s = 0
for X, y in zip(X_data, y_data):
if self._fx(X) != y:
s += 1
if s / self.N <= self.epsilon: # 分类错误数目占比小于等于epsilon, 停止训练
print('the err ratio is {0}'.format(s / self.N))
break
return
def predict(self, X):
# 预测
return self._fx(X)
if __name__ == '__main__':
X_data_raw = np.linspace(-50, 50, 100)
np.random.shuffle(X_data_raw)
y_data = np.sign(X_data_raw)
X_data = np.transpose([X_data_raw])
from machine_learning_algorithm.cross_validation import validate
g = validate(X_data, y_data)
for item in g:
X_train, y_train, X_test, y_test = item
AB = AdaBoost(epsilon=0.02)
AB.fit(X_train, y_train)
score = 0
for X, y in zip(X_test, y_test):
if AB.predict(X) == y:
score += 1
print(score / len(y_test))
self.disp_helper(current_node.right)
return
if __name__ == '__main__':
from sklearn.datasets import load_iris
X_data = load_iris().data
y_data = load_iris().target
from machine_learning_algorithm.cross_validation import validate
g = validate(X_data, y_data, ratio=0.2)
for item in g:
X_data_train, y_data_train, X_data_test, y_data_test = item
clf = CART_CLF()
clf.fit(X_data_train, y_data_train)
score = 0
for X, y in zip(X_data_test, y_data_test):
if clf.predict(X) == y: