python - 为什么我们在 cross_val_score 之前使用 ' - '(负)符号

Question

为什么我们使用' -cross_val_score ' 而不仅仅是 cross_val_score ？

cv_mae = -cross_val_score(lm,
                         x_train,y_train,
                         cv=10,
                         scoring='neg_mean_absolute_error')

Answer 1

这是由于 scikit-learn 中的约定所致:

All scorer objects follow the convention that higher return values are better than lower return values. Thus metrics which measure the distance between the model and the data, like metrics.mean_squared_error, are available as neg_mean_squared_error which return the negated value of the metric.

(引自 here)
由于您的 cross_val_score返回负 MAE(请参阅您将 scoring='neg_mean_absolute_error' 作为参数传递)，您需要负号才能获得实际 MAE。