机器学习——监督分类MLP 二分类的不确定估计

Posted 2021-03-03 smartisn

代码：

 1 # -- coding: gbk --
 2 from sklearn.datasets import load_breast_cancer
 3 from sklearn.model_selection import  train_test_split
 4 import pandas as pd
 5 import mglearn
 6 from sklearn.neural_network import MLPClassifier
 7 from sklearn.datasets import make_moons
 8 from sklearn.ensemble import GradientBoostingClassifier
 9 from sklearn.datasets import make_circles
10 from pylab import *
11 from sklearn.datasets import load_iris
12 
13 def MLP初理解():
14     X, y = make_moons(n_samples=100, noise=0.25, random_state=3)
15     print(X.shape)
16     print(y.shape)
17     X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)
18 
19     mlp = MLPClassifier(solver=‘lbfgs‘, random_state=0).fit(X_train, y_train)
20     ‘‘‘降低隐节点‘‘‘
21     #mlp = MLPClassifier(solver=‘lbfgs‘, random_state=0, hidden_layer_sizes=[10])
22     # 使用2个隐层，每个包含10个单元
23     #mlp = MLPClassifier(solver=‘lbfgs‘, random_state=0,hidden_layer_sizes=[10, 10])
24 
25     # 使用2个隐层，每个包含10个单元，这次使用tanh非线性
26     #mlp = MLPClassifier(solver=‘lbfgs‘, activation=‘tanh‘, random_state=0, hidden_layer_sizes=[10, 10])
27 
28 def MLP理解():
29     cancer=load_breast_cancer()
30     X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)
31     mlp = MLPClassifier(random_state=42)
32     mlp.fit(X_train, y_train)
33     y_pred=mlp.predict(X_test)
34     print(np.mean(y_pred==y_test))
35 
36     ‘‘‘消除数据缩放‘‘‘
37     ‘‘‘计算每个特征平均值‘‘‘
38     mean_on_train = X_train.mean(axis=0)
39     ‘‘‘每个特征标准差‘‘‘
40     std_on_train = X_train.std(axis=0)
41     X_train_scaled = (X_train - mean_on_train) / std_on_train
42     X_test_scaled = (X_test - mean_on_train) / std_on_train
43     mlp = MLPClassifier(max_iter=1000,alpha=1,random_state=0)
44     mlp.fit(X_train_scaled, y_train)
45     print("Accuracy on training set: {:.3f}".format(mlp.score(X_train_scaled, y_train)))
46     print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))
47 
48 def 二分类的不确定估计():
49     X, y = make_circles(noise=0.25, factor=0.5, random_state=1)
50     y_named = np.array(["blue", "red"])[y]
51     X_train, X_test, y_train_named, y_test_named, y_train, y_test = 52         train_test_split(X, y_named, y, random_state=0)
53     gbrt = GradientBoostingClassifier(random_state=0)
54     gbrt.fit(X_train, y_train_named)
55     y_pred=gbrt.predict(X_test)
56     print(y_pred)
57     ‘‘‘估计概率‘‘‘
58     y_pred = gbrt.predict_proba(X_test)
59     print(y_pred)
60     print("Predicted probabilities:
{}".format(gbrt.predict_proba(X_test[:6])))
61 if __name__ ==‘__main__‘:
62     iris = load_iris()
63     X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=42)
64     gbrt = GradientBoostingClassifier(learning_rate=0.01, random_state=0)
65     gbrt.fit(X_train, y_train)
66     print("Decision function shape: {}".format(gbrt.decision_function(X_test).shape))