因为注释已经很详细了,所以直接上代码:

 1 # -- coding: gbk --
 2 import mglearn
 3 from pylab import *
 4 from sklearn.model_selection import train_test_split
 5 mpl.rcParams['font.sans-serif'] = ['SimHei']
 6 from sklearn.datasets import load_breast_cancer
 7 from sklearn.datasets import load_boston
 8 from sklearn.linear_model import LinearRegression
 9 import sklearn
10 from sklearn.linear_model import Ridge
11 from sklearn.linear_model import Lasso
12 from sklearn.linear_model import ElasticNet
13 def forge数据集():
14     print("A")
15     X,y=mglearn.datasets.make_forge()
16     print(X.shape)
17     print(y.shape)
18     mglearn.discrete_scatter(X[:, 0], X[:, 1], y)
19     plt.legend(["Class 0", "Class 1"], loc=4)
20     plt.xlabel("第一特征")
21     plt.ylabel("第二特征")
22     #plt.show()
23 
24 def wave数据集():
25     X,y=mglearn.datasets.make_wave(n_samples=40)
26     plt.plot(X, y, 'o')
27     plt.ylim(-3, 3)
28     plt.xlabel("Feature")
29     plt.ylabel("Target")
30     plt.show()
31 
32 def 肿瘤数据集():
33     cancer=load_breast_cancer()
34     print(cancer.keys())
35     print("AAAA")
36     print(np.bincount(cancer.target))
37     print("Sample counts per class:\n{}".format(
38         {n: v for n, v in zip(cancer.target_names, np.bincount(cancer.target))}))
39 
40 def 波士顿():
41     boston = load_boston()
42     print("Data shape: {}".format(boston.data.shape))
43 
44 def 线性回归_最小二乘法():
45     X, y = mglearn.datasets.load_extended_boston()
46     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
47 
48     '''最小二乘法'''
49     lr = LinearRegression().fit(X_train, y_train)
50     print("斜率", lr.coef_)
51     print("截距", lr.intercept_)
52 
53     '''评测数据'''
54     print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
55     print("Test set score: {:.2f}".format(lr.score(X_test, y_test)))
56 
57 def 岭回归Ridge():
58     X, y = mglearn.datasets.load_extended_boston()
59     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
60     ridge = Ridge(alpha=10).fit(X_train, y_train)
61     '''岭回归'''
62     print("斜率", ridge.coef_)
63     print("截距", ridge.intercept_)
64 
65     '''评测'''
66     print("Training set score: {:.2f}".format(ridge.score(X_train, y_train)))
67     print("Test set score: {:.2f}".format(ridge.score(X_test, y_test)))
68 
69 def lasso():
70     X, y = mglearn.datasets.load_extended_boston()
71     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
72     lasso = Lasso().fit(X_train, y_train)
73     '''lasso'''
74     print("斜率", lasso.coef_)
75     print("截距", lasso.intercept_)
76 
77     '''评测'''
78     print("Training set score: {:.2f}".format(lasso.score(X_train, y_train)))
79     print("Test set score: {:.2f}".format(lasso.score(X_test, y_test)))
80     print("Number of features used: {}".format(np.sum(lasso.coef_ != 0)))
81 
82     lasso001 = Lasso(alpha=0.01, max_iter=100000).fit(X_train, y_train)
83     print("Training set score: {:.2f}".format(lasso001.score(X_train, y_train)))
84     print("Test set score: {:.2f}".format(lasso001.score(X_test, y_test)))
85     print("Number of features used: {}".format(np.sum(lasso001.coef_ != 0)))
86 
87 def ElasticNet_L1正则化_L2正则化():
88     X, y = mglearn.datasets.load_extended_boston()
89     X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
90     lasso = ElasticNet().fit(X_train, y_train)
91     '''lasso'''
92     print("斜率", lasso.coef_)
93     print("截距", lasso.intercept_)
94 if __name__ =='__main__':
95     lasso()