我在Python中使用rmsle作为评估指标训练LightGBM机器学习模型时，尝试启用早期停止功能时遇到了问题。
这是我的代码:
import numpy as npimport pandas as pdimport lightgbm as lgbfrom sklearn.model_selection import train_test_splitdf_train = pd.read_csv('train_data.csv')X_train = df_train.drop('target', axis=1)y_train = np.log(df_train['target'])sample_params = { 'boosting_type': 'gbdt', 'objective': 'regression', 'random_state': 42, 'metric': 'rmsle', 'lambda_l1': 5, 'lambda_l2': 5, 'num_leaves': 5, 'bagging_freq': 5, 'max_depth': 5, 'max_bin': 5, 'min_child_samples': 5, 'feature_fraction': 0.5, 'bagging_fraction': 0.5, 'learning_rate': 0.1,}X_train_tr, X_train_val, y_train_tr, y_train_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)def train_lightgbm(X_train_tr, y_train_tr, X_train_val, y_train_val, params, num_boost_round, early_stopping_rounds, verbose_eval): d_train = lgb.Dataset(X_train_tr, y_train_tr) d_val = lgb.Dataset(X_train_val, y_train_val) model = lgb.train( params=params, train_set=d_train, num_boost_round=num_boost_round, valid_sets=d_val, early_stopping_rounds=early_stopping_rounds, verbose_eval=verbose_eval, ) return modelmodel = train_lightgbm( X_train_tr, y_train_tr, X_train_val, y_train_val, params=sample_params, num_boost_round=500, early_stopping_rounds=True, verbose_eval=1)df_test = pd.read_csv('test_data.csv')X_test = df_test.drop('target', axis=1)y_test = np.log(df_test['target'])df_train['prediction'] = np.exp(model.predict(X_train))df_test['prediction'] = np.exp(model.predict(X_test))def rmsle(y_true, y_pred): assert len(y_true) == len(y_pred) return np.sqrt(np.mean(np.power(np.log1p(y_true + 1) - np.log1p(y_pred + 1), 2)))metric = rmsle(y_test, df_test['prediction'])print('Test Metric Value:', round(metric, 4))如果我在train_lightgbm方法中将early_stopping_rounds=False，代码可以正常编译。
但是，当我设置early_stopping_rounds=True时，它会抛出以下错误:
ValueError: For early stopping, at least one dataset and eval metric is required for evaluation.
如果我运行一个类似的脚本，但将sample_params中的’metric’: ‘rmse’改为’rmsle’，即使early_stopping_rounds=True，它也可以正常编译。
我需要添加什么才能让LightGBM识别我的数据集和评估指标？谢谢！
回答：
rmsle默认情况下不被LGB支持作为指标（查看这里以获取可用列表）
为了应用这个自定义指标，你需要定义一个自定义函数
def rmsle_lgbm(y_pred, data): y_true = np.array(data.get_label()) score = np.sqrt(np.mean(np.power(np.log1p(y_true) - np.log1p(y_pred), 2))) return 'rmsle', score, False以这种方式重新定义你的参数字典:
params = {....'objective': 'regression','metric': 'custom', # <=============....}然后进行训练
model = lgb.train( params=params, train_set=d_train, num_boost_round=num_boost_round, valid_sets=d_val, early_stopping_rounds=early_stopping_rounds, verbose_eval=verbose_eval, feval=rmsle_lgbm # <============= )附注: np.log(y + 1) = np.log1p(y) ===> np.log1p(y + 1) 看起来是个错误
