我在使用 Kickstarter 项目数据的 CSV 文件测试机器学习方法。虽然我能得到”准确率得分“，但在尝试获取”R2 得分“时却遇到了以下错误。原因是什么呢？

import numpy as npimport pandas as pdfrom sklearn.tree import DecisionTreeRegressorfrom sklearn.metrics import accuracy_scorefrom sklearn.metrics import r2_scoreveri = pd.read_csv("kick_rev.csv")veri = veri.drop(['id'], axis=1)veri = veri.drop(['i'], axis=1)y = np.array(veri['state_num'])x = np.array(veri.drop(['state_num','usd_goal_real','deadline','launched','country'], axis=1))X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.33)DTR = DecisionTreeRegressor()DTR.fit(X_train,y_train)ytahmin = DTR.predict(x)DTR.fit(veri[['goal','pledged','backers','usd_pledged','usd_pledged_real','category_num','category_main_num','currency_num','country_num']],veri.state_num)accuracy_score = DTR.score(X_test,y_test)a = np.array([5000,94175.0,1,57763.8,6469.73,13,6,0,0]).reshape(1, -1)predict_DTR = DTR.predict(a)r2 = DTR.r2_score(X_test, y_test)print(accuracy_score)print(r2)

错误：

AttributeError: 'DecisionTreeRegressor' object has no attribute 'r2_score'

回答：

R2 得分是预测值和实际值之间的比较。因此，您不能使用训练特征和预测值来进行比较

r2_score(y_pred, y_true)

您可以使用以下链接获取更多说明

https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html