机器学习——监督分类MLP 二分类的不确定估计

代码：

# -- coding: gbk --
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import  train_test_split
import pandas as pd
import mglearn
from sklearn.neural_network import MLPClassifier
from sklearn.datasets import make_moons
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.datasets import make_circles
from pylab import *
from sklearn.datasets import load_iris

def MLP初理解():
    X, y = make_moons(n_samples=100, noise=0.25, random_state=3)
    print(X.shape)
    print(y.shape)
    X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)

    mlp = MLPClassifier(solver='lbfgs', random_state=0).fit(X_train, y_train)
    '''降低隐节点'''
    #mlp = MLPClassifier(solver='lbfgs', random_state=0, hidden_layer_sizes=[10])
    # 使用2个隐层，每个包含10个单元
    #mlp = MLPClassifier(solver='lbfgs', random_state=0,hidden_layer_sizes=[10, 10])

    # 使用2个隐层，每个包含10个单元，这次使用tanh非线性
    #mlp = MLPClassifier(solver='lbfgs', activation='tanh', random_state=0, hidden_layer_sizes=[10, 10])

def MLP理解():
    cancer=load_breast_cancer()
    X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)
    mlp = MLPClassifier(random_state=42)
    mlp.fit(X_train, y_train)
    y_pred=mlp.predict(X_test)
    print(np.mean(y_pred==y_test))

    '''消除数据缩放'''
    '''计算每个特征平均值'''
    mean_on_train = X_train.mean(axis=0)
    '''每个特征标准差'''
    std_on_train = X_train.std(axis=0)
    X_train_scaled = (X_train - mean_on_train) / std_on_train
    X_test_scaled = (X_test - mean_on_train) / std_on_train
    mlp = MLPClassifier(max_iter=1000,alpha=1,random_state=0)
    mlp.fit(X_train_scaled, y_train)
    print("Accuracy on training set: {:.3f}".format(mlp.score(X_train_scaled, y_train)))
    print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))

def 二分类的不确定估计():
    X, y = make_circles(noise=0.25, factor=0.5, random_state=1)
    y_named = np.array(["blue", "red"])[y]
    X_train, X_test, y_train_named, y_test_named, y_train, y_test = \
        train_test_split(X, y_named, y, random_state=0)
    gbrt = GradientBoostingClassifier(random_state=0)
    gbrt.fit(X_train, y_train_named)
    y_pred=gbrt.predict(X_test)
    print(y_pred)
    '''估计概率'''
    y_pred = gbrt.predict_proba(X_test)
    print(y_pred)
    print("Predicted probabilities:\n{}".format(gbrt.predict_proba(X_test[:6])))
if __name__ =='__main__':
    iris = load_iris()
    X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=42)
    gbrt = GradientBoostingClassifier(learning_rate=0.01, random_state=0)
    gbrt.fit(X_train, y_train)
    print("Decision function shape: {}".format(gbrt.decision_function(X_test).shape))