8-6 验证数据集与交叉验证
Nnotbook 示例
Notbook 源码
1 交叉验证
2 [1]
3 import numpy as np
4 from sklearn import datasets
5 [2]
6 digits = datasets.load_digits()
7 X = digits.data
8 y = digits.target
9 测试 train_test_split
10 [3]
11 from sklearn.model_selection import train_test_split
12 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=666)
13 [4]
14 from sklearn.neighbors import KNeighborsClassifier
15
16 best_score, best_p, best_k = 0, 0, 0
17 for k in range(2,11):
18 for p in range(1,6):
19 knn_clf = KNeighborsClassifier(weights="distance",n_neighbors=k,p=p)
20 knn_clf.fit(X_train, y_train)
21 score = knn_clf.score(X_test,y_test)
22 if score > best_score:
23 best_score, best_p, best_k = score, p, k
24
25 print("Best_k = ", best_k)
26 print("Best_p = ",best_p)
27 print("Best_score = ",best_score)
28 Best_k = 3
29 Best_p = 2
30 Best_score = 0.9860917941585535
31
32 使用交叉验证
33 [5]
34 from sklearn.model_selection import cross_val_score
35
36 knn_clf = KNeighborsClassifier()
37 cross_val_score(knn_clf, X_train,y_train)
38 array([0.99537037, 0.98148148, 0.97685185, 0.97674419, 0.97209302])
39 [6]
40 best_score, best_p, best_k = 0, 0, 0
41 for k in range(2,11):
42 for p in range(1,6):
43 knn_clf = KNeighborsClassifier(weights="distance",n_neighbors=k,p=p)
44 knn_clf.fit(X_train, y_train)
45 scores = cross_val_score(knn_clf,X_train,y_train)
46 score = np.mean(scores)
47 if score > best_score:
48 best_score, best_p, best_k = score, p, k
49
50 print("Best_k = ", best_k)
51 print("Best_p = ",best_p)
52 print("Best_score = ",best_score)
53 Best_k = 2
54 Best_p = 2
55 Best_score = 0.9851507321274763
56
57 [7]
58 best_knn_clf = KNeighborsClassifier(weights="distance", n_neighbors =2,p=2)
59 [8]
60 best_knn_clf.fit(X_train, y_train)
61 best_knn_clf.score(X_test, y_test)
62 0.980528511821975
63 回顾网格搜索
64 [13]
65 from sklearn.model_selection import GridSearchCV
66
67 param_grid = [
68 {
69 "weights":["distance"],
70 "n_neighbors":[i for i in range(2,11)],
71 "p":[i for i in range(1,6)]
72 }
73 ]
74
75 grid_search = GridSearchCV(knn_clf, param_grid, verbose=1)
76 grid_search.fit(X_train,y_train)
77 Fitting 5 folds for each of 45 candidates, totalling 225 fits
78
79 GridSearchCV(estimator=KNeighborsClassifier(n_neighbors=10, p=5,
80 weights='distance'),
81 param_grid=[{'n_neighbors': [2, 3, 4, 5, 6, 7, 8, 9, 10],
82 'p': [1, 2, 3, 4, 5], 'weights': ['distance']}],
83 verbose=1)
84 [14]
85 grid_search.best_score_
86 0.9851507321274763
87 [15]
88 grid_search.best_params_
89 {'n_neighbors': 2, 'p': 2, 'weights': 'distance'}
90 [17]
91 best_knn_clf = grid_search.best_estimator_
92 best_knn_clf.score(X_test,y_test)
93 0.980528511821975
94 [18]
95 cross_val_score(knn_clf, X_train,y_train,cv=3)
96 array([0.98055556, 0.98050139, 0.96100279])
97 [19]
98 GridSearchCV(knn_clf, param_grid, verbose=1, cv=3)
99 GridSearchCV(cv=3,
100 estimator=KNeighborsClassifier(n_neighbors=10, p=5,
101 weights='distance'),
102 param_grid=[{'n_neighbors': [2, 3, 4, 5, 6, 7, 8, 9, 10],
103 'p': [1, 2, 3, 4, 5], 'weights': ['distance']}],
104 verbose=1)
8-7 偏差方差平衡
8-8 模型泛化与岭回归
Notbook 示例
Notbook 源码
1 [1]
2 import numpy as np
3 import matplotlib.pyplot as plt
4 [2]
5 x = np.random.uniform(-3, 3, size=100)
6 X = x.reshape(-1,1)
7 y = 0.5 * x**2 + x + 2 + np.random.normal(0, 1, size=100)
8 [3]
9 from sklearn.linear_model import LinearRegression
10 from sklearn.pipeline import Pipeline
11 from sklearn.preprocessing import PolynomialFeatures
12 from sklearn.preprocessing import StandardScaler
13
14 lin_reg = LinearRegression()
15 def PolynomialRegression(degree):
16 return Pipeline([
17 ("poly",PolynomialFeatures(degree=degree)),#!!!!!!!!!
