machine-learning - 如何使用投票回归器来预测特定实例？

Question

我从一些回归器中创建了一个投票回归器，例如

voting_regressor = VotingRegressor(估计器=[('xg',xgbregressor),('gb',gradient_boosting_regressor),('et',extra_trees_regressor),('rf',random_forest_regressor)])
vote_regressor.fit(X_train, y_train)

回归器在测试集上预测良好

y_pred = voting_regressor.predict(X_test)

但是当我尝试预测特定实例时

voting_regressor.predict(X_test.iloc[0].values.reshape(1,-1))

显示以下错误

ValueError: feature_names mismatch: ['yearpublished', 'minplayers', 'maxplayers', 'playingtime', 'minplaytime', 'maxplaytime', 'minage', 'users_rated', 'total_owners', 'total_traders', 'total_wanters', 'total_wishers', 'total_comments', 'total_weights', 'average_weight'] ['f0', 'f1', 'f2', 'f3', 'f4', 'f5', 'f6', 'f7', 'f8', 'f9', 'f10', 'f11', 'f12', 'f13', 'f14'] expected users_rated, total_wishers, yearpublished, maxplayers, maxplaytime, total_owners, total_weights, average_weight, minplaytime, total_wanters, total_traders, playingtime, minage, total_comments, minplayers in input data training data did not have the following fields: f9, f3, f13, f0, f8, f4, f14, f5, f2, f6, f12, f11, f7, f10, f1

Answer 1

当使用iloc时，当错误指示需要列名时，您正在传递pandas.Series而不是pandas.DataFrame。

如果您想返回带有一个示例的数据帧，您可以将其用另一个列表包装，如下所示:

voting_regressor.predict(X_test.iloc[[0]])

这样可以保留列名

您也可以简单地使用[0, 1, 2, 3]来指定许多示例。