如何通过循环高效地向RandomForestRegressor传递超参数

hparams = {
    'n_estimators': 460,
    'bootstrap': False,
    # ... 其他参数
}
model_regressor = RandomForestRegressor(hparams)

model_regressor = RandomForestRegressor(**hparams)

from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score, mean_squared_error
import numpy as np

# 假设有一些示例数据
X = np.random.rand(100, 5) # 100个样本，5个特征
y = np.random.rand(100) * 10 # 100个目标值

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 定义多组超参数
hyperparams_sets = [
    {
        'n_estimators': 460,
        'bootstrap': False,
        'criterion': 'poisson', # 注意：Poisson准则通常用于计数数据，这里仅作示例
        'max_depth': 60,
        'max_features': 2,
        'min_samples_leaf': 1,
        'min_samples_split': 2,
        'random_state': 42 # 添加random_state以保证结果可复现
    },
    {
        'n_estimators': 60,
        'bootstrap': False,
        'criterion': 'friedman_mse',
        'max_depth': 90,
        'max_features': 3,
        'min_samples_leaf': 1,
        'min_samples_split': 2,
        'random_state': 42
    }
]

results = []

# 遍历每组超参数
for i, hparams in enumerate(hyperparams_sets):
    print(f"\n--- 正在使用第 {i+1} 组超参数 ---")
    print("当前超参数:", hparams)

    # 正确地解包字典并初始化模型
    model_regressor = RandomForestRegressor(**hparams)

    # 打印模型初始化后的参数，确认解包成功
    print("模型初始化参数:", model_regressor.get_params())

    total_r2_score_value = 0
    total_mean_squared_error_value = 0 # 更正变量名，保持一致

    total_tests = 5 # 减少循环次数以便快速演示

    # 进行多次训练和评估以获得更稳定的结果
    for index in range(1, total_tests + 1):
        print(f"  - 训练轮次 {index}/{total_tests}")

        # 模型训练
        model_regressor.fit(X_train, y_train)

        # 模型预测
        y_pred = model_regressor.predict(X_test)

        # 计算评估指标
        r2 = r2_score(y_test, y_pred)
        mse = mean_squared_error(y_test, y_pred)

        total_r2_score_value += r2
        total_mean_squared_error_value += mse

    avg_r2 = total_r2_score_value / total_tests
    avg_mse = total_mean_squared_error_value / total_tests

    print(f"平均 R2 分数: {avg_r2:.4f}")
    print(f"平均 均方误差 (MSE): {avg_mse:.4f}")

    results.append({
        'hyperparameters': hparams,
        'avg_r2_score': avg_r2,
        'avg_mean_squared_error': avg_mse
    })

print("\n--- 所有超参数组合的评估结果 ---")
for res in results:
    print(f"超参数: {res['hyperparameters']}")
    print(f"  平均 R2: {res['avg_r2_score']:.4f}")
    print(f"  平均 MSE: {res['avg_mean_squared_error']:.4f}")