18 ("std_scaler",StandardScaler()),
19 ("lin_reg",lin_reg)
20 ])
21 [4]
22 from sklearn.metrics import mean_squared_error
23
24 poly100_reg = PolynomialRegression(degree=100)
25 poly100_reg.fit(X,y)
26 y100_predict = poly100_reg.predict(X)
27 mean_squared_error(y,y100_predict)
28 0.3630662022937054
29 [5]
30 X_plot = np.linspace(-3, 3, 100).reshape(100,1)
31 y_plot = poly100_reg.predict(X_plot)
32
33 plt.scatter(x,y)
34 plt.plot(X_plot[:,0],y_plot,color='r')
35 plt.axis([-3, 3, 0, 10])
36 (-3.0, 3.0, 0.0, 10.0)
37
38 [7]
39 lin_reg.coef_
40 array([ 2.85566833e+13, -4.86652731e+00, -7.63042344e+01, 6.36319430e+02,
41 6.80489039e+03, -2.54310157e+04, -2.61198355e+05, 4.27336689e+05,
42 5.34542751e+06, -6.94337912e+05, -6.10790341e+07, -8.57691190e+07,
43 3.45202670e+08, 1.52465049e+09, 1.63928865e+08, -1.37144024e+10,
44 -1.83536476e+10, 7.66032914e+10, 1.51424297e+11, -2.77869759e+11,
45 -6.87557673e+11, 6.35340216e+11, 1.95698070e+12, -7.64753325e+11,
46 -3.41717491e+12, -5.12331050e+10, 2.97457272e+12, 1.50129966e+12,
47 3.40803862e+11, -1.39777394e+12, -2.30445737e+12, -1.21676316e+12,
48 -1.35548542e+12, 3.17823462e+12, 4.37853931e+12, -2.07598680e+12,
49 7.58006069e+11, 2.79811420e+11, -5.12394013e+12, 7.17900735e+11,
50 3.11502081e+11, -1.29435321e+12, 3.24230619e+12, 1.90755460e+11,
51 -1.82400131e+12, 6.13112904e+11, 2.74467307e+12, 7.50934834e+11,
52 -1.11741536e+12, -1.12780418e+12, -1.79875318e+12, 1.00555887e+12,
53 -1.81669614e+12, -2.06157950e+11, 1.95131392e+12, -1.64604514e+12,
54 2.95054100e+12, -3.60793010e+11, -2.25796459e+12, 3.78295754e+11,
55 -1.55480037e+12, 2.64352577e+12, 2.96302159e+12, 6.25824566e+11,
56 6.90176136e+11, -2.17209673e+12, -2.54504094e+12, 1.19441715e+11,
57 -1.56445519e+12, 5.18954696e+11, 7.81463582e+10, -2.19228398e+12,
58 1.65924203e+12, -4.84099102e+11, 1.29028838e+12, 5.91610483e+10,
59 3.85131883e+11, 2.18088026e+12, 7.85255857e+10, 4.20546626e+12,
60 -2.34625370e+12, -1.77089952e+12, 1.25388875e+11, -4.66199247e+12,
61 -5.50443098e+11, 9.78014262e+11, 1.54262864e+12, 4.78137117e+11,
62 6.60472983e+11, -1.09921649e+12, -1.21323016e+12, 2.42539428e+12,
63 3.52655517e+11, 5.42616419e+11, -1.52587784e+11, -1.43140935e+12,
64 -3.82481390e+11, -8.61566638e+10, 7.93538571e+11, 2.24669016e+11,
65 -3.49271059e+11])
66 岭回归
67 [10]
68 np.random.seed(42)
69 x = np.random.uniform(-3.0, 3.0, size=100)
70 X = x.reshape(-1,1)
71 y = 0.5 * x + 3 + np.random.normal(0, 1, size=100)
72 [11]
73 plt.scatter(x,y)
74 <matplotlib.collections.PathCollection at 0x1a7f0b35d00>
1 岭回归
2 [1]
3 import numpy as np
4 import matplotlib.pyplot as plt
5 [2]
6 np.random.seed(42)
7 x = np.random.uniform(-3.0, 3.0, size=100)
8 X = x.reshape(-1,1)
9 y = 0.5 * x + 3 + np.random.normal(0, 1, size=100)
10 [3]
11 plt.scatter(x,y)
12 <matplotlib.collections.PathCollection at 0x247e4798910>
13
14 [4]
15 from sklearn.linear_model import LinearRegression
16 from sklearn.pipeline import Pipeline
17 from sklearn.preprocessing import PolynomialFeatures
18 from sklearn.preprocessing import StandardScaler
19
20 def PolynomialRegression(degree):
21 return Pipeline([
22 ("poly",PolynomialFeatures(degree=degree)),#!!!!!!!!!
