2021-10-27

# K折交叉验证
from sklearn.model_selection import KFold
​
kf = KFold(n_splits=10) # 10折
​
rmse_scores = [] # 保存10折运行的结果
​
​
for train_indices, test_indices in kf.split(X): # 分割元数据，生成索引
    X_train, X_test = X[train_indices], X[test_indices] # 训练集和验证集
    y_train, y_test = y[train_indices], y[test_indices] # 训练标签集和验证标签集
    # 初始化线性回归模型对象
    LR = LinearRegression(normalize=True)
    LR.fit(X_train, y_train) # 训练
    y_pred = LR.predict(X_test) # 预测
    rmse = np.sqrt(mean_absolute_error(np.log(y_test), np.log(abs(y_pred)))) # 评估
    rmse_scores.append(rmse) # 累计每一轮的验证结果
   
​
print("rmse scores : ", rmse_scores)
print(f'average rmse score : {np.mean(rmse_scores)}')

# 2 随机森林（回归）
from sklearn.ensemble import RandomForestRegressor​# K折交叉验证kf = KFold(n_splits=10)​rmse_scores = [] ​for train_indices, test_indices in kf.split(X):    X_train, X_test = X[train_indices], X[test_indices]    y_train, y_test = y[train_indices], y[test_indices]    # 初始化模型    RFR = RandomForestRegressor() # 基模型    # 训练/fit拟合    RFR.fit(X_train, y_train)    # 预测    y_pred = RFR.predict(X_test)    # 评估    rmse = mean_absolute_error(y_test, y_pred)    # 累计结果    rmse_scores.append(rmse)​print("rmse scores : ", rmse_scores)print(f'average rmse scores : {np.mean(rmse_scores)}')