波士顿房价预测正则化代码实现

import pandas as pd from sklearn.linear_model import LinearRegression, Lasso, Ridge, ElasticNet from sklearn.model_selection import train_test_split from sklearn.preprocessing import PolynomialFeatures import warnings warnings.filterwarnings("ignore") # 加载数据 data = pd.read_csv('./boston_housing.data', sep='\s+', header=None) # 获取特征属性X和目标属性Y X = data.iloc[:, :-1] Y = data.iloc[:, -1] # 划分训练集和测试集 x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=10) # 多项式扩展 poly = PolynomialFeatures(degree=3, interaction_only=False, include_bias=True) x_train_poly = poly.fit_transform(x_train) x_test_poly = poly.transform(x_test) '''linear模型''' # 构建模型 linear = LinearRegression() # 模型训练 linear.fit(x_train_poly, y_train) # 预测 测试集 y_test_hat1 = linear.predict(x_test_poly) # 评估 print(linear.score(x_train_poly, y_train)) # 1.0 print(linear.score(x_test_poly, y_test)) # -4922.138866671163 '''Lasso模型''' # 构建模型 lasso = Lasso(alpha=10000) # 模型训练 lasso.fit(x_train_poly, y_train) # 预测 测试集 y_test_hat2 = lasso.predict(x_test_poly) # 评估 print(lasso.score(x_train_poly, y_train)) # 0.8612579413693275 print(lasso.score(x_test_poly, y_test)) # 0.8183003056515205 ''' Ridge模型''' # 构建模型 ridge = Ridge(alpha=1000000000000) # 模型训练 ridge.fit(x_train_poly, y_train) # 预测 测试集 y_test_hat3 = ridge.predict(x_test_poly) # 评估 print(ridge.score(x_train_poly, y_train)) # 0.8177143202090826 print(ridge.score(x_test_poly, y_test)) # 0.773014538352527 ''' ElasticNet模型''' # 构建模型 elasticNet = ElasticNet(alpha=600) # 模型训练 elasticNet.fit(x_train_poly, y_train) # 预测 测试集 y_test_hat4 = elasticNet.predict(x_test_poly) # 评估 print(elasticNet.score(x_train_poly, y_train)) # 0.9047004688116072 print(elasticNet.score(x_test_poly, y_test)) # 0.8246288062659108