0

我很困惑为什么在我实施提前停止时 lightgbm 没有保留最好的模型。

我的代码在这里：

params = {'num_leaves': 31,
          'class_weight' : 'balanced',
 'max_depth': -1,
 'learning_rate': 0.1,
 'n_estimators': 1000,
 'subsample_for_bin': 200000,
 'objective': 'binary',
 'class_weight': 'balanced',
 'min_split_gain': 0.0,
 'min_child_weight': 0.001,
 'min_child_samples': 20,
 'subsample': 1.0,
 'subsample_freq': 0,
 'colsample_bytree': 0.7,
 'reg_alpha': 0.2,
 'reg_lambda': 10.0,
 'random_state': 7,
 'n_jobs': -1,
 'silent': True,
 'importance_type': 'split' }

def f_lgboost(data, params):

    model = lgb.LGBMClassifier(**params)


    X_train = data['X_train']

    y_train = data['y_train']

    X_dev = data['X_dev']

    y_dev = data['y_dev']

    X_test = data['X_test']

    categorical_feature= ['Ticker_code', 'Category_code']

    X_train[categorical_feature] = X_train[categorical_feature].astype('category')

    X_dev[categorical_feature] = X_dev[categorical_feature].astype('category')

    X_test[categorical_feature] = X_test[categorical_feature].astype('category')


    feature_name = X_train.columns.to_list()

    model.fit(X_train, y_train, eval_set = [(X_dev, y_dev)], eval_metric = 'auc', early_stopping_rounds = 20, 
              categorical_feature = categorical_feature, feature_name = feature_name)

    y_pred_train = model.predict_proba(X_train)[:, 1].ravel()

    y_pred_dev = model.predict_proba(X_dev)[:, 1].ravel()

    from sklearn.metrics import roc_auc_score

    auc_train = roc_auc_score(y_train, y_pred_train)

    auc_dev = roc_auc_score(y_dev, y_pred_dev)

    from sklearn.metrics import precision_recall_fscore_support

    precision, recall ,fscore, support = precision_recall_fscore_support(y_dev, (y_pred_dev > 0.5).astype(int), beta=0.5)

    y_pred_test = model.predict_proba(X_test)[:, 1].ravel()

    print(f'auc_train: {auc_train}, auc_dev : {auc_dev}, precision : {precision}, recall: {recall}, fscore : {fscore}')

    Results = {

            'params' : params,

            'data' : data,

            'lg_boost_model' : bst,

            'y_pred_train' : y_pred_train,

            'y_pred_dev' : y_pred_dev,

            'y_pred_test' : y_pred_test,

            'auc_train' : auc_train,

            'auc_dev' : auc_dev,

            'precision_dev': precision,

            'recall_dev' : recall,

            'fscore_dev' : fscore,

            'support_dev' : support


        }


    return Results

在此处输入图像描述

你如何解释这一点，你会给我什么建议？

4

1 回答 1

0

我也对此很好奇。first_metric_only没有帮助我。metric = None我通过在模型参数中指定解决了这个问题

lgb = LGBMClassifier(random_state=42, metric=None)

lgb.fit(
    train_s, target_s.values.ravel(),
    eval_set=[(valid_s, valid_target_s.values.ravel())],
    eval_metric='auc',
    verbose=4,
    early_stopping_rounds=100
    )

然后它真的会在训练期间查看验证 auc。这是关于 github 上的有用线程

于 2020-03-01T11:26:14.603 回答