23 ("std_scaler",StandardScaler()),
24 ("lin_reg",LinearRegression())
25 ])
26 [5]
27 from sklearn.model_selection import train_test_split
28
29 np.random.seed(666)
30 X_train, X_test, y_train, y_test = train_test_split(X, y)
31 [6]
32 from sklearn.metrics import mean_squared_error
33
34 poly_reg = PolynomialRegression(degree=20)
35 poly_reg.fit(X_train,y_train)
36
37 y_poly_predict = poly_reg.predict(X_test)
38 mean_squared_error(y_test,y_poly_predict)
39 167.9401086187559
40 [7]
41 X_plot = np.linspace(-3, 3, 100).reshape(100,1)
42 y_plot = poly_reg.predict(X_plot)
43
44 plt.scatter(x,y)
45 plt.plot(X_plot[:,0],y_plot,color='r')
46 plt.axis([-3, 3, 0, 10])
47 (-3.0, 3.0, 0.0, 10.0)
48
49 [8]
50 def plot_model(model):
51 X_plot = np.linspace(-3, 3, 100).reshape(100,1)
52 y_plot = model.predict(X_plot)
53
54 plt.scatter(x,y)
55 plt.plot(X_plot[:,0],y_plot,color='r')
56 plt.axis([-3, 3, 0, 10])
57
58 plot_model(poly_reg)
59
60 使用岭回归
61 [9]
62 from sklearn.linear_model import Ridge
63
64 def RidgeRegression(degree, alpha):
65 return Pipeline([
66 ("poly",PolynomialFeatures(degree=degree)),
67 ("std_scaler",StandardScaler()),
68 ("lin_reg",Ridge(alpha=alpha))
69 ])
70 [10]
71 ridg1_reg = RidgeRegression(20,0.0001)
72 ridg1_reg.fit(X_train,y_train)
73
74 y1_predict = ridg1_reg.predict(X_test)
75 mean_squared_error(y_test,y1_predict)
76 1.323349275399316
77 [11]
78 plot_model(ridg1_reg)
79
80 [13]
81 ridg2_reg = RidgeRegression(20,1)
82 ridg2_reg.fit(X_train,y_train)
83
84 y2_predict = ridg2_reg.predict(X_test)
85 mean_squared_error(y_test,y2_predict)
86 1.1888759304218464
87 [14]
88 plot_model(ridg2_reg)
89
90 [16]
91 ridg3_reg = RidgeRegression(20,100)
92 ridg3_reg.fit(X_train,y_train)
93
94 y3_predict = ridg3_reg.predict(X_test)
95 mean_squared_error(y_test,y3_predict)
96 1.31964561130862
97 [17]
98 plot_model(ridg3_reg)
99
100 [18]
101 ridg4_reg = RidgeRegression(20,1000000000)
102 ridg4_reg.fit(X_train,y_train)
103
104 y4_predict = ridg4_reg.predict(X_test)
105 mean_squared_error(y_test,y4_predict)
106 1.8408934818370333
107 [19]
108 plot_model(ridg4_reg)
8-9 LASSO
标签：11,12,泛化,章下,train,多项式,score,reg,best From： https://www.cnblogs.com/Cai-Gbro/p/16837642.html