我在尝试绘制测试误差与训练误差时，遇到了以下代码的问题：

from sklearn.model_selection import GridSearchCVtrees_grid = {"n_estimators":[100,150,200,250,300,350,400,450]}grid_search = GridSearchCV(estimator=xgb,n_jobs=1,param_grid=trees_grid,                       scoring="neg_mean_absolute_error",cv=10,verbose=1,return_train_score=True)results = pd.DataFrame(grid_search.cv_results_)figsize(8,8)plt.style.use("ggplot")plt.plot(results["param_n_estimators"], -1*results["mean_test_score"], label="testing error")plt.plot(results["param_n_estimators"], -1*results["mean_train_score"], label="training error")plt.legend()plt.ylabel("mean absolute error", size=20)plt.xlabel("number of trees", size= 20)plt.show()

我的sklearn版本是0.22.1。我也尝试了grid_search.grid_scores_，但显然不起作用。

回答：

为了获得这个属性，你需要先对GridSearchCV进行拟合：

grid_search.fit(train_data, train_labels)

你可以参考以下示例，这来自于文档（https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html）：

>>> from sklearn import svm, datasets>>> from sklearn.model_selection import GridSearchCV>>> iris = datasets.load_iris()>>> parameters = {'kernel':('linear', 'rbf'), 'C':[1, 10]}>>> svc = svm.SVC()>>> clf = GridSearchCV(svc, parameters)>>> clf.fit(iris.data, iris.target)GridSearchCV(estimator=SVC(),             param_grid={'C': [1, 10], 'kernel': ('linear', 'rbf')})>>> sorted(clf.cv_results_.keys())['mean_fit_time', 'mean_score_time', 'mean_test_score',... 'param_C', 'param_kernel', 'params',... 'rank_test_score', 'split0_test_score',... 'split2_test_score', ... 'std_fit_time', 'std_score_time', 'std_test_score']