机器学习--基础算法--集成学习

1 什么是集成学习

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

x, y = datasets.make_moons(n_samples=500, noise = 0.3, random_state=42)

plt.scatter(x[y == 0, 0], x[y == 0, 1])
plt.scatter(x[y == 1, 0], x[y == 1, 1])
plt.show()

输出：

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y)

# 使用逻辑回归预测
from sklearn.linear_model import LogisticRegression
log_reg = LogisticRegression()
log_reg.fit(x_train, y_train)
log_reg.score(x_test, y_test)
>>>0.864

# 使用支撑向量机
from sklearn.svm import SVC
svc = SVC()
svc.fit(x_train, y_train)
svc.score(x_test, y_test)
>>>0.928

# 使用决策树
from sklearn.tree import DecisionTreeClassifier
dt_clf = DecisionTreeClassifier()
dt_clf.fit(x_train, y_train)
dt_clf.score(x_test, y_test)
>>>0.856

# 得到不同模型对测试数据集的预测值
y_predict1 = log_reg.predict(x_test)
y_predict2 = svc.predict(x_test)
y_predict3 = dt_clf.predict(x_test)

# 得到三种模型预测值的投票结果
y_predict = np.array(y_predict1 + y_predict2 + y_predict3 >= 2, dtype = 'int')

# 查看y_predict的准确度
from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_predict)
>>>0.928

使用集成学习：