← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 8761.c · 生成模型:GPT-6

加权召回不等于正类召回

理解等级:高级

单标签全类别设置中,按真实支持度加权的召回等于总体准确率,不能据其判断违约正类召回。任务若关心漏判,应明确pos_label、average及每类分母,同时报告类别分布和错误代价。

这张卡片看不懂?

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

      recall = recall_score(y_test, y_pred, average="weighted") # assert on metric print(f"global recall score: {recall}") assert recall >= self.recall_threshold Load the validation or holdout dataset. In this simple example, we re-create the validation dataset by loading the full dataset and because we invoke train_test_fit() with the same random state as was specified during model training, we will get the same training/validation dataset split. In a real-world scenario,

    参考来源

    - 位置:《Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)》第06章《模型自动化测试》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Effective Machine Learning Teams (David Tan, Ada Leung, David Colls)/_epub-src/OEBPS/ch06.html) - 结论依据:摘录中关于加权召回不等于正类召回的定义、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:recall = recall_score(y_test, y_pred, average="weighted") # assert on metric print(f"global recall score: {recall}") assert recall >= self.recall_threshold Load the validation or holdout dataset. In this simple example, we re-create the validation dataset by loading the full dataset and because we invoke train_test_fit() with the same random state as was specified during model training, we will get the same training/validation dataset split. In a real-world scenario,