix([[0.2]]))
res = np.array([[-1.], [1.], [-1.], [-1.], [1.]])
self.assertEqual(True, (best_estimation == res).all())
def test_classify(self):
print("Test Classify:")
print("Classify Simple Data:")
data_mat, labels_arr = adb.load_simple_data()
classifies_arr, est_agg = adb.train(data_mat, labels_arr, 30)
pred = adb.classify([[5, 5], [0, 0]], classifies_arr)
res = np.matrix([[1.], [-1.]])
self.assertEqual(True, (pred == res).all())
print("Classify Loaded Data:")
datArr, labelArr = adb.load_data_set('horseColicTraining2.txt')
classiferArray, aggClassEst = adb.train(datArr, labelArr, 10)
testArr, testLabelArr = adb.load_data_set('horseColicTest2.txt')
prediction10 = adb.classify(testArr, classiferArray)
errArr = np.mat(np.ones((67, 1)))
err_rate = errArr[prediction10 != np.mat(testLabelArr).T].sum() / 67
self.assertEqual(16.0 / 67, err_rate)
print("Test Error: %f%%" % (err_rate * 100))
# 绘制ROC和计算AUC
val_auc = adb.plot_roc(aggClassEst, labelArr)
self.assertLessEqual(0.8582969635, round(val_auc, 10))
D = np.multiply(D, np.exp(expon))
D = D / np.sum(D)
agg_class_est += alpha * predict_value
print("agg_class_est: ", agg_class_est.T)
# np.sign(agg_class_est) != np.mat(class_labels).T 将错误的置位1 对的置位0 便于统计错误的个数
agg_errors = np.multiply(
np.sign(agg_class_est) != np.mat(class_labels).T, np.ones((m, 1)))
error_rate = agg_errors.sum() / m
print('total error:', error_rate)
if error_rate == 0:
break
return weak_class_arr
if __name__ == '__main__':
# 加载简单的数据
dat_arr, labels_arr = adaboost.load_simple_data()
# show_plot(dat_arr, labels_arr)
m = np.shape(dat_arr)[0]
D = np.mat(np.ones((m, 1)) / m)
# 最佳单层决策树
# best_stump, error, predict_value, = build_stump(dat_arr, labels_arr, D)
# print(best_stump, error)
# print(predict_value)
weak_class_arr = adaboost_train_ds(dat_arr, labels_arr)
print('********' * 10)
print(weak_class_arr)
agg_error = np.multiply(np.sign(agg_class_est) != np.mat(class_labels).T, np.ones((m, 1)))
error_rate = agg_error.sum()/m
<<<<<<< HEAD
print "total error: ", error_rate, "\n"
=======
# print "total error: ", error_rate, "\n"
>>>>>>> 68d745d9f4a5c0b75e4d74d7d47153b544aab2b9
if error_rate == 0:
break
return weak_class_arr
<<<<<<< HEAD
if __name__ == '__main__':
import adaboost
data_mat, class_labels = adaboost.load_simple_data()
a = adaboost.adaboost_train(data_mat, class_labels, 9)
print a
=======
def ada_classify(datto_class, classifier_arr):
data_mat = np.matrix(datto_class)
m = data_mat.shape[0]
agg_class_est = np.zeros((m, 1))
for i in range(len(classifier_arr)):
class_est = stump_classify(data_mat, classifier_arr[i]["dim"], classifier_arr[i]["threshold"],
classifier_arr[i]["inequality"])
agg_class_est += classifier_arr[i]["alpha"] * class_est
# print agg_class_est
# print np.sign(agg_class_est)
return np.sign(agg_class_est)