Question

在我使用VS法典中的灯光时,我会遇到一个问题:

parameters = {
 application :  binary ,
 objective :  binary ,
 metric :  auc ,
 is_unbalance :  true ,
 boosting :  gbdt ,
 num_leaves : 50,#31,
 feature_fraction : 0.8,
 bagging_fraction : 0.8,
 bagging_freq : 20,
 learning_rate : 0.003,
 max_depth : 5,
 verbose : 0}
model = lgb.train(parameters,
            train_data_lgb,
            valid_sets=test_data_lgb,
            num_boost_round=3000,
            early_stopping_rounds=100)

错误是:

TypeError                                 Traceback (most recent 
call last)
c:Userslvn06DesktopML bootcampSesión 52. Bagging y Boosting - Clasificación.ipynb Cell 178 line 1
----> 1 model = lgb.train(parameters,
  2                 train_data_lgb,
  3                 valid_sets=test_data_lgb,
  4                 num_boost_round=3000,
  5                 early_stopping_rounds=100)

TypeError: train() got an unexpected keyword argument  early_stopping_rounds

我正在寻找解决办法,但却没有找到解决办法。

Answer 1

这一错误信息表明,你重新使用<代码>lightgbm>=4.0.0。 rel=nofollow noretinger>microsoft/LGBM#4908。

见lightgbm>=4.0.0, 通行证确认套和lightgbm.early_stopping( callsback,如以下双亲分类例子:

import lightgbm as lgb

from sklearn.datasets import make_blobs
from sklearn.model_selection import train_test_split

X, y = make_blobs(n_samples=10_000, centers=2)

X_train, X_valid, y_train, y_valid = train_test_split(X, y, train_size=0.8)

dtrain = lgb.Dataset(X_train, label=y_train)
dvalid = lgb.Dataset(X_valid, label=y_valid)

model = lgb.train(
    params={
        "objective": "binary",
        "metric": "auc",
    },
    train_set=dtrain,
    valid_sets=[dvalid],
    num_boost_round=10,
    callbacks=[
        lgb.early_stopping(stopping_rounds=3),
    ]
)

修改论点<编码> 停止使用_rounds 至lgb.early_stopping(),从而改变圆数。

友情链接