知识卡片
曲线下面积与准确率不同
ROC曲线比较不同阈值下TPR与FPR,ROC-AUC反映分数排序能力;PR曲线轴为精确率与召回率,是另一种对象。AUC不是概率误差总和或准确率,0.989不能直接叫98.9%的评论分类正确。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
The receiver operating characteristic (ROC) curve area under the curve (AUC) metric balances all the different ways a classifier can be wrong by computing the integral (area) under the precision versus recall plot (curve) for a classifier. This ensures models that are confidently wrong are penalized more than models that are closer to the truth with their predicted probability values. And the roc_auc_score within this
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第09章《可堆叠的Transformer》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-9.html)
- 结论依据:摘录中关于曲线下面积与准确率不同的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:The receiver operating characteristic (ROC) curve area under the curve (AUC) metric balances all the different ways a classifier can be wrong by computing the integral (area) under the precision versus recall plot (curve) for a classifier. This ensures models that are confidently wrong are penalized more than models that are closer to the truth with their predicted probability values. And the roc_auc_score within this