机器学习之路: python 线性回归LinearRegression, 随机参数回归SGDRegressor 预测波士顿房价

python3学习使用api

线性回归，和 随机参数回归

git: https://github.com/linyi0604/MachineLearning

 1 from sklearn.datasets import load_boston
 2 from sklearn.cross_validation import train_test_split
 3 from sklearn.preprocessing import StandardScaler
 4 from sklearn.linear_model import LinearRegression, SGDRegressor
 5 from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
 6 import numpy as np
 7
 8 # 1 准备数据
 9 # 读取波士顿地区房价信息
10 boston = load_boston()
11 # 查看数据描述
12 # print(boston.DESCR)   # 共506条波士顿地区房价信息，每条13项数值特征描述和目标房价
13 # 查看数据的差异情况
14 # print("最大房价：", np.max(boston.target))   # 50
15 # print("最小房价：",np.min(boston.target))    # 5
16 # print("平均房价：", np.mean(boston.target))   # 22.532806324110677
17
18 x = boston.data
19 y = boston.target
20
21 # 2 分割训练数据和测试数据
22 # 随机采样25%作为测试 75%作为训练
23 x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=33)
24
25
26 # 3 训练数据和测试数据进行标准化处理
27 ss_x = StandardScaler()
28 x_train = ss_x.fit_transform(x_train)
29 x_test = ss_x.transform(x_test)
30
31 ss_y = StandardScaler()
32 y_train = ss_y.fit_transform(y_train.reshape(-1, 1))
33 y_test = ss_y.transform(y_test.reshape(-1, 1))
34
35 # 4 使用两种线性回归模型进行训练和预测
36 # 初始化LinearRegression线性回归模型
37 lr = LinearRegression()
38 # 训练
39 lr.fit(x_train, y_train)
40 # 预测 保存预测结果
41 lr_y_predict = lr.predict(x_test)
42
43 # 初始化SGDRRegressor随机梯度回归模型
44 sgdr = SGDRegressor()
45 # 训练
46 sgdr.fit(x_train, y_train)
47 # 预测 保存预测结果
48 sgdr_y_predict = sgdr.predict(x_test)
49
50 # 5 模型评估
51 # 对Linear模型评估
52 lr_score = lr.score(x_test, y_test)
53 print("Linear的默认评估值为：", lr_score)
54 lr_R_squared = r2_score(y_test, lr_y_predict)
55 print("Linear的R_squared值为：", lr_R_squared)
56 lr_mse = mean_squared_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(lr_y_predict))
57 print("Linear的均方误差为:", lr_mse)
58 lr_mae = mean_absolute_error(ss_y.inverse_transform(y_test),ss_y.inverse_transform(lr_y_predict))
59 print("Linear的平均绝对误差为:", lr_mae)
60
61 # 对SGD模型评估
62 sgdr_score = sgdr.score(x_test, y_test)
63 print("SGD的默认评估值为：", sgdr_score)
64 sgdr_R_squared = r2_score(y_test, sgdr_y_predict)
65 print("SGD的R_squared值为：", sgdr_R_squared)
66 sgdr_mse = mean_squared_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(sgdr_y_predict))
67 print("SGD的均方误差为:", sgdr_mse)
68 sgdr_mae = mean_absolute_error(ss_y.inverse_transform(y_test), ss_y.inverse_transform(sgdr_y_predict))
69 print("SGD的平均绝对误差为:", sgdr_mae)
70
71 ‘‘‘
72 Linear的默认评估值为： 0.6763403830998702
73 Linear的R_squared值为： 0.6763403830998701
74 Linear的均方误差为: 25.09698569206773
75 Linear的平均绝对误差为: 3.5261239963985433
76
77 SGD的默认评估值为： 0.659795654161198
78 SGD的R_squared值为： 0.659795654161198
79 SGD的均方误差为: 26.379885392159494
80 SGD的平均绝对误差为: 3.5094445431026413
81 ‘‘‘

原文地址：https://www.cnblogs.com/Lin-Yi/p/8971798.html