sklearn.model_selection GridSearchCV is throwing KeyError: 'mean_train_score'

Question

我正在尝试使用 5 折交叉验证从 GridSearchCV 方法中获取 classifierobject.cv_result_ 的平均火车分数，但它在 Google Colab 中给了我 *** KeyError: 'mean_train_score'。但是，对于 sklearn 版本 0.19.1，相同的代码在本地计算机 Ipython 笔记本中运行没问题。谁能帮我如何在 google colab 中获得输出？

clf.cv_results_.keys() 输出如下 -

我的本地笔记本 -

dict_keys(['mean_fit_time', 'std_fit_time', 'mean_score_time', 'std_score_time', 'param_n_neighbors', 'params', 'split0_test_score', 'split1_test_score', 'split2_test_score', 'split3_test_score', 'split4_test_score', 'mean_test_score', 'std_test_score', 'rank_test_score', 'split0_train_score', 'split1_train_score', 'split2_train_score', 'split3_train_score', 'split4_train_score', 'mean_train_score', 'std_train_score'])

在 google colab 笔记本上 -

dict_keys(['mean_fit_time', 'std_fit_time', 'mean_score_time', 'std_score_time', 'param_n_neighbors', 'params', 'split0_test_score', 'split1_test_score', 'split2_test_score', 'split3_test_score', 'split4_test_score', 'mean_test_score', 'std_test_score', 'rank_test_score'])

google colab 中的 mean_train_score 在哪里。我错过了什么吗？

from sklearn.model_selection import GridSearchCV

neigh = KNeighborsClassifier(n_jobs=-1)
parameters = {'n_neighbors':[1, 5, 10, 15, 19 , 21, 31, 41, 51]}
clf = GridSearchCV(neigh, parameters, cv=5,\ 
                   scoring='roc_auc',n_jobs=-1) 
clf.fit(x_train, y_train)
train_auc= clf.cv_results_['mean_train_score']
train_auc_std= clf.cv_results_['std_train_score']
cv_auc = clf.cv_results_['mean_test_score'] 
cv_auc_std= clf.cv_results_['std_test_score']

Answer 1

尝试在 GridSearchCV() 中设置 return_train_score=True 来计算火车分数（默认情况下关闭，请参阅 docs）。也许您在 sklearn 某处本地集有某种全局变量。

sklearn.model_selection GridSearchCV is throwing KeyError: 'mean_train_score'

sklearn.model_selection GridSearchCV is throwing KeyError: 'mean_train_score'

machine-learning

scikit-learn

cross-validation

google-colaboratory

gridsearchcv