from sklearn.metrics import mean_squared.error
# 计算MSE
mse_train1=mean_squared.error(y_train_pred1,y_train)
mse_train3=mean_squared.error(y_train_pred3,y_train)
mse_train10=mean_squared.error(y_train_pred10,y_train)
mse_train30=mean_squared.error(y_train_pred30,y_train)# 打印结果print('MSE:')print('1 order polynomial:{:.2f}'.format(mse_train1))print('3 order polynomial:{:.2f}'.format(mse_train3))print('10 order polynomial:{:.2f}'.format(mse_train10))print('30 order polynomial:{:.2f}'.format(mse_train30))# 输出结果
MSE:1 order polynomial:149.923 order polynomial:24.3210 order polynomial:23.6430 order polynomial:15.05
指标说明:
训练集MSE指标从好到坏的模型是:30阶多项式、10阶多项式、3阶多项式、1阶多项式
4.测试集检验
4.1多项式特征模型预测函数
defpoly_fit_predict(degree,X,y,model):#如果degree不是整数就报错ifnotisinstance(degree,int):raise ValueError('degree should be interger.')#如果degree不大于0就报错if degree <=0:raise Valuation('degree should be greater than 0.')# 为了满足model.fit函数的输入要求,将特征函数数据从一维变成二维,即从(samples,)变为(samples,1)
X_2D=X.reshape(-1,1)# 如果degree大于1,生成多项式数据if degree>1:
poly=PolynomialFeatures(degree=degree,include_bias=False)
X_2D=poly.fit_transform(X_2D)#数据标准化(减均值除标准差)
scaler=StandarScaler()
X_2D=scaler.fit_transform(X_2D)#模型预测
y_pred=model.predict(X_2D)# 画出样本的散点图
plt.scatter(X,y,maker='o',
color='c',label='test dataset')# 画出预测函数曲线
plt.plot(np.sort(X),y_pred[np.argsort(X)],
color='r',label=str(degree)+'order fitting')
plt.legend()
plt.xlabel('x')
plt.ylabel('y')
plt.show()return y_pred
# 计算MSE
mse_test1=mean_squared.error(y_test_pred1,y_test)
mse_test3=mean_squared.error(y_test_pred3,y_test)
mse_test10=mean_squared.error(y_test_pred10,y_test)
mse_test30=mean_squared.error(y_test_pred30,y_test)# 打印结果print('MSE:')print('1 order polynomial:{:.2f}'.format(mse_test1))print('3 order polynomial:{:.2f}'.format(mse_test3))print('10 order polynomial:{:.2f}'.format(mse_test10))print('30 order polynomial:{:.2f}'.format(mse_test30))# 输出结果
MSE:1 order polynomial:659.953 order polynomial:39.7110 order polynomial:41.0030 order polynomial:85.45
欠拟合与过拟合解释实例–多项式拟合1.导入必要的模块import numpy as npimport pandas as pdimport matplotlib.pyplot as plt2.生成数据2.1构建数据生成函数def data_generator(samples,random_seed=0): np.random.seed(random_seed)# 设置随机种子 X=np.random.uniform(-5,5,size=samples)# 从-5到5中随机抽取100个